pipeline_tag
stringclasses 48
values | library_name
stringclasses 198
values | text
stringlengths 1
900k
| metadata
stringlengths 2
438k
| id
stringlengths 5
122
| last_modified
null | tags
sequencelengths 1
1.84k
| sha
null | created_at
stringlengths 25
25
| arxiv
sequencelengths 0
201
| languages
sequencelengths 0
1.83k
| tags_str
stringlengths 17
9.34k
| text_str
stringlengths 0
389k
| text_lists
sequencelengths 0
722
| processed_texts
sequencelengths 1
723
|
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
text-generation | transformers | # merge
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
## Merge Details
### Merge Method
This model was merged using the SLERP merge method.
### Models Merged
The following models were included in the merge:
* [NousResearch/Hermes-2-Pro-Mistral-7B](https://huggingface.co/NousResearch/Hermes-2-Pro-Mistral-7B)
* [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B)
### Configuration
The following YAML configuration was used to produce this model:
```yaml
models:
- model: meta-llama/Meta-Llama-3-8B
- model: NousResearch/Hermes-2-Pro-Mistral-7B
merge_method: slerp
base_model: meta-llama/Meta-Llama-3-8B
dtype: bfloat16
parameters:
t: [0, 0.5, 1, 0.5, 0] # V shaped curve: Hermes for input & output, WizardMath in the middle layers
```
| {"library_name": "transformers", "tags": ["mergekit", "merge"], "base_model": ["NousResearch/Hermes-2-Pro-Mistral-7B", "meta-llama/Meta-Llama-3-8B"]} | djward888/mergekit-slerp-cnxcquj | null | [
"transformers",
"safetensors",
"llama",
"text-generation",
"mergekit",
"merge",
"base_model:NousResearch/Hermes-2-Pro-Mistral-7B",
"base_model:meta-llama/Meta-Llama-3-8B",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-04-19T16:55:38+00:00 | [] | [] | TAGS
#transformers #safetensors #llama #text-generation #mergekit #merge #base_model-NousResearch/Hermes-2-Pro-Mistral-7B #base_model-meta-llama/Meta-Llama-3-8B #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us
| # merge
This is a merge of pre-trained language models created using mergekit.
## Merge Details
### Merge Method
This model was merged using the SLERP merge method.
### Models Merged
The following models were included in the merge:
* NousResearch/Hermes-2-Pro-Mistral-7B
* meta-llama/Meta-Llama-3-8B
### Configuration
The following YAML configuration was used to produce this model:
| [
"# merge\n\nThis is a merge of pre-trained language models created using mergekit.",
"## Merge Details",
"### Merge Method\n\nThis model was merged using the SLERP merge method.",
"### Models Merged\n\nThe following models were included in the merge:\n* NousResearch/Hermes-2-Pro-Mistral-7B\n* meta-llama/Meta-Llama-3-8B",
"### Configuration\n\nThe following YAML configuration was used to produce this model:"
] | [
"TAGS\n#transformers #safetensors #llama #text-generation #mergekit #merge #base_model-NousResearch/Hermes-2-Pro-Mistral-7B #base_model-meta-llama/Meta-Llama-3-8B #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n",
"# merge\n\nThis is a merge of pre-trained language models created using mergekit.",
"## Merge Details",
"### Merge Method\n\nThis model was merged using the SLERP merge method.",
"### Models Merged\n\nThe following models were included in the merge:\n* NousResearch/Hermes-2-Pro-Mistral-7B\n* meta-llama/Meta-Llama-3-8B",
"### Configuration\n\nThe following YAML configuration was used to produce this model:"
] |
null | transformers | ## About
<!-- ### quantize_version: 1 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: -->
<!-- ### vocab_type: -->
static quants of https://huggingface.co/mayacinka/OkapiLlama-3-dpo
<!-- provided-files -->
weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion.
## Usage
If you are unsure how to use GGUF files, refer to one of [TheBloke's
READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
more details, including on how to concatenate multi-part files.
## Provided Quants
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
| Link | Type | Size/GB | Notes |
|:-----|:-----|--------:|:------|
| [GGUF](https://huggingface.co/mradermacher/OkapiLlama-3-dpo-GGUF/resolve/main/OkapiLlama-3-dpo.Q2_K.gguf) | Q2_K | 3.3 | |
| [GGUF](https://huggingface.co/mradermacher/OkapiLlama-3-dpo-GGUF/resolve/main/OkapiLlama-3-dpo.IQ3_XS.gguf) | IQ3_XS | 3.6 | |
| [GGUF](https://huggingface.co/mradermacher/OkapiLlama-3-dpo-GGUF/resolve/main/OkapiLlama-3-dpo.Q3_K_S.gguf) | Q3_K_S | 3.8 | |
| [GGUF](https://huggingface.co/mradermacher/OkapiLlama-3-dpo-GGUF/resolve/main/OkapiLlama-3-dpo.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/OkapiLlama-3-dpo-GGUF/resolve/main/OkapiLlama-3-dpo.IQ3_M.gguf) | IQ3_M | 3.9 | |
| [GGUF](https://huggingface.co/mradermacher/OkapiLlama-3-dpo-GGUF/resolve/main/OkapiLlama-3-dpo.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/OkapiLlama-3-dpo-GGUF/resolve/main/OkapiLlama-3-dpo.Q3_K_L.gguf) | Q3_K_L | 4.4 | |
| [GGUF](https://huggingface.co/mradermacher/OkapiLlama-3-dpo-GGUF/resolve/main/OkapiLlama-3-dpo.IQ4_XS.gguf) | IQ4_XS | 4.6 | |
| [GGUF](https://huggingface.co/mradermacher/OkapiLlama-3-dpo-GGUF/resolve/main/OkapiLlama-3-dpo.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/OkapiLlama-3-dpo-GGUF/resolve/main/OkapiLlama-3-dpo.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/OkapiLlama-3-dpo-GGUF/resolve/main/OkapiLlama-3-dpo.Q5_K_S.gguf) | Q5_K_S | 5.7 | |
| [GGUF](https://huggingface.co/mradermacher/OkapiLlama-3-dpo-GGUF/resolve/main/OkapiLlama-3-dpo.Q5_K_M.gguf) | Q5_K_M | 5.8 | |
| [GGUF](https://huggingface.co/mradermacher/OkapiLlama-3-dpo-GGUF/resolve/main/OkapiLlama-3-dpo.Q6_K.gguf) | Q6_K | 6.7 | very good quality |
| [GGUF](https://huggingface.co/mradermacher/OkapiLlama-3-dpo-GGUF/resolve/main/OkapiLlama-3-dpo.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality |
Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):
And here are Artefact2's thoughts on the matter:
https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
## FAQ / Model Request
See https://huggingface.co/mradermacher/model_requests for some answers to
questions you might have and/or if you want some other model quantized.
## Thanks
I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
me use its servers and providing upgrades to my workstation to enable
this work in my free time.
<!-- end -->
| {"language": ["en"], "license": "apache-2.0", "library_name": "transformers", "tags": ["text-generation-inference", "transformers", "unsloth", "llama", "trl", "dpo"], "datasets": ["mlabonne/orpo-dpo-mix-40k"], "base_model": "mayacinka/OkapiLlama-3-dpo", "quantized_by": "mradermacher"} | mradermacher/OkapiLlama-3-dpo-GGUF | null | [
"transformers",
"gguf",
"text-generation-inference",
"unsloth",
"llama",
"trl",
"dpo",
"en",
"dataset:mlabonne/orpo-dpo-mix-40k",
"base_model:mayacinka/OkapiLlama-3-dpo",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | 2024-04-19T16:55:53+00:00 | [] | [
"en"
] | TAGS
#transformers #gguf #text-generation-inference #unsloth #llama #trl #dpo #en #dataset-mlabonne/orpo-dpo-mix-40k #base_model-mayacinka/OkapiLlama-3-dpo #license-apache-2.0 #endpoints_compatible #region-us
| About
-----
static quants of URL
weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion.
Usage
-----
If you are unsure how to use GGUF files, refer to one of TheBloke's
READMEs for
more details, including on how to concatenate multi-part files.
Provided Quants
---------------
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):
!URL
And here are Artefact2's thoughts on the matter:
URL
FAQ / Model Request
-------------------
See URL for some answers to
questions you might have and/or if you want some other model quantized.
Thanks
------
I thank my company, nethype GmbH, for letting
me use its servers and providing upgrades to my workstation to enable
this work in my free time.
| [] | [
"TAGS\n#transformers #gguf #text-generation-inference #unsloth #llama #trl #dpo #en #dataset-mlabonne/orpo-dpo-mix-40k #base_model-mayacinka/OkapiLlama-3-dpo #license-apache-2.0 #endpoints_compatible #region-us \n"
] |
null | transformers | ## About
<!-- ### quantize_version: 1 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: -->
<!-- ### vocab_type: -->
static quants of https://huggingface.co/Replete-AI/DevsDoCode-LLama-3-8b-Uncensored
<!-- provided-files -->
weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion.
## Usage
If you are unsure how to use GGUF files, refer to one of [TheBloke's
READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
more details, including on how to concatenate multi-part files.
## Provided Quants
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
| Link | Type | Size/GB | Notes |
|:-----|:-----|--------:|:------|
| [GGUF](https://huggingface.co/mradermacher/DevsDoCode-LLama-3-8b-Uncensored-GGUF/resolve/main/DevsDoCode-LLama-3-8b-Uncensored.Q2_K.gguf) | Q2_K | 3.3 | |
| [GGUF](https://huggingface.co/mradermacher/DevsDoCode-LLama-3-8b-Uncensored-GGUF/resolve/main/DevsDoCode-LLama-3-8b-Uncensored.IQ3_XS.gguf) | IQ3_XS | 3.6 | |
| [GGUF](https://huggingface.co/mradermacher/DevsDoCode-LLama-3-8b-Uncensored-GGUF/resolve/main/DevsDoCode-LLama-3-8b-Uncensored.Q3_K_S.gguf) | Q3_K_S | 3.8 | |
| [GGUF](https://huggingface.co/mradermacher/DevsDoCode-LLama-3-8b-Uncensored-GGUF/resolve/main/DevsDoCode-LLama-3-8b-Uncensored.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/DevsDoCode-LLama-3-8b-Uncensored-GGUF/resolve/main/DevsDoCode-LLama-3-8b-Uncensored.IQ3_M.gguf) | IQ3_M | 3.9 | |
| [GGUF](https://huggingface.co/mradermacher/DevsDoCode-LLama-3-8b-Uncensored-GGUF/resolve/main/DevsDoCode-LLama-3-8b-Uncensored.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/DevsDoCode-LLama-3-8b-Uncensored-GGUF/resolve/main/DevsDoCode-LLama-3-8b-Uncensored.Q3_K_L.gguf) | Q3_K_L | 4.4 | |
| [GGUF](https://huggingface.co/mradermacher/DevsDoCode-LLama-3-8b-Uncensored-GGUF/resolve/main/DevsDoCode-LLama-3-8b-Uncensored.IQ4_XS.gguf) | IQ4_XS | 4.6 | |
| [GGUF](https://huggingface.co/mradermacher/DevsDoCode-LLama-3-8b-Uncensored-GGUF/resolve/main/DevsDoCode-LLama-3-8b-Uncensored.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/DevsDoCode-LLama-3-8b-Uncensored-GGUF/resolve/main/DevsDoCode-LLama-3-8b-Uncensored.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/DevsDoCode-LLama-3-8b-Uncensored-GGUF/resolve/main/DevsDoCode-LLama-3-8b-Uncensored.Q5_K_S.gguf) | Q5_K_S | 5.7 | |
| [GGUF](https://huggingface.co/mradermacher/DevsDoCode-LLama-3-8b-Uncensored-GGUF/resolve/main/DevsDoCode-LLama-3-8b-Uncensored.Q5_K_M.gguf) | Q5_K_M | 5.8 | |
| [GGUF](https://huggingface.co/mradermacher/DevsDoCode-LLama-3-8b-Uncensored-GGUF/resolve/main/DevsDoCode-LLama-3-8b-Uncensored.Q6_K.gguf) | Q6_K | 6.7 | very good quality |
| [GGUF](https://huggingface.co/mradermacher/DevsDoCode-LLama-3-8b-Uncensored-GGUF/resolve/main/DevsDoCode-LLama-3-8b-Uncensored.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality |
Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):
And here are Artefact2's thoughts on the matter:
https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
## FAQ / Model Request
See https://huggingface.co/mradermacher/model_requests for some answers to
questions you might have and/or if you want some other model quantized.
## Thanks
I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
me use its servers and providing upgrades to my workstation to enable
this work in my free time.
<!-- end -->
| {"language": ["en"], "license": "apache-2.0", "library_name": "transformers", "tags": ["uncensored", "transformers", "llama", "llama-3", "unsloth", "llama-factory"], "base_model": "Replete-AI/DevsDoCode-LLama-3-8b-Uncensored", "quantized_by": "mradermacher"} | mradermacher/DevsDoCode-LLama-3-8b-Uncensored-GGUF | null | [
"transformers",
"gguf",
"uncensored",
"llama",
"llama-3",
"unsloth",
"llama-factory",
"en",
"base_model:Replete-AI/DevsDoCode-LLama-3-8b-Uncensored",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | 2024-04-19T16:56:57+00:00 | [] | [
"en"
] | TAGS
#transformers #gguf #uncensored #llama #llama-3 #unsloth #llama-factory #en #base_model-Replete-AI/DevsDoCode-LLama-3-8b-Uncensored #license-apache-2.0 #endpoints_compatible #region-us
| About
-----
static quants of URL
weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion.
Usage
-----
If you are unsure how to use GGUF files, refer to one of TheBloke's
READMEs for
more details, including on how to concatenate multi-part files.
Provided Quants
---------------
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):
!URL
And here are Artefact2's thoughts on the matter:
URL
FAQ / Model Request
-------------------
See URL for some answers to
questions you might have and/or if you want some other model quantized.
Thanks
------
I thank my company, nethype GmbH, for letting
me use its servers and providing upgrades to my workstation to enable
this work in my free time.
| [] | [
"TAGS\n#transformers #gguf #uncensored #llama #llama-3 #unsloth #llama-factory #en #base_model-Replete-AI/DevsDoCode-LLama-3-8b-Uncensored #license-apache-2.0 #endpoints_compatible #region-us \n"
] |
text-generation | transformers |
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] | {"library_name": "transformers", "tags": []} | heyllm234/sc41 | null | [
"transformers",
"safetensors",
"stablelm",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | null | 2024-04-19T16:58:32+00:00 | [
"1910.09700"
] | [] | TAGS
#transformers #safetensors #stablelm #text-generation #conversational #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #region-us
|
# Model Card for Model ID
## Model Details
### Model Description
This is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.
- Developed by:
- Funded by [optional]:
- Shared by [optional]:
- Model type:
- Language(s) (NLP):
- License:
- Finetuned from model [optional]:
### Model Sources [optional]
- Repository:
- Paper [optional]:
- Demo [optional]:
## Uses
### Direct Use
### Downstream Use [optional]
### Out-of-Scope Use
## Bias, Risks, and Limitations
### Recommendations
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
## Training Details
### Training Data
### Training Procedure
#### Preprocessing [optional]
#### Training Hyperparameters
- Training regime:
#### Speeds, Sizes, Times [optional]
## Evaluation
### Testing Data, Factors & Metrics
#### Testing Data
#### Factors
#### Metrics
### Results
#### Summary
## Model Examination [optional]
## Environmental Impact
Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).
- Hardware Type:
- Hours used:
- Cloud Provider:
- Compute Region:
- Carbon Emitted:
## Technical Specifications [optional]
### Model Architecture and Objective
### Compute Infrastructure
#### Hardware
#### Software
[optional]
BibTeX:
APA:
## Glossary [optional]
## More Information [optional]
## Model Card Authors [optional]
## Model Card Contact
| [
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.",
"## How to Get Started with the Model\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] | [
"TAGS\n#transformers #safetensors #stablelm #text-generation #conversational #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #region-us \n",
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.",
"## How to Get Started with the Model\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] |
text-to-image | diffusers |
# AutoTrain SDXL LoRA DreamBooth - iow9/autotrain-iwqdh-4wn3s
<Gallery />
## Model description
These are iow9/autotrain-iwqdh-4wn3s LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0.
The weights were trained using [DreamBooth](https://dreambooth.github.io/).
LoRA for the text encoder was enabled: False.
Special VAE used for training: None.
## Trigger words
You should use RJ Mitte Man to trigger the image generation.
## Download model
Weights for this model are available in Safetensors format.
[Download](iow9/autotrain-iwqdh-4wn3s/tree/main) them in the Files & versions tab.
| {"license": "openrail++", "tags": ["autotrain", "stable-diffusion-xl", "stable-diffusion-xl-diffusers", "text-to-image", "diffusers", "lora", "template:sd-lora"], "base_model": "stabilityai/stable-diffusion-xl-base-1.0", "instance_prompt": "RJ Mitte Man"} | iow9/autotrain-iwqdh-4wn3s | null | [
"diffusers",
"autotrain",
"stable-diffusion-xl",
"stable-diffusion-xl-diffusers",
"text-to-image",
"lora",
"template:sd-lora",
"base_model:stabilityai/stable-diffusion-xl-base-1.0",
"license:openrail++",
"region:us"
] | null | 2024-04-19T16:58:58+00:00 | [] | [] | TAGS
#diffusers #autotrain #stable-diffusion-xl #stable-diffusion-xl-diffusers #text-to-image #lora #template-sd-lora #base_model-stabilityai/stable-diffusion-xl-base-1.0 #license-openrail++ #region-us
|
# AutoTrain SDXL LoRA DreamBooth - iow9/autotrain-iwqdh-4wn3s
<Gallery />
## Model description
These are iow9/autotrain-iwqdh-4wn3s LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0.
The weights were trained using DreamBooth.
LoRA for the text encoder was enabled: False.
Special VAE used for training: None.
## Trigger words
You should use RJ Mitte Man to trigger the image generation.
## Download model
Weights for this model are available in Safetensors format.
Download them in the Files & versions tab.
| [
"# AutoTrain SDXL LoRA DreamBooth - iow9/autotrain-iwqdh-4wn3s\n\n<Gallery />",
"## Model description\n\nThese are iow9/autotrain-iwqdh-4wn3s LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0.\n\nThe weights were trained using DreamBooth.\n\nLoRA for the text encoder was enabled: False.\n\nSpecial VAE used for training: None.",
"## Trigger words\n\nYou should use RJ Mitte Man to trigger the image generation.",
"## Download model\n\nWeights for this model are available in Safetensors format.\n\nDownload them in the Files & versions tab."
] | [
"TAGS\n#diffusers #autotrain #stable-diffusion-xl #stable-diffusion-xl-diffusers #text-to-image #lora #template-sd-lora #base_model-stabilityai/stable-diffusion-xl-base-1.0 #license-openrail++ #region-us \n",
"# AutoTrain SDXL LoRA DreamBooth - iow9/autotrain-iwqdh-4wn3s\n\n<Gallery />",
"## Model description\n\nThese are iow9/autotrain-iwqdh-4wn3s LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0.\n\nThe weights were trained using DreamBooth.\n\nLoRA for the text encoder was enabled: False.\n\nSpecial VAE used for training: None.",
"## Trigger words\n\nYou should use RJ Mitte Man to trigger the image generation.",
"## Download model\n\nWeights for this model are available in Safetensors format.\n\nDownload them in the Files & versions tab."
] |
null | transformers |
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] | {"library_name": "transformers", "tags": []} | hi000000/insta_chai-llama-koen_200 | null | [
"transformers",
"safetensors",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null | 2024-04-19T16:59:59+00:00 | [
"1910.09700"
] | [] | TAGS
#transformers #safetensors #arxiv-1910.09700 #endpoints_compatible #region-us
|
# Model Card for Model ID
## Model Details
### Model Description
This is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.
- Developed by:
- Funded by [optional]:
- Shared by [optional]:
- Model type:
- Language(s) (NLP):
- License:
- Finetuned from model [optional]:
### Model Sources [optional]
- Repository:
- Paper [optional]:
- Demo [optional]:
## Uses
### Direct Use
### Downstream Use [optional]
### Out-of-Scope Use
## Bias, Risks, and Limitations
### Recommendations
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
## Training Details
### Training Data
### Training Procedure
#### Preprocessing [optional]
#### Training Hyperparameters
- Training regime:
#### Speeds, Sizes, Times [optional]
## Evaluation
### Testing Data, Factors & Metrics
#### Testing Data
#### Factors
#### Metrics
### Results
#### Summary
## Model Examination [optional]
## Environmental Impact
Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).
- Hardware Type:
- Hours used:
- Cloud Provider:
- Compute Region:
- Carbon Emitted:
## Technical Specifications [optional]
### Model Architecture and Objective
### Compute Infrastructure
#### Hardware
#### Software
[optional]
BibTeX:
APA:
## Glossary [optional]
## More Information [optional]
## Model Card Authors [optional]
## Model Card Contact
| [
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.",
"## How to Get Started with the Model\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] | [
"TAGS\n#transformers #safetensors #arxiv-1910.09700 #endpoints_compatible #region-us \n",
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.",
"## How to Get Started with the Model\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] |
text-generation | transformers | Hello Nurse 11b quantized at 4.0bpw in EXL2 format. Original model - https://huggingface.co/MarsupialAI/HelloNurse-11b | {} | MarsupialAI/HelloNurse-11b_4.0bpw_exl2 | null | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"4-bit",
"region:us"
] | null | 2024-04-19T17:00:40+00:00 | [] | [] | TAGS
#transformers #safetensors #mistral #text-generation #autotrain_compatible #endpoints_compatible #text-generation-inference #4-bit #region-us
| Hello Nurse 11b quantized at 4.0bpw in EXL2 format. Original model - URL | [] | [
"TAGS\n#transformers #safetensors #mistral #text-generation #autotrain_compatible #endpoints_compatible #text-generation-inference #4-bit #region-us \n"
] |
null | transformers | ## About
<!-- ### quantize_version: 1 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: -->
<!-- ### vocab_type: -->
static quants of https://huggingface.co/royallab/Aetheria-L2-70B
<!-- provided-files -->
weighted/imatrix quants are available at https://huggingface.co/mradermacher/Aetheria-L2-70B-i1-GGUF
## Usage
If you are unsure how to use GGUF files, refer to one of [TheBloke's
READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
more details, including on how to concatenate multi-part files.
## Provided Quants
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
| Link | Type | Size/GB | Notes |
|:-----|:-----|--------:|:------|
| [GGUF](https://huggingface.co/mradermacher/Aetheria-L2-70B-GGUF/resolve/main/Aetheria-L2-70B.Q2_K.gguf) | Q2_K | 25.6 | |
| [GGUF](https://huggingface.co/mradermacher/Aetheria-L2-70B-GGUF/resolve/main/Aetheria-L2-70B.IQ3_XS.gguf) | IQ3_XS | 28.4 | |
| [GGUF](https://huggingface.co/mradermacher/Aetheria-L2-70B-GGUF/resolve/main/Aetheria-L2-70B.IQ3_S.gguf) | IQ3_S | 30.0 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/Aetheria-L2-70B-GGUF/resolve/main/Aetheria-L2-70B.Q3_K_S.gguf) | Q3_K_S | 30.0 | |
| [GGUF](https://huggingface.co/mradermacher/Aetheria-L2-70B-GGUF/resolve/main/Aetheria-L2-70B.IQ3_M.gguf) | IQ3_M | 31.0 | |
| [GGUF](https://huggingface.co/mradermacher/Aetheria-L2-70B-GGUF/resolve/main/Aetheria-L2-70B.Q3_K_M.gguf) | Q3_K_M | 33.4 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/Aetheria-L2-70B-GGUF/resolve/main/Aetheria-L2-70B.Q3_K_L.gguf) | Q3_K_L | 36.2 | |
| [GGUF](https://huggingface.co/mradermacher/Aetheria-L2-70B-GGUF/resolve/main/Aetheria-L2-70B.IQ4_XS.gguf) | IQ4_XS | 37.3 | |
| [GGUF](https://huggingface.co/mradermacher/Aetheria-L2-70B-GGUF/resolve/main/Aetheria-L2-70B.Q4_K_S.gguf) | Q4_K_S | 39.3 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Aetheria-L2-70B-GGUF/resolve/main/Aetheria-L2-70B.Q4_K_M.gguf) | Q4_K_M | 41.5 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Aetheria-L2-70B-GGUF/resolve/main/Aetheria-L2-70B.Q5_K_S.gguf) | Q5_K_S | 47.6 | |
| [GGUF](https://huggingface.co/mradermacher/Aetheria-L2-70B-GGUF/resolve/main/Aetheria-L2-70B.Q5_K_M.gguf) | Q5_K_M | 48.9 | |
| [PART 1](https://huggingface.co/mradermacher/Aetheria-L2-70B-GGUF/resolve/main/Aetheria-L2-70B.Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Aetheria-L2-70B-GGUF/resolve/main/Aetheria-L2-70B.Q6_K.gguf.part2of2) | Q6_K | 56.7 | very good quality |
| [PART 1](https://huggingface.co/mradermacher/Aetheria-L2-70B-GGUF/resolve/main/Aetheria-L2-70B.Q8_0.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Aetheria-L2-70B-GGUF/resolve/main/Aetheria-L2-70B.Q8_0.gguf.part2of2) | Q8_0 | 73.4 | fast, best quality |
Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):
And here are Artefact2's thoughts on the matter:
https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
## FAQ / Model Request
See https://huggingface.co/mradermacher/model_requests for some answers to
questions you might have and/or if you want some other model quantized.
## Thanks
I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
me use its servers and providing upgrades to my workstation to enable
this work in my free time.
<!-- end -->
| {"language": ["en"], "library_name": "transformers", "tags": ["llama", "llama 2"], "base_model": "royallab/Aetheria-L2-70B", "quantized_by": "mradermacher"} | mradermacher/Aetheria-L2-70B-GGUF | null | [
"transformers",
"gguf",
"llama",
"llama 2",
"en",
"base_model:royallab/Aetheria-L2-70B",
"endpoints_compatible",
"region:us"
] | null | 2024-04-19T17:01:01+00:00 | [] | [
"en"
] | TAGS
#transformers #gguf #llama #llama 2 #en #base_model-royallab/Aetheria-L2-70B #endpoints_compatible #region-us
| About
-----
static quants of URL
weighted/imatrix quants are available at URL
Usage
-----
If you are unsure how to use GGUF files, refer to one of TheBloke's
READMEs for
more details, including on how to concatenate multi-part files.
Provided Quants
---------------
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):
!URL
And here are Artefact2's thoughts on the matter:
URL
FAQ / Model Request
-------------------
See URL for some answers to
questions you might have and/or if you want some other model quantized.
Thanks
------
I thank my company, nethype GmbH, for letting
me use its servers and providing upgrades to my workstation to enable
this work in my free time.
| [] | [
"TAGS\n#transformers #gguf #llama #llama 2 #en #base_model-royallab/Aetheria-L2-70B #endpoints_compatible #region-us \n"
] |
null | fastai |
# Amazing!
🥳 Congratulations on hosting your fastai model on the Hugging Face Hub!
# Some next steps
1. Fill out this model card with more information (see the template below and the [documentation here](https://huggingface.co/docs/hub/model-repos))!
2. Create a demo in Gradio or Streamlit using 🤗 Spaces ([documentation here](https://huggingface.co/docs/hub/spaces)).
3. Join the fastai community on the [Fastai Discord](https://discord.com/invite/YKrxeNn)!
Greetings fellow fastlearner 🤝! Don't forget to delete this content from your model card.
---
# Model card
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
| {"tags": ["fastai"]} | ungonzal/deportistas | null | [
"fastai",
"region:us"
] | null | 2024-04-19T17:01:09+00:00 | [] | [] | TAGS
#fastai #region-us
|
# Amazing!
Congratulations on hosting your fastai model on the Hugging Face Hub!
# Some next steps
1. Fill out this model card with more information (see the template below and the documentation here)!
2. Create a demo in Gradio or Streamlit using Spaces (documentation here).
3. Join the fastai community on the Fastai Discord!
Greetings fellow fastlearner ! Don't forget to delete this content from your model card.
---
# Model card
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
| [
"# Amazing!\n\n Congratulations on hosting your fastai model on the Hugging Face Hub!",
"# Some next steps\n1. Fill out this model card with more information (see the template below and the documentation here)!\n\n2. Create a demo in Gradio or Streamlit using Spaces (documentation here).\n\n3. Join the fastai community on the Fastai Discord!\n\nGreetings fellow fastlearner ! Don't forget to delete this content from your model card.\n\n\n---",
"# Model card",
"## Model description\nMore information needed",
"## Intended uses & limitations\nMore information needed",
"## Training and evaluation data\nMore information needed"
] | [
"TAGS\n#fastai #region-us \n",
"# Amazing!\n\n Congratulations on hosting your fastai model on the Hugging Face Hub!",
"# Some next steps\n1. Fill out this model card with more information (see the template below and the documentation here)!\n\n2. Create a demo in Gradio or Streamlit using Spaces (documentation here).\n\n3. Join the fastai community on the Fastai Discord!\n\nGreetings fellow fastlearner ! Don't forget to delete this content from your model card.\n\n\n---",
"# Model card",
"## Model description\nMore information needed",
"## Intended uses & limitations\nMore information needed",
"## Training and evaluation data\nMore information needed"
] |
null | transformers |
# Uploaded model
- **Developed by:** Haxirus
- **License:** apache-2.0
- **Finetuned from model :** unsloth/gemma-2b-it-bnb-4bit
This gemma model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
| {"language": ["en"], "license": "apache-2.0", "tags": ["text-generation-inference", "transformers", "unsloth", "gemma", "trl"], "base_model": "unsloth/gemma-2b-it-bnb-4bit"} | Haxirus/Gemma_2B_Fine-tuned_Adapters | null | [
"transformers",
"safetensors",
"text-generation-inference",
"unsloth",
"gemma",
"trl",
"en",
"base_model:unsloth/gemma-2b-it-bnb-4bit",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | 2024-04-19T17:06:42+00:00 | [] | [
"en"
] | TAGS
#transformers #safetensors #text-generation-inference #unsloth #gemma #trl #en #base_model-unsloth/gemma-2b-it-bnb-4bit #license-apache-2.0 #endpoints_compatible #region-us
|
# Uploaded model
- Developed by: Haxirus
- License: apache-2.0
- Finetuned from model : unsloth/gemma-2b-it-bnb-4bit
This gemma model was trained 2x faster with Unsloth and Huggingface's TRL library.
<img src="URL width="200"/>
| [
"# Uploaded model\n\n- Developed by: Haxirus\n- License: apache-2.0\n- Finetuned from model : unsloth/gemma-2b-it-bnb-4bit\n\nThis gemma model was trained 2x faster with Unsloth and Huggingface's TRL library.\n\n<img src=\"URL width=\"200\"/>"
] | [
"TAGS\n#transformers #safetensors #text-generation-inference #unsloth #gemma #trl #en #base_model-unsloth/gemma-2b-it-bnb-4bit #license-apache-2.0 #endpoints_compatible #region-us \n",
"# Uploaded model\n\n- Developed by: Haxirus\n- License: apache-2.0\n- Finetuned from model : unsloth/gemma-2b-it-bnb-4bit\n\nThis gemma model was trained 2x faster with Unsloth and Huggingface's TRL library.\n\n<img src=\"URL width=\"200\"/>"
] |
text-generation | transformers |
# OpenVINO IR model with int4 quantization of llama-3-8B-Instruct
Model definition for LocalAI:
```
name: llama3
backend: transformers
parameters:
model: fakezeta/llama-3-8b-instruct-ov-int4
context_size: 8192
type: OVModelForCausalLM
template:
use_tokenizer_template: true
stopwords:
- "<|eot_id|>"
- "<|end_of_text|>"
```
## Model Details
Meta developed and released the Meta Llama 3 family of large language models (LLMs), a collection of pretrained and instruction tuned generative text models in 8 and 70B sizes. The Llama 3 instruction tuned models are optimized for dialogue use cases and outperform many of the available open source chat models on common industry benchmarks. Further, in developing these models, we took great care to optimize helpfulness and safety.
**Model developers** Meta
**Variations** Llama 3 comes in two sizes — 8B and 70B parameters — in pre-trained and instruction tuned variants.
**Input** Models input text only.
**Output** Models generate text and code only.
**Model Architecture** Llama 3 is an auto-regressive language model that uses an optimized transformer architecture. The tuned versions use supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF) to align with human preferences for helpfulness and safety.
<table>
<tr>
<td>
</td>
<td><strong>Training Data</strong>
</td>
<td><strong>Params</strong>
</td>
<td><strong>Context length</strong>
</td>
<td><strong>GQA</strong>
</td>
<td><strong>Token count</strong>
</td>
<td><strong>Knowledge cutoff</strong>
</td>
</tr>
<tr>
<td rowspan="2" >Llama 3
</td>
<td rowspan="2" >A new mix of publicly available online data.
</td>
<td>8B
</td>
<td>8k
</td>
<td>Yes
</td>
<td rowspan="2" >15T+
</td>
<td>March, 2023
</td>
</tr>
<tr>
<td>70B
</td>
<td>8k
</td>
<td>Yes
</td>
<td>December, 2023
</td>
</tr>
</table>
**Llama 3 family of models**. Token counts refer to pretraining data only. Both the 8 and 70B versions use Grouped-Query Attention (GQA) for improved inference scalability.
**Model Release Date** April 18, 2024.
**Status** This is a static model trained on an offline dataset. Future versions of the tuned models will be released as we improve model safety with community feedback.
**License** A custom commercial license is available at: [https://llama.meta.com/llama3/license](https://llama.meta.com/llama3/license)
Where to send questions or comments about the model Instructions on how to provide feedback or comments on the model can be found in the model [README](https://github.com/meta-llama/llama3). For more technical information about generation parameters and recipes for how to use Llama 3 in applications, please go [here](https://github.com/meta-llama/llama-recipes).
## Intended Use
**Intended Use Cases** Llama 3 is intended for commercial and research use in English. Instruction tuned models are intended for assistant-like chat, whereas pretrained models can be adapted for a variety of natural language generation tasks.
**Out-of-scope** Use in any manner that violates applicable laws or regulations (including trade compliance laws). Use in any other way that is prohibited by the Acceptable Use Policy and Llama 3 Community License. Use in languages other than English**.
**Note: Developers may fine-tune Llama 3 models for languages beyond English provided they comply with the Llama 3 Community License and the Acceptable Use Policy.
## How to use
This repository contains two versions of Meta-Llama-3-8B, for use with transformers and with the original `llama3` codebase.
### Use with transformers
See the snippet below for usage with Transformers:
```python
>>> import transformers
>>> import torch
>>> model_id = "meta-llama/Meta-Llama-3-8B"
>>> pipeline = transformers.pipeline(
"text-generation", model=model_id, model_kwargs={"torch_dtype": torch.bfloat16}, device_map="auto"
)
>>> pipeline("Hey how are you doing today?")
```
### Use with `llama3`
Please, follow the instructions in the [repository](https://github.com/meta-llama/llama3).
To download Original checkpoints, see the example command below leveraging `huggingface-cli`:
```
huggingface-cli download meta-llama/Meta-Llama-3-8B --include "original/*" --local-dir Meta-Llama-3-8B
```
For Hugging Face support, we recommend using transformers or TGI, but a similar command works.
## Hardware and Software
**Training Factors** We used custom training libraries, Meta's Research SuperCluster, and production clusters for pretraining. Fine-tuning, annotation, and evaluation were also performed on third-party cloud compute.
**Carbon Footprint Pretraining utilized a cumulative** 7.7M GPU hours of computation on hardware of type H100-80GB (TDP of 700W). Estimated total emissions were 2290 tCO2eq, 100% of which were offset by Meta’s sustainability program.
<table>
<tr>
<td>
</td>
<td><strong>Time (GPU hours)</strong>
</td>
<td><strong>Power Consumption (W)</strong>
</td>
<td><strong>Carbon Emitted(tCO2eq)</strong>
</td>
</tr>
<tr>
<td>Llama 3 8B
</td>
<td>1.3M
</td>
<td>700
</td>
<td>390
</td>
</tr>
<tr>
<td>Llama 3 70B
</td>
<td>6.4M
</td>
<td>700
</td>
<td>1900
</td>
</tr>
<tr>
<td>Total
</td>
<td>7.7M
</td>
<td>
</td>
<td>2290
</td>
</tr>
</table>
**CO2 emissions during pre-training**. Time: total GPU time required for training each model. Power Consumption: peak power capacity per GPU device for the GPUs used adjusted for power usage efficiency. 100% of the emissions are directly offset by Meta's sustainability program, and because we are openly releasing these models, the pretraining costs do not need to be incurred by others.
## Training Data
**Overview** Llama 3 was pretrained on over 15 trillion tokens of data from publicly available sources. The fine-tuning data includes publicly available instruction datasets, as well as over 10M human-annotated examples. Neither the pretraining nor the fine-tuning datasets include Meta user data.
**Data Freshness** The pretraining data has a cutoff of March 2023 for the 7B and December 2023 for the 70B models respectively.
## Benchmarks
In this section, we report the results for Llama 3 models on standard automatic benchmarks. For all the evaluations, we use our internal evaluations library. For details on the methodology see [here](https://github.com/meta-llama/llama3/blob/main/eval_methodology.md).
### Base pretrained models
<table>
<tr>
<td><strong>Category</strong>
</td>
<td><strong>Benchmark</strong>
</td>
<td><strong>Llama 3 8B</strong>
</td>
<td><strong>Llama2 7B</strong>
</td>
<td><strong>Llama2 13B</strong>
</td>
<td><strong>Llama 3 70B</strong>
</td>
<td><strong>Llama2 70B</strong>
</td>
</tr>
<tr>
<td rowspan="6" >General
</td>
<td>MMLU (5-shot)
</td>
<td>66.6
</td>
<td>45.7
</td>
<td>53.8
</td>
<td>79.5
</td>
<td>69.7
</td>
</tr>
<tr>
<td>AGIEval English (3-5 shot)
</td>
<td>45.9
</td>
<td>28.8
</td>
<td>38.7
</td>
<td>63.0
</td>
<td>54.8
</td>
</tr>
<tr>
<td>CommonSenseQA (7-shot)
</td>
<td>72.6
</td>
<td>57.6
</td>
<td>67.6
</td>
<td>83.8
</td>
<td>78.7
</td>
</tr>
<tr>
<td>Winogrande (5-shot)
</td>
<td>76.1
</td>
<td>73.3
</td>
<td>75.4
</td>
<td>83.1
</td>
<td>81.8
</td>
</tr>
<tr>
<td>BIG-Bench Hard (3-shot, CoT)
</td>
<td>61.1
</td>
<td>38.1
</td>
<td>47.0
</td>
<td>81.3
</td>
<td>65.7
</td>
</tr>
<tr>
<td>ARC-Challenge (25-shot)
</td>
<td>78.6
</td>
<td>53.7
</td>
<td>67.6
</td>
<td>93.0
</td>
<td>85.3
</td>
</tr>
<tr>
<td>Knowledge reasoning
</td>
<td>TriviaQA-Wiki (5-shot)
</td>
<td>78.5
</td>
<td>72.1
</td>
<td>79.6
</td>
<td>89.7
</td>
<td>87.5
</td>
</tr>
<tr>
<td rowspan="4" >Reading comprehension
</td>
<td>SQuAD (1-shot)
</td>
<td>76.4
</td>
<td>72.2
</td>
<td>72.1
</td>
<td>85.6
</td>
<td>82.6
</td>
</tr>
<tr>
<td>QuAC (1-shot, F1)
</td>
<td>44.4
</td>
<td>39.6
</td>
<td>44.9
</td>
<td>51.1
</td>
<td>49.4
</td>
</tr>
<tr>
<td>BoolQ (0-shot)
</td>
<td>75.7
</td>
<td>65.5
</td>
<td>66.9
</td>
<td>79.0
</td>
<td>73.1
</td>
</tr>
<tr>
<td>DROP (3-shot, F1)
</td>
<td>58.4
</td>
<td>37.9
</td>
<td>49.8
</td>
<td>79.7
</td>
<td>70.2
</td>
</tr>
</table>
### Instruction tuned models
<table>
<tr>
<td><strong>Benchmark</strong>
</td>
<td><strong>Llama 3 8B</strong>
</td>
<td><strong>Llama 2 7B</strong>
</td>
<td><strong>Llama 2 13B</strong>
</td>
<td><strong>Llama 3 70B</strong>
</td>
<td><strong>Llama 2 70B</strong>
</td>
</tr>
<tr>
<td>MMLU (5-shot)
</td>
<td>68.4
</td>
<td>34.1
</td>
<td>47.8
</td>
<td>82.0
</td>
<td>52.9
</td>
</tr>
<tr>
<td>GPQA (0-shot)
</td>
<td>34.2
</td>
<td>21.7
</td>
<td>22.3
</td>
<td>39.5
</td>
<td>21.0
</td>
</tr>
<tr>
<td>HumanEval (0-shot)
</td>
<td>62.2
</td>
<td>7.9
</td>
<td>14.0
</td>
<td>81.7
</td>
<td>25.6
</td>
</tr>
<tr>
<td>GSM-8K (8-shot, CoT)
</td>
<td>79.6
</td>
<td>25.7
</td>
<td>77.4
</td>
<td>93.0
</td>
<td>57.5
</td>
</tr>
<tr>
<td>MATH (4-shot, CoT)
</td>
<td>30.0
</td>
<td>3.8
</td>
<td>6.7
</td>
<td>50.4
</td>
<td>11.6
</td>
</tr>
</table>
### Responsibility & Safety
We believe that an open approach to AI leads to better, safer products, faster innovation, and a bigger overall market. We are committed to Responsible AI development and took a series of steps to limit misuse and harm and support the open source community.
Foundation models are widely capable technologies that are built to be used for a diverse range of applications. They are not designed to meet every developer preference on safety levels for all use cases, out-of-the-box, as those by their nature will differ across different applications.
Rather, responsible LLM-application deployment is achieved by implementing a series of safety best practices throughout the development of such applications, from the model pre-training, fine-tuning and the deployment of systems composed of safeguards to tailor the safety needs specifically to the use case and audience.
As part of the Llama 3 release, we updated our [Responsible Use Guide](https://llama.meta.com/responsible-use-guide/) to outline the steps and best practices for developers to implement model and system level safety for their application. We also provide a set of resources including [Meta Llama Guard 2](https://llama.meta.com/purple-llama/) and [Code Shield](https://llama.meta.com/purple-llama/) safeguards. These tools have proven to drastically reduce residual risks of LLM Systems, while maintaining a high level of helpfulness. We encourage developers to tune and deploy these safeguards according to their needs and we provide a [reference implementation](https://github.com/meta-llama/llama-recipes/tree/main/recipes/responsible_ai) to get you started.
#### Llama 3-Instruct
As outlined in the Responsible Use Guide, some trade-off between model helpfulness and model alignment is likely unavoidable. Developers should exercise discretion about how to weigh the benefits of alignment and helpfulness for their specific use case and audience. Developers should be mindful of residual risks when using Llama models and leverage additional safety tools as needed to reach the right safety bar for their use case.
<span style="text-decoration:underline;">Safety</span>
For our instruction tuned model, we conducted extensive red teaming exercises, performed adversarial evaluations and implemented safety mitigations techniques to lower residual risks. As with any Large Language Model, residual risks will likely remain and we recommend that developers assess these risks in the context of their use case. In parallel, we are working with the community to make AI safety benchmark standards transparent, rigorous and interpretable.
<span style="text-decoration:underline;">Refusals</span>
In addition to residual risks, we put a great emphasis on model refusals to benign prompts. Over-refusing not only can impact the user experience but could even be harmful in certain contexts as well. We’ve heard the feedback from the developer community and improved our fine tuning to ensure that Llama 3 is significantly less likely to falsely refuse to answer prompts than Llama 2.
We built internal benchmarks and developed mitigations to limit false refusals making Llama 3 our most helpful model to date.
#### Responsible release
In addition to responsible use considerations outlined above, we followed a rigorous process that requires us to take extra measures against misuse and critical risks before we make our release decision.
Misuse
If you access or use Llama 3, you agree to the Acceptable Use Policy. The most recent copy of this policy can be found at [https://llama.meta.com/llama3/use-policy/](https://llama.meta.com/llama3/use-policy/).
#### Critical risks
<span style="text-decoration:underline;">CBRNE</span> (Chemical, Biological, Radiological, Nuclear, and high yield Explosives)
We have conducted a two fold assessment of the safety of the model in this area:
* Iterative testing during model training to assess the safety of responses related to CBRNE threats and other adversarial risks.
* Involving external CBRNE experts to conduct an uplift test assessing the ability of the model to accurately provide expert knowledge and reduce barriers to potential CBRNE misuse, by reference to what can be achieved using web search (without the model).
### <span style="text-decoration:underline;">Cyber Security </span>
We have evaluated Llama 3 with CyberSecEval, Meta’s cybersecurity safety eval suite, measuring Llama 3’s propensity to suggest insecure code when used as a coding assistant, and Llama 3’s propensity to comply with requests to help carry out cyber attacks, where attacks are defined by the industry standard MITRE ATT&CK cyber attack ontology. On our insecure coding and cyber attacker helpfulness tests, Llama 3 behaved in the same range or safer than models of [equivalent coding capability](https://huggingface.co/spaces/facebook/CyberSecEval).
### <span style="text-decoration:underline;">Child Safety</span>
Child Safety risk assessments were conducted using a team of experts, to assess the model’s capability to produce outputs that could result in Child Safety risks and inform on any necessary and appropriate risk mitigations via fine tuning. We leveraged those expert red teaming sessions to expand the coverage of our evaluation benchmarks through Llama 3 model development. For Llama 3, we conducted new in-depth sessions using objective based methodologies to assess the model risks along multiple attack vectors. We also partnered with content specialists to perform red teaming exercises assessing potentially violating content while taking account of market specific nuances or experiences.
### Community
Generative AI safety requires expertise and tooling, and we believe in the strength of the open community to accelerate its progress. We are active members of open consortiums, including the AI Alliance, Partnership in AI and MLCommons, actively contributing to safety standardization and transparency. We encourage the community to adopt taxonomies like the MLCommons Proof of Concept evaluation to facilitate collaboration and transparency on safety and content evaluations. Our Purple Llama tools are open sourced for the community to use and widely distributed across ecosystem partners including cloud service providers. We encourage community contributions to our [Github repository](https://github.com/meta-llama/PurpleLlama).
Finally, we put in place a set of resources including an [output reporting mechanism](https://developers.facebook.com/llama_output_feedback) and [bug bounty program](https://www.facebook.com/whitehat) to continuously improve the Llama technology with the help of the community.
## Ethical Considerations and Limitations
The core values of Llama 3 are openness, inclusivity and helpfulness. It is meant to serve everyone, and to work for a wide range of use cases. It is thus designed to be accessible to people across many different backgrounds, experiences and perspectives. Llama 3 addresses users and their needs as they are, without insertion unnecessary judgment or normativity, while reflecting the understanding that even content that may appear problematic in some cases can serve valuable purposes in others. It respects the dignity and autonomy of all users, especially in terms of the values of free thought and expression that power innovation and progress.
But Llama 3 is a new technology, and like any new technology, there are risks associated with its use. Testing conducted to date has been in English, and has not covered, nor could it cover, all scenarios. For these reasons, as with all LLMs, Llama 3’s potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate, biased or other objectionable responses to user prompts. Therefore, before deploying any applications of Llama 3 models, developers should perform safety testing and tuning tailored to their specific applications of the model. As outlined in the Responsible Use Guide, we recommend incorporating [Purple Llama](https://github.com/facebookresearch/PurpleLlama) solutions into your workflows and specifically [Llama Guard](https://ai.meta.com/research/publications/llama-guard-llm-based-input-output-safeguard-for-human-ai-conversations/) which provides a base model to filter input and output prompts to layer system-level safety on top of model-level safety.
Please see the Responsible Use Guide available at [http://llama.meta.com/responsible-use-guide](http://llama.meta.com/responsible-use-guide)
## Citation instructions
@article{llama3modelcard,
title={Llama 3 Model Card},
author={AI@Meta},
year={2024},
url = {https://github.com/meta-llama/llama3/blob/main/MODEL_CARD.md}
}
## Contributors
Aaditya Singh; Aaron Grattafiori; Abhimanyu Dubey; Abhinav Jauhri; Abhinav Pandey; Abhishek Kadian; Adam Kelsey; Adi Gangidi; Ahmad Al-Dahle; Ahuva Goldstand; Aiesha Letman; Ajay Menon; Akhil Mathur; Alan Schelten; Alex Vaughan; Amy Yang; Andrei Lupu; Andres Alvarado; Andrew Gallagher; Andrew Gu; Andrew Ho; Andrew Poulton; Andrew Ryan; Angela Fan; Ankit Ramchandani; Anthony Hartshorn; Archi Mitra; Archie Sravankumar; Artem Korenev; Arun Rao; Ashley Gabriel; Ashwin Bharambe; Assaf Eisenman; Aston Zhang; Aurelien Rodriguez; Austen Gregerson; Ava Spataru; Baptiste Roziere; Ben Maurer; Benjamin Leonhardi; Bernie Huang; Bhargavi Paranjape; Bing Liu; Binh Tang; Bobbie Chern; Brani Stojkovic; Brian Fuller; Catalina Mejia Arenas; Chao Zhou; Charlotte Caucheteux; Chaya Nayak; Ching-Hsiang Chu; Chloe Bi; Chris Cai; Chris Cox; Chris Marra; Chris McConnell; Christian Keller; Christoph Feichtenhofer; Christophe Touret; Chunyang Wu; Corinne Wong; Cristian Canton Ferrer; Damien Allonsius; Daniel Kreymer; Daniel Haziza; Daniel Li; Danielle Pintz; Danny Livshits; Danny Wyatt; David Adkins; David Esiobu; David Xu; Davide Testuggine; Delia David; Devi Parikh; Dhruv Choudhary; Dhruv Mahajan; Diana Liskovich; Diego Garcia-Olano; Diego Perino; Dieuwke Hupkes; Dingkang Wang; Dustin Holland; Egor Lakomkin; Elina Lobanova; Xiaoqing Ellen Tan; Emily Dinan; Eric Smith; Erik Brinkman; Esteban Arcaute; Filip Radenovic; Firat Ozgenel; Francesco Caggioni; Frank Seide; Frank Zhang; Gabriel Synnaeve; Gabriella Schwarz; Gabrielle Lee; Gada Badeer; Georgia Anderson; Graeme Nail; Gregoire Mialon; Guan Pang; Guillem Cucurell; Hailey Nguyen; Hannah Korevaar; Hannah Wang; Haroun Habeeb; Harrison Rudolph; Henry Aspegren; Hu Xu; Hugo Touvron; Iga Kozlowska; Igor Molybog; Igor Tufanov; Iliyan Zarov; Imanol Arrieta Ibarra; Irina-Elena Veliche; Isabel Kloumann; Ishan Misra; Ivan Evtimov; Jacob Xu; Jade Copet; Jake Weissman; Jan Geffert; Jana Vranes; Japhet Asher; Jason Park; Jay Mahadeokar; Jean-Baptiste Gaya; Jeet Shah; Jelmer van der Linde; Jennifer Chan; Jenny Hong; Jenya Lee; Jeremy Fu; Jeremy Teboul; Jianfeng Chi; Jianyu Huang; Jie Wang; Jiecao Yu; Joanna Bitton; Joe Spisak; Joelle Pineau; Jon Carvill; Jongsoo Park; Joseph Rocca; Joshua Johnstun; Junteng Jia; Kalyan Vasuden Alwala; Kam Hou U; Kate Plawiak; Kartikeya Upasani; Kaushik Veeraraghavan; Ke Li; Kenneth Heafield; Kevin Stone; Khalid El-Arini; Krithika Iyer; Kshitiz Malik; Kuenley Chiu; Kunal Bhalla; Kyle Huang; Lakshya Garg; Lauren Rantala-Yeary; Laurens van der Maaten; Lawrence Chen; Leandro Silva; Lee Bell; Lei Zhang; Liang Tan; Louis Martin; Lovish Madaan; Luca Wehrstedt; Lukas Blecher; Luke de Oliveira; Madeline Muzzi; Madian Khabsa; Manav Avlani; Mannat Singh; Manohar Paluri; Mark Zuckerberg; Marcin Kardas; Martynas Mankus; Mathew Oldham; Mathieu Rita; Matthew Lennie; Maya Pavlova; Meghan Keneally; Melanie Kambadur; Mihir Patel; Mikayel Samvelyan; Mike Clark; Mike Lewis; Min Si; Mitesh Kumar Singh; Mo Metanat; Mona Hassan; Naman Goyal; Narjes Torabi; Nicolas Usunier; Nikolay Bashlykov; Nikolay Bogoychev; Niladri Chatterji; Ning Dong; Oliver Aobo Yang; Olivier Duchenne; Onur Celebi; Parth Parekh; Patrick Alrassy; Paul Saab; Pavan Balaji; Pedro Rittner; Pengchuan Zhang; Pengwei Li; Petar Vasic; Peter Weng; Polina Zvyagina; Prajjwal Bhargava; Pratik Dubal; Praveen Krishnan; Punit Singh Koura; Qing He; Rachel Rodriguez; Ragavan Srinivasan; Rahul Mitra; Ramon Calderer; Raymond Li; Robert Stojnic; Roberta Raileanu; Robin Battey; Rocky Wang; Rohit Girdhar; Rohit Patel; Romain Sauvestre; Ronnie Polidoro; Roshan Sumbaly; Ross Taylor; Ruan Silva; Rui Hou; Rui Wang; Russ Howes; Ruty Rinott; Saghar Hosseini; Sai Jayesh Bondu; Samyak Datta; Sanjay Singh; Sara Chugh; Sargun Dhillon; Satadru Pan; Sean Bell; Sergey Edunov; Shaoliang Nie; Sharan Narang; Sharath Raparthy; Shaun Lindsay; Sheng Feng; Sheng Shen; Shenghao Lin; Shiva Shankar; Shruti Bhosale; Shun Zhang; Simon Vandenhende; Sinong Wang; Seohyun Sonia Kim; Soumya Batra; Sten Sootla; Steve Kehoe; Suchin Gururangan; Sumit Gupta; Sunny Virk; Sydney Borodinsky; Tamar Glaser; Tamar Herman; Tamara Best; Tara Fowler; Thomas Georgiou; Thomas Scialom; Tianhe Li; Todor Mihaylov; Tong Xiao; Ujjwal Karn; Vedanuj Goswami; Vibhor Gupta; Vignesh Ramanathan; Viktor Kerkez; Vinay Satish Kumar; Vincent Gonguet; Vish Vogeti; Vlad Poenaru; Vlad Tiberiu Mihailescu; Vladan Petrovic; Vladimir Ivanov; Wei Li; Weiwei Chu; Wenhan Xiong; Wenyin Fu; Wes Bouaziz; Whitney Meers; Will Constable; Xavier Martinet; Xiaojian Wu; Xinbo Gao; Xinfeng Xie; Xuchao Jia; Yaelle Goldschlag; Yann LeCun; Yashesh Gaur; Yasmine Babaei; Ye Qi; Yenda Li; Yi Wen; Yiwen Song; Youngjin Nam; Yuchen Hao; Yuchen Zhang; Yun Wang; Yuning Mao; Yuzi He; Zacharie Delpierre Coudert; Zachary DeVito; Zahra Hankir; Zhaoduo Wen; Zheng Yan; Zhengxing Chen; Zhenyu Yang; Zoe Papakipos | {"language": ["en"], "license": "other", "tags": ["facebook", "meta", "pytorch", "llama", "llama-3"], "pipeline_tag": "text-generation", "license_name": "llama3", "license_link": "https://huggingface.co/meta-llama/Meta-Llama-3-8B/blob/main/LICENSE"} | fakezeta/llama-3-8b-instruct-ov-int4 | null | [
"transformers",
"openvino",
"llama",
"text-generation",
"facebook",
"meta",
"pytorch",
"llama-3",
"en",
"license:other",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-04-19T17:08:32+00:00 | [] | [
"en"
] | TAGS
#transformers #openvino #llama #text-generation #facebook #meta #pytorch #llama-3 #en #license-other #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us
| OpenVINO IR model with int4 quantization of llama-3-8B-Instruct
===============================================================
Model definition for LocalAI:
Model Details
-------------
Meta developed and released the Meta Llama 3 family of large language models (LLMs), a collection of pretrained and instruction tuned generative text models in 8 and 70B sizes. The Llama 3 instruction tuned models are optimized for dialogue use cases and outperform many of the available open source chat models on common industry benchmarks. Further, in developing these models, we took great care to optimize helpfulness and safety.
Model developers Meta
Variations Llama 3 comes in two sizes — 8B and 70B parameters — in pre-trained and instruction tuned variants.
Input Models input text only.
Output Models generate text and code only.
Model Architecture Llama 3 is an auto-regressive language model that uses an optimized transformer architecture. The tuned versions use supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF) to align with human preferences for helpfulness and safety.
Llama 3 family of models. Token counts refer to pretraining data only. Both the 8 and 70B versions use Grouped-Query Attention (GQA) for improved inference scalability.
Model Release Date April 18, 2024.
Status This is a static model trained on an offline dataset. Future versions of the tuned models will be released as we improve model safety with community feedback.
License A custom commercial license is available at: URL
Where to send questions or comments about the model Instructions on how to provide feedback or comments on the model can be found in the model README. For more technical information about generation parameters and recipes for how to use Llama 3 in applications, please go here.
Intended Use
------------
Intended Use Cases Llama 3 is intended for commercial and research use in English. Instruction tuned models are intended for assistant-like chat, whereas pretrained models can be adapted for a variety of natural language generation tasks.
Out-of-scope Use in any manner that violates applicable laws or regulations (including trade compliance laws). Use in any other way that is prohibited by the Acceptable Use Policy and Llama 3 Community License. Use in languages other than English.
Note: Developers may fine-tune Llama 3 models for languages beyond English provided they comply with the Llama 3 Community License and the Acceptable Use Policy.
How to use
----------
This repository contains two versions of Meta-Llama-3-8B, for use with transformers and with the original 'llama3' codebase.
### Use with transformers
See the snippet below for usage with Transformers:
### Use with 'llama3'
Please, follow the instructions in the repository.
To download Original checkpoints, see the example command below leveraging 'huggingface-cli':
For Hugging Face support, we recommend using transformers or TGI, but a similar command works.
Hardware and Software
---------------------
Training Factors We used custom training libraries, Meta's Research SuperCluster, and production clusters for pretraining. Fine-tuning, annotation, and evaluation were also performed on third-party cloud compute.
Carbon Footprint Pretraining utilized a cumulative 7.7M GPU hours of computation on hardware of type H100-80GB (TDP of 700W). Estimated total emissions were 2290 tCO2eq, 100% of which were offset by Meta’s sustainability program.
CO2 emissions during pre-training. Time: total GPU time required for training each model. Power Consumption: peak power capacity per GPU device for the GPUs used adjusted for power usage efficiency. 100% of the emissions are directly offset by Meta's sustainability program, and because we are openly releasing these models, the pretraining costs do not need to be incurred by others.
Training Data
-------------
Overview Llama 3 was pretrained on over 15 trillion tokens of data from publicly available sources. The fine-tuning data includes publicly available instruction datasets, as well as over 10M human-annotated examples. Neither the pretraining nor the fine-tuning datasets include Meta user data.
Data Freshness The pretraining data has a cutoff of March 2023 for the 7B and December 2023 for the 70B models respectively.
Benchmarks
----------
In this section, we report the results for Llama 3 models on standard automatic benchmarks. For all the evaluations, we use our internal evaluations library. For details on the methodology see here.
### Base pretrained models
### Instruction tuned models
### Responsibility & Safety
We believe that an open approach to AI leads to better, safer products, faster innovation, and a bigger overall market. We are committed to Responsible AI development and took a series of steps to limit misuse and harm and support the open source community.
Foundation models are widely capable technologies that are built to be used for a diverse range of applications. They are not designed to meet every developer preference on safety levels for all use cases, out-of-the-box, as those by their nature will differ across different applications.
Rather, responsible LLM-application deployment is achieved by implementing a series of safety best practices throughout the development of such applications, from the model pre-training, fine-tuning and the deployment of systems composed of safeguards to tailor the safety needs specifically to the use case and audience.
As part of the Llama 3 release, we updated our Responsible Use Guide to outline the steps and best practices for developers to implement model and system level safety for their application. We also provide a set of resources including Meta Llama Guard 2 and Code Shield safeguards. These tools have proven to drastically reduce residual risks of LLM Systems, while maintaining a high level of helpfulness. We encourage developers to tune and deploy these safeguards according to their needs and we provide a reference implementation to get you started.
#### Llama 3-Instruct
As outlined in the Responsible Use Guide, some trade-off between model helpfulness and model alignment is likely unavoidable. Developers should exercise discretion about how to weigh the benefits of alignment and helpfulness for their specific use case and audience. Developers should be mindful of residual risks when using Llama models and leverage additional safety tools as needed to reach the right safety bar for their use case.
Safety
For our instruction tuned model, we conducted extensive red teaming exercises, performed adversarial evaluations and implemented safety mitigations techniques to lower residual risks. As with any Large Language Model, residual risks will likely remain and we recommend that developers assess these risks in the context of their use case. In parallel, we are working with the community to make AI safety benchmark standards transparent, rigorous and interpretable.
Refusals
In addition to residual risks, we put a great emphasis on model refusals to benign prompts. Over-refusing not only can impact the user experience but could even be harmful in certain contexts as well. We’ve heard the feedback from the developer community and improved our fine tuning to ensure that Llama 3 is significantly less likely to falsely refuse to answer prompts than Llama 2.
We built internal benchmarks and developed mitigations to limit false refusals making Llama 3 our most helpful model to date.
#### Responsible release
In addition to responsible use considerations outlined above, we followed a rigorous process that requires us to take extra measures against misuse and critical risks before we make our release decision.
Misuse
If you access or use Llama 3, you agree to the Acceptable Use Policy. The most recent copy of this policy can be found at URL
#### Critical risks
CBRNE (Chemical, Biological, Radiological, Nuclear, and high yield Explosives)
We have conducted a two fold assessment of the safety of the model in this area:
* Iterative testing during model training to assess the safety of responses related to CBRNE threats and other adversarial risks.
* Involving external CBRNE experts to conduct an uplift test assessing the ability of the model to accurately provide expert knowledge and reduce barriers to potential CBRNE misuse, by reference to what can be achieved using web search (without the model).
### Cyber Security
We have evaluated Llama 3 with CyberSecEval, Meta’s cybersecurity safety eval suite, measuring Llama 3’s propensity to suggest insecure code when used as a coding assistant, and Llama 3’s propensity to comply with requests to help carry out cyber attacks, where attacks are defined by the industry standard MITRE ATT&CK cyber attack ontology. On our insecure coding and cyber attacker helpfulness tests, Llama 3 behaved in the same range or safer than models of equivalent coding capability.
### Child Safety
Child Safety risk assessments were conducted using a team of experts, to assess the model’s capability to produce outputs that could result in Child Safety risks and inform on any necessary and appropriate risk mitigations via fine tuning. We leveraged those expert red teaming sessions to expand the coverage of our evaluation benchmarks through Llama 3 model development. For Llama 3, we conducted new in-depth sessions using objective based methodologies to assess the model risks along multiple attack vectors. We also partnered with content specialists to perform red teaming exercises assessing potentially violating content while taking account of market specific nuances or experiences.
### Community
Generative AI safety requires expertise and tooling, and we believe in the strength of the open community to accelerate its progress. We are active members of open consortiums, including the AI Alliance, Partnership in AI and MLCommons, actively contributing to safety standardization and transparency. We encourage the community to adopt taxonomies like the MLCommons Proof of Concept evaluation to facilitate collaboration and transparency on safety and content evaluations. Our Purple Llama tools are open sourced for the community to use and widely distributed across ecosystem partners including cloud service providers. We encourage community contributions to our Github repository.
Finally, we put in place a set of resources including an output reporting mechanism and bug bounty program to continuously improve the Llama technology with the help of the community.
Ethical Considerations and Limitations
--------------------------------------
The core values of Llama 3 are openness, inclusivity and helpfulness. It is meant to serve everyone, and to work for a wide range of use cases. It is thus designed to be accessible to people across many different backgrounds, experiences and perspectives. Llama 3 addresses users and their needs as they are, without insertion unnecessary judgment or normativity, while reflecting the understanding that even content that may appear problematic in some cases can serve valuable purposes in others. It respects the dignity and autonomy of all users, especially in terms of the values of free thought and expression that power innovation and progress.
But Llama 3 is a new technology, and like any new technology, there are risks associated with its use. Testing conducted to date has been in English, and has not covered, nor could it cover, all scenarios. For these reasons, as with all LLMs, Llama 3’s potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate, biased or other objectionable responses to user prompts. Therefore, before deploying any applications of Llama 3 models, developers should perform safety testing and tuning tailored to their specific applications of the model. As outlined in the Responsible Use Guide, we recommend incorporating Purple Llama solutions into your workflows and specifically Llama Guard which provides a base model to filter input and output prompts to layer system-level safety on top of model-level safety.
Please see the Responsible Use Guide available at URL
instructions
@article{llama3modelcard,
title={Llama 3 Model Card},
author={AI@Meta},
year={2024},
url = {URL
}
Contributors
------------
Aaditya Singh; Aaron Grattafiori; Abhimanyu Dubey; Abhinav Jauhri; Abhinav Pandey; Abhishek Kadian; Adam Kelsey; Adi Gangidi; Ahmad Al-Dahle; Ahuva Goldstand; Aiesha Letman; Ajay Menon; Akhil Mathur; Alan Schelten; Alex Vaughan; Amy Yang; Andrei Lupu; Andres Alvarado; Andrew Gallagher; Andrew Gu; Andrew Ho; Andrew Poulton; Andrew Ryan; Angela Fan; Ankit Ramchandani; Anthony Hartshorn; Archi Mitra; Archie Sravankumar; Artem Korenev; Arun Rao; Ashley Gabriel; Ashwin Bharambe; Assaf Eisenman; Aston Zhang; Aurelien Rodriguez; Austen Gregerson; Ava Spataru; Baptiste Roziere; Ben Maurer; Benjamin Leonhardi; Bernie Huang; Bhargavi Paranjape; Bing Liu; Binh Tang; Bobbie Chern; Brani Stojkovic; Brian Fuller; Catalina Mejia Arenas; Chao Zhou; Charlotte Caucheteux; Chaya Nayak; Ching-Hsiang Chu; Chloe Bi; Chris Cai; Chris Cox; Chris Marra; Chris McConnell; Christian Keller; Christoph Feichtenhofer; Christophe Touret; Chunyang Wu; Corinne Wong; Cristian Canton Ferrer; Damien Allonsius; Daniel Kreymer; Daniel Haziza; Daniel Li; Danielle Pintz; Danny Livshits; Danny Wyatt; David Adkins; David Esiobu; David Xu; Davide Testuggine; Delia David; Devi Parikh; Dhruv Choudhary; Dhruv Mahajan; Diana Liskovich; Diego Garcia-Olano; Diego Perino; Dieuwke Hupkes; Dingkang Wang; Dustin Holland; Egor Lakomkin; Elina Lobanova; Xiaoqing Ellen Tan; Emily Dinan; Eric Smith; Erik Brinkman; Esteban Arcaute; Filip Radenovic; Firat Ozgenel; Francesco Caggioni; Frank Seide; Frank Zhang; Gabriel Synnaeve; Gabriella Schwarz; Gabrielle Lee; Gada Badeer; Georgia Anderson; Graeme Nail; Gregoire Mialon; Guan Pang; Guillem Cucurell; Hailey Nguyen; Hannah Korevaar; Hannah Wang; Haroun Habeeb; Harrison Rudolph; Henry Aspegren; Hu Xu; Hugo Touvron; Iga Kozlowska; Igor Molybog; Igor Tufanov; Iliyan Zarov; Imanol Arrieta Ibarra; Irina-Elena Veliche; Isabel Kloumann; Ishan Misra; Ivan Evtimov; Jacob Xu; Jade Copet; Jake Weissman; Jan Geffert; Jana Vranes; Japhet Asher; Jason Park; Jay Mahadeokar; Jean-Baptiste Gaya; Jeet Shah; Jelmer van der Linde; Jennifer Chan; Jenny Hong; Jenya Lee; Jeremy Fu; Jeremy Teboul; Jianfeng Chi; Jianyu Huang; Jie Wang; Jiecao Yu; Joanna Bitton; Joe Spisak; Joelle Pineau; Jon Carvill; Jongsoo Park; Joseph Rocca; Joshua Johnstun; Junteng Jia; Kalyan Vasuden Alwala; Kam Hou U; Kate Plawiak; Kartikeya Upasani; Kaushik Veeraraghavan; Ke Li; Kenneth Heafield; Kevin Stone; Khalid El-Arini; Krithika Iyer; Kshitiz Malik; Kuenley Chiu; Kunal Bhalla; Kyle Huang; Lakshya Garg; Lauren Rantala-Yeary; Laurens van der Maaten; Lawrence Chen; Leandro Silva; Lee Bell; Lei Zhang; Liang Tan; Louis Martin; Lovish Madaan; Luca Wehrstedt; Lukas Blecher; Luke de Oliveira; Madeline Muzzi; Madian Khabsa; Manav Avlani; Mannat Singh; Manohar Paluri; Mark Zuckerberg; Marcin Kardas; Martynas Mankus; Mathew Oldham; Mathieu Rita; Matthew Lennie; Maya Pavlova; Meghan Keneally; Melanie Kambadur; Mihir Patel; Mikayel Samvelyan; Mike Clark; Mike Lewis; Min Si; Mitesh Kumar Singh; Mo Metanat; Mona Hassan; Naman Goyal; Narjes Torabi; Nicolas Usunier; Nikolay Bashlykov; Nikolay Bogoychev; Niladri Chatterji; Ning Dong; Oliver Aobo Yang; Olivier Duchenne; Onur Celebi; Parth Parekh; Patrick Alrassy; Paul Saab; Pavan Balaji; Pedro Rittner; Pengchuan Zhang; Pengwei Li; Petar Vasic; Peter Weng; Polina Zvyagina; Prajjwal Bhargava; Pratik Dubal; Praveen Krishnan; Punit Singh Koura; Qing He; Rachel Rodriguez; Ragavan Srinivasan; Rahul Mitra; Ramon Calderer; Raymond Li; Robert Stojnic; Roberta Raileanu; Robin Battey; Rocky Wang; Rohit Girdhar; Rohit Patel; Romain Sauvestre; Ronnie Polidoro; Roshan Sumbaly; Ross Taylor; Ruan Silva; Rui Hou; Rui Wang; Russ Howes; Ruty Rinott; Saghar Hosseini; Sai Jayesh Bondu; Samyak Datta; Sanjay Singh; Sara Chugh; Sargun Dhillon; Satadru Pan; Sean Bell; Sergey Edunov; Shaoliang Nie; Sharan Narang; Sharath Raparthy; Shaun Lindsay; Sheng Feng; Sheng Shen; Shenghao Lin; Shiva Shankar; Shruti Bhosale; Shun Zhang; Simon Vandenhende; Sinong Wang; Seohyun Sonia Kim; Soumya Batra; Sten Sootla; Steve Kehoe; Suchin Gururangan; Sumit Gupta; Sunny Virk; Sydney Borodinsky; Tamar Glaser; Tamar Herman; Tamara Best; Tara Fowler; Thomas Georgiou; Thomas Scialom; Tianhe Li; Todor Mihaylov; Tong Xiao; Ujjwal Karn; Vedanuj Goswami; Vibhor Gupta; Vignesh Ramanathan; Viktor Kerkez; Vinay Satish Kumar; Vincent Gonguet; Vish Vogeti; Vlad Poenaru; Vlad Tiberiu Mihailescu; Vladan Petrovic; Vladimir Ivanov; Wei Li; Weiwei Chu; Wenhan Xiong; Wenyin Fu; Wes Bouaziz; Whitney Meers; Will Constable; Xavier Martinet; Xiaojian Wu; Xinbo Gao; Xinfeng Xie; Xuchao Jia; Yaelle Goldschlag; Yann LeCun; Yashesh Gaur; Yasmine Babaei; Ye Qi; Yenda Li; Yi Wen; Yiwen Song; Youngjin Nam; Yuchen Hao; Yuchen Zhang; Yun Wang; Yuning Mao; Yuzi He; Zacharie Delpierre Coudert; Zachary DeVito; Zahra Hankir; Zhaoduo Wen; Zheng Yan; Zhengxing Chen; Zhenyu Yang; Zoe Papakipos
| [
"### Use with transformers\n\n\nSee the snippet below for usage with Transformers:",
"### Use with 'llama3'\n\n\nPlease, follow the instructions in the repository.\n\n\nTo download Original checkpoints, see the example command below leveraging 'huggingface-cli':\n\n\nFor Hugging Face support, we recommend using transformers or TGI, but a similar command works.\n\n\nHardware and Software\n---------------------\n\n\nTraining Factors We used custom training libraries, Meta's Research SuperCluster, and production clusters for pretraining. Fine-tuning, annotation, and evaluation were also performed on third-party cloud compute.\n\n\nCarbon Footprint Pretraining utilized a cumulative 7.7M GPU hours of computation on hardware of type H100-80GB (TDP of 700W). Estimated total emissions were 2290 tCO2eq, 100% of which were offset by Meta’s sustainability program.\n\n\n\nCO2 emissions during pre-training. Time: total GPU time required for training each model. Power Consumption: peak power capacity per GPU device for the GPUs used adjusted for power usage efficiency. 100% of the emissions are directly offset by Meta's sustainability program, and because we are openly releasing these models, the pretraining costs do not need to be incurred by others.\n\n\nTraining Data\n-------------\n\n\nOverview Llama 3 was pretrained on over 15 trillion tokens of data from publicly available sources. The fine-tuning data includes publicly available instruction datasets, as well as over 10M human-annotated examples. Neither the pretraining nor the fine-tuning datasets include Meta user data.\n\n\nData Freshness The pretraining data has a cutoff of March 2023 for the 7B and December 2023 for the 70B models respectively.\n\n\nBenchmarks\n----------\n\n\nIn this section, we report the results for Llama 3 models on standard automatic benchmarks. For all the evaluations, we use our internal evaluations library. For details on the methodology see here.",
"### Base pretrained models",
"### Instruction tuned models",
"### Responsibility & Safety\n\n\nWe believe that an open approach to AI leads to better, safer products, faster innovation, and a bigger overall market. We are committed to Responsible AI development and took a series of steps to limit misuse and harm and support the open source community.\n\n\nFoundation models are widely capable technologies that are built to be used for a diverse range of applications. They are not designed to meet every developer preference on safety levels for all use cases, out-of-the-box, as those by their nature will differ across different applications.\n\n\nRather, responsible LLM-application deployment is achieved by implementing a series of safety best practices throughout the development of such applications, from the model pre-training, fine-tuning and the deployment of systems composed of safeguards to tailor the safety needs specifically to the use case and audience.\n\n\nAs part of the Llama 3 release, we updated our Responsible Use Guide to outline the steps and best practices for developers to implement model and system level safety for their application. We also provide a set of resources including Meta Llama Guard 2 and Code Shield safeguards. These tools have proven to drastically reduce residual risks of LLM Systems, while maintaining a high level of helpfulness. We encourage developers to tune and deploy these safeguards according to their needs and we provide a reference implementation to get you started.",
"#### Llama 3-Instruct\n\n\nAs outlined in the Responsible Use Guide, some trade-off between model helpfulness and model alignment is likely unavoidable. Developers should exercise discretion about how to weigh the benefits of alignment and helpfulness for their specific use case and audience. Developers should be mindful of residual risks when using Llama models and leverage additional safety tools as needed to reach the right safety bar for their use case.\n\n\nSafety\n\n\nFor our instruction tuned model, we conducted extensive red teaming exercises, performed adversarial evaluations and implemented safety mitigations techniques to lower residual risks. As with any Large Language Model, residual risks will likely remain and we recommend that developers assess these risks in the context of their use case. In parallel, we are working with the community to make AI safety benchmark standards transparent, rigorous and interpretable.\n\n\nRefusals\n\n\nIn addition to residual risks, we put a great emphasis on model refusals to benign prompts. Over-refusing not only can impact the user experience but could even be harmful in certain contexts as well. We’ve heard the feedback from the developer community and improved our fine tuning to ensure that Llama 3 is significantly less likely to falsely refuse to answer prompts than Llama 2.\n\n\nWe built internal benchmarks and developed mitigations to limit false refusals making Llama 3 our most helpful model to date.",
"#### Responsible release\n\n\nIn addition to responsible use considerations outlined above, we followed a rigorous process that requires us to take extra measures against misuse and critical risks before we make our release decision.\n\n\nMisuse\n\n\nIf you access or use Llama 3, you agree to the Acceptable Use Policy. The most recent copy of this policy can be found at URL",
"#### Critical risks\n\n\nCBRNE (Chemical, Biological, Radiological, Nuclear, and high yield Explosives)\n\n\nWe have conducted a two fold assessment of the safety of the model in this area:\n\n\n* Iterative testing during model training to assess the safety of responses related to CBRNE threats and other adversarial risks.\n* Involving external CBRNE experts to conduct an uplift test assessing the ability of the model to accurately provide expert knowledge and reduce barriers to potential CBRNE misuse, by reference to what can be achieved using web search (without the model).",
"### Cyber Security\n\n\nWe have evaluated Llama 3 with CyberSecEval, Meta’s cybersecurity safety eval suite, measuring Llama 3’s propensity to suggest insecure code when used as a coding assistant, and Llama 3’s propensity to comply with requests to help carry out cyber attacks, where attacks are defined by the industry standard MITRE ATT&CK cyber attack ontology. On our insecure coding and cyber attacker helpfulness tests, Llama 3 behaved in the same range or safer than models of equivalent coding capability.",
"### Child Safety\n\n\nChild Safety risk assessments were conducted using a team of experts, to assess the model’s capability to produce outputs that could result in Child Safety risks and inform on any necessary and appropriate risk mitigations via fine tuning. We leveraged those expert red teaming sessions to expand the coverage of our evaluation benchmarks through Llama 3 model development. For Llama 3, we conducted new in-depth sessions using objective based methodologies to assess the model risks along multiple attack vectors. We also partnered with content specialists to perform red teaming exercises assessing potentially violating content while taking account of market specific nuances or experiences.",
"### Community\n\n\nGenerative AI safety requires expertise and tooling, and we believe in the strength of the open community to accelerate its progress. We are active members of open consortiums, including the AI Alliance, Partnership in AI and MLCommons, actively contributing to safety standardization and transparency. We encourage the community to adopt taxonomies like the MLCommons Proof of Concept evaluation to facilitate collaboration and transparency on safety and content evaluations. Our Purple Llama tools are open sourced for the community to use and widely distributed across ecosystem partners including cloud service providers. We encourage community contributions to our Github repository.\n\n\nFinally, we put in place a set of resources including an output reporting mechanism and bug bounty program to continuously improve the Llama technology with the help of the community.\n\n\nEthical Considerations and Limitations\n--------------------------------------\n\n\nThe core values of Llama 3 are openness, inclusivity and helpfulness. It is meant to serve everyone, and to work for a wide range of use cases. It is thus designed to be accessible to people across many different backgrounds, experiences and perspectives. Llama 3 addresses users and their needs as they are, without insertion unnecessary judgment or normativity, while reflecting the understanding that even content that may appear problematic in some cases can serve valuable purposes in others. It respects the dignity and autonomy of all users, especially in terms of the values of free thought and expression that power innovation and progress.\n\n\nBut Llama 3 is a new technology, and like any new technology, there are risks associated with its use. Testing conducted to date has been in English, and has not covered, nor could it cover, all scenarios. For these reasons, as with all LLMs, Llama 3’s potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate, biased or other objectionable responses to user prompts. Therefore, before deploying any applications of Llama 3 models, developers should perform safety testing and tuning tailored to their specific applications of the model. As outlined in the Responsible Use Guide, we recommend incorporating Purple Llama solutions into your workflows and specifically Llama Guard which provides a base model to filter input and output prompts to layer system-level safety on top of model-level safety.\n\n\nPlease see the Responsible Use Guide available at URL\n\n\ninstructions\n\n\n@article{llama3modelcard,\n\n\ntitle={Llama 3 Model Card},\n\n\nauthor={AI@Meta},\n\n\nyear={2024},\n\n\nurl = {URL\n\n\n}\n\n\nContributors\n------------\n\n\nAaditya Singh; Aaron Grattafiori; Abhimanyu Dubey; Abhinav Jauhri; Abhinav Pandey; Abhishek Kadian; Adam Kelsey; Adi Gangidi; Ahmad Al-Dahle; Ahuva Goldstand; Aiesha Letman; Ajay Menon; Akhil Mathur; Alan Schelten; Alex Vaughan; Amy Yang; Andrei Lupu; Andres Alvarado; Andrew Gallagher; Andrew Gu; Andrew Ho; Andrew Poulton; Andrew Ryan; Angela Fan; Ankit Ramchandani; Anthony Hartshorn; Archi Mitra; Archie Sravankumar; Artem Korenev; Arun Rao; Ashley Gabriel; Ashwin Bharambe; Assaf Eisenman; Aston Zhang; Aurelien Rodriguez; Austen Gregerson; Ava Spataru; Baptiste Roziere; Ben Maurer; Benjamin Leonhardi; Bernie Huang; Bhargavi Paranjape; Bing Liu; Binh Tang; Bobbie Chern; Brani Stojkovic; Brian Fuller; Catalina Mejia Arenas; Chao Zhou; Charlotte Caucheteux; Chaya Nayak; Ching-Hsiang Chu; Chloe Bi; Chris Cai; Chris Cox; Chris Marra; Chris McConnell; Christian Keller; Christoph Feichtenhofer; Christophe Touret; Chunyang Wu; Corinne Wong; Cristian Canton Ferrer; Damien Allonsius; Daniel Kreymer; Daniel Haziza; Daniel Li; Danielle Pintz; Danny Livshits; Danny Wyatt; David Adkins; David Esiobu; David Xu; Davide Testuggine; Delia David; Devi Parikh; Dhruv Choudhary; Dhruv Mahajan; Diana Liskovich; Diego Garcia-Olano; Diego Perino; Dieuwke Hupkes; Dingkang Wang; Dustin Holland; Egor Lakomkin; Elina Lobanova; Xiaoqing Ellen Tan; Emily Dinan; Eric Smith; Erik Brinkman; Esteban Arcaute; Filip Radenovic; Firat Ozgenel; Francesco Caggioni; Frank Seide; Frank Zhang; Gabriel Synnaeve; Gabriella Schwarz; Gabrielle Lee; Gada Badeer; Georgia Anderson; Graeme Nail; Gregoire Mialon; Guan Pang; Guillem Cucurell; Hailey Nguyen; Hannah Korevaar; Hannah Wang; Haroun Habeeb; Harrison Rudolph; Henry Aspegren; Hu Xu; Hugo Touvron; Iga Kozlowska; Igor Molybog; Igor Tufanov; Iliyan Zarov; Imanol Arrieta Ibarra; Irina-Elena Veliche; Isabel Kloumann; Ishan Misra; Ivan Evtimov; Jacob Xu; Jade Copet; Jake Weissman; Jan Geffert; Jana Vranes; Japhet Asher; Jason Park; Jay Mahadeokar; Jean-Baptiste Gaya; Jeet Shah; Jelmer van der Linde; Jennifer Chan; Jenny Hong; Jenya Lee; Jeremy Fu; Jeremy Teboul; Jianfeng Chi; Jianyu Huang; Jie Wang; Jiecao Yu; Joanna Bitton; Joe Spisak; Joelle Pineau; Jon Carvill; Jongsoo Park; Joseph Rocca; Joshua Johnstun; Junteng Jia; Kalyan Vasuden Alwala; Kam Hou U; Kate Plawiak; Kartikeya Upasani; Kaushik Veeraraghavan; Ke Li; Kenneth Heafield; Kevin Stone; Khalid El-Arini; Krithika Iyer; Kshitiz Malik; Kuenley Chiu; Kunal Bhalla; Kyle Huang; Lakshya Garg; Lauren Rantala-Yeary; Laurens van der Maaten; Lawrence Chen; Leandro Silva; Lee Bell; Lei Zhang; Liang Tan; Louis Martin; Lovish Madaan; Luca Wehrstedt; Lukas Blecher; Luke de Oliveira; Madeline Muzzi; Madian Khabsa; Manav Avlani; Mannat Singh; Manohar Paluri; Mark Zuckerberg; Marcin Kardas; Martynas Mankus; Mathew Oldham; Mathieu Rita; Matthew Lennie; Maya Pavlova; Meghan Keneally; Melanie Kambadur; Mihir Patel; Mikayel Samvelyan; Mike Clark; Mike Lewis; Min Si; Mitesh Kumar Singh; Mo Metanat; Mona Hassan; Naman Goyal; Narjes Torabi; Nicolas Usunier; Nikolay Bashlykov; Nikolay Bogoychev; Niladri Chatterji; Ning Dong; Oliver Aobo Yang; Olivier Duchenne; Onur Celebi; Parth Parekh; Patrick Alrassy; Paul Saab; Pavan Balaji; Pedro Rittner; Pengchuan Zhang; Pengwei Li; Petar Vasic; Peter Weng; Polina Zvyagina; Prajjwal Bhargava; Pratik Dubal; Praveen Krishnan; Punit Singh Koura; Qing He; Rachel Rodriguez; Ragavan Srinivasan; Rahul Mitra; Ramon Calderer; Raymond Li; Robert Stojnic; Roberta Raileanu; Robin Battey; Rocky Wang; Rohit Girdhar; Rohit Patel; Romain Sauvestre; Ronnie Polidoro; Roshan Sumbaly; Ross Taylor; Ruan Silva; Rui Hou; Rui Wang; Russ Howes; Ruty Rinott; Saghar Hosseini; Sai Jayesh Bondu; Samyak Datta; Sanjay Singh; Sara Chugh; Sargun Dhillon; Satadru Pan; Sean Bell; Sergey Edunov; Shaoliang Nie; Sharan Narang; Sharath Raparthy; Shaun Lindsay; Sheng Feng; Sheng Shen; Shenghao Lin; Shiva Shankar; Shruti Bhosale; Shun Zhang; Simon Vandenhende; Sinong Wang; Seohyun Sonia Kim; Soumya Batra; Sten Sootla; Steve Kehoe; Suchin Gururangan; Sumit Gupta; Sunny Virk; Sydney Borodinsky; Tamar Glaser; Tamar Herman; Tamara Best; Tara Fowler; Thomas Georgiou; Thomas Scialom; Tianhe Li; Todor Mihaylov; Tong Xiao; Ujjwal Karn; Vedanuj Goswami; Vibhor Gupta; Vignesh Ramanathan; Viktor Kerkez; Vinay Satish Kumar; Vincent Gonguet; Vish Vogeti; Vlad Poenaru; Vlad Tiberiu Mihailescu; Vladan Petrovic; Vladimir Ivanov; Wei Li; Weiwei Chu; Wenhan Xiong; Wenyin Fu; Wes Bouaziz; Whitney Meers; Will Constable; Xavier Martinet; Xiaojian Wu; Xinbo Gao; Xinfeng Xie; Xuchao Jia; Yaelle Goldschlag; Yann LeCun; Yashesh Gaur; Yasmine Babaei; Ye Qi; Yenda Li; Yi Wen; Yiwen Song; Youngjin Nam; Yuchen Hao; Yuchen Zhang; Yun Wang; Yuning Mao; Yuzi He; Zacharie Delpierre Coudert; Zachary DeVito; Zahra Hankir; Zhaoduo Wen; Zheng Yan; Zhengxing Chen; Zhenyu Yang; Zoe Papakipos"
] | [
"TAGS\n#transformers #openvino #llama #text-generation #facebook #meta #pytorch #llama-3 #en #license-other #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n",
"### Use with transformers\n\n\nSee the snippet below for usage with Transformers:",
"### Use with 'llama3'\n\n\nPlease, follow the instructions in the repository.\n\n\nTo download Original checkpoints, see the example command below leveraging 'huggingface-cli':\n\n\nFor Hugging Face support, we recommend using transformers or TGI, but a similar command works.\n\n\nHardware and Software\n---------------------\n\n\nTraining Factors We used custom training libraries, Meta's Research SuperCluster, and production clusters for pretraining. Fine-tuning, annotation, and evaluation were also performed on third-party cloud compute.\n\n\nCarbon Footprint Pretraining utilized a cumulative 7.7M GPU hours of computation on hardware of type H100-80GB (TDP of 700W). Estimated total emissions were 2290 tCO2eq, 100% of which were offset by Meta’s sustainability program.\n\n\n\nCO2 emissions during pre-training. Time: total GPU time required for training each model. Power Consumption: peak power capacity per GPU device for the GPUs used adjusted for power usage efficiency. 100% of the emissions are directly offset by Meta's sustainability program, and because we are openly releasing these models, the pretraining costs do not need to be incurred by others.\n\n\nTraining Data\n-------------\n\n\nOverview Llama 3 was pretrained on over 15 trillion tokens of data from publicly available sources. The fine-tuning data includes publicly available instruction datasets, as well as over 10M human-annotated examples. Neither the pretraining nor the fine-tuning datasets include Meta user data.\n\n\nData Freshness The pretraining data has a cutoff of March 2023 for the 7B and December 2023 for the 70B models respectively.\n\n\nBenchmarks\n----------\n\n\nIn this section, we report the results for Llama 3 models on standard automatic benchmarks. For all the evaluations, we use our internal evaluations library. For details on the methodology see here.",
"### Base pretrained models",
"### Instruction tuned models",
"### Responsibility & Safety\n\n\nWe believe that an open approach to AI leads to better, safer products, faster innovation, and a bigger overall market. We are committed to Responsible AI development and took a series of steps to limit misuse and harm and support the open source community.\n\n\nFoundation models are widely capable technologies that are built to be used for a diverse range of applications. They are not designed to meet every developer preference on safety levels for all use cases, out-of-the-box, as those by their nature will differ across different applications.\n\n\nRather, responsible LLM-application deployment is achieved by implementing a series of safety best practices throughout the development of such applications, from the model pre-training, fine-tuning and the deployment of systems composed of safeguards to tailor the safety needs specifically to the use case and audience.\n\n\nAs part of the Llama 3 release, we updated our Responsible Use Guide to outline the steps and best practices for developers to implement model and system level safety for their application. We also provide a set of resources including Meta Llama Guard 2 and Code Shield safeguards. These tools have proven to drastically reduce residual risks of LLM Systems, while maintaining a high level of helpfulness. We encourage developers to tune and deploy these safeguards according to their needs and we provide a reference implementation to get you started.",
"#### Llama 3-Instruct\n\n\nAs outlined in the Responsible Use Guide, some trade-off between model helpfulness and model alignment is likely unavoidable. Developers should exercise discretion about how to weigh the benefits of alignment and helpfulness for their specific use case and audience. Developers should be mindful of residual risks when using Llama models and leverage additional safety tools as needed to reach the right safety bar for their use case.\n\n\nSafety\n\n\nFor our instruction tuned model, we conducted extensive red teaming exercises, performed adversarial evaluations and implemented safety mitigations techniques to lower residual risks. As with any Large Language Model, residual risks will likely remain and we recommend that developers assess these risks in the context of their use case. In parallel, we are working with the community to make AI safety benchmark standards transparent, rigorous and interpretable.\n\n\nRefusals\n\n\nIn addition to residual risks, we put a great emphasis on model refusals to benign prompts. Over-refusing not only can impact the user experience but could even be harmful in certain contexts as well. We’ve heard the feedback from the developer community and improved our fine tuning to ensure that Llama 3 is significantly less likely to falsely refuse to answer prompts than Llama 2.\n\n\nWe built internal benchmarks and developed mitigations to limit false refusals making Llama 3 our most helpful model to date.",
"#### Responsible release\n\n\nIn addition to responsible use considerations outlined above, we followed a rigorous process that requires us to take extra measures against misuse and critical risks before we make our release decision.\n\n\nMisuse\n\n\nIf you access or use Llama 3, you agree to the Acceptable Use Policy. The most recent copy of this policy can be found at URL",
"#### Critical risks\n\n\nCBRNE (Chemical, Biological, Radiological, Nuclear, and high yield Explosives)\n\n\nWe have conducted a two fold assessment of the safety of the model in this area:\n\n\n* Iterative testing during model training to assess the safety of responses related to CBRNE threats and other adversarial risks.\n* Involving external CBRNE experts to conduct an uplift test assessing the ability of the model to accurately provide expert knowledge and reduce barriers to potential CBRNE misuse, by reference to what can be achieved using web search (without the model).",
"### Cyber Security\n\n\nWe have evaluated Llama 3 with CyberSecEval, Meta’s cybersecurity safety eval suite, measuring Llama 3’s propensity to suggest insecure code when used as a coding assistant, and Llama 3’s propensity to comply with requests to help carry out cyber attacks, where attacks are defined by the industry standard MITRE ATT&CK cyber attack ontology. On our insecure coding and cyber attacker helpfulness tests, Llama 3 behaved in the same range or safer than models of equivalent coding capability.",
"### Child Safety\n\n\nChild Safety risk assessments were conducted using a team of experts, to assess the model’s capability to produce outputs that could result in Child Safety risks and inform on any necessary and appropriate risk mitigations via fine tuning. We leveraged those expert red teaming sessions to expand the coverage of our evaluation benchmarks through Llama 3 model development. For Llama 3, we conducted new in-depth sessions using objective based methodologies to assess the model risks along multiple attack vectors. We also partnered with content specialists to perform red teaming exercises assessing potentially violating content while taking account of market specific nuances or experiences.",
"### Community\n\n\nGenerative AI safety requires expertise and tooling, and we believe in the strength of the open community to accelerate its progress. We are active members of open consortiums, including the AI Alliance, Partnership in AI and MLCommons, actively contributing to safety standardization and transparency. We encourage the community to adopt taxonomies like the MLCommons Proof of Concept evaluation to facilitate collaboration and transparency on safety and content evaluations. Our Purple Llama tools are open sourced for the community to use and widely distributed across ecosystem partners including cloud service providers. We encourage community contributions to our Github repository.\n\n\nFinally, we put in place a set of resources including an output reporting mechanism and bug bounty program to continuously improve the Llama technology with the help of the community.\n\n\nEthical Considerations and Limitations\n--------------------------------------\n\n\nThe core values of Llama 3 are openness, inclusivity and helpfulness. It is meant to serve everyone, and to work for a wide range of use cases. It is thus designed to be accessible to people across many different backgrounds, experiences and perspectives. Llama 3 addresses users and their needs as they are, without insertion unnecessary judgment or normativity, while reflecting the understanding that even content that may appear problematic in some cases can serve valuable purposes in others. It respects the dignity and autonomy of all users, especially in terms of the values of free thought and expression that power innovation and progress.\n\n\nBut Llama 3 is a new technology, and like any new technology, there are risks associated with its use. Testing conducted to date has been in English, and has not covered, nor could it cover, all scenarios. For these reasons, as with all LLMs, Llama 3’s potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate, biased or other objectionable responses to user prompts. Therefore, before deploying any applications of Llama 3 models, developers should perform safety testing and tuning tailored to their specific applications of the model. As outlined in the Responsible Use Guide, we recommend incorporating Purple Llama solutions into your workflows and specifically Llama Guard which provides a base model to filter input and output prompts to layer system-level safety on top of model-level safety.\n\n\nPlease see the Responsible Use Guide available at URL\n\n\ninstructions\n\n\n@article{llama3modelcard,\n\n\ntitle={Llama 3 Model Card},\n\n\nauthor={AI@Meta},\n\n\nyear={2024},\n\n\nurl = {URL\n\n\n}\n\n\nContributors\n------------\n\n\nAaditya Singh; Aaron Grattafiori; Abhimanyu Dubey; Abhinav Jauhri; Abhinav Pandey; Abhishek Kadian; Adam Kelsey; Adi Gangidi; Ahmad Al-Dahle; Ahuva Goldstand; Aiesha Letman; Ajay Menon; Akhil Mathur; Alan Schelten; Alex Vaughan; Amy Yang; Andrei Lupu; Andres Alvarado; Andrew Gallagher; Andrew Gu; Andrew Ho; Andrew Poulton; Andrew Ryan; Angela Fan; Ankit Ramchandani; Anthony Hartshorn; Archi Mitra; Archie Sravankumar; Artem Korenev; Arun Rao; Ashley Gabriel; Ashwin Bharambe; Assaf Eisenman; Aston Zhang; Aurelien Rodriguez; Austen Gregerson; Ava Spataru; Baptiste Roziere; Ben Maurer; Benjamin Leonhardi; Bernie Huang; Bhargavi Paranjape; Bing Liu; Binh Tang; Bobbie Chern; Brani Stojkovic; Brian Fuller; Catalina Mejia Arenas; Chao Zhou; Charlotte Caucheteux; Chaya Nayak; Ching-Hsiang Chu; Chloe Bi; Chris Cai; Chris Cox; Chris Marra; Chris McConnell; Christian Keller; Christoph Feichtenhofer; Christophe Touret; Chunyang Wu; Corinne Wong; Cristian Canton Ferrer; Damien Allonsius; Daniel Kreymer; Daniel Haziza; Daniel Li; Danielle Pintz; Danny Livshits; Danny Wyatt; David Adkins; David Esiobu; David Xu; Davide Testuggine; Delia David; Devi Parikh; Dhruv Choudhary; Dhruv Mahajan; Diana Liskovich; Diego Garcia-Olano; Diego Perino; Dieuwke Hupkes; Dingkang Wang; Dustin Holland; Egor Lakomkin; Elina Lobanova; Xiaoqing Ellen Tan; Emily Dinan; Eric Smith; Erik Brinkman; Esteban Arcaute; Filip Radenovic; Firat Ozgenel; Francesco Caggioni; Frank Seide; Frank Zhang; Gabriel Synnaeve; Gabriella Schwarz; Gabrielle Lee; Gada Badeer; Georgia Anderson; Graeme Nail; Gregoire Mialon; Guan Pang; Guillem Cucurell; Hailey Nguyen; Hannah Korevaar; Hannah Wang; Haroun Habeeb; Harrison Rudolph; Henry Aspegren; Hu Xu; Hugo Touvron; Iga Kozlowska; Igor Molybog; Igor Tufanov; Iliyan Zarov; Imanol Arrieta Ibarra; Irina-Elena Veliche; Isabel Kloumann; Ishan Misra; Ivan Evtimov; Jacob Xu; Jade Copet; Jake Weissman; Jan Geffert; Jana Vranes; Japhet Asher; Jason Park; Jay Mahadeokar; Jean-Baptiste Gaya; Jeet Shah; Jelmer van der Linde; Jennifer Chan; Jenny Hong; Jenya Lee; Jeremy Fu; Jeremy Teboul; Jianfeng Chi; Jianyu Huang; Jie Wang; Jiecao Yu; Joanna Bitton; Joe Spisak; Joelle Pineau; Jon Carvill; Jongsoo Park; Joseph Rocca; Joshua Johnstun; Junteng Jia; Kalyan Vasuden Alwala; Kam Hou U; Kate Plawiak; Kartikeya Upasani; Kaushik Veeraraghavan; Ke Li; Kenneth Heafield; Kevin Stone; Khalid El-Arini; Krithika Iyer; Kshitiz Malik; Kuenley Chiu; Kunal Bhalla; Kyle Huang; Lakshya Garg; Lauren Rantala-Yeary; Laurens van der Maaten; Lawrence Chen; Leandro Silva; Lee Bell; Lei Zhang; Liang Tan; Louis Martin; Lovish Madaan; Luca Wehrstedt; Lukas Blecher; Luke de Oliveira; Madeline Muzzi; Madian Khabsa; Manav Avlani; Mannat Singh; Manohar Paluri; Mark Zuckerberg; Marcin Kardas; Martynas Mankus; Mathew Oldham; Mathieu Rita; Matthew Lennie; Maya Pavlova; Meghan Keneally; Melanie Kambadur; Mihir Patel; Mikayel Samvelyan; Mike Clark; Mike Lewis; Min Si; Mitesh Kumar Singh; Mo Metanat; Mona Hassan; Naman Goyal; Narjes Torabi; Nicolas Usunier; Nikolay Bashlykov; Nikolay Bogoychev; Niladri Chatterji; Ning Dong; Oliver Aobo Yang; Olivier Duchenne; Onur Celebi; Parth Parekh; Patrick Alrassy; Paul Saab; Pavan Balaji; Pedro Rittner; Pengchuan Zhang; Pengwei Li; Petar Vasic; Peter Weng; Polina Zvyagina; Prajjwal Bhargava; Pratik Dubal; Praveen Krishnan; Punit Singh Koura; Qing He; Rachel Rodriguez; Ragavan Srinivasan; Rahul Mitra; Ramon Calderer; Raymond Li; Robert Stojnic; Roberta Raileanu; Robin Battey; Rocky Wang; Rohit Girdhar; Rohit Patel; Romain Sauvestre; Ronnie Polidoro; Roshan Sumbaly; Ross Taylor; Ruan Silva; Rui Hou; Rui Wang; Russ Howes; Ruty Rinott; Saghar Hosseini; Sai Jayesh Bondu; Samyak Datta; Sanjay Singh; Sara Chugh; Sargun Dhillon; Satadru Pan; Sean Bell; Sergey Edunov; Shaoliang Nie; Sharan Narang; Sharath Raparthy; Shaun Lindsay; Sheng Feng; Sheng Shen; Shenghao Lin; Shiva Shankar; Shruti Bhosale; Shun Zhang; Simon Vandenhende; Sinong Wang; Seohyun Sonia Kim; Soumya Batra; Sten Sootla; Steve Kehoe; Suchin Gururangan; Sumit Gupta; Sunny Virk; Sydney Borodinsky; Tamar Glaser; Tamar Herman; Tamara Best; Tara Fowler; Thomas Georgiou; Thomas Scialom; Tianhe Li; Todor Mihaylov; Tong Xiao; Ujjwal Karn; Vedanuj Goswami; Vibhor Gupta; Vignesh Ramanathan; Viktor Kerkez; Vinay Satish Kumar; Vincent Gonguet; Vish Vogeti; Vlad Poenaru; Vlad Tiberiu Mihailescu; Vladan Petrovic; Vladimir Ivanov; Wei Li; Weiwei Chu; Wenhan Xiong; Wenyin Fu; Wes Bouaziz; Whitney Meers; Will Constable; Xavier Martinet; Xiaojian Wu; Xinbo Gao; Xinfeng Xie; Xuchao Jia; Yaelle Goldschlag; Yann LeCun; Yashesh Gaur; Yasmine Babaei; Ye Qi; Yenda Li; Yi Wen; Yiwen Song; Youngjin Nam; Yuchen Hao; Yuchen Zhang; Yun Wang; Yuning Mao; Yuzi He; Zacharie Delpierre Coudert; Zachary DeVito; Zahra Hankir; Zhaoduo Wen; Zheng Yan; Zhengxing Chen; Zhenyu Yang; Zoe Papakipos"
] |
text-generation | transformers |
# Uploaded model
- **Developed by:** Haxirus
- **License:** apache-2.0
- **Finetuned from model :** unsloth/gemma-2b-it-bnb-4bit
This gemma model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
| {"language": ["en"], "license": "apache-2.0", "tags": ["text-generation-inference", "transformers", "unsloth", "gemma", "trl", "sft"], "base_model": "unsloth/gemma-2b-it-bnb-4bit"} | Haxirus/Gemma_2B_Fine-tuned | null | [
"transformers",
"pytorch",
"gemma",
"text-generation",
"text-generation-inference",
"unsloth",
"trl",
"sft",
"conversational",
"en",
"base_model:unsloth/gemma-2b-it-bnb-4bit",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | null | 2024-04-19T17:10:51+00:00 | [] | [
"en"
] | TAGS
#transformers #pytorch #gemma #text-generation #text-generation-inference #unsloth #trl #sft #conversational #en #base_model-unsloth/gemma-2b-it-bnb-4bit #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us
|
# Uploaded model
- Developed by: Haxirus
- License: apache-2.0
- Finetuned from model : unsloth/gemma-2b-it-bnb-4bit
This gemma model was trained 2x faster with Unsloth and Huggingface's TRL library.
<img src="URL width="200"/>
| [
"# Uploaded model\n\n- Developed by: Haxirus\n- License: apache-2.0\n- Finetuned from model : unsloth/gemma-2b-it-bnb-4bit\n\nThis gemma model was trained 2x faster with Unsloth and Huggingface's TRL library.\n\n<img src=\"URL width=\"200\"/>"
] | [
"TAGS\n#transformers #pytorch #gemma #text-generation #text-generation-inference #unsloth #trl #sft #conversational #en #base_model-unsloth/gemma-2b-it-bnb-4bit #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us \n",
"# Uploaded model\n\n- Developed by: Haxirus\n- License: apache-2.0\n- Finetuned from model : unsloth/gemma-2b-it-bnb-4bit\n\nThis gemma model was trained 2x faster with Unsloth and Huggingface's TRL library.\n\n<img src=\"URL width=\"200\"/>"
] |
null | transformers |
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] | {"library_name": "transformers", "tags": []} | wendy41/llama-3-user0-100 | null | [
"transformers",
"safetensors",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null | 2024-04-19T17:12:56+00:00 | [
"1910.09700"
] | [] | TAGS
#transformers #safetensors #arxiv-1910.09700 #endpoints_compatible #region-us
|
# Model Card for Model ID
## Model Details
### Model Description
This is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.
- Developed by:
- Funded by [optional]:
- Shared by [optional]:
- Model type:
- Language(s) (NLP):
- License:
- Finetuned from model [optional]:
### Model Sources [optional]
- Repository:
- Paper [optional]:
- Demo [optional]:
## Uses
### Direct Use
### Downstream Use [optional]
### Out-of-Scope Use
## Bias, Risks, and Limitations
### Recommendations
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
## Training Details
### Training Data
### Training Procedure
#### Preprocessing [optional]
#### Training Hyperparameters
- Training regime:
#### Speeds, Sizes, Times [optional]
## Evaluation
### Testing Data, Factors & Metrics
#### Testing Data
#### Factors
#### Metrics
### Results
#### Summary
## Model Examination [optional]
## Environmental Impact
Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).
- Hardware Type:
- Hours used:
- Cloud Provider:
- Compute Region:
- Carbon Emitted:
## Technical Specifications [optional]
### Model Architecture and Objective
### Compute Infrastructure
#### Hardware
#### Software
[optional]
BibTeX:
APA:
## Glossary [optional]
## More Information [optional]
## Model Card Authors [optional]
## Model Card Contact
| [
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.",
"## How to Get Started with the Model\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] | [
"TAGS\n#transformers #safetensors #arxiv-1910.09700 #endpoints_compatible #region-us \n",
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.",
"## How to Get Started with the Model\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] |
null | null | MLC compiled model library with Vulkan for Windows | {"license": "apache-2.0"} | TheHpx/Llama-3-8B-Instruct-q4f16_1-MLC-vulkan | null | [
"license:apache-2.0",
"region:us"
] | null | 2024-04-19T17:12:57+00:00 | [] | [] | TAGS
#license-apache-2.0 #region-us
| MLC compiled model library with Vulkan for Windows | [] | [
"TAGS\n#license-apache-2.0 #region-us \n"
] |
automatic-speech-recognition | transformers |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# wtimit-base-normal-all-nofreeze
This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the wtimit_asr dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3190
- Wer: 0.0999
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0001
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 1000
- num_epochs: 50
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|:-------------:|:-----:|:------:|:---------------:|:------:|
| 1.5076 | 0.4 | 1000 | 1.1220 | 0.6793 |
| 0.4102 | 0.81 | 2000 | 0.7851 | 0.4338 |
| 0.2278 | 1.21 | 3000 | 0.6897 | 0.3203 |
| 0.1723 | 1.61 | 4000 | 0.5668 | 0.2890 |
| 0.1407 | 2.02 | 5000 | 0.4399 | 0.2362 |
| 0.117 | 2.42 | 6000 | 0.4853 | 0.2508 |
| 0.098 | 2.83 | 7000 | 0.6732 | 0.2871 |
| 0.0862 | 3.23 | 8000 | 0.5802 | 0.2680 |
| 0.0806 | 3.63 | 9000 | 0.4730 | 0.2488 |
| 0.0706 | 4.04 | 10000 | 0.4001 | 0.1953 |
| 0.061 | 4.44 | 11000 | 0.4108 | 0.1971 |
| 0.063 | 4.84 | 12000 | 0.4544 | 0.2056 |
| 0.0527 | 5.25 | 13000 | 0.4235 | 0.1938 |
| 0.049 | 5.65 | 14000 | 0.4375 | 0.2054 |
| 0.0489 | 6.06 | 15000 | 0.5451 | 0.2522 |
| 0.0473 | 6.46 | 16000 | 0.3939 | 0.1868 |
| 0.0442 | 6.86 | 17000 | 0.5662 | 0.2548 |
| 0.0428 | 7.27 | 18000 | 0.6695 | 0.2755 |
| 0.0379 | 7.67 | 19000 | 0.3929 | 0.1947 |
| 0.0398 | 8.07 | 20000 | 0.4446 | 0.2066 |
| 0.0336 | 8.48 | 21000 | 0.5409 | 0.2260 |
| 0.0316 | 8.88 | 22000 | 0.3819 | 0.1715 |
| 0.0322 | 9.29 | 23000 | 0.3861 | 0.1711 |
| 0.0352 | 9.69 | 24000 | 0.4063 | 0.1728 |
| 0.0315 | 10.09 | 25000 | 0.4992 | 0.2146 |
| 0.0254 | 10.5 | 26000 | 0.5838 | 0.2158 |
| 0.0243 | 10.9 | 27000 | 0.3458 | 0.1523 |
| 0.0245 | 11.3 | 28000 | 0.5121 | 0.1953 |
| 0.0231 | 11.71 | 29000 | 0.3773 | 0.1616 |
| 0.0202 | 12.11 | 30000 | 0.4110 | 0.1715 |
| 0.0261 | 12.52 | 31000 | 0.5376 | 0.2116 |
| 0.0243 | 12.92 | 32000 | 0.4066 | 0.1569 |
| 0.0201 | 13.32 | 33000 | 0.5944 | 0.2276 |
| 0.0211 | 13.73 | 34000 | 0.4670 | 0.1997 |
| 0.0249 | 14.13 | 35000 | 0.5521 | 0.2254 |
| 0.021 | 14.53 | 36000 | 0.4602 | 0.2061 |
| 0.0169 | 14.94 | 37000 | 0.4870 | 0.1690 |
| 0.0184 | 15.34 | 38000 | 0.6038 | 0.2208 |
| 0.0207 | 15.74 | 39000 | 0.5266 | 0.2068 |
| 0.0209 | 16.15 | 40000 | 0.5197 | 0.2083 |
| 0.0175 | 16.55 | 41000 | 0.5074 | 0.1927 |
| 0.0164 | 16.96 | 42000 | 0.4594 | 0.1615 |
| 0.0164 | 17.36 | 43000 | 0.2956 | 0.1151 |
| 0.0142 | 17.76 | 44000 | 0.3834 | 0.1580 |
| 0.0139 | 18.17 | 45000 | 0.5316 | 0.2175 |
| 0.0181 | 18.57 | 46000 | 0.5226 | 0.1890 |
| 0.0159 | 18.97 | 47000 | 0.4914 | 0.1689 |
| 0.0127 | 19.38 | 48000 | 0.5454 | 0.1957 |
| 0.0136 | 19.78 | 49000 | 0.5530 | 0.2172 |
| 0.0129 | 20.19 | 50000 | 0.6980 | 0.2636 |
| 0.0131 | 20.59 | 51000 | 0.3984 | 0.1379 |
| 0.0123 | 20.99 | 52000 | 0.4925 | 0.1843 |
| 0.0095 | 21.4 | 53000 | 0.5367 | 0.1931 |
| 0.0124 | 21.8 | 54000 | 0.4299 | 0.1763 |
| 0.0115 | 22.2 | 55000 | 0.4797 | 0.1803 |
| 0.0136 | 22.61 | 56000 | 0.6638 | 0.2300 |
| 0.0121 | 23.01 | 57000 | 0.4292 | 0.1530 |
| 0.0097 | 23.42 | 58000 | 0.4064 | 0.1520 |
| 0.0143 | 23.82 | 59000 | 0.4691 | 0.1771 |
| 0.0092 | 24.22 | 60000 | 0.5134 | 0.2009 |
| 0.0097 | 24.63 | 61000 | 0.6165 | 0.2281 |
| 0.0078 | 25.03 | 62000 | 0.4828 | 0.1863 |
| 0.0114 | 25.43 | 63000 | 0.4817 | 0.1868 |
| 0.0089 | 25.84 | 64000 | 0.5137 | 0.2003 |
| 0.0083 | 26.24 | 65000 | 0.4194 | 0.1524 |
| 0.01 | 26.65 | 66000 | 0.3416 | 0.1332 |
| 0.0102 | 27.05 | 67000 | 0.3834 | 0.1475 |
| 0.0076 | 27.45 | 68000 | 0.3390 | 0.1277 |
| 0.0085 | 27.86 | 69000 | 0.4708 | 0.1843 |
| 0.0074 | 28.26 | 70000 | 0.4434 | 0.1530 |
| 0.0078 | 28.66 | 71000 | 0.2942 | 0.1104 |
| 0.0075 | 29.07 | 72000 | 0.3623 | 0.1442 |
| 0.0066 | 29.47 | 73000 | 0.4709 | 0.1547 |
| 0.0073 | 29.87 | 74000 | 0.5198 | 0.1750 |
| 0.0056 | 30.28 | 75000 | 0.3083 | 0.1211 |
| 0.0066 | 30.68 | 76000 | 0.3204 | 0.1243 |
| 0.0048 | 31.09 | 77000 | 0.3713 | 0.1326 |
| 0.0047 | 31.49 | 78000 | 0.3121 | 0.1018 |
| 0.0066 | 31.89 | 79000 | 0.4510 | 0.1473 |
| 0.0053 | 32.3 | 80000 | 0.3599 | 0.1130 |
| 0.0058 | 32.7 | 81000 | 0.4256 | 0.1463 |
| 0.0056 | 33.1 | 82000 | 0.4393 | 0.1605 |
| 0.0046 | 33.51 | 83000 | 0.6327 | 0.2056 |
| 0.0049 | 33.91 | 84000 | 0.4069 | 0.1360 |
| 0.0031 | 34.32 | 85000 | 0.4359 | 0.1458 |
| 0.0052 | 34.72 | 86000 | 0.2825 | 0.1032 |
| 0.0039 | 35.12 | 87000 | 0.3545 | 0.1256 |
| 0.003 | 35.53 | 88000 | 0.3674 | 0.1252 |
| 0.004 | 35.93 | 89000 | 0.3849 | 0.1288 |
| 0.0029 | 36.33 | 90000 | 0.3465 | 0.1130 |
| 0.003 | 36.74 | 91000 | 0.4034 | 0.1294 |
| 0.0036 | 37.14 | 92000 | 0.3456 | 0.1209 |
| 0.0033 | 37.55 | 93000 | 0.3882 | 0.1407 |
| 0.0037 | 37.95 | 94000 | 0.3372 | 0.1094 |
| 0.0025 | 38.35 | 95000 | 0.3601 | 0.1137 |
| 0.0037 | 38.76 | 96000 | 0.2804 | 0.1027 |
| 0.0022 | 39.16 | 97000 | 0.4160 | 0.1354 |
| 0.0027 | 39.56 | 98000 | 0.3379 | 0.1202 |
| 0.002 | 39.97 | 99000 | 0.3462 | 0.1171 |
| 0.0021 | 40.37 | 100000 | 0.3694 | 0.1272 |
| 0.0014 | 40.78 | 101000 | 0.3315 | 0.1048 |
| 0.0025 | 41.18 | 102000 | 0.3316 | 0.1088 |
| 0.002 | 41.58 | 103000 | 0.3776 | 0.1319 |
| 0.0028 | 41.99 | 104000 | 0.3024 | 0.1028 |
| 0.0015 | 42.39 | 105000 | 0.3087 | 0.1102 |
| 0.0018 | 42.79 | 106000 | 0.3254 | 0.1067 |
| 0.0028 | 43.2 | 107000 | 0.3305 | 0.1081 |
| 0.002 | 43.6 | 108000 | 0.3445 | 0.1120 |
| 0.0019 | 44.0 | 109000 | 0.3264 | 0.1082 |
| 0.0019 | 44.41 | 110000 | 0.3650 | 0.1202 |
| 0.001 | 44.81 | 111000 | 0.3415 | 0.1133 |
| 0.0015 | 45.22 | 112000 | 0.3194 | 0.1044 |
| 0.0011 | 45.62 | 113000 | 0.3302 | 0.1085 |
| 0.0013 | 46.02 | 114000 | 0.3083 | 0.1053 |
| 0.0008 | 46.43 | 115000 | 0.2976 | 0.0982 |
| 0.0019 | 46.83 | 116000 | 0.3212 | 0.1057 |
| 0.0006 | 47.23 | 117000 | 0.3415 | 0.1089 |
| 0.0025 | 47.64 | 118000 | 0.3188 | 0.1043 |
| 0.0009 | 48.04 | 119000 | 0.3136 | 0.1025 |
| 0.0015 | 48.45 | 120000 | 0.3180 | 0.1050 |
| 0.0013 | 48.85 | 121000 | 0.3439 | 0.1110 |
| 0.0007 | 49.25 | 122000 | 0.3286 | 0.1048 |
| 0.0014 | 49.66 | 123000 | 0.3190 | 0.0999 |
### Framework versions
- Transformers 4.39.3
- Pytorch 2.0.1+cu117
- Datasets 2.18.0
- Tokenizers 0.15.2
| {"license": "apache-2.0", "tags": ["generated_from_trainer"], "datasets": ["wtimit_asr"], "metrics": ["wer"], "base_model": "facebook/wav2vec2-base", "model-index": [{"name": "wtimit-base-normal-all-nofreeze", "results": [{"task": {"type": "automatic-speech-recognition", "name": "Automatic Speech Recognition"}, "dataset": {"name": "wtimit_asr", "type": "wtimit_asr", "config": "clean", "split": "None", "args": "clean"}, "metrics": [{"type": "wer", "value": 0.09987953700309014, "name": "Wer"}]}]}]} | SpeechResearch/wtimit-base-normal-all-nofreeze | null | [
"transformers",
"safetensors",
"wav2vec2",
"automatic-speech-recognition",
"generated_from_trainer",
"dataset:wtimit_asr",
"base_model:facebook/wav2vec2-base",
"license:apache-2.0",
"model-index",
"endpoints_compatible",
"region:us"
] | null | 2024-04-19T17:14:55+00:00 | [] | [] | TAGS
#transformers #safetensors #wav2vec2 #automatic-speech-recognition #generated_from_trainer #dataset-wtimit_asr #base_model-facebook/wav2vec2-base #license-apache-2.0 #model-index #endpoints_compatible #region-us
| wtimit-base-normal-all-nofreeze
===============================
This model is a fine-tuned version of facebook/wav2vec2-base on the wtimit\_asr dataset.
It achieves the following results on the evaluation set:
* Loss: 0.3190
* Wer: 0.0999
Model description
-----------------
More information needed
Intended uses & limitations
---------------------------
More information needed
Training and evaluation data
----------------------------
More information needed
Training procedure
------------------
### Training hyperparameters
The following hyperparameters were used during training:
* learning\_rate: 0.0001
* train\_batch\_size: 8
* eval\_batch\_size: 8
* seed: 42
* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
* lr\_scheduler\_type: linear
* lr\_scheduler\_warmup\_steps: 1000
* num\_epochs: 50
* mixed\_precision\_training: Native AMP
### Training results
### Framework versions
* Transformers 4.39.3
* Pytorch 2.0.1+cu117
* Datasets 2.18.0
* Tokenizers 0.15.2
| [
"### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0001\n* train\\_batch\\_size: 8\n* eval\\_batch\\_size: 8\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* lr\\_scheduler\\_warmup\\_steps: 1000\n* num\\_epochs: 50\n* mixed\\_precision\\_training: Native AMP",
"### Training results",
"### Framework versions\n\n\n* Transformers 4.39.3\n* Pytorch 2.0.1+cu117\n* Datasets 2.18.0\n* Tokenizers 0.15.2"
] | [
"TAGS\n#transformers #safetensors #wav2vec2 #automatic-speech-recognition #generated_from_trainer #dataset-wtimit_asr #base_model-facebook/wav2vec2-base #license-apache-2.0 #model-index #endpoints_compatible #region-us \n",
"### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0001\n* train\\_batch\\_size: 8\n* eval\\_batch\\_size: 8\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* lr\\_scheduler\\_warmup\\_steps: 1000\n* num\\_epochs: 50\n* mixed\\_precision\\_training: Native AMP",
"### Training results",
"### Framework versions\n\n\n* Transformers 4.39.3\n* Pytorch 2.0.1+cu117\n* Datasets 2.18.0\n* Tokenizers 0.15.2"
] |
null | null | # Stable Diffusion web UI
A browser interface based on Gradio library for Stable Diffusion.
## Features
[Detailed feature showcase with images](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Features):
- Original txt2img and img2img modes
- One click install and run script (but you still must install python and git)
- Outpainting
- Inpainting
- Color Sketch
- Prompt Matrix
- Stable Diffusion Upscale
- Attention, specify parts of text that the model should pay more attention to
- a man in a `((tuxedo))` - will pay more attention to tuxedo
- a man in a `(tuxedo:1.21)` - alternative syntax
- select text and press `Ctrl+Up` or `Ctrl+Down` (or `Command+Up` or `Command+Down` if you're on a MacOS) to automatically adjust attention to selected text (code contributed by anonymous user)
- Loopback, run img2img processing multiple times
- X/Y/Z plot, a way to draw a 3 dimensional plot of images with different parameters
- Textual Inversion
- have as many embeddings as you want and use any names you like for them
- use multiple embeddings with different numbers of vectors per token
- works with half precision floating point numbers
- train embeddings on 8GB (also reports of 6GB working)
- Extras tab with:
- GFPGAN, neural network that fixes faces
- CodeFormer, face restoration tool as an alternative to GFPGAN
- RealESRGAN, neural network upscaler
- ESRGAN, neural network upscaler with a lot of third party models
- SwinIR and Swin2SR ([see here](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/2092)), neural network upscalers
- LDSR, Latent diffusion super resolution upscaling
- Resizing aspect ratio options
- Sampling method selection
- Adjust sampler eta values (noise multiplier)
- More advanced noise setting options
- Interrupt processing at any time
- 4GB video card support (also reports of 2GB working)
- Correct seeds for batches
- Live prompt token length validation
- Generation parameters
- parameters you used to generate images are saved with that image
- in PNG chunks for PNG, in EXIF for JPEG
- can drag the image to PNG info tab to restore generation parameters and automatically copy them into UI
- can be disabled in settings
- drag and drop an image/text-parameters to promptbox
- Read Generation Parameters Button, loads parameters in promptbox to UI
- Settings page
- Running arbitrary python code from UI (must run with `--allow-code` to enable)
- Mouseover hints for most UI elements
- Possible to change defaults/mix/max/step values for UI elements via text config
- Tiling support, a checkbox to create images that can be tiled like textures
- Progress bar and live image generation preview
- Can use a separate neural network to produce previews with almost none VRAM or compute requirement
- Negative prompt, an extra text field that allows you to list what you don't want to see in generated image
- Styles, a way to save part of prompt and easily apply them via dropdown later
- Variations, a way to generate same image but with tiny differences
- Seed resizing, a way to generate same image but at slightly different resolution
- CLIP interrogator, a button that tries to guess prompt from an image
- Prompt Editing, a way to change prompt mid-generation, say to start making a watermelon and switch to anime girl midway
- Batch Processing, process a group of files using img2img
- Img2img Alternative, reverse Euler method of cross attention control
- Highres Fix, a convenience option to produce high resolution pictures in one click without usual distortions
- Reloading checkpoints on the fly
- Checkpoint Merger, a tab that allows you to merge up to 3 checkpoints into one
- [Custom scripts](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Custom-Scripts) with many extensions from community
- [Composable-Diffusion](https://energy-based-model.github.io/Compositional-Visual-Generation-with-Composable-Diffusion-Models/), a way to use multiple prompts at once
- separate prompts using uppercase `AND`
- also supports weights for prompts: `a cat :1.2 AND a dog AND a penguin :2.2`
- No token limit for prompts (original stable diffusion lets you use up to 75 tokens)
- DeepDanbooru integration, creates danbooru style tags for anime prompts
- [xformers](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Xformers), major speed increase for select cards: (add `--xformers` to commandline args)
- via extension: [History tab](https://github.com/yfszzx/stable-diffusion-webui-images-browser): view, direct and delete images conveniently within the UI
- Generate forever option
- Training tab
- hypernetworks and embeddings options
- Preprocessing images: cropping, mirroring, autotagging using BLIP or deepdanbooru (for anime)
- Clip skip
- Hypernetworks
- Loras (same as Hypernetworks but more pretty)
- A separate UI where you can choose, with preview, which embeddings, hypernetworks or Loras to add to your prompt
- Can select to load a different VAE from settings screen
- Estimated completion time in progress bar
- API
- Support for dedicated [inpainting model](https://github.com/runwayml/stable-diffusion#inpainting-with-stable-diffusion) by RunwayML
- via extension: [Aesthetic Gradients](https://github.com/AUTOMATIC1111/stable-diffusion-webui-aesthetic-gradients), a way to generate images with a specific aesthetic by using clip images embeds (implementation of [https://github.com/vicgalle/stable-diffusion-aesthetic-gradients](https://github.com/vicgalle/stable-diffusion-aesthetic-gradients))
- [Stable Diffusion 2.0](https://github.com/Stability-AI/stablediffusion) support - see [wiki](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Features#stable-diffusion-20) for instructions
- [Alt-Diffusion](https://arxiv.org/abs/2211.06679) support - see [wiki](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Features#alt-diffusion) for instructions
- Now without any bad letters!
- Load checkpoints in safetensors format
- Eased resolution restriction: generated image's dimensions must be a multiple of 8 rather than 64
- Now with a license!
- Reorder elements in the UI from settings screen
- [Segmind Stable Diffusion](https://huggingface.co/segmind/SSD-1B) support
## Installation and Running
Make sure the required [dependencies](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Dependencies) are met and follow the instructions available for:
- [NVidia](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Install-and-Run-on-NVidia-GPUs) (recommended)
- [AMD](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Install-and-Run-on-AMD-GPUs) GPUs.
- [Intel CPUs, Intel GPUs (both integrated and discrete)](https://github.com/openvinotoolkit/stable-diffusion-webui/wiki/Installation-on-Intel-Silicon) (external wiki page)
Alternatively, use online services (like Google Colab):
- [List of Online Services](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Online-Services)
### Installation on Windows 10/11 with NVidia-GPUs using release package
1. Download `sd.webui.zip` from [v1.0.0-pre](https://github.com/AUTOMATIC1111/stable-diffusion-webui/releases/tag/v1.0.0-pre) and extract its contents.
2. Run `update.bat`.
3. Run `run.bat`.
> For more details see [Install-and-Run-on-NVidia-GPUs](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Install-and-Run-on-NVidia-GPUs)
### Automatic Installation on Windows
1. Install [Python 3.10.6](https://www.python.org/downloads/release/python-3106/) (Newer version of Python does not support torch), checking "Add Python to PATH".
2. Install [git](https://git-scm.com/download/win).
3. Download the stable-diffusion-webui repository, for example by running `git clone https://github.com/AUTOMATIC1111/stable-diffusion-webui.git`.
4. Run `webui-user.bat` from Windows Explorer as normal, non-administrator, user.
### Automatic Installation on Linux
1. Install the dependencies:
```bash
# Debian-based:
sudo apt install wget git python3 python3-venv libgl1 libglib2.0-0
# Red Hat-based:
sudo dnf install wget git python3 gperftools-libs libglvnd-glx
# openSUSE-based:
sudo zypper install wget git python3 libtcmalloc4 libglvnd
# Arch-based:
sudo pacman -S wget git python3
```
2. Navigate to the directory you would like the webui to be installed and execute the following command:
```bash
wget -q https://raw.githubusercontent.com/AUTOMATIC1111/stable-diffusion-webui/master/webui.sh
```
3. Run `webui.sh`.
4. Check `webui-user.sh` for options.
### Installation on Apple Silicon
Find the instructions [here](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Installation-on-Apple-Silicon).
## Contributing
Here's how to add code to this repo: [Contributing](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Contributing)
## Documentation
The documentation was moved from this README over to the project's [wiki](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki).
For the purposes of getting Google and other search engines to crawl the wiki, here's a link to the (not for humans) [crawlable wiki](https://github-wiki-see.page/m/AUTOMATIC1111/stable-diffusion-webui/wiki).
## Credits
Licenses for borrowed code can be found in `Settings -> Licenses` screen, and also in `html/licenses.html` file.
- Stable Diffusion - https://github.com/Stability-AI/stablediffusion, https://github.com/CompVis/taming-transformers
- k-diffusion - https://github.com/crowsonkb/k-diffusion.git
- GFPGAN - https://github.com/TencentARC/GFPGAN.git
- CodeFormer - https://github.com/sczhou/CodeFormer
- ESRGAN - https://github.com/xinntao/ESRGAN
- SwinIR - https://github.com/JingyunLiang/SwinIR
- Swin2SR - https://github.com/mv-lab/swin2sr
- LDSR - https://github.com/Hafiidz/latent-diffusion
- MiDaS - https://github.com/isl-org/MiDaS
- Ideas for optimizations - https://github.com/basujindal/stable-diffusion
- Cross Attention layer optimization - Doggettx - https://github.com/Doggettx/stable-diffusion, original idea for prompt editing.
- Cross Attention layer optimization - InvokeAI, lstein - https://github.com/invoke-ai/InvokeAI (originally http://github.com/lstein/stable-diffusion)
- Sub-quadratic Cross Attention layer optimization - Alex Birch (https://github.com/Birch-san/diffusers/pull/1), Amin Rezaei (https://github.com/AminRezaei0x443/memory-efficient-attention)
- Textual Inversion - Rinon Gal - https://github.com/rinongal/textual_inversion (we're not using his code, but we are using his ideas).
- Idea for SD upscale - https://github.com/jquesnelle/txt2imghd
- Noise generation for outpainting mk2 - https://github.com/parlance-zz/g-diffuser-bot
- CLIP interrogator idea and borrowing some code - https://github.com/pharmapsychotic/clip-interrogator
- Idea for Composable Diffusion - https://github.com/energy-based-model/Compositional-Visual-Generation-with-Composable-Diffusion-Models-PyTorch
- xformers - https://github.com/facebookresearch/xformers
- DeepDanbooru - interrogator for anime diffusers https://github.com/KichangKim/DeepDanbooru
- Sampling in float32 precision from a float16 UNet - marunine for the idea, Birch-san for the example Diffusers implementation (https://github.com/Birch-san/diffusers-play/tree/92feee6)
- Instruct pix2pix - Tim Brooks (star), Aleksander Holynski (star), Alexei A. Efros (no star) - https://github.com/timothybrooks/instruct-pix2pix
- Security advice - RyotaK
- UniPC sampler - Wenliang Zhao - https://github.com/wl-zhao/UniPC
- TAESD - Ollin Boer Bohan - https://github.com/madebyollin/taesd
- LyCORIS - KohakuBlueleaf
- Restart sampling - lambertae - https://github.com/Newbeeer/diffusion_restart_sampling
- Hypertile - tfernd - https://github.com/tfernd/HyperTile
- Initial Gradio script - posted on 4chan by an Anonymous user. Thank you Anonymous user.
- (You)
| {} | eddiesmith/eddieweb | null | [
"arxiv:2211.06679",
"region:us"
] | null | 2024-04-19T17:15:55+00:00 | [
"2211.06679"
] | [] | TAGS
#arxiv-2211.06679 #region-us
| # Stable Diffusion web UI
A browser interface based on Gradio library for Stable Diffusion.
## Features
Detailed feature showcase with images:
- Original txt2img and img2img modes
- One click install and run script (but you still must install python and git)
- Outpainting
- Inpainting
- Color Sketch
- Prompt Matrix
- Stable Diffusion Upscale
- Attention, specify parts of text that the model should pay more attention to
- a man in a '((tuxedo))' - will pay more attention to tuxedo
- a man in a '(tuxedo:1.21)' - alternative syntax
- select text and press 'Ctrl+Up' or 'Ctrl+Down' (or 'Command+Up' or 'Command+Down' if you're on a MacOS) to automatically adjust attention to selected text (code contributed by anonymous user)
- Loopback, run img2img processing multiple times
- X/Y/Z plot, a way to draw a 3 dimensional plot of images with different parameters
- Textual Inversion
- have as many embeddings as you want and use any names you like for them
- use multiple embeddings with different numbers of vectors per token
- works with half precision floating point numbers
- train embeddings on 8GB (also reports of 6GB working)
- Extras tab with:
- GFPGAN, neural network that fixes faces
- CodeFormer, face restoration tool as an alternative to GFPGAN
- RealESRGAN, neural network upscaler
- ESRGAN, neural network upscaler with a lot of third party models
- SwinIR and Swin2SR (see here), neural network upscalers
- LDSR, Latent diffusion super resolution upscaling
- Resizing aspect ratio options
- Sampling method selection
- Adjust sampler eta values (noise multiplier)
- More advanced noise setting options
- Interrupt processing at any time
- 4GB video card support (also reports of 2GB working)
- Correct seeds for batches
- Live prompt token length validation
- Generation parameters
- parameters you used to generate images are saved with that image
- in PNG chunks for PNG, in EXIF for JPEG
- can drag the image to PNG info tab to restore generation parameters and automatically copy them into UI
- can be disabled in settings
- drag and drop an image/text-parameters to promptbox
- Read Generation Parameters Button, loads parameters in promptbox to UI
- Settings page
- Running arbitrary python code from UI (must run with '--allow-code' to enable)
- Mouseover hints for most UI elements
- Possible to change defaults/mix/max/step values for UI elements via text config
- Tiling support, a checkbox to create images that can be tiled like textures
- Progress bar and live image generation preview
- Can use a separate neural network to produce previews with almost none VRAM or compute requirement
- Negative prompt, an extra text field that allows you to list what you don't want to see in generated image
- Styles, a way to save part of prompt and easily apply them via dropdown later
- Variations, a way to generate same image but with tiny differences
- Seed resizing, a way to generate same image but at slightly different resolution
- CLIP interrogator, a button that tries to guess prompt from an image
- Prompt Editing, a way to change prompt mid-generation, say to start making a watermelon and switch to anime girl midway
- Batch Processing, process a group of files using img2img
- Img2img Alternative, reverse Euler method of cross attention control
- Highres Fix, a convenience option to produce high resolution pictures in one click without usual distortions
- Reloading checkpoints on the fly
- Checkpoint Merger, a tab that allows you to merge up to 3 checkpoints into one
- Custom scripts with many extensions from community
- Composable-Diffusion, a way to use multiple prompts at once
- separate prompts using uppercase 'AND'
- also supports weights for prompts: 'a cat :1.2 AND a dog AND a penguin :2.2'
- No token limit for prompts (original stable diffusion lets you use up to 75 tokens)
- DeepDanbooru integration, creates danbooru style tags for anime prompts
- xformers, major speed increase for select cards: (add '--xformers' to commandline args)
- via extension: History tab: view, direct and delete images conveniently within the UI
- Generate forever option
- Training tab
- hypernetworks and embeddings options
- Preprocessing images: cropping, mirroring, autotagging using BLIP or deepdanbooru (for anime)
- Clip skip
- Hypernetworks
- Loras (same as Hypernetworks but more pretty)
- A separate UI where you can choose, with preview, which embeddings, hypernetworks or Loras to add to your prompt
- Can select to load a different VAE from settings screen
- Estimated completion time in progress bar
- API
- Support for dedicated inpainting model by RunwayML
- via extension: Aesthetic Gradients, a way to generate images with a specific aesthetic by using clip images embeds (implementation of URL
- Stable Diffusion 2.0 support - see wiki for instructions
- Alt-Diffusion support - see wiki for instructions
- Now without any bad letters!
- Load checkpoints in safetensors format
- Eased resolution restriction: generated image's dimensions must be a multiple of 8 rather than 64
- Now with a license!
- Reorder elements in the UI from settings screen
- Segmind Stable Diffusion support
## Installation and Running
Make sure the required dependencies are met and follow the instructions available for:
- NVidia (recommended)
- AMD GPUs.
- Intel CPUs, Intel GPUs (both integrated and discrete) (external wiki page)
Alternatively, use online services (like Google Colab):
- List of Online Services
### Installation on Windows 10/11 with NVidia-GPUs using release package
1. Download 'URL' from v1.0.0-pre and extract its contents.
2. Run 'URL'.
3. Run 'URL'.
> For more details see Install-and-Run-on-NVidia-GPUs
### Automatic Installation on Windows
1. Install Python 3.10.6 (Newer version of Python does not support torch), checking "Add Python to PATH".
2. Install git.
3. Download the stable-diffusion-webui repository, for example by running 'git clone URL
4. Run 'URL' from Windows Explorer as normal, non-administrator, user.
### Automatic Installation on Linux
1. Install the dependencies:
2. Navigate to the directory you would like the webui to be installed and execute the following command:
3. Run 'URL'.
4. Check 'URL' for options.
### Installation on Apple Silicon
Find the instructions here.
## Contributing
Here's how to add code to this repo: Contributing
## Documentation
The documentation was moved from this README over to the project's wiki.
For the purposes of getting Google and other search engines to crawl the wiki, here's a link to the (not for humans) crawlable wiki.
## Credits
Licenses for borrowed code can be found in 'Settings -> Licenses' screen, and also in 'html/URL' file.
- Stable Diffusion - URL URL
- k-diffusion - URL
- GFPGAN - URL
- CodeFormer - URL
- ESRGAN - URL
- SwinIR - URL
- Swin2SR - URL
- LDSR - URL
- MiDaS - URL
- Ideas for optimizations - URL
- Cross Attention layer optimization - Doggettx - URL original idea for prompt editing.
- Cross Attention layer optimization - InvokeAI, lstein - URL (originally URL
- Sub-quadratic Cross Attention layer optimization - Alex Birch (URL Amin Rezaei (URL
- Textual Inversion - Rinon Gal - URL (we're not using his code, but we are using his ideas).
- Idea for SD upscale - URL
- Noise generation for outpainting mk2 - URL
- CLIP interrogator idea and borrowing some code - URL
- Idea for Composable Diffusion - URL
- xformers - URL
- DeepDanbooru - interrogator for anime diffusers URL
- Sampling in float32 precision from a float16 UNet - marunine for the idea, Birch-san for the example Diffusers implementation (URL
- Instruct pix2pix - Tim Brooks (star), Aleksander Holynski (star), Alexei A. Efros (no star) - URL
- Security advice - RyotaK
- UniPC sampler - Wenliang Zhao - URL
- TAESD - Ollin Boer Bohan - URL
- LyCORIS - KohakuBlueleaf
- Restart sampling - lambertae - URL
- Hypertile - tfernd - URL
- Initial Gradio script - posted on 4chan by an Anonymous user. Thank you Anonymous user.
- (You)
| [
"# Stable Diffusion web UI\nA browser interface based on Gradio library for Stable Diffusion.\n\n",
"## Features\nDetailed feature showcase with images:\n- Original txt2img and img2img modes\n- One click install and run script (but you still must install python and git)\n- Outpainting\n- Inpainting\n- Color Sketch\n- Prompt Matrix\n- Stable Diffusion Upscale\n- Attention, specify parts of text that the model should pay more attention to\n - a man in a '((tuxedo))' - will pay more attention to tuxedo\n - a man in a '(tuxedo:1.21)' - alternative syntax\n - select text and press 'Ctrl+Up' or 'Ctrl+Down' (or 'Command+Up' or 'Command+Down' if you're on a MacOS) to automatically adjust attention to selected text (code contributed by anonymous user)\n- Loopback, run img2img processing multiple times\n- X/Y/Z plot, a way to draw a 3 dimensional plot of images with different parameters\n- Textual Inversion\n - have as many embeddings as you want and use any names you like for them\n - use multiple embeddings with different numbers of vectors per token\n - works with half precision floating point numbers\n - train embeddings on 8GB (also reports of 6GB working)\n- Extras tab with:\n - GFPGAN, neural network that fixes faces\n - CodeFormer, face restoration tool as an alternative to GFPGAN\n - RealESRGAN, neural network upscaler\n - ESRGAN, neural network upscaler with a lot of third party models\n - SwinIR and Swin2SR (see here), neural network upscalers\n - LDSR, Latent diffusion super resolution upscaling\n- Resizing aspect ratio options\n- Sampling method selection\n - Adjust sampler eta values (noise multiplier)\n - More advanced noise setting options\n- Interrupt processing at any time\n- 4GB video card support (also reports of 2GB working)\n- Correct seeds for batches\n- Live prompt token length validation\n- Generation parameters\n - parameters you used to generate images are saved with that image\n - in PNG chunks for PNG, in EXIF for JPEG\n - can drag the image to PNG info tab to restore generation parameters and automatically copy them into UI\n - can be disabled in settings\n - drag and drop an image/text-parameters to promptbox\n- Read Generation Parameters Button, loads parameters in promptbox to UI\n- Settings page\n- Running arbitrary python code from UI (must run with '--allow-code' to enable)\n- Mouseover hints for most UI elements\n- Possible to change defaults/mix/max/step values for UI elements via text config\n- Tiling support, a checkbox to create images that can be tiled like textures\n- Progress bar and live image generation preview\n - Can use a separate neural network to produce previews with almost none VRAM or compute requirement\n- Negative prompt, an extra text field that allows you to list what you don't want to see in generated image\n- Styles, a way to save part of prompt and easily apply them via dropdown later\n- Variations, a way to generate same image but with tiny differences\n- Seed resizing, a way to generate same image but at slightly different resolution\n- CLIP interrogator, a button that tries to guess prompt from an image\n- Prompt Editing, a way to change prompt mid-generation, say to start making a watermelon and switch to anime girl midway\n- Batch Processing, process a group of files using img2img\n- Img2img Alternative, reverse Euler method of cross attention control\n- Highres Fix, a convenience option to produce high resolution pictures in one click without usual distortions\n- Reloading checkpoints on the fly\n- Checkpoint Merger, a tab that allows you to merge up to 3 checkpoints into one\n- Custom scripts with many extensions from community\n- Composable-Diffusion, a way to use multiple prompts at once\n - separate prompts using uppercase 'AND'\n - also supports weights for prompts: 'a cat :1.2 AND a dog AND a penguin :2.2'\n- No token limit for prompts (original stable diffusion lets you use up to 75 tokens)\n- DeepDanbooru integration, creates danbooru style tags for anime prompts\n- xformers, major speed increase for select cards: (add '--xformers' to commandline args)\n- via extension: History tab: view, direct and delete images conveniently within the UI\n- Generate forever option\n- Training tab\n - hypernetworks and embeddings options\n - Preprocessing images: cropping, mirroring, autotagging using BLIP or deepdanbooru (for anime)\n- Clip skip\n- Hypernetworks\n- Loras (same as Hypernetworks but more pretty)\n- A separate UI where you can choose, with preview, which embeddings, hypernetworks or Loras to add to your prompt \n- Can select to load a different VAE from settings screen\n- Estimated completion time in progress bar\n- API\n- Support for dedicated inpainting model by RunwayML\n- via extension: Aesthetic Gradients, a way to generate images with a specific aesthetic by using clip images embeds (implementation of URL\n- Stable Diffusion 2.0 support - see wiki for instructions\n- Alt-Diffusion support - see wiki for instructions\n- Now without any bad letters!\n- Load checkpoints in safetensors format\n- Eased resolution restriction: generated image's dimensions must be a multiple of 8 rather than 64\n- Now with a license!\n- Reorder elements in the UI from settings screen\n- Segmind Stable Diffusion support",
"## Installation and Running\nMake sure the required dependencies are met and follow the instructions available for:\n- NVidia (recommended)\n- AMD GPUs.\n- Intel CPUs, Intel GPUs (both integrated and discrete) (external wiki page)\n\nAlternatively, use online services (like Google Colab):\n\n- List of Online Services",
"### Installation on Windows 10/11 with NVidia-GPUs using release package\n1. Download 'URL' from v1.0.0-pre and extract its contents.\n2. Run 'URL'.\n3. Run 'URL'.\n> For more details see Install-and-Run-on-NVidia-GPUs",
"### Automatic Installation on Windows\n1. Install Python 3.10.6 (Newer version of Python does not support torch), checking \"Add Python to PATH\".\n2. Install git.\n3. Download the stable-diffusion-webui repository, for example by running 'git clone URL\n4. Run 'URL' from Windows Explorer as normal, non-administrator, user.",
"### Automatic Installation on Linux\n1. Install the dependencies:\n\n2. Navigate to the directory you would like the webui to be installed and execute the following command:\n\n3. Run 'URL'.\n4. Check 'URL' for options.",
"### Installation on Apple Silicon\n\nFind the instructions here.",
"## Contributing\nHere's how to add code to this repo: Contributing",
"## Documentation\n\nThe documentation was moved from this README over to the project's wiki.\n\nFor the purposes of getting Google and other search engines to crawl the wiki, here's a link to the (not for humans) crawlable wiki.",
"## Credits\nLicenses for borrowed code can be found in 'Settings -> Licenses' screen, and also in 'html/URL' file.\n\n- Stable Diffusion - URL URL\n- k-diffusion - URL\n- GFPGAN - URL\n- CodeFormer - URL\n- ESRGAN - URL\n- SwinIR - URL\n- Swin2SR - URL\n- LDSR - URL\n- MiDaS - URL\n- Ideas for optimizations - URL\n- Cross Attention layer optimization - Doggettx - URL original idea for prompt editing.\n- Cross Attention layer optimization - InvokeAI, lstein - URL (originally URL\n- Sub-quadratic Cross Attention layer optimization - Alex Birch (URL Amin Rezaei (URL\n- Textual Inversion - Rinon Gal - URL (we're not using his code, but we are using his ideas).\n- Idea for SD upscale - URL\n- Noise generation for outpainting mk2 - URL\n- CLIP interrogator idea and borrowing some code - URL\n- Idea for Composable Diffusion - URL\n- xformers - URL\n- DeepDanbooru - interrogator for anime diffusers URL\n- Sampling in float32 precision from a float16 UNet - marunine for the idea, Birch-san for the example Diffusers implementation (URL\n- Instruct pix2pix - Tim Brooks (star), Aleksander Holynski (star), Alexei A. Efros (no star) - URL\n- Security advice - RyotaK\n- UniPC sampler - Wenliang Zhao - URL\n- TAESD - Ollin Boer Bohan - URL\n- LyCORIS - KohakuBlueleaf\n- Restart sampling - lambertae - URL\n- Hypertile - tfernd - URL\n- Initial Gradio script - posted on 4chan by an Anonymous user. Thank you Anonymous user.\n- (You)"
] | [
"TAGS\n#arxiv-2211.06679 #region-us \n",
"# Stable Diffusion web UI\nA browser interface based on Gradio library for Stable Diffusion.\n\n",
"## Features\nDetailed feature showcase with images:\n- Original txt2img and img2img modes\n- One click install and run script (but you still must install python and git)\n- Outpainting\n- Inpainting\n- Color Sketch\n- Prompt Matrix\n- Stable Diffusion Upscale\n- Attention, specify parts of text that the model should pay more attention to\n - a man in a '((tuxedo))' - will pay more attention to tuxedo\n - a man in a '(tuxedo:1.21)' - alternative syntax\n - select text and press 'Ctrl+Up' or 'Ctrl+Down' (or 'Command+Up' or 'Command+Down' if you're on a MacOS) to automatically adjust attention to selected text (code contributed by anonymous user)\n- Loopback, run img2img processing multiple times\n- X/Y/Z plot, a way to draw a 3 dimensional plot of images with different parameters\n- Textual Inversion\n - have as many embeddings as you want and use any names you like for them\n - use multiple embeddings with different numbers of vectors per token\n - works with half precision floating point numbers\n - train embeddings on 8GB (also reports of 6GB working)\n- Extras tab with:\n - GFPGAN, neural network that fixes faces\n - CodeFormer, face restoration tool as an alternative to GFPGAN\n - RealESRGAN, neural network upscaler\n - ESRGAN, neural network upscaler with a lot of third party models\n - SwinIR and Swin2SR (see here), neural network upscalers\n - LDSR, Latent diffusion super resolution upscaling\n- Resizing aspect ratio options\n- Sampling method selection\n - Adjust sampler eta values (noise multiplier)\n - More advanced noise setting options\n- Interrupt processing at any time\n- 4GB video card support (also reports of 2GB working)\n- Correct seeds for batches\n- Live prompt token length validation\n- Generation parameters\n - parameters you used to generate images are saved with that image\n - in PNG chunks for PNG, in EXIF for JPEG\n - can drag the image to PNG info tab to restore generation parameters and automatically copy them into UI\n - can be disabled in settings\n - drag and drop an image/text-parameters to promptbox\n- Read Generation Parameters Button, loads parameters in promptbox to UI\n- Settings page\n- Running arbitrary python code from UI (must run with '--allow-code' to enable)\n- Mouseover hints for most UI elements\n- Possible to change defaults/mix/max/step values for UI elements via text config\n- Tiling support, a checkbox to create images that can be tiled like textures\n- Progress bar and live image generation preview\n - Can use a separate neural network to produce previews with almost none VRAM or compute requirement\n- Negative prompt, an extra text field that allows you to list what you don't want to see in generated image\n- Styles, a way to save part of prompt and easily apply them via dropdown later\n- Variations, a way to generate same image but with tiny differences\n- Seed resizing, a way to generate same image but at slightly different resolution\n- CLIP interrogator, a button that tries to guess prompt from an image\n- Prompt Editing, a way to change prompt mid-generation, say to start making a watermelon and switch to anime girl midway\n- Batch Processing, process a group of files using img2img\n- Img2img Alternative, reverse Euler method of cross attention control\n- Highres Fix, a convenience option to produce high resolution pictures in one click without usual distortions\n- Reloading checkpoints on the fly\n- Checkpoint Merger, a tab that allows you to merge up to 3 checkpoints into one\n- Custom scripts with many extensions from community\n- Composable-Diffusion, a way to use multiple prompts at once\n - separate prompts using uppercase 'AND'\n - also supports weights for prompts: 'a cat :1.2 AND a dog AND a penguin :2.2'\n- No token limit for prompts (original stable diffusion lets you use up to 75 tokens)\n- DeepDanbooru integration, creates danbooru style tags for anime prompts\n- xformers, major speed increase for select cards: (add '--xformers' to commandline args)\n- via extension: History tab: view, direct and delete images conveniently within the UI\n- Generate forever option\n- Training tab\n - hypernetworks and embeddings options\n - Preprocessing images: cropping, mirroring, autotagging using BLIP or deepdanbooru (for anime)\n- Clip skip\n- Hypernetworks\n- Loras (same as Hypernetworks but more pretty)\n- A separate UI where you can choose, with preview, which embeddings, hypernetworks or Loras to add to your prompt \n- Can select to load a different VAE from settings screen\n- Estimated completion time in progress bar\n- API\n- Support for dedicated inpainting model by RunwayML\n- via extension: Aesthetic Gradients, a way to generate images with a specific aesthetic by using clip images embeds (implementation of URL\n- Stable Diffusion 2.0 support - see wiki for instructions\n- Alt-Diffusion support - see wiki for instructions\n- Now without any bad letters!\n- Load checkpoints in safetensors format\n- Eased resolution restriction: generated image's dimensions must be a multiple of 8 rather than 64\n- Now with a license!\n- Reorder elements in the UI from settings screen\n- Segmind Stable Diffusion support",
"## Installation and Running\nMake sure the required dependencies are met and follow the instructions available for:\n- NVidia (recommended)\n- AMD GPUs.\n- Intel CPUs, Intel GPUs (both integrated and discrete) (external wiki page)\n\nAlternatively, use online services (like Google Colab):\n\n- List of Online Services",
"### Installation on Windows 10/11 with NVidia-GPUs using release package\n1. Download 'URL' from v1.0.0-pre and extract its contents.\n2. Run 'URL'.\n3. Run 'URL'.\n> For more details see Install-and-Run-on-NVidia-GPUs",
"### Automatic Installation on Windows\n1. Install Python 3.10.6 (Newer version of Python does not support torch), checking \"Add Python to PATH\".\n2. Install git.\n3. Download the stable-diffusion-webui repository, for example by running 'git clone URL\n4. Run 'URL' from Windows Explorer as normal, non-administrator, user.",
"### Automatic Installation on Linux\n1. Install the dependencies:\n\n2. Navigate to the directory you would like the webui to be installed and execute the following command:\n\n3. Run 'URL'.\n4. Check 'URL' for options.",
"### Installation on Apple Silicon\n\nFind the instructions here.",
"## Contributing\nHere's how to add code to this repo: Contributing",
"## Documentation\n\nThe documentation was moved from this README over to the project's wiki.\n\nFor the purposes of getting Google and other search engines to crawl the wiki, here's a link to the (not for humans) crawlable wiki.",
"## Credits\nLicenses for borrowed code can be found in 'Settings -> Licenses' screen, and also in 'html/URL' file.\n\n- Stable Diffusion - URL URL\n- k-diffusion - URL\n- GFPGAN - URL\n- CodeFormer - URL\n- ESRGAN - URL\n- SwinIR - URL\n- Swin2SR - URL\n- LDSR - URL\n- MiDaS - URL\n- Ideas for optimizations - URL\n- Cross Attention layer optimization - Doggettx - URL original idea for prompt editing.\n- Cross Attention layer optimization - InvokeAI, lstein - URL (originally URL\n- Sub-quadratic Cross Attention layer optimization - Alex Birch (URL Amin Rezaei (URL\n- Textual Inversion - Rinon Gal - URL (we're not using his code, but we are using his ideas).\n- Idea for SD upscale - URL\n- Noise generation for outpainting mk2 - URL\n- CLIP interrogator idea and borrowing some code - URL\n- Idea for Composable Diffusion - URL\n- xformers - URL\n- DeepDanbooru - interrogator for anime diffusers URL\n- Sampling in float32 precision from a float16 UNet - marunine for the idea, Birch-san for the example Diffusers implementation (URL\n- Instruct pix2pix - Tim Brooks (star), Aleksander Holynski (star), Alexei A. Efros (no star) - URL\n- Security advice - RyotaK\n- UniPC sampler - Wenliang Zhao - URL\n- TAESD - Ollin Boer Bohan - URL\n- LyCORIS - KohakuBlueleaf\n- Restart sampling - lambertae - URL\n- Hypertile - tfernd - URL\n- Initial Gradio script - posted on 4chan by an Anonymous user. Thank you Anonymous user.\n- (You)"
] |
automatic-speech-recognition | transformers |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# whisper-medium-ga2en-v3
This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on an unknown dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0001
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 0.03
- training_steps: 2000
- mixed_precision_training: Native AMP
### Framework versions
- Transformers 4.40.0
- Pytorch 2.0.1+cu118
- Datasets 2.19.0
- Tokenizers 0.19.1
| {"license": "apache-2.0", "tags": ["generated_from_trainer"], "base_model": "openai/whisper-medium", "model-index": [{"name": "whisper-medium-ga2en-v3", "results": []}]} | ymoslem/whisper-medium-ga2en-v3 | null | [
"transformers",
"tensorboard",
"safetensors",
"whisper",
"automatic-speech-recognition",
"generated_from_trainer",
"base_model:openai/whisper-medium",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | 2024-04-19T17:18:37+00:00 | [] | [] | TAGS
#transformers #tensorboard #safetensors #whisper #automatic-speech-recognition #generated_from_trainer #base_model-openai/whisper-medium #license-apache-2.0 #endpoints_compatible #region-us
|
# whisper-medium-ga2en-v3
This model is a fine-tuned version of openai/whisper-medium on an unknown dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0001
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 0.03
- training_steps: 2000
- mixed_precision_training: Native AMP
### Framework versions
- Transformers 4.40.0
- Pytorch 2.0.1+cu118
- Datasets 2.19.0
- Tokenizers 0.19.1
| [
"# whisper-medium-ga2en-v3\n\nThis model is a fine-tuned version of openai/whisper-medium on an unknown dataset.",
"## Model description\n\nMore information needed",
"## Intended uses & limitations\n\nMore information needed",
"## Training and evaluation data\n\nMore information needed",
"## Training procedure",
"### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 0.0001\n- train_batch_size: 8\n- eval_batch_size: 8\n- seed: 42\n- gradient_accumulation_steps: 2\n- total_train_batch_size: 16\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- lr_scheduler_warmup_steps: 0.03\n- training_steps: 2000\n- mixed_precision_training: Native AMP",
"### Framework versions\n\n- Transformers 4.40.0\n- Pytorch 2.0.1+cu118\n- Datasets 2.19.0\n- Tokenizers 0.19.1"
] | [
"TAGS\n#transformers #tensorboard #safetensors #whisper #automatic-speech-recognition #generated_from_trainer #base_model-openai/whisper-medium #license-apache-2.0 #endpoints_compatible #region-us \n",
"# whisper-medium-ga2en-v3\n\nThis model is a fine-tuned version of openai/whisper-medium on an unknown dataset.",
"## Model description\n\nMore information needed",
"## Intended uses & limitations\n\nMore information needed",
"## Training and evaluation data\n\nMore information needed",
"## Training procedure",
"### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 0.0001\n- train_batch_size: 8\n- eval_batch_size: 8\n- seed: 42\n- gradient_accumulation_steps: 2\n- total_train_batch_size: 16\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- lr_scheduler_warmup_steps: 0.03\n- training_steps: 2000\n- mixed_precision_training: Native AMP",
"### Framework versions\n\n- Transformers 4.40.0\n- Pytorch 2.0.1+cu118\n- Datasets 2.19.0\n- Tokenizers 0.19.1"
] |
null | null |
# Yamshadowexperiment28Multi_verse_model-7B
Yamshadowexperiment28Multi_verse_model-7B is an automated merge created by [Maxime Labonne](https://huggingface.co/mlabonne) using the following configuration.
* [automerger/YamshadowExperiment28-7B](https://huggingface.co/automerger/YamshadowExperiment28-7B)
* [MTSAIR/multi_verse_model](https://huggingface.co/MTSAIR/multi_verse_model)
## 🧩 Configuration
```yaml
slices:
- sources:
- model: automerger/YamshadowExperiment28-7B
layer_range: [0, 32]
- model: MTSAIR/multi_verse_model
layer_range: [0, 32]
merge_method: slerp
base_model: automerger/YamshadowExperiment28-7B
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: bfloat16
random_seed: 0
```
## 💻 Usage
```python
!pip install -qU transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "automerger/Yamshadowexperiment28Multi_verse_model-7B"
messages = [{"role": "user", "content": "What is a large language model?"}]
tokenizer = AutoTokenizer.from_pretrained(model)
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
pipeline = transformers.pipeline(
"text-generation",
model=model,
torch_dtype=torch.float16,
device_map="auto",
)
outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])
``` | {"license": "apache-2.0", "tags": ["merge", "mergekit", "lazymergekit", "automerger"], "base_model": ["automerger/YamshadowExperiment28-7B", "MTSAIR/multi_verse_model"]} | automerger/Yamshadowexperiment28Multi_verse_model-7B | null | [
"merge",
"mergekit",
"lazymergekit",
"automerger",
"base_model:automerger/YamshadowExperiment28-7B",
"base_model:MTSAIR/multi_verse_model",
"license:apache-2.0",
"region:us"
] | null | 2024-04-19T17:20:53+00:00 | [] | [] | TAGS
#merge #mergekit #lazymergekit #automerger #base_model-automerger/YamshadowExperiment28-7B #base_model-MTSAIR/multi_verse_model #license-apache-2.0 #region-us
|
# Yamshadowexperiment28Multi_verse_model-7B
Yamshadowexperiment28Multi_verse_model-7B is an automated merge created by Maxime Labonne using the following configuration.
* automerger/YamshadowExperiment28-7B
* MTSAIR/multi_verse_model
## Configuration
## Usage
| [
"# Yamshadowexperiment28Multi_verse_model-7B\n\nYamshadowexperiment28Multi_verse_model-7B is an automated merge created by Maxime Labonne using the following configuration.\n* automerger/YamshadowExperiment28-7B\n* MTSAIR/multi_verse_model",
"## Configuration",
"## Usage"
] | [
"TAGS\n#merge #mergekit #lazymergekit #automerger #base_model-automerger/YamshadowExperiment28-7B #base_model-MTSAIR/multi_verse_model #license-apache-2.0 #region-us \n",
"# Yamshadowexperiment28Multi_verse_model-7B\n\nYamshadowexperiment28Multi_verse_model-7B is an automated merge created by Maxime Labonne using the following configuration.\n* automerger/YamshadowExperiment28-7B\n* MTSAIR/multi_verse_model",
"## Configuration",
"## Usage"
] |
text-generation | null | # Meta-Llama-3-8B-GGUF
- This is a GGUF quantized version of [Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B/edit/main/README.md).
## Model Details
* Meta developed and released the Meta Llama 3 family of large language models (LLMs) based on the Transformer architecture.
* Model Architecture: Transformer-based with 8.5 billion parameters.
* GGUF Quantization: Currently only availabel in f_16, Q8_0 version.
## About GGUF
GGUF is a new format introduced by the llama.cpp team on August 21st 2023. It is a replacement for GGML, which is no longer supported by llama.cpp. GGUF offers numerous advantages over GGML, such as better tokenisation, and support for special tokens. It is also supports metadata, and is designed to be extensible.
Here is an incomplate list of clients and libraries that are known to support GGUF:
llama.cpp. The source project for GGUF. Offers a CLI and a server option.
text-generation-webui, the most widely used web UI, with many features and powerful extensions. Supports GPU acceleration.
KoboldCpp, a fully featured web UI, with GPU accel across all platforms and GPU architectures. Especially good for story telling.
LM Studio, an easy-to-use and powerful local GUI for Windows and macOS (Silicon), with GPU acceleration.
LoLLMS Web UI, a great web UI with many interesting and unique features, including a full model library for easy model selection.
Faraday.dev, an attractive and easy to use character-based chat GUI for Windows and macOS (both Silicon and Intel), with GPU acceleration.
ctransformers, a Python library with GPU accel, LangChain support, and OpenAI-compatible AI server.
llama-cpp-python, a Python library with GPU accel, LangChain support, and OpenAI-compatible API server.
candle, a Rust ML framework with a focus on performance, including GPU support, and ease of use.
## Intended Use
* This model is intended for research and experimentation in understanding and advancing language model capabilities.
* Sample Use Cases:
* Text generation of various kinds (creative, factual, etc.)
* Summarization
* Question-answering
## Performance & Limitations
* Performance Metrics: Report speed improvements, performance changes compared to the original model.
* Limitations:
May still generate unsafe or biased outputs, use with caution.
Performance changes compared to the original due to quantization.
## How to Use
1. **Load the model and tokenizer:**
```python
##### Llama3 Inference #############
from huggingface_hub import hf_hub_download
import time
from llama_cpp.llama import Llama, LlamaGrammar
import httpx
import json
import torch
import multiprocessing as mp
number_of_cpu = mp.cpu_count()
grammar_text = httpx.get("https://raw.githubusercontent.com/ggerganov/llama.cpp/master/grammars/json.gbnf").text
grammar = LlamaGrammar.from_string(grammar_text)
model_name_or_path = "Orneyfish/Meta-Llama-3-8B_F_16.gguf"
model_basename = "Meta-Llama-3-8B_F_16.gguf" # the model is in bin format
model_path = hf_hub_download(repo_id=model_name_or_path, filename=model_basename, local_dir='models/')
from langchain import PromptTemplate, LLMChain
from langchain.callbacks.manager import CallbackManager
from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler
# Callbacks support token-wise streaming
callback_manager = CallbackManager([StreamingStdOutCallbackHandler()])
# Verbose is required to pass to the callback manager
n_gpu_layers = 40 # Change this value based on your model and your GPU VRAM pool.
n_batch = 1024 # Should be between 1 and n_ctx, consider the amount of VRAM in your GPU.
# Loading model,
llm = Llama(
model_path=model_path,
n_threads=number_of_cpu,
n_gpu_layers=n_gpu_layers,
n_batch=n_batch,
n_threads_batch = 512,
# use_mlock =True,
callback_manager=callback_manager,
verbose=True,
n_ctx=8196, # Context window
stop = ['USER:'], # Dynamic stopping when such token is detected.
temperature = 0.2,
# use_mmap = False,
)
```
## Prompt Template
**1. System prompt message added to a single user message**
```python
prompt = """<|begin_of_text|><|start_header_id|>system<|end_header_id|>
{{ system_prompt }}<|eot_id|><|start_header_id|>user<|end_header_id|>
{{ user_message }}<|eot_id|><|start_header_id|>assistant<|end_header_id|>"""
```
**2. System prompt and multiple turn conversation between the user and assistant**
```python
prompt = """<|begin_of_text|><|start_header_id|>system<|end_header_id|>
{{ system_prompt }}<|eot_id|><|start_header_id|>user<|end_header_id|>
{{ user_message_1 }}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
{{ model_answer_1 }}<|eot_id|><|start_header_id|>user<|end_header_id|>
{{ user_message_2 }}<|eot_id|><|start_header_id|>assistant<|end_header_id|>"""
```
## Please test the model out | {"language": ["en"], "license": "other", "tags": ["facebook", "meta", "pytorch", "llama", "llama-3"], "model_name": "Meta-Llama-3-8B", "result": [{"type": "text-generation"}], "license_name": "llama3", "license_link": "LICENSE", "arxiv": 2307.09288, "base_model": "meta-llama/Meta-Llama-3-8B", "inference": false, "model_creator": "Meta Llama 3", "model_type": "llama", "pipeline_tag": "text-generation", "prompt_template": "<|begin_of_text|><|start_header_id|>system<|end_header_id|> {{ system_prompt }}<|eot_id|><|start_header_id|>user<|end_header_id|> {{ user_message }}<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n", "quantized_by": "Orneyfish"} | Orneyfish/Meta-Llama-3-8B_F_16.gguf | null | [
"gguf",
"facebook",
"meta",
"pytorch",
"llama",
"llama-3",
"text-generation",
"en",
"base_model:meta-llama/Meta-Llama-3-8B",
"license:other",
"region:us"
] | null | 2024-04-19T17:22:40+00:00 | [] | [
"en"
] | TAGS
#gguf #facebook #meta #pytorch #llama #llama-3 #text-generation #en #base_model-meta-llama/Meta-Llama-3-8B #license-other #region-us
| # Meta-Llama-3-8B-GGUF
- This is a GGUF quantized version of Meta-Llama-3-8B.
## Model Details
* Meta developed and released the Meta Llama 3 family of large language models (LLMs) based on the Transformer architecture.
* Model Architecture: Transformer-based with 8.5 billion parameters.
* GGUF Quantization: Currently only availabel in f_16, Q8_0 version.
## About GGUF
GGUF is a new format introduced by the URL team on August 21st 2023. It is a replacement for GGML, which is no longer supported by URL. GGUF offers numerous advantages over GGML, such as better tokenisation, and support for special tokens. It is also supports metadata, and is designed to be extensible.
Here is an incomplate list of clients and libraries that are known to support GGUF:
URL. The source project for GGUF. Offers a CLI and a server option.
text-generation-webui, the most widely used web UI, with many features and powerful extensions. Supports GPU acceleration.
KoboldCpp, a fully featured web UI, with GPU accel across all platforms and GPU architectures. Especially good for story telling.
LM Studio, an easy-to-use and powerful local GUI for Windows and macOS (Silicon), with GPU acceleration.
LoLLMS Web UI, a great web UI with many interesting and unique features, including a full model library for easy model selection.
URL, an attractive and easy to use character-based chat GUI for Windows and macOS (both Silicon and Intel), with GPU acceleration.
ctransformers, a Python library with GPU accel, LangChain support, and OpenAI-compatible AI server.
llama-cpp-python, a Python library with GPU accel, LangChain support, and OpenAI-compatible API server.
candle, a Rust ML framework with a focus on performance, including GPU support, and ease of use.
## Intended Use
* This model is intended for research and experimentation in understanding and advancing language model capabilities.
* Sample Use Cases:
* Text generation of various kinds (creative, factual, etc.)
* Summarization
* Question-answering
## Performance & Limitations
* Performance Metrics: Report speed improvements, performance changes compared to the original model.
* Limitations:
May still generate unsafe or biased outputs, use with caution.
Performance changes compared to the original due to quantization.
## How to Use
1. Load the model and tokenizer:
## Prompt Template
1. System prompt message added to a single user message
2. System prompt and multiple turn conversation between the user and assistant
## Please test the model out | [
"# Meta-Llama-3-8B-GGUF\n\n- This is a GGUF quantized version of Meta-Llama-3-8B.",
"## Model Details\n\n* Meta developed and released the Meta Llama 3 family of large language models (LLMs) based on the Transformer architecture.\n* Model Architecture: Transformer-based with 8.5 billion parameters.\n* GGUF Quantization: Currently only availabel in f_16, Q8_0 version.",
"## About GGUF\nGGUF is a new format introduced by the URL team on August 21st 2023. It is a replacement for GGML, which is no longer supported by URL. GGUF offers numerous advantages over GGML, such as better tokenisation, and support for special tokens. It is also supports metadata, and is designed to be extensible.\n\nHere is an incomplate list of clients and libraries that are known to support GGUF:\n\nURL. The source project for GGUF. Offers a CLI and a server option.\ntext-generation-webui, the most widely used web UI, with many features and powerful extensions. Supports GPU acceleration.\nKoboldCpp, a fully featured web UI, with GPU accel across all platforms and GPU architectures. Especially good for story telling.\nLM Studio, an easy-to-use and powerful local GUI for Windows and macOS (Silicon), with GPU acceleration.\nLoLLMS Web UI, a great web UI with many interesting and unique features, including a full model library for easy model selection.\nURL, an attractive and easy to use character-based chat GUI for Windows and macOS (both Silicon and Intel), with GPU acceleration.\nctransformers, a Python library with GPU accel, LangChain support, and OpenAI-compatible AI server.\nllama-cpp-python, a Python library with GPU accel, LangChain support, and OpenAI-compatible API server.\ncandle, a Rust ML framework with a focus on performance, including GPU support, and ease of use.",
"## Intended Use\n\n* This model is intended for research and experimentation in understanding and advancing language model capabilities.\n* Sample Use Cases:\n * Text generation of various kinds (creative, factual, etc.)\n * Summarization\n * Question-answering",
"## Performance & Limitations\n\n* Performance Metrics: Report speed improvements, performance changes compared to the original model.\n* Limitations:\n May still generate unsafe or biased outputs, use with caution.\n Performance changes compared to the original due to quantization.",
"## How to Use\n\n1. Load the model and tokenizer:",
"## Prompt Template\n1. System prompt message added to a single user message\n\n\n2. System prompt and multiple turn conversation between the user and assistant",
"## Please test the model out"
] | [
"TAGS\n#gguf #facebook #meta #pytorch #llama #llama-3 #text-generation #en #base_model-meta-llama/Meta-Llama-3-8B #license-other #region-us \n",
"# Meta-Llama-3-8B-GGUF\n\n- This is a GGUF quantized version of Meta-Llama-3-8B.",
"## Model Details\n\n* Meta developed and released the Meta Llama 3 family of large language models (LLMs) based on the Transformer architecture.\n* Model Architecture: Transformer-based with 8.5 billion parameters.\n* GGUF Quantization: Currently only availabel in f_16, Q8_0 version.",
"## About GGUF\nGGUF is a new format introduced by the URL team on August 21st 2023. It is a replacement for GGML, which is no longer supported by URL. GGUF offers numerous advantages over GGML, such as better tokenisation, and support for special tokens. It is also supports metadata, and is designed to be extensible.\n\nHere is an incomplate list of clients and libraries that are known to support GGUF:\n\nURL. The source project for GGUF. Offers a CLI and a server option.\ntext-generation-webui, the most widely used web UI, with many features and powerful extensions. Supports GPU acceleration.\nKoboldCpp, a fully featured web UI, with GPU accel across all platforms and GPU architectures. Especially good for story telling.\nLM Studio, an easy-to-use and powerful local GUI for Windows and macOS (Silicon), with GPU acceleration.\nLoLLMS Web UI, a great web UI with many interesting and unique features, including a full model library for easy model selection.\nURL, an attractive and easy to use character-based chat GUI for Windows and macOS (both Silicon and Intel), with GPU acceleration.\nctransformers, a Python library with GPU accel, LangChain support, and OpenAI-compatible AI server.\nllama-cpp-python, a Python library with GPU accel, LangChain support, and OpenAI-compatible API server.\ncandle, a Rust ML framework with a focus on performance, including GPU support, and ease of use.",
"## Intended Use\n\n* This model is intended for research and experimentation in understanding and advancing language model capabilities.\n* Sample Use Cases:\n * Text generation of various kinds (creative, factual, etc.)\n * Summarization\n * Question-answering",
"## Performance & Limitations\n\n* Performance Metrics: Report speed improvements, performance changes compared to the original model.\n* Limitations:\n May still generate unsafe or biased outputs, use with caution.\n Performance changes compared to the original due to quantization.",
"## How to Use\n\n1. Load the model and tokenizer:",
"## Prompt Template\n1. System prompt message added to a single user message\n\n\n2. System prompt and multiple turn conversation between the user and assistant",
"## Please test the model out"
] |
null | peft |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# RM-HH-Gemma_harmless_human_20000_gemma2b
This model is a fine-tuned version of [google/gemma-2b](https://huggingface.co/google/gemma-2b) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.6196
- Accuracy: 0.6678
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1.41e-05
- train_batch_size: 1
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 4
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 1.0
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 0.7635 | 0.06 | 250 | 0.7536 | 0.4972 |
| 0.7325 | 0.11 | 500 | 0.7235 | 0.5378 |
| 0.7285 | 0.17 | 750 | 0.7007 | 0.5673 |
| 0.7183 | 0.22 | 1000 | 0.6823 | 0.5973 |
| 0.6913 | 0.28 | 1250 | 0.6703 | 0.6113 |
| 0.6918 | 0.33 | 1500 | 0.6594 | 0.6263 |
| 0.6673 | 0.39 | 1750 | 0.6509 | 0.6368 |
| 0.6753 | 0.44 | 2000 | 0.6432 | 0.6398 |
| 0.6616 | 0.5 | 2250 | 0.6382 | 0.6503 |
| 0.672 | 0.56 | 2500 | 0.6336 | 0.6488 |
| 0.6457 | 0.61 | 2750 | 0.6308 | 0.6533 |
| 0.6705 | 0.67 | 3000 | 0.6276 | 0.6563 |
| 0.6534 | 0.72 | 3250 | 0.6247 | 0.6593 |
| 0.6176 | 0.78 | 3500 | 0.6228 | 0.6623 |
| 0.6597 | 0.83 | 3750 | 0.6210 | 0.6643 |
| 0.6404 | 0.89 | 4000 | 0.6201 | 0.6663 |
| 0.6199 | 0.94 | 4250 | 0.6196 | 0.6678 |
### Framework versions
- PEFT 0.9.0
- Transformers 4.38.2
- Pytorch 2.1.2
- Datasets 2.18.0
- Tokenizers 0.15.2 | {"license": "gemma", "library_name": "peft", "tags": ["trl", "reward-trainer", "generated_from_trainer"], "metrics": ["accuracy"], "base_model": "google/gemma-2b", "model-index": [{"name": "RM-HH-Gemma_harmless_human_20000_gemma2b", "results": []}]} | Holarissun/RM-HH-Gemma_harmless_human_20000_gemma2b | null | [
"peft",
"safetensors",
"trl",
"reward-trainer",
"generated_from_trainer",
"base_model:google/gemma-2b",
"license:gemma",
"region:us"
] | null | 2024-04-19T17:23:19+00:00 | [] | [] | TAGS
#peft #safetensors #trl #reward-trainer #generated_from_trainer #base_model-google/gemma-2b #license-gemma #region-us
| RM-HH-Gemma\_harmless\_human\_20000\_gemma2b
============================================
This model is a fine-tuned version of google/gemma-2b on an unknown dataset.
It achieves the following results on the evaluation set:
* Loss: 0.6196
* Accuracy: 0.6678
Model description
-----------------
More information needed
Intended uses & limitations
---------------------------
More information needed
Training and evaluation data
----------------------------
More information needed
Training procedure
------------------
### Training hyperparameters
The following hyperparameters were used during training:
* learning\_rate: 1.41e-05
* train\_batch\_size: 1
* eval\_batch\_size: 8
* seed: 42
* gradient\_accumulation\_steps: 4
* total\_train\_batch\_size: 4
* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
* lr\_scheduler\_type: linear
* num\_epochs: 1.0
### Training results
### Framework versions
* PEFT 0.9.0
* Transformers 4.38.2
* Pytorch 2.1.2
* Datasets 2.18.0
* Tokenizers 0.15.2
| [
"### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 1.41e-05\n* train\\_batch\\_size: 1\n* eval\\_batch\\_size: 8\n* seed: 42\n* gradient\\_accumulation\\_steps: 4\n* total\\_train\\_batch\\_size: 4\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 1.0",
"### Training results",
"### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.1.2\n* Datasets 2.18.0\n* Tokenizers 0.15.2"
] | [
"TAGS\n#peft #safetensors #trl #reward-trainer #generated_from_trainer #base_model-google/gemma-2b #license-gemma #region-us \n",
"### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 1.41e-05\n* train\\_batch\\_size: 1\n* eval\\_batch\\_size: 8\n* seed: 42\n* gradient\\_accumulation\\_steps: 4\n* total\\_train\\_batch\\_size: 4\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 1.0",
"### Training results",
"### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.1.2\n* Datasets 2.18.0\n* Tokenizers 0.15.2"
] |
null | peft |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# mistral7binstruct_summarize
This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on the generator dataset.
It achieves the following results on the evaluation set:
- Loss: 1.5578
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0002
- train_batch_size: 1
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant
- lr_scheduler_warmup_steps: 0.03
- training_steps: 50
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:------:|:----:|:---------------:|
| 1.7418 | 0.0146 | 25 | 1.6358 |
| 1.5434 | 0.0292 | 50 | 1.5578 |
### Framework versions
- PEFT 0.10.0
- Transformers 4.40.0
- Pytorch 2.2.2+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1 | {"library_name": "peft", "tags": ["trl", "sft", "generated_from_trainer"], "datasets": ["generator"], "base_model": "mistralai/Mistral-7B-Instruct-v0.2", "model-index": [{"name": "mistral7binstruct_summarize", "results": []}]} | ymath/mistral7binstruct_summarize | null | [
"peft",
"safetensors",
"trl",
"sft",
"generated_from_trainer",
"dataset:generator",
"base_model:mistralai/Mistral-7B-Instruct-v0.2",
"region:us"
] | null | 2024-04-19T17:24:39+00:00 | [] | [] | TAGS
#peft #safetensors #trl #sft #generated_from_trainer #dataset-generator #base_model-mistralai/Mistral-7B-Instruct-v0.2 #region-us
| mistral7binstruct\_summarize
============================
This model is a fine-tuned version of mistralai/Mistral-7B-Instruct-v0.2 on the generator dataset.
It achieves the following results on the evaluation set:
* Loss: 1.5578
Model description
-----------------
More information needed
Intended uses & limitations
---------------------------
More information needed
Training and evaluation data
----------------------------
More information needed
Training procedure
------------------
### Training hyperparameters
The following hyperparameters were used during training:
* learning\_rate: 0.0002
* train\_batch\_size: 1
* eval\_batch\_size: 8
* seed: 42
* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
* lr\_scheduler\_type: constant
* lr\_scheduler\_warmup\_steps: 0.03
* training\_steps: 50
### Training results
### Framework versions
* PEFT 0.10.0
* Transformers 4.40.0
* Pytorch 2.2.2+cu121
* Datasets 2.19.0
* Tokenizers 0.19.1
| [
"### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0002\n* train\\_batch\\_size: 1\n* eval\\_batch\\_size: 8\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: constant\n* lr\\_scheduler\\_warmup\\_steps: 0.03\n* training\\_steps: 50",
"### Training results",
"### Framework versions\n\n\n* PEFT 0.10.0\n* Transformers 4.40.0\n* Pytorch 2.2.2+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1"
] | [
"TAGS\n#peft #safetensors #trl #sft #generated_from_trainer #dataset-generator #base_model-mistralai/Mistral-7B-Instruct-v0.2 #region-us \n",
"### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0002\n* train\\_batch\\_size: 1\n* eval\\_batch\\_size: 8\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: constant\n* lr\\_scheduler\\_warmup\\_steps: 0.03\n* training\\_steps: 50",
"### Training results",
"### Framework versions\n\n\n* PEFT 0.10.0\n* Transformers 4.40.0\n* Pytorch 2.2.2+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1"
] |
reinforcement-learning | stable-baselines3 |
# **A2C** Agent playing **PandaReachDense-v3**
This is a trained model of a **A2C** agent playing **PandaReachDense-v3**
using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
## Usage (with Stable-baselines3)
TODO: Add your code
```python
from stable_baselines3 import ...
from huggingface_sb3 import load_from_hub
...
```
| {"library_name": "stable-baselines3", "tags": ["PandaReachDense-v3", "deep-reinforcement-learning", "reinforcement-learning", "stable-baselines3"], "model-index": [{"name": "A2C", "results": [{"task": {"type": "reinforcement-learning", "name": "reinforcement-learning"}, "dataset": {"name": "PandaReachDense-v3", "type": "PandaReachDense-v3"}, "metrics": [{"type": "mean_reward", "value": "-0.27 +/- 0.11", "name": "mean_reward", "verified": false}]}]}]} | BWangila/a2c-PandaReachDense-v3 | null | [
"stable-baselines3",
"PandaReachDense-v3",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] | null | 2024-04-19T17:24:52+00:00 | [] | [] | TAGS
#stable-baselines3 #PandaReachDense-v3 #deep-reinforcement-learning #reinforcement-learning #model-index #region-us
|
# A2C Agent playing PandaReachDense-v3
This is a trained model of a A2C agent playing PandaReachDense-v3
using the stable-baselines3 library.
## Usage (with Stable-baselines3)
TODO: Add your code
| [
"# A2C Agent playing PandaReachDense-v3\nThis is a trained model of a A2C agent playing PandaReachDense-v3\nusing the stable-baselines3 library.",
"## Usage (with Stable-baselines3)\nTODO: Add your code"
] | [
"TAGS\n#stable-baselines3 #PandaReachDense-v3 #deep-reinforcement-learning #reinforcement-learning #model-index #region-us \n",
"# A2C Agent playing PandaReachDense-v3\nThis is a trained model of a A2C agent playing PandaReachDense-v3\nusing the stable-baselines3 library.",
"## Usage (with Stable-baselines3)\nTODO: Add your code"
] |
text-classification | transformers |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# distilBert_cased_for_binary_sentiment_classification
This model is a fine-tuned version of [distilbert/distilbert-base-cased](https://huggingface.co/distilbert/distilbert-base-cased) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2352
- Accuracy: 0.923
- F1: 0.9199
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
| 0.2856 | 1.0 | 1000 | 0.2463 | 0.913 | 0.9096 |
| 0.2074 | 2.0 | 2000 | 0.2352 | 0.923 | 0.9199 |
### Framework versions
- Transformers 4.39.3
- Pytorch 2.2.2
- Datasets 2.18.0
- Tokenizers 0.15.2
| {"license": "apache-2.0", "tags": ["generated_from_trainer"], "metrics": ["accuracy", "f1"], "base_model": "distilbert/distilbert-base-cased", "model-index": [{"name": "distilBert_cased_for_binary_sentiment_classification", "results": []}]} | ThoMyh/distilBert_cased_for_binary_sentiment_classification | null | [
"transformers",
"tensorboard",
"safetensors",
"distilbert",
"text-classification",
"generated_from_trainer",
"base_model:distilbert/distilbert-base-cased",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | null | 2024-04-19T17:25:07+00:00 | [] | [] | TAGS
#transformers #tensorboard #safetensors #distilbert #text-classification #generated_from_trainer #base_model-distilbert/distilbert-base-cased #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us
| distilBert\_cased\_for\_binary\_sentiment\_classification
=========================================================
This model is a fine-tuned version of distilbert/distilbert-base-cased on the None dataset.
It achieves the following results on the evaluation set:
* Loss: 0.2352
* Accuracy: 0.923
* F1: 0.9199
Model description
-----------------
More information needed
Intended uses & limitations
---------------------------
More information needed
Training and evaluation data
----------------------------
More information needed
Training procedure
------------------
### Training hyperparameters
The following hyperparameters were used during training:
* learning\_rate: 2e-05
* train\_batch\_size: 16
* eval\_batch\_size: 16
* seed: 42
* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
* lr\_scheduler\_type: linear
* num\_epochs: 2
### Training results
### Framework versions
* Transformers 4.39.3
* Pytorch 2.2.2
* Datasets 2.18.0
* Tokenizers 0.15.2
| [
"### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 2e-05\n* train\\_batch\\_size: 16\n* eval\\_batch\\_size: 16\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 2",
"### Training results",
"### Framework versions\n\n\n* Transformers 4.39.3\n* Pytorch 2.2.2\n* Datasets 2.18.0\n* Tokenizers 0.15.2"
] | [
"TAGS\n#transformers #tensorboard #safetensors #distilbert #text-classification #generated_from_trainer #base_model-distilbert/distilbert-base-cased #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us \n",
"### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 2e-05\n* train\\_batch\\_size: 16\n* eval\\_batch\\_size: 16\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 2",
"### Training results",
"### Framework versions\n\n\n* Transformers 4.39.3\n* Pytorch 2.2.2\n* Datasets 2.18.0\n* Tokenizers 0.15.2"
] |
null | transformers | ## About
<!-- ### quantize_version: 1 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: -->
<!-- ### vocab_type: -->
static quants of https://huggingface.co/mpasila/Meta-Llama-3-11.5B
<!-- provided-files -->
weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion.
## Usage
If you are unsure how to use GGUF files, refer to one of [TheBloke's
READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
more details, including on how to concatenate multi-part files.
## Provided Quants
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
| Link | Type | Size/GB | Notes |
|:-----|:-----|--------:|:------|
| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-11.5B-GGUF/resolve/main/Meta-Llama-3-11.5B.Q2_K.gguf) | Q2_K | 4.6 | |
| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-11.5B-GGUF/resolve/main/Meta-Llama-3-11.5B.IQ3_XS.gguf) | IQ3_XS | 5.0 | |
| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-11.5B-GGUF/resolve/main/Meta-Llama-3-11.5B.Q3_K_S.gguf) | Q3_K_S | 5.3 | |
| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-11.5B-GGUF/resolve/main/Meta-Llama-3-11.5B.IQ3_S.gguf) | IQ3_S | 5.3 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-11.5B-GGUF/resolve/main/Meta-Llama-3-11.5B.IQ3_M.gguf) | IQ3_M | 5.4 | |
| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-11.5B-GGUF/resolve/main/Meta-Llama-3-11.5B.Q3_K_M.gguf) | Q3_K_M | 5.8 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-11.5B-GGUF/resolve/main/Meta-Llama-3-11.5B.Q3_K_L.gguf) | Q3_K_L | 6.3 | |
| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-11.5B-GGUF/resolve/main/Meta-Llama-3-11.5B.IQ4_XS.gguf) | IQ4_XS | 6.5 | |
| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-11.5B-GGUF/resolve/main/Meta-Llama-3-11.5B.Q4_K_S.gguf) | Q4_K_S | 6.8 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-11.5B-GGUF/resolve/main/Meta-Llama-3-11.5B.Q4_K_M.gguf) | Q4_K_M | 7.1 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-11.5B-GGUF/resolve/main/Meta-Llama-3-11.5B.Q5_K_S.gguf) | Q5_K_S | 8.1 | |
| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-11.5B-GGUF/resolve/main/Meta-Llama-3-11.5B.Q5_K_M.gguf) | Q5_K_M | 8.3 | |
| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-11.5B-GGUF/resolve/main/Meta-Llama-3-11.5B.Q6_K.gguf) | Q6_K | 9.6 | very good quality |
| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-11.5B-GGUF/resolve/main/Meta-Llama-3-11.5B.Q8_0.gguf) | Q8_0 | 12.3 | fast, best quality |
Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):
And here are Artefact2's thoughts on the matter:
https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
## FAQ / Model Request
See https://huggingface.co/mradermacher/model_requests for some answers to
questions you might have and/or if you want some other model quantized.
## Thanks
I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
me use its servers and providing upgrades to my workstation to enable
this work in my free time.
<!-- end -->
| {"language": ["en"], "license": "other", "library_name": "transformers", "tags": ["mergekit", "merge", "facebook", "meta", "pytorch", "llama", "llama-3"], "base_model": "mpasila/Meta-Llama-3-11.5B", "extra_gated_button_content": "Submit", "extra_gated_fields": {"Affiliation": "text", "By clicking Submit below I accept the terms of the license and acknowledge that the information I provide will be collected stored processed and shared in accordance with the Meta Privacy Policy": "checkbox", "Country": "country", "Date of birth": "date_picker", "First Name": "text", "Last Name": "text", "geo": "ip_location"}, "extra_gated_prompt": "### META LLAMA 3 COMMUNITY LICENSE AGREEMENT\nMeta Llama 3 Version Release Date: April 18, 2024\n\"Agreement\" means the terms and conditions for use, reproduction, distribution and modification of the Llama Materials set forth herein.\n\"Documentation\" means the specifications, manuals and documentation accompanying Meta Llama 3 distributed by Meta at https://llama.meta.com/get-started/.\n\"Licensee\" or \"you\" means you, or your employer or any other person or entity (if you are entering into this Agreement on such person or entity\u2019s behalf), of the age required under applicable laws, rules or regulations to provide legal consent and that has legal authority to bind your employer or such other person or entity if you are entering in this Agreement on their behalf.\n\"Meta Llama 3\" means the foundational large language models and software and algorithms, including machine-learning model code, trained model weights, inference-enabling code, training-enabling code, fine-tuning enabling code and other elements of the foregoing distributed by Meta at https://llama.meta.com/llama-downloads.\n\"Llama Materials\" means, collectively, Meta\u2019s proprietary Meta Llama 3 and Documentation (and any portion thereof) made available under this Agreement.\n\"Meta\" or \"we\" means Meta Platforms Ireland Limited (if you are located in or, if you are an entity, your principal place of business is in the EEA or Switzerland) and Meta Platforms, Inc. (if you are located outside of the EEA or Switzerland).\n \n1. License Rights and Redistribution.\na. Grant of Rights. You are granted a non-exclusive, worldwide, non-transferable and royalty-free limited license under Meta\u2019s intellectual property or other rights owned by Meta embodied in the Llama Materials to use, reproduce, distribute, copy, create derivative works of, and make modifications to the Llama Materials.\nb. Redistribution and Use.\ni. If you distribute or make available the Llama Materials (or any derivative works thereof), or a product or service that uses any of them, including another AI model, you shall (A) provide a copy of this Agreement with any such Llama Materials; and (B) prominently display \u201cBuilt with Meta Llama 3\u201d on a related website, user interface, blogpost, about page, or product documentation. If you use the Llama Materials to create, train, fine tune, or otherwise improve an AI model, which is distributed or made available, you shall also include \u201cLlama 3\u201d at the beginning of any such AI model name.\nii. If you receive Llama Materials, or any derivative works thereof, from a Licensee as part of an integrated end user product, then Section 2 of this Agreement will not apply to you.\niii. You must retain in all copies of the Llama Materials that you distribute the following attribution notice within a \u201cNotice\u201d text file distributed as a part of such copies: \u201cMeta Llama 3 is licensed under the Meta Llama 3 Community License, Copyright \u00a9 Meta Platforms, Inc. All Rights Reserved.\u201d\niv. Your use of the Llama Materials must comply with applicable laws and regulations (including trade compliance laws and regulations) and adhere to the Acceptable Use Policy for the Llama Materials (available at https://llama.meta.com/llama3/use-policy), which is hereby incorporated by reference into this Agreement.\nv. You will not use the Llama Materials or any output or results of the Llama Materials to improve any other large language model (excluding Meta Llama 3 or derivative works thereof).\n2. Additional Commercial Terms. If, on the Meta Llama 3 version release date, the monthly active users of the products or services made available by or for Licensee, or Licensee\u2019s affiliates, is greater than 700 million monthly active users in the preceding calendar month, you must request a license from Meta, which Meta may grant to you in its sole discretion, and you are not authorized to exercise any of the rights under this Agreement unless or until Meta otherwise expressly grants you such rights.\n3. Disclaimer of Warranty. UNLESS REQUIRED BY APPLICABLE LAW, THE LLAMA MATERIALS AND ANY OUTPUT AND RESULTS THEREFROM ARE PROVIDED ON AN \u201cAS IS\u201d BASIS, WITHOUT WARRANTIES OF ANY KIND, AND META DISCLAIMS ALL WARRANTIES OF ANY KIND, BOTH EXPRESS AND IMPLIED, INCLUDING, WITHOUT LIMITATION, ANY WARRANTIES OF TITLE, NON-INFRINGEMENT, MERCHANTABILITY, OR FITNESS FOR A PARTICULAR PURPOSE. YOU ARE SOLELY RESPONSIBLE FOR DETERMINING THE APPROPRIATENESS OF USING OR REDISTRIBUTING THE LLAMA MATERIALS AND ASSUME ANY RISKS ASSOCIATED WITH YOUR USE OF THE LLAMA MATERIALS AND ANY OUTPUT AND RESULTS.\n4. Limitation of Liability. IN NO EVENT WILL META OR ITS AFFILIATES BE LIABLE UNDER ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, TORT, NEGLIGENCE, PRODUCTS LIABILITY, OR OTHERWISE, ARISING OUT OF THIS AGREEMENT, FOR ANY LOST PROFITS OR ANY INDIRECT, SPECIAL, CONSEQUENTIAL, INCIDENTAL, EXEMPLARY OR PUNITIVE DAMAGES, EVEN IF META OR ITS AFFILIATES HAVE BEEN ADVISED OF THE POSSIBILITY OF ANY OF THE FOREGOING.\n5. Intellectual Property.\na. No trademark licenses are granted under this Agreement, and in connection with the Llama Materials, neither Meta nor Licensee may use any name or mark owned by or associated with the other or any of its affiliates, except as required for reasonable and customary use in describing and redistributing the Llama Materials or as set forth in this Section 5(a). Meta hereby grants you a license to use \u201cLlama 3\u201d (the \u201cMark\u201d) solely as required to comply with the last sentence of Section 1.b.i. You will comply with Meta\u2019s brand guidelines (currently accessible at https://about.meta.com/brand/resources/meta/company-brand/ ). All goodwill arising out of your use of the Mark will inure to the benefit of Meta.\nb. Subject to Meta\u2019s ownership of Llama Materials and derivatives made by or for Meta, with respect to any derivative works and modifications of the Llama Materials that are made by you, as between you and Meta, you are and will be the owner of such derivative works and modifications.\nc. If you institute litigation or other proceedings against Meta or any entity (including a cross-claim or counterclaim in a lawsuit) alleging that the Llama Materials or Meta Llama 3 outputs or results, or any portion of any of the foregoing, constitutes infringement of intellectual property or other rights owned or licensable by you, then any licenses granted to you under this Agreement shall terminate as of the date such litigation or claim is filed or instituted. You will indemnify and hold harmless Meta from and against any claim by any third party arising out of or related to your use or distribution of the Llama Materials.\n6. Term and Termination. The term of this Agreement will commence upon your acceptance of this Agreement or access to the Llama Materials and will continue in full force and effect until terminated in accordance with the terms and conditions herein. Meta may terminate this Agreement if you are in breach of any term or condition of this Agreement. Upon termination of this Agreement, you shall delete and cease use of the Llama Materials. Sections 3, 4 and 7 shall survive the termination of this Agreement.\n7. Governing Law and Jurisdiction. This Agreement will be governed and construed under the laws of the State of California without regard to choice of law principles, and the UN Convention on Contracts for the International Sale of Goods does not apply to this Agreement. The courts of California shall have exclusive jurisdiction of any dispute arising out of this Agreement.\n### Meta Llama 3 Acceptable Use Policy\nMeta is committed to promoting safe and fair use of its tools and features, including Meta Llama 3. If you access or use Meta Llama 3, you agree to this Acceptable Use Policy (\u201cPolicy\u201d). The most recent copy of this policy can be found at [https://llama.meta.com/llama3/use-policy](https://llama.meta.com/llama3/use-policy)\n#### Prohibited Uses\nWe want everyone to use Meta Llama 3 safely and responsibly. You agree you will not use, or allow others to use, Meta Llama 3 to: 1. Violate the law or others\u2019 rights, including to:\n 1. Engage in, promote, generate, contribute to, encourage, plan, incite, or further illegal or unlawful activity or content, such as:\n 1. Violence or terrorism\n 2. Exploitation or harm to children, including the solicitation, creation, acquisition, or dissemination of child exploitative content or failure to report Child Sexual Abuse Material\n 3. Human trafficking, exploitation, and sexual violence\n 4. The illegal distribution of information or materials to minors, including obscene materials, or failure to employ legally required age-gating in connection with such information or materials.\n 5. Sexual solicitation\n 6. Any other criminal activity\n 2. Engage in, promote, incite, or facilitate the harassment, abuse, threatening, or bullying of individuals or groups of individuals\n 3. Engage in, promote, incite, or facilitate discrimination or other unlawful or harmful conduct in the provision of employment, employment benefits, credit, housing, other economic benefits, or other essential goods and services\n 4. Engage in the unauthorized or unlicensed practice of any profession including, but not limited to, financial, legal, medical/health, or related professional practices\n 5. Collect, process, disclose, generate, or infer health, demographic, or other sensitive personal or private information about individuals without rights and consents required by applicable laws\n 6. Engage in or facilitate any action or generate any content that infringes, misappropriates, or otherwise violates any third-party rights, including the outputs or results of any products or services using the Llama Materials\n 7. Create, generate, or facilitate the creation of malicious code, malware, computer viruses or do anything else that could disable, overburden, interfere with or impair the proper working, integrity, operation or appearance of a website or computer system\n2. Engage in, promote, incite, facilitate, or assist in the planning or development of activities that present a risk of death or bodily harm to individuals, including use of Meta Llama 3 related to the following:\n 1. Military, warfare, nuclear industries or applications, espionage, use for materials or activities that are subject to the International Traffic Arms Regulations (ITAR) maintained by the United States Department of State\n 2. Guns and illegal weapons (including weapon development)\n 3. Illegal drugs and regulated/controlled substances\n 4. Operation of critical infrastructure, transportation technologies, or heavy machinery\n 5. Self-harm or harm to others, including suicide, cutting, and eating disorders\n 6. Any content intended to incite or promote violence, abuse, or any infliction of bodily harm to an individual\n3. Intentionally deceive or mislead others, including use of Meta Llama 3 related to the following:\n 1. Generating, promoting, or furthering fraud or the creation or promotion of disinformation\n 2. Generating, promoting, or furthering defamatory content, including the creation of defamatory statements, images, or other content\n 3. Generating, promoting, or further distributing spam\n 4. Impersonating another individual without consent, authorization, or legal right\n 5. Representing that the use of Meta Llama 3 or outputs are human-generated\n 6. Generating or facilitating false online engagement, including fake reviews and other means of fake online engagement\n4. Fail to appropriately disclose to end users any known dangers of your AI system\nPlease report any violation of this Policy, software \u201cbug,\u201d or other problems that could lead to a violation of this Policy through one of the following means:\n * Reporting issues with the model: [https://github.com/meta-llama/llama3](https://github.com/meta-llama/llama3)\n * Reporting risky content generated by the model:\n developers.facebook.com/llama_output_feedback\n * Reporting bugs and security concerns: facebook.com/whitehat/info\n * Reporting violations of the Acceptable Use Policy or unlicensed uses of Meta Llama 3: [email protected]", "license_link": "LICENSE", "license_name": "llama3", "quantized_by": "mradermacher"} | mradermacher/Meta-Llama-3-11.5B-GGUF | null | [
"transformers",
"gguf",
"mergekit",
"merge",
"facebook",
"meta",
"pytorch",
"llama",
"llama-3",
"en",
"base_model:mpasila/Meta-Llama-3-11.5B",
"license:other",
"endpoints_compatible",
"region:us"
] | null | 2024-04-19T17:25:57+00:00 | [] | [
"en"
] | TAGS
#transformers #gguf #mergekit #merge #facebook #meta #pytorch #llama #llama-3 #en #base_model-mpasila/Meta-Llama-3-11.5B #license-other #endpoints_compatible #region-us
| About
-----
static quants of URL
weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion.
Usage
-----
If you are unsure how to use GGUF files, refer to one of TheBloke's
READMEs for
more details, including on how to concatenate multi-part files.
Provided Quants
---------------
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):
!URL
And here are Artefact2's thoughts on the matter:
URL
FAQ / Model Request
-------------------
See URL for some answers to
questions you might have and/or if you want some other model quantized.
Thanks
------
I thank my company, nethype GmbH, for letting
me use its servers and providing upgrades to my workstation to enable
this work in my free time.
| [] | [
"TAGS\n#transformers #gguf #mergekit #merge #facebook #meta #pytorch #llama #llama-3 #en #base_model-mpasila/Meta-Llama-3-11.5B #license-other #endpoints_compatible #region-us \n"
] |
automatic-speech-recognition | transformers |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# Whisper Small for Quran Recognition
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Quran_Reciters dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 8000
- mixed_precision_training: Native AMP
### Framework versions
- Transformers 4.41.0.dev0
- Pytorch 2.1.2
- Datasets 2.17.1
- Tokenizers 0.19.1
| {"language": ["ara"], "license": "apache-2.0", "tags": ["hf-asr-leaderboard", "generated_from_trainer"], "datasets": ["AsemBadr/GP"], "base_model": "openai/whisper-small", "model-index": [{"name": "Whisper Small for Quran Recognition", "results": []}]} | AsemBadr/final-whisper-for-initial-publish | null | [
"transformers",
"tensorboard",
"safetensors",
"whisper",
"automatic-speech-recognition",
"hf-asr-leaderboard",
"generated_from_trainer",
"ara",
"dataset:AsemBadr/GP",
"base_model:openai/whisper-small",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | 2024-04-19T17:26:28+00:00 | [] | [
"ara"
] | TAGS
#transformers #tensorboard #safetensors #whisper #automatic-speech-recognition #hf-asr-leaderboard #generated_from_trainer #ara #dataset-AsemBadr/GP #base_model-openai/whisper-small #license-apache-2.0 #endpoints_compatible #region-us
|
# Whisper Small for Quran Recognition
This model is a fine-tuned version of openai/whisper-small on the Quran_Reciters dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 8000
- mixed_precision_training: Native AMP
### Framework versions
- Transformers 4.41.0.dev0
- Pytorch 2.1.2
- Datasets 2.17.1
- Tokenizers 0.19.1
| [
"# Whisper Small for Quran Recognition\n\nThis model is a fine-tuned version of openai/whisper-small on the Quran_Reciters dataset.",
"## Model description\n\nMore information needed",
"## Intended uses & limitations\n\nMore information needed",
"## Training and evaluation data\n\nMore information needed",
"## Training procedure",
"### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 1e-05\n- train_batch_size: 16\n- eval_batch_size: 8\n- seed: 42\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- lr_scheduler_warmup_steps: 500\n- training_steps: 8000\n- mixed_precision_training: Native AMP",
"### Framework versions\n\n- Transformers 4.41.0.dev0\n- Pytorch 2.1.2\n- Datasets 2.17.1\n- Tokenizers 0.19.1"
] | [
"TAGS\n#transformers #tensorboard #safetensors #whisper #automatic-speech-recognition #hf-asr-leaderboard #generated_from_trainer #ara #dataset-AsemBadr/GP #base_model-openai/whisper-small #license-apache-2.0 #endpoints_compatible #region-us \n",
"# Whisper Small for Quran Recognition\n\nThis model is a fine-tuned version of openai/whisper-small on the Quran_Reciters dataset.",
"## Model description\n\nMore information needed",
"## Intended uses & limitations\n\nMore information needed",
"## Training and evaluation data\n\nMore information needed",
"## Training procedure",
"### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 1e-05\n- train_batch_size: 16\n- eval_batch_size: 8\n- seed: 42\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- lr_scheduler_warmup_steps: 500\n- training_steps: 8000\n- mixed_precision_training: Native AMP",
"### Framework versions\n\n- Transformers 4.41.0.dev0\n- Pytorch 2.1.2\n- Datasets 2.17.1\n- Tokenizers 0.19.1"
] |
null | null |
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
This modelcard aims to be a base template for new models. It has been generated using [this raw template](https://github.com/huggingface/huggingface_hub/blob/main/src/huggingface_hub/templates/modelcard_template.md?plain=1).
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] | {} | Saleh11623/Saleh | null | [
"arxiv:1910.09700",
"region:us"
] | null | 2024-04-19T17:26:37+00:00 | [
"1910.09700"
] | [] | TAGS
#arxiv-1910.09700 #region-us
|
# Model Card for Model ID
This modelcard aims to be a base template for new models. It has been generated using this raw template.
## Model Details
### Model Description
- Developed by:
- Funded by [optional]:
- Shared by [optional]:
- Model type:
- Language(s) (NLP):
- License:
- Finetuned from model [optional]:
### Model Sources [optional]
- Repository:
- Paper [optional]:
- Demo [optional]:
## Uses
### Direct Use
### Downstream Use [optional]
### Out-of-Scope Use
## Bias, Risks, and Limitations
### Recommendations
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
## Training Details
### Training Data
### Training Procedure
#### Preprocessing [optional]
#### Training Hyperparameters
- Training regime:
#### Speeds, Sizes, Times [optional]
## Evaluation
### Testing Data, Factors & Metrics
#### Testing Data
#### Factors
#### Metrics
### Results
#### Summary
## Model Examination [optional]
## Environmental Impact
Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).
- Hardware Type:
- Hours used:
- Cloud Provider:
- Compute Region:
- Carbon Emitted:
## Technical Specifications [optional]
### Model Architecture and Objective
### Compute Infrastructure
#### Hardware
#### Software
[optional]
BibTeX:
APA:
## Glossary [optional]
## More Information [optional]
## Model Card Authors [optional]
## Model Card Contact
| [
"# Model Card for Model ID\n\n\n\nThis modelcard aims to be a base template for new models. It has been generated using this raw template.",
"## Model Details",
"### Model Description\n\n\n\n\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.",
"## How to Get Started with the Model\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] | [
"TAGS\n#arxiv-1910.09700 #region-us \n",
"# Model Card for Model ID\n\n\n\nThis modelcard aims to be a base template for new models. It has been generated using this raw template.",
"## Model Details",
"### Model Description\n\n\n\n\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.",
"## How to Get Started with the Model\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] |
text-generation | transformers |
# Model Card for Mistral-7B-Instruct-v0.2
The Mistral-7B-Instruct-v0.2 Large Language Model (LLM) is an improved instruct fine-tuned version of [Mistral-7B-Instruct-v0.1](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1).
For full details of this model please read our [paper](https://arxiv.org/abs/2310.06825) and [release blog post](https://mistral.ai/news/la-plateforme/).
## Instruction format
In order to leverage instruction fine-tuning, your prompt should be surrounded by `[INST]` and `[/INST]` tokens. The very first instruction should begin with a begin of sentence id. The next instructions should not. The assistant generation will be ended by the end-of-sentence token id.
E.g.
```
text = "<s>[INST] What is your favourite condiment? [/INST]"
"Well, I'm quite partial to a good squeeze of fresh lemon juice. It adds just the right amount of zesty flavour to whatever I'm cooking up in the kitchen!</s> "
"[INST] Do you have mayonnaise recipes? [/INST]"
```
This format is available as a [chat template](https://huggingface.co/docs/transformers/main/chat_templating) via the `apply_chat_template()` method:
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
device = "cuda" # the device to load the model onto
model = AutoModelForCausalLM.from_pretrained("mistralai/Mistral-7B-Instruct-v0.2")
tokenizer = AutoTokenizer.from_pretrained("mistralai/Mistral-7B-Instruct-v0.2")
messages = [
{"role": "user", "content": "What is your favourite condiment?"},
{"role": "assistant", "content": "Well, I'm quite partial to a good squeeze of fresh lemon juice. It adds just the right amount of zesty flavour to whatever I'm cooking up in the kitchen!"},
{"role": "user", "content": "Do you have mayonnaise recipes?"}
]
encodeds = tokenizer.apply_chat_template(messages, return_tensors="pt")
model_inputs = encodeds.to(device)
model.to(device)
generated_ids = model.generate(model_inputs, max_new_tokens=1000, do_sample=True)
decoded = tokenizer.batch_decode(generated_ids)
print(decoded[0])
```
## Model Architecture
This instruction model is based on Mistral-7B-v0.1, a transformer model with the following architecture choices:
- Grouped-Query Attention
- Sliding-Window Attention
- Byte-fallback BPE tokenizer
## Troubleshooting
- If you see the following error:
```
Traceback (most recent call last):
File "", line 1, in
File "/transformers/models/auto/auto_factory.py", line 482, in from_pretrained
config, kwargs = AutoConfig.from_pretrained(
File "/transformers/models/auto/configuration_auto.py", line 1022, in from_pretrained
config_class = CONFIG_MAPPING[config_dict["model_type"]]
File "/transformers/models/auto/configuration_auto.py", line 723, in getitem
raise KeyError(key)
KeyError: 'mistral'
```
Installing transformers from source should solve the issue
pip install git+https://github.com/huggingface/transformers
This should not be required after transformers-v4.33.4.
## Limitations
The Mistral 7B Instruct model is a quick demonstration that the base model can be easily fine-tuned to achieve compelling performance.
It does not have any moderation mechanisms. We're looking forward to engaging with the community on ways to
make the model finely respect guardrails, allowing for deployment in environments requiring moderated outputs.
## The Mistral AI Team
Albert Jiang, Alexandre Sablayrolles, Arthur Mensch, Blanche Savary, Chris Bamford, Devendra Singh Chaplot, Diego de las Casas, Emma Bou Hanna, Florian Bressand, Gianna Lengyel, Guillaume Bour, Guillaume Lample, Lélio Renard Lavaud, Louis Ternon, Lucile Saulnier, Marie-Anne Lachaux, Pierre Stock, Teven Le Scao, Théophile Gervet, Thibaut Lavril, Thomas Wang, Timothée Lacroix, William El Sayed. | {"license": "apache-2.0", "tags": ["finetuned"], "pipeline_tag": "text-generation", "inference": false} | ltaler01/Mistral-7B-Instruct-v0.2 | null | [
"transformers",
"pytorch",
"safetensors",
"mistral",
"text-generation",
"finetuned",
"conversational",
"arxiv:2310.06825",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-04-19T17:29:53+00:00 | [
"2310.06825"
] | [] | TAGS
#transformers #pytorch #safetensors #mistral #text-generation #finetuned #conversational #arxiv-2310.06825 #license-apache-2.0 #autotrain_compatible #text-generation-inference #region-us
|
# Model Card for Mistral-7B-Instruct-v0.2
The Mistral-7B-Instruct-v0.2 Large Language Model (LLM) is an improved instruct fine-tuned version of Mistral-7B-Instruct-v0.1.
For full details of this model please read our paper and release blog post.
## Instruction format
In order to leverage instruction fine-tuning, your prompt should be surrounded by '[INST]' and '[/INST]' tokens. The very first instruction should begin with a begin of sentence id. The next instructions should not. The assistant generation will be ended by the end-of-sentence token id.
E.g.
This format is available as a chat template via the 'apply_chat_template()' method:
## Model Architecture
This instruction model is based on Mistral-7B-v0.1, a transformer model with the following architecture choices:
- Grouped-Query Attention
- Sliding-Window Attention
- Byte-fallback BPE tokenizer
## Troubleshooting
- If you see the following error:
Installing transformers from source should solve the issue
pip install git+URL
This should not be required after transformers-v4.33.4.
## Limitations
The Mistral 7B Instruct model is a quick demonstration that the base model can be easily fine-tuned to achieve compelling performance.
It does not have any moderation mechanisms. We're looking forward to engaging with the community on ways to
make the model finely respect guardrails, allowing for deployment in environments requiring moderated outputs.
## The Mistral AI Team
Albert Jiang, Alexandre Sablayrolles, Arthur Mensch, Blanche Savary, Chris Bamford, Devendra Singh Chaplot, Diego de las Casas, Emma Bou Hanna, Florian Bressand, Gianna Lengyel, Guillaume Bour, Guillaume Lample, Lélio Renard Lavaud, Louis Ternon, Lucile Saulnier, Marie-Anne Lachaux, Pierre Stock, Teven Le Scao, Théophile Gervet, Thibaut Lavril, Thomas Wang, Timothée Lacroix, William El Sayed. | [
"# Model Card for Mistral-7B-Instruct-v0.2\n\nThe Mistral-7B-Instruct-v0.2 Large Language Model (LLM) is an improved instruct fine-tuned version of Mistral-7B-Instruct-v0.1.\n\nFor full details of this model please read our paper and release blog post.",
"## Instruction format\n\nIn order to leverage instruction fine-tuning, your prompt should be surrounded by '[INST]' and '[/INST]' tokens. The very first instruction should begin with a begin of sentence id. The next instructions should not. The assistant generation will be ended by the end-of-sentence token id.\n\nE.g.\n\n\nThis format is available as a chat template via the 'apply_chat_template()' method:",
"## Model Architecture\nThis instruction model is based on Mistral-7B-v0.1, a transformer model with the following architecture choices:\n- Grouped-Query Attention\n- Sliding-Window Attention\n- Byte-fallback BPE tokenizer",
"## Troubleshooting\n- If you see the following error:\n\n\nInstalling transformers from source should solve the issue\npip install git+URL\n\nThis should not be required after transformers-v4.33.4.",
"## Limitations\n\nThe Mistral 7B Instruct model is a quick demonstration that the base model can be easily fine-tuned to achieve compelling performance. \nIt does not have any moderation mechanisms. We're looking forward to engaging with the community on ways to\nmake the model finely respect guardrails, allowing for deployment in environments requiring moderated outputs.",
"## The Mistral AI Team\n\nAlbert Jiang, Alexandre Sablayrolles, Arthur Mensch, Blanche Savary, Chris Bamford, Devendra Singh Chaplot, Diego de las Casas, Emma Bou Hanna, Florian Bressand, Gianna Lengyel, Guillaume Bour, Guillaume Lample, Lélio Renard Lavaud, Louis Ternon, Lucile Saulnier, Marie-Anne Lachaux, Pierre Stock, Teven Le Scao, Théophile Gervet, Thibaut Lavril, Thomas Wang, Timothée Lacroix, William El Sayed."
] | [
"TAGS\n#transformers #pytorch #safetensors #mistral #text-generation #finetuned #conversational #arxiv-2310.06825 #license-apache-2.0 #autotrain_compatible #text-generation-inference #region-us \n",
"# Model Card for Mistral-7B-Instruct-v0.2\n\nThe Mistral-7B-Instruct-v0.2 Large Language Model (LLM) is an improved instruct fine-tuned version of Mistral-7B-Instruct-v0.1.\n\nFor full details of this model please read our paper and release blog post.",
"## Instruction format\n\nIn order to leverage instruction fine-tuning, your prompt should be surrounded by '[INST]' and '[/INST]' tokens. The very first instruction should begin with a begin of sentence id. The next instructions should not. The assistant generation will be ended by the end-of-sentence token id.\n\nE.g.\n\n\nThis format is available as a chat template via the 'apply_chat_template()' method:",
"## Model Architecture\nThis instruction model is based on Mistral-7B-v0.1, a transformer model with the following architecture choices:\n- Grouped-Query Attention\n- Sliding-Window Attention\n- Byte-fallback BPE tokenizer",
"## Troubleshooting\n- If you see the following error:\n\n\nInstalling transformers from source should solve the issue\npip install git+URL\n\nThis should not be required after transformers-v4.33.4.",
"## Limitations\n\nThe Mistral 7B Instruct model is a quick demonstration that the base model can be easily fine-tuned to achieve compelling performance. \nIt does not have any moderation mechanisms. We're looking forward to engaging with the community on ways to\nmake the model finely respect guardrails, allowing for deployment in environments requiring moderated outputs.",
"## The Mistral AI Team\n\nAlbert Jiang, Alexandre Sablayrolles, Arthur Mensch, Blanche Savary, Chris Bamford, Devendra Singh Chaplot, Diego de las Casas, Emma Bou Hanna, Florian Bressand, Gianna Lengyel, Guillaume Bour, Guillaume Lample, Lélio Renard Lavaud, Louis Ternon, Lucile Saulnier, Marie-Anne Lachaux, Pierre Stock, Teven Le Scao, Théophile Gervet, Thibaut Lavril, Thomas Wang, Timothée Lacroix, William El Sayed."
] |
text-generation | transformers |
# OpenVINO IR model with int8 quantization of llama-3-8B-Instruct
Model definition for LocalAI:
```
name: llama3
backend: transformers
parameters:
model: fakezeta/llama-3-8b-instruct-ov-int8
context_size: 8192
type: OVModelForCausalLM
template:
use_tokenizer_template: true
stopwords:
- "<|eot_id|>"
- "<|end_of_text|>"
```
## Model Details
Meta developed and released the Meta Llama 3 family of large language models (LLMs), a collection of pretrained and instruction tuned generative text models in 8 and 70B sizes. The Llama 3 instruction tuned models are optimized for dialogue use cases and outperform many of the available open source chat models on common industry benchmarks. Further, in developing these models, we took great care to optimize helpfulness and safety.
**Model developers** Meta
**Variations** Llama 3 comes in two sizes — 8B and 70B parameters — in pre-trained and instruction tuned variants.
**Input** Models input text only.
**Output** Models generate text and code only.
**Model Architecture** Llama 3 is an auto-regressive language model that uses an optimized transformer architecture. The tuned versions use supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF) to align with human preferences for helpfulness and safety.
<table>
<tr>
<td>
</td>
<td><strong>Training Data</strong>
</td>
<td><strong>Params</strong>
</td>
<td><strong>Context length</strong>
</td>
<td><strong>GQA</strong>
</td>
<td><strong>Token count</strong>
</td>
<td><strong>Knowledge cutoff</strong>
</td>
</tr>
<tr>
<td rowspan="2" >Llama 3
</td>
<td rowspan="2" >A new mix of publicly available online data.
</td>
<td>8B
</td>
<td>8k
</td>
<td>Yes
</td>
<td rowspan="2" >15T+
</td>
<td>March, 2023
</td>
</tr>
<tr>
<td>70B
</td>
<td>8k
</td>
<td>Yes
</td>
<td>December, 2023
</td>
</tr>
</table>
**Llama 3 family of models**. Token counts refer to pretraining data only. Both the 8 and 70B versions use Grouped-Query Attention (GQA) for improved inference scalability.
**Model Release Date** April 18, 2024.
**Status** This is a static model trained on an offline dataset. Future versions of the tuned models will be released as we improve model safety with community feedback.
**License** A custom commercial license is available at: [https://llama.meta.com/llama3/license](https://llama.meta.com/llama3/license)
Where to send questions or comments about the model Instructions on how to provide feedback or comments on the model can be found in the model [README](https://github.com/meta-llama/llama3). For more technical information about generation parameters and recipes for how to use Llama 3 in applications, please go [here](https://github.com/meta-llama/llama-recipes).
## Intended Use
**Intended Use Cases** Llama 3 is intended for commercial and research use in English. Instruction tuned models are intended for assistant-like chat, whereas pretrained models can be adapted for a variety of natural language generation tasks.
**Out-of-scope** Use in any manner that violates applicable laws or regulations (including trade compliance laws). Use in any other way that is prohibited by the Acceptable Use Policy and Llama 3 Community License. Use in languages other than English**.
**Note: Developers may fine-tune Llama 3 models for languages beyond English provided they comply with the Llama 3 Community License and the Acceptable Use Policy.
## How to use
This repository contains two versions of Meta-Llama-3-8B, for use with transformers and with the original `llama3` codebase.
### Use with transformers
See the snippet below for usage with Transformers:
```python
>>> import transformers
>>> import torch
>>> model_id = "meta-llama/Meta-Llama-3-8B"
>>> pipeline = transformers.pipeline(
"text-generation", model=model_id, model_kwargs={"torch_dtype": torch.bfloat16}, device_map="auto"
)
>>> pipeline("Hey how are you doing today?")
```
### Use with `llama3`
Please, follow the instructions in the [repository](https://github.com/meta-llama/llama3).
To download Original checkpoints, see the example command below leveraging `huggingface-cli`:
```
huggingface-cli download meta-llama/Meta-Llama-3-8B --include "original/*" --local-dir Meta-Llama-3-8B
```
For Hugging Face support, we recommend using transformers or TGI, but a similar command works.
## Hardware and Software
**Training Factors** We used custom training libraries, Meta's Research SuperCluster, and production clusters for pretraining. Fine-tuning, annotation, and evaluation were also performed on third-party cloud compute.
**Carbon Footprint Pretraining utilized a cumulative** 7.7M GPU hours of computation on hardware of type H100-80GB (TDP of 700W). Estimated total emissions were 2290 tCO2eq, 100% of which were offset by Meta’s sustainability program.
<table>
<tr>
<td>
</td>
<td><strong>Time (GPU hours)</strong>
</td>
<td><strong>Power Consumption (W)</strong>
</td>
<td><strong>Carbon Emitted(tCO2eq)</strong>
</td>
</tr>
<tr>
<td>Llama 3 8B
</td>
<td>1.3M
</td>
<td>700
</td>
<td>390
</td>
</tr>
<tr>
<td>Llama 3 70B
</td>
<td>6.4M
</td>
<td>700
</td>
<td>1900
</td>
</tr>
<tr>
<td>Total
</td>
<td>7.7M
</td>
<td>
</td>
<td>2290
</td>
</tr>
</table>
**CO2 emissions during pre-training**. Time: total GPU time required for training each model. Power Consumption: peak power capacity per GPU device for the GPUs used adjusted for power usage efficiency. 100% of the emissions are directly offset by Meta's sustainability program, and because we are openly releasing these models, the pretraining costs do not need to be incurred by others.
## Training Data
**Overview** Llama 3 was pretrained on over 15 trillion tokens of data from publicly available sources. The fine-tuning data includes publicly available instruction datasets, as well as over 10M human-annotated examples. Neither the pretraining nor the fine-tuning datasets include Meta user data.
**Data Freshness** The pretraining data has a cutoff of March 2023 for the 7B and December 2023 for the 70B models respectively.
## Benchmarks
In this section, we report the results for Llama 3 models on standard automatic benchmarks. For all the evaluations, we use our internal evaluations library. For details on the methodology see [here](https://github.com/meta-llama/llama3/blob/main/eval_methodology.md).
### Base pretrained models
<table>
<tr>
<td><strong>Category</strong>
</td>
<td><strong>Benchmark</strong>
</td>
<td><strong>Llama 3 8B</strong>
</td>
<td><strong>Llama2 7B</strong>
</td>
<td><strong>Llama2 13B</strong>
</td>
<td><strong>Llama 3 70B</strong>
</td>
<td><strong>Llama2 70B</strong>
</td>
</tr>
<tr>
<td rowspan="6" >General
</td>
<td>MMLU (5-shot)
</td>
<td>66.6
</td>
<td>45.7
</td>
<td>53.8
</td>
<td>79.5
</td>
<td>69.7
</td>
</tr>
<tr>
<td>AGIEval English (3-5 shot)
</td>
<td>45.9
</td>
<td>28.8
</td>
<td>38.7
</td>
<td>63.0
</td>
<td>54.8
</td>
</tr>
<tr>
<td>CommonSenseQA (7-shot)
</td>
<td>72.6
</td>
<td>57.6
</td>
<td>67.6
</td>
<td>83.8
</td>
<td>78.7
</td>
</tr>
<tr>
<td>Winogrande (5-shot)
</td>
<td>76.1
</td>
<td>73.3
</td>
<td>75.4
</td>
<td>83.1
</td>
<td>81.8
</td>
</tr>
<tr>
<td>BIG-Bench Hard (3-shot, CoT)
</td>
<td>61.1
</td>
<td>38.1
</td>
<td>47.0
</td>
<td>81.3
</td>
<td>65.7
</td>
</tr>
<tr>
<td>ARC-Challenge (25-shot)
</td>
<td>78.6
</td>
<td>53.7
</td>
<td>67.6
</td>
<td>93.0
</td>
<td>85.3
</td>
</tr>
<tr>
<td>Knowledge reasoning
</td>
<td>TriviaQA-Wiki (5-shot)
</td>
<td>78.5
</td>
<td>72.1
</td>
<td>79.6
</td>
<td>89.7
</td>
<td>87.5
</td>
</tr>
<tr>
<td rowspan="4" >Reading comprehension
</td>
<td>SQuAD (1-shot)
</td>
<td>76.4
</td>
<td>72.2
</td>
<td>72.1
</td>
<td>85.6
</td>
<td>82.6
</td>
</tr>
<tr>
<td>QuAC (1-shot, F1)
</td>
<td>44.4
</td>
<td>39.6
</td>
<td>44.9
</td>
<td>51.1
</td>
<td>49.4
</td>
</tr>
<tr>
<td>BoolQ (0-shot)
</td>
<td>75.7
</td>
<td>65.5
</td>
<td>66.9
</td>
<td>79.0
</td>
<td>73.1
</td>
</tr>
<tr>
<td>DROP (3-shot, F1)
</td>
<td>58.4
</td>
<td>37.9
</td>
<td>49.8
</td>
<td>79.7
</td>
<td>70.2
</td>
</tr>
</table>
### Instruction tuned models
<table>
<tr>
<td><strong>Benchmark</strong>
</td>
<td><strong>Llama 3 8B</strong>
</td>
<td><strong>Llama 2 7B</strong>
</td>
<td><strong>Llama 2 13B</strong>
</td>
<td><strong>Llama 3 70B</strong>
</td>
<td><strong>Llama 2 70B</strong>
</td>
</tr>
<tr>
<td>MMLU (5-shot)
</td>
<td>68.4
</td>
<td>34.1
</td>
<td>47.8
</td>
<td>82.0
</td>
<td>52.9
</td>
</tr>
<tr>
<td>GPQA (0-shot)
</td>
<td>34.2
</td>
<td>21.7
</td>
<td>22.3
</td>
<td>39.5
</td>
<td>21.0
</td>
</tr>
<tr>
<td>HumanEval (0-shot)
</td>
<td>62.2
</td>
<td>7.9
</td>
<td>14.0
</td>
<td>81.7
</td>
<td>25.6
</td>
</tr>
<tr>
<td>GSM-8K (8-shot, CoT)
</td>
<td>79.6
</td>
<td>25.7
</td>
<td>77.4
</td>
<td>93.0
</td>
<td>57.5
</td>
</tr>
<tr>
<td>MATH (4-shot, CoT)
</td>
<td>30.0
</td>
<td>3.8
</td>
<td>6.7
</td>
<td>50.4
</td>
<td>11.6
</td>
</tr>
</table>
### Responsibility & Safety
We believe that an open approach to AI leads to better, safer products, faster innovation, and a bigger overall market. We are committed to Responsible AI development and took a series of steps to limit misuse and harm and support the open source community.
Foundation models are widely capable technologies that are built to be used for a diverse range of applications. They are not designed to meet every developer preference on safety levels for all use cases, out-of-the-box, as those by their nature will differ across different applications.
Rather, responsible LLM-application deployment is achieved by implementing a series of safety best practices throughout the development of such applications, from the model pre-training, fine-tuning and the deployment of systems composed of safeguards to tailor the safety needs specifically to the use case and audience.
As part of the Llama 3 release, we updated our [Responsible Use Guide](https://llama.meta.com/responsible-use-guide/) to outline the steps and best practices for developers to implement model and system level safety for their application. We also provide a set of resources including [Meta Llama Guard 2](https://llama.meta.com/purple-llama/) and [Code Shield](https://llama.meta.com/purple-llama/) safeguards. These tools have proven to drastically reduce residual risks of LLM Systems, while maintaining a high level of helpfulness. We encourage developers to tune and deploy these safeguards according to their needs and we provide a [reference implementation](https://github.com/meta-llama/llama-recipes/tree/main/recipes/responsible_ai) to get you started.
#### Llama 3-Instruct
As outlined in the Responsible Use Guide, some trade-off between model helpfulness and model alignment is likely unavoidable. Developers should exercise discretion about how to weigh the benefits of alignment and helpfulness for their specific use case and audience. Developers should be mindful of residual risks when using Llama models and leverage additional safety tools as needed to reach the right safety bar for their use case.
<span style="text-decoration:underline;">Safety</span>
For our instruction tuned model, we conducted extensive red teaming exercises, performed adversarial evaluations and implemented safety mitigations techniques to lower residual risks. As with any Large Language Model, residual risks will likely remain and we recommend that developers assess these risks in the context of their use case. In parallel, we are working with the community to make AI safety benchmark standards transparent, rigorous and interpretable.
<span style="text-decoration:underline;">Refusals</span>
In addition to residual risks, we put a great emphasis on model refusals to benign prompts. Over-refusing not only can impact the user experience but could even be harmful in certain contexts as well. We’ve heard the feedback from the developer community and improved our fine tuning to ensure that Llama 3 is significantly less likely to falsely refuse to answer prompts than Llama 2.
We built internal benchmarks and developed mitigations to limit false refusals making Llama 3 our most helpful model to date.
#### Responsible release
In addition to responsible use considerations outlined above, we followed a rigorous process that requires us to take extra measures against misuse and critical risks before we make our release decision.
Misuse
If you access or use Llama 3, you agree to the Acceptable Use Policy. The most recent copy of this policy can be found at [https://llama.meta.com/llama3/use-policy/](https://llama.meta.com/llama3/use-policy/).
#### Critical risks
<span style="text-decoration:underline;">CBRNE</span> (Chemical, Biological, Radiological, Nuclear, and high yield Explosives)
We have conducted a two fold assessment of the safety of the model in this area:
* Iterative testing during model training to assess the safety of responses related to CBRNE threats and other adversarial risks.
* Involving external CBRNE experts to conduct an uplift test assessing the ability of the model to accurately provide expert knowledge and reduce barriers to potential CBRNE misuse, by reference to what can be achieved using web search (without the model).
### <span style="text-decoration:underline;">Cyber Security </span>
We have evaluated Llama 3 with CyberSecEval, Meta’s cybersecurity safety eval suite, measuring Llama 3’s propensity to suggest insecure code when used as a coding assistant, and Llama 3’s propensity to comply with requests to help carry out cyber attacks, where attacks are defined by the industry standard MITRE ATT&CK cyber attack ontology. On our insecure coding and cyber attacker helpfulness tests, Llama 3 behaved in the same range or safer than models of [equivalent coding capability](https://huggingface.co/spaces/facebook/CyberSecEval).
### <span style="text-decoration:underline;">Child Safety</span>
Child Safety risk assessments were conducted using a team of experts, to assess the model’s capability to produce outputs that could result in Child Safety risks and inform on any necessary and appropriate risk mitigations via fine tuning. We leveraged those expert red teaming sessions to expand the coverage of our evaluation benchmarks through Llama 3 model development. For Llama 3, we conducted new in-depth sessions using objective based methodologies to assess the model risks along multiple attack vectors. We also partnered with content specialists to perform red teaming exercises assessing potentially violating content while taking account of market specific nuances or experiences.
### Community
Generative AI safety requires expertise and tooling, and we believe in the strength of the open community to accelerate its progress. We are active members of open consortiums, including the AI Alliance, Partnership in AI and MLCommons, actively contributing to safety standardization and transparency. We encourage the community to adopt taxonomies like the MLCommons Proof of Concept evaluation to facilitate collaboration and transparency on safety and content evaluations. Our Purple Llama tools are open sourced for the community to use and widely distributed across ecosystem partners including cloud service providers. We encourage community contributions to our [Github repository](https://github.com/meta-llama/PurpleLlama).
Finally, we put in place a set of resources including an [output reporting mechanism](https://developers.facebook.com/llama_output_feedback) and [bug bounty program](https://www.facebook.com/whitehat) to continuously improve the Llama technology with the help of the community.
## Ethical Considerations and Limitations
The core values of Llama 3 are openness, inclusivity and helpfulness. It is meant to serve everyone, and to work for a wide range of use cases. It is thus designed to be accessible to people across many different backgrounds, experiences and perspectives. Llama 3 addresses users and their needs as they are, without insertion unnecessary judgment or normativity, while reflecting the understanding that even content that may appear problematic in some cases can serve valuable purposes in others. It respects the dignity and autonomy of all users, especially in terms of the values of free thought and expression that power innovation and progress.
But Llama 3 is a new technology, and like any new technology, there are risks associated with its use. Testing conducted to date has been in English, and has not covered, nor could it cover, all scenarios. For these reasons, as with all LLMs, Llama 3’s potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate, biased or other objectionable responses to user prompts. Therefore, before deploying any applications of Llama 3 models, developers should perform safety testing and tuning tailored to their specific applications of the model. As outlined in the Responsible Use Guide, we recommend incorporating [Purple Llama](https://github.com/facebookresearch/PurpleLlama) solutions into your workflows and specifically [Llama Guard](https://ai.meta.com/research/publications/llama-guard-llm-based-input-output-safeguard-for-human-ai-conversations/) which provides a base model to filter input and output prompts to layer system-level safety on top of model-level safety.
Please see the Responsible Use Guide available at [http://llama.meta.com/responsible-use-guide](http://llama.meta.com/responsible-use-guide)
## Citation instructions
@article{llama3modelcard,
title={Llama 3 Model Card},
author={AI@Meta},
year={2024},
url = {https://github.com/meta-llama/llama3/blob/main/MODEL_CARD.md}
}
## Contributors
Aaditya Singh; Aaron Grattafiori; Abhimanyu Dubey; Abhinav Jauhri; Abhinav Pandey; Abhishek Kadian; Adam Kelsey; Adi Gangidi; Ahmad Al-Dahle; Ahuva Goldstand; Aiesha Letman; Ajay Menon; Akhil Mathur; Alan Schelten; Alex Vaughan; Amy Yang; Andrei Lupu; Andres Alvarado; Andrew Gallagher; Andrew Gu; Andrew Ho; Andrew Poulton; Andrew Ryan; Angela Fan; Ankit Ramchandani; Anthony Hartshorn; Archi Mitra; Archie Sravankumar; Artem Korenev; Arun Rao; Ashley Gabriel; Ashwin Bharambe; Assaf Eisenman; Aston Zhang; Aurelien Rodriguez; Austen Gregerson; Ava Spataru; Baptiste Roziere; Ben Maurer; Benjamin Leonhardi; Bernie Huang; Bhargavi Paranjape; Bing Liu; Binh Tang; Bobbie Chern; Brani Stojkovic; Brian Fuller; Catalina Mejia Arenas; Chao Zhou; Charlotte Caucheteux; Chaya Nayak; Ching-Hsiang Chu; Chloe Bi; Chris Cai; Chris Cox; Chris Marra; Chris McConnell; Christian Keller; Christoph Feichtenhofer; Christophe Touret; Chunyang Wu; Corinne Wong; Cristian Canton Ferrer; Damien Allonsius; Daniel Kreymer; Daniel Haziza; Daniel Li; Danielle Pintz; Danny Livshits; Danny Wyatt; David Adkins; David Esiobu; David Xu; Davide Testuggine; Delia David; Devi Parikh; Dhruv Choudhary; Dhruv Mahajan; Diana Liskovich; Diego Garcia-Olano; Diego Perino; Dieuwke Hupkes; Dingkang Wang; Dustin Holland; Egor Lakomkin; Elina Lobanova; Xiaoqing Ellen Tan; Emily Dinan; Eric Smith; Erik Brinkman; Esteban Arcaute; Filip Radenovic; Firat Ozgenel; Francesco Caggioni; Frank Seide; Frank Zhang; Gabriel Synnaeve; Gabriella Schwarz; Gabrielle Lee; Gada Badeer; Georgia Anderson; Graeme Nail; Gregoire Mialon; Guan Pang; Guillem Cucurell; Hailey Nguyen; Hannah Korevaar; Hannah Wang; Haroun Habeeb; Harrison Rudolph; Henry Aspegren; Hu Xu; Hugo Touvron; Iga Kozlowska; Igor Molybog; Igor Tufanov; Iliyan Zarov; Imanol Arrieta Ibarra; Irina-Elena Veliche; Isabel Kloumann; Ishan Misra; Ivan Evtimov; Jacob Xu; Jade Copet; Jake Weissman; Jan Geffert; Jana Vranes; Japhet Asher; Jason Park; Jay Mahadeokar; Jean-Baptiste Gaya; Jeet Shah; Jelmer van der Linde; Jennifer Chan; Jenny Hong; Jenya Lee; Jeremy Fu; Jeremy Teboul; Jianfeng Chi; Jianyu Huang; Jie Wang; Jiecao Yu; Joanna Bitton; Joe Spisak; Joelle Pineau; Jon Carvill; Jongsoo Park; Joseph Rocca; Joshua Johnstun; Junteng Jia; Kalyan Vasuden Alwala; Kam Hou U; Kate Plawiak; Kartikeya Upasani; Kaushik Veeraraghavan; Ke Li; Kenneth Heafield; Kevin Stone; Khalid El-Arini; Krithika Iyer; Kshitiz Malik; Kuenley Chiu; Kunal Bhalla; Kyle Huang; Lakshya Garg; Lauren Rantala-Yeary; Laurens van der Maaten; Lawrence Chen; Leandro Silva; Lee Bell; Lei Zhang; Liang Tan; Louis Martin; Lovish Madaan; Luca Wehrstedt; Lukas Blecher; Luke de Oliveira; Madeline Muzzi; Madian Khabsa; Manav Avlani; Mannat Singh; Manohar Paluri; Mark Zuckerberg; Marcin Kardas; Martynas Mankus; Mathew Oldham; Mathieu Rita; Matthew Lennie; Maya Pavlova; Meghan Keneally; Melanie Kambadur; Mihir Patel; Mikayel Samvelyan; Mike Clark; Mike Lewis; Min Si; Mitesh Kumar Singh; Mo Metanat; Mona Hassan; Naman Goyal; Narjes Torabi; Nicolas Usunier; Nikolay Bashlykov; Nikolay Bogoychev; Niladri Chatterji; Ning Dong; Oliver Aobo Yang; Olivier Duchenne; Onur Celebi; Parth Parekh; Patrick Alrassy; Paul Saab; Pavan Balaji; Pedro Rittner; Pengchuan Zhang; Pengwei Li; Petar Vasic; Peter Weng; Polina Zvyagina; Prajjwal Bhargava; Pratik Dubal; Praveen Krishnan; Punit Singh Koura; Qing He; Rachel Rodriguez; Ragavan Srinivasan; Rahul Mitra; Ramon Calderer; Raymond Li; Robert Stojnic; Roberta Raileanu; Robin Battey; Rocky Wang; Rohit Girdhar; Rohit Patel; Romain Sauvestre; Ronnie Polidoro; Roshan Sumbaly; Ross Taylor; Ruan Silva; Rui Hou; Rui Wang; Russ Howes; Ruty Rinott; Saghar Hosseini; Sai Jayesh Bondu; Samyak Datta; Sanjay Singh; Sara Chugh; Sargun Dhillon; Satadru Pan; Sean Bell; Sergey Edunov; Shaoliang Nie; Sharan Narang; Sharath Raparthy; Shaun Lindsay; Sheng Feng; Sheng Shen; Shenghao Lin; Shiva Shankar; Shruti Bhosale; Shun Zhang; Simon Vandenhende; Sinong Wang; Seohyun Sonia Kim; Soumya Batra; Sten Sootla; Steve Kehoe; Suchin Gururangan; Sumit Gupta; Sunny Virk; Sydney Borodinsky; Tamar Glaser; Tamar Herman; Tamara Best; Tara Fowler; Thomas Georgiou; Thomas Scialom; Tianhe Li; Todor Mihaylov; Tong Xiao; Ujjwal Karn; Vedanuj Goswami; Vibhor Gupta; Vignesh Ramanathan; Viktor Kerkez; Vinay Satish Kumar; Vincent Gonguet; Vish Vogeti; Vlad Poenaru; Vlad Tiberiu Mihailescu; Vladan Petrovic; Vladimir Ivanov; Wei Li; Weiwei Chu; Wenhan Xiong; Wenyin Fu; Wes Bouaziz; Whitney Meers; Will Constable; Xavier Martinet; Xiaojian Wu; Xinbo Gao; Xinfeng Xie; Xuchao Jia; Yaelle Goldschlag; Yann LeCun; Yashesh Gaur; Yasmine Babaei; Ye Qi; Yenda Li; Yi Wen; Yiwen Song; Youngjin Nam; Yuchen Hao; Yuchen Zhang; Yun Wang; Yuning Mao; Yuzi He; Zacharie Delpierre Coudert; Zachary DeVito; Zahra Hankir; Zhaoduo Wen; Zheng Yan; Zhengxing Chen; Zhenyu Yang; Zoe Papakipos | {"language": ["en"], "license": "other", "tags": ["facebook", "meta", "pytorch", "llama", "llama-3"], "pipeline_tag": "text-generation", "license_name": "llama3", "license_link": "https://huggingface.co/meta-llama/Meta-Llama-3-8B/blob/main/LICENSE"} | fakezeta/llama-3-8b-instruct-ov-int8 | null | [
"transformers",
"openvino",
"llama",
"text-generation",
"facebook",
"meta",
"pytorch",
"llama-3",
"conversational",
"en",
"license:other",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-04-19T17:30:39+00:00 | [] | [
"en"
] | TAGS
#transformers #openvino #llama #text-generation #facebook #meta #pytorch #llama-3 #conversational #en #license-other #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us
| OpenVINO IR model with int8 quantization of llama-3-8B-Instruct
===============================================================
Model definition for LocalAI:
Model Details
-------------
Meta developed and released the Meta Llama 3 family of large language models (LLMs), a collection of pretrained and instruction tuned generative text models in 8 and 70B sizes. The Llama 3 instruction tuned models are optimized for dialogue use cases and outperform many of the available open source chat models on common industry benchmarks. Further, in developing these models, we took great care to optimize helpfulness and safety.
Model developers Meta
Variations Llama 3 comes in two sizes — 8B and 70B parameters — in pre-trained and instruction tuned variants.
Input Models input text only.
Output Models generate text and code only.
Model Architecture Llama 3 is an auto-regressive language model that uses an optimized transformer architecture. The tuned versions use supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF) to align with human preferences for helpfulness and safety.
Llama 3 family of models. Token counts refer to pretraining data only. Both the 8 and 70B versions use Grouped-Query Attention (GQA) for improved inference scalability.
Model Release Date April 18, 2024.
Status This is a static model trained on an offline dataset. Future versions of the tuned models will be released as we improve model safety with community feedback.
License A custom commercial license is available at: URL
Where to send questions or comments about the model Instructions on how to provide feedback or comments on the model can be found in the model README. For more technical information about generation parameters and recipes for how to use Llama 3 in applications, please go here.
Intended Use
------------
Intended Use Cases Llama 3 is intended for commercial and research use in English. Instruction tuned models are intended for assistant-like chat, whereas pretrained models can be adapted for a variety of natural language generation tasks.
Out-of-scope Use in any manner that violates applicable laws or regulations (including trade compliance laws). Use in any other way that is prohibited by the Acceptable Use Policy and Llama 3 Community License. Use in languages other than English.
Note: Developers may fine-tune Llama 3 models for languages beyond English provided they comply with the Llama 3 Community License and the Acceptable Use Policy.
How to use
----------
This repository contains two versions of Meta-Llama-3-8B, for use with transformers and with the original 'llama3' codebase.
### Use with transformers
See the snippet below for usage with Transformers:
### Use with 'llama3'
Please, follow the instructions in the repository.
To download Original checkpoints, see the example command below leveraging 'huggingface-cli':
For Hugging Face support, we recommend using transformers or TGI, but a similar command works.
Hardware and Software
---------------------
Training Factors We used custom training libraries, Meta's Research SuperCluster, and production clusters for pretraining. Fine-tuning, annotation, and evaluation were also performed on third-party cloud compute.
Carbon Footprint Pretraining utilized a cumulative 7.7M GPU hours of computation on hardware of type H100-80GB (TDP of 700W). Estimated total emissions were 2290 tCO2eq, 100% of which were offset by Meta’s sustainability program.
CO2 emissions during pre-training. Time: total GPU time required for training each model. Power Consumption: peak power capacity per GPU device for the GPUs used adjusted for power usage efficiency. 100% of the emissions are directly offset by Meta's sustainability program, and because we are openly releasing these models, the pretraining costs do not need to be incurred by others.
Training Data
-------------
Overview Llama 3 was pretrained on over 15 trillion tokens of data from publicly available sources. The fine-tuning data includes publicly available instruction datasets, as well as over 10M human-annotated examples. Neither the pretraining nor the fine-tuning datasets include Meta user data.
Data Freshness The pretraining data has a cutoff of March 2023 for the 7B and December 2023 for the 70B models respectively.
Benchmarks
----------
In this section, we report the results for Llama 3 models on standard automatic benchmarks. For all the evaluations, we use our internal evaluations library. For details on the methodology see here.
### Base pretrained models
### Instruction tuned models
### Responsibility & Safety
We believe that an open approach to AI leads to better, safer products, faster innovation, and a bigger overall market. We are committed to Responsible AI development and took a series of steps to limit misuse and harm and support the open source community.
Foundation models are widely capable technologies that are built to be used for a diverse range of applications. They are not designed to meet every developer preference on safety levels for all use cases, out-of-the-box, as those by their nature will differ across different applications.
Rather, responsible LLM-application deployment is achieved by implementing a series of safety best practices throughout the development of such applications, from the model pre-training, fine-tuning and the deployment of systems composed of safeguards to tailor the safety needs specifically to the use case and audience.
As part of the Llama 3 release, we updated our Responsible Use Guide to outline the steps and best practices for developers to implement model and system level safety for their application. We also provide a set of resources including Meta Llama Guard 2 and Code Shield safeguards. These tools have proven to drastically reduce residual risks of LLM Systems, while maintaining a high level of helpfulness. We encourage developers to tune and deploy these safeguards according to their needs and we provide a reference implementation to get you started.
#### Llama 3-Instruct
As outlined in the Responsible Use Guide, some trade-off between model helpfulness and model alignment is likely unavoidable. Developers should exercise discretion about how to weigh the benefits of alignment and helpfulness for their specific use case and audience. Developers should be mindful of residual risks when using Llama models and leverage additional safety tools as needed to reach the right safety bar for their use case.
Safety
For our instruction tuned model, we conducted extensive red teaming exercises, performed adversarial evaluations and implemented safety mitigations techniques to lower residual risks. As with any Large Language Model, residual risks will likely remain and we recommend that developers assess these risks in the context of their use case. In parallel, we are working with the community to make AI safety benchmark standards transparent, rigorous and interpretable.
Refusals
In addition to residual risks, we put a great emphasis on model refusals to benign prompts. Over-refusing not only can impact the user experience but could even be harmful in certain contexts as well. We’ve heard the feedback from the developer community and improved our fine tuning to ensure that Llama 3 is significantly less likely to falsely refuse to answer prompts than Llama 2.
We built internal benchmarks and developed mitigations to limit false refusals making Llama 3 our most helpful model to date.
#### Responsible release
In addition to responsible use considerations outlined above, we followed a rigorous process that requires us to take extra measures against misuse and critical risks before we make our release decision.
Misuse
If you access or use Llama 3, you agree to the Acceptable Use Policy. The most recent copy of this policy can be found at URL
#### Critical risks
CBRNE (Chemical, Biological, Radiological, Nuclear, and high yield Explosives)
We have conducted a two fold assessment of the safety of the model in this area:
* Iterative testing during model training to assess the safety of responses related to CBRNE threats and other adversarial risks.
* Involving external CBRNE experts to conduct an uplift test assessing the ability of the model to accurately provide expert knowledge and reduce barriers to potential CBRNE misuse, by reference to what can be achieved using web search (without the model).
### Cyber Security
We have evaluated Llama 3 with CyberSecEval, Meta’s cybersecurity safety eval suite, measuring Llama 3’s propensity to suggest insecure code when used as a coding assistant, and Llama 3’s propensity to comply with requests to help carry out cyber attacks, where attacks are defined by the industry standard MITRE ATT&CK cyber attack ontology. On our insecure coding and cyber attacker helpfulness tests, Llama 3 behaved in the same range or safer than models of equivalent coding capability.
### Child Safety
Child Safety risk assessments were conducted using a team of experts, to assess the model’s capability to produce outputs that could result in Child Safety risks and inform on any necessary and appropriate risk mitigations via fine tuning. We leveraged those expert red teaming sessions to expand the coverage of our evaluation benchmarks through Llama 3 model development. For Llama 3, we conducted new in-depth sessions using objective based methodologies to assess the model risks along multiple attack vectors. We also partnered with content specialists to perform red teaming exercises assessing potentially violating content while taking account of market specific nuances or experiences.
### Community
Generative AI safety requires expertise and tooling, and we believe in the strength of the open community to accelerate its progress. We are active members of open consortiums, including the AI Alliance, Partnership in AI and MLCommons, actively contributing to safety standardization and transparency. We encourage the community to adopt taxonomies like the MLCommons Proof of Concept evaluation to facilitate collaboration and transparency on safety and content evaluations. Our Purple Llama tools are open sourced for the community to use and widely distributed across ecosystem partners including cloud service providers. We encourage community contributions to our Github repository.
Finally, we put in place a set of resources including an output reporting mechanism and bug bounty program to continuously improve the Llama technology with the help of the community.
Ethical Considerations and Limitations
--------------------------------------
The core values of Llama 3 are openness, inclusivity and helpfulness. It is meant to serve everyone, and to work for a wide range of use cases. It is thus designed to be accessible to people across many different backgrounds, experiences and perspectives. Llama 3 addresses users and their needs as they are, without insertion unnecessary judgment or normativity, while reflecting the understanding that even content that may appear problematic in some cases can serve valuable purposes in others. It respects the dignity and autonomy of all users, especially in terms of the values of free thought and expression that power innovation and progress.
But Llama 3 is a new technology, and like any new technology, there are risks associated with its use. Testing conducted to date has been in English, and has not covered, nor could it cover, all scenarios. For these reasons, as with all LLMs, Llama 3’s potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate, biased or other objectionable responses to user prompts. Therefore, before deploying any applications of Llama 3 models, developers should perform safety testing and tuning tailored to their specific applications of the model. As outlined in the Responsible Use Guide, we recommend incorporating Purple Llama solutions into your workflows and specifically Llama Guard which provides a base model to filter input and output prompts to layer system-level safety on top of model-level safety.
Please see the Responsible Use Guide available at URL
instructions
@article{llama3modelcard,
title={Llama 3 Model Card},
author={AI@Meta},
year={2024},
url = {URL
}
Contributors
------------
Aaditya Singh; Aaron Grattafiori; Abhimanyu Dubey; Abhinav Jauhri; Abhinav Pandey; Abhishek Kadian; Adam Kelsey; Adi Gangidi; Ahmad Al-Dahle; Ahuva Goldstand; Aiesha Letman; Ajay Menon; Akhil Mathur; Alan Schelten; Alex Vaughan; Amy Yang; Andrei Lupu; Andres Alvarado; Andrew Gallagher; Andrew Gu; Andrew Ho; Andrew Poulton; Andrew Ryan; Angela Fan; Ankit Ramchandani; Anthony Hartshorn; Archi Mitra; Archie Sravankumar; Artem Korenev; Arun Rao; Ashley Gabriel; Ashwin Bharambe; Assaf Eisenman; Aston Zhang; Aurelien Rodriguez; Austen Gregerson; Ava Spataru; Baptiste Roziere; Ben Maurer; Benjamin Leonhardi; Bernie Huang; Bhargavi Paranjape; Bing Liu; Binh Tang; Bobbie Chern; Brani Stojkovic; Brian Fuller; Catalina Mejia Arenas; Chao Zhou; Charlotte Caucheteux; Chaya Nayak; Ching-Hsiang Chu; Chloe Bi; Chris Cai; Chris Cox; Chris Marra; Chris McConnell; Christian Keller; Christoph Feichtenhofer; Christophe Touret; Chunyang Wu; Corinne Wong; Cristian Canton Ferrer; Damien Allonsius; Daniel Kreymer; Daniel Haziza; Daniel Li; Danielle Pintz; Danny Livshits; Danny Wyatt; David Adkins; David Esiobu; David Xu; Davide Testuggine; Delia David; Devi Parikh; Dhruv Choudhary; Dhruv Mahajan; Diana Liskovich; Diego Garcia-Olano; Diego Perino; Dieuwke Hupkes; Dingkang Wang; Dustin Holland; Egor Lakomkin; Elina Lobanova; Xiaoqing Ellen Tan; Emily Dinan; Eric Smith; Erik Brinkman; Esteban Arcaute; Filip Radenovic; Firat Ozgenel; Francesco Caggioni; Frank Seide; Frank Zhang; Gabriel Synnaeve; Gabriella Schwarz; Gabrielle Lee; Gada Badeer; Georgia Anderson; Graeme Nail; Gregoire Mialon; Guan Pang; Guillem Cucurell; Hailey Nguyen; Hannah Korevaar; Hannah Wang; Haroun Habeeb; Harrison Rudolph; Henry Aspegren; Hu Xu; Hugo Touvron; Iga Kozlowska; Igor Molybog; Igor Tufanov; Iliyan Zarov; Imanol Arrieta Ibarra; Irina-Elena Veliche; Isabel Kloumann; Ishan Misra; Ivan Evtimov; Jacob Xu; Jade Copet; Jake Weissman; Jan Geffert; Jana Vranes; Japhet Asher; Jason Park; Jay Mahadeokar; Jean-Baptiste Gaya; Jeet Shah; Jelmer van der Linde; Jennifer Chan; Jenny Hong; Jenya Lee; Jeremy Fu; Jeremy Teboul; Jianfeng Chi; Jianyu Huang; Jie Wang; Jiecao Yu; Joanna Bitton; Joe Spisak; Joelle Pineau; Jon Carvill; Jongsoo Park; Joseph Rocca; Joshua Johnstun; Junteng Jia; Kalyan Vasuden Alwala; Kam Hou U; Kate Plawiak; Kartikeya Upasani; Kaushik Veeraraghavan; Ke Li; Kenneth Heafield; Kevin Stone; Khalid El-Arini; Krithika Iyer; Kshitiz Malik; Kuenley Chiu; Kunal Bhalla; Kyle Huang; Lakshya Garg; Lauren Rantala-Yeary; Laurens van der Maaten; Lawrence Chen; Leandro Silva; Lee Bell; Lei Zhang; Liang Tan; Louis Martin; Lovish Madaan; Luca Wehrstedt; Lukas Blecher; Luke de Oliveira; Madeline Muzzi; Madian Khabsa; Manav Avlani; Mannat Singh; Manohar Paluri; Mark Zuckerberg; Marcin Kardas; Martynas Mankus; Mathew Oldham; Mathieu Rita; Matthew Lennie; Maya Pavlova; Meghan Keneally; Melanie Kambadur; Mihir Patel; Mikayel Samvelyan; Mike Clark; Mike Lewis; Min Si; Mitesh Kumar Singh; Mo Metanat; Mona Hassan; Naman Goyal; Narjes Torabi; Nicolas Usunier; Nikolay Bashlykov; Nikolay Bogoychev; Niladri Chatterji; Ning Dong; Oliver Aobo Yang; Olivier Duchenne; Onur Celebi; Parth Parekh; Patrick Alrassy; Paul Saab; Pavan Balaji; Pedro Rittner; Pengchuan Zhang; Pengwei Li; Petar Vasic; Peter Weng; Polina Zvyagina; Prajjwal Bhargava; Pratik Dubal; Praveen Krishnan; Punit Singh Koura; Qing He; Rachel Rodriguez; Ragavan Srinivasan; Rahul Mitra; Ramon Calderer; Raymond Li; Robert Stojnic; Roberta Raileanu; Robin Battey; Rocky Wang; Rohit Girdhar; Rohit Patel; Romain Sauvestre; Ronnie Polidoro; Roshan Sumbaly; Ross Taylor; Ruan Silva; Rui Hou; Rui Wang; Russ Howes; Ruty Rinott; Saghar Hosseini; Sai Jayesh Bondu; Samyak Datta; Sanjay Singh; Sara Chugh; Sargun Dhillon; Satadru Pan; Sean Bell; Sergey Edunov; Shaoliang Nie; Sharan Narang; Sharath Raparthy; Shaun Lindsay; Sheng Feng; Sheng Shen; Shenghao Lin; Shiva Shankar; Shruti Bhosale; Shun Zhang; Simon Vandenhende; Sinong Wang; Seohyun Sonia Kim; Soumya Batra; Sten Sootla; Steve Kehoe; Suchin Gururangan; Sumit Gupta; Sunny Virk; Sydney Borodinsky; Tamar Glaser; Tamar Herman; Tamara Best; Tara Fowler; Thomas Georgiou; Thomas Scialom; Tianhe Li; Todor Mihaylov; Tong Xiao; Ujjwal Karn; Vedanuj Goswami; Vibhor Gupta; Vignesh Ramanathan; Viktor Kerkez; Vinay Satish Kumar; Vincent Gonguet; Vish Vogeti; Vlad Poenaru; Vlad Tiberiu Mihailescu; Vladan Petrovic; Vladimir Ivanov; Wei Li; Weiwei Chu; Wenhan Xiong; Wenyin Fu; Wes Bouaziz; Whitney Meers; Will Constable; Xavier Martinet; Xiaojian Wu; Xinbo Gao; Xinfeng Xie; Xuchao Jia; Yaelle Goldschlag; Yann LeCun; Yashesh Gaur; Yasmine Babaei; Ye Qi; Yenda Li; Yi Wen; Yiwen Song; Youngjin Nam; Yuchen Hao; Yuchen Zhang; Yun Wang; Yuning Mao; Yuzi He; Zacharie Delpierre Coudert; Zachary DeVito; Zahra Hankir; Zhaoduo Wen; Zheng Yan; Zhengxing Chen; Zhenyu Yang; Zoe Papakipos
| [
"### Use with transformers\n\n\nSee the snippet below for usage with Transformers:",
"### Use with 'llama3'\n\n\nPlease, follow the instructions in the repository.\n\n\nTo download Original checkpoints, see the example command below leveraging 'huggingface-cli':\n\n\nFor Hugging Face support, we recommend using transformers or TGI, but a similar command works.\n\n\nHardware and Software\n---------------------\n\n\nTraining Factors We used custom training libraries, Meta's Research SuperCluster, and production clusters for pretraining. Fine-tuning, annotation, and evaluation were also performed on third-party cloud compute.\n\n\nCarbon Footprint Pretraining utilized a cumulative 7.7M GPU hours of computation on hardware of type H100-80GB (TDP of 700W). Estimated total emissions were 2290 tCO2eq, 100% of which were offset by Meta’s sustainability program.\n\n\n\nCO2 emissions during pre-training. Time: total GPU time required for training each model. Power Consumption: peak power capacity per GPU device for the GPUs used adjusted for power usage efficiency. 100% of the emissions are directly offset by Meta's sustainability program, and because we are openly releasing these models, the pretraining costs do not need to be incurred by others.\n\n\nTraining Data\n-------------\n\n\nOverview Llama 3 was pretrained on over 15 trillion tokens of data from publicly available sources. The fine-tuning data includes publicly available instruction datasets, as well as over 10M human-annotated examples. Neither the pretraining nor the fine-tuning datasets include Meta user data.\n\n\nData Freshness The pretraining data has a cutoff of March 2023 for the 7B and December 2023 for the 70B models respectively.\n\n\nBenchmarks\n----------\n\n\nIn this section, we report the results for Llama 3 models on standard automatic benchmarks. For all the evaluations, we use our internal evaluations library. For details on the methodology see here.",
"### Base pretrained models",
"### Instruction tuned models",
"### Responsibility & Safety\n\n\nWe believe that an open approach to AI leads to better, safer products, faster innovation, and a bigger overall market. We are committed to Responsible AI development and took a series of steps to limit misuse and harm and support the open source community.\n\n\nFoundation models are widely capable technologies that are built to be used for a diverse range of applications. They are not designed to meet every developer preference on safety levels for all use cases, out-of-the-box, as those by their nature will differ across different applications.\n\n\nRather, responsible LLM-application deployment is achieved by implementing a series of safety best practices throughout the development of such applications, from the model pre-training, fine-tuning and the deployment of systems composed of safeguards to tailor the safety needs specifically to the use case and audience.\n\n\nAs part of the Llama 3 release, we updated our Responsible Use Guide to outline the steps and best practices for developers to implement model and system level safety for their application. We also provide a set of resources including Meta Llama Guard 2 and Code Shield safeguards. These tools have proven to drastically reduce residual risks of LLM Systems, while maintaining a high level of helpfulness. We encourage developers to tune and deploy these safeguards according to their needs and we provide a reference implementation to get you started.",
"#### Llama 3-Instruct\n\n\nAs outlined in the Responsible Use Guide, some trade-off between model helpfulness and model alignment is likely unavoidable. Developers should exercise discretion about how to weigh the benefits of alignment and helpfulness for their specific use case and audience. Developers should be mindful of residual risks when using Llama models and leverage additional safety tools as needed to reach the right safety bar for their use case.\n\n\nSafety\n\n\nFor our instruction tuned model, we conducted extensive red teaming exercises, performed adversarial evaluations and implemented safety mitigations techniques to lower residual risks. As with any Large Language Model, residual risks will likely remain and we recommend that developers assess these risks in the context of their use case. In parallel, we are working with the community to make AI safety benchmark standards transparent, rigorous and interpretable.\n\n\nRefusals\n\n\nIn addition to residual risks, we put a great emphasis on model refusals to benign prompts. Over-refusing not only can impact the user experience but could even be harmful in certain contexts as well. We’ve heard the feedback from the developer community and improved our fine tuning to ensure that Llama 3 is significantly less likely to falsely refuse to answer prompts than Llama 2.\n\n\nWe built internal benchmarks and developed mitigations to limit false refusals making Llama 3 our most helpful model to date.",
"#### Responsible release\n\n\nIn addition to responsible use considerations outlined above, we followed a rigorous process that requires us to take extra measures against misuse and critical risks before we make our release decision.\n\n\nMisuse\n\n\nIf you access or use Llama 3, you agree to the Acceptable Use Policy. The most recent copy of this policy can be found at URL",
"#### Critical risks\n\n\nCBRNE (Chemical, Biological, Radiological, Nuclear, and high yield Explosives)\n\n\nWe have conducted a two fold assessment of the safety of the model in this area:\n\n\n* Iterative testing during model training to assess the safety of responses related to CBRNE threats and other adversarial risks.\n* Involving external CBRNE experts to conduct an uplift test assessing the ability of the model to accurately provide expert knowledge and reduce barriers to potential CBRNE misuse, by reference to what can be achieved using web search (without the model).",
"### Cyber Security\n\n\nWe have evaluated Llama 3 with CyberSecEval, Meta’s cybersecurity safety eval suite, measuring Llama 3’s propensity to suggest insecure code when used as a coding assistant, and Llama 3’s propensity to comply with requests to help carry out cyber attacks, where attacks are defined by the industry standard MITRE ATT&CK cyber attack ontology. On our insecure coding and cyber attacker helpfulness tests, Llama 3 behaved in the same range or safer than models of equivalent coding capability.",
"### Child Safety\n\n\nChild Safety risk assessments were conducted using a team of experts, to assess the model’s capability to produce outputs that could result in Child Safety risks and inform on any necessary and appropriate risk mitigations via fine tuning. We leveraged those expert red teaming sessions to expand the coverage of our evaluation benchmarks through Llama 3 model development. For Llama 3, we conducted new in-depth sessions using objective based methodologies to assess the model risks along multiple attack vectors. We also partnered with content specialists to perform red teaming exercises assessing potentially violating content while taking account of market specific nuances or experiences.",
"### Community\n\n\nGenerative AI safety requires expertise and tooling, and we believe in the strength of the open community to accelerate its progress. We are active members of open consortiums, including the AI Alliance, Partnership in AI and MLCommons, actively contributing to safety standardization and transparency. We encourage the community to adopt taxonomies like the MLCommons Proof of Concept evaluation to facilitate collaboration and transparency on safety and content evaluations. Our Purple Llama tools are open sourced for the community to use and widely distributed across ecosystem partners including cloud service providers. We encourage community contributions to our Github repository.\n\n\nFinally, we put in place a set of resources including an output reporting mechanism and bug bounty program to continuously improve the Llama technology with the help of the community.\n\n\nEthical Considerations and Limitations\n--------------------------------------\n\n\nThe core values of Llama 3 are openness, inclusivity and helpfulness. It is meant to serve everyone, and to work for a wide range of use cases. It is thus designed to be accessible to people across many different backgrounds, experiences and perspectives. Llama 3 addresses users and their needs as they are, without insertion unnecessary judgment or normativity, while reflecting the understanding that even content that may appear problematic in some cases can serve valuable purposes in others. It respects the dignity and autonomy of all users, especially in terms of the values of free thought and expression that power innovation and progress.\n\n\nBut Llama 3 is a new technology, and like any new technology, there are risks associated with its use. Testing conducted to date has been in English, and has not covered, nor could it cover, all scenarios. For these reasons, as with all LLMs, Llama 3’s potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate, biased or other objectionable responses to user prompts. Therefore, before deploying any applications of Llama 3 models, developers should perform safety testing and tuning tailored to their specific applications of the model. As outlined in the Responsible Use Guide, we recommend incorporating Purple Llama solutions into your workflows and specifically Llama Guard which provides a base model to filter input and output prompts to layer system-level safety on top of model-level safety.\n\n\nPlease see the Responsible Use Guide available at URL\n\n\ninstructions\n\n\n@article{llama3modelcard,\n\n\ntitle={Llama 3 Model Card},\n\n\nauthor={AI@Meta},\n\n\nyear={2024},\n\n\nurl = {URL\n\n\n}\n\n\nContributors\n------------\n\n\nAaditya Singh; Aaron Grattafiori; Abhimanyu Dubey; Abhinav Jauhri; Abhinav Pandey; Abhishek Kadian; Adam Kelsey; Adi Gangidi; Ahmad Al-Dahle; Ahuva Goldstand; Aiesha Letman; Ajay Menon; Akhil Mathur; Alan Schelten; Alex Vaughan; Amy Yang; Andrei Lupu; Andres Alvarado; Andrew Gallagher; Andrew Gu; Andrew Ho; Andrew Poulton; Andrew Ryan; Angela Fan; Ankit Ramchandani; Anthony Hartshorn; Archi Mitra; Archie Sravankumar; Artem Korenev; Arun Rao; Ashley Gabriel; Ashwin Bharambe; Assaf Eisenman; Aston Zhang; Aurelien Rodriguez; Austen Gregerson; Ava Spataru; Baptiste Roziere; Ben Maurer; Benjamin Leonhardi; Bernie Huang; Bhargavi Paranjape; Bing Liu; Binh Tang; Bobbie Chern; Brani Stojkovic; Brian Fuller; Catalina Mejia Arenas; Chao Zhou; Charlotte Caucheteux; Chaya Nayak; Ching-Hsiang Chu; Chloe Bi; Chris Cai; Chris Cox; Chris Marra; Chris McConnell; Christian Keller; Christoph Feichtenhofer; Christophe Touret; Chunyang Wu; Corinne Wong; Cristian Canton Ferrer; Damien Allonsius; Daniel Kreymer; Daniel Haziza; Daniel Li; Danielle Pintz; Danny Livshits; Danny Wyatt; David Adkins; David Esiobu; David Xu; Davide Testuggine; Delia David; Devi Parikh; Dhruv Choudhary; Dhruv Mahajan; Diana Liskovich; Diego Garcia-Olano; Diego Perino; Dieuwke Hupkes; Dingkang Wang; Dustin Holland; Egor Lakomkin; Elina Lobanova; Xiaoqing Ellen Tan; Emily Dinan; Eric Smith; Erik Brinkman; Esteban Arcaute; Filip Radenovic; Firat Ozgenel; Francesco Caggioni; Frank Seide; Frank Zhang; Gabriel Synnaeve; Gabriella Schwarz; Gabrielle Lee; Gada Badeer; Georgia Anderson; Graeme Nail; Gregoire Mialon; Guan Pang; Guillem Cucurell; Hailey Nguyen; Hannah Korevaar; Hannah Wang; Haroun Habeeb; Harrison Rudolph; Henry Aspegren; Hu Xu; Hugo Touvron; Iga Kozlowska; Igor Molybog; Igor Tufanov; Iliyan Zarov; Imanol Arrieta Ibarra; Irina-Elena Veliche; Isabel Kloumann; Ishan Misra; Ivan Evtimov; Jacob Xu; Jade Copet; Jake Weissman; Jan Geffert; Jana Vranes; Japhet Asher; Jason Park; Jay Mahadeokar; Jean-Baptiste Gaya; Jeet Shah; Jelmer van der Linde; Jennifer Chan; Jenny Hong; Jenya Lee; Jeremy Fu; Jeremy Teboul; Jianfeng Chi; Jianyu Huang; Jie Wang; Jiecao Yu; Joanna Bitton; Joe Spisak; Joelle Pineau; Jon Carvill; Jongsoo Park; Joseph Rocca; Joshua Johnstun; Junteng Jia; Kalyan Vasuden Alwala; Kam Hou U; Kate Plawiak; Kartikeya Upasani; Kaushik Veeraraghavan; Ke Li; Kenneth Heafield; Kevin Stone; Khalid El-Arini; Krithika Iyer; Kshitiz Malik; Kuenley Chiu; Kunal Bhalla; Kyle Huang; Lakshya Garg; Lauren Rantala-Yeary; Laurens van der Maaten; Lawrence Chen; Leandro Silva; Lee Bell; Lei Zhang; Liang Tan; Louis Martin; Lovish Madaan; Luca Wehrstedt; Lukas Blecher; Luke de Oliveira; Madeline Muzzi; Madian Khabsa; Manav Avlani; Mannat Singh; Manohar Paluri; Mark Zuckerberg; Marcin Kardas; Martynas Mankus; Mathew Oldham; Mathieu Rita; Matthew Lennie; Maya Pavlova; Meghan Keneally; Melanie Kambadur; Mihir Patel; Mikayel Samvelyan; Mike Clark; Mike Lewis; Min Si; Mitesh Kumar Singh; Mo Metanat; Mona Hassan; Naman Goyal; Narjes Torabi; Nicolas Usunier; Nikolay Bashlykov; Nikolay Bogoychev; Niladri Chatterji; Ning Dong; Oliver Aobo Yang; Olivier Duchenne; Onur Celebi; Parth Parekh; Patrick Alrassy; Paul Saab; Pavan Balaji; Pedro Rittner; Pengchuan Zhang; Pengwei Li; Petar Vasic; Peter Weng; Polina Zvyagina; Prajjwal Bhargava; Pratik Dubal; Praveen Krishnan; Punit Singh Koura; Qing He; Rachel Rodriguez; Ragavan Srinivasan; Rahul Mitra; Ramon Calderer; Raymond Li; Robert Stojnic; Roberta Raileanu; Robin Battey; Rocky Wang; Rohit Girdhar; Rohit Patel; Romain Sauvestre; Ronnie Polidoro; Roshan Sumbaly; Ross Taylor; Ruan Silva; Rui Hou; Rui Wang; Russ Howes; Ruty Rinott; Saghar Hosseini; Sai Jayesh Bondu; Samyak Datta; Sanjay Singh; Sara Chugh; Sargun Dhillon; Satadru Pan; Sean Bell; Sergey Edunov; Shaoliang Nie; Sharan Narang; Sharath Raparthy; Shaun Lindsay; Sheng Feng; Sheng Shen; Shenghao Lin; Shiva Shankar; Shruti Bhosale; Shun Zhang; Simon Vandenhende; Sinong Wang; Seohyun Sonia Kim; Soumya Batra; Sten Sootla; Steve Kehoe; Suchin Gururangan; Sumit Gupta; Sunny Virk; Sydney Borodinsky; Tamar Glaser; Tamar Herman; Tamara Best; Tara Fowler; Thomas Georgiou; Thomas Scialom; Tianhe Li; Todor Mihaylov; Tong Xiao; Ujjwal Karn; Vedanuj Goswami; Vibhor Gupta; Vignesh Ramanathan; Viktor Kerkez; Vinay Satish Kumar; Vincent Gonguet; Vish Vogeti; Vlad Poenaru; Vlad Tiberiu Mihailescu; Vladan Petrovic; Vladimir Ivanov; Wei Li; Weiwei Chu; Wenhan Xiong; Wenyin Fu; Wes Bouaziz; Whitney Meers; Will Constable; Xavier Martinet; Xiaojian Wu; Xinbo Gao; Xinfeng Xie; Xuchao Jia; Yaelle Goldschlag; Yann LeCun; Yashesh Gaur; Yasmine Babaei; Ye Qi; Yenda Li; Yi Wen; Yiwen Song; Youngjin Nam; Yuchen Hao; Yuchen Zhang; Yun Wang; Yuning Mao; Yuzi He; Zacharie Delpierre Coudert; Zachary DeVito; Zahra Hankir; Zhaoduo Wen; Zheng Yan; Zhengxing Chen; Zhenyu Yang; Zoe Papakipos"
] | [
"TAGS\n#transformers #openvino #llama #text-generation #facebook #meta #pytorch #llama-3 #conversational #en #license-other #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n",
"### Use with transformers\n\n\nSee the snippet below for usage with Transformers:",
"### Use with 'llama3'\n\n\nPlease, follow the instructions in the repository.\n\n\nTo download Original checkpoints, see the example command below leveraging 'huggingface-cli':\n\n\nFor Hugging Face support, we recommend using transformers or TGI, but a similar command works.\n\n\nHardware and Software\n---------------------\n\n\nTraining Factors We used custom training libraries, Meta's Research SuperCluster, and production clusters for pretraining. Fine-tuning, annotation, and evaluation were also performed on third-party cloud compute.\n\n\nCarbon Footprint Pretraining utilized a cumulative 7.7M GPU hours of computation on hardware of type H100-80GB (TDP of 700W). Estimated total emissions were 2290 tCO2eq, 100% of which were offset by Meta’s sustainability program.\n\n\n\nCO2 emissions during pre-training. Time: total GPU time required for training each model. Power Consumption: peak power capacity per GPU device for the GPUs used adjusted for power usage efficiency. 100% of the emissions are directly offset by Meta's sustainability program, and because we are openly releasing these models, the pretraining costs do not need to be incurred by others.\n\n\nTraining Data\n-------------\n\n\nOverview Llama 3 was pretrained on over 15 trillion tokens of data from publicly available sources. The fine-tuning data includes publicly available instruction datasets, as well as over 10M human-annotated examples. Neither the pretraining nor the fine-tuning datasets include Meta user data.\n\n\nData Freshness The pretraining data has a cutoff of March 2023 for the 7B and December 2023 for the 70B models respectively.\n\n\nBenchmarks\n----------\n\n\nIn this section, we report the results for Llama 3 models on standard automatic benchmarks. For all the evaluations, we use our internal evaluations library. For details on the methodology see here.",
"### Base pretrained models",
"### Instruction tuned models",
"### Responsibility & Safety\n\n\nWe believe that an open approach to AI leads to better, safer products, faster innovation, and a bigger overall market. We are committed to Responsible AI development and took a series of steps to limit misuse and harm and support the open source community.\n\n\nFoundation models are widely capable technologies that are built to be used for a diverse range of applications. They are not designed to meet every developer preference on safety levels for all use cases, out-of-the-box, as those by their nature will differ across different applications.\n\n\nRather, responsible LLM-application deployment is achieved by implementing a series of safety best practices throughout the development of such applications, from the model pre-training, fine-tuning and the deployment of systems composed of safeguards to tailor the safety needs specifically to the use case and audience.\n\n\nAs part of the Llama 3 release, we updated our Responsible Use Guide to outline the steps and best practices for developers to implement model and system level safety for their application. We also provide a set of resources including Meta Llama Guard 2 and Code Shield safeguards. These tools have proven to drastically reduce residual risks of LLM Systems, while maintaining a high level of helpfulness. We encourage developers to tune and deploy these safeguards according to their needs and we provide a reference implementation to get you started.",
"#### Llama 3-Instruct\n\n\nAs outlined in the Responsible Use Guide, some trade-off between model helpfulness and model alignment is likely unavoidable. Developers should exercise discretion about how to weigh the benefits of alignment and helpfulness for their specific use case and audience. Developers should be mindful of residual risks when using Llama models and leverage additional safety tools as needed to reach the right safety bar for their use case.\n\n\nSafety\n\n\nFor our instruction tuned model, we conducted extensive red teaming exercises, performed adversarial evaluations and implemented safety mitigations techniques to lower residual risks. As with any Large Language Model, residual risks will likely remain and we recommend that developers assess these risks in the context of their use case. In parallel, we are working with the community to make AI safety benchmark standards transparent, rigorous and interpretable.\n\n\nRefusals\n\n\nIn addition to residual risks, we put a great emphasis on model refusals to benign prompts. Over-refusing not only can impact the user experience but could even be harmful in certain contexts as well. We’ve heard the feedback from the developer community and improved our fine tuning to ensure that Llama 3 is significantly less likely to falsely refuse to answer prompts than Llama 2.\n\n\nWe built internal benchmarks and developed mitigations to limit false refusals making Llama 3 our most helpful model to date.",
"#### Responsible release\n\n\nIn addition to responsible use considerations outlined above, we followed a rigorous process that requires us to take extra measures against misuse and critical risks before we make our release decision.\n\n\nMisuse\n\n\nIf you access or use Llama 3, you agree to the Acceptable Use Policy. The most recent copy of this policy can be found at URL",
"#### Critical risks\n\n\nCBRNE (Chemical, Biological, Radiological, Nuclear, and high yield Explosives)\n\n\nWe have conducted a two fold assessment of the safety of the model in this area:\n\n\n* Iterative testing during model training to assess the safety of responses related to CBRNE threats and other adversarial risks.\n* Involving external CBRNE experts to conduct an uplift test assessing the ability of the model to accurately provide expert knowledge and reduce barriers to potential CBRNE misuse, by reference to what can be achieved using web search (without the model).",
"### Cyber Security\n\n\nWe have evaluated Llama 3 with CyberSecEval, Meta’s cybersecurity safety eval suite, measuring Llama 3’s propensity to suggest insecure code when used as a coding assistant, and Llama 3’s propensity to comply with requests to help carry out cyber attacks, where attacks are defined by the industry standard MITRE ATT&CK cyber attack ontology. On our insecure coding and cyber attacker helpfulness tests, Llama 3 behaved in the same range or safer than models of equivalent coding capability.",
"### Child Safety\n\n\nChild Safety risk assessments were conducted using a team of experts, to assess the model’s capability to produce outputs that could result in Child Safety risks and inform on any necessary and appropriate risk mitigations via fine tuning. We leveraged those expert red teaming sessions to expand the coverage of our evaluation benchmarks through Llama 3 model development. For Llama 3, we conducted new in-depth sessions using objective based methodologies to assess the model risks along multiple attack vectors. We also partnered with content specialists to perform red teaming exercises assessing potentially violating content while taking account of market specific nuances or experiences.",
"### Community\n\n\nGenerative AI safety requires expertise and tooling, and we believe in the strength of the open community to accelerate its progress. We are active members of open consortiums, including the AI Alliance, Partnership in AI and MLCommons, actively contributing to safety standardization and transparency. We encourage the community to adopt taxonomies like the MLCommons Proof of Concept evaluation to facilitate collaboration and transparency on safety and content evaluations. Our Purple Llama tools are open sourced for the community to use and widely distributed across ecosystem partners including cloud service providers. We encourage community contributions to our Github repository.\n\n\nFinally, we put in place a set of resources including an output reporting mechanism and bug bounty program to continuously improve the Llama technology with the help of the community.\n\n\nEthical Considerations and Limitations\n--------------------------------------\n\n\nThe core values of Llama 3 are openness, inclusivity and helpfulness. It is meant to serve everyone, and to work for a wide range of use cases. It is thus designed to be accessible to people across many different backgrounds, experiences and perspectives. Llama 3 addresses users and their needs as they are, without insertion unnecessary judgment or normativity, while reflecting the understanding that even content that may appear problematic in some cases can serve valuable purposes in others. It respects the dignity and autonomy of all users, especially in terms of the values of free thought and expression that power innovation and progress.\n\n\nBut Llama 3 is a new technology, and like any new technology, there are risks associated with its use. Testing conducted to date has been in English, and has not covered, nor could it cover, all scenarios. For these reasons, as with all LLMs, Llama 3’s potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate, biased or other objectionable responses to user prompts. Therefore, before deploying any applications of Llama 3 models, developers should perform safety testing and tuning tailored to their specific applications of the model. As outlined in the Responsible Use Guide, we recommend incorporating Purple Llama solutions into your workflows and specifically Llama Guard which provides a base model to filter input and output prompts to layer system-level safety on top of model-level safety.\n\n\nPlease see the Responsible Use Guide available at URL\n\n\ninstructions\n\n\n@article{llama3modelcard,\n\n\ntitle={Llama 3 Model Card},\n\n\nauthor={AI@Meta},\n\n\nyear={2024},\n\n\nurl = {URL\n\n\n}\n\n\nContributors\n------------\n\n\nAaditya Singh; Aaron Grattafiori; Abhimanyu Dubey; Abhinav Jauhri; Abhinav Pandey; Abhishek Kadian; Adam Kelsey; Adi Gangidi; Ahmad Al-Dahle; Ahuva Goldstand; Aiesha Letman; Ajay Menon; Akhil Mathur; Alan Schelten; Alex Vaughan; Amy Yang; Andrei Lupu; Andres Alvarado; Andrew Gallagher; Andrew Gu; Andrew Ho; Andrew Poulton; Andrew Ryan; Angela Fan; Ankit Ramchandani; Anthony Hartshorn; Archi Mitra; Archie Sravankumar; Artem Korenev; Arun Rao; Ashley Gabriel; Ashwin Bharambe; Assaf Eisenman; Aston Zhang; Aurelien Rodriguez; Austen Gregerson; Ava Spataru; Baptiste Roziere; Ben Maurer; Benjamin Leonhardi; Bernie Huang; Bhargavi Paranjape; Bing Liu; Binh Tang; Bobbie Chern; Brani Stojkovic; Brian Fuller; Catalina Mejia Arenas; Chao Zhou; Charlotte Caucheteux; Chaya Nayak; Ching-Hsiang Chu; Chloe Bi; Chris Cai; Chris Cox; Chris Marra; Chris McConnell; Christian Keller; Christoph Feichtenhofer; Christophe Touret; Chunyang Wu; Corinne Wong; Cristian Canton Ferrer; Damien Allonsius; Daniel Kreymer; Daniel Haziza; Daniel Li; Danielle Pintz; Danny Livshits; Danny Wyatt; David Adkins; David Esiobu; David Xu; Davide Testuggine; Delia David; Devi Parikh; Dhruv Choudhary; Dhruv Mahajan; Diana Liskovich; Diego Garcia-Olano; Diego Perino; Dieuwke Hupkes; Dingkang Wang; Dustin Holland; Egor Lakomkin; Elina Lobanova; Xiaoqing Ellen Tan; Emily Dinan; Eric Smith; Erik Brinkman; Esteban Arcaute; Filip Radenovic; Firat Ozgenel; Francesco Caggioni; Frank Seide; Frank Zhang; Gabriel Synnaeve; Gabriella Schwarz; Gabrielle Lee; Gada Badeer; Georgia Anderson; Graeme Nail; Gregoire Mialon; Guan Pang; Guillem Cucurell; Hailey Nguyen; Hannah Korevaar; Hannah Wang; Haroun Habeeb; Harrison Rudolph; Henry Aspegren; Hu Xu; Hugo Touvron; Iga Kozlowska; Igor Molybog; Igor Tufanov; Iliyan Zarov; Imanol Arrieta Ibarra; Irina-Elena Veliche; Isabel Kloumann; Ishan Misra; Ivan Evtimov; Jacob Xu; Jade Copet; Jake Weissman; Jan Geffert; Jana Vranes; Japhet Asher; Jason Park; Jay Mahadeokar; Jean-Baptiste Gaya; Jeet Shah; Jelmer van der Linde; Jennifer Chan; Jenny Hong; Jenya Lee; Jeremy Fu; Jeremy Teboul; Jianfeng Chi; Jianyu Huang; Jie Wang; Jiecao Yu; Joanna Bitton; Joe Spisak; Joelle Pineau; Jon Carvill; Jongsoo Park; Joseph Rocca; Joshua Johnstun; Junteng Jia; Kalyan Vasuden Alwala; Kam Hou U; Kate Plawiak; Kartikeya Upasani; Kaushik Veeraraghavan; Ke Li; Kenneth Heafield; Kevin Stone; Khalid El-Arini; Krithika Iyer; Kshitiz Malik; Kuenley Chiu; Kunal Bhalla; Kyle Huang; Lakshya Garg; Lauren Rantala-Yeary; Laurens van der Maaten; Lawrence Chen; Leandro Silva; Lee Bell; Lei Zhang; Liang Tan; Louis Martin; Lovish Madaan; Luca Wehrstedt; Lukas Blecher; Luke de Oliveira; Madeline Muzzi; Madian Khabsa; Manav Avlani; Mannat Singh; Manohar Paluri; Mark Zuckerberg; Marcin Kardas; Martynas Mankus; Mathew Oldham; Mathieu Rita; Matthew Lennie; Maya Pavlova; Meghan Keneally; Melanie Kambadur; Mihir Patel; Mikayel Samvelyan; Mike Clark; Mike Lewis; Min Si; Mitesh Kumar Singh; Mo Metanat; Mona Hassan; Naman Goyal; Narjes Torabi; Nicolas Usunier; Nikolay Bashlykov; Nikolay Bogoychev; Niladri Chatterji; Ning Dong; Oliver Aobo Yang; Olivier Duchenne; Onur Celebi; Parth Parekh; Patrick Alrassy; Paul Saab; Pavan Balaji; Pedro Rittner; Pengchuan Zhang; Pengwei Li; Petar Vasic; Peter Weng; Polina Zvyagina; Prajjwal Bhargava; Pratik Dubal; Praveen Krishnan; Punit Singh Koura; Qing He; Rachel Rodriguez; Ragavan Srinivasan; Rahul Mitra; Ramon Calderer; Raymond Li; Robert Stojnic; Roberta Raileanu; Robin Battey; Rocky Wang; Rohit Girdhar; Rohit Patel; Romain Sauvestre; Ronnie Polidoro; Roshan Sumbaly; Ross Taylor; Ruan Silva; Rui Hou; Rui Wang; Russ Howes; Ruty Rinott; Saghar Hosseini; Sai Jayesh Bondu; Samyak Datta; Sanjay Singh; Sara Chugh; Sargun Dhillon; Satadru Pan; Sean Bell; Sergey Edunov; Shaoliang Nie; Sharan Narang; Sharath Raparthy; Shaun Lindsay; Sheng Feng; Sheng Shen; Shenghao Lin; Shiva Shankar; Shruti Bhosale; Shun Zhang; Simon Vandenhende; Sinong Wang; Seohyun Sonia Kim; Soumya Batra; Sten Sootla; Steve Kehoe; Suchin Gururangan; Sumit Gupta; Sunny Virk; Sydney Borodinsky; Tamar Glaser; Tamar Herman; Tamara Best; Tara Fowler; Thomas Georgiou; Thomas Scialom; Tianhe Li; Todor Mihaylov; Tong Xiao; Ujjwal Karn; Vedanuj Goswami; Vibhor Gupta; Vignesh Ramanathan; Viktor Kerkez; Vinay Satish Kumar; Vincent Gonguet; Vish Vogeti; Vlad Poenaru; Vlad Tiberiu Mihailescu; Vladan Petrovic; Vladimir Ivanov; Wei Li; Weiwei Chu; Wenhan Xiong; Wenyin Fu; Wes Bouaziz; Whitney Meers; Will Constable; Xavier Martinet; Xiaojian Wu; Xinbo Gao; Xinfeng Xie; Xuchao Jia; Yaelle Goldschlag; Yann LeCun; Yashesh Gaur; Yasmine Babaei; Ye Qi; Yenda Li; Yi Wen; Yiwen Song; Youngjin Nam; Yuchen Hao; Yuchen Zhang; Yun Wang; Yuning Mao; Yuzi He; Zacharie Delpierre Coudert; Zachary DeVito; Zahra Hankir; Zhaoduo Wen; Zheng Yan; Zhengxing Chen; Zhenyu Yang; Zoe Papakipos"
] |
text2text-generation | transformers |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# UrduSum10
This model is a fine-tuned version of [ahmed0189/mT5-Arabic-text-summarization](https://huggingface.co/ahmed0189/mT5-Arabic-text-summarization) on the None dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 1
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
| No log | 1.0 | 450 | 4.9510 | 0.0 | 0.0 | 0.0 | 0.0 | 30.7383 |
### Framework versions
- Transformers 4.28.0
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.13.3
| {"license": "apache-2.0", "tags": ["generated_from_trainer"], "model-index": [{"name": "UrduSum10", "results": []}]} | Alefiah/UrduSum10 | null | [
"transformers",
"pytorch",
"tensorboard",
"mt5",
"text2text-generation",
"generated_from_trainer",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-04-19T17:31:20+00:00 | [] | [] | TAGS
#transformers #pytorch #tensorboard #mt5 #text2text-generation #generated_from_trainer #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us
| UrduSum10
=========
This model is a fine-tuned version of ahmed0189/mT5-Arabic-text-summarization on the None dataset.
Model description
-----------------
More information needed
Intended uses & limitations
---------------------------
More information needed
Training and evaluation data
----------------------------
More information needed
Training procedure
------------------
### Training hyperparameters
The following hyperparameters were used during training:
* learning\_rate: 2e-05
* train\_batch\_size: 2
* eval\_batch\_size: 2
* seed: 42
* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
* lr\_scheduler\_type: linear
* num\_epochs: 1
* mixed\_precision\_training: Native AMP
### Training results
### Framework versions
* Transformers 4.28.0
* Pytorch 2.2.1+cu121
* Datasets 2.19.0
* Tokenizers 0.13.3
| [
"### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 2e-05\n* train\\_batch\\_size: 2\n* eval\\_batch\\_size: 2\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 1\n* mixed\\_precision\\_training: Native AMP",
"### Training results",
"### Framework versions\n\n\n* Transformers 4.28.0\n* Pytorch 2.2.1+cu121\n* Datasets 2.19.0\n* Tokenizers 0.13.3"
] | [
"TAGS\n#transformers #pytorch #tensorboard #mt5 #text2text-generation #generated_from_trainer #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n",
"### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 2e-05\n* train\\_batch\\_size: 2\n* eval\\_batch\\_size: 2\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 1\n* mixed\\_precision\\_training: Native AMP",
"### Training results",
"### Framework versions\n\n\n* Transformers 4.28.0\n* Pytorch 2.2.1+cu121\n* Datasets 2.19.0\n* Tokenizers 0.13.3"
] |
text2text-generation | transformers |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# flant5-small-running-v3
This model is a fine-tuned version of [google/flan-t5-small](https://huggingface.co/google/flan-t5-small) on an unknown dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
### Training results
### Framework versions
- Transformers 4.39.3
- Pytorch 2.1.2
- Datasets 2.19.0
- Tokenizers 0.15.2
| {"license": "apache-2.0", "tags": ["generated_from_trainer"], "base_model": "google/flan-t5-small", "model-index": [{"name": "flant5-small-running-v3", "results": []}]} | dtruong46me/flant5-small-running-v3 | null | [
"transformers",
"safetensors",
"t5",
"text2text-generation",
"generated_from_trainer",
"base_model:google/flan-t5-small",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-04-19T17:31:36+00:00 | [] | [] | TAGS
#transformers #safetensors #t5 #text2text-generation #generated_from_trainer #base_model-google/flan-t5-small #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us
|
# flant5-small-running-v3
This model is a fine-tuned version of google/flan-t5-small on an unknown dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
### Training results
### Framework versions
- Transformers 4.39.3
- Pytorch 2.1.2
- Datasets 2.19.0
- Tokenizers 0.15.2
| [
"# flant5-small-running-v3\n\nThis model is a fine-tuned version of google/flan-t5-small on an unknown dataset.",
"## Model description\n\nMore information needed",
"## Intended uses & limitations\n\nMore information needed",
"## Training and evaluation data\n\nMore information needed",
"## Training procedure",
"### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 5e-05\n- train_batch_size: 8\n- eval_batch_size: 8\n- seed: 42\n- gradient_accumulation_steps: 4\n- total_train_batch_size: 32\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 3",
"### Training results",
"### Framework versions\n\n- Transformers 4.39.3\n- Pytorch 2.1.2\n- Datasets 2.19.0\n- Tokenizers 0.15.2"
] | [
"TAGS\n#transformers #safetensors #t5 #text2text-generation #generated_from_trainer #base_model-google/flan-t5-small #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n",
"# flant5-small-running-v3\n\nThis model is a fine-tuned version of google/flan-t5-small on an unknown dataset.",
"## Model description\n\nMore information needed",
"## Intended uses & limitations\n\nMore information needed",
"## Training and evaluation data\n\nMore information needed",
"## Training procedure",
"### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 5e-05\n- train_batch_size: 8\n- eval_batch_size: 8\n- seed: 42\n- gradient_accumulation_steps: 4\n- total_train_batch_size: 32\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 3",
"### Training results",
"### Framework versions\n\n- Transformers 4.39.3\n- Pytorch 2.1.2\n- Datasets 2.19.0\n- Tokenizers 0.15.2"
] |
null | transformers |
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] | {"library_name": "transformers", "tags": []} | wendy41/llama-3-user0-200 | null | [
"transformers",
"safetensors",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null | 2024-04-19T17:31:48+00:00 | [
"1910.09700"
] | [] | TAGS
#transformers #safetensors #arxiv-1910.09700 #endpoints_compatible #region-us
|
# Model Card for Model ID
## Model Details
### Model Description
This is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.
- Developed by:
- Funded by [optional]:
- Shared by [optional]:
- Model type:
- Language(s) (NLP):
- License:
- Finetuned from model [optional]:
### Model Sources [optional]
- Repository:
- Paper [optional]:
- Demo [optional]:
## Uses
### Direct Use
### Downstream Use [optional]
### Out-of-Scope Use
## Bias, Risks, and Limitations
### Recommendations
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
## Training Details
### Training Data
### Training Procedure
#### Preprocessing [optional]
#### Training Hyperparameters
- Training regime:
#### Speeds, Sizes, Times [optional]
## Evaluation
### Testing Data, Factors & Metrics
#### Testing Data
#### Factors
#### Metrics
### Results
#### Summary
## Model Examination [optional]
## Environmental Impact
Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).
- Hardware Type:
- Hours used:
- Cloud Provider:
- Compute Region:
- Carbon Emitted:
## Technical Specifications [optional]
### Model Architecture and Objective
### Compute Infrastructure
#### Hardware
#### Software
[optional]
BibTeX:
APA:
## Glossary [optional]
## More Information [optional]
## Model Card Authors [optional]
## Model Card Contact
| [
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.",
"## How to Get Started with the Model\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] | [
"TAGS\n#transformers #safetensors #arxiv-1910.09700 #endpoints_compatible #region-us \n",
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.",
"## How to Get Started with the Model\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] |
reinforcement-learning | null |
# **Q-Learning** Agent playing1 **FrozenLake-v1**
This is a trained model of a **Q-Learning** agent playing **FrozenLake-v1** .
## Usage
```python
model = load_from_hub(repo_id="moczard/q-FrozenLake-v1-4x4-noSlippery", filename="q-learning.pkl")
# Don't forget to check if you need to add additional attributes (is_slippery=False etc)
env = gym.make(model["env_id"])
```
| {"tags": ["FrozenLake-v1-4x4-no_slippery", "q-learning", "reinforcement-learning", "custom-implementation"], "model-index": [{"name": "q-FrozenLake-v1-4x4-noSlippery", "results": [{"task": {"type": "reinforcement-learning", "name": "reinforcement-learning"}, "dataset": {"name": "FrozenLake-v1-4x4-no_slippery", "type": "FrozenLake-v1-4x4-no_slippery"}, "metrics": [{"type": "mean_reward", "value": "1.00 +/- 0.00", "name": "mean_reward", "verified": false}]}]}]} | moczard/q-FrozenLake-v1-4x4-noSlippery | null | [
"FrozenLake-v1-4x4-no_slippery",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
] | null | 2024-04-19T17:33:04+00:00 | [] | [] | TAGS
#FrozenLake-v1-4x4-no_slippery #q-learning #reinforcement-learning #custom-implementation #model-index #region-us
|
# Q-Learning Agent playing1 FrozenLake-v1
This is a trained model of a Q-Learning agent playing FrozenLake-v1 .
## Usage
| [
"# Q-Learning Agent playing1 FrozenLake-v1\n This is a trained model of a Q-Learning agent playing FrozenLake-v1 .\n\n ## Usage"
] | [
"TAGS\n#FrozenLake-v1-4x4-no_slippery #q-learning #reinforcement-learning #custom-implementation #model-index #region-us \n",
"# Q-Learning Agent playing1 FrozenLake-v1\n This is a trained model of a Q-Learning agent playing FrozenLake-v1 .\n\n ## Usage"
] |
null | transformers |
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] | {"library_name": "transformers", "tags": []} | galbitang/koalpacapoly-user0-200 | null | [
"transformers",
"safetensors",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null | 2024-04-19T17:33:22+00:00 | [
"1910.09700"
] | [] | TAGS
#transformers #safetensors #arxiv-1910.09700 #endpoints_compatible #region-us
|
# Model Card for Model ID
## Model Details
### Model Description
This is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.
- Developed by:
- Funded by [optional]:
- Shared by [optional]:
- Model type:
- Language(s) (NLP):
- License:
- Finetuned from model [optional]:
### Model Sources [optional]
- Repository:
- Paper [optional]:
- Demo [optional]:
## Uses
### Direct Use
### Downstream Use [optional]
### Out-of-Scope Use
## Bias, Risks, and Limitations
### Recommendations
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
## Training Details
### Training Data
### Training Procedure
#### Preprocessing [optional]
#### Training Hyperparameters
- Training regime:
#### Speeds, Sizes, Times [optional]
## Evaluation
### Testing Data, Factors & Metrics
#### Testing Data
#### Factors
#### Metrics
### Results
#### Summary
## Model Examination [optional]
## Environmental Impact
Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).
- Hardware Type:
- Hours used:
- Cloud Provider:
- Compute Region:
- Carbon Emitted:
## Technical Specifications [optional]
### Model Architecture and Objective
### Compute Infrastructure
#### Hardware
#### Software
[optional]
BibTeX:
APA:
## Glossary [optional]
## More Information [optional]
## Model Card Authors [optional]
## Model Card Contact
| [
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.",
"## How to Get Started with the Model\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] | [
"TAGS\n#transformers #safetensors #arxiv-1910.09700 #endpoints_compatible #region-us \n",
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.",
"## How to Get Started with the Model\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] |
text-generation | transformers | # Replete-AI/DevsDoCode-LLama-3-8b-Uncensored AWQ
## Model Summary
Project may of migrated to https://huggingface.co/DevsDoCode
| {"library_name": "transformers", "tags": ["4-bit", "AWQ", "text-generation", "autotrain_compatible", "endpoints_compatible"], "pipeline_tag": "text-generation", "inference": false, "quantized_by": "Suparious"} | solidrust/DevsDoCode-LLama-3-8b-Uncensored-AWQ | null | [
"transformers",
"safetensors",
"llama",
"text-generation",
"4-bit",
"AWQ",
"autotrain_compatible",
"endpoints_compatible",
"conversational",
"text-generation-inference",
"region:us"
] | null | 2024-04-19T17:33:40+00:00 | [] | [] | TAGS
#transformers #safetensors #llama #text-generation #4-bit #AWQ #autotrain_compatible #endpoints_compatible #conversational #text-generation-inference #region-us
| # Replete-AI/DevsDoCode-LLama-3-8b-Uncensored AWQ
## Model Summary
Project may of migrated to URL
| [
"# Replete-AI/DevsDoCode-LLama-3-8b-Uncensored AWQ",
"## Model Summary\n\nProject may of migrated to URL"
] | [
"TAGS\n#transformers #safetensors #llama #text-generation #4-bit #AWQ #autotrain_compatible #endpoints_compatible #conversational #text-generation-inference #region-us \n",
"# Replete-AI/DevsDoCode-LLama-3-8b-Uncensored AWQ",
"## Model Summary\n\nProject may of migrated to URL"
] |
null | peft |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# mistral7binstruct_summarize
This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on the generator dataset.
It achieves the following results on the evaluation set:
- Loss: 1.4664
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0002
- train_batch_size: 1
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant
- lr_scheduler_warmup_steps: 0.03
- training_steps: 50
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:------:|:----:|:---------------:|
| 1.825 | 0.2174 | 25 | 1.5563 |
| 1.5953 | 0.4348 | 50 | 1.4664 |
### Framework versions
- PEFT 0.10.0
- Transformers 4.40.0
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1 | {"license": "apache-2.0", "library_name": "peft", "tags": ["trl", "sft", "generated_from_trainer"], "datasets": ["generator"], "base_model": "mistralai/Mistral-7B-Instruct-v0.2", "model-index": [{"name": "mistral7binstruct_summarize", "results": []}]} | tdeshane/mistral7binstruct_summarize | null | [
"peft",
"tensorboard",
"safetensors",
"trl",
"sft",
"generated_from_trainer",
"dataset:generator",
"base_model:mistralai/Mistral-7B-Instruct-v0.2",
"license:apache-2.0",
"region:us"
] | null | 2024-04-19T17:33:58+00:00 | [] | [] | TAGS
#peft #tensorboard #safetensors #trl #sft #generated_from_trainer #dataset-generator #base_model-mistralai/Mistral-7B-Instruct-v0.2 #license-apache-2.0 #region-us
| mistral7binstruct\_summarize
============================
This model is a fine-tuned version of mistralai/Mistral-7B-Instruct-v0.2 on the generator dataset.
It achieves the following results on the evaluation set:
* Loss: 1.4664
Model description
-----------------
More information needed
Intended uses & limitations
---------------------------
More information needed
Training and evaluation data
----------------------------
More information needed
Training procedure
------------------
### Training hyperparameters
The following hyperparameters were used during training:
* learning\_rate: 0.0002
* train\_batch\_size: 1
* eval\_batch\_size: 8
* seed: 42
* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
* lr\_scheduler\_type: constant
* lr\_scheduler\_warmup\_steps: 0.03
* training\_steps: 50
### Training results
### Framework versions
* PEFT 0.10.0
* Transformers 4.40.0
* Pytorch 2.2.1+cu121
* Datasets 2.19.0
* Tokenizers 0.19.1
| [
"### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0002\n* train\\_batch\\_size: 1\n* eval\\_batch\\_size: 8\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: constant\n* lr\\_scheduler\\_warmup\\_steps: 0.03\n* training\\_steps: 50",
"### Training results",
"### Framework versions\n\n\n* PEFT 0.10.0\n* Transformers 4.40.0\n* Pytorch 2.2.1+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1"
] | [
"TAGS\n#peft #tensorboard #safetensors #trl #sft #generated_from_trainer #dataset-generator #base_model-mistralai/Mistral-7B-Instruct-v0.2 #license-apache-2.0 #region-us \n",
"### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0002\n* train\\_batch\\_size: 1\n* eval\\_batch\\_size: 8\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: constant\n* lr\\_scheduler\\_warmup\\_steps: 0.03\n* training\\_steps: 50",
"### Training results",
"### Framework versions\n\n\n* PEFT 0.10.0\n* Transformers 4.40.0\n* Pytorch 2.2.1+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1"
] |
null | null | # Clone the repo and use test.ipynb file
Install pkg
1. Pytorch
2. Matplotlib
3. Numpy
4. Ultralytics
5. opencv-python | {} | rakib72642/BUBT_Japan | null | [
"region:us"
] | null | 2024-04-19T17:36:00+00:00 | [] | [] | TAGS
#region-us
| # Clone the repo and use URL file
Install pkg
1. Pytorch
2. Matplotlib
3. Numpy
4. Ultralytics
5. opencv-python | [
"# Clone the repo and use URL file\n\nInstall pkg\n1. Pytorch\n2. Matplotlib\n3. Numpy\n4. Ultralytics\n5. opencv-python"
] | [
"TAGS\n#region-us \n",
"# Clone the repo and use URL file\n\nInstall pkg\n1. Pytorch\n2. Matplotlib\n3. Numpy\n4. Ultralytics\n5. opencv-python"
] |
text-generation | transformers |
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] | {"library_name": "transformers", "tags": []} | ryanu/EEVE-10.8-BOOK-v0.2 | null | [
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-04-19T17:37:23+00:00 | [
"1910.09700"
] | [] | TAGS
#transformers #safetensors #llama #text-generation #conversational #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us
|
# Model Card for Model ID
## Model Details
### Model Description
This is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.
- Developed by:
- Funded by [optional]:
- Shared by [optional]:
- Model type:
- Language(s) (NLP):
- License:
- Finetuned from model [optional]:
### Model Sources [optional]
- Repository:
- Paper [optional]:
- Demo [optional]:
## Uses
### Direct Use
### Downstream Use [optional]
### Out-of-Scope Use
## Bias, Risks, and Limitations
### Recommendations
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
## Training Details
### Training Data
### Training Procedure
#### Preprocessing [optional]
#### Training Hyperparameters
- Training regime:
#### Speeds, Sizes, Times [optional]
## Evaluation
### Testing Data, Factors & Metrics
#### Testing Data
#### Factors
#### Metrics
### Results
#### Summary
## Model Examination [optional]
## Environmental Impact
Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).
- Hardware Type:
- Hours used:
- Cloud Provider:
- Compute Region:
- Carbon Emitted:
## Technical Specifications [optional]
### Model Architecture and Objective
### Compute Infrastructure
#### Hardware
#### Software
[optional]
BibTeX:
APA:
## Glossary [optional]
## More Information [optional]
## Model Card Authors [optional]
## Model Card Contact
| [
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.",
"## How to Get Started with the Model\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] | [
"TAGS\n#transformers #safetensors #llama #text-generation #conversational #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n",
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.",
"## How to Get Started with the Model\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] |
image-classification | transformers |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# lung-cancer-image-classification
This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the imagefolder dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0177
- Precision: 0.9963
- Recall: 0.9963
- F1: 0.9963
- Accuracy: 0.9963
- Confusion matrix: 1245 1 4
0 1250 0
9 0 1241
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0002
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
### Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | Confusion matrix |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|:-----------------------------:|
| 0.3173 | 0.21 | 100 | 0.1952 | 0.9371 | 0.9331 | 0.9339 | 0.9331 | 1186 0 64
90 1160 0
97 0 1153 |
| 0.1312 | 0.43 | 200 | 0.0752 | 0.9786 | 0.9779 | 0.9778 | 0.9779 | 1178 1 71
2 1248 0
9 0 1241 |
| 0.1453 | 0.64 | 300 | 0.0688 | 0.9759 | 0.9752 | 0.9752 | 0.9752 | 1232 1 17
8 1242 0
67 0 1183 |
| 0.0146 | 0.85 | 400 | 0.0485 | 0.9854 | 0.9853 | 0.9853 | 0.9853 | 1212 2 36
0 1250 0
17 0 1233 |
| 0.0075 | 1.07 | 500 | 0.0376 | 0.9897 | 0.9896 | 0.9896 | 0.9896 | 1220 1 29
5 1245 0
4 0 1246 |
| 0.054 | 1.28 | 600 | 0.0233 | 0.9939 | 0.9939 | 0.9939 | 0.9939 | 1241 1 8
0 1250 0
14 0 1236 |
| 0.0272 | 1.49 | 700 | 0.0156 | 0.9950 | 0.9949 | 0.9949 | 0.9949 | 1235 1 14
0 1250 0
4 0 1246 |
| 0.0307 | 1.71 | 800 | 0.0172 | 0.9949 | 0.9949 | 0.9949 | 0.9949 | 1244 1 5
0 1250 0
13 0 1237 |
| 0.0022 | 1.92 | 900 | 0.0144 | 0.9963 | 0.9963 | 0.9963 | 0.9963 | 1237 1 12
0 1250 0
1 0 1249 |
| 0.0015 | 2.13 | 1000 | 0.0156 | 0.9963 | 0.9963 | 0.9963 | 0.9963 | 1238 1 11
0 1250 0
2 0 1248 |
| 0.0014 | 2.35 | 1100 | 0.0138 | 0.9971 | 0.9971 | 0.9971 | 0.9971 | 1243 1 6
0 1250 0
4 0 1246 |
| 0.0317 | 2.56 | 1200 | 0.0110 | 0.9973 | 0.9973 | 0.9973 | 0.9973 | 1244 1 5
0 1250 0
4 0 1246 |
| 0.0011 | 2.77 | 1300 | 0.0159 | 0.9963 | 0.9963 | 0.9963 | 0.9963 | 1236 1 13
0 1250 0
0 0 1250 |
| 0.0012 | 2.99 | 1400 | 0.0120 | 0.9971 | 0.9971 | 0.9971 | 0.9971 | 1239 1 10
0 1250 0
0 0 1250 |
### Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.15.2
| {"license": "apache-2.0", "tags": ["generated_from_trainer"], "datasets": ["imagefolder"], "metrics": ["precision", "recall", "f1", "accuracy"], "base_model": "google/vit-base-patch16-224-in21k", "model-index": [{"name": "lung-cancer-image-classification", "results": [{"task": {"type": "image-classification", "name": "Image Classification"}, "dataset": {"name": "imagefolder", "type": "imagefolder", "config": "default", "split": "None", "args": "default"}, "metrics": [{"type": "precision", "value": 0.9962702515299879, "name": "Precision"}, {"type": "recall", "value": 0.9962666666666666, "name": "Recall"}, {"type": "f1", "value": 0.9962662282604144, "name": "F1"}, {"type": "accuracy", "value": 0.9962666666666666, "name": "Accuracy"}]}]}]} | ebmonser/lung-cancer-image-classification | null | [
"transformers",
"tensorboard",
"safetensors",
"vit",
"image-classification",
"generated_from_trainer",
"dataset:imagefolder",
"base_model:google/vit-base-patch16-224-in21k",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | null | 2024-04-19T17:38:39+00:00 | [] | [] | TAGS
#transformers #tensorboard #safetensors #vit #image-classification #generated_from_trainer #dataset-imagefolder #base_model-google/vit-base-patch16-224-in21k #license-apache-2.0 #model-index #autotrain_compatible #endpoints_compatible #region-us
| lung-cancer-image-classification
================================
This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the imagefolder dataset.
It achieves the following results on the evaluation set:
* Loss: 0.0177
* Precision: 0.9963
* Recall: 0.9963
* F1: 0.9963
* Accuracy: 0.9963
* Confusion matrix: 1245 1 4
0 1250 0
9 0 1241
Model description
-----------------
More information needed
Intended uses & limitations
---------------------------
More information needed
Training and evaluation data
----------------------------
More information needed
Training procedure
------------------
### Training hyperparameters
The following hyperparameters were used during training:
* learning\_rate: 0.0002
* train\_batch\_size: 16
* eval\_batch\_size: 8
* seed: 42
* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
* lr\_scheduler\_type: linear
* num\_epochs: 3
### Training results
### Framework versions
* Transformers 4.38.2
* Pytorch 2.2.1+cu121
* Datasets 2.19.0
* Tokenizers 0.15.2
| [
"### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0002\n* train\\_batch\\_size: 16\n* eval\\_batch\\_size: 8\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 3",
"### Training results",
"### Framework versions\n\n\n* Transformers 4.38.2\n* Pytorch 2.2.1+cu121\n* Datasets 2.19.0\n* Tokenizers 0.15.2"
] | [
"TAGS\n#transformers #tensorboard #safetensors #vit #image-classification #generated_from_trainer #dataset-imagefolder #base_model-google/vit-base-patch16-224-in21k #license-apache-2.0 #model-index #autotrain_compatible #endpoints_compatible #region-us \n",
"### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0002\n* train\\_batch\\_size: 16\n* eval\\_batch\\_size: 8\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 3",
"### Training results",
"### Framework versions\n\n\n* Transformers 4.38.2\n* Pytorch 2.2.1+cu121\n* Datasets 2.19.0\n* Tokenizers 0.15.2"
] |
null | null |
Model reuplods for https://github.com/yl4579/StyleTTS-VC | {"license": "mit"} | ml-for-speech/styletts-vc | null | [
"license:mit",
"region:us"
] | null | 2024-04-19T17:38:52+00:00 | [] | [] | TAGS
#license-mit #region-us
|
Model reuplods for URL | [] | [
"TAGS\n#license-mit #region-us \n"
] |
text-generation | transformers |
# Finetune Mistral, Gemma, Llama 2-5x faster with 70% less memory via Unsloth!
We have a Google Colab Tesla T4 notebook for Llama-3 8b here: https://colab.research.google.com/drive/135ced7oHytdxu3N2DNe1Z0kqjyYIkDXp?usp=sharing
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/Discord%20button.png" width="200"/>](https://discord.gg/u54VK8m8tk)
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/buy%20me%20a%20coffee%20button.png" width="200"/>](https://ko-fi.com/unsloth)
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
## ✨ Finetune for Free
All notebooks are **beginner friendly**! Add your dataset, click "Run All", and you'll get a 2x faster finetuned model which can be exported to GGUF, vLLM or uploaded to Hugging Face.
| Unsloth supports | Free Notebooks | Performance | Memory use |
|-----------------|--------------------------------------------------------------------------------------------------------------------------|-------------|----------|
| **Llama-3 8b** | [▶️ Start on Colab](https://colab.research.google.com/drive/135ced7oHytdxu3N2DNe1Z0kqjyYIkDXp?usp=sharing) | 2.4x faster | 58% less |
| **Gemma 7b** | [▶️ Start on Colab](https://colab.research.google.com/drive/10NbwlsRChbma1v55m8LAPYG15uQv6HLo?usp=sharing) | 2.4x faster | 58% less |
| **Mistral 7b** | [▶️ Start on Colab](https://colab.research.google.com/drive/1Dyauq4kTZoLewQ1cApceUQVNcnnNTzg_?usp=sharing) | 2.2x faster | 62% less |
| **Llama-2 7b** | [▶️ Start on Colab](https://colab.research.google.com/drive/1lBzz5KeZJKXjvivbYvmGarix9Ao6Wxe5?usp=sharing) | 2.2x faster | 43% less |
| **TinyLlama** | [▶️ Start on Colab](https://colab.research.google.com/drive/1AZghoNBQaMDgWJpi4RbffGM1h6raLUj9?usp=sharing) | 3.9x faster | 74% less |
| **CodeLlama 34b** A100 | [▶️ Start on Colab](https://colab.research.google.com/drive/1y7A0AxE3y8gdj4AVkl2aZX47Xu3P1wJT?usp=sharing) | 1.9x faster | 27% less |
| **Mistral 7b** 1xT4 | [▶️ Start on Kaggle](https://www.kaggle.com/code/danielhanchen/kaggle-mistral-7b-unsloth-notebook) | 5x faster\* | 62% less |
| **DPO - Zephyr** | [▶️ Start on Colab](https://colab.research.google.com/drive/15vttTpzzVXv_tJwEk-hIcQ0S9FcEWvwP?usp=sharing) | 1.9x faster | 19% less |
- This [conversational notebook](https://colab.research.google.com/drive/1Aau3lgPzeZKQ-98h69CCu1UJcvIBLmy2?usp=sharing) is useful for ShareGPT ChatML / Vicuna templates.
- This [text completion notebook](https://colab.research.google.com/drive/1ef-tab5bhkvWmBOObepl1WgJvfvSzn5Q?usp=sharing) is for raw text. This [DPO notebook](https://colab.research.google.com/drive/15vttTpzzVXv_tJwEk-hIcQ0S9FcEWvwP?usp=sharing) replicates Zephyr.
- \* Kaggle has 2x T4s, but we use 1. Due to overhead, 1x T4 is 5x faster. | {"language": ["en"], "license": "apache-2.0", "library_name": "transformers", "tags": ["unsloth", "transformers", "llama", "llama-3"]} | unsloth/llama-3-70b-Instruct-bnb-4bit | null | [
"transformers",
"safetensors",
"llama",
"text-generation",
"unsloth",
"llama-3",
"conversational",
"en",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"4-bit",
"region:us"
] | null | 2024-04-19T17:39:17+00:00 | [] | [
"en"
] | TAGS
#transformers #safetensors #llama #text-generation #unsloth #llama-3 #conversational #en #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #4-bit #region-us
| Finetune Mistral, Gemma, Llama 2-5x faster with 70% less memory via Unsloth!
============================================================================
We have a Google Colab Tesla T4 notebook for Llama-3 8b here: URL
<img src="URL width="200"/>
<img src="URL width="200"/>
<img src="URL width="200"/>
Finetune for Free
-----------------
All notebooks are beginner friendly! Add your dataset, click "Run All", and you'll get a 2x faster finetuned model which can be exported to GGUF, vLLM or uploaded to Hugging Face.
* This conversational notebook is useful for ShareGPT ChatML / Vicuna templates.
* This text completion notebook is for raw text. This DPO notebook replicates Zephyr.
* \* Kaggle has 2x T4s, but we use 1. Due to overhead, 1x T4 is 5x faster.
| [] | [
"TAGS\n#transformers #safetensors #llama #text-generation #unsloth #llama-3 #conversational #en #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #4-bit #region-us \n"
] |
token-classification | transformers |
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
| {"library_name": "transformers", "tags": []} | abrarhkml/bert-base-finetuned-pii-ner | null | [
"transformers",
"safetensors",
"bert",
"token-classification",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | null | 2024-04-19T17:39:25+00:00 | [
"1910.09700"
] | [] | TAGS
#transformers #safetensors #bert #token-classification #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #region-us
|
# Model Card for Model ID
## Model Details
### Model Description
This is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.
- Developed by:
- Funded by [optional]:
- Shared by [optional]:
- Model type:
- Language(s) (NLP):
- License:
- Finetuned from model [optional]:
### Model Sources [optional]
- Repository:
- Paper [optional]:
- Demo [optional]:
## Uses
### Direct Use
### Downstream Use [optional]
### Out-of-Scope Use
## Bias, Risks, and Limitations
### Recommendations
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
## Training Details
### Training Data
### Training Procedure
#### Preprocessing [optional]
#### Training Hyperparameters
- Training regime:
#### Speeds, Sizes, Times [optional]
## Evaluation
### Testing Data, Factors & Metrics
#### Testing Data
#### Factors
#### Metrics
### Results
#### Summary
## Model Examination [optional]
## Environmental Impact
Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).
- Hardware Type:
- Hours used:
- Cloud Provider:
- Compute Region:
- Carbon Emitted:
## Technical Specifications [optional]
### Model Architecture and Objective
### Compute Infrastructure
#### Hardware
#### Software
[optional]
BibTeX:
APA:
## Glossary [optional]
## More Information [optional]
## Model Card Authors [optional]
## Model Card Contact
| [
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.",
"## How to Get Started with the Model\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] | [
"TAGS\n#transformers #safetensors #bert #token-classification #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #region-us \n",
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.",
"## How to Get Started with the Model\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] |
text-generation | transformers |
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] | {"library_name": "transformers", "tags": []} | hgnoi/fine-tune-12 | null | [
"transformers",
"safetensors",
"stablelm",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | null | 2024-04-19T17:40:32+00:00 | [
"1910.09700"
] | [] | TAGS
#transformers #safetensors #stablelm #text-generation #conversational #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #region-us
|
# Model Card for Model ID
## Model Details
### Model Description
This is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.
- Developed by:
- Funded by [optional]:
- Shared by [optional]:
- Model type:
- Language(s) (NLP):
- License:
- Finetuned from model [optional]:
### Model Sources [optional]
- Repository:
- Paper [optional]:
- Demo [optional]:
## Uses
### Direct Use
### Downstream Use [optional]
### Out-of-Scope Use
## Bias, Risks, and Limitations
### Recommendations
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
## Training Details
### Training Data
### Training Procedure
#### Preprocessing [optional]
#### Training Hyperparameters
- Training regime:
#### Speeds, Sizes, Times [optional]
## Evaluation
### Testing Data, Factors & Metrics
#### Testing Data
#### Factors
#### Metrics
### Results
#### Summary
## Model Examination [optional]
## Environmental Impact
Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).
- Hardware Type:
- Hours used:
- Cloud Provider:
- Compute Region:
- Carbon Emitted:
## Technical Specifications [optional]
### Model Architecture and Objective
### Compute Infrastructure
#### Hardware
#### Software
[optional]
BibTeX:
APA:
## Glossary [optional]
## More Information [optional]
## Model Card Authors [optional]
## Model Card Contact
| [
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.",
"## How to Get Started with the Model\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] | [
"TAGS\n#transformers #safetensors #stablelm #text-generation #conversational #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #region-us \n",
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.",
"## How to Get Started with the Model\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] |
text-generation | transformers |
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] | {"library_name": "transformers", "tags": []} | hgnoi/fine-tune-13 | null | [
"transformers",
"safetensors",
"stablelm",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | null | 2024-04-19T17:41:40+00:00 | [
"1910.09700"
] | [] | TAGS
#transformers #safetensors #stablelm #text-generation #conversational #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #region-us
|
# Model Card for Model ID
## Model Details
### Model Description
This is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.
- Developed by:
- Funded by [optional]:
- Shared by [optional]:
- Model type:
- Language(s) (NLP):
- License:
- Finetuned from model [optional]:
### Model Sources [optional]
- Repository:
- Paper [optional]:
- Demo [optional]:
## Uses
### Direct Use
### Downstream Use [optional]
### Out-of-Scope Use
## Bias, Risks, and Limitations
### Recommendations
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
## Training Details
### Training Data
### Training Procedure
#### Preprocessing [optional]
#### Training Hyperparameters
- Training regime:
#### Speeds, Sizes, Times [optional]
## Evaluation
### Testing Data, Factors & Metrics
#### Testing Data
#### Factors
#### Metrics
### Results
#### Summary
## Model Examination [optional]
## Environmental Impact
Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).
- Hardware Type:
- Hours used:
- Cloud Provider:
- Compute Region:
- Carbon Emitted:
## Technical Specifications [optional]
### Model Architecture and Objective
### Compute Infrastructure
#### Hardware
#### Software
[optional]
BibTeX:
APA:
## Glossary [optional]
## More Information [optional]
## Model Card Authors [optional]
## Model Card Contact
| [
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.",
"## How to Get Started with the Model\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] | [
"TAGS\n#transformers #safetensors #stablelm #text-generation #conversational #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #region-us \n",
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.",
"## How to Get Started with the Model\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] |
text-generation | transformers |
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] | {"library_name": "transformers", "tags": []} | hgnoi/fine-tune-11 | null | [
"transformers",
"safetensors",
"stablelm",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | null | 2024-04-19T17:41:40+00:00 | [
"1910.09700"
] | [] | TAGS
#transformers #safetensors #stablelm #text-generation #conversational #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #region-us
|
# Model Card for Model ID
## Model Details
### Model Description
This is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.
- Developed by:
- Funded by [optional]:
- Shared by [optional]:
- Model type:
- Language(s) (NLP):
- License:
- Finetuned from model [optional]:
### Model Sources [optional]
- Repository:
- Paper [optional]:
- Demo [optional]:
## Uses
### Direct Use
### Downstream Use [optional]
### Out-of-Scope Use
## Bias, Risks, and Limitations
### Recommendations
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
## Training Details
### Training Data
### Training Procedure
#### Preprocessing [optional]
#### Training Hyperparameters
- Training regime:
#### Speeds, Sizes, Times [optional]
## Evaluation
### Testing Data, Factors & Metrics
#### Testing Data
#### Factors
#### Metrics
### Results
#### Summary
## Model Examination [optional]
## Environmental Impact
Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).
- Hardware Type:
- Hours used:
- Cloud Provider:
- Compute Region:
- Carbon Emitted:
## Technical Specifications [optional]
### Model Architecture and Objective
### Compute Infrastructure
#### Hardware
#### Software
[optional]
BibTeX:
APA:
## Glossary [optional]
## More Information [optional]
## Model Card Authors [optional]
## Model Card Contact
| [
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.",
"## How to Get Started with the Model\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] | [
"TAGS\n#transformers #safetensors #stablelm #text-generation #conversational #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #region-us \n",
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.",
"## How to Get Started with the Model\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] |
text-generation | transformers |
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] | {"library_name": "transformers", "tags": []} | hgnoi/fine-tune-2 | null | [
"transformers",
"safetensors",
"stablelm",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | null | 2024-04-19T17:41:40+00:00 | [
"1910.09700"
] | [] | TAGS
#transformers #safetensors #stablelm #text-generation #conversational #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #region-us
|
# Model Card for Model ID
## Model Details
### Model Description
This is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.
- Developed by:
- Funded by [optional]:
- Shared by [optional]:
- Model type:
- Language(s) (NLP):
- License:
- Finetuned from model [optional]:
### Model Sources [optional]
- Repository:
- Paper [optional]:
- Demo [optional]:
## Uses
### Direct Use
### Downstream Use [optional]
### Out-of-Scope Use
## Bias, Risks, and Limitations
### Recommendations
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
## Training Details
### Training Data
### Training Procedure
#### Preprocessing [optional]
#### Training Hyperparameters
- Training regime:
#### Speeds, Sizes, Times [optional]
## Evaluation
### Testing Data, Factors & Metrics
#### Testing Data
#### Factors
#### Metrics
### Results
#### Summary
## Model Examination [optional]
## Environmental Impact
Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).
- Hardware Type:
- Hours used:
- Cloud Provider:
- Compute Region:
- Carbon Emitted:
## Technical Specifications [optional]
### Model Architecture and Objective
### Compute Infrastructure
#### Hardware
#### Software
[optional]
BibTeX:
APA:
## Glossary [optional]
## More Information [optional]
## Model Card Authors [optional]
## Model Card Contact
| [
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.",
"## How to Get Started with the Model\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] | [
"TAGS\n#transformers #safetensors #stablelm #text-generation #conversational #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #region-us \n",
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.",
"## How to Get Started with the Model\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] |
text-generation | transformers |
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] | {"library_name": "transformers", "tags": []} | hgnoi/fine-tune-14 | null | [
"transformers",
"safetensors",
"stablelm",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | null | 2024-04-19T17:41:41+00:00 | [
"1910.09700"
] | [] | TAGS
#transformers #safetensors #stablelm #text-generation #conversational #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #region-us
|
# Model Card for Model ID
## Model Details
### Model Description
This is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.
- Developed by:
- Funded by [optional]:
- Shared by [optional]:
- Model type:
- Language(s) (NLP):
- License:
- Finetuned from model [optional]:
### Model Sources [optional]
- Repository:
- Paper [optional]:
- Demo [optional]:
## Uses
### Direct Use
### Downstream Use [optional]
### Out-of-Scope Use
## Bias, Risks, and Limitations
### Recommendations
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
## Training Details
### Training Data
### Training Procedure
#### Preprocessing [optional]
#### Training Hyperparameters
- Training regime:
#### Speeds, Sizes, Times [optional]
## Evaluation
### Testing Data, Factors & Metrics
#### Testing Data
#### Factors
#### Metrics
### Results
#### Summary
## Model Examination [optional]
## Environmental Impact
Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).
- Hardware Type:
- Hours used:
- Cloud Provider:
- Compute Region:
- Carbon Emitted:
## Technical Specifications [optional]
### Model Architecture and Objective
### Compute Infrastructure
#### Hardware
#### Software
[optional]
BibTeX:
APA:
## Glossary [optional]
## More Information [optional]
## Model Card Authors [optional]
## Model Card Contact
| [
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.",
"## How to Get Started with the Model\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] | [
"TAGS\n#transformers #safetensors #stablelm #text-generation #conversational #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #region-us \n",
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.",
"## How to Get Started with the Model\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] |
text-generation | transformers |
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] | {"library_name": "transformers", "tags": []} | hgnoi/fine-tune-10 | null | [
"transformers",
"safetensors",
"stablelm",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | null | 2024-04-19T17:41:41+00:00 | [
"1910.09700"
] | [] | TAGS
#transformers #safetensors #stablelm #text-generation #conversational #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #region-us
|
# Model Card for Model ID
## Model Details
### Model Description
This is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.
- Developed by:
- Funded by [optional]:
- Shared by [optional]:
- Model type:
- Language(s) (NLP):
- License:
- Finetuned from model [optional]:
### Model Sources [optional]
- Repository:
- Paper [optional]:
- Demo [optional]:
## Uses
### Direct Use
### Downstream Use [optional]
### Out-of-Scope Use
## Bias, Risks, and Limitations
### Recommendations
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
## Training Details
### Training Data
### Training Procedure
#### Preprocessing [optional]
#### Training Hyperparameters
- Training regime:
#### Speeds, Sizes, Times [optional]
## Evaluation
### Testing Data, Factors & Metrics
#### Testing Data
#### Factors
#### Metrics
### Results
#### Summary
## Model Examination [optional]
## Environmental Impact
Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).
- Hardware Type:
- Hours used:
- Cloud Provider:
- Compute Region:
- Carbon Emitted:
## Technical Specifications [optional]
### Model Architecture and Objective
### Compute Infrastructure
#### Hardware
#### Software
[optional]
BibTeX:
APA:
## Glossary [optional]
## More Information [optional]
## Model Card Authors [optional]
## Model Card Contact
| [
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.",
"## How to Get Started with the Model\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] | [
"TAGS\n#transformers #safetensors #stablelm #text-generation #conversational #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #region-us \n",
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.",
"## How to Get Started with the Model\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] |
text-generation | transformers |
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] | {"library_name": "transformers", "tags": []} | hgnoi/fine-tune-6 | null | [
"transformers",
"safetensors",
"stablelm",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | null | 2024-04-19T17:41:41+00:00 | [
"1910.09700"
] | [] | TAGS
#transformers #safetensors #stablelm #text-generation #conversational #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #region-us
|
# Model Card for Model ID
## Model Details
### Model Description
This is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.
- Developed by:
- Funded by [optional]:
- Shared by [optional]:
- Model type:
- Language(s) (NLP):
- License:
- Finetuned from model [optional]:
### Model Sources [optional]
- Repository:
- Paper [optional]:
- Demo [optional]:
## Uses
### Direct Use
### Downstream Use [optional]
### Out-of-Scope Use
## Bias, Risks, and Limitations
### Recommendations
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
## Training Details
### Training Data
### Training Procedure
#### Preprocessing [optional]
#### Training Hyperparameters
- Training regime:
#### Speeds, Sizes, Times [optional]
## Evaluation
### Testing Data, Factors & Metrics
#### Testing Data
#### Factors
#### Metrics
### Results
#### Summary
## Model Examination [optional]
## Environmental Impact
Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).
- Hardware Type:
- Hours used:
- Cloud Provider:
- Compute Region:
- Carbon Emitted:
## Technical Specifications [optional]
### Model Architecture and Objective
### Compute Infrastructure
#### Hardware
#### Software
[optional]
BibTeX:
APA:
## Glossary [optional]
## More Information [optional]
## Model Card Authors [optional]
## Model Card Contact
| [
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.",
"## How to Get Started with the Model\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] | [
"TAGS\n#transformers #safetensors #stablelm #text-generation #conversational #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #region-us \n",
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.",
"## How to Get Started with the Model\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] |
text-generation | transformers |
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] | {"library_name": "transformers", "tags": []} | hgnoi/fine-tune-4 | null | [
"transformers",
"safetensors",
"stablelm",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | null | 2024-04-19T17:41:42+00:00 | [
"1910.09700"
] | [] | TAGS
#transformers #safetensors #stablelm #text-generation #conversational #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #region-us
|
# Model Card for Model ID
## Model Details
### Model Description
This is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.
- Developed by:
- Funded by [optional]:
- Shared by [optional]:
- Model type:
- Language(s) (NLP):
- License:
- Finetuned from model [optional]:
### Model Sources [optional]
- Repository:
- Paper [optional]:
- Demo [optional]:
## Uses
### Direct Use
### Downstream Use [optional]
### Out-of-Scope Use
## Bias, Risks, and Limitations
### Recommendations
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
## Training Details
### Training Data
### Training Procedure
#### Preprocessing [optional]
#### Training Hyperparameters
- Training regime:
#### Speeds, Sizes, Times [optional]
## Evaluation
### Testing Data, Factors & Metrics
#### Testing Data
#### Factors
#### Metrics
### Results
#### Summary
## Model Examination [optional]
## Environmental Impact
Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).
- Hardware Type:
- Hours used:
- Cloud Provider:
- Compute Region:
- Carbon Emitted:
## Technical Specifications [optional]
### Model Architecture and Objective
### Compute Infrastructure
#### Hardware
#### Software
[optional]
BibTeX:
APA:
## Glossary [optional]
## More Information [optional]
## Model Card Authors [optional]
## Model Card Contact
| [
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.",
"## How to Get Started with the Model\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] | [
"TAGS\n#transformers #safetensors #stablelm #text-generation #conversational #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #region-us \n",
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.",
"## How to Get Started with the Model\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] |
text-generation | transformers |
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] | {"library_name": "transformers", "tags": []} | hgnoi/fine-tune-7 | null | [
"transformers",
"safetensors",
"stablelm",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | null | 2024-04-19T17:41:47+00:00 | [
"1910.09700"
] | [] | TAGS
#transformers #safetensors #stablelm #text-generation #conversational #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #region-us
|
# Model Card for Model ID
## Model Details
### Model Description
This is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.
- Developed by:
- Funded by [optional]:
- Shared by [optional]:
- Model type:
- Language(s) (NLP):
- License:
- Finetuned from model [optional]:
### Model Sources [optional]
- Repository:
- Paper [optional]:
- Demo [optional]:
## Uses
### Direct Use
### Downstream Use [optional]
### Out-of-Scope Use
## Bias, Risks, and Limitations
### Recommendations
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
## Training Details
### Training Data
### Training Procedure
#### Preprocessing [optional]
#### Training Hyperparameters
- Training regime:
#### Speeds, Sizes, Times [optional]
## Evaluation
### Testing Data, Factors & Metrics
#### Testing Data
#### Factors
#### Metrics
### Results
#### Summary
## Model Examination [optional]
## Environmental Impact
Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).
- Hardware Type:
- Hours used:
- Cloud Provider:
- Compute Region:
- Carbon Emitted:
## Technical Specifications [optional]
### Model Architecture and Objective
### Compute Infrastructure
#### Hardware
#### Software
[optional]
BibTeX:
APA:
## Glossary [optional]
## More Information [optional]
## Model Card Authors [optional]
## Model Card Contact
| [
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.",
"## How to Get Started with the Model\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] | [
"TAGS\n#transformers #safetensors #stablelm #text-generation #conversational #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #region-us \n",
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.",
"## How to Get Started with the Model\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] |
text-generation | transformers |
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] | {"library_name": "transformers", "tags": []} | hgnoi/fine-tune-5 | null | [
"transformers",
"safetensors",
"stablelm",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | null | 2024-04-19T17:41:48+00:00 | [
"1910.09700"
] | [] | TAGS
#transformers #safetensors #stablelm #text-generation #conversational #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #region-us
|
# Model Card for Model ID
## Model Details
### Model Description
This is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.
- Developed by:
- Funded by [optional]:
- Shared by [optional]:
- Model type:
- Language(s) (NLP):
- License:
- Finetuned from model [optional]:
### Model Sources [optional]
- Repository:
- Paper [optional]:
- Demo [optional]:
## Uses
### Direct Use
### Downstream Use [optional]
### Out-of-Scope Use
## Bias, Risks, and Limitations
### Recommendations
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
## Training Details
### Training Data
### Training Procedure
#### Preprocessing [optional]
#### Training Hyperparameters
- Training regime:
#### Speeds, Sizes, Times [optional]
## Evaluation
### Testing Data, Factors & Metrics
#### Testing Data
#### Factors
#### Metrics
### Results
#### Summary
## Model Examination [optional]
## Environmental Impact
Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).
- Hardware Type:
- Hours used:
- Cloud Provider:
- Compute Region:
- Carbon Emitted:
## Technical Specifications [optional]
### Model Architecture and Objective
### Compute Infrastructure
#### Hardware
#### Software
[optional]
BibTeX:
APA:
## Glossary [optional]
## More Information [optional]
## Model Card Authors [optional]
## Model Card Contact
| [
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.",
"## How to Get Started with the Model\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] | [
"TAGS\n#transformers #safetensors #stablelm #text-generation #conversational #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #region-us \n",
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.",
"## How to Get Started with the Model\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] |
text-generation | transformers |
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] | {"library_name": "transformers", "tags": []} | hgnoi/fine-tune-3 | null | [
"transformers",
"safetensors",
"stablelm",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | null | 2024-04-19T17:41:48+00:00 | [
"1910.09700"
] | [] | TAGS
#transformers #safetensors #stablelm #text-generation #conversational #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #region-us
|
# Model Card for Model ID
## Model Details
### Model Description
This is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.
- Developed by:
- Funded by [optional]:
- Shared by [optional]:
- Model type:
- Language(s) (NLP):
- License:
- Finetuned from model [optional]:
### Model Sources [optional]
- Repository:
- Paper [optional]:
- Demo [optional]:
## Uses
### Direct Use
### Downstream Use [optional]
### Out-of-Scope Use
## Bias, Risks, and Limitations
### Recommendations
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
## Training Details
### Training Data
### Training Procedure
#### Preprocessing [optional]
#### Training Hyperparameters
- Training regime:
#### Speeds, Sizes, Times [optional]
## Evaluation
### Testing Data, Factors & Metrics
#### Testing Data
#### Factors
#### Metrics
### Results
#### Summary
## Model Examination [optional]
## Environmental Impact
Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).
- Hardware Type:
- Hours used:
- Cloud Provider:
- Compute Region:
- Carbon Emitted:
## Technical Specifications [optional]
### Model Architecture and Objective
### Compute Infrastructure
#### Hardware
#### Software
[optional]
BibTeX:
APA:
## Glossary [optional]
## More Information [optional]
## Model Card Authors [optional]
## Model Card Contact
| [
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.",
"## How to Get Started with the Model\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] | [
"TAGS\n#transformers #safetensors #stablelm #text-generation #conversational #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #region-us \n",
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.",
"## How to Get Started with the Model\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] |
text-generation | transformers |
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] | {"library_name": "transformers", "tags": []} | hgnoi/fine-tune-9 | null | [
"transformers",
"safetensors",
"stablelm",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | null | 2024-04-19T17:41:49+00:00 | [
"1910.09700"
] | [] | TAGS
#transformers #safetensors #stablelm #text-generation #conversational #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #region-us
|
# Model Card for Model ID
## Model Details
### Model Description
This is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.
- Developed by:
- Funded by [optional]:
- Shared by [optional]:
- Model type:
- Language(s) (NLP):
- License:
- Finetuned from model [optional]:
### Model Sources [optional]
- Repository:
- Paper [optional]:
- Demo [optional]:
## Uses
### Direct Use
### Downstream Use [optional]
### Out-of-Scope Use
## Bias, Risks, and Limitations
### Recommendations
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
## Training Details
### Training Data
### Training Procedure
#### Preprocessing [optional]
#### Training Hyperparameters
- Training regime:
#### Speeds, Sizes, Times [optional]
## Evaluation
### Testing Data, Factors & Metrics
#### Testing Data
#### Factors
#### Metrics
### Results
#### Summary
## Model Examination [optional]
## Environmental Impact
Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).
- Hardware Type:
- Hours used:
- Cloud Provider:
- Compute Region:
- Carbon Emitted:
## Technical Specifications [optional]
### Model Architecture and Objective
### Compute Infrastructure
#### Hardware
#### Software
[optional]
BibTeX:
APA:
## Glossary [optional]
## More Information [optional]
## Model Card Authors [optional]
## Model Card Contact
| [
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.",
"## How to Get Started with the Model\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] | [
"TAGS\n#transformers #safetensors #stablelm #text-generation #conversational #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #region-us \n",
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.",
"## How to Get Started with the Model\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] |
text-generation | transformers |
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] | {"library_name": "transformers", "tags": []} | hgnoi/fine-tune-8 | null | [
"transformers",
"safetensors",
"stablelm",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | null | 2024-04-19T17:41:49+00:00 | [
"1910.09700"
] | [] | TAGS
#transformers #safetensors #stablelm #text-generation #conversational #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #region-us
|
# Model Card for Model ID
## Model Details
### Model Description
This is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.
- Developed by:
- Funded by [optional]:
- Shared by [optional]:
- Model type:
- Language(s) (NLP):
- License:
- Finetuned from model [optional]:
### Model Sources [optional]
- Repository:
- Paper [optional]:
- Demo [optional]:
## Uses
### Direct Use
### Downstream Use [optional]
### Out-of-Scope Use
## Bias, Risks, and Limitations
### Recommendations
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
## Training Details
### Training Data
### Training Procedure
#### Preprocessing [optional]
#### Training Hyperparameters
- Training regime:
#### Speeds, Sizes, Times [optional]
## Evaluation
### Testing Data, Factors & Metrics
#### Testing Data
#### Factors
#### Metrics
### Results
#### Summary
## Model Examination [optional]
## Environmental Impact
Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).
- Hardware Type:
- Hours used:
- Cloud Provider:
- Compute Region:
- Carbon Emitted:
## Technical Specifications [optional]
### Model Architecture and Objective
### Compute Infrastructure
#### Hardware
#### Software
[optional]
BibTeX:
APA:
## Glossary [optional]
## More Information [optional]
## Model Card Authors [optional]
## Model Card Contact
| [
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.",
"## How to Get Started with the Model\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] | [
"TAGS\n#transformers #safetensors #stablelm #text-generation #conversational #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #region-us \n",
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.",
"## How to Get Started with the Model\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] |
reinforcement-learning | null |
# **Q-Learning** Agent playing1 **Taxi-v3**
This is a trained model of a **Q-Learning** agent playing **Taxi-v3** .
## Usage
```python
model = load_from_hub(repo_id="moczard/q-Taxi-v3", filename="q-learning.pkl")
# Don't forget to check if you need to add additional attributes (is_slippery=False etc)
env = gym.make(model["env_id"])
```
| {"tags": ["Taxi-v3", "q-learning", "reinforcement-learning", "custom-implementation"], "model-index": [{"name": "q-Taxi-v3", "results": [{"task": {"type": "reinforcement-learning", "name": "reinforcement-learning"}, "dataset": {"name": "Taxi-v3", "type": "Taxi-v3"}, "metrics": [{"type": "mean_reward", "value": "7.56 +/- 2.71", "name": "mean_reward", "verified": false}]}]}]} | moczard/q-Taxi-v3 | null | [
"Taxi-v3",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
] | null | 2024-04-19T17:42:26+00:00 | [] | [] | TAGS
#Taxi-v3 #q-learning #reinforcement-learning #custom-implementation #model-index #region-us
|
# Q-Learning Agent playing1 Taxi-v3
This is a trained model of a Q-Learning agent playing Taxi-v3 .
## Usage
| [
"# Q-Learning Agent playing1 Taxi-v3\n This is a trained model of a Q-Learning agent playing Taxi-v3 .\n\n ## Usage"
] | [
"TAGS\n#Taxi-v3 #q-learning #reinforcement-learning #custom-implementation #model-index #region-us \n",
"# Q-Learning Agent playing1 Taxi-v3\n This is a trained model of a Q-Learning agent playing Taxi-v3 .\n\n ## Usage"
] |
text-generation | transformers |
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] | {"library_name": "transformers", "tags": []} | playgroundai/cogvlm_finetune_v4 | null | [
"transformers",
"safetensors",
"text-generation",
"custom_code",
"arxiv:1910.09700",
"autotrain_compatible",
"region:us"
] | null | 2024-04-19T17:48:02+00:00 | [
"1910.09700"
] | [] | TAGS
#transformers #safetensors #text-generation #custom_code #arxiv-1910.09700 #autotrain_compatible #region-us
|
# Model Card for Model ID
## Model Details
### Model Description
This is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.
- Developed by:
- Funded by [optional]:
- Shared by [optional]:
- Model type:
- Language(s) (NLP):
- License:
- Finetuned from model [optional]:
### Model Sources [optional]
- Repository:
- Paper [optional]:
- Demo [optional]:
## Uses
### Direct Use
### Downstream Use [optional]
### Out-of-Scope Use
## Bias, Risks, and Limitations
### Recommendations
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
## Training Details
### Training Data
### Training Procedure
#### Preprocessing [optional]
#### Training Hyperparameters
- Training regime:
#### Speeds, Sizes, Times [optional]
## Evaluation
### Testing Data, Factors & Metrics
#### Testing Data
#### Factors
#### Metrics
### Results
#### Summary
## Model Examination [optional]
## Environmental Impact
Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).
- Hardware Type:
- Hours used:
- Cloud Provider:
- Compute Region:
- Carbon Emitted:
## Technical Specifications [optional]
### Model Architecture and Objective
### Compute Infrastructure
#### Hardware
#### Software
[optional]
BibTeX:
APA:
## Glossary [optional]
## More Information [optional]
## Model Card Authors [optional]
## Model Card Contact
| [
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.",
"## How to Get Started with the Model\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] | [
"TAGS\n#transformers #safetensors #text-generation #custom_code #arxiv-1910.09700 #autotrain_compatible #region-us \n",
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.",
"## How to Get Started with the Model\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] |
null | adapter-transformers |
# Adapter `BigTMiami/pretrain_dapt_tapt_seq_bn_adpater` for roberta-base
An [adapter](https://adapterhub.ml) for the `roberta-base` model that was trained on the [BigTMiami/amazon_helpfulness_TAPT_pretraining_dataset](https://huggingface.co/datasets/BigTMiami/amazon_helpfulness_TAPT_pretraining_dataset/) dataset.
This adapter was created for usage with the **[Adapters](https://github.com/Adapter-Hub/adapters)** library.
## Usage
First, install `adapters`:
```
pip install -U adapters
```
Now, the adapter can be loaded and activated like this:
```python
from adapters import AutoAdapterModel
model = AutoAdapterModel.from_pretrained("roberta-base")
adapter_name = model.load_adapter("BigTMiami/pretrain_dapt_tapt_seq_bn_adpater", source="hf", set_active=True)
```
## Architecture & Training
<!-- Add some description here -->
## Evaluation results
<!-- Add some description here -->
## Citation
<!-- Add some description here --> | {"tags": ["adapter-transformers", "roberta"], "datasets": ["BigTMiami/amazon_helpfulness_TAPT_pretraining_dataset"]} | BigTMiami/pretrain_dapt_tapt_seq_bn_adpater | null | [
"adapter-transformers",
"roberta",
"dataset:BigTMiami/amazon_helpfulness_TAPT_pretraining_dataset",
"region:us"
] | null | 2024-04-19T17:49:12+00:00 | [] | [] | TAGS
#adapter-transformers #roberta #dataset-BigTMiami/amazon_helpfulness_TAPT_pretraining_dataset #region-us
|
# Adapter 'BigTMiami/pretrain_dapt_tapt_seq_bn_adpater' for roberta-base
An adapter for the 'roberta-base' model that was trained on the BigTMiami/amazon_helpfulness_TAPT_pretraining_dataset dataset.
This adapter was created for usage with the Adapters library.
## Usage
First, install 'adapters':
Now, the adapter can be loaded and activated like this:
## Architecture & Training
## Evaluation results
| [
"# Adapter 'BigTMiami/pretrain_dapt_tapt_seq_bn_adpater' for roberta-base\n\nAn adapter for the 'roberta-base' model that was trained on the BigTMiami/amazon_helpfulness_TAPT_pretraining_dataset dataset.\n\nThis adapter was created for usage with the Adapters library.",
"## Usage\n\nFirst, install 'adapters':\n\n\n\nNow, the adapter can be loaded and activated like this:",
"## Architecture & Training",
"## Evaluation results"
] | [
"TAGS\n#adapter-transformers #roberta #dataset-BigTMiami/amazon_helpfulness_TAPT_pretraining_dataset #region-us \n",
"# Adapter 'BigTMiami/pretrain_dapt_tapt_seq_bn_adpater' for roberta-base\n\nAn adapter for the 'roberta-base' model that was trained on the BigTMiami/amazon_helpfulness_TAPT_pretraining_dataset dataset.\n\nThis adapter was created for usage with the Adapters library.",
"## Usage\n\nFirst, install 'adapters':\n\n\n\nNow, the adapter can be loaded and activated like this:",
"## Architecture & Training",
"## Evaluation results"
] |
null | null |
Model reuploads for https://github.com/MasayaKawamura/MB-iSTFT-VITS | {"license": "apache-2.0"} | ml-for-speech/MB-iSTFT-VITS | null | [
"license:apache-2.0",
"region:us"
] | null | 2024-04-19T17:50:17+00:00 | [] | [] | TAGS
#license-apache-2.0 #region-us
|
Model reuploads for URL | [] | [
"TAGS\n#license-apache-2.0 #region-us \n"
] |
text-classification | transformers |
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] | {"library_name": "transformers", "tags": []} | PFraud/BERT_Covid_Emotion_Classifier | null | [
"transformers",
"safetensors",
"distilbert",
"text-classification",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | null | 2024-04-19T17:50:32+00:00 | [
"1910.09700"
] | [] | TAGS
#transformers #safetensors #distilbert #text-classification #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #region-us
|
# Model Card for Model ID
## Model Details
### Model Description
This is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.
- Developed by:
- Funded by [optional]:
- Shared by [optional]:
- Model type:
- Language(s) (NLP):
- License:
- Finetuned from model [optional]:
### Model Sources [optional]
- Repository:
- Paper [optional]:
- Demo [optional]:
## Uses
### Direct Use
### Downstream Use [optional]
### Out-of-Scope Use
## Bias, Risks, and Limitations
### Recommendations
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
## Training Details
### Training Data
### Training Procedure
#### Preprocessing [optional]
#### Training Hyperparameters
- Training regime:
#### Speeds, Sizes, Times [optional]
## Evaluation
### Testing Data, Factors & Metrics
#### Testing Data
#### Factors
#### Metrics
### Results
#### Summary
## Model Examination [optional]
## Environmental Impact
Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).
- Hardware Type:
- Hours used:
- Cloud Provider:
- Compute Region:
- Carbon Emitted:
## Technical Specifications [optional]
### Model Architecture and Objective
### Compute Infrastructure
#### Hardware
#### Software
[optional]
BibTeX:
APA:
## Glossary [optional]
## More Information [optional]
## Model Card Authors [optional]
## Model Card Contact
| [
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.",
"## How to Get Started with the Model\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] | [
"TAGS\n#transformers #safetensors #distilbert #text-classification #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #region-us \n",
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.",
"## How to Get Started with the Model\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] |
text-classification | bertopic |
# impf_ukrain_postcov_all_sns_topics_umap_lok_hdbscan_lok_ctfidf_seed_17_prob
This is a [BERTopic](https://github.com/MaartenGr/BERTopic) model.
BERTopic is a flexible and modular topic modeling framework that allows for the generation of easily interpretable topics from large datasets.
## Usage
To use this model, please install BERTopic:
```
pip install -U bertopic
```
You can use the model as follows:
```python
from bertopic import BERTopic
topic_model = BERTopic.load("RolMax/impf_ukrain_postcov_all_sns_topics_umap_lok_hdbscan_lok_ctfidf_seed_17_prob")
topic_model.get_topic_info()
```
## Topic overview
* Number of topics: 1010
* Number of training documents: 92912
<details>
<summary>Click here for an overview of all topics.</summary>
| Topic ID | Topic Keywords | Topic Frequency | Label |
|----------|----------------|-----------------|-------|
| 0 | ich - du - bin - hab - mal | 2520 | 0_ich_du_bin_hab |
| 1 | flüchtlinge - migranten - flüchtlingen - kriegsflüchtlinge - migration | 1130 | 1_flüchtlinge_migranten_flüchtlingen_kriegsflüchtlinge |
| 2 | biolabore - biowaffen - biologischen - biologische - labore | 543 | 2_biolabore_biowaffen_biologischen_biologische |
| 3 | öl - gas - russisches - russland - embargo | 824 | 3_öl_gas_russisches_russland |
| 4 | youtube - video - schau - videos - dir | 487 | 4_youtube_video_schau_videos |
| 5 | autos - atomkraft - 2030 - auto - energiewende | 508 | 5_autos_atomkraft_2030_auto |
| 6 | military - krieg - trump - militär - ect | 399 | 6_military_krieg_trump_militär |
| 7 | trump - fbi - hunter - biden - laptop | 408 | 7_trump_fbi_hunter_biden |
| 8 | 18 - rathaus - uhr - markt - 00 | 300 | 8_18_rathaus_uhr_markt |
| 9 | proteste - städten - tausende - polizei - corona | 344 | 9_proteste_städten_tausende_polizei |
| 10 | medien - journalisten - journalismus - mainstream - journalist | 490 | 10_medien_journalisten_journalismus_mainstream |
| 11 | masken - maske - cochrane - tragen - maskenpflicht | 306 | 11_masken_maske_cochrane_tragen |
| 12 | putin - putins - wladimir - waters - präsidenten | 663 | 12_putin_putins_wladimir_waters |
| 13 | my - tägliche - geoengineering - greetings - patriots | 273 | 13_my_tägliche_geoengineering_greetings |
| 14 | weizen - getreide - mais - ag - preise | 273 | 14_weizen_getreide_mais_ag |
| 15 | mrna - dna - gene - impfstoffe - impfstoff | 370 | 15_mrna_dna_gene_impfstoffe |
| 16 | erdbeben - türkei - syrien - beben - syrischen | 373 | 16_erdbeben_türkei_syrien_beben |
| 17 | inflation - ezb - inflationsrate - prozent - fed | 295 | 17_inflation_ezb_inflationsrate_prozent |
| 18 | weihnachten - weihnachtszeit - wünschen - advent - weihnachtsmann | 436 | 18_weihnachten_weihnachtszeit_wünschen_advent |
| 19 | gas - energiepreise - strompreise - benzin - preise | 391 | 19_gas_energiepreise_strompreise_benzin |
| 20 | covid - todesfälle - 19 - injektion - fälle | 486 | 20_covid_todesfälle_19_injektion |
| 21 | strasse - folgt - mir - heute - gestern | 263 | 21_strasse_folgt_mir_heute |
| 22 | frauen - gender - frauentag - gendern - männer | 203 | 22_frauen_gender_frauentag_gendern |
| 23 | cyber - hacker - bsi - schwachstelle - ransomware | 199 | 23_cyber_hacker_bsi_schwachstelle |
| 24 | israel - juden - iran - israels - israelische | 240 | 24_israel_juden_iran_israels |
| 25 | partioten - gruß - mein - kanäle - welt | 190 | 25_partioten_gruß_mein_kanäle |
| 26 | richter - bundesverfassungsgericht - gericht - bundesnotbremse - urteil | 292 | 26_richter_bundesverfassungsgericht_gericht_bundesnotbremse |
| 27 | russen - russische - russland - russischen - russia | 609 | 27_russen_russische_russland_russischen |
| 28 | mariupol - kiew - truppen - ukrainische - russische | 401 | 28_mariupol_kiew_truppen_ukrainische |
| 29 | balloon - ballon - ballons - chinese - spy | 216 | 29_balloon_ballon_ballons_chinese |
| 30 | pfizer - fda - nebenwirkungen - dokumente - impfstoff | 234 | 30_pfizer_fda_nebenwirkungen_dokumente |
| 31 | sanktionen - russland - eu - russische - wirtschaft | 354 | 31_sanktionen_russland_eu_russische |
| 32 | spd - giffey - berlin - rot - wahl | 238 | 32_spd_giffey_berlin_rot |
| 33 | telegram - gu - verteiler - mail - folgt | 241 | 33_telegram_gu_verteiler_mail |
| 34 | insekten - lebensmitteln - lebensmittel - kremerskothen - essen | 150 | 34_insekten_lebensmitteln_lebensmittel_kremerskothen |
| 35 | ignazbearth - wertschätzung - me - läuft - paypal | 162 | 35_ignazbearth_wertschätzung_me_läuft |
| 36 | maßnahmen - infektionsschutzgesetz - märz - corona - regeln | 234 | 36_maßnahmen_infektionsschutzgesetz_märz_corona |
| 37 | kinder - stiko - impfung - impfkommission - kindern | 238 | 37_kinder_stiko_impfung_impfkommission |
| 38 | twitter - tweet - ceiberweiber - account - akten | 177 | 38_twitter_tweet_ceiberweiber_account |
| 39 | china - samsung - peking - chinas - xi | 212 | 39_china_samsung_peking_chinas |
| 40 | trinkwasser - wasser - wasserversorgung - lagern - gechlort | 186 | 40_trinkwasser_wasser_wasserversorgung_lagern |
| 41 | strasse - 12 - folgt - 20 - mir | 287 | 41_strasse_12_folgt_20 |
| 42 | zerstückelung - versteckten - ruin - ziele - europas | 133 | 42_zerstückelung_versteckten_ruin_ziele |
| 43 | greetings - patriots - personal - my - germany | 138 | 43_greetings_patriots_personal_my |
| 44 | kampfjets - polen - mig - lieferung - stoltenberg | 266 | 44_kampfjets_polen_mig_lieferung |
| 45 | greetings - patriots - personal - my - germany | 120 | 45_greetings_patriots_personal_my |
| 46 | negativbewertungen - attacken - german - aufhalten - deutsch | 314 | 46_negativbewertungen_attacken_german_aufhalten |
| 47 | neuestes - zerstörten - zerstückelung - versteckten - ruin | 201 | 47_neuestes_zerstörten_zerstückelung_versteckten |
| 48 | türkei - turkey - chapter - türkiye - türken | 176 | 48_türkei_turkey_chapter_türkiye |
| 49 | telegram - kretschmer - bolsonaro - faeser - messengerdienst | 159 | 49_telegram_kretschmer_bolsonaro_faeser |
| 50 | geoengineering - partioten - tägliche - gruß - politische | 177 | 50_geoengineering_partioten_tägliche_gruß |
| 51 | ufo - ufos - aliens - alien - außerirdische | 154 | 51_ufo_ufos_aliens_alien |
| 52 | klimawandel - klima - co2 - erwärmung - klimawandels | 147 | 52_klimawandel_klima_co2_erwärmung |
| 53 | danke - kallistalk - dank - dolli - allerliebste | 161 | 53_danke_kallistalk_dank_dolli |
| 54 | eva - liebe - andreas - grüße - lieber | 215 | 54_eva_liebe_andreas_grüße |
| 55 | nord - stream - pipeline - inbetriebnahme - ostsee | 144 | 55_nord_stream_pipeline_inbetriebnahme |
| 56 | grundrechte - mfg - neubeginn - kärnten - freiheit | 118 | 56_grundrechte_mfg_neubeginn_kärnten |
| 57 | schulschließungen - schulen - gerichtshof - menschenrechte - egmr | 140 | 57_schulschließungen_schulen_gerichtshof_menschenrechte |
| 58 | impfpflicht - ungeimpfter - impfung - verfassungswidrig - diskriminierung | 200 | 58_impfpflicht_ungeimpfter_impfung_verfassungswidrig |
| 59 | nord - hersh - stream - seymour - pipelines | 124 | 59_nord_hersh_stream_seymour |
| 60 | greetings - patriots - personal - my - germany | 105 | 60_greetings_patriots_personal_my |
| 61 | frieden - wagenknecht - brandenburger - 2023 - schwarzer | 142 | 61_frieden_wagenknecht_brandenburger_2023 |
| 62 | impfpflicht - österreich - verhältnismäßig - ausgesetzt - strafen | 189 | 62_impfpflicht_österreich_verhältnismäßig_ausgesetzt |
| 63 | leopard - panzer - kampfpanzer - lieferung - panzern | 113 | 63_leopard_panzer_kampfpanzer_lieferung |
| 64 | lauterbach - karl - gesundheitsminister - lauterbachs - bundesgesundheitsminister | 184 | 64_lauterbach_karl_gesundheitsminister_lauterbachs |
| 65 | budapest - antifa - linksextremisten - ungarn - engel | 130 | 65_budapest_antifa_linksextremisten_ungarn |
| 66 | gesellschaft - menschenfeinde - entschuldigung - menschen - tyrannei | 320 | 66_gesellschaft_menschenfeinde_entschuldigung_menschen |
| 67 | stromausfall - strom - betroffen - haushalte - ausgefallen | 124 | 67_stromausfall_strom_betroffen_haushalte |
| 68 | negativbewertungen - german - attacken - aufhalten - deutsch | 293 | 68_negativbewertungen_german_attacken_aufhalten |
| 69 | maxwell - epstein - ghislaine - epsteins - andrew | 102 | 69_maxwell_epstein_ghislaine_epsteins |
| 70 | wähler - partei - wahlen - fpö - waldhäusl | 223 | 70_wähler_partei_wahlen_fpö |
| 71 | chip - ki - roboter - musk - nano | 159 | 71_chip_ki_roboter_musk |
| 72 | germany - end - greetings - patriots - personal | 94 | 72_germany_end_greetings_patriots |
| 73 | nesara - gesara - plan - lernst - biblisch | 102 | 73_nesara_gesara_plan_lernst |
| 74 | ignazbearth - wertschätzung - me - strasse - paypal | 159 | 74_ignazbearth_wertschätzung_me_strasse |
| 75 | hersh - seymour - nord - stream - pulitzerpreisträger | 129 | 75_hersh_seymour_nord_stream |
| 76 | germany - end - greetings - patriots - personal | 90 | 76_germany_end_greetings_patriots |
| 77 | shenzhen - hongkong - china - qr - chinesischen | 124 | 77_shenzhen_hongkong_china_qr |
| 78 | barrel - ölpreis - öl - brent - ölpreise | 147 | 78_barrel_ölpreis_öl_brent |
| 79 | omikron - variante - südafrika - omicron - delta | 167 | 79_omikron_variante_südafrika_omicron |
| 80 | löschautomatik - kochgelegenheit - steuerungen - ölpumpen - warmer | 94 | 80_löschautomatik_kochgelegenheit_steuerungen_ölpumpen |
| 81 | pcr - test - tests - impfdosen - mikroben | 131 | 81_pcr_test_tests_impfdosen |
| 82 | schulen - masken - maske - maskenpflicht - schüler | 152 | 82_schulen_masken_maske_maskenpflicht |
| 83 | frieden - gandhi - mahatma - lebendiges - friedensbewegung | 107 | 83_frieden_gandhi_mahatma_lebendiges |
| 84 | frieden - selbstbestimmung - spaziergang - spazieren - montag | 149 | 84_frieden_selbstbestimmung_spaziergang_spazieren |
| 85 | erdbeben - fukushima - freimaurer - stärke - japan | 128 | 85_erdbeben_fukushima_freimaurer_stärke |
| 86 | impfpflicht - allgemeine - impfstoff - booster - deutschland | 257 | 86_impfpflicht_allgemeine_impfstoff_booster |
| 87 | greetings - patriots - personal - my - germany | 80 | 87_greetings_patriots_personal_my |
| 88 | impfpflicht - protest - berlin - impffreiheit - proteste | 103 | 88_impfpflicht_protest_berlin_impffreiheit |
| 89 | palma - la - vulkan - lava - vulkanausbruch | 103 | 89_palma_la_vulkan_lava |
| 90 | polizei - polizisten - bestehend - sachsen - polizeikette | 202 | 90_polizei_polizisten_bestehend_sachsen |
| 91 | denkanstoß - 12 - 2021 - denk - pm | 212 | 91_denkanstoß_12_2021_denk |
| 92 | satanische - satanisten - grammy - satanismus - satan | 103 | 92_satanische_satanisten_grammy_satanismus |
| 93 | vital - ernährung - kopp - borax - zutaten | 102 | 93_vital_ernährung_kopp_borax |
| 94 | angst - panik - entwarnung - furcht - knopf | 151 | 94_angst_panik_entwarnung_furcht |
| 95 | balaton - deutschsprachigen - gemeinschaft - arslan - ben | 87 | 95_balaton_deutschsprachigen_gemeinschaft_arslan |
| 96 | 5g - selleriesaft - trinity - emf - device | 103 | 96_5g_selleriesaft_trinity_emf |
| 97 | brighteon - ecoflow - puresocialnetwork - spreely - spend | 81 | 97_brighteon_ecoflow_puresocialnetwork_spreely |
| 98 | münchen - hamburg - strasse - hannover - düsseldorf | 136 | 98_münchen_hamburg_strasse_hannover |
| 99 | mama - kinder - löwenmamas - mutter - gib | 181 | 99_mama_kinder_löwenmamas_mutter |
| 100 | bitcoin - kryptowährungen - sparkassen - krypto - ethereum | 107 | 100_bitcoin_kryptowährungen_sparkassen_krypto |
| 101 | swift - visa - banken - mastercard - sanktionen | 177 | 101_swift_visa_banken_mastercard |
| 102 | sars - cov - covid - virus - 19 | 140 | 102_sars_cov_covid_virus |
| 103 | bennett - chabad - israels - naftali - premier | 112 | 103_bennett_chabad_israels_naftali |
| 104 | freie - beitreten - medien - medienarbeit - unabhängige | 127 | 104_freie_beitreten_medien_medienarbeit |
| 105 | coronavirus - eg - impfungen - impfstoffe - corona | 159 | 105_coronavirus_eg_impfungen_impfstoffe |
| 106 | lufthansa - flughafen - flughäfen - passagiere - flüge | 92 | 106_lufthansa_flughafen_flughäfen_passagiere |
| 107 | kirche - erzbischof - vigano - katholischen - kirchen | 109 | 107_kirche_erzbischof_vigano_katholischen |
| 108 | demonstrationen - demo - demoteilnehmer - friedfertigkeit - traiskirchen | 151 | 108_demonstrationen_demo_demoteilnehmer_friedfertigkeit |
| 109 | kinder - depressionen - kindern - jugendlichen - jugendliche | 165 | 109_kinder_depressionen_kindern_jugendlichen |
| 110 | buch - charakter - hauptaspekte - beleuchte - bücher | 126 | 110_buch_charakter_hauptaspekte_beleuchte |
| 111 | grünen - grüne - greenpeace - neofaschisten - demokratieverweigerer | 125 | 111_grünen_grüne_greenpeace_neofaschisten |
| 112 | profortis - video - videos - 2546 - 0773 | 160 | 112_profortis_video_videos_2546 |
| 113 | paypal - de22830654080004273567 - iban - bitcoin - iqm | 96 | 113_paypal_de22830654080004273567_iban_bitcoin |
| 114 | dresden - 1945 - dresdens - gedenken - feuersturm | 94 | 114_dresden_1945_dresdens_gedenken |
| 115 | grad - schnee - wetter - celsius - kälte | 76 | 115_grad_schnee_wetter_celsius |
| 116 | tschernobyl - saporischschja - iaea - kernkraftwerk - atomkraftwerk | 103 | 116_tschernobyl_saporischschja_iaea_kernkraftwerk |
| 117 | quade - herr - minute - harley - frag | 83 | 117_quade_herr_minute_harley |
| 118 | friskó - panzió - partioten - gruß - bearth | 85 | 118_friskó_panzió_partioten_gruß |
| 119 | kanal - vivoterra - abonnieren - schatzkammer - wissens | 114 | 119_kanal_vivoterra_abonnieren_schatzkammer |
| 120 | internet - russischen - russland - russische - russiagate | 149 | 120_internet_russischen_russland_russische |
| 121 | övp - fpö - österreicher - neuwahlen - spö | 188 | 121_övp_fpö_österreicher_neuwahlen |
| 122 | x22 - english - report - rumble - bourla | 77 | 122_x22_english_report_rumble |
| 123 | facebook - bmi - velázquez - aya - emails | 77 | 123_facebook_bmi_velázquez_aya |
| 124 | ukraine - ukrainische - ukrainischen - ukrainer - waffen | 300 | 124_ukraine_ukrainische_ukrainischen_ukrainer |
| 125 | rothschild - rothschilds - logen - dynastie - familie | 66 | 125_rothschild_rothschilds_logen_dynastie |
| 126 | who - pandemievertrag - hpi - gecko - abkommen | 117 | 126_who_pandemievertrag_hpi_gecko |
| 127 | gott - kennen - bibel - wonders - abendgebet | 165 | 127_gott_kennen_bibel_wonders |
| 128 | deutschen - 1871 - reich - deutschland - okkupation | 141 | 128_deutschen_1871_reich_deutschland |
| 129 | impfung - impfstoffe - impfstoff - impfpflicht - impfnebenwirkungen | 380 | 129_impfung_impfstoffe_impfstoff_impfpflicht |
| 130 | bali - klimaschützer - klima - generation - klimakleber | 66 | 130_bali_klimaschützer_klima_generation |
| 131 | mega - demo - wien - kundgebung - nachschauen | 118 | 131_mega_demo_wien_kundgebung |
| 132 | cannabis - pflanzen - sauerkraut - permakultur - garten | 118 | 132_cannabis_pflanzen_sauerkraut_permakultur |
| 133 | mückstein - rücktritt - gesundheitsminister - wolfgang - gesundheitsministers | 80 | 133_mückstein_rücktritt_gesundheitsminister_wolfgang |
| 134 | bbc - sears - jp - komiker - patienten | 82 | 134_bbc_sears_jp_komiker |
| 135 | erwachenbefreiung - eindecken - popcorn - zugreifen - medwedew | 71 | 135_erwachenbefreiung_eindecken_popcorn_zugreifen |
| 136 | kimmich - joshua - kim - pucher - dot | 74 | 136_kimmich_joshua_kim_pucher |
| 137 | lauterbach - karl - scholz - gesundheitsminister - bundesgesundheitsminister | 162 | 137_lauterbach_karl_scholz_gesundheitsminister |
| 138 | stirnlampe - lampe - montagearbeiten - perfekte - notfallsituation | 68 | 138_stirnlampe_lampe_montagearbeiten_perfekte |
| 139 | selenskyj - wolodymyr - präsident - ukrainische - eu | 108 | 139_selenskyj_wolodymyr_präsident_ukrainische |
| 140 | deutschland - deutsche - deutschen - linke - rechts | 310 | 140_deutschland_deutsche_deutschen_linke |
| 141 | russland - westen - usa - europarat - russische | 324 | 141_russland_westen_usa_europarat |
| 142 | al - islamischen - syrien - islamisten - ditib | 91 | 142_al_islamischen_syrien_islamisten |
| 143 | krankenhäuser - australischer - krankenhaus - kliniken - 93 | 123 | 143_krankenhäuser_australischer_krankenhaus_kliniken |
| 144 | unsachlicher - beleidigender - aufkommens - deaktivieren - ampelmussweg | 69 | 144_unsachlicher_beleidigender_aufkommens_deaktivieren |
| 145 | pandemie - virus - coetzee - variante - omikron | 151 | 145_pandemie_virus_coetzee_variante |
| 146 | unterstütze - anmelden - rutter - newsletter - ihm | 61 | 146_unterstütze_anmelden_rutter_newsletter |
| 147 | jaco - consultation - landing - precious - page | 76 | 147_jaco_consultation_landing_precious |
| 148 | gold - zukunftskonferenz - goldpreis - dollar - goldmünzen | 76 | 148_gold_zukunftskonferenz_goldpreis_dollar |
| 149 | end - germany - greetings - patriots - personal | 60 | 149_end_germany_greetings_patriots |
| 150 | merkel - angela - politiker - loge - ur | 93 | 150_merkel_angela_politiker_loge |
| 151 | kinder - sozialkontakte - eltern - kind - kindern | 107 | 151_kinder_sozialkontakte_eltern_kind |
| 152 | afd - vorsitz - democracy - abgeordnete - partei | 115 | 152_afd_vorsitz_democracy_abgeordnete |
| 153 | apolut - app - homepage - ios - huawei | 88 | 153_apolut_app_homepage_ios |
| 154 | politiker - politikern - hausverbot - span - fpö | 187 | 154_politiker_politikern_hausverbot_span |
| 155 | megawattstunde - gas - erdgas - gaspreis - ttf | 75 | 155_megawattstunde_gas_erdgas_gaspreis |
| 156 | steuern - quellensteuer - steuer - staat - grundeinkommen | 104 | 156_steuern_quellensteuer_steuer_staat |
| 157 | schiff - schiffe - häfen - suezkanal - hafen | 96 | 157_schiff_schiffe_häfen_suezkanal |
| 158 | orf - gis - zwangsgebühren - ziegler - gebühr | 57 | 158_orf_gis_zwangsgebühren_ziegler |
| 159 | dinar - märz - anleihen - ethereum - wechselkurs | 105 | 159_dinar_märz_anleihen_ethereum |
| 160 | stellplätze - pflanzen - fraubrunnen - wildpflanzen - cannergrow | 96 | 160_stellplätze_pflanzen_fraubrunnen_wildpflanzen |
| 161 | info - direkt - fpö - 2050 - durchblättern | 105 | 161_info_direkt_fpö_2050 |
| 162 | 2g - einzelhandel - regel - oberverwaltungsgericht - lüneburg | 119 | 162_2g_einzelhandel_regel_oberverwaltungsgericht |
| 163 | rassismus - hass - hautfarbe - weißer - hahne | 89 | 163_rassismus_hass_hautfarbe_weißer |
| 164 | regelmäßige - spaziergänge - ca - teilnehmer - spaziergang | 104 | 164_regelmäßige_spaziergänge_ca_teilnehmer |
| 165 | ärztekammer - ärzte - brief - innen - mediziner | 103 | 165_ärztekammer_ärzte_brief_innen |
| 166 | 00 - uhr - nürnberg - sonntag - gipfelkreuz | 81 | 166_00_uhr_nürnberg_sonntag |
| 167 | pharmaindustrie - medikamente - pharma - medikament - rockefeller | 128 | 167_pharmaindustrie_medikamente_pharma_medikament |
| 168 | reitschuster - boris - bundespressekonferenz - zensurwelle - zensurfreien | 100 | 168_reitschuster_boris_bundespressekonferenz_zensurwelle |
| 169 | bohlen - dsds - krasavice - gerry - anmerkungen | 161 | 169_bohlen_dsds_krasavice_gerry |
| 170 | drucksimulation - gewichtsdecke - schlafqualität - hervorgerufene - umarmung | 93 | 170_drucksimulation_gewichtsdecke_schlafqualität_hervorgerufene |
| 171 | gasheizung - teekessel - ester - verbrennungsluftzufuhr - stromunabhängiges | 64 | 171_gasheizung_teekessel_ester_verbrennungsluftzufuhr |
| 172 | karmasin - sophie - familienministerin - övp - festgenommen | 65 | 172_karmasin_sophie_familienministerin_övp |
| 173 | 02 - 2023 - 06 - 2023folgt - stnewslive | 93 | 173_02_2023_06_2023folgt |
| 174 | filter - hohlfaser - zuverlässigste - verschmutzten - fortschrittlicher | 54 | 174_filter_hohlfaser_zuverlässigste_verschmutzten |
| 175 | veritas - rosenberg - project - undercover - fbi | 70 | 175_veritas_rosenberg_project_undercover |
| 176 | übersterblichkeit - schweden - sterbefallzahlen - mittleren - vorjahre | 97 | 176_übersterblichkeit_schweden_sterbefallzahlen_mittleren |
| 177 | messer - verletzt - mann - polizei - polizist | 168 | 177_messer_verletzt_mann_polizei |
| 178 | nürnberg - straße - saalfeld - 12 - wien | 122 | 178_nürnberg_straße_saalfeld_12 |
| 179 | impfpflicht - bundestag - impfpflichtgesetz - stellungnahme - allgemeine | 257 | 179_impfpflicht_bundestag_impfpflichtgesetz_stellungnahme |
| 180 | nato - krieg - usa - jugoslawien - osterweiterung | 269 | 180_nato_krieg_usa_jugoslawien |
| 181 | rt - sputnik - talpa - rtl - today | 69 | 181_rt_sputnik_talpa_rtl |
| 182 | thurner - interview - catherine - hahn - nadja | 123 | 182_thurner_interview_catherine_hahn |
| 183 | stromnetz - teslas - stromnetze - kadri - energiekommissarin | 71 | 183_stromnetz_teslas_stromnetze_kadri |
| 184 | tornados - kentucky - beshear - tornado - taifun | 103 | 184_tornados_kentucky_beshear_tornado |
| 185 | zelensky - zelenskyy - sandu - maia - zemmour | 92 | 185_zelensky_zelenskyy_sandu_maia |
| 186 | kaliningrad - domizil - facebook - nichtkommerziellen - informationskanals | 71 | 186_kaliningrad_domizil_facebook_nichtkommerziellen |
| 187 | 850 - fc - funkgerät - schwimmfähiges - wasserdichtes | 52 | 187_850_fc_funkgerät_schwimmfähiges |
| 188 | polizei - polizisten - polizeigewalt - kette - durchbruch | 121 | 188_polizei_polizisten_polizeigewalt_kette |
| 189 | kolloidales - silber - bakterien - pilze - meistverkaufte | 58 | 189_kolloidales_silber_bakterien_pilze |
| 190 | habeck - wirtschaftsminister - robert - reduction - vizekanzler | 148 | 190_habeck_wirtschaftsminister_robert_reduction |
| 191 | nachtragshaushalt - schulden - milliarden - vermögensregister - bargeld | 137 | 191_nachtragshaushalt_schulden_milliarden_vermögensregister |
| 192 | brille - alt - nervigeres - kontaktlinsen - nerviger | 59 | 192_brille_alt_nervigeres_kontaktlinsen |
| 193 | geräuschlose - hervorzuheben - innenräumen - profi - verwendung | 58 | 193_geräuschlose_hervorzuheben_innenräumen_profi |
| 194 | risikobewertung - covid - 19 - impfstoffe - übertragungen | 173 | 194_risikobewertung_covid_19_impfstoffe |
| 195 | ukraine - krieg - ukrainekrieg - ritter - scott | 219 | 195_ukraine_krieg_ukrainekrieg_ritter |
| 196 | krieg - nato - ukraine - mali - scholz | 244 | 196_krieg_nato_ukraine_mali |
| 197 | weihnachten - lockdown - ungeimpfte - regeln - weihnachtsfest | 164 | 197_weihnachten_lockdown_ungeimpfte_regeln |
| 198 | infrastruktur - feuerwehr - kritische - omikron - grundversorgung | 77 | 198_infrastruktur_feuerwehr_kritische_omikron |
| 199 | transgender - geschlecht - trans - reed - ditib | 72 | 199_transgender_geschlecht_trans_reed |
| 200 | convoy - konvoi - trucker - dc - washington | 59 | 200_convoy_konvoi_trucker_dc |
| 201 | nelson - moral - vorlesung - luther - fingen | 106 | 201_nelson_moral_vorlesung_luther |
| 202 | europarat - eu - gerichtshof - unversehrtheit - union | 89 | 202_europarat_eu_gerichtshof_unversehrtheit |
| 203 | irlmaier - chatgpt - verschwörungstheorie - alois - verschwörungstheorien | 113 | 203_irlmaier_chatgpt_verschwörungstheorie_alois |
| 204 | wissenschaft - wissenschaftler - körpersprache - slomka - zahlen | 120 | 204_wissenschaft_wissenschaftler_körpersprache_slomka |
| 205 | netzfund - jenny - russländer - gutmütige - ruhezeit | 86 | 205_netzfund_jenny_russländer_gutmütige |
| 206 | micro - kurbelradio - honorieren - pfefferspraypistole - notration | 57 | 206_micro_kurbelradio_honorieren_pfefferspraypistole |
| 207 | österreich - adnet - dänemark - markel - resort | 154 | 207_österreich_adnet_dänemark_markel |
| 208 | abendlandes - oswald - kommunismus - spengler - untergang | 131 | 208_abendlandes_oswald_kommunismus_spengler |
| 209 | mariupol - hafenstadt - stadt - wasser - kiew | 120 | 209_mariupol_hafenstadt_stadt_wasser |
| 210 | pelargoni - pilogrip - tabs - bingen - hildegard | 95 | 210_pelargoni_pilogrip_tabs_bingen |
| 211 | juden - jüdische - jüdischen - antisemitische - adl | 115 | 211_juden_jüdische_jüdischen_antisemitische |
| 212 | bechern - gusseisen - untersetzer - teekanne - edlem | 54 | 212_bechern_gusseisen_untersetzer_teekanne |
| 213 | germany - end - greetings - patriots - personal | 50 | 213_germany_end_greetings_patriots |
| 214 | piks - nieswandt - hill - schatten - luis | 55 | 214_piks_nieswandt_hill_schatten |
| 215 | novavax - impfstoff - totimpfstoff - valneva - proteinimpfstoff | 56 | 215_novavax_impfstoff_totimpfstoff_valneva |
| 216 | biostatus - biotechnokratie - wohlwollender - gesundheitswesen - allumfassenden | 73 | 216_biostatus_biotechnokratie_wohlwollender_gesundheitswesen |
| 217 | music - discord - contribution - brown - minds | 65 | 217_music_discord_contribution_brown |
| 218 | grosz - gerald - geraldgrosz - oe24 - com | 55 | 218_grosz_gerald_geraldgrosz_oe24 |
| 219 | gunnar - kaiser - kaisertv - kanalmitgliedschaft - seminaren | 62 | 219_gunnar_kaiser_kaisertv_kanalmitgliedschaft |
| 220 | polens - verschwiegene - compact - geschichtsheft - schuld | 60 | 220_polens_verschwiegene_compact_geschichtsheft |
| 221 | geld - schritt - inflation - exklusivem - enteignen | 206 | 221_geld_schritt_inflation_exklusivem |
| 222 | münchen - 2023 - spunktnews - düsseldorf - 02 | 93 | 222_münchen_2023_spunktnews_düsseldorf |
| 223 | spike - protein - spikeprotein - mutationen - südkorea | 98 | 223_spike_protein_spikeprotein_mutationen |
| 224 | biden - joe - putin - soros - präsident | 267 | 224_biden_joe_putin_soros |
| 225 | starlink - musk - spacex - elon - satelliten | 48 | 225_starlink_musk_spacex_elon |
| 226 | lion - media - de32100110012624879184 - maca - kontoverbindung | 97 | 226_lion_media_de32100110012624879184_maca |
| 227 | agüero - herzstillstand - lindelof - fußball - sergio | 50 | 227_agüero_herzstillstand_lindelof_fußball |
| 228 | heldenplatz - samstag - 12 - linz - freiheit | 101 | 228_heldenplatz_samstag_12_linz |
| 229 | wien - heldenplatz - megademo - wi2612 - 12 | 110 | 229_wien_heldenplatz_megademo_wi2612 |
| 230 | tesla - wse - grünheide - gigafactory - kubikmeter | 69 | 230_tesla_wse_grünheide_gigafactory |
| 231 | neutralität - österreichs - immerwährende - österreich - neutral | 63 | 231_neutralität_österreichs_immerwährende_österreich |
| 232 | hallo - 7605 - überweisung - 0013 - meinung | 60 | 232_hallo_7605_überweisung_0013 |
| 233 | stauraum - taiwan - tarp - lügen - schlafbereich | 119 | 233_stauraum_taiwan_tarp_lügen |
| 234 | beschwerde - orf - verharmlost - formelle - nebenwirkungen | 55 | 234_beschwerde_orf_verharmlost_formelle |
| 235 | perspektiven - arge - veranstalten - bundeskazleramt - andauernde | 99 | 235_perspektiven_arge_veranstalten_bundeskazleramt |
| 236 | ukrainerin - vergewaltigt - tunesier - hotelschiff - flüchtlingsunterkunft | 69 | 236_ukrainerin_vergewaltigt_tunesier_hotelschiff |
| 237 | demokratie - direkte - parteidiktatur - hilf - blah | 69 | 237_demokratie_direkte_parteidiktatur_hilf |
| 238 | transhumanismus - magnet - stefan - transhumanisten - auflage | 57 | 238_transhumanismus_magnet_stefan_transhumanisten |
| 239 | nolade21sho - de11230510300115432221 - 23051030 - südholstein - zahlungsgrund | 59 | 239_nolade21sho_de11230510300115432221_23051030_südholstein |
| 240 | rtl - borrell - josep - außenbeauftragte - zensur | 46 | 240_rtl_borrell_josep_außenbeauftragte |
| 241 | impfpflicht - allgemeine - gesetz - bundestag - gesetzentwurf | 307 | 241_impfpflicht_allgemeine_gesetz_bundestag |
| 242 | gold - mehrwertsteuer - edelmetallen - rubel - wertverluste | 51 | 242_gold_mehrwertsteuer_edelmetallen_rubel |
| 243 | mayerweck - psychopathen - psychedelika - stockholmsyndrom - dauerpropaganda | 66 | 243_mayerweck_psychopathen_psychedelika_stockholmsyndrom |
| 244 | sönnichsen - freispruch - prozess - amtsanmaßung - andreas | 121 | 244_sönnichsen_freispruch_prozess_amtsanmaßung |
| 245 | registriert - 2022 - nostradamus - pocus - hocus | 101 | 245_registriert_2022_nostradamus_pocus |
| 246 | partioten - gruß - mein - kanäle - welt | 46 | 246_partioten_gruß_mein_kanäle |
| 247 | armut - kapitalismus - wohlstand - krise - marktwirtschaft | 164 | 247_armut_kapitalismus_wohlstand_krise |
| 248 | nato - russland - ukraine - waffen - stoltenberg | 299 | 248_nato_russland_ukraine_waffen |
| 249 | cdu - maaßen - maca - merz - georg | 61 | 249_cdu_maaßen_maca_merz |
| 250 | gott - jesus - gottes - huxley - jesu | 79 | 250_gott_jesus_gottes_huxley |
| 251 | ärztekammer - wohlfahrtsfonds - szekeres - referate - pensionsversicherung | 58 | 251_ärztekammer_wohlfahrtsfonds_szekeres_referate |
| 252 | duran - 0xd449694348b1d618eca2829bbc901782f5172689 - exx4kk9pzlx7uilwncxtp7imkjtq6o5b6r - emc2 - hex | 48 | 252_duran_0xd449694348b1d618eca2829bbc901782f5172689_exx4kk9pzlx7uilwncxtp7imkjtq6o5b6r_emc2 |
| 253 | faeser - hessen - nancy - bundesinnenministerin - ministerpräsidentin | 68 | 253_faeser_hessen_nancy_bundesinnenministerin |
| 254 | rt - abgelehnt - telegram - de - debitkarten | 53 | 254_rt_abgelehnt_telegram_de |
| 255 | polizei - polizisten - spaziergänge - personalien - pölten | 133 | 255_polizei_polizisten_spaziergänge_personalien |
| 256 | hitler - nazis - nazi - adolf - umerziehung | 225 | 256_hitler_nazis_nazi_adolf |
| 257 | anwälte - bundesverfassungsgericht - karlsruhe - aufklärung - demonstration | 110 | 257_anwälte_bundesverfassungsgericht_karlsruhe_aufklärung |
| 258 | antarktis - antarctica - insel - byrd - admiral | 48 | 258_antarktis_antarctica_insel_byrd |
| 259 | servustv - servus - suche - marlene - meeting | 68 | 259_servustv_servus_suche_marlene |
| 260 | protest - symbol - freiheit - patriotische - banner | 116 | 260_protest_symbol_freiheit_patriotische |
| 261 | ecoflow - patentierter - aufgeladen - powerstation - tragbare | 42 | 261_ecoflow_patentierter_aufgeladen_powerstation |
| 262 | sahara - staub - schwermetalle - laboranalyse - magnetisch | 42 | 262_sahara_staub_schwermetalle_laboranalyse |
| 263 | aktiendepot - investieren - micro - adresse - captrader | 62 | 263_aktiendepot_investieren_micro_adresse |
| 264 | orban - ungarn - viktor - ungarische - orbán | 48 | 264_orban_ungarn_viktor_ungarische |
| 265 | lied - song - baby - concordia - costa | 85 | 265_lied_song_baby_concordia |
| 266 | betten - intensivbetten - intensivstationen - krankenhäuser - patienten | 153 | 266_betten_intensivbetten_intensivstationen_krankenhäuser |
| 267 | greetings - patriots - personal - my - germany | 42 | 267_greetings_patriots_personal_my |
| 268 | vitamin - k2 - fettlösliches - mct - d3 | 42 | 268_vitamin_k2_fettlösliches_mct |
| 269 | wien - demo - datum - 12 - 00 | 127 | 269_wien_demo_datum_12 |
| 270 | ahrtal - flutkatastrophe - flut - katastrophe - rheinland | 55 | 270_ahrtal_flutkatastrophe_flut_katastrophe |
| 271 | hierfür - petroleumheizung - folgende - vorteile - alternative | 42 | 271_hierfür_petroleumheizung_folgende_vorteile |
| 272 | rt - impfforscher - haintz_ - eigensicht - behandlungsforscher | 46 | 272_rt_impfforscher_haintz__eigensicht |
| 273 | gutenmorgen - wochenende - exxtrafrüh - wünscht - morgen | 73 | 273_gutenmorgen_wochenende_exxtrafrüh_wünscht |
| 274 | schlaf - nacht - schlafen - hellwach - wälzt | 89 | 274_schlaf_nacht_schlafen_hellwach |
| 275 | vonovia - wohnungen - neubau - zinsen - wohnungsmarkt | 88 | 275_vonovia_wohnungen_neubau_zinsen |
| 276 | blackout - pc - blackouts - stromausfall - checkliste | 75 | 276_blackout_pc_blackouts_stromausfall |
| 277 | cbdc - id - sucharit - bhakdi - digital | 49 | 277_cbdc_id_sucharit_bhakdi |
| 278 | zensur - blockierungen - qualitätssiegel - löschungen - strikes | 83 | 278_zensur_blockierungen_qualitätssiegel_löschungen |
| 279 | mahlsteinen - korund - selbstschärfender - getreides - getrocknete | 40 | 279_mahlsteinen_korund_selbstschärfender_getreides |
| 280 | 2g - hochschulen - verwaltungsgerichtshof - vgh - regelung | 76 | 280_2g_hochschulen_verwaltungsgerichtshof_vgh |
| 281 | verbrechen - verbrechern - niro - verbrecher - samurai | 126 | 281_verbrechen_verbrechern_niro_verbrecher |
| 282 | flugobjekt - alaska - flugobjekte - objekt - abgeschossen | 99 | 282_flugobjekt_alaska_flugobjekte_objekt |
| 283 | versteckte - ressourcen - nutzen - zugriffe - unerwartet | 48 | 283_versteckte_ressourcen_nutzen_zugriffe |
| 284 | neuestes - zerstörten - boden - wasserstandsmeldung - mäckle | 62 | 284_neuestes_zerstörten_boden_wasserstandsmeldung |
| 285 | feb - march - day - 122221 - october | 94 | 285_feb_march_day_122221 |
| 286 | cnn - russland - bbc - ard - berichterstattung | 184 | 286_cnn_russland_bbc_ard |
| 287 | vorzubauen - rechtzeitig - zensurfreien - tragen - auf1 | 49 | 287_vorzubauen_rechtzeitig_zensurfreien_tragen |
| 288 | msm - selbstfaktenfriedenfreiheit - denkt - shorts - tiktok | 47 | 288_msm_selbstfaktenfriedenfreiheit_denkt_shorts |
| 289 | powerstation - stromvorrat - abrufen - jeglichen - speichern | 45 | 289_powerstation_stromvorrat_abrufen_jeglichen |
| 290 | rauch - gesundheitsminister - spahn - johannes - impfpflicht | 101 | 290_rauch_gesundheitsminister_spahn_johannes |
| 291 | atomkraftwerk - akw - saporischschja - odessa - ukrenerho | 79 | 291_atomkraftwerk_akw_saporischschja_odessa |
| 292 | anne - spiegel - bundesfamilienministerin - rheinland - flutkatastrophe | 61 | 292_anne_spiegel_bundesfamilienministerin_rheinland |
| 293 | preise - milch - butter - kühe - survivalspezialisten | 78 | 293_preise_milch_butter_kühe |
| 294 | chemikalien - pfas - sporen - umwelt - luftreiniger | 99 | 294_chemikalien_pfas_sporen_umwelt |
| 295 | corona - aufarbeitung - maßnahmen - yeadon - gipfel | 148 | 295_corona_aufarbeitung_maßnahmen_yeadon |
| 296 | impfpflicht - impfung - allgemeine - impfzwanges - impfzwang | 304 | 296_impfpflicht_impfung_allgemeine_impfzwanges |
| 297 | mfg - dr - univ - med - rechtsanwalt | 71 | 297_mfg_dr_univ_med |
| 298 | geburtshaus - schwangere - baby - mutter - schwangeren | 93 | 298_geburtshaus_schwangere_baby_mutter |
| 299 | bubble - leiberl - komm - zeug - kumm | 66 | 299_bubble_leiberl_komm_zeug |
| 300 | putin - russland - nato - russlands - wladimir | 379 | 300_putin_russland_nato_russlands |
| 301 | jane - ruby - peters - stew - show | 62 | 301_jane_ruby_peters_stew |
| 302 | moral - unmoral - henry - australien - miller | 96 | 302_moral_unmoral_henry_australien |
| 303 | haushalt - einfachste - anymore - unfortunately - kritisches | 38 | 303_haushalt_einfachste_anymore_unfortunately |
| 304 | freundinnen - braun - roman - thule - freunde | 49 | 304_freundinnen_braun_roman_thule |
| 305 | 4200 - keramik - eingebauter - aussenbereiche - heizstufen | 38 | 305_4200_keramik_eingebauter_aussenbereiche |
| 306 | brauche - liebe - du - abendgebet - bist | 110 | 306_brauche_liebe_du_abendgebet |
| 307 | euro - geld - hauser - grundsteuer - inflation | 217 | 307_euro_geld_hauser_grundsteuer |
| 308 | zahnpulver - fluchtrucksack - birkengold - lausen - österreicher | 46 | 308_zahnpulver_fluchtrucksack_birkengold_lausen |
| 309 | reichelt - zeitung - berliner - lobbyarbeit - döpfner | 122 | 309_reichelt_zeitung_berliner_lobbyarbeit |
| 310 | medizin - sepp - forcher - med - hausärztliche | 55 | 310_medizin_sepp_forcher_med |
| 311 | geschützt - niedrigstand - lagerbestand - eco - begrenzter | 38 | 311_geschützt_niedrigstand_lagerbestand_eco |
| 312 | rabbit - research - folge - verlierst - enger | 40 | 312_rabbit_research_folge_verlierst |
| 313 | unterirdischen - fort - 555 - tunnel - kampfeinheiten | 51 | 313_unterirdischen_fort_555_tunnel |
| 314 | gps - satelliten - enercon - kosmos - windkraftanlagen | 40 | 314_gps_satelliten_enercon_kosmos |
| 315 | gates - bill - melinda - epstein - jeffrey | 37 | 315_gates_bill_melinda_epstein |
| 316 | jobsuche - jobplattform - füreinefreieimpfentscheidung - vollzeit - jobs | 48 | 316_jobsuche_jobplattform_füreinefreieimpfentscheidung_vollzeit |
| 317 | lauterbach - marcel - karl - felix - format | 78 | 317_lauterbach_marcel_karl_felix |
| 318 | russische - russen - soldaten - russischen - mariupol | 226 | 318_russische_russen_soldaten_russischen |
| 319 | cyberangriff - cyber - websites - israelische - israel | 54 | 319_cyberangriff_cyber_websites_israelische |
| 320 | ohio - raststätten - palestine - train - tankkarten | 97 | 320_ohio_raststätten_palestine_train |
| 321 | eu - verschlüsselte - verhandlungsakten - visart - bocarmé | 63 | 321_eu_verschlüsselte_verhandlungsakten_visart |
| 322 | lichte - dreibändige - reinkarnation - erkenntnisquelle - sinnzusammenhänge | 37 | 322_lichte_dreibändige_reinkarnation_erkenntnisquelle |
| 323 | innsbruck - tiroler - stahls - tageszeitung - eisbrocken | 52 | 323_innsbruck_tiroler_stahls_tageszeitung |
| 324 | neutralität - meloni - bellen - österreich - nato | 178 | 324_neutralität_meloni_bellen_österreich |
| 325 | taschenmesser - forester - funktionen - victorinox - pisten | 93 | 325_taschenmesser_forester_funktionen_victorinox |
| 326 | asta - polizei - polizisten - wertekultur - staatsbürgerlichen | 119 | 326_asta_polizei_polizisten_wertekultur |
| 327 | impfpflicht - flyover - schöfbeck - geiselhaft - impfung | 234 | 327_impfpflicht_flyover_schöfbeck_geiselhaft |
| 328 | faschismus - fabianer - faschisten - schockiert - nazi | 120 | 328_faschismus_fabianer_faschisten_schockiert |
| 329 | digitale - währung - digitalen - zentralbanken - brics | 122 | 329_digitale_währung_digitalen_zentralbanken |
| 330 | prozesse - wcr - entzündliche - copd - astaxanthin | 51 | 330_prozesse_wcr_entzündliche_copd |
| 331 | foto - unregierbar - gartz - ludwig - catherine | 52 | 331_foto_unregierbar_gartz_ludwig |
| 332 | eu - deutschland - deutschen - deutsche - außenpolitik | 203 | 332_eu_deutschland_deutschen_deutsche |
| 333 | französisch - dreisprachig - prass - innen - holzschnitten | 178 | 333_französisch_dreisprachig_prass_innen |
| 334 | freedom - food - contamination - passionately - remedies | 42 | 334_freedom_food_contamination_passionately |
| 335 | streik - dich - organisiertes - streikpotenzial - profilnamen | 41 | 335_streik_dich_organisiertes_streikpotenzial |
| 336 | bundeswehr - sondervermögen - milliarden - soldatinnen - amtshilfe | 94 | 336_bundeswehr_sondervermögen_milliarden_soldatinnen |
| 337 | willst - sklaven - sklaverei - neutralität - sklave | 54 | 337_willst_sklaven_sklaverei_neutralität |
| 338 | trägt - vitamin - kiefernadeln - normalen - bestellung | 49 | 338_trägt_vitamin_kiefernadeln_normalen |
| 339 | guten - morgen - schönen - freundinnen - denkt | 89 | 339_guten_morgen_schönen_freundinnen |
| 340 | krankenhäuser - kliniken - intensivstationen - corona - intensivbetten | 133 | 340_krankenhäuser_kliniken_intensivstationen_corona |
| 341 | edeka - produkte - regale - regalen - händler | 47 | 341_edeka_produkte_regale_regalen |
| 342 | bodensafe - xl - panzerband - komfortabel - kistenschleppen | 74 | 342_bodensafe_xl_panzerband_komfortabel |
| 343 | wirtschaftsbereiche - bundesgerichtshof - bgh - entschädigung - staatshaftung | 64 | 343_wirtschaftsbereiche_bundesgerichtshof_bgh_entschädigung |
| 344 | budapest - bettinalube - ungarn - telegramzur - ignazbearth | 73 | 344_budapest_bettinalube_ungarn_telegramzur |
| 345 | corona - schilling - 22 - mayer - stellungnahmemöglichkeit | 61 | 345_corona_schilling_22_mayer |
| 346 | nazis - 2014 - ukrainische - bataillon - säubern | 110 | 346_nazis_2014_ukrainische_bataillon |
| 347 | aramid - handschuhe - handrückenbereich - handfläche - leder | 35 | 347_aramid_handschuhe_handrückenbereich_handfläche |
| 348 | akku - universalradio - weltempfänger - weltempfang - unersetzlichen | 41 | 348_akku_universalradio_weltempfänger_weltempfang |
| 349 | teiegram - rüber - aufgerollt - verspreche - gleichgeschaltet | 55 | 349_teiegram_rüber_aufgerollt_verspreche |
| 350 | willhaben - idealism - prevails - 4810 - gmunden | 58 | 350_willhaben_idealism_prevails_4810 |
| 351 | kaserne - soldaten - arrest - minden - mindener | 108 | 351_kaserne_soldaten_arrest_minden |
| 352 | assange - julian - wikileaks - auslieferung - ausgeliefert | 51 | 352_assange_julian_wikileaks_auslieferung |
| 353 | wiederzuentdecken - unzulänglichkeiten - gelegenheiten - verborgene - fortschritt | 35 | 353_wiederzuentdecken_unzulänglichkeiten_gelegenheiten_verborgene |
| 354 | bitcoin - neuezeit - 19q8odiu2zar7dfl18ouqivwauvnripceu - core - 1wxoeuy6ghetkmurdiipllwvya1vh2iwa | 45 | 354_bitcoin_neuezeit_19q8odiu2zar7dfl18ouqivwauvnripceu_core |
| 355 | müller - kaiser - philharmoniker - dirigent - musik | 61 | 355_müller_kaiser_philharmoniker_dirigent |
| 356 | nährstoffe - bioverfügbarkeit - phospholipid - doppelschicht - liposomale | 35 | 356_nährstoffe_bioverfügbarkeit_phospholipid_doppelschicht |
| 357 | erde - giuliana - asteroid - conforto - persei | 79 | 357_erde_giuliana_asteroid_conforto |
| 358 | geigerzähler - radioaktiver - counter - strahlung - cm | 64 | 358_geigerzähler_radioaktiver_counter_strahlung |
| 359 | platzsparende - kraftpapier - plombierbarem - granulate - außenliegendem | 35 | 359_platzsparende_kraftpapier_plombierbarem_granulate |
| 360 | handgenerators - umdrehungen - einsatzfähig - schlechtem - genügen | 35 | 360_handgenerators_umdrehungen_einsatzfähig_schlechtem |
| 361 | weishaupt - schlagstöcke - pfefferspray - saskia - maßnahmen | 164 | 361_weishaupt_schlagstöcke_pfefferspray_saskia |
| 362 | pawlowski - pastor - artur - stewpeters - his | 46 | 362_pawlowski_pastor_artur_stewpeters |
| 363 | faktenchecker - faktenchecks - fakten - finanziert - behauptung | 108 | 363_faktenchecker_faktenchecks_fakten_finanziert |
| 364 | ausgängen - usb - aufladung - netzsteckdosen - kfz | 35 | 364_ausgängen_usb_aufladung_netzsteckdosen |
| 365 | bäckereien - fleisch - landwirtschaft - tonnen - vegane | 94 | 365_bäckereien_fleisch_landwirtschaft_tonnen |
| 366 | krankenschwester - ärztekammer - sönnichsen - andreas - atzorn | 143 | 366_krankenschwester_ärztekammer_sönnichsen_andreas |
| 367 | leer - vollkorn - lebensmitteldiscounter - dosenbrot - verfügen | 60 | 367_leer_vollkorn_lebensmitteldiscounter_dosenbrot |
| 368 | arabien - saudi - yuan - indien - dollar | 35 | 368_arabien_saudi_yuan_indien |
| 369 | stew - content - advertise - episodes - shedding | 34 | 369_stew_content_advertise_episodes |
| 370 | niedersachsen - aktionen - freieniedersachsen - übersicht - info | 52 | 370_niedersachsen_aktionen_freieniedersachsen_übersicht |
| 371 | 3506 - 0006 - 1309 - at2s - at75 | 192 | 371_3506_0006_1309_at2s |
| 372 | schlafsack - schlafsackinneren - thermolite - geringem - isolierung | 42 | 372_schlafsack_schlafsackinneren_thermolite_geringem |
| 373 | biden - hunter - joe - burisma - trump | 111 | 373_biden_hunter_joe_burisma |
| 374 | humanus - codex - sturmlaterne - flamme - klassiker | 77 | 374_humanus_codex_sturmlaterne_flamme |
| 375 | gärventilschon - säuerlichen - beete - aromatischen - karotten | 45 | 375_gärventilschon_säuerlichen_beete_aromatischen |
| 376 | diesel - liter - benzin - e10 - cent | 68 | 376_diesel_liter_benzin_e10 |
| 377 | verordnungen - covid - verfassungs - gesetzeswidrig - gesetzwidrig | 99 | 377_verordnungen_covid_verfassungs_gesetzeswidrig |
| 378 | kabellos - integriertes - digitalkamera - spritzwassergeschütztes - tablet | 53 | 378_kabellos_integriertes_digitalkamera_spritzwassergeschütztes |
| 379 | lautstärke - stuht - zusätze - kai - filmprojekte | 34 | 379_lautstärke_stuht_zusätze_kai |
| 380 | kommission - leyen - flyer - york - times | 80 | 380_kommission_leyen_flyer_york |
| 381 | tool - rvm - victorinox - gun - papers | 74 | 381_tool_rvm_victorinox_gun |
| 382 | videokanal - rebell - nachrichtenkanal - aufklärungsvideos - hilfreiche | 34 | 382_videokanal_rebell_nachrichtenkanal_aufklärungsvideos |
| 383 | bunker - ioi - oil - nuklearen - a6 | 100 | 383_bunker_ioi_oil_nuklearen |
| 384 | bismarck - negativbewertungen - aufhalten - german - attacken | 304 | 384_bismarck_negativbewertungen_aufhalten_german |
| 385 | viralität - seminare - scenes - kanalmitglied - livestreams | 68 | 385_viralität_seminare_scenes_kanalmitglied |
| 386 | salman - saudi - mohammed - schwert - trump | 36 | 386_salman_saudi_mohammed_schwert |
| 387 | spiritualität - mystica - spirituellen - abendgebet - tepperwein | 53 | 387_spiritualität_mystica_spirituellen_abendgebet |
| 388 | catherine - thurner - catherines - kanalinfo - sendungen | 134 | 388_catherine_thurner_catherines_kanalinfo |
| 389 | wolff - ngos - ernst - komlosy - sarabennett | 64 | 389_wolff_ngos_ernst_komlosy |
| 390 | bp - nattokinase - nährwerte - süß - norwegischen | 50 | 390_bp_nattokinase_nährwerte_süß |
| 391 | innenfach - abnehmbare - hüfttasche - urheberrechtsgesetz - schutzrechte | 68 | 391_innenfach_abnehmbare_hüfttasche_urheberrechtsgesetz |
| 392 | live - streamen - twitch - lbry - kanälen | 52 | 392_live_streamen_twitch_lbry |
| 393 | abtreibungen - abtreibung - abortion - didenko - geburt | 50 | 393_abtreibungen_abtreibung_abortion_didenko |
| 394 | müller - soul - mittelerde - checkmatenews - sam | 43 | 394_müller_soul_mittelerde_checkmatenews |
| 395 | selenskyj - wolodymyr - berlusconi - pandora - papers | 82 | 395_selenskyj_wolodymyr_berlusconi_pandora |
| 396 | he - zirkusaffe - him - impfen - er | 284 | 396_he_zirkusaffe_him_impfen |
| 397 | wolff - schwab - reset - great - komplex | 44 | 397_wolff_schwab_reset_great |
| 398 | euro - monat - verdienen - impfzentren - monatsgehalt | 50 | 398_euro_monat_verdienen_impfzentren |
| 399 | sonnenblumenöl - speiseöl - aldi - metro - flaschen | 70 | 399_sonnenblumenöl_speiseöl_aldi_metro |
| 400 | odysee - löwenmamas - gettr - herztod - dfb | 43 | 400_odysee_löwenmamas_gettr_herztod |
| 401 | stew - content - episodes - shedding - efforts | 38 | 401_stew_content_episodes_shedding |
| 402 | impfgegner - impfstoff - impfung - minderheit - impfstoffe | 135 | 402_impfgegner_impfstoff_impfung_minderheit |
| 403 | bp - seenotration - lebensmittelbevorratung - müsliriegel - notverpflegung | 33 | 403_bp_seenotration_lebensmittelbevorratung_müsliriegel |
| 404 | dr - haditsch - infektiologie - facharzt - mikrobiologie | 52 | 404_dr_haditsch_infektiologie_facharzt |
| 405 | ukraine - putin - lawrow - russland - russische | 425 | 405_ukraine_putin_lawrow_russland |
| 406 | soundbite - demonstrationen - corona - politik3 - hofstaat | 75 | 406_soundbite_demonstrationen_corona_politik3 |
| 407 | auf1 - wenko - vivien - vogt - janotka | 60 | 407_auf1_wenko_vivien_vogt |
| 408 | 00 - hauptplatz - uhr - marsch - kundgebung | 48 | 408_00_hauptplatz_uhr_marsch |
| 409 | oli - kanalmitglied - spende - negativbewertungen - carolin | 69 | 409_oli_kanalmitglied_spende_negativbewertungen |
| 410 | kennedy - fauci - anthony - jr - kaufman | 50 | 410_kennedy_fauci_anthony_jr |
| 411 | weihnachtsgeschäft - einzelhandel - 2g - innenstädte - hde | 38 | 411_weihnachtsgeschäft_einzelhandel_2g_innenstädte |
| 412 | 02 - bielefeld - 2023 - ilverfahren - danielkonrad | 69 | 412_02_bielefeld_2023_ilverfahren |
| 413 | tschentscher - hamburg - impfstatus - bürgermeister - ungeimpften | 48 | 413_tschentscher_hamburg_impfstatus_bürgermeister |
| 414 | cdl - patentierbar - preiswert - krankheitserregenden - oxidiert | 85 | 414_cdl_patentierbar_preiswert_krankheitserregenden |
| 415 | nrg - heizgerätes - eingebaute - keramikbrenner - strahlungswärme | 45 | 415_nrg_heizgerätes_eingebaute_keramikbrenner |
| 416 | selbstreinigend - alleskönner - absoluter - wasserfilter - extrem | 32 | 416_selbstreinigend_alleskönner_absoluter_wasserfilter |
| 417 | abend - nacht - circles - crop - grüße | 87 | 417_abend_nacht_circles_crop |
| 418 | bgl - logistik - engelhardt - versorgungskrise - regale | 137 | 418_bgl_logistik_engelhardt_versorgungskrise |
| 419 | funkgeräte - limitierung - verschlüsselung - abhörsicher - ausstatten | 32 | 419_funkgeräte_limitierung_verschlüsselung_abhörsicher |
| 420 | petromax - rvm - stack - protocol - wandel | 72 | 420_petromax_rvm_stack_protocol |
| 421 | nehammer - kanzler - övp - bundeskanzler - karl | 56 | 421_nehammer_kanzler_övp_bundeskanzler |
| 422 | macron - pen - zemmour - frankreich - le | 36 | 422_macron_pen_zemmour_frankreich |
| 423 | schwerkraft - pumpen - magnetfeld - sauberes - michaeljaco10 | 52 | 423_schwerkraft_pumpen_magnetfeld_sauberes |
| 424 | versionen - wasserkanister - normalen - trinkwasserreserve - lebensmitteltransporte | 46 | 424_versionen_wasserkanister_normalen_trinkwasserreserve |
| 425 | be43 - monese - pesobeb1 - 5101 - 9194 | 37 | 425_be43_monese_pesobeb1_5101 |
| 426 | zensorin - congresswoman - mace - anhörung - kongress | 37 | 426_zensorin_congresswoman_mace_anhörung |
| 427 | unverpackten - stapelbar - lebensmittelsicherheit - platzsparend - aufbewahrung | 32 | 427_unverpackten_stapelbar_lebensmittelsicherheit_platzsparend |
| 428 | brighteon - spend - goals - toward - puresocialnetwork | 32 | 428_brighteon_spend_goals_toward |
| 429 | lausen - tom - intensivzahlen - cbdc - rossum | 41 | 429_lausen_tom_intensivzahlen_cbdc |
| 430 | reawaken - tour - mel - america - events | 36 | 430_reawaken_tour_mel_america |
| 431 | salzkristall - leuchte - rohkakao - aufstriche - nudel | 41 | 431_salzkristall_leuchte_rohkakao_aufstriche |
| 432 | euro - diäten - simson - gehalt - faeser | 32 | 432_euro_diäten_simson_gehalt |
| 433 | bezahlt - erfolgreich - deanna - ami - bestellung | 69 | 433_bezahlt_erfolgreich_deanna_ami |
| 434 | terheş - herr - cristian - jahresrückblick - sohn | 165 | 434_terheş_herr_cristian_jahresrückblick |
| 435 | ablage - holzstücken - nachgeschoben - holzkohle - briketts | 31 | 435_ablage_holzstücken_nachgeschoben_holzkohle |
| 436 | angesagteste - schickeria - de97100110012620193011 - betteln - ntsbdeb1xxx | 43 | 436_angesagteste_schickeria_de97100110012620193011_betteln |
| 437 | drohne - zagreb - kroatiens - luftraum - plenkovic | 50 | 437_drohne_zagreb_kroatiens_luftraum |
| 438 | lichtgrüße - engmaschiger - lebensmonat - erschaudern - dritt | 44 | 438_lichtgrüße_engmaschiger_lebensmonat_erschaudern |
| 439 | humor - verwunderte - partenkirchen - lustiges - garmisch | 55 | 439_humor_verwunderte_partenkirchen_lustiges |
| 440 | tragegriffe - anheben - grauem - pulverbeschichtetem - versetzen | 44 | 440_tragegriffe_anheben_grauem_pulverbeschichtetem |
| 441 | europaweit - klicken - pflanzen - heilkräuteressenzen - naturrein | 45 | 441_europaweit_klicken_pflanzen_heilkräuteressenzen |
| 442 | newsmax - mail - bastyon - neuigkeiten - newsletter | 49 | 442_newsmax_mail_bastyon_neuigkeiten |
| 443 | naturheilkunde - bänden - buch - medizin - doktoren | 41 | 443_naturheilkunde_bänden_buch_medizin |
| 444 | eu - millionen - deripaska - dollar - steuergelder | 68 | 444_eu_millionen_deripaska_dollar |
| 445 | telefoniert - kolleginnen - ärzte - 59 - email | 78 | 445_telefoniert_kolleginnen_ärzte_59 |
| 446 | demos - suchst - aktualisierter - demo - kalender | 42 | 446_demos_suchst_aktualisierter_demo |
| 447 | saharastaub - schwefeldioxid - staub - sahara - sand | 37 | 447_saharastaub_schwefeldioxid_staub_sahara |
| 448 | dörrleckereien - konservierungsmethode - geschmackserlebnisse - veredeln - geerntetes | 31 | 448_dörrleckereien_konservierungsmethode_geschmackserlebnisse_veredeln |
| 449 | gasspeicher - füllstand - gefüllt - prozent - bleschke | 38 | 449_gasspeicher_füllstand_gefüllt_prozent |
| 450 | bonnell - kommissionspräsidentin - leyen - parlamentarier - ursula | 40 | 450_bonnell_kommissionspräsidentin_leyen_parlamentarier |
| 451 | lipp - alina - mslive - spreaker - audioanalysen | 174 | 451_lipp_alina_mslive_spreaker |
| 452 | hubschrauber - unbemannte - luftfahrzeuge - su - flugzeuge | 40 | 452_hubschrauber_unbemannte_luftfahrzeuge_su |
| 453 | fachanwältin - medizinrecht - bahner - beate - fachbuchautorin | 37 | 453_fachanwältin_medizinrecht_bahner_beate |
| 454 | lenkrollen - größtmögliche - mobilität - stabile - lieferbar | 30 | 454_lenkrollen_größtmögliche_mobilität_stabile |
| 455 | kardinal - überwachungsstaat - müller - bischof - gleichzuschalten | 78 | 455_kardinal_überwachungsstaat_müller_bischof |
| 456 | dr - schäfer - ablenkung - jacob - vollpsychopath | 38 | 456_dr_schäfer_ablenkung_jacob |
| 457 | raphael - bonelli - bauchgefühle - nützen - entstehen | 37 | 457_raphael_bonelli_bauchgefühle_nützen |
| 458 | aktiendepot - etoro - consorsbank - sparpläne - smartbroker | 70 | 458_aktiendepot_etoro_consorsbank_sparpläne |
| 459 | patienten - krankenhaus - rki - positivem - behandelt | 108 | 459_patienten_krankenhaus_rki_positivem |
| 460 | jemen - josilo - masseneinwanderungsversuchen - marko - saudi | 36 | 460_jemen_josilo_masseneinwanderungsversuchen_marko |
| 461 | berlin - deutschland - dildos - taufe - ott | 73 | 461_berlin_deutschland_dildos_taufe |
| 462 | china - chinas - cips - evergrande - chinesische | 102 | 462_china_chinas_cips_evergrande |
| 463 | roedik - nationalisten - kira - ukrainische - kämpfen | 64 | 463_roedik_nationalisten_kira_ukrainische |
| 464 | überschwemmungen - sydney - australien - queensland - australiens | 36 | 464_überschwemmungen_sydney_australien_queensland |
| 465 | norbert - ai - schwarzer - daten - gis | 72 | 465_norbert_ai_schwarzer_daten |
| 466 | amazon - funkgerät - compliance - abhörsicher - 2er | 54 | 466_amazon_funkgerät_compliance_abhörsicher |
| 467 | patente - spielfilmen - zukommt - 11 - clock | 94 | 467_patente_spielfilmen_zukommt_11 |
| 468 | rundbriefabo - bearbeitungsverlaufteilen - fanpost - newsletter - abschicken | 48 | 468_rundbriefabo_bearbeitungsverlaufteilen_fanpost_newsletter |
| 469 | rfid - geldbörsen - damen - esquire - herren | 35 | 469_rfid_geldbörsen_damen_esquire |
| 470 | frankreich - impfpass - endgültig - aussperren - gerold | 63 | 470_frankreich_impfpass_endgültig_aussperren |
| 471 | akku - polymer - schlaufe - wanderns - aufzuhängen | 29 | 471_akku_polymer_schlaufe_wanderns |
| 472 | krankenhaus - lustiges - sitzkreis - herzoperation - gespann | 73 | 472_krankenhaus_lustiges_sitzkreis_herzoperation |
| 473 | feldhose - slim - fit - bdu - teesar | 37 | 473_feldhose_slim_fit_bdu |
| 474 | guntermann - ausführliches - urteilsverkündung - witt - ballweg | 78 | 474_guntermann_ausführliches_urteilsverkündung_witt |
| 475 | terrassenheizung - gusspfanne - gusstopf - traditionelles - einsatzmöglichkeiten | 75 | 475_terrassenheizung_gusspfanne_gusstopf_traditionelles |
| 476 | grundrecht - grüne - schwarz - erimpfen - wischte | 41 | 476_grundrecht_grüne_schwarz_erimpfen |
| 477 | polen - belgrad - warschau - tagebuch - antrittsbesuch | 78 | 477_polen_belgrad_warschau_tagebuch |
| 478 | verbrenner - 2035 - eu - autos - parlament | 117 | 478_verbrenner_2035_eu_autos |
| 479 | energieverbrauch - sanddorn - zutaten - fleisch - brot | 84 | 479_energieverbrauch_sanddorn_zutaten_fleisch |
| 480 | kapitel - zufährt - corrrronapolitik - schwindel - narrativede | 87 | 480_kapitel_zufährt_corrrronapolitik_schwindel |
| 481 | draghi - italien - eu - schulden - scholz | 91 | 481_draghi_italien_eu_schulden |
| 482 | graphene - pfizer - technologie - mrna - fibrosen | 46 | 482_graphene_pfizer_technologie_mrna |
| 483 | live - bearth - étterem - anmeldung - balaton | 106 | 483_live_bearth_étterem_anmeldung |
| 484 | illusionen - ausfahrt - verfassungsrechtlichen - hotspot - gemeinderat | 58 | 484_illusionen_ausfahrt_verfassungsrechtlichen_hotspot |
| 485 | werbematerial - 0028 - bankverbindung - 1100 - zusendungen | 57 | 485_werbematerial_0028_bankverbindung_1100 |
| 486 | nattokinase - natto - hergestellt - heilnatura - zusatzstofffrei | 29 | 486_nattokinase_natto_hergestellt_heilnatura |
| 487 | antikörper - antikörperabfall - infektion - antikörperspiegel - infiziert | 49 | 487_antikörper_antikörperabfall_infektion_antikörperspiegel |
| 488 | profilnamen - emoji - schliess - platziert - eintragen | 29 | 488_profilnamen_emoji_schliess_platziert |
| 489 | neutralität - österreichs - beitritt - neutrales - schweiz | 67 | 489_neutralität_österreichs_beitritt_neutrales |
| 490 | schwab - klaus - peters - stew - edward | 45 | 490_schwab_klaus_peters_stew |
| 491 | kaffee - guayusa - edelstahl - trinkbecher - stanley | 62 | 491_kaffee_guayusa_edelstahl_trinkbecher |
| 492 | pipelines - c4 - sprengstoff - nord - stream | 46 | 492_pipelines_c4_sprengstoff_nord |
| 493 | löwenzahn - biologischem - extrakts - löwenzahnfelder - broendegaarden | 43 | 493_löwenzahn_biologischem_extrakts_löwenzahnfelder |
| 494 | verantwortung - upsi - schuldzuweisungen - willst - mich | 163 | 494_verantwortung_upsi_schuldzuweisungen_willst |
| 495 | siga - mega - fairdenker - wien - fairdenken | 69 | 495_siga_mega_fairdenker_wien |
| 496 | ulrike - guérot - guerot - schweigt - knappen | 29 | 496_ulrike_guérot_guerot_schweigt |
| 497 | 2029 - omikron - variante - corona - verträge | 123 | 497_2029_omikron_variante_corona |
| 498 | taylor - musik - album - sänger - aufzurütteln | 63 | 498_taylor_musik_album_sänger |
| 499 | versammlung - staatsrechtler - versammlungsfreiheit - ortsfest - versammlungen | 78 | 499_versammlung_staatsrechtler_versammlungsfreiheit_ortsfest |
| 500 | heizung - extra - petroleum - flammlöschautomatik - abschaltvorrichtung | 50 | 500_heizung_extra_petroleum_flammlöschautomatik |
| 501 | geschützt - niedrigstand - lagerbestand - eco - begrenzter | 50 | 501_geschützt_niedrigstand_lagerbestand_eco |
| 502 | ermächtigungsgesetz - strafandrohungen - erforderlichkeit - ultima - durchsetzbar | 84 | 502_ermächtigungsgesetz_strafandrohungen_erforderlichkeit_ultima |
| 503 | gierhake - diskriminierung - katrin - verfassungsrichter - rechtsstaat | 142 | 503_gierhake_diskriminierung_katrin_verfassungsrichter |
| 504 | impfschäden - impfnebenwirkungen - daten - fälle - anzahl | 149 | 504_impfschäden_impfnebenwirkungen_daten_fälle |
| 505 | trocknen100 - nüssen - rezepte - dörren - fleisch | 47 | 505_trocknen100_nüssen_rezepte_dörren |
| 506 | 00 - uhr - toskana - löwelstr - leharkino | 34 | 506_00_uhr_toskana_löwelstr |
| 507 | übersterblichkeit - clots - fibrous - destatis - embalmers | 87 | 507_übersterblichkeit_clots_fibrous_destatis |
| 508 | leben - eidenberger - geistesblitze - lebens - wir | 197 | 508_leben_eidenberger_geistesblitze_lebens |
| 509 | vollmilchpulver - basics - ef - bio - grundnahrungsmitteln | 33 | 509_vollmilchpulver_basics_ef_bio |
| 510 | ärzte - patienten - medizin - ärztliche - medizinischen | 142 | 510_ärzte_patienten_medizin_ärztliche |
| 511 | hervorzuheben - geräuschlose - jeglichen - innenräumen - profi | 28 | 511_hervorzuheben_geräuschlose_jeglichen_innenräumen |
| 512 | freedom - food - billa - educating - remedies | 40 | 512_freedom_food_billa_educating |
| 513 | warentest - ffp2 - stiftung - masken - atemwiderstand | 36 | 513_warentest_ffp2_stiftung_masken |
| 514 | wasserfilter - guardian - modernste - purifier - preisgekrönte | 34 | 514_wasserfilter_guardian_modernste_purifier |
| 515 | bundespressekonferenz - empfehle - zensurwelle - zensurfreien - voraus | 71 | 515_bundespressekonferenz_empfehle_zensurwelle_zensurfreien |
| 516 | 00 - rathaus - 18 - marktplatz - darmstadt | 28 | 516_00_rathaus_18_marktplatz |
| 517 | lichterspaziergang - autokorso - bruck - gleisdorf - autocorso | 117 | 517_lichterspaziergang_autokorso_bruck_gleisdorf |
| 518 | rentner - rente - schlegel - drv - bundessozialgerichtspräsident | 53 | 518_rentner_rente_schlegel_drv |
| 519 | notieren - einlagerungsdatum - vorratstonne - eingelagerte - erntejahr | 35 | 519_notieren_einlagerungsdatum_vorratstonne_eingelagerte |
| 520 | jaco - ladezeit - tragbarer - schneller - fünfmal | 50 | 520_jaco_ladezeit_tragbarer_schneller |
| 521 | 4970 - at82 - 1843 - 4500 - gibaatwwxxx | 34 | 521_4970_at82_1843_4500 |
| 522 | survivaldecke - rettungsdecke - alzheimer - wehren - isolierend | 37 | 522_survivaldecke_rettungsdecke_alzheimer_wehren |
| 523 | 20 - 12 - 2021 - mittelfranken - linz | 92 | 523_20_12_2021_mittelfranken |
| 524 | wehrpflicht - bundeswehr - geheimarmeen - afghanistan - högl | 180 | 524_wehrpflicht_bundeswehr_geheimarmeen_afghanistan |
| 525 | frankfurt - aufzug - taunusanlage - mainmetropole - aktuellste | 34 | 525_frankfurt_aufzug_taunusanlage_mainmetropole |
| 526 | leibnitz - karlsplatz - trommel - 17 - trommeln | 46 | 526_leibnitz_karlsplatz_trommel_17 |
| 527 | russen - rassismus - fußballerische - hass - russischen | 205 | 527_russen_rassismus_fußballerische_hass |
| 528 | nontschew - mirco - obduktion - baldwin - riedel | 40 | 528_nontschew_mirco_obduktion_baldwin |
| 529 | maitrunk - odysseylbry - videokanäle - 5594 - 1031 | 55 | 529_maitrunk_odysseylbry_videokanäle_5594 |
| 530 | sellner - postfach - monero - monatlich - vorab | 45 | 530_sellner_postfach_monero_monatlich |
| 531 | funkgeräte - limitierung - verschlüsselung - abhörsicher - ausstatten | 28 | 531_funkgeräte_limitierung_verschlüsselung_abhörsicher |
| 532 | haft - ballweg - janich - remo - gericht | 106 | 532_haft_ballweg_janich_remo |
| 533 | mah - powerbank - smollett - solar - kabellos | 61 | 533_mah_powerbank_smollett_solar |
| 534 | milch - trocknungsprozess - wasserzugabe - abgepackt - dehydrierte | 34 | 534_milch_trocknungsprozess_wasserzugabe_abgepackt |
| 535 | youtbe - odyssee - rabbit - substack - research | 36 | 535_youtbe_odyssee_rabbit_substack |
| 536 | de22830654080004273567 - mediakanälen - spendenkonto - sozial - iban | 28 | 536_de22830654080004273567_mediakanälen_spendenkonto_sozial |
| 537 | 35 - manöver - atomraketen - raketen - defender | 87 | 537_35_manöver_atomraketen_raketen |
| 538 | marburg - äquatorialguinea - virus - ausbruch - fiebers | 28 | 538_marburg_äquatorialguinea_virus_ausbruch |
| 539 | poppel - patrick - michaelsen - fahren - grünen | 46 | 539_poppel_patrick_michaelsen_fahren |
| 540 | wärme - heizung - sorgt - wohlige - stromausfalls | 27 | 540_wärme_heizung_sorgt_wohlige |
| 541 | wien - strasse - vermüllung - rotationseuropäer - olli | 54 | 541_wien_strasse_vermüllung_rotationseuropäer |
| 542 | laptop - donbass - gefunden - verlassenen - militärbase | 29 | 542_laptop_donbass_gefunden_verlassenen |
| 543 | österreich - impfpflicht - arbeitskleidung - epidemische - vorerhebung | 103 | 543_österreich_impfpflicht_arbeitskleidung_epidemische |
| 544 | kogler - werner - demonstranten - vizekanzler - neofaschisten | 39 | 544_kogler_werner_demonstranten_vizekanzler |
| 545 | kanada - trucker - trudeau - kanadischen - eingefroren | 40 | 545_kanada_trucker_trudeau_kanadischen |
| 546 | kubicki - impfpflicht - schiessler - fdp - wolfgang | 131 | 546_kubicki_impfpflicht_schiessler_fdp |
| 547 | polizeidemos - einvernahme - sos - kanalmitteilung - vielfache | 45 | 547_polizeidemos_einvernahme_sos_kanalmitteilung |
| 548 | frühstück - sicherheitsdatenblatt - esta - teilenfolgen - zensurfrei | 121 | 548_frühstück_sicherheitsdatenblatt_esta_teilenfolgen |
| 549 | autoindustrie - wirtschaft - deutsche - kriegs - krieg | 116 | 549_autoindustrie_wirtschaft_deutsche_kriegs |
| 550 | suat - gestorben - trauert - unerwartet - alter | 40 | 550_suat_gestorben_trauert_unerwartet |
| 551 | scheingast - frauenkollektiv - wissenschaftsforscher - rednerinnen - weish | 37 | 551_scheingast_frauenkollektiv_wissenschaftsforscher_rednerinnen |
| 552 | waldhäusl - asyl - wien - landesrat - gottfried | 45 | 552_waldhäusl_asyl_wien_landesrat |
| 553 | attkisson - sharyl - journalistin - rechtsstaat - tóth | 31 | 553_attkisson_sharyl_journalistin_rechtsstaat |
| 554 | außensohle - stahlkappe - dämpfung - fersenbereich - innensohle | 27 | 554_außensohle_stahlkappe_dämpfung_fersenbereich |
| 555 | angst - risch - yale - epidemiologie - harvey | 86 | 555_angst_risch_yale_epidemiologie |
| 556 | kontaktbeschränkungen - geimpfte - genesene - zusammenkünfte - tschentscher | 37 | 556_kontaktbeschränkungen_geimpfte_genesene_zusammenkünfte |
| 557 | copyright - use - fair - otherwise - materials | 27 | 557_copyright_use_fair_otherwise |
| 558 | warburg - kohn - schmid - cum - hamburger | 54 | 558_warburg_kohn_schmid_cum |
| 559 | würdest - möchtest - freiwillige - spende - freuen | 32 | 559_würdest_möchtest_freiwillige_spende |
| 560 | musk - elon - netflix - verliebt - stasi | 41 | 560_musk_elon_netflix_verliebt |
| 561 | blair - donald - tannen - kiefernzapfen - rinde | 54 | 561_blair_donald_tannen_kiefernzapfen |
| 562 | maskenpflicht - maske - fahrgäste - öffis - gaststätten | 38 | 562_maskenpflicht_maske_fahrgäste_öffis |
| 563 | freiheit - seelenkräfte - arendt - hannah - zwängen | 59 | 563_freiheit_seelenkräfte_arendt_hannah |
| 564 | szekeres - ärztekammer - mediziner - ärzte - brief | 58 | 564_szekeres_ärztekammer_mediziner_ärzte |
| 565 | kettle - kelly - sturmkanne - edelstahl - original | 26 | 565_kettle_kelly_sturmkanne_edelstahl |
| 566 | lagern - 10er - notwasserbeutel - katastrophenfälle - wasserbeutel | 34 | 566_lagern_10er_notwasserbeutel_katastrophenfälle |
| 567 | pipelines - marine - ostsee - navy - nord | 66 | 567_pipelines_marine_ostsee_navy |
| 568 | english - 0550 - sparkassede88 - 6010 - twitterusa | 26 | 568_english_0550_sparkassede88_6010 |
| 569 | palmer - sperrung - corona - maßnahmen - beugehaft | 235 | 569_palmer_sperrung_corona_maßnahmen |
| 570 | taiwan - arctic - schlafsack - umlaufender - wärmeleistung | 76 | 570_taiwan_arctic_schlafsack_umlaufender |
| 571 | diesel - österreicher - benzin - cent - grünen | 81 | 571_diesel_österreicher_benzin_cent |
| 572 | satire - bezogenes - hintergrundwissen - ironie - auszutauschen | 55 | 572_satire_bezogenes_hintergrundwissen_ironie |
| 573 | putin - westen - feindbild - marschiert - babel | 168 | 573_putin_westen_feindbild_marschiert |
| 574 | ibrahim - abgeschoben - brokstedt - amri - regionalzug | 54 | 574_ibrahim_abgeschoben_brokstedt_amri |
| 575 | 8ant3kdzjzbzqlndben4uy3oiyveuazuifnqb7ive6s6f4odjhqddcsjvzkqx8t4rtyfxjsrdlhxqduspxood1nnetf3ee3 - ddzffzcqrht1ina7ahbtrnttatqfzald29h2naqagl7k5r1s31yv2t1u2khp73dl8unvfu - cardano - patriots - rechtsextremen | 26 | 575_8ant3kdzjzbzqlndben4uy3oiyveuazuifnqb7ive6s6f4odjhqddcsjvzkqx8t4rtyfxjsrdlhxqduspxood1nnetf3ee3_ddzffzcqrht1ina7ahbtrnttatqfzald29h2naqagl7k5r1s31yv2t1u2khp73dl8unvfu_cardano_patriots |
| 576 | österreich - österreicher - waldhäusl - städtische - barbarei | 109 | 576_österreich_österreicher_waldhäusl_städtische |
| 577 | münchen - straße - theresienwiese - frieden - friedlich | 197 | 577_münchen_straße_theresienwiese_frieden |
| 578 | valdai - club - einzelstream - erholsameren - schnarchen | 48 | 578_valdai_club_einzelstream_erholsameren |
| 579 | salzburg - mundus24 - valentinusvonsalzburg - 4x - monika | 30 | 579_salzburg_mundus24_valentinusvonsalzburg_4x |
| 580 | getreidetonne - unpraktisch - säcken - vorratshaltung - notvorräte | 37 | 580_getreidetonne_unpraktisch_säcken_vorratshaltung |
| 581 | generation - klimaterroristen - klima - diehl - culpa | 64 | 581_generation_klimaterroristen_klima_diehl |
| 582 | pour - classic - kaffee - stanley - autonome | 26 | 582_pour_classic_kaffee_stanley |
| 583 | wiederverschließbaren - hauptmahlzeiten - stapelbaren - standbodenbeutel - eimer | 40 | 583_wiederverschließbaren_hauptmahlzeiten_stapelbaren_standbodenbeutel |
| 584 | todesursachen - rodriguez - his - gerd - gehirn | 71 | 584_todesursachen_rodriguez_his_gerd |
| 585 | merith - streicher - kinder - distanzunterricht - düsseldorf | 43 | 585_merith_streicher_kinder_distanzunterricht |
| 586 | hauptbahnhof - graz - kundgebung - 13 - nähere | 61 | 586_hauptbahnhof_graz_kundgebung_13 |
| 587 | medienallianz - unheilige - gendersprache - schwarze - durchschaubares | 60 | 587_medienallianz_unheilige_gendersprache_schwarze |
| 588 | hierfür - petroleumheizung - folgende - vorteile - alternative | 27 | 588_hierfür_petroleumheizung_folgende_vorteile |
| 589 | ukraine - krim - kadyrow - donbass - selenskyj | 240 | 589_ukraine_krim_kadyrow_donbass |
| 590 | erbil - iran - raketen - abgefeuert - konsulat | 28 | 590_erbil_iran_raketen_abgefeuert |
| 591 | kpa - bear - bushcraft - bc1qej2dflmp7xkay2jtf44c72awe6stxcyq7czy08 - hello | 35 | 591_kpa_bear_bushcraft_bc1qej2dflmp7xkay2jtf44c72awe6stxcyq7czy08 |
| 592 | raketenofen - brennbaren - outdoorküche - raketenöfen - multitalent | 33 | 592_raketenofen_brennbaren_outdoorküche_raketenöfen |
| 593 | band - lauterbachruecktrittsofort - ungekürzten - steinpach - werkausgabe | 90 | 593_band_lauterbachruecktrittsofort_ungekürzten_steinpach |
| 594 | humanus - codex - gesundheit - krankheiten - schubert | 159 | 594_humanus_codex_gesundheit_krankheiten |
| 595 | adidas - ikea - russland - unternehmen - russischen | 116 | 595_adidas_ikea_russland_unternehmen |
| 596 | kaspersky - website - fan - soundcloud - bsi | 62 | 596_kaspersky_website_fan_soundcloud |
| 597 | kongress - interviewgästen - rednern - hochkarätigen - freigeschaltet | 27 | 597_kongress_interviewgästen_rednern_hochkarätigen |
| 598 | smart - handy - whatsapp - meter - smartphones | 50 | 598_smart_handy_whatsapp_meter |
| 599 | atomwaffen - usa - nato - russland - russia | 265 | 599_atomwaffen_usa_nato_russland |
| 600 | cia - globalisten - trump - hats - into | 125 | 600_cia_globalisten_trump_hats |
| 601 | hyundai - arabica - crema - geschriebenes - bescheinigt | 65 | 601_hyundai_arabica_crema_geschriebenes |
| 602 | eintopfofen - grill - praktisch - grillrost - holzgriff | 25 | 602_eintopfofen_grill_praktisch_grillrost |
| 603 | katastrophenforscher - felssturz - goersch - akzep - schäuble | 47 | 603_katastrophenforscher_felssturz_goersch_akzep |
| 604 | kostenlawine - klimaschutz - erfindungen - teuerungslawine - klimawahns | 158 | 604_kostenlawine_klimaschutz_erfindungen_teuerungslawine |
| 605 | überreicht - kostenfrei - zulässig - größerem - erarbeiten | 51 | 605_überreicht_kostenfrei_zulässig_größerem |
| 606 | fuellmich - livestream - reiner - aperio - zensurwelle | 51 | 606_fuellmich_livestream_reiner_aperio |
| 607 | per - banküberweisung - brenndauer - rvsaat2s - at483500000000163378 | 54 | 607_per_banküberweisung_brenndauer_rvsaat2s |
| 608 | südafrika - kenia - omikron - ne - omicron | 31 | 608_südafrika_kenia_omikron_ne |
| 609 | graham - bücherwie - ersatzpetroleumheizungfenix - überlebensperfekte - langzeitlebensmittelwasseraufbereitungstromgeneratorraketenofen | 55 | 609_graham_bücherwie_ersatzpetroleumheizungfenix_überlebensperfekte |
| 610 | optimismus - durchdrücken - schlimm - ausgebombt - gm | 66 | 610_optimismus_durchdrücken_schlimm_ausgebombt |
| 611 | eisenstadt - halberstadt - 2021 - 02 - 12 | 126 | 611_eisenstadt_halberstadt_2021_02 |
| 612 | schröder - annalena - olaf - baerbock - gerhard | 87 | 612_schröder_annalena_olaf_baerbock |
| 613 | plan - kommst - lernst - sammlung - q74you | 25 | 613_plan_kommst_lernst_sammlung |
| 614 | defcon - pope - stufe - steps - death | 25 | 614_defcon_pope_stufe_steps |
| 615 | mcdonald - wodka - filialen - produkte - böser | 57 | 615_mcdonald_wodka_filialen_produkte |
| 616 | schulprojekt - briefe - aufklärungsvideos - volksschulkinder - kindgerechten | 25 | 616_schulprojekt_briefe_aufklärungsvideos_volksschulkinder |
| 617 | lampenöl - autark - petroleumlampen - reinheit - brennstoff | 25 | 617_lampenöl_autark_petroleumlampen_reinheit |
| 618 | leitungswasser - bonus - trinkwasserqualität - maximale - wasserbar | 55 | 618_leitungswasser_bonus_trinkwasserqualität_maximale |
| 619 | schlaf - melatonin - nacht - wohlbefinden - cortisol | 29 | 619_schlaf_melatonin_nacht_wohlbefinden |
| 620 | serbien - belgrad - kosovo - serbia - stampa | 47 | 620_serbien_belgrad_kosovo_serbia |
| 621 | bub - thais - reporter - meridian - polizei | 106 | 621_bub_thais_reporter_meridian |
| 622 | rechtsextremismus - matter - lives - nancy - black | 104 | 622_rechtsextremismus_matter_lives_nancy |
| 623 | flutkatastrophe - hochwasser - reul - ahrtal - warntag | 72 | 623_flutkatastrophe_hochwasser_reul_ahrtal |
| 624 | vordenken - mitdenken - nachdenken - hellsten - köpfe | 66 | 624_vordenken_mitdenken_nachdenken_hellsten |
| 625 | our - nemos - listener - cycle - censored | 32 | 625_our_nemos_listener_cycle |
| 626 | gesellschaft - freiheitsrechte - regime - munter - weiter | 202 | 626_gesellschaft_freiheitsrechte_regime_munter |
| 627 | kaufverpflichtung - mindestlaufzeit - mtl - kündigungsfristen - platin | 41 | 627_kaufverpflichtung_mindestlaufzeit_mtl_kündigungsfristen |
| 628 | alc - lipid - 0315 - bnt162b2 - forschungszwecke | 39 | 628_alc_lipid_0315_bnt162b2 |
| 629 | website - gunnar - kaiser - führich - lukas | 37 | 629_website_gunnar_kaiser_führich |
| 630 | calvez - flamme - gefertigt - bilbo - saruj | 39 | 630_calvez_flamme_gefertigt_bilbo |
| 631 | rpp - innere - präsentiert - körpergewicht - barucker | 54 | 631_rpp_innere_präsentiert_körpergewicht |
| 632 | inform - restricted - help - networks - remaining | 54 | 632_inform_restricted_help_networks |
| 633 | sendung - playlist - freuen - generell - kollateral | 124 | 633_sendung_playlist_freuen_generell |
| 634 | film - doku - wachrütteln - wahrheit - sprengkraft | 101 | 634_film_doku_wachrütteln_wahrheit |
| 635 | powerbank - silikonkappe - netzunabhängige - charging - spritzwassergeschützte | 28 | 635_powerbank_silikonkappe_netzunabhängige_charging |
| 636 | zdf - bellut - nuoviso - mediathek - zuschauer | 34 | 636_zdf_bellut_nuoviso_mediathek |
| 637 | micropur - 4970 - at82 - 1843 - respekt | 46 | 637_micropur_4970_at82_1843 |
| 638 | handy - ortung - privatsphäre - spionage - lokalisierung | 33 | 638_handy_ortung_privatsphäre_spionage |
| 639 | standrechtlich - hinzurichten - schutzpflicht - satirischen - regierungsmitglieder | 142 | 639_standrechtlich_hinzurichten_schutzpflicht_satirischen |
| 640 | kekulé - halle - mittelerde - virologen - dienstenthebung | 37 | 640_kekulé_halle_mittelerde_virologen |
| 641 | order - cacoa - stew20 - off - promocode | 25 | 641_order_cacoa_stew20_off |
| 642 | laterne - helping - brighteon - ladung - usb | 72 | 642_laterne_helping_brighteon_ladung |
| 643 | tönnies - fleischbranche - fleisch - versorgungssicherheit - preise | 69 | 643_tönnies_fleischbranche_fleisch_versorgungssicherheit |
| 644 | ganser - daniele - intendantin - waldhäusl - schlesinger | 164 | 644_ganser_daniele_intendantin_waldhäusl |
| 645 | mückstein - schuldiges - putzt - mitgetragen - bauernopfer | 56 | 645_mückstein_schuldiges_putzt_mitgetragen |
| 646 | lauterbach - karl - bundesgesundheitsminister - sommerwelle - corona | 198 | 646_lauterbach_karl_bundesgesundheitsminister_sommerwelle |
| 647 | cbdc - mydatamychoice - zugänglicher - sample - sucharit | 27 | 647_cbdc_mydatamychoice_zugänglicher_sample |
| 648 | versammlungen - stuttgartgrundgesetzdemos - aktionstag - überalldeutschlandweit - freiepressesauerland | 108 | 648_versammlungen_stuttgartgrundgesetzdemos_aktionstag_überalldeutschlandweit |
| 649 | schweizer - wolldecke - armee - strapazierfähige - qualitätsbewusstsein | 24 | 649_schweizer_wolldecke_armee_strapazierfähige |
| 650 | bergholz - kontrollgruppe - ethylenoxid - teststäbchen - werner | 55 | 650_bergholz_kontrollgruppe_ethylenoxid_teststäbchen |
| 651 | webkante - farbstreifen - originalvorgaben - schafwolle - fertigt | 24 | 651_webkante_farbstreifen_originalvorgaben_schafwolle |
| 652 | sklaven - staat - diktatur - widerlegbar - kriegshetzer | 237 | 652_sklaven_staat_diktatur_widerlegbar |
| 653 | saatgut - fallschirmjäger - kennengelernt - petersilie - urlaubs | 57 | 653_saatgut_fallschirmjäger_kennengelernt_petersilie |
| 654 | pakistan - iran - nuklearen - cia - hwasong | 80 | 654_pakistan_iran_nuklearen_cia |
| 655 | diskret - lebensmittel - lebensmittelvorrat - morgenstund - hirse | 79 | 655_diskret_lebensmittel_lebensmittelvorrat_morgenstund |
| 656 | rezession - raiffeisen - wachstum - tennet - bank | 95 | 656_rezession_raiffeisen_wachstum_tennet |
| 657 | dänemark - 83 - geboostert - geimpft - impfquote | 37 | 657_dänemark_83_geboostert_geimpft |
| 658 | sold - pei - bkk - out - jackson | 68 | 658_sold_pei_bkk_out |
| 659 | fabianer - atheismus - ect - fügsamen - srce | 49 | 659_fabianer_atheismus_ect_fügsamen |
| 660 | widerstand - zuviele - freiheit - besinnt - bedrängnis | 87 | 660_widerstand_zuviele_freiheit_besinnt |
| 661 | plötz - chenoweth - ect - bäcker - sharp | 75 | 661_plötz_chenoweth_ect_bäcker |
| 662 | österreich - krisensicherheitsgesetz - österreichische - regierungsberater - anhaltelager | 94 | 662_österreich_krisensicherheitsgesetz_österreichische_regierungsberater |
| 663 | schrank - monteur - läuft - geil - straßenbahn | 170 | 663_schrank_monteur_läuft_geil |
| 664 | eier - haltbar - sprühgetrocknet - bodenhaltung - hühnereiern | 47 | 664_eier_haltbar_sprühgetrocknet_bodenhaltung |
| 665 | ohio - chemikalien - entgleisung - vinylchlorid - giftigen | 44 | 665_ohio_chemikalien_entgleisung_vinylchlorid |
| 666 | brotbackautomat - brot - brote - ilverfahren - concoy | 24 | 666_brotbackautomat_brot_brote_ilverfahren |
| 667 | kochen - windigstem - nassem - rekordzeit - kanne | 24 | 667_kochen_windigstem_nassem_rekordzeit |
| 668 | telegramelite - rundbrief - gruppenbetreiber - tagesbericht - ehrlich | 58 | 668_telegramelite_rundbrief_gruppenbetreiber_tagesbericht |
| 669 | stiefel - atmungsaktiven - wasserabweisenden - abriebfestes - obermaterial | 24 | 669_stiefel_atmungsaktiven_wasserabweisenden_abriebfestes |
| 670 | song - catherines - miriam - hope - raik | 83 | 670_song_catherines_miriam_hope |
| 671 | netflix - geläut - wienerinnen - selbstbestimmten - passende | 47 | 671_netflix_geläut_wienerinnen_selbstbestimmten |
| 672 | globalisierung - kiss - gcr - endre - menschheit | 79 | 672_globalisierung_kiss_gcr_endre |
| 673 | discounter - preise - supermarkt - teurer - aldi | 66 | 673_discounter_preise_supermarkt_teurer |
| 674 | klarnamenpflicht - volksverräter - patrioten - einführen - polizeigewerkschaft | 124 | 674_klarnamenpflicht_volksverräter_patrioten_einführen |
| 675 | juan - intel - markel - pizzagate - charlie | 155 | 675_juan_intel_markel_pizzagate |
| 676 | einsatzstiefel - squad - inch - stiefel - superlative | 24 | 676_einsatzstiefel_squad_inch_stiefel |
| 677 | söder - löhnitz - zoo - absatz - hannover | 65 | 677_söder_löhnitz_zoo_absatz |
| 678 | ada - 3jvdnoywmb93hsrgk58zstuxg11pw9mksr - 0xf39bdfb41f639b82e3d2bf022828bc6394f533a3 - mgfimc18zvif6dccixmqaap11tg4tf6acj - ltc | 29 | 678_ada_3jvdnoywmb93hsrgk58zstuxg11pw9mksr_0xf39bdfb41f639b82e3d2bf022828bc6394f533a3_mgfimc18zvif6dccixmqaap11tg4tf6acj |
| 679 | arbeitgeber - köchin - unbezahlt - arbeitsgericht - freistellung | 47 | 679_arbeitgeber_köchin_unbezahlt_arbeitsgericht |
| 680 | blackrock - vermögensverwalter - rügemer - vanguard - aktien | 26 | 680_blackrock_vermögensverwalter_rügemer_vanguard |
| 681 | verharmloser - hetzern - stopfen - lügnern - geschichtsausgabe | 88 | 681_verharmloser_hetzern_stopfen_lügnern |
| 682 | frankfurt - dresden - montagsspaziergang - bb - nürnberg | 177 | 682_frankfurt_dresden_montagsspaziergang_bb |
| 683 | polizei - polizeipräsident - lka - polizisten - demo | 141 | 683_polizei_polizeipräsident_lka_polizisten |
| 684 | donezk - donbass - ukrainischer - separatisten - zivilisten | 146 | 684_donezk_donbass_ukrainischer_separatisten |
| 685 | team - teamheimat - squad - cycleang - hrinkow | 40 | 685_team_teamheimat_squad_cycleang |
| 686 | abonnieren - folgt - mir - vernetze - nochmals | 36 | 686_abonnieren_folgt_mir_vernetze |
| 687 | sturmfeuerzeug - cibis - landgrebe - jonas - legendäre | 87 | 687_sturmfeuerzeug_cibis_landgrebe_jonas |
| 688 | apple - app - iphone - angeschmiert - nutzer | 40 | 688_apple_app_iphone_angeschmiert |
| 689 | bernays - deine - lüge - lügen - gesellschaftsbild | 52 | 689_bernays_deine_lüge_lügen |
| 690 | mfg - bundesvorstand - zukunftsweg - pressekonferenz - österreichweiten | 53 | 690_mfg_bundesvorstand_zukunftsweg_pressekonferenz |
| 691 | passierscheine - ausgangssperre - pflegepersonals - easily - ringstraße | 42 | 691_passierscheine_ausgangssperre_pflegepersonals_easily |
| 692 | zuckerberg - fermentierglas - astrozyten - soundcloud - fermentations | 79 | 692_zuckerberg_fermentierglas_astrozyten_soundcloud |
| 693 | hartkekse - wassergehalt - epas - tagesration - trekkingbereich | 23 | 693_hartkekse_wassergehalt_epas_tagesration |
| 694 | verbinde - punkte - sunny - neugier - jugendlicher | 23 | 694_verbinde_punkte_sunny_neugier |
| 695 | pumpernickel - 40er - roggenbrot - langzeithaltbarkeit - vollkornbrotbereits | 42 | 695_pumpernickel_40er_roggenbrot_langzeithaltbarkeit |
| 696 | 6713 - aspkat2lxxx - at50 - 0058 - 0321 | 38 | 696_6713_aspkat2lxxx_at50_0058 |
| 697 | fluchtrucksacklars - gestattete - urlaubs - krisengebieten - hilfsmittel | 23 | 697_fluchtrucksacklars_gestattete_urlaubs_krisengebieten |
| 698 | gifte - schmerzen - bindemittel - lebermittel - fettlöslichen | 30 | 698_gifte_schmerzen_bindemittel_lebermittel |
| 699 | lesen - compact - videos - ganzen - inbee | 26 | 699_lesen_compact_videos_ganzen |
| 700 | polizei - spaziergang - spaziergänger - freiberg - reutlingen | 128 | 700_polizei_spaziergang_spaziergänger_freiberg |
| 701 | sönnichsen - freigesprochen - amtsanmaßung - anklagepunkten - prof | 37 | 701_sönnichsen_freigesprochen_amtsanmaßung_anklagepunkten |
| 702 | schöning - heiko - seilschaften - verbrechen - enthüllungsbuch | 31 | 702_schöning_heiko_seilschaften_verbrechen |
| 703 | impfung - nebenwirkungen - impfstoffe - impfungen - impfstoff | 427 | 703_impfung_nebenwirkungen_impfstoffe_impfungen |
| 704 | fahrer - sanktionen - russland - häfen - lkw | 150 | 704_fahrer_sanktionen_russland_häfen |
| 705 | bowl - super - levine - chiefs - erfolges | 23 | 705_bowl_super_levine_chiefs |
| 706 | hinterlegte - zensiert - unzensiert - newsletter - telegramzensur | 25 | 706_hinterlegte_zensiert_unzensiert_newsletter |
| 707 | berlin - they - vvwg1vvga - ncsvvic - deepstate | 89 | 707_berlin_they_vvwg1vvga_ncsvvic |
| 708 | ron - desantis - theater - gouverneur - florida | 24 | 708_ron_desantis_theater_gouverneur |
| 709 | impfpflicht - impfung - hippokratischer - impfungen - ärzte | 249 | 709_impfpflicht_impfung_hippokratischer_impfungen |
| 710 | verbinde - punkte - presseschau - wandels - interessierten | 86 | 710_verbinde_punkte_presseschau_wandels |
| 711 | committee - ausschuss - untersuchungsausschuss - ausschusses - reiner | 26 | 711_committee_ausschuss_untersuchungsausschuss_ausschusses |
| 712 | q74you - dein - anfänger - anrollen - schnelleinstieg | 48 | 712_q74you_dein_anfänger_anrollen |
| 713 | hildegard - bingen - ephesus - abendgebete - jonathan | 23 | 713_hildegard_bingen_ephesus_abendgebete |
| 714 | gasheizofen - belüfteten - wettergeschützten - innenbereich - außenbereich | 22 | 714_gasheizofen_belüfteten_wettergeschützten_innenbereich |
| 715 | lieferumfang - enthalten - butangasflaschen - pulverlackiertes - stahlblechgehäuse | 22 | 715_lieferumfang_enthalten_butangasflaschen_pulverlackiertes |
| 716 | gauck - lebensglück - frieren - lebensfreude - bundespräsident | 22 | 716_gauck_lebensglück_frieren_lebensfreude |
| 717 | heimatkurier - zensursicheren - förderer - de97430609671028731602 - studentenstehenauf | 64 | 717_heimatkurier_zensursicheren_förderer_de97430609671028731602 |
| 718 | vitamin - sicherheitsgefühl - b2 - selbstverteidigungsschirm - abwehrstock | 29 | 718_vitamin_sicherheitsgefühl_b2_selbstverteidigungsschirm |
| 719 | minderheit - rechtsextremismus - rechtsextrem - unbeteiligtem - rechts | 102 | 719_minderheit_rechtsextremismus_rechtsextrem_unbeteiligtem |
| 720 | fluchtrucksack - eier - bourla - hühnervolleipulver - pfannkuchen | 58 | 720_fluchtrucksack_eier_bourla_hühnervolleipulver |
| 721 | chlorella - chlordioxid - süßwasseralge - weis - notleidend | 57 | 721_chlorella_chlordioxid_süßwasseralge_weis |
| 722 | mgk1q17 - at34 - kdw - 7162 - 2609 | 51 | 722_mgk1q17_at34_kdw_7162 |
| 723 | australien - aktuelles - australier - australia - westaustralien | 43 | 723_australien_aktuelles_australier_australia |
| 724 | mich - pfleger - zitternd - disziplinarvorgesetzten - blickte | 27 | 724_mich_pfleger_zitternd_disziplinarvorgesetzten |
| 725 | raumluft - atemwiderstand - lavera - calcium - grundanliegen | 47 | 725_raumluft_atemwiderstand_lavera_calcium |
| 726 | warne - sono - kricketspieler - videosicherung - zusammenschnitt | 47 | 726_warne_sono_kricketspieler_videosicherung |
| 727 | neuinfektionen - todesfälle - österreichweit - 24 - lehrerinnen | 30 | 727_neuinfektionen_todesfälle_österreichweit_24 |
| 728 | herman - popp - leserin - liebe - zuschrift | 129 | 728_herman_popp_leserin_liebe |
| 729 | armeekompass - kompass - hauptadresse - vergrößerungsglas - wasserwaage | 29 | 729_armeekompass_kompass_hauptadresse_vergrößerungsglas |
| 730 | ryanair - faa - dmso - beschwerden - leary | 47 | 730_ryanair_faa_dmso_beschwerden |
| 731 | einsiedel - peutenhausen - asylheim - wiens - löst | 47 | 731_einsiedel_peutenhausen_asylheim_wiens |
| 732 | rauch - zigarre - musterbrief - loewenmamaspapas - versenden | 53 | 732_rauch_zigarre_musterbrief_loewenmamaspapas |
| 733 | 36amywfs2n6sxxwfmzpgz5vs2gnbrtlajxvdzepnvrif4c56r1k2pfgevvfffbztpn - ultralite - bivy - folie - memo | 43 | 733_36amywfs2n6sxxwfmzpgz5vs2gnbrtlajxvdzepnvrif4c56r1k2pfgevvfffbztpn_ultralite_bivy_folie |
| 734 | crowdbunker - wintergrillen - anziehungspunkt - hingucker - gartenparty | 33 | 734_crowdbunker_wintergrillen_anziehungspunkt_hingucker |
| 735 | partioten - gruß - mein - kanäle - welt | 129 | 735_partioten_gruß_mein_kanäle |
| 736 | sahin - ugur - zugelassene - lebensgefahr - dahlke | 67 | 736_sahin_ugur_zugelassene_lebensgefahr |
| 737 | zdf - ard - reichelt - vernichtungsfeldzug - chefredakteur | 61 | 737_zdf_ard_reichelt_vernichtungsfeldzug |
| 738 | virus - variante - omikron - coronavirus - kretschmann | 159 | 738_virus_variante_omikron_coronavirus |
| 739 | jaspers - übertechnisierung - grundfragen - selbstvernichtung - individualität | 53 | 739_jaspers_übertechnisierung_grundfragen_selbstvernichtung |
| 740 | guardiola - pep - versager - neutralität - manchester | 56 | 740_guardiola_pep_versager_neutralität |
| 741 | matthie - angesagteste - carolinmatthie - schickeria - de97100110012620193011 | 25 | 741_matthie_angesagteste_carolinmatthie_schickeria |
| 742 | co2 - frühstückstisch - grössten - virtuell - livevideo | 40 | 742_co2_frühstückstisch_grössten_virtuell |
| 743 | türkei - lira - erdoğan - iskenderun - erdogan | 55 | 743_türkei_lira_erdoğan_iskenderun |
| 744 | aktivisten - demonstrationen - banner - demonstranten - waldhäusl | 91 | 744_aktivisten_demonstrationen_banner_demonstranten |
| 745 | lauterbach - impfpflicht - karl - impfungen - 1995 | 77 | 745_lauterbach_impfpflicht_karl_impfungen |
| 746 | vpn - ripple - cftc - sec - windows | 66 | 746_vpn_ripple_cftc_sec |
| 747 | schuler - wisnewski - gleichschritt - ralf - jahrbuch | 37 | 747_schuler_wisnewski_gleichschritt_ralf |
| 748 | eintopf - elektroschocker - lady - ausnahmslos - evtl | 102 | 748_eintopf_elektroschocker_lady_ausnahmslos |
| 749 | gettr - republikanischer - kongressabgeordneter - appannie - breakout | 30 | 749_gettr_republikanischer_kongressabgeordneter_appannie |
| 750 | sanktionen - unwälzung - kommmt - lossagen - ruppig | 80 | 750_sanktionen_unwälzung_kommmt_lossagen |
| 751 | övp - sobotka - korruptionsuntersuchungsausschuss - befragungstag - kennenlerntreffen | 33 | 751_övp_sobotka_korruptionsuntersuchungsausschuss_befragungstag |
| 752 | elektrosmog - umgebung - sinus - tester - baubiologischen | 29 | 752_elektrosmog_umgebung_sinus_tester |
| 753 | kinderpornos - teichtmeister - meek - kinderpornografie - hinwegrollen | 34 | 753_kinderpornos_teichtmeister_meek_kinderpornografie |
| 754 | thecrowhouse - brennbaren - crowhouse - grauem - pulverbeschichtetem | 71 | 754_thecrowhouse_brennbaren_crowhouse_grauem |
| 755 | obdachlose - bahnsteigen - 3g - obdachlosen - schickes | 29 | 755_obdachlose_bahnsteigen_3g_obdachlosen |
| 756 | taiwan - südchinesischen - china - philippinen - manila | 27 | 756_taiwan_südchinesischen_china_philippinen |
| 757 | wasserfilter - guardian - modernste - purifier - preisgekrönte | 22 | 757_wasserfilter_guardian_modernste_purifier |
| 758 | aufklärungsvideos - hilfreiche - jeglicher - zensur - frei | 22 | 758_aufklärungsvideos_hilfreiche_jeglicher_zensur |
| 759 | lichte - bevorratung - expeditionsbereich - werk - speziellen | 45 | 759_lichte_bevorratung_expeditionsbereich_werk |
| 760 | piexon - protector - jpx6 - jet - schuss | 29 | 760_piexon_protector_jpx6_jet |
| 761 | schäden - milliarden - gurtschneider - flutkatastrophe - dächer | 88 | 761_schäden_milliarden_gurtschneider_flutkatastrophe |
| 762 | abonnenten - mutigmacher - movipo - facebook - webseite | 72 | 762_abonnenten_mutigmacher_movipo_facebook |
| 763 | theduran - locals - brave - enjoyed - icke | 32 | 763_theduran_locals_brave_enjoyed |
| 764 | bitterstoffe - spirulina - abnehmen - melatonin - entschlacken | 30 | 764_bitterstoffe_spirulina_abnehmen_melatonin |
| 765 | cum - olaf - staatsanwaltschaft - scholz - hamburger | 44 | 765_cum_olaf_staatsanwaltschaft_scholz |
| 766 | iss - raumstation - production - drohnen - grau | 28 | 766_iss_raumstation_production_drohnen |
| 767 | dynamo - kurbel - stromgenerierung - ausflüge - powerstation | 22 | 767_dynamo_kurbel_stromgenerierung_ausflüge |
| 768 | qfs - quantum - system - swift - ust | 34 | 768_qfs_quantum_system_swift |
| 769 | ecoflow - delta - solarpanel - powerstation - heimwerkergeräte | 26 | 769_ecoflow_delta_solarpanel_powerstation |
| 770 | germany - end - greetings - patriots - personal | 21 | 770_germany_end_greetings_patriots |
| 771 | körperzellen - bahner - beate - lebensgefahr - hauptbestandteile | 56 | 771_körperzellen_bahner_beate_lebensgefahr |
| 772 | lidl - supermarktkette - fleisch - produkten - discounter | 22 | 772_lidl_supermarktkette_fleisch_produkten |
| 773 | geschichten - dokumentarfilm - leidvollen - vakzin - beeinträchtigungen | 21 | 773_geschichten_dokumentarfilm_leidvollen_vakzin |
| 774 | kickl - herbert - captain - anne - davos | 157 | 774_kickl_herbert_captain_anne |
| 775 | westen - westregierungen - geschehen - demokratien - giftgasangriffe | 51 | 775_westen_westregierungen_geschehen_demokratien |
| 776 | unserige - interviewgäste - geposteten - distanziere - haftungsausschluss | 21 | 776_unserige_interviewgäste_geposteten_distanziere |
| 777 | 2g - linien - wiener - loipenbenutzung - erholung | 59 | 777_2g_linien_wiener_loipenbenutzung |
| 778 | butter - butterfass - kilner - wildberg - sahne | 52 | 778_butter_butterfass_kilner_wildberg |
| 779 | exodus - kliniken - apothekenmitarbeiterin - ärzte - pfleger | 93 | 779_exodus_kliniken_apothekenmitarbeiterin_ärzte |
| 780 | kaniber - bauern - agrarministerin - michaela - hilf | 26 | 780_kaniber_bauern_agrarministerin_michaela |
| 781 | kastenform - poncho - petromax - liner - deckel | 53 | 781_kastenform_poncho_petromax_liner |
| 782 | webinar - stattfindet - hiermit - kopfschmerzen - 6713 | 36 | 782_webinar_stattfindet_hiermit_kopfschmerzen |
| 783 | gedichte - adventskalender - geschichten - kleinentürchen - grzywa | 27 | 783_gedichte_adventskalender_geschichten_kleinentürchen |
| 784 | solltest - nebenwirkung - streams - interessieren - pollen | 31 | 784_solltest_nebenwirkung_streams_interessieren |
| 785 | lockdown - lockdowns - angrisano - edtstadler - sector | 71 | 785_lockdown_lockdowns_angrisano_edtstadler |
| 786 | schulleiterin - kollateral - schule - lehrer - entblößen | 59 | 786_schulleiterin_kollateral_schule_lehrer |
| 787 | melancholie - eingeweide - vertilgt - wärmt - reinigt | 39 | 787_melancholie_eingeweide_vertilgt_wärmt |
| 788 | gewalt - ruppert - franz - psychologie - dynamiken | 50 | 788_gewalt_ruppert_franz_psychologie |
| 789 | papua - meister - angreifer - größtmögliche - babynahrung | 52 | 789_papua_meister_angreifer_größtmögliche |
| 790 | bewusst - spielzeug - zufriedenheit - illusion - fackel | 57 | 790_bewusst_spielzeug_zufriedenheit_illusion |
| 791 | kalender - schüler - christopher - initiativen - schiesst | 76 | 791_kalender_schüler_christopher_initiativen |
| 792 | id - austria - digitale - verknüpfung - nutzungsmöglichkeiten | 23 | 792_id_austria_digitale_verknüpfung |
| 793 | mitgründer - schriftlich - umfangreiche - analyst - organisierten | 21 | 793_mitgründer_schriftlich_umfangreiche_analyst |
| 794 | kostenlos - stabildurchdenwandel - datei - austausch - audio | 40 | 794_kostenlos_stabildurchdenwandel_datei_austausch |
| 795 | mütze - topfset - alpine - tompos - kanada | 53 | 795_mütze_topfset_alpine_tompos |
| 796 | virus - viren - krankmachendes - mutation - existiert | 101 | 796_virus_viren_krankmachendes_mutation |
| 797 | hanni - plagiats - palmer - johnson - dehm | 144 | 797_hanni_plagiats_palmer_johnson |
| 798 | taxifahrer - vermummungsverbot - durchregulierten - maskenverbot - maskenpflicht | 21 | 798_taxifahrer_vermummungsverbot_durchregulierten_maskenverbot |
| 799 | ppm - gleisdorf - konstantina - rösch - ross | 94 | 799_ppm_gleisdorf_konstantina_rösch |
| 800 | manuka - honig - cistustee - bedrop - karmin | 33 | 800_manuka_honig_cistustee_bedrop |
| 801 | straßen - raus - straße - indianapolis - dülmen | 42 | 801_straßen_raus_straße_indianapolis |
| 802 | magdeburg - per - banküberweisung - at483500000000163378 - rvsaat2s | 37 | 802_magdeburg_per_banküberweisung_at483500000000163378 |
| 803 | getestet - gedruckte - 3d - hebamme - gebratwurstete | 45 | 803_getestet_gedruckte_3d_hebamme |
| 804 | eier - backmischungen - vogelgrippe - hühner - hochwertige | 64 | 804_eier_backmischungen_vogelgrippe_hühner |
| 805 | stellenangebote - rottenburg - arbeiten - packen - worüber | 47 | 805_stellenangebote_rottenburg_arbeiten_packen |
| 806 | taktische - taschenlampe - hra90 - edelstahlring - wolframstahlspitzen | 58 | 806_taktische_taschenlampe_hra90_edelstahlring |
| 807 | bon - gustave - massenpsychologie - begründer - le | 22 | 807_bon_gustave_massenpsychologie_begründer |
| 808 | frisierter - veruntreut - umverteilt - manipulierter - epochaler | 35 | 808_frisierter_veruntreut_umverteilt_manipulierter |
| 809 | schweden - abriegelung - positivrate - lockdowns - tote | 36 | 809_schweden_abriegelung_positivrate_lockdowns |
| 810 | extrakt - eintopfofen - fermentierung - pasteurisierung - milchsäurebakterien | 72 | 810_extrakt_eintopfofen_fermentierung_pasteurisierung |
| 811 | greene - verunglimpfen - management - mace - anerkannte | 41 | 811_greene_verunglimpfen_management_mace |
| 812 | freiwillige - studieren - ukrainischen - soldaten - ukrainische | 117 | 812_freiwillige_studieren_ukrainischen_soldaten |
| 813 | grüße - paraguay - abendgrüße - liebe - uttley | 112 | 813_grüße_paraguay_abendgrüße_liebe |
| 814 | catherine - marc - vimeo - frank - freiheitsgeist | 69 | 814_catherine_marc_vimeo_frank |
| 815 | conco - erledigt - demokratie - respekt - wachsamkeit | 125 | 815_conco_erledigt_demokratie_respekt |
| 816 | schmölen - stillen - staatsanwaltschaft - blutrausch - b107 | 90 | 816_schmölen_stillen_staatsanwaltschaft_blutrausch |
| 817 | strohmeier - natascha - our - briefverkehr - patriot | 92 | 817_strohmeier_natascha_our_briefverkehr |
| 818 | daniele - ganser - historiker - friedensforscher - zweitverwertung | 32 | 818_daniele_ganser_historiker_friedensforscher |
| 819 | telekom - bauarbeiten - durchtrennt - bagger - glasfaser | 33 | 819_telekom_bauarbeiten_durchtrennt_bagger |
| 820 | diplomaten - kneissl - ausweisung - schamalow - gratae | 72 | 820_diplomaten_kneissl_ausweisung_schamalow |
| 821 | myokarditis - moderna - mrna - studie - herzmuskelentzündung | 113 | 821_myokarditis_moderna_mrna_studie |
| 822 | agamben - giorgio - nachwort - essayband - madrid | 33 | 822_agamben_giorgio_nachwort_essayband |
| 823 | fitz - lisa - matrix - swr - kabarettistin | 162 | 823_fitz_lisa_matrix_swr |
| 824 | aktivisten - klimaaktivisten - generation - zerren - mallorca | 69 | 824_aktivisten_klimaaktivisten_generation_zerren |
| 825 | denkt - dran - selbst - drin - quelle | 38 | 825_denkt_dran_selbst_drin |
| 826 | spazierten - veranstalteten - bundeskazleramt - deponieren - andauernde | 28 | 826_spazierten_veranstalteten_bundeskazleramt_deponieren |
| 827 | assault - attraktiven - pack - fidor - spendenmöglichkeit | 31 | 827_assault_attraktiven_pack_fidor |
| 828 | wildgebieten - selbstreinigend - alleskönner - absoluter - entwicklungsländern | 20 | 828_wildgebieten_selbstreinigend_alleskönner_absoluter |
| 829 | verkehrskameras - autobahnen - beirut - wars - kameras | 48 | 829_verkehrskameras_autobahnen_beirut_wars |
| 830 | wetteradler - erde - sonnenstürme - teilchen - aktivierung | 77 | 830_wetteradler_erde_sonnenstürme_teilchen |
| 831 | pasta - kurkuma - dmso - schmerzen - libido | 58 | 831_pasta_kurkuma_dmso_schmerzen |
| 832 | kunst - philine - conrad - cibis - gründerin | 94 | 832_kunst_philine_conrad_cibis |
| 833 | selbstfaktenfriedenfreiheit - denkt - guten - dran - lieben | 23 | 833_selbstfaktenfriedenfreiheit_denkt_guten_dran |
| 834 | jva - menschenkette - mahnwache - einsitzt - hafi | 33 | 834_jva_menschenkette_mahnwache_einsitzt |
| 835 | wildgebieten - pump - selbstreinigend - alleskönner - absoluter | 20 | 835_wildgebieten_pump_selbstreinigend_alleskönner |
| 836 | 11kg - umrüstgasschlauch - propangasflaschen - mehrwöchiger - widerstandsfähigen | 35 | 836_11kg_umrüstgasschlauch_propangasflaschen_mehrwöchiger |
| 837 | busfahrer - bus - greenpass - novaccinepassportsanywhere - novaccinemandates | 43 | 837_busfahrer_bus_greenpass_novaccinepassportsanywhere |
| 838 | linz - strafverfügungen - sucht - namensgebung - pregnant | 29 | 838_linz_strafverfügungen_sucht_namensgebung |
| 839 | prof - dr - med - doctor - pd | 20 | 839_prof_dr_med_doctor |
| 840 | brandenburg - hotels - hotel - rumänien - nonnemacher | 64 | 840_brandenburg_hotels_hotel_rumänien |
| 841 | fermentation - entweichen - luftdichten - gärventil - selbsteingelegten | 20 | 841_fermentation_entweichen_luftdichten_gärventil |
| 842 | 850 - funkgerät - fc - stabo - bezahlte | 35 | 842_850_funkgerät_fc_stabo |
| 843 | artenschutz - offshore - windenergie - windräder - notfallverordnung | 73 | 843_artenschutz_offshore_windenergie_windräder |
| 844 | ifo - unternehmen - prozent - produktion - industrie | 93 | 844_ifo_unternehmen_prozent_produktion |
| 845 | china - bmw - baic - chinas - verlagert | 73 | 845_china_bmw_baic_chinas |
| 846 | nassem - windigstem - brennbarem - wasserkocher - rekordzeit | 34 | 846_nassem_windigstem_brennbarem_wasserkocher |
| 847 | cdl - lula - praxisbuch - hamann - chlordioxid | 54 | 847_cdl_lula_praxisbuch_hamann |
| 848 | mütze - stablampe - led - schlagstock - unverwüstlichem | 24 | 848_mütze_stablampe_led_schlagstock |
| 849 | korsika - colonna - korsischen - yvan - ausschreitungen | 29 | 849_korsika_colonna_korsischen_yvan |
| 850 | bakterien - pilzeauch - mundspülungen - viren - gurgeln | 20 | 850_bakterien_pilzeauch_mundspülungen_viren |
| 851 | schröder - lugner - vermitteln - gerhard - moskau | 46 | 851_schröder_lugner_vermitteln_gerhard |
| 852 | barrington - hilfen - außeruniversitäre - euro - krankenkassen | 74 | 852_barrington_hilfen_außeruniversitäre_euro |
| 853 | magnesium - bundespressekonferenz - magnesiummangel - mineralstoff - rücksprache | 59 | 853_magnesium_bundespressekonferenz_magnesiummangel_mineralstoff |
| 854 | nessmuk - tiere - animal - woodcraft - spirit | 181 | 854_nessmuk_tiere_animal_woodcraft |
| 855 | schule - jesper - träff - larsson - schulen | 58 | 855_schule_jesper_träff_larsson |
| 856 | verbrennen - feuerwehrmann - feuerwehren - qualvoll - kanzlerpark | 48 | 856_verbrennen_feuerwehrmann_feuerwehren_qualvoll |
| 857 | lautstarkes - selbstbestimmtes - demos - bevormundung - unterdrückung | 33 | 857_lautstarkes_selbstbestimmtes_demos_bevormundung |
| 858 | selbstverteidigungsschirm - alltagsgegenstand - unterliegt - gewöhnlichen - dach | 35 | 858_selbstverteidigungsschirm_alltagsgegenstand_unterliegt_gewöhnlichen |
| 859 | ordnungsamt - inbreeding - restaurantleiter - restaurant - coefficient | 37 | 859_ordnungsamt_inbreeding_restaurantleiter_restaurant |
| 860 | tagesreport - podcasts - live - sendungen - verbindediepunkte | 66 | 860_tagesreport_podcasts_live_sendungen |
| 861 | grundrechtsaktivist - di - trieste - con - via | 74 | 861_grundrechtsaktivist_di_trieste_con |
| 862 | your - navy - visit - family - seal | 64 | 862_your_navy_visit_family |
| 863 | cern - headquarters - queen - geneva - buckingham | 61 | 863_cern_headquarters_queen_geneva |
| 864 | riegler - janotka - isabelle - auf1 - wenko | 91 | 864_riegler_janotka_isabelle_auf1 |
| 865 | _frank_und_marc_ - vimeo - _catherine - vom_nichts_zur_perle_carsten - 07_03_22 | 20 | 865__frank_und_marc__vimeo__catherine_vom_nichts_zur_perle_carsten |
| 866 | adams - folter - thoma - sanktionsmöglichkeit - lit | 105 | 866_adams_folter_thoma_sanktionsmöglichkeit |
| 867 | lampenöl - autark - ausgießtülle - trichter - lagerbar | 20 | 867_lampenöl_autark_ausgießtülle_trichter |
| 868 | trinkwasserqualität - leitungswasser - maximale - vitales - osmoseanlage | 20 | 868_trinkwasserqualität_leitungswasser_maximale_vitales |
| 869 | addr1v94ayqu53uklgqnn6c4x4 - ltc - 3jvdnoywmb93hsrgk58zstuxg11pw9mksr - ada - 0xf39bdfb41f639b82e3d2bf022828bc6394f533a3 | 24 | 869_addr1v94ayqu53uklgqnn6c4x4_ltc_3jvdnoywmb93hsrgk58zstuxg11pw9mksr_ada |
| 870 | doku - lampe - lichtbogen - wohnmobil - usb | 27 | 870_doku_lampe_lichtbogen_wohnmobil |
| 871 | vorrat - leer - stinkstoffen - beschreibung - krisenvorsorgewas | 36 | 871_vorrat_leer_stinkstoffen_beschreibung |
| 872 | hauptadresse - bc1q7xfc7ppuw5jwz77sy29txy0efwqnpxw70swgy6 - genodef1m03 - 9466 - 7016 | 19 | 872_hauptadresse_bc1q7xfc7ppuw5jwz77sy29txy0efwqnpxw70swgy6_genodef1m03_9466 |
| 873 | stew - content - episodes - shedding - treatment | 50 | 873_stew_content_episodes_shedding |
| 874 | laune - schlafsprachnachricht - leiberl - mäckle - zeug | 51 | 874_laune_schlafsprachnachricht_leiberl_mäckle |
| 875 | d3 - vitamin - gaskartuschen - inklusive - nervensystem | 49 | 875_d3_vitamin_gaskartuschen_inklusive |
| 876 | mel - melk - precious - kugelschreiber - show | 32 | 876_mel_melk_precious_kugelschreiber |
| 877 | stk - trinkwasserqualität - bestelle - erhalte - guardian | 55 | 877_stk_trinkwasserqualität_bestelle_erhalte |
| 878 | gusseisen - oven - dutch - dekorativer - aufbewahrungs | 68 | 878_gusseisen_oven_dutch_dekorativer |
| 879 | schreyer - commentary - wirtschaftskrise - ausnahmezustand - paul | 19 | 879_schreyer_commentary_wirtschaftskrise_ausnahmezustand |
| 880 | medizin - pharma - punktdenkt - haditschs - reineke | 70 | 880_medizin_pharma_punktdenkt_haditschs |
| 881 | broschüre - ärzte - erleben - umlauf - funktionierende | 43 | 881_broschüre_ärzte_erleben_umlauf |
| 882 | hyundai - wei - stromgenerator - reading - language | 45 | 882_hyundai_wei_stromgenerator_reading |
| 883 | 4801 - at26 - 1828 - kontoinhaber - 6035 | 28 | 883_4801_at26_1828_kontoinhaber |
| 884 | nehammer - politiker - demokratie - party - politischen | 174 | 884_nehammer_politiker_demokratie_party |
| 885 | streik - samira - impfzwang - hentschel - gesundheitsberufe | 66 | 885_streik_samira_impfzwang_hentschel |
| 886 | linz - bauern - folgt - strasse - lichterkette | 21 | 886_linz_bauern_folgt_strasse |
| 887 | wasser - kochen - kannen - kamineffektes - minderwertigere | 19 | 887_wasser_kochen_kannen_kamineffektes |
| 888 | biometrischen - dogmen - wohnräume - id - intensivstation | 34 | 888_biometrischen_dogmen_wohnräume_id |
| 889 | zuwanderung - tierschutz - beihilfen - handwerk - religionsgemeinschaften | 67 | 889_zuwanderung_tierschutz_beihilfen_handwerk |
| 890 | tangsworld - bl - witze - chaplin - geistes | 23 | 890_tangsworld_bl_witze_chaplin |
| 891 | kerzen - dissertation - tenure - track - bachelorarbeit | 54 | 891_kerzen_dissertation_tenure_track |
| 892 | nürnberg - maréchal - marion - pen - prominententransport | 32 | 892_nürnberg_maréchal_marion_pen |
| 893 | habt - risikobewertung - rki - streeck - calhoun | 101 | 893_habt_risikobewertung_rki_streeck |
| 894 | katastrophen - überleben - signalpfeife - handbuch - katastrophenfall | 57 | 894_katastrophen_überleben_signalpfeife_handbuch |
| 895 | bye - kalcker - biophysiker - behandlung - handhabende | 29 | 895_bye_kalcker_biophysiker_behandlung |
| 896 | blackout - blackouts - stromausfall - stromausfälle - strom | 107 | 896_blackout_blackouts_stromausfall_stromausfälle |
| 897 | rt - verwaltungsstrafe - sanktionsmaßnahmen - demokratieabgabe - blechen | 26 | 897_rt_verwaltungsstrafe_sanktionsmaßnahmen_demokratieabgabe |
| 898 | rstp - haltungsnachrichten - meistverbreiteten - hodges - intel | 40 | 898_rstp_haltungsnachrichten_meistverbreiteten_hodges |
| 899 | straße - sachsen - demonstration - demonstranten - demonstrieren | 140 | 899_straße_sachsen_demonstration_demonstranten |
| 900 | warnstreik - curcuma - notbremse - doppelhochwertiges - curcuminoide | 38 | 900_warnstreik_curcuma_notbremse_doppelhochwertiges |
| 901 | nato - weltkrieg - springer - döpfner - ukraine | 164 | 901_nato_weltkrieg_springer_döpfner |
| 902 | berufsbranchen - streikpotenzial - warnstreiktag - gesundheitspersonal - streik | 40 | 902_berufsbranchen_streikpotenzial_warnstreiktag_gesundheitspersonal |
| 903 | zion - devil - metal - density - earth | 63 | 903_zion_devil_metal_density |
| 904 | geometrie - milov - heilige - grüße - liebe | 82 | 904_geometrie_milov_heilige_grüße |
| 905 | ukraine - russia - russen - stalingrad - russland | 340 | 905_ukraine_russia_russen_stalingrad |
| 906 | omicron - dosen - impfstoff - biontech - ceo | 25 | 906_omicron_dosen_impfstoff_biontech |
| 907 | facebookseite - fpoe - facebook - landesgruppe - fpö | 24 | 907_facebookseite_fpoe_facebook_landesgruppe |
| 908 | cic - brandt - marcel - felix - satire | 28 | 908_cic_brandt_marcel_felix |
| 909 | disney - peterson - walt - jordan - judd | 132 | 909_disney_peterson_walt_jordan |
| 910 | obama - 336 - biologische - labors - lugar | 39 | 910_obama_336_biologische_labors |
| 911 | schmerzfrei - tägliche - standpunkte - fraktion - geoengineering | 54 | 911_schmerzfrei_tägliche_standpunkte_fraktion |
| 912 | schwarzer - wagenknecht - sahra - alice - manifest | 24 | 912_schwarzer_wagenknecht_sahra_alice |
| 913 | geldautomaten - bankfilialen - kurkuma - diabetes - nervenerkrankungen | 35 | 913_geldautomaten_bankfilialen_kurkuma_diabetes |
| 914 | england - 750 - todesfälle - mutmaßt - todesfällen | 46 | 914_england_750_todesfälle_mutmaßt |
| 915 | özdemir - bobby - wildfremde - definierten - cem | 46 | 915_özdemir_bobby_wildfremde_definierten |
| 916 | feuerstahl - leina - zündmittel - funktionsfähiges - einfaches | 24 | 916_feuerstahl_leina_zündmittel_funktionsfähiges |
| 917 | ecmo - remdesivir - sterberate - lausen - patienten | 72 | 917_ecmo_remdesivir_sterberate_lausen |
| 918 | friedliches - zeichen - wien - lautes - starkes | 86 | 918_friedliches_zeichen_wien_lautes |
| 919 | repräsentiert - logan - mengele - papierkrieg - fox | 60 | 919_repräsentiert_logan_mengele_papierkrieg |
| 920 | transzendenz - meyer - karlfried - dürckheim - immanente | 27 | 920_transzendenz_meyer_karlfried_dürckheim |
| 921 | massivsten - ärzte - mpfpflicht - ooh - schäferhunden | 20 | 921_massivsten_ärzte_mpfpflicht_ooh |
| 922 | niemals - hollywood - euren - vergwaltigt - jungbrunnens | 33 | 922_niemals_hollywood_euren_vergwaltigt |
| 923 | busfahrer - spülmaschinenfest - geburtshilfe - bpafrei - linz | 42 | 923_busfahrer_spülmaschinenfest_geburtshilfe_bpafrei |
| 924 | gegenuni - sommersemester - semester - einschreiben - startet | 37 | 924_gegenuni_sommersemester_semester_einschreiben |
| 925 | überlastet - einlagern - liter - set - beuteln | 33 | 925_überlastet_einlagern_liter_set |
| 926 | strafverfahren - mord - raub - langer - haftentlassungen | 27 | 926_strafverfahren_mord_raub_langer |
| 927 | google - landgericht - einstweilige - rechtsanwältin - gassmann | 23 | 927_google_landgericht_einstweilige_rechtsanwältin |
| 928 | hifi - mikrowelle - kochherd - spannungs - frequenzschwankungen | 39 | 928_hifi_mikrowelle_kochherd_spannungs |
| 929 | nano - alc - lipide - 0159 - 0315 | 24 | 929_nano_alc_lipide_0159 |
| 930 | senat - lüneburg - 2g - ovg - harbarth | 59 | 930_senat_lüneburg_2g_ovg |
| 931 | sozialismus - sexualisierung - demokratie - kommunismus - kommunisten | 56 | 931_sozialismus_sexualisierung_demokratie_kommunismus |
| 932 | logo - reformation - mohrenbrauerei - kollmorgen - reformationstag | 31 | 932_logo_reformation_mohrenbrauerei_kollmorgen |
| 933 | folgende - safety - faszinierendsten - liberty - immunsystem | 45 | 933_folgende_safety_faszinierendsten_liberty |
| 934 | zeitzeugen - apartheid - salzburg - band - pucher | 70 | 934_zeitzeugen_apartheid_salzburg_band |
| 935 | passantin - share - fußgängerin - schauspielerin - viralität | 74 | 935_passantin_share_fußgängerin_schauspielerin |
| 936 | immunsystem - stärken - gesundheit - abwehrmechanismus - wächter | 57 | 936_immunsystem_stärken_gesundheit_abwehrmechanismus |
| 937 | rwe - florida - notrationnimmt - jahredieses - oberstes | 60 | 937_rwe_florida_notrationnimmt_jahredieses |
| 938 | chelsea - abramowitsch - nürnberg - roman - eingefroren | 37 | 938_chelsea_abramowitsch_nürnberg_roman |
| 939 | valentinstag - schwiegermutter - vorbildern - kissingen - lohnerhöhung | 30 | 939_valentinstag_schwiegermutter_vorbildern_kissingen |
| 940 | christoforou - topic - coupon - trial - locals | 25 | 940_christoforou_topic_coupon_trial |
| 941 | anderwertig - zerstückelt - schriftlicher - kopiert - thefalseflag | 18 | 941_anderwertig_zerstückelt_schriftlicher_kopiert |
| 942 | wagenknecht - sahra - deutsche - göring - außenministerin | 208 | 942_wagenknecht_sahra_deutsche_göring |
| 943 | venus - anja - schäfer - rbb - spirit | 23 | 943_venus_anja_schäfer_rbb |
| 944 | oven - dutch - aktualisierter - kalender - feuertopf | 60 | 944_oven_dutch_aktualisierter_kalender |
| 945 | roxon - river - einsteigermodell - storm - tragbaren | 29 | 945_roxon_river_einsteigermodell_storm |
| 946 | filterkaraffe - esprit - rieger - lotus - schmeckendem | 40 | 946_filterkaraffe_esprit_rieger_lotus |
| 947 | strafverfahren - anhängige - mg - verletzung - freiheitsstrafe | 57 | 947_strafverfahren_anhängige_mg_verletzung |
| 948 | wunder - gehackt - entdecken - potenzial - potential | 45 | 948_wunder_gehackt_entdecken_potenzial |
| 949 | hildmann - nikolai - attila - kommunistendeckel - nerling | 78 | 949_hildmann_nikolai_attila_kommunistendeckel |
| 950 | freiheit - ibounigg - pfr - gesampredigt - verteidigen | 28 | 950_freiheit_ibounigg_pfr_gesampredigt |
| 951 | größere - praktisch - personengruppen - suppen - fasst | 39 | 951_größere_praktisch_personengruppen_suppen |
| 952 | ecoflow - leiseste - batteriegespeister - stromgenerator - tragbare | 18 | 952_ecoflow_leiseste_batteriegespeister_stromgenerator |
| 953 | geeignet - einsäen - sonnenfenstern - gurken - vorziehen | 39 | 953_geeignet_einsäen_sonnenfenstern_gurken |
| 954 | datei - stabildurchdenwandel - audio - download - frisieren | 31 | 954_datei_stabildurchdenwandel_audio_download |
| 955 | soros - busek - open - society - erhard | 38 | 955_soros_busek_open_society |
| 956 | spd - fdp - wähler - mm - kinderstempel | 115 | 956_spd_fdp_wähler_mm |
| 957 | fake - news - kronenzeitung - zuschauer - postillion | 123 | 957_fake_news_kronenzeitung_zuschauer |
| 958 | spars - pandemie - fauci - coronavirus - booster | 103 | 958_spars_pandemie_fauci_coronavirus |
| 959 | neutralität - nehammer - korruption - fitnesstrainerin - steueraufsichtsbehörde | 81 | 959_neutralität_nehammer_korruption_fitnesstrainerin |
| 960 | wisnewski - groissböck - düringer - jesionek - jahrbuch | 154 | 960_wisnewski_groissböck_düringer_jesionek |
| 961 | instrumenten - op - 1at - krankheiten - zirrhose | 58 | 961_instrumenten_op_1at_krankheiten |
| 962 | edelmetalle - auvesta - gold - erstelle - ausgezeichnetem | 26 | 962_edelmetalle_auvesta_gold_erstelle |
| 963 | gasheizung - weitaus - mobile - heater - unterbrochenen | 51 | 963_gasheizung_weitaus_mobile_heater |
| 964 | friedman - stratfor - george - cia - rockefellers | 44 | 964_friedman_stratfor_george_cia |
| 965 | ensslin - raf - weltgeschichte - gudrun - steinmeier | 18 | 965_ensslin_raf_weltgeschichte_gudrun |
| 966 | smart - du - dummheit - willst - blöd | 344 | 966_smart_du_dummheit_willst |
| 967 | liefersituation - gleichwertigen - abweichen - gepackt - enthaltenen | 18 | 967_liefersituation_gleichwertigen_abweichen_gepackt |
| 968 | kocher - outdoor - allesbrenner - kreditsystem - cbdcs | 25 | 968_kocher_outdoor_allesbrenner_kreditsystem |
| 969 | galgant - posch - hildegard - naturheilkundler - heilkraft | 23 | 969_galgant_posch_hildegard_naturheilkundler |
| 970 | river - elektrogeräte - wandsteckdosen - branchenstandard - laden | 23 | 970_river_elektrogeräte_wandsteckdosen_branchenstandard |
| 971 | zeolith - entgiftung - mineralerde - bakteriengifte - schimmelpilzgifte | 32 | 971_zeolith_entgiftung_mineralerde_bakteriengifte |
| 972 | 2050 - info - durchblättern - direkt - ausgabe | 48 | 972_2050_info_durchblättern_direkt |
| 973 | menschheitsgeschichte - kindesmissbrauch - geraubt - rechte - ausflug | 55 | 973_menschheitsgeschichte_kindesmissbrauch_geraubt_rechte |
| 974 | hersh - seymour - recherchen - gruner - enthüllt | 31 | 974_hersh_seymour_recherchen_gruner |
| 975 | gesundheitsberufe - angehörigen - fahrgemeinschaften - genauere - strang | 23 | 975_gesundheitsberufe_angehörigen_fahrgemeinschaften_genauere |
| 976 | fauci - richterin - disziplinaranzeige - gericht - las | 79 | 976_fauci_richterin_disziplinaranzeige_gericht |
| 977 | 520 - flugzeuge - leasen - luftraum - fluggesellschaften | 42 | 977_520_flugzeuge_leasen_luftraum |
| 978 | dlive - vollstahlaxt - sauerland - twitchnach - lancaster | 31 | 978_dlive_vollstahlaxt_sauerland_twitchnach |
| 979 | aldi - kassen - süd - cksack - geklaut | 27 | 979_aldi_kassen_süd_cksack |
| 980 | münchen - schellingstrasse - owens - leopoldstrasse - candace | 41 | 980_münchen_schellingstrasse_owens_leopoldstrasse |
| 981 | arginin - honig - antioxidans - manuka - entzündungen | 73 | 981_arginin_honig_antioxidans_manuka |
| 982 | zdfheute - unangemeldete - kameramänner - monatsabo - grafiker | 18 | 982_zdfheute_unangemeldete_kameramänner_monatsabo |
| 983 | gefälscht - notleidend - profession - notwendiger - tue | 24 | 983_gefälscht_notleidend_profession_notwendiger |
| 984 | widerstand - demütig - friedlichen - härter - artikel | 46 | 984_widerstand_demütig_friedlichen_härter |
| 985 | eu - ahu - brüssel - europa - krise | 129 | 985_eu_ahu_brüssel_europa |
| 986 | anstalt - 0820 - de83 - nadine - 0500 | 86 | 986_anstalt_0820_de83_nadine |
| 987 | impfpflichtgesetz - covid - ig - 19 - pflaster | 71 | 987_impfpflichtgesetz_covid_ig_19 |
| 988 | kireev - denis - unterhändler - mcgregor - sanft | 74 | 988_kireev_denis_unterhändler_mcgregor |
| 989 | winnetou - massengeschmacks - verriss - sechziger - gnadenloser | 90 | 989_winnetou_massengeschmacks_verriss_sechziger |
| 990 | kilez - mona - ehrlich - rubina - more | 53 | 990_kilez_mona_ehrlich_rubina |
| 991 | europaweit - versandkostenfrei - koppverlag - bestellen - liter | 36 | 991_europaweit_versandkostenfrei_koppverlag_bestellen |
| 992 | rpp - 92k - raphael - bonelli - lama | 62 | 992_rpp_92k_raphael_bonelli |
| 993 | medien - meinungen - gesellschaft - öffentlich - presse | 218 | 993_medien_meinungen_gesellschaft_öffentlich |
| 994 | laterne - ladung - geraldgrosz - usb - kurbelbetrieb | 18 | 994_laterne_ladung_geraldgrosz_usb |
| 995 | infrarot - konservierungsmethode - geschmackserlebnisse - sonderpreis - dörrautomat | 18 | 995_infrarot_konservierungsmethode_geschmackserlebnisse_sonderpreis |
| 996 | vdfr - zusammengestelltes - gemüsen - komplettpaket - anzucht | 44 | 996_vdfr_zusammengestelltes_gemüsen_komplettpaket |
| 997 | schöning - heiko - globaleliten - chaos - ausgedient | 40 | 997_schöning_heiko_globaleliten_chaos |
| 998 | q10 - leistungsstarke - kichererbsen - bohnen - erbsen | 28 | 998_q10_leistungsstarke_kichererbsen_bohnen |
| 999 | mockmill - getreidemühlen - getreide - getreidemühle - nährstoffreiche | 18 | 999_mockmill_getreidemühlen_getreide_getreidemühle |
| 1000 | holter - regionalwahlen - zukunftsfähigkeit - bildungsminister - lombardei | 79 | 1000_holter_regionalwahlen_zukunftsfähigkeit_bildungsminister |
| 1001 | lauterbach - drosten - wiesendanger - lauterbachs - eklige | 66 | 1001_lauterbach_drosten_wiesendanger_lauterbachs |
| 1002 | rtv - maps - halbstaatlichen - zensurmaschine - privatsender | 45 | 1002_rtv_maps_halbstaatlichen_zensurmaschine |
| 1003 | gräftner - nelles - psychologie - thurner - barbara | 48 | 1003_gräftner_nelles_psychologie_thurner |
| 1004 | belgien - belgische - impfpflichtgesetzes - ybbs - mfg | 32 | 1004_belgien_belgische_impfpflichtgesetzes_ybbs |
| 1005 | kult - verlag - rubikon - haimbuchner - erscheint | 68 | 1005_kult_verlag_rubikon_haimbuchner |
| 1006 | doorjammer - cbdc - stew - content - sheets | 71 | 1006_doorjammer_cbdc_stew_content |
| 1007 | friedenspreis - unesco - merkel - angela - elfenbeinküste | 32 | 1007_friedenspreis_unesco_merkel_angela |
| 1008 | covid - derzeitigem - vakzinen - kenntnisstand - wissenschaftlern | 100 | 1008_covid_derzeitigem_vakzinen_kenntnisstand |
| 1009 | versammlungsleiter - wr - organisator - kreuzweg - einspieler | 51 | 1009_versammlungsleiter_wr_organisator_kreuzweg |
</details>
## Training hyperparameters
* calculate_probabilities: True
* language: multilingual
* low_memory: False
* min_topic_size: 10
* n_gram_range: (1, 1)
* nr_topics: None
* seed_topic_list: None
* top_n_words: 10
* verbose: True
* zeroshot_min_similarity: 0.7
* zeroshot_topic_list: None
## Framework versions
* Numpy: 1.25.2
* HDBSCAN: 0.8.33
* UMAP: 0.5.6
* Pandas: 2.0.3
* Scikit-Learn: 1.2.2
* Sentence-transformers: 2.7.0
* Transformers: 4.38.2
* Numba: 0.58.1
* Plotly: 5.15.0
* Python: 3.10.12
| {"library_name": "bertopic", "tags": ["bertopic"], "pipeline_tag": "text-classification"} | RolMax/impf_ukrain_postcov_all_sns_topics_umap_lok_hdbscan_lok_ctfidf_seed_17_prob | null | [
"bertopic",
"text-classification",
"region:us"
] | null | 2024-04-19T17:51:34+00:00 | [] | [] | TAGS
#bertopic #text-classification #region-us
| impf\_ukrain\_postcov\_all\_sns\_topics\_umap\_lok\_hdbscan\_lok\_ctfidf\_seed\_17\_prob
========================================================================================
This is a BERTopic model.
BERTopic is a flexible and modular topic modeling framework that allows for the generation of easily interpretable topics from large datasets.
Usage
-----
To use this model, please install BERTopic:
You can use the model as follows:
Topic overview
--------------
* Number of topics: 1010
* Number of training documents: 92912
Click here for an overview of all topics.
Training hyperparameters
------------------------
* calculate\_probabilities: True
* language: multilingual
* low\_memory: False
* min\_topic\_size: 10
* n\_gram\_range: (1, 1)
* nr\_topics: None
* seed\_topic\_list: None
* top\_n\_words: 10
* verbose: True
* zeroshot\_min\_similarity: 0.7
* zeroshot\_topic\_list: None
Framework versions
------------------
* Numpy: 1.25.2
* HDBSCAN: 0.8.33
* UMAP: 0.5.6
* Pandas: 2.0.3
* Scikit-Learn: 1.2.2
* Sentence-transformers: 2.7.0
* Transformers: 4.38.2
* Numba: 0.58.1
* Plotly: 5.15.0
* Python: 3.10.12
| [] | [
"TAGS\n#bertopic #text-classification #region-us \n"
] |
null | adapter-transformers |
# Adapter `BigTMiami/micro_helpfulness_tapt_pretrain_seq_bn_adapter` for roberta-base
An [adapter](https://adapterhub.ml) for the `roberta-base` model that was trained on the [BigTMiami/amazon_MICRO_helpfulness_dataset_condensed](https://huggingface.co/datasets/BigTMiami/amazon_MICRO_helpfulness_dataset_condensed/) dataset and includes a prediction head for masked lm.
This adapter was created for usage with the **[Adapters](https://github.com/Adapter-Hub/adapters)** library.
## Usage
First, install `adapters`:
```
pip install -U adapters
```
Now, the adapter can be loaded and activated like this:
```python
from adapters import AutoAdapterModel
model = AutoAdapterModel.from_pretrained("roberta-base")
adapter_name = model.load_adapter("BigTMiami/micro_helpfulness_tapt_pretrain_seq_bn_adapter", source="hf", set_active=True)
```
## Architecture & Training
<!-- Add some description here -->
## Evaluation results
<!-- Add some description here -->
## Citation
<!-- Add some description here --> | {"tags": ["adapter-transformers", "roberta"], "datasets": ["BigTMiami/amazon_MICRO_helpfulness_dataset_condensed"]} | BigTMiami/micro_helpfulness_tapt_pretrain_seq_bn_adapter | null | [
"adapter-transformers",
"roberta",
"dataset:BigTMiami/amazon_MICRO_helpfulness_dataset_condensed",
"region:us"
] | null | 2024-04-19T17:52:01+00:00 | [] | [] | TAGS
#adapter-transformers #roberta #dataset-BigTMiami/amazon_MICRO_helpfulness_dataset_condensed #region-us
|
# Adapter 'BigTMiami/micro_helpfulness_tapt_pretrain_seq_bn_adapter' for roberta-base
An adapter for the 'roberta-base' model that was trained on the BigTMiami/amazon_MICRO_helpfulness_dataset_condensed dataset and includes a prediction head for masked lm.
This adapter was created for usage with the Adapters library.
## Usage
First, install 'adapters':
Now, the adapter can be loaded and activated like this:
## Architecture & Training
## Evaluation results
| [
"# Adapter 'BigTMiami/micro_helpfulness_tapt_pretrain_seq_bn_adapter' for roberta-base\n\nAn adapter for the 'roberta-base' model that was trained on the BigTMiami/amazon_MICRO_helpfulness_dataset_condensed dataset and includes a prediction head for masked lm.\n\nThis adapter was created for usage with the Adapters library.",
"## Usage\n\nFirst, install 'adapters':\n\n\n\nNow, the adapter can be loaded and activated like this:",
"## Architecture & Training",
"## Evaluation results"
] | [
"TAGS\n#adapter-transformers #roberta #dataset-BigTMiami/amazon_MICRO_helpfulness_dataset_condensed #region-us \n",
"# Adapter 'BigTMiami/micro_helpfulness_tapt_pretrain_seq_bn_adapter' for roberta-base\n\nAn adapter for the 'roberta-base' model that was trained on the BigTMiami/amazon_MICRO_helpfulness_dataset_condensed dataset and includes a prediction head for masked lm.\n\nThis adapter was created for usage with the Adapters library.",
"## Usage\n\nFirst, install 'adapters':\n\n\n\nNow, the adapter can be loaded and activated like this:",
"## Architecture & Training",
"## Evaluation results"
] |
text-to-image | diffusers |
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🧨 diffusers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
| {"library_name": "diffusers"} | Niggendar/AnimeLike2D_v11Pruned | null | [
"diffusers",
"safetensors",
"arxiv:1910.09700",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
] | null | 2024-04-19T17:54:34+00:00 | [
"1910.09700"
] | [] | TAGS
#diffusers #safetensors #arxiv-1910.09700 #endpoints_compatible #diffusers-StableDiffusionPipeline #region-us
|
# Model Card for Model ID
## Model Details
### Model Description
This is the model card of a diffusers model that has been pushed on the Hub. This model card has been automatically generated.
- Developed by:
- Funded by [optional]:
- Shared by [optional]:
- Model type:
- Language(s) (NLP):
- License:
- Finetuned from model [optional]:
### Model Sources [optional]
- Repository:
- Paper [optional]:
- Demo [optional]:
## Uses
### Direct Use
### Downstream Use [optional]
### Out-of-Scope Use
## Bias, Risks, and Limitations
### Recommendations
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
## Training Details
### Training Data
### Training Procedure
#### Preprocessing [optional]
#### Training Hyperparameters
- Training regime:
#### Speeds, Sizes, Times [optional]
## Evaluation
### Testing Data, Factors & Metrics
#### Testing Data
#### Factors
#### Metrics
### Results
#### Summary
## Model Examination [optional]
## Environmental Impact
Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).
- Hardware Type:
- Hours used:
- Cloud Provider:
- Compute Region:
- Carbon Emitted:
## Technical Specifications [optional]
### Model Architecture and Objective
### Compute Infrastructure
#### Hardware
#### Software
[optional]
BibTeX:
APA:
## Glossary [optional]
## More Information [optional]
## Model Card Authors [optional]
## Model Card Contact
| [
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a diffusers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.",
"## How to Get Started with the Model\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] | [
"TAGS\n#diffusers #safetensors #arxiv-1910.09700 #endpoints_compatible #diffusers-StableDiffusionPipeline #region-us \n",
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a diffusers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.",
"## How to Get Started with the Model\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] |
null | espnet |
## ESPnet2 ST model
### `espnet/iwslt24_indic_en_ta_bpe_tc4000_use_wandbtrue`
This model was trained by cromz22 using iwslt24_indic recipe in [espnet](https://github.com/espnet/espnet/).
### Demo: How to use in ESPnet2
Follow the [ESPnet installation instructions](https://espnet.github.io/espnet/installation.html)
if you haven't done that already.
```bash
cd espnet
git checkout 3a161c5ac0f74cc593410a4a32001073ed456580
pip install -e .
cd egs2/iwslt24_indic/st1
./run.sh --skip_data_prep false --skip_train true --download_model espnet/iwslt24_indic_en_ta_bpe_tc4000_use_wandbtrue
```
<!-- Generated by scripts/utils/show_translation_result.sh -->
# RESULTS
## Environments
- date: `Wed Apr 17 02:51:38 JST 2024`
- python version: `3.10.14 (main, Mar 21 2024, 16:24:04) [GCC 11.2.0]`
- espnet version: `espnet 202402`
- pytorch version: `pytorch 2.1.0`
- Git hash: `83c179ab842987cf01642df2db372aaae260df55`
- Commit date: `Wed Apr 17 00:28:29 2024 +0900`
## st_train_st_conformer_raw_en_bn_bpe_tc4000
### BLEU
|dataset|score|verbose_score|
|---|---|---|
|decode_st_conformer_st_model_valid.acc.ave/dev.en-bn|2.1|19.7/3.6/1.0/0.3 (BP = 1.000 ratio = 1.185 hyp_len = 46094 ref_len = 38883)|
## ST config
<details><summary>expand</summary>
```
config: conf/tuning/train_st_conformer.yaml
print_config: false
log_level: INFO
drop_last_iter: false
dry_run: false
iterator_type: sequence
valid_iterator_type: null
output_dir: exp/st_train_st_conformer_raw_en_bn_bpe_tc4000
ngpu: 1
seed: 0
num_workers: 1
num_att_plot: 3
dist_backend: nccl
dist_init_method: env://
dist_world_size: null
dist_rank: null
local_rank: 0
dist_master_addr: null
dist_master_port: null
dist_launcher: null
multiprocessing_distributed: false
unused_parameters: false
sharded_ddp: false
cudnn_enabled: true
cudnn_benchmark: false
cudnn_deterministic: true
collect_stats: false
write_collected_feats: false
max_epoch: 80
patience: null
val_scheduler_criterion:
- valid
- loss
early_stopping_criterion:
- valid
- loss
- min
best_model_criterion:
- - valid
- acc
- max
keep_nbest_models: 10
nbest_averaging_interval: 0
grad_clip: 5.0
grad_clip_type: 2.0
grad_noise: false
accum_grad: 2
no_forward_run: false
resume: true
train_dtype: float32
use_amp: false
log_interval: null
use_matplotlib: true
use_tensorboard: true
create_graph_in_tensorboard: false
use_wandb: false
wandb_project: null
wandb_id: null
wandb_entity: null
wandb_name: null
wandb_model_log_interval: -1
detect_anomaly: false
use_adapter: false
adapter: lora
save_strategy: all
adapter_conf: {}
pretrain_path: null
init_param: []
ignore_init_mismatch: false
freeze_param: []
num_iters_per_epoch: null
batch_size: 20
valid_batch_size: null
batch_bins: 25000000
valid_batch_bins: null
train_shape_file:
- exp/st_stats_raw_en_bn_bpe4000/train/speech_shape
- exp/st_stats_raw_en_bn_bpe4000/train/text_shape.bpe
- exp/st_stats_raw_en_bn_bpe4000/train/src_text_shape.bpe
valid_shape_file:
- exp/st_stats_raw_en_bn_bpe4000/valid/speech_shape
- exp/st_stats_raw_en_bn_bpe4000/valid/text_shape.bpe
- exp/st_stats_raw_en_bn_bpe4000/valid/src_text_shape.bpe
batch_type: numel
valid_batch_type: null
fold_length:
- 80000
- 150
- 150
sort_in_batch: descending
shuffle_within_batch: false
sort_batch: descending
multiple_iterator: false
chunk_length: 500
chunk_shift_ratio: 0.5
num_cache_chunks: 1024
chunk_excluded_key_prefixes: []
chunk_default_fs: null
train_data_path_and_name_and_type:
- - dump/raw/train.en-bn/wav.scp
- speech
- kaldi_ark
- - dump/raw/train.en-bn/text.tc.bn
- text
- text
- - dump/raw/train.en-bn/text.lc.rm.en
- src_text
- text
valid_data_path_and_name_and_type:
- - dump/raw/dev.en-bn/wav.scp
- speech
- kaldi_ark
- - dump/raw/dev.en-bn/text.tc.bn
- text
- text
- - dump/raw/dev.en-bn/text.lc.rm.en
- src_text
- text
allow_variable_data_keys: false
max_cache_size: 0.0
max_cache_fd: 32
allow_multi_rates: false
valid_max_cache_size: null
exclude_weight_decay: false
exclude_weight_decay_conf: {}
optim: adam
optim_conf:
lr: 0.002
weight_decay: 1.0e-06
scheduler: warmuplr
scheduler_conf:
warmup_steps: 25000
token_list:
- <blank>
- <unk>
- ▁
- ্
- ▁়
- য
- র
- ▁প
- ▁এবং
- ের
- ▁য
- কে
- ▁স
- ▁ব
- ▁যে
- ▁একটি
- রা
- ও
- ▁যা
- ▁ে
- ▁করে
- ▁ত
- ▁সম
- ▁করা
- ▁জন
- ▁করতে
- ▁এটি
- ে
- স
- হয
- ▁ক
- ▁দ
- ▁আম
- ▁এই
- তে
- ▁ট
- ড
- িয
- ায
- ই
- ▁আমাদের
- ▁।
- ন
- ▁না
- ত
- ▁ন
- ▁তাদের
- ▁আপনি
- টি
- ▁পারে
- ▁আমি
- ভাবে
- ▁কিন
- ▁তু
- ী
- ▁তা
- ▁গ
- ▁তার
- ▁রয
- ▁র
- ▁তারা
- ার
- ▁েছে
- ▁থেকে
- ▁া
- দের
- ▁বা
- ▁হবে
- ▁সাথে
- ▁পর
- ▁হ
- ▁নির
- িত
- ▁ম
- ▁অন
- ক
- ▁ছিল
- ▁যান
- ▁ার
- ▁তি
- ▁আপনার
- ▁নিয
- ▁মধ
- ষ
- ▁আর
- ▁তৈরি
- ▁অ
- ▁ধ
- ▁বন
- ▁জ
- ▁তাই
- ▁যখন
- ▁এক
- ▁বিশ
- ▁কার
- ▁শ
- গুলি
- ▁কিছু
- ▁দে
- ল
- ঙ
- ▁বাস
- ▁তবে
- ▁ণ
- ▁যদি
- ▁শক
- ুক
- ▁অর
- ঞ
- ▁এমন
- ▁চ
- ▁ভ
- ▁কাজ
- ▁এখন
- ▁থ
- ▁হল
- ▁তর
- ▁অনেক
- ▁বেশি
- ▁হতে
- ▁পরিব
- ি
- ▁আ
- িক
- ▁করি
- ▁েছিল
- ▁এর
- ▁যবহার
- মাত
- ▁কারণ
- উত
- ▁যায
- াড
- ▁তখন
- ▁ড
- ▁মতো
- পূর
- চ
- ▁পারি
- ▁সত
- প
- ▁সেই
- ▁ষ
- ▁আমা
- ▁তন
- ▁নয
- ▁চে
- া
- ▁শুরু
- ▁মনে
- ▁বর
- ব
- ▁কম
- ▁উদ
- ▁ু
- ▁কী
- ▁ছে
- ▁ষা
- ▁আছে
- দ
- ▁রি
- ▁বি
- ▁বের
- ▁যক
- ▁করেন
- ▁বলে
- ▁একজন
- ▁তিনি
- ▁হিসাবে
- জ
- ▁এটা
- ▁যন
- '-'
- ▁নতুন
- ▁সে
- ▁দিকে
- ','
- ▁করেছে
- ▁করেছিল
- ▁রক
- ▁রে
- িষ
- ▁যেতে
- ▁দি
- ▁উপর
- ▁জলব
- ▁শুধু
- ▁থান
- ▁রতি
- ▁কি
- ▁ল
- ▁যাক
- ▁পারেন
- ▁কর
- গ
- ▁কয
- ▁রস
- ▁রথম
- ▁যেখানে
- ▁থাকে
- ▁টা
- ▁কাছে
- ▁কথা
- বচে
- ▁লক
- ▁সং
- শ
- ▁ঘ
- ▁আগে
- ▁োজন
- ▁একই
- ▁বারা
- ▁করছে
- ▁যার
- ▁সালে
- ▁দেখা
- ংখ
- ▁এখানে
- ▁করেছিলেন
- ▁ষণ
- ▁কেন
- যোগ
- ▁আপনা
- ▁ভাল
- ▁মূল
- ট
- ▁তির
- ▁সাহা
- ▁বৈ
- ম
- ান
- ▁খুব
- ▁বছর
- ▁ফ
- ▁সর
- ৃষ
- েন
- ▁দেশ
- ▁রম
- ▁অস
- ▁বড
- ▁কোম
- কি
- ▁ঠিক
- ▁ধরে
- ▁বিজ
- ▁করবে
- ফ
- ▁গুরুত
- ▁থা
- ু
- ▁রুত
- ▁বিদ
- ▁যারা
- ▁দেখতে
- ▁নি
- ▁সাধারণ
- ▁পূর
- ▁করেছি
- াও
- ▁মান
- ▁ভাব
- বিষ
- েষ
- ▁যিই
- রণ
- ▁ছ
- ▁করুন
- ▁ধি
- ▁উচ
- ▁রতিটি
- ▁পদ
- ▁বিক
- হ
- ▁গল
- ▁পরে
- ৃদ
- চিত
- ▁রশ
- ▁উ
- ▁উচিত
- ▁সহ
- মধ
- ▁চিত
- ▁জীবন
- ▁েক
- ▁20
- ▁কখন
- উন
- ▁বেশিরভাগ
- ▁ছোট
- ▁রাস
- ▁দিতে
- ▁যাচ
- ▁ঘুম
- ুদ
- ▁মানুষ
- ▁কোন
- দক
- রূপ
- ▁চাই
- ▁বিষ
- ▁রভাব
- ▁থাকা
- ▁দুর
- ▁এ
- রীক
- ▁উপা
- ▁দুটি
- ▁বিশেষ
- ▁আক
- ▁অক
- ▁বলতে
- ▁আন
- দীর
- ▁ষে
- ▁নেই
- ▁ধন
- ▁ষেত
- ▁বলা
- ▁তী
- ▁রত
- ▁পুনর
- ▁সক
- নিশ
- ▁শেষ
- ▁সিস
- ▁আসলে
- াম
- এ
- ণ
- ▁ছা
- ▁ঘন
- ▁মার
- মাধ
- ▁ভাগ
- ▁সঠিক
- ▁কেউ
- ▁ইতি
- ▁কিভাবে
- ▁শিল
- ▁পার
- ▁উদাহরণ
- িং
- ▁কারণে
- ▁বল
- ▁সুত
- িজ
- ▁রতিক
- ▁ফির
- ▁মানুষের
- ▁লোক
- ▁ভব
- ▁সমাধান
- ▁আসে
- ▁চলে
- িতে
- ▁কেবল
- ▁রী
- ▁ঞানী
- ▁নিজে
- ভিন
- ▁সেখানে
- ▁অবস
- বর
- ▁যত
- ▁খুঁজ
- ▁কঠিন
- ▁হাজার
- ▁জানেন
- ▁জানি
- খ
- ▁সব
- ▁বে
- ▁যমে
- বিশ
- ▁রহ
- ▁ধান
- ▁টার
- ▁জিনিস
- ▁থনীতি
- ▁ধরনের
- ▁সহজ
- ▁তব
- ▁রাজ
- ▁তিত
- ▁গেছে
- পক
- াহলে
- িকল
- ▁আলো
- ▁রহণ
- ▁করবেন
- ▁10
- ▁অবশ
- ং
- ▁পনা
- ▁পে
- কারী
- ▁ধে
- িদ
- তার
- ▁যেমন
- ▁চা
- ▁তাপ
- ▁যাপ
- ▁দিন
- ▁এত
- ▁ছি
- ▁নে
- ▁সাম
- ▁গত
- তা
- ▁অংশ
- ▁রান
- ছন
- ▁বিত
- ▁কোষ
- ▁সরকার
- ▁োগ
- তি
- বার
- ▁বিশাল
- ▁পেতে
- ▁উপ
- ▁চিন
- '2'
- ▁রাখা
- ুর
- ▁জিন
- ▁বৈশ
- ▁পানি
- ▁গমন
- ▁াই
- ▁ভবত
- ▁সন
- ▁অগ
- চুর
- ▁পরিস
- ▁েছি
- ▁তিশালী
- ▁শতাংশ
- ▁ভিত
- ▁বছরের
- াল
- ▁যাকসিন
- ▁যবাদ
- ▁রকৃত
- ▁মত
- ▁থাপন
- ▁রণ
- ▁আজ
- ▁লোকেরা
- ▁লা
- ▁রের
- ▁রিক
- ▁ষতি
- শব
- ▁থাকতে
- ▁বিল
- ▁দেশে
- ▁উভ
- ▁মস
- ▁জু
- ▁রমণ
- ▁ষমতা
- ▁রদান
- ▁যবস
- নের
- রুদ
- ▁করেছেন
- ▁সার
- টিকে
- ▁গাছ
- ▁জীবা
- গত
- ▁মিলি
- ▁ডলার
- াং
- ▁পণ
- ▁রূপা
- ▁ষম
- ▁গা
- ▁কল
- নেও
- ▁যাট
- জন
- ▁যথ
- ▁পুরো
- ▁অনুমান
- ▁রাখতে
- ▁যাস
- এর
- ▁েছিলেন
- ▁লেখ
- ▁পরিষ
- ▁জল
- ▁রঙ
- ▁মাত
- ▁বিনি
- ▁জা
- ▁তারপর
- ▁তুলনা
- ▁পৃথিবী
- ▁খরচ
- ▁বিবেচনা
- ▁চল
- ▁রিত
- ▁টেলি
- ▁েছিলাম
- ▁টেম
- ▁সি
- বদ
- ▁অনুস
- ▁আলাদা
- ▁তৃত
- গুলিতে
- ▁ভর
- ▁রাপ
- ানো
- ▁সুযোগ
- ▁মুহ
- ▁মাথা
- ▁সংক
- ▁ভাবনা
- ▁যাগ
- সাথে
- ▁মী
- ▁যাত
- ▁নীচে
- ▁তোলে
- ▁বাইরে
- তির
- ▁তিনটি
- ▁বুঝ
- ▁চিকি
- ▁কোনও
- ▁হার
- ▁19
- ▁মক
- ▁থিতি
- ▁গবেষণা
- ▁সরবরাহ
- ▁তারপরে
- ▁একক
- ▁মের
- ▁সৌর
- ▁চাল
- ▁মহিলা
- ▁চর
- ▁কোনো
- ▁নীতি
- ▁বস
- ▁CO
- ▁সবুজ
- ▁অবশেষে
- ▁যুৎ
- ▁বেগ
- ▁রাখে
- ▁দুই
- ▁ডে
- ▁চান
- ▁রোগ
- ▁বলি
- ▁রমাণ
- ▁নিজ
- ▁গি
- ▁ভুল
- ংক
- ▁টের
- ▁শহরে
- ▁অত
- ▁যাবে
- মে
- ▁শহর
- ▁কের
- ▁মহা
- েবে
- ▁কোথা
- ▁সাইড
- ▁নের
- ির
- ▁ঠ
- গুলো
- ফর
- ▁তথ
- ▁পানির
- ▁চালি
- ▁ভালো
- ▁ধরণ
- ▁ধারণ
- ▁মাণ
- ▁াল
- ▁বিপ
- ▁ভাষা
- ▁দরকার
- ▁রিট
- ▁কো
- ▁রদা
- ▁মৃত
- ▁ছেন
- ▁যুতিক
- ▁যকর
- ▁লাস
- ▁তমান
- ▁মিশর
- ▁রাম
- ▁দল
- ▁নিজের
- ▁ডার
- থায
- ▁সারা
- েও
- োড
- ▁সা
- ▁রাতে
- ▁বিস
- টা
- ▁ছিলেন
- ▁ফলাফল
- ▁ডাই
- ▁ঞাসা
- ▁মিথ
- ▁নীল
- ▁হিস
- ▁চুল
- ঘ
- ▁যালে
- ▁ষেপ
- ▁বব
- ▁যু
- ▁বাধ
- ▁দেশগুলি
- ▁মানে
- ▁ান
- ৃশ
- ▁াতে
- ▁আশ
- ▁খারাপ
- ▁লাল
- ূর
- ▁ধার
- ▁তুত
- ষম
- ▁পরিচিত
- ▁বক
- ▁ডা
- ▁নাম
- ▁জার
- ▁ছিলাম
- টোক
- ▁তম
- োক
- ▁যবসা
- ▁বার
- ▁পথ
- লম
- ▁ধতি
- ▁অনুভব
- ▁কৌশল
- ▁রসারিত
- ▁আঘাত
- ▁জিনিসগুলি
- িন
- ▁গতি
- ▁অতির
- ▁পাচ
- াকে
- ▁করছেন
- াঙ
- ▁মাই
- ▁পা
- ▁জানা
- ▁নব
- ▁আশা
- ▁ধারণা
- ▁অভ
- ▁সুবিধা
- ▁সবাই
- না
- েতু
- ংস
- মেন
- ▁পাঁচ
- ▁জীব
- ▁নিষ
- ▁হুমকি
- ▁বালানি
- ▁নিরাপদ
- ূন
- ▁বোধ
- ▁যগুলি
- ▁গে
- রক
- ▁চাপ
- ▁রোটিন
- নী
- ▁যোগ
- ▁রাণী
- ▁ভারতে
- ▁টির
- ▁রকৃতি
- ▁মহামারী
- সের
- ▁মে
- ▁15
- ▁থনৈতিক
- ▁ঝুঁকি
- ▁রকাশ
- ▁তিন
- ▁সুস
- ▁রাজা
- ▁ডিস
- ▁এড
- ▁মারা
- ▁টন
- শীল
- ▁নামে
- ▁দু
- জু
- ▁উপাদান
- ▁অপ
- থ
- ুষ
- ▁পরিণত
- ▁তত
- ▁বেঁচে
- ▁বালানী
- ▁অনুম
- ▁বেশ
- ▁যানো
- ▁ধমান
- লে
- ▁এগ
- ▁থন
- ▁আবার
- ▁অসম
- ময
- ▁উপস
- াস
- ▁যমান
- ▁শিক
- রামর
- ▁হাই
- কাল
- ▁থী
- ▁ঞান
- ▁পাদন
- ▁রিকা
- ▁দূরে
- ▁হলে
- ো
- ▁ভিন
- ▁নিক
- ▁রাব
- ৎ
- ▁কোপ
- ▁শী
- লব
- ▁দা
- হত
- ▁দেখেছি
- ▁বোঝা
- ▁টিক
- ▁মরুভূমি
- ▁বৃহ
- তম
- ▁তিগত
- ▁অফ
- ▁ষতা
- ▁ফলে
- ▁সীমা
- িহ
- ▁সেন
- ▁যুদ
- ▁মন
- ▁দশকে
- ▁সেগুলি
- ▁গড
- ▁যো
- ▁রদ
- ▁11
- ▁4
- ▁পরিবার
- ▁ডিজাইন
- ▁রজাতি
- ▁হাসি
- ▁নামক
- ▁খাদ
- ▁তো
- ▁তিক
- েক
- সূর
- ▁ভারত
- ▁ইন
- ▁যাপক
- ▁আসা
- ▁কিনা
- ▁ঠান
- ▁আত
- ▁অব
- ▁কোষে
- ▁পুরুষ
- ▁ডি
- ▁রার
- ▁সংগ
- ▁যাকে
- ▁থাকবে
- ▁বিন
- ▁ইংতাই
- ▁মোমবাতি
- ▁রাকৃতিক
- ▁লোকেদের
- ীকরণ
- ▁রতিশ
- ▁খ
- ▁চারপাশে
- ▁এশ
- ▁খনি
- ▁উপরে
- ▁রুতি
- ▁পরিমাণে
- ▁আসন
- ▁বিভ
- পড
- ▁দূর
- ▁1
- ▁বেড
- ▁রিস
- ▁কোষগুলি
- ▁আগ
- ▁একে
- ▁রাক
- ▁শহরগুলি
- ▁সেট
- েই
- তটা
- ▁শরীর
- ▁পরিমাণ
- ▁খিঁচুনি
- ▁ফেলে
- গায
- ▁জো
- দিনের
- নির
- ▁ইমিউন
- ▁যাল
- ▁আস
- ▁অপর
- ▁বাচ
- ▁কত
- ৈর
- ▁তরে
- ▁রেক
- ▁করছি
- ▁অনু
- ▁করলে
- ▁আল
- ▁আধ
- ▁ভাবন
- ▁এমআরএনএ
- ▁টেকসই
- ▁রোজান
- ▁পরিচালনা
- ▁যুত
- ▁বছরে
- ▁যালি
- ▁ডেটা
- ▁একাধিক
- ▁দর
- ▁পিছনে
- ▁মাটি
- ▁যতা
- ▁বদা
- ডিগ
- ▁এগুলি
- ▁ঞতা
- ▁আচরণ
- লা
- ফোর
- ▁একবার
- ▁সহা
- ▁শন
- টিস
- ▁রতিরোধ
- ▁আরেক
- ▁6
- াক
- কার
- লি
- বা
- ▁সেরা
- ▁বংস
- ▁লি
- ▁বপ
- ▁অপসারণ
- s
- ▁মোকাবেলা
- ▁রবেশ
- ▁ইলেক
- ▁চিকিৎসা
- ▁ভেঙ
- ▁বিপরীত
- ▁রধান
- মূলক
- ▁হত
- ▁পাশা
- ▁পুর
- ▁দাস
- ▁জনস
- ▁মডেল
- নি
- োয
- ▁থক
- ▁আপ
- াচ
- রিদ
- ছিলাম
- ▁মা
- বে
- ▁এলাকা
- ▁দশক
- ▁ঘটনা
- ভূত
- ▁কন
- ▁শতা
- ▁তরা
- ▁ভার
- রবর
- িনি
- ▁খা
- ▁নিজেদের
- রূপে
- ▁মোট
- ▁কাঠামো
- ▁যোগাযোগ
- ▁বীকার
- ▁ভূমিকা
- বু
- ▁ঠী
- ▁ডিক
- ▁জোর
- '20'
- ▁আমেরিকান
- ▁সাল
- ▁েন
- ▁নৈতিক
- ঠা
- শত
- াপী
- ▁সপ
- াতে
- বেক
- ▁ফল
- পত
- ▁জীবনে
- ▁গো
- ▁যাই
- ▁অদ
- ▁নত
- ▁ডাক
- ▁সেস
- কৃত
- ▁টিভ
- ▁জটিল
- হীন
- ▁কঠোর
- ▁চাহিদা
- ▁মুখোমুখি
- ▁রকৌশলী
- ▁রাচীন
- ▁উৎপাদন
- ▁রগতি
- ▁লেষণ
- ▁জাতিগত
- ▁শোষণ
- ▁খাবার
- ▁ধীর
- ▁পারবেন
- ুনিক
- ▁ভিতরে
- ▁ভাইরাস
- ▁দেখি
- তিতে
- ▁দেবে
- কল
- ▁লেট
- ▁েছেন
- ৃত
- ▁াম
- ▁ইস
- ▁নিচে
- ▁চম
- ▁গদ
- ▁ধু
- ▁তুলত
- ▁টেবিলে
- পী
- মা
- ▁আকার
- ▁অণু
- ▁অনুপ
- ▁টে
- ▁নিত
- ▁মূ
- ▁ওষুধ
- ▁কাছাকাছি
- ▁ডিএনএ
- ▁সুপারনোভা
- ▁শুনতে
- ▁গপাল
- ▁অভাব
- ▁যপ
- ▁মাঝ
- নাক
- ▁আটকে
- ▁বিচ
- ▁গভীর
- ▁যজনক
- মি
- ▁200
- টিক
- ▁যেভাবে
- ▁পাশে
- ▁রতিদ
- ▁সেলস
- ▁ফেল
- ▁নতি
- ▁বাধা
- ▁বজ
- ▁মানব
- ছে
- ▁থতা
- াই
- ▁শতাংশের
- ▁শান
- ▁হন
- ▁নিম
- ▁শিকার
- পাশ
- বৃত
- ▁সমব
- ▁5
- েছে
- ▁তেলাপোকা
- ▁ঝ
- ▁বসে
- ▁গুণ
- ▁ণবাদ
- ▁লিপ
- ▁যব
- ▁ঘটে
- তী
- ▁আইন
- ▁জানে
- ▁আশেপাশে
- ▁নাগরিক
- ▁গঠন
- ▁তরীণ
- ▁যাটার
- ▁অভিজ
- ▁সংযোগ
- ▁চরম
- ▁করব
- জেন
- ▁পানিগুলি
- ▁ডিম
- লার
- াফল
- ▁জলে
- বহা
- ▁উজ
- ▁সামনে
- ▁30
- ▁থিত
- াগত
- ▁ঝাঁক
- ▁পগুলি
- উড
- ▁যাম
- ▁কুল
- ▁থাগুলি
- ▁মানসিক
- ▁বাঁচ
- ▁পরব
- ▁ডেন
- ▁থে
- ▁রেস
- ▁ছবি
- ▁কাছ
- ▁সমান
- বন
- ▁পান
- ▁সিম
- ▁2
- ▁সহক
- ▁ঞা
- ▁লিপিড
- ▁অধ
- ▁কোভিড
- ▁অবদান
- ▁যোগফল
- ▁সোনা
- ▁েকটি
- ▁কালো
- ▁কমাতে
- ▁গবেষকরা
- ▁অনন
- ▁দেখে
- মান
- ▁মুখী
- ▁রজনন
- ▁সূচক
- ▁জাত
- টাই
- ▁পরিবেশ
- ▁আদ
- ▁ইউরোপ
- ▁আচ
- ▁পেট
- ▁লাগ
- ▁ছিন
- ▁যাশ
- ▁জি
- ▁চিম
- োষ
- ▁মু
- ▁যটি
- ▁গেলে
- ▁ষিণ
- ▁ভিদ
- ▁বেত
- ▁রেম
- ▁বিপর
- ▁তিদের
- েশন
- লেন
- ভুক
- ▁রোগী
- ▁পাত
- ▁চার
- বসম
- ▁রাণ
- ▁ঘো
- ▁আরো
- ▁এম
- মন
- ুরক
- ▁খেলা
- দিকে
- োজ
- ▁রো
- ▁বাভাবিক
- '0000'
- ▁যবহ
- ▁নিন
- ▁ইতিহাস
- ▁শত
- ▁পরিচ
- ▁রাথমিক
- ▁ভাইপার
- ▁জনগণ
- ▁থাকলে
- ▁শোনা
- ▁ঘুর
- ▁বিয
- ▁লোব
- ▁বাণ
- ▁পরিবহন
- ▁যবান
- ▁সাদা
- ▁ওজন
- ▁কিছুটা
- ▁চাকা
- ▁অপে
- ▁ঠে
- ▁মিলিত
- ▁সেক
- ▁বাকি
- ▁শরীরে
- ▁যেকের
- েট
- মাস
- ইচ
- ▁পালি
- ▁রচ
- দার
- ▁আকাশে
- ▁মুখে
- ারি
- ালন
- ▁রবাহ
- ▁কিলোমিটার
- ▁আকারে
- ▁শে
- ারিদ
- ▁সুন
- ভাগ
- পু
- ▁লোকের
- '50'
- ▁বাবা
- ▁মিত
- সাম
- ছেন
- বি
- ▁যৌন
- ▁রবণ
- মণ
- ▁বাক
- ▁ধেক
- ▁বহু
- ▁অদলবদল
- ▁তেজনা
- ▁বসবাস
- ▁পরিমাপ
- ▁রাজনৈতিক
- ▁আবাস
- ▁সংকেত
- ▁পরিবেশগত
- ▁বিকাশ
- ▁বিগুণ
- ▁যানেল
- ▁যাঁ
- ▁ইংরেজি
- ▁অভি
- ▁মিনিটের
- াধিক
- ▁যিকার
- ▁জানত
- ▁রজন
- ▁অসু
- রকম
- ▁থিক
- ▁রেখে
- ▁জেনে
- ▁3
- ণনা
- ▁নারী
- ▁সংয
- াত
- ▁টেমের
- ▁রেড
- লান
- ▁ানো
- ▁সাহ
- ▁চাচ
- ▁কাজটি
- ▁রিড
- ▁থল
- ▁পন
- ▁রন
- াজার
- ▁রিন
- ▁কোপে
- ▁গন
- ▁সৌ
- পথে
- ▁লুপ
- ▁সূ
- ▁ভাই
- ▁ষিত
- ▁কেল
- ▁ওঠে
- ▁70
- ▁জাহাজ
- ৷
- ▁থেরাপি
- ▁চাকরি
- ▁মৌলিক
- ▁চাঁদ
- ▁রতিফল
- ▁নেতৃ
- ▁শাসন
- ▁খবর
- ▁নাটক
- ▁ঘুমানো
- ▁করছিলাম
- ▁ইতিহাসে
- ▁চালানো
- ▁ষরিক
- ▁ষত
- ▁বীপ
- ▁আমেরিকানদের
- হিত
- ▁করছিল
- লাম
- ▁আউট
- ▁যাটারি
- ▁কথোপকথন
- ▁তোলা
- ▁থানে
- সংশ
- ▁দেন
- ▁ঘট
- ▁বাতাস
- ▁নিউ
- ▁নেট
- ামাজ
- জনক
- ▁দাম
- শক
- ূ
- ▁যাকসিনগুলি
- ▁নম
- হার
- ▁রাসা
- ▁শিশু
- োল
- ালের
- ▁কোর
- ▁16
- ▁রাত
- ▁চালা
- ▁100
- ▁সমাজ
- কেন
- ▁তাহ
- ভূমি
- ▁কমে
- ▁মাস
- াময
- ▁12
- শিত
- ▁পেশী
- মাক
- a
- ▁ফোকাস
- ▁শিখেছি
- ▁তহবিল
- ▁রতিবেশী
- ▁রভু
- ▁উপকূল
- ▁দুধ
- ▁পরিচাল
- ▁আলোক
- ▁বলুন
- ▁সিজেন
- ▁দাবি
- ▁দূষণ
- ▁শতকে
- ▁যতক
- ▁পাঠানো
- ▁রাণিত
- ▁রোগীর
- ▁কাউ
- ▁রাখবে
- ▁বোত
- ▁জানতে
- টিভ
- ▁ঞানিক
- ষণা
- ▁গেম
- ▁পুনরা
- োচ
- ▁মিল
- ▁হৃদয
- ▁করেছিলাম
- ▁মুখ
- ▁পোর
- বিদ
- ▁রহস
- ▁পাবল
- ৃ
- ▁কেরি
- ▁রণে
- ▁আজকে
- ▁অপরি
- ংশ
- ▁মহিলার
- ▁রগুলি
- ালোক
- েমন
- ▁জিত
- ▁ষক
- ▁হাতি
- ▁একা
- ষিক
- ▁হাতে
- ▁াস
- তুর
- ▁কা
- ▁কোণ
- ▁দশকের
- ফিল
- ▁গুরুতর
- ▁বলছি
- ▁পাই
- ▁আমেরিকা
- ▁8
- ▁বাজার
- াদী
- ▁চোখে
- ▁রমে
- '3'
- িপিং
- ▁দাঁ
- ▁তরুণ
- '9'
- ▁নদী
- ▁যাপন
- ▁চলেছে
- ▁পাঠ
- ▁অবকাঠামো
- ▁কবুতর
- ▁টুকরো
- ▁অনুবাদ
- ▁একটু
- ▁জিডিপি
- ▁নমুনা
- ▁দখল
- ▁যমজ
- ▁24
- ▁রোজেন
- ▁যাপচার
- '26'
- ▁শারীরিক
- ▁তুলনামূলক
- ▁কিত
- হাউস
- ▁সফল
- ▁দরজা
- ▁নিরাপ
- ▁যালসি
- ▁গরম
- ▁দেখেন
- ▁রমিক
- ▁টাও
- ▁গম
- ▁তিগুলি
- ▁চারটি
- ▁দেবতা
- ▁েল
- ▁তবতা
- ▁শহ
- ▁বিতা
- ▁দৈ
- ▁মাক
- ▁সংকট
- ▁অনুসার
- গুণ
- ▁ইহুদি
- ▁ণবাদী
- ▁রুটি
- ▁মালি
- ▁বালি
- ▁পুনরু
- াশ
- ▁জনক
- ▁পৌঁছা
- ▁উপাদানগুলি
- ▁80
- ▁ইক
- ▁ষি
- ▁কোনটি
- ▁কুশ
- দুর
- রি
- োগ
- ▁করেনি
- ুল
- নিয
- ▁নিব
- ▁জের
- িকভাবে
- ▁শুক
- ▁বান
- ▁রাণীর
- ▁মগুলি
- ুরে
- ▁তাত
- ▁শিখ
- ▁কক
- ুনি
- ▁রেই
- ▁কাট
- ▁তিকর
- পোস
- ▁খালি
- ▁যাগুলি
- ▁বনাইজ
- ▁ভূ
- ▁যেগুলি
- ▁লাভ
- ▁গেল
- ▁জাতিক
- ▁পরিশ
- ▁উপরের
- কর
- ▁মেশিন
- েল
- ▁ছেলে
- ▁সু
- ছিল
- ▁জাম
- ▁শানবো
- সাশ
- ূত
- ▁থিতিশীল
- ▁বো
- ▁তুলা
- ▁বকে
- ▁অবি
- '00'
- ▁থানগুলি
- ালকা
- ▁লু
- ▁ইউ
- ▁অধিকার
- ▁রাইলোবাইট
- ▁টেরিওটাইপ
- ানদের
- ▁মিটার
- ▁জাতি
- ▁ভালবাসা
- ▁সীমিত
- ▁অনুশীলন
- ▁মোনালিসা
- ▁জীবনযাপন
- ▁আলোচনা
- ▁লোরো
- ▁আগামী
- ▁তেজিত
- ▁রনালী
- ▁2030
- ▁উঠেছে
- ▁আগুন
- ▁নেতিবাচক
- ▁যাকটাস
- ৎকার
- ▁যালাক
- ▁থনীতিবিদ
- ▁বিরল
- ▁লেজ
- ▁পৌঁছানো
- ▁বীকৃত
- ▁পাহা
- ▁চেইন
- ▁যামেরা
- ▁রু
- ▁রেখা
- মস
- ▁দেখানো
- ▁চীন
- ▁জনসাধারণ
- ▁তাব
- ▁রাজি
- েড
- ▁ছদ
- ▁ডিং
- ▁তালিকা
- নো
- ▁পরিবেশে
- ▁ফি
- ▁রাউন
- ▁রোল
- দৌ
- ▁চোখ
- ▁সাক
- ▁রোম
- ▁ফাঁদ
- শন
- ▁ডস
- '5'
- ▁সাই
- াজ
- ▁শেখা
- ▁জিনগুলি
- িণ
- ▁টিকেল
- কোণ
- ▁গান
- ▁সেতু
- ▁সরকারকে
- ▁মাসের
- ▁রাপক
- ▁খাল
- ▁কান
- মিশ
- শি
- দস
- কোনো
- ▁শিবির
- ▁হো
- ▁ছাত
- সরি
- ▁রহে
- ▁পথে
- ▁বলবে
- ▁এন
- যুদ
- ▁ভু
- মনী
- সে
- ▁অংশে
- ▁খেল
- জার
- ▁াট
- ▁দী
- '7'
- ইহ
- ▁সিরি
- ▁লাইন
- ▁মাসে
- ▁াদে
- ▁চক
- ▁ছেদ
- ▁খু
- ▁ডল
- ▁রীক
- ▁বলছে
- ▁এসে
- ▁উপকরণ
- কিং
- ▁ভাইরা
- ▁ঐতিহ
- '&'
- ;
- o
- p
- Ş
-
- ▁চুনাপাথর
- ▁মেলাটোনিন
- ▁রাজধানী
- ▁ষুধা
- ▁সবকিছু
- ▁অপারেটর
- ▁মবেশ
- ▁হরমোন
- ▁গাছপালা
- ▁উপভাষা
- ▁আইডি
- ▁যসেবা
- ▁দেশাবলী
- ▁যানবাহন
- ারের
- ▁হারানো
- ▁তরাধিকার
- ▁পাবেন
- ▁বিকৃত
- ▁ষেপণ
- ▁জেট
- ▁অংশগ
- ▁জমি
- ▁অভিযোজন
- ▁বাণী
- ▁বিবর
- ▁যাধি
- ▁হোম
- ▁যাটি
- ▁চলগুলি
- ▁বলেছিল
- ▁টাকা
- ▁খোলা
- ▁মীদের
- লো
- ▁রচার
- ▁রেণী
- ▁সামর
- ▁রহী
- ▁মানবতা
- ▁রতিদিন
- ▁দেহ
- ▁নিজেদেরকে
- ▁যাপার
- ▁াগুলি
- ▁ভারতকে
- ধিক
- বিরক
- ▁গর
- ▁টান
- ▁দান
- ▁90
- ▁কাজে
- ▁িগুলি
- ▁বাদ
- ▁সাত
- ▁25
- ▁হবেন
- ▁লেখক
- বাদী
- াউন
- াদের
- ▁পেরেছি
- ▁পক
- ▁পাইক
- '1'
- ▁1000
- িস
- ▁অল
- ▁রাশ
- ▁উপন
- ▁শিকারী
- সাধারণ
- ভার
- ▁ষিণে
- ▁বুদ
- ▁পশ
- ▁ভুলে
- ▁সাপ
- ▁রিজ
- াইড
- ▁ভূত
- ▁50
- ▁লাগে
- ▁বারে
- দিন
- ▁দৃ
- তন
- ▁পাদ
- '8'
- ▁আট
- ▁আকাশ
- ▁নিচ
- ▁বিগ
- '6'
- চে
- ▁খুল
- ▁ভূগ
- ▁দাতা
- ▁বলেছি
- ▁সুলতান
- পর
- কুচি
- ▁তনশীল
- ▁এতটা
- ▁মানি
- ▁অথ
- ীন
- তুল
- ▁লাই
- ▁পাখি
- ▁রোধ
- ▁নিদ
- ধ
- ▁বাধীন
- ▁এসেছি
- ঢ
- ▁ঘর
- তিবাচক
- ▁ডিভাইস
- ▁মোটামুটি
- T
- ▁পৃথক
- ▁যালঘু
- ▁সহযোগিতা
- ▁পুনঃ
- ▁আবেগ
- ▁যকলাপ
- ▁ঝিল
- ▁নিঃসরণ
- ▁আংশিক
- ▁চিৎকার
- ▁লিওন
- ▁মনোযোগ
- ▁আবেদন
- ▁বিবেচ
- ▁আছি
- ▁ফসল
- ▁পোরেশনগুলি
- ▁পেরু
- ▁বিতরণ
- ▁লাইট
- ▁কিলো
- ▁এসেছে
- ▁বহি
- ▁ইউনি
- ▁বামী
- ▁কভার
- ুব
- ▁ফলাফলগুলি
- ▁কৃষি
- ▁তাক
- কারক
- ▁যাকশন
- ▁পাঠা
- ▁নেতা
- ▁খে
- ▁সকলের
- ▁তনে
- নাইট
- পুর
- ডাউন
- ▁যৌনতা
- ▁ডান
- রম
- ▁শীত
- ▁চলা
- ▁কানের
- ▁মিং
- ▁মুদ
- ▁শাসক
- ▁গোপন
- ▁তোমা
- ▁কৃতি
- ▁টেক
- ▁রেট
- ▁সকালে
- ▁যাবেন
- ▁জান
- ▁পরিসরে
- ▁ফুল
- ▁হাত
- ▁এভাবে
- াইভ
- পূরণ
- ▁হলেন
- ▁শিশুর
- শীর
- ▁ডানা
- পতি
- ▁মাতা
- ▁শুনে
- ▁কাটা
- ▁ধারণাটি
- ▁যিক
- ছা
- ▁গাছে
- ▁রমা
- ▁সমাধানে
- সম
- ীদের
- ▁মাল
- িড
- আই
- ▁দার
- মার
- ুন
- ▁ভে
- ▁চতা
- ▁400
- ▁বাহ
- ▁ইতাল
- লস
- ▁রাইভ
- ▁এরিক
- ▁থি
- ▁হারি
- মাঝ
- েইনফ
- ▁পেরেছিল
- '4'
- ▁টিকে
- েব
- থাক
- ▁শর
- ▁ডাকা
- ▁রেখেছিল
- ▁তুলে
- ▁অসুবিধা
- ▁নগুলি
- ▁আই
- ▁টু
- ▁শেষে
- ▁জনপ
- খানে
- ▁বহুল
- ▁দেখেছিল
- ▁ঋণ
- ▁রুপ
- ▁দূষ
- ▁মহাকা
- ০
- ▁আরএনএ
- ▁নাৎসি
- ▁সুপারহিরো
- ▁রতিযোগিতা
- ▁পাইলট
- ▁বজনীন
- ▁ঐতিহাসিক
- ▁চিঠি
- ▁মরিসন
- ▁বাজেট
- ▁সুপারিশ
- ▁পুলিশ
- ▁দেখুন
- ▁অভিযান
- ▁রাহক
- ▁যবধান
- ▁রতিযোগী
- ▁ডানদিকে
- ▁পাগল
- ▁খনন
- ▁ঘটছে
- ▁বেষণ
- ▁সংবেদন
- ▁লাগানো
- ▁দেখেছিলেন
- ▁ঢে
- ▁পারবে
- ▁কাশন
- ▁বিকেলে
- ▁শুনেছেন
- ▁এসেছিল
- ▁যাসিড
- ▁নেমে
- ▁3-
- ▁রশংস
- ▁বাহু
- ▁করত
- ▁রঙে
- গদ
- ▁40
- ▁গক
- ▁শোষ
- ▁জোট
- ▁গণনা
- ▁হাঁট
- ▁বেস
- ▁রিলি
- ▁টিং
- ▁দাদা
- ▁সরকারগুলি
- ▁অংশগুলি
- ▁দোষ
- ▁খলা
- ▁করতেন
- ▁জাপান
- ▁আধি
- ▁বাহিনী
- ঘাত
- ▁সরকারী
- ▁থিতিতে
- ▁পারেনি
- ▁যাংক
- াসের
- াইজ
- ▁মেট
- ঃ
- ▁কুলে
- ▁বাচন
- ▁কোড
- ▁মাঝা
- ▁রেমে
- েইন
- রমাণব
- ▁যাগগুলি
- বহন
- বাজারে
- ▁টেবিল
- ▁চারা
- ▁রাখ
- ▁ঠানিক
- ▁বংসা
- ▁ধকারে
- ▁ঝুল
- ▁18
- ▁থাকেন
- ▁কৃষ
- ▁তক
- ▁চি
- বিরোধ
- হন
- ▁নাক
- ▁যাতন
- মিন
- দা
- চার
- ▁গগুলি
- ▁আছেন
- '21'
- ▁ডলে
- ▁তিটি
- পা
- ▁রোত
- ▁রকেট
- ▁তাহে
- ▁পাস
- ুলার
- ▁বাঁচা
- ▁আসেন
- ▁যথায
- ▁কৃতিক
- ▁ধকার
- ▁পরিষেবা
- বিক
- ▁তগুলি
- ▁যাণ
- ▁দেবী
- ▁ষর
- ▁সীমান
- ▁কৃত
- সি
- ছি
- ▁পিতামাতার
- ভান
- ▁মেঘ
- ▁আরি
- ▁ফাঁক
- েজ
- ধি
- ▁পরি
- ▁মেটা
- টো
- পাস
- নে
- তিগ
- োপ
- মুখী
- ▁যদ
- জীবন
- '0'
- ▁অতি
- ফো
- ▁মিনিট
- ▁রিপ
- ▁মিক
- ▁পিছ
- ▁কু
- ▁যানবাহনে
- ▁শো
- ▁নাগা
- বেন
- ▁পোরেশন
- ▁োগকারী
- শালী
- ▁জাতিসংঘ
- ৃৎপ
- ▁ডিজিটাল
- ▁নিখুঁত
- ▁পিতামহ
- ▁মহাসাগর
- ▁রিলোবাইট
- ▁রীতদাস
- ▁রোপচার
- ▁সেনাবাহিনী
- ▁অপারেশন
- ▁জরুরী
- ▁শেলোব
- P
- ▁অনুভূমিক
- ▁যাটেলাইট
- ▁বাছাই
- ▁যকারিতা
- ▁আঠালো
- ▁কেটলি
- ▁সৈন
- ▁ইনজেকশন
- ▁একাকী
- ▁রতিকৃতি
- ▁মালিকানা
- ▁রাকচার
- ▁তুলেছে
- ▁কবিতা
- ▁আসুন
- কোহ
- ▁বুশ
- মলত
- ▁আসছে
- ▁আশাবাদী
- ▁আসবে
- ▁উৎসাহ
- ▁বোতাম
- পোকা
- ▁অধীন
- ▁একমত
- ▁ভেবেছিল
- ▁সুখ
- ▁গঠিত
- ▁নজর
- ▁বিবরণ
- ▁201
- ▁দেখবে
- ▁লিনিক
- ছ
- ৌক
- ▁সুইচ
- ▁পরিণতি
- ▁মোটা
- ▁উৎপ
- ▁লেটগুলি
- ▁পাথর
- ▁ফেলবে
- ▁ফরাস
- ▁হৃদ
- িগার
- ▁মাপ
- ▁ভাঙ
- ফুস
- ▁ধুদের
- ▁বিরতি
- ▁কতা
- ▁লাইস
- ▁দিল
- ▁থাকি
- ▁নীতিগুলি
- ▁আবদ
- ▁রেলি
- ▁পেস
- ▁মাইক
- ▁টেমগুলি
- ▁গু
- ▁টেশন
- ▁গেট
- নশীল
- ▁লুক
- ▁পরাজ
- ▁পাঁচটি
- ▁বতন
- ▁পাবে
- ▁রোমান
- ▁বাপক
- ▁লাইনের
- ▁00
- পোর
- ▁উঠ
- ▁17
- ▁যাতি
- ▁জাল
- বাইন
- ▁ঘটা
- ▁কমান
- ▁ইমে
- ▁দগুলি
- ▁উপয
- ▁হতাশা
- ▁যুতে
- ▁নিষি
- ভ
- ▁সেল
- োর
- ▁ফিল
- ▁সিটি
- ▁ভবন
- ▁দীপ
- ▁194
- ▁ষাগুলি
- ▁যাগে
- ▁আবর
- ▁সকল
- মিড
- ▁টিকেলগুলি
- ▁কারণগুলি
- ▁দিক
- ▁হেল
- ▁বিট
- ▁রেরণা
- ▁কুশি
- ▁ঘোরা
- ▁ধরা
- ▁সী
- ফি
- ▁রবৃ
- ▁রোটিনে
- ▁কাজগুলি
- ▁মহাকাশে
- ামগ
- ▁অনেকের
- ▁পলি
- ফিক
- ▁রহণকারী
- ▁বিধ
- রেস
- ▁লোককে
- ▁মহাদেশ
- ুত
- ▁ণতা
- ▁রপ
- ▁মিশ
- ▁উৎস
- ▁গার
- কেটে
- গো
- মেডি
- ▁লেখা
- ▁ভিদে
- ▁ষী
- ▁দিনে
- বশেষ
- ▁দেশটি
- ▁মেস
- ▁বিচারে
- ৌ
- ▁ডিত
- ▁আব
- ▁মহাকাশ
- ▁রেডি
- ▁36
- ▁22
- ▁10000
- োস
- ▁বুজ
- কেল
- ▁বাতাসে
- েটর
- ীর
- ▁বেল
- ▁বীপে
- দন
- লাইন
- ূপ
- ▁সাহারা
- ▁রমণে
- ▁হাস
- ▁েজ
- ▁বলতা
- ▁জুন
- কোস
- ▁হই
- ▁মজা
- ▁নটি
- ▁করণ
- বিজ
- ▁যেকোন
- াবে
- াদা
- ▁রুট
- তিক
- ▁থের
- ▁সহজে
- ▁তাকা
- ▁গবেষক
- ▁ধর
- ▁রাইড
- ▁এলোমেলো
- ▁উঁচু
- ▁উদযাপন
- ▁কীটনাশক
- ▁রতিনিধি
- ▁শিরোনাম
- ▁শৈশব
- ▁াকলাপ
- ▁এনকোড
- ▁মজুরি
- ▁লাটিপাস
- ফেডারে
- ▁থেরানোস
- ▁মনোনিবেশ
- ▁ইটনভিল
- ▁লুরোস
- ▁জরিপ
- ▁টিউমার
- ▁মনিকা
- ▁সমাবেশ
- ▁বাসনালী
- ▁ইংল
- ▁খাঁচা
- ▁জীবিকা
- ▁গৃহ
- ▁ভিডিও
- ▁বেলারুশ
- ▁অধিকাংশ
- ▁রিগস
- ▁বাভাস
- ▁তুলবে
- ▁ঝাঁপ
- ▁পোশাক
- ▁খলিল
- ▁রতিবাদ
- ▁সাফো
- ▁আসল
- ▁সহিংসতা
- ▁সমাধি
- ▁কমিশন
- ▁বিদেশ
- ▁রেখেছিলেন
- ▁রাইম
- ▁কিং
- ▁ধতিগত
- ▁টাইন
- ▁অংশীদারদের
- ▁অনুভূতি
- থার
- ▁লাইম
- ▁বীজন
- ▁বিমান
- ▁রপাতি
- ▁কোলে
- ▁যানেলগুলি
- ুঁ
- ▁লিপিডগুলি
- িশোধ
- ▁সেগুলো
- ▁শিশুদের
- ▁লাফ
- ▁বেকার
- ▁সরানো
- ভাইরাস
- ▁অনুরোধ
- ▁শনিক
- ▁মালিক
- ▁রিকান
- ▁জমা
- ▁ফাঁ
- ▁অনুমোদন
- ▁করিনি
- ▁আবি
- ▁গণত
- ▁সভ
- ▁কমানো
- ▁দীতে
- ▁তৃতা
- ▁রতিরোধী
- ▁যুট
- ▁টাল
- িচ
- ▁রোপণ
- ▁বিবাহ
- বহুল
- ▁রবণতা
- ▁করলেন
- রিকানদের
- ▁দাঁত
- ▁আপস
- ▁যাকিং
- ▁যবাহ
- ▁জে
- ▁বোঝাতে
- ▁রামী
- ▁রুব
- ▁2000
- ▁মাছ
- ▁ারিং
- ▁জীবাণু
- ▁লিনার
- ▁ফুট
- ▁ধাপ
- চাপ
- আইনি
- ভাল
- গম
- ▁লেগে
- লুপ
- ▁কাপ
- ▁রহটি
- দূর
- শাস
- ▁টিমে
- ▁ঘটনাটি
- ▁কিলোমিটারের
- ▁সংগঠ
- থিত
- ▁অণুগুলি
- ▁বীর
- ▁সবে
- ▁করুক
- ▁লিফটে
- ▁সমাজে
- ▁ারশ
- ▁খরা
- ▁তেল
- ▁আঁক
- ▁চেল
- পশ
- ▁পরিপ
- ▁শহরটি
- ▁লোড
- েকটি
- ▁বিচার
- ▁লাগা
- বল
- ▁লাইটে
- ▁ভূমি
- ▁ফার
- সব
- ▁গণিত
- ▁চির
- ▁পৌঁছে
- লিপি
- ▁ালা
- াপ
- ▁আনা
- ▁পানিটি
- চক
- ▁186
- াংস
- িডা
- ▁একদিন
- ▁7
- ▁হারা
- কারীদের
- ুখ
- িএস
- ▁দশ
- োঁ
- ▁অফিসে
- ▁মুছ
- িশ
- ▁সিং
- ▁াশা
- ▁75
- ▁কাঠ
- ▁সাপে
- '11'
- ▁যদেব
- েম
- ▁ারগুলি
- কোষ
- ▁ফোন
- সেট
- ▁কোট
- ▁দলগুলি
- িটি
- ▁শুরুতে
- বিয
- তীতে
- িঁ
- ▁রেন
- ▁দামে
- করা
- ▁সেটা
- ▁ধিত
- দল
- লিক
- ▁টল
- ▁রোস
- ▁জেনি
- '60'
- ▁তাকান
- ▁যাং
- ▁পাতা
- ▁ো
- ▁পরিক
- ▁একবারে
- ▁কথোপকথনে
- ▁সমতা
- ▁ইউরোপে
- ▁দির
- হো
- শু
- ▁রিডে
- িদর
- ▁জৈব
- ▁জাদু
- ▁যালো
- ▁উৎ
- '15'
- টল
- ▁সুই
- ▁চত
- াবধানে
- ▁অনুমোদ
- ▁এখান
- ▁কিশোর
- ালোচনা
- িছু
- ▁কাগজে
- ▁তরল
- ▁বিরত
- ▁সমীক
- ▁রামক
- ▁অংশীদার
- বাজ
- ▁খামার
- বেদন
- ▁01
- ▁ধাঁধা
- ▁যাথোজেন
- ৫
- ৭
- ▁আনুমানিক
- ▁কমিউনিটি
- ▁করোনাভাইরাস
- ▁চাবিকাঠি
- ▁জরুরি
- ▁তঃসংয
- ▁তাভাবনা
- ▁নকশা
- ▁সহানুভূতি
- ▁অভিনেতা
- ▁ওভাররাইড
- ▁মামালেক
- ▁যামিগডালা
- ▁হতবাক
- ▁পুঁজিবাদ
- ▁মেঝে
- ▁বপুরুষ
- ▁জেগোটা
- ▁1970
- কাহিনী
- ▁বিবৃতি
- ▁বিরোধিতা
- ▁আইনজীবী
- ▁মচারী
- ▁থাপিত
- ▁ঞাপন
- ▁লেবেল
- ▁মামলা
- ▁কোলাহল
- ▁রচারণা
- ▁সোলার
- '99'
- ▁14
- ▁দোলন
- ▁গিগা
- ▁ভীক
- ▁ঘটবে
- ▁আপাত
- ▁ফেলেছিল
- ▁লাগবে
- ▁দেখছেন
- ▁যালসাই
- '35'
- ▁উপভ
- ▁বরাবর
- ▁ঘটেছে
- ▁ভেবেছিলেন
- লিভার
- ▁পেরেছিলাম
- ▁নিউরন
- ▁আমূল
- ▁ইরানে
- ▁সমতল
- ▁ওভার
- ▁আদেশ
- ▁কাঁটা
- ▁ধারনা
- ▁যুবক
- ▁এসেছিলেন
- ▁তানুকি
- ▁খামারগুলি
- ▁ণালী
- োফা
- ▁দুজন
- ▁ছুট
- ▁চৌ
- ▁সিরিজ
- ▁বলেছিলেন
- ▁উপক
- ধকতা
- ▁খুঁজছেন
- ▁জস
- ▁সচেতন
- ▁করছিলেন
- ▁লিটার
- ▁পিটার
- ▁রথা
- ▁ষমা
- ▁নথি
- ▁টোট
- ▁জামগুলি
- ▁কাগজ
- ▁তকরণ
- াবলী
- ▁পেশীগুলি
- ▁ঋণী
- ▁বছরগুলিতে
- ▁কেপ
- ▁নেহ
- ▁সেবা
- ▁তুলো
- সাঁ
- ▁অভিবাসী
- ▁পৌঁছেছে
- ▁চারণ
- ▁হেড
- ▁উঠে
- ▁যাডি
- ▁রাইভার
- ▁বেনি
- ▁আইল
- ▁সৃজনশীলতা
- ুমি
- ▁কোরবা
- ▁পারব
- চিং
- ▁চলেছেন
- ▁জীবনযা
- বসতি
- ▁রিফ
- ▁ওঠেন
- ▁ছবিটি
- ▁টাফ
- ▁সভা
- ▁ঘাম
- জগতে
- ▁রঙগুলি
- ▁বাই
- ▁তাৎ
- ▁পানী
- ▁শুনি
- শে
- ▁টেট
- ▁কারখানার
- ▁থাকবেন
- ▁যানগত
- াইরে
- ▁দো
- ▁কাঁ
- ▁সজ
- ▁থাংশ
- তীত
- ▁জেনিস
- ▁মি
- সিস
- ▁তাকালে
- োত
- পার
- ▁মোহ
- ▁পিট
- ▁টাপো
- গান
- ▁জিও
- ▁যাদা
- ▁হাম
- ▁মানিত
- ▁পাচার
- ▁সাহসী
- ▁মানগুলি
- '16'
- ুনির
- ▁ফটোগ
- ▁টাইম
- ▁পৃ
- ▁বংশ
- ▁রাণু
- ▁লট
- ▁মৃতি
- অপস
- ▁27
- '23'
- টে
- হারে
- নুপাত
- ▁শট
- ▁ফেলা
- ▁পশু
- ▁গেছেন
- ▁জারি
- ▁রমিত
- ▁রোতা
- টিং
- ▁জেনারেল
- ▁সৎ
- ▁লেন
- ▁বাগত
- ▁রমণকারী
- ▁চিতভাবে
- ▁বাসা
- ▁মডেলগুলি
- ▁টেন
- ▁গুর
- াগুলি
- দেবী
- ▁রোড
- দাতা
- ▁পরিবারগুলি
- ▁টানা
- লগ
- ▁রিটাউনে
- কিলোমিটার
- ▁রতা
- লাভ
- বৈ
- ▁কাম
- কন
- ▁বাব
- ▁সুবিধাগুলি
- ▁কগুলি
- ▁থীর
- ▁বিকভাবে
- রিশ
- ▁বই
- লিস
- ▁নগ
- দেশ
- ▁যৎ
- ▁দূরব
- ▁রাইভে
- ▁শিলা
- ▁চুরি
- মোন
- ▁অতীতে
- ▁সির
- ▁দেখাতে
- ▁হাব
- ▁কেলে
- সোস
- ▁ডাকে
- ▁আলোকব
- ▁তান
- ▁ামি
- টক
- ▁দানি
- ▁ডগুলি
- ▁পেরে
- ▁কেনা
- ▁ষণিক
- ▁কুশে
- টার
- ▁তৃপ
- ▁নেন
- ▁চাপা
- ভা
- দান
- ▁বিধা
- ▁যাকেজ
- েলে
- ▁গোল
- গন
- পরি
- ▁যাসে
- ছিলেন
- ▁চালান
- ▁নতা
- ▁যাশন
- ▁নাল
- ▁কোপটি
- িবাসী
- বশ
- িরোধী
- ▁অনুগ
- সিলি
- মত
- ▁মুন
- ▁ঞানে
- কালে
- ▁চিল
- েছিল
- ▁পরিত
- ▁যথা
- ▁যাকর
- োট
- ইনস
- ▁মিলে
- তঃ
- ▁সিএ
- ▁েলস
- শেষে
- ▁লোম
- জা
- ▁দেরি
- ▁রল
- টেক
- ▁সাহস
- ▁এইচ
- ▁মনো
- ▁রেরণ
- ▁পালা
- নিক
- ▁বাঁকা
- ছুক
- াইট
- ▁ফর
- ▁আটক
- ▁দটি
- ▁রাফ
- ▁মিস
- ▁ধা
- ▁পরিবারে
- ▁উঠত
- নুষ
- োম
- োদ
- খানার
- ▁অশ
- িরে
- বিত
- ভিল
- ▁ধুত
- ▁পাব
- ▁রেখেছি
- িটা
- ৈ
- াগন
- ▁কামান
- টাস
- ▁কারখানা
- ▁ধানে
- ▁দিত
- ▁অপরাধ
- ভি
- ালী
- রিকা
- ▁20000
- ▁সংঘ
- ▁সৃজনশীল
- '18'
- ▁অভিবাস
- ▁বলব
- ▁ধারক
- খানা
- রাধিকার
- ▁থাকব
- ▁লিখ
- ▁অমরজ
- ▁রপাত
- ▁উঠবে
- ▁রোমা
- াষী
- ▁দেখেছে
- ▁ডিশনার
- ▁াসে
- ▁নীত
- াগারে
- াফা
- ▁160
- জির
- াব
- '87'
- ▁ইনজেক
- ▁গোলকধাঁধা
- C
- L
- r
- ▁ইঁদুর
- ▁ইউটিলিটি
- ▁ইমিউনোথেরাপি
- ▁এলিভেটর
- ▁কাদামাটি
- ▁কৌতূহল
- ▁চিরতরে
- ▁ধারাবাহিক
- ▁মিসৌরি
- ▁রচারাভিযান
- ▁রাজকুমার
- ▁রেনেসাঁ
- ▁শিথিল
- ▁ষরেখা
- ▁হাসপাতাল
- ▁অবজারভেটরি
- ▁পরিকাঠামো
- ▁ররেখা
- ▁তলদেশে
- ▁শৈল
- ▁মদপুর
- ▁ওলাফ
- ▁গতিশীলতা
- ▁সাসপেন
- ▁ঘেটো
- ▁সংহতি
- ▁আইটেম
- ▁মেরামত
- ▁মৃদু
- ঁচট
- ▁96
- ▁রজেকশন
- ▁কংগ
- ▁রাচীর
- ▁রাজনীতিবিদ
- ▁সমালোচনামূলক
- ঘাট
- ▁রাখুন
- ▁উপনিবেশ
- ▁হিম
- ▁অনুকরণ
- ▁রামবাসী
- ▁দেশিকা
- টেইনার
- ▁ডেনিম
- ▁সাজানো
- রফেস
- ▁ষপাত
- ▁সাগর
- ▁পারতাম
- ▁মোতা
- ▁জিনোম
- ▁2019
- ▁এনেছিল
- ▁লুকানো
- িউএ
- ▁অভিজাত
- ▁রিটিশ
- ▁গুণমান
- ▁অভিনব
- ▁পরিপূরক
- ▁টগুলি
- ▁ষাপটে
- ▁রিলিফ
- ▁টানেল
- ▁জেগ
- ▁সুপার
- কটের
- ▁বৈধ
- ▁সেথেস
- ▁কাঁপ
- ▁জটিলতা
- ▁ফোরণ
- ▁টুকরা
- ▁ভরশীল
- ▁শদাতা
- ▁বালতি
- ▁পালক
- লিথি
- ▁ধরন
- ▁পেশা
- ▁পরিণতিগুলি
- ▁বাগান
- ▁মনোভাব
- ▁অনলাইন
- ▁থাপক
- ▁বলেছে
- ▁সেটিং
- ▁ডিফ
- ▁চোরা
- ▁ভিড
- ▁দেখেছেন
- ▁বোঝানো
- ▁শকুন
- ▁থাপকতা
- রবী
- লানিক
- ▁নীতিগত
- ▁করেননি
- ▁বিভাগে
- ▁দিকটি
- ামী
- ▁ওঠা
- িসিসি
- ▁তাকাতে
- ▁বলেছেন
- ▁পিতৃ
- ▁ফেট
- ▁পাঠক
- নাতক
- ▁দাগ
- ▁পারিনি
- ▁চেতনা
- ▁কফি
- ▁পাঠান
- ▁অবসান
- রোধে
- ▁রতিবার
- ▁মুদি
- ▁মূলধারার
- ▁বাতি
- ▁রাগন
- ▁গাম
- াবস
- ▁শনগুলি
- পোলি
- ▁বাধীনতা
- ▁ভাস
- ▁রাণীগুলি
- ▁আইস
- ▁কিছুর
- ▁জানতেন
- ▁জানু
- ▁রামগুলি
- ▁লোহ
- ▁কেজি
- ▁সাব
- ▁রাইট
- াচল
- ▁ইট
- ▁ছাপ
- বৃ
- ▁বিপদ
- সিভ
- ▁কলে
- ▁অসহ
- ▁টেরল
- ▁খাই
- ▁রমিকরা
- আইভ
- ▁উপাদানটি
- ▁মহামারীটি
- ▁যালোকে
- ▁সমাধানগুলি
- ▁যি
- ▁থিতিশীলতা
- ▁ওটা
- ▁রেখেছে
- ▁আদালতে
- ▁রোচ
- ▁গণ
- ▁দলে
- ভিয
- ▁উপহা
- ডেট
- ▁খালটি
- সুবিধাজনক
- ▁মগ
- ▁লালন
- ▁কণা
- ▁নিষেধ
- ▁১
- েলাই
- াবল
- ▁চেক
- ▁নই
- ▁অভিন
- ▁টেমে
- ▁ভট
- োন
- ▁গভীরতা
- ▁ষণগুলি
- ▁সারি
- ▁বরে
- ▁ধেকের
- ▁যাসী
- ▁দিরে
- ▁দৈন
- কড
- ঁ
- মাদ
- ▁টরের
- ▁কারো
- ▁গী
- ▁ফু
- ▁রাজারা
- জেনি
- কো
- ▁বীপগুলি
- ▁কণ
- ▁বাঁক
- ▁পিতামাতা
- ঠিত
- ▁সবাইকে
- ▁থির
- ▁মিনি
- বাহ
- ▁বাসী
- ▁তনগুলি
- ডো
- ▁থাপনা
- রো
- ▁াটি
- ▁রীর
- ▁নেবে
- ▁বুজে
- ▁রীন
- লুস
- রিটি
- নোর
- ▁500
- ▁এলাকাগুলি
- ▁উই
- ▁রোটিনটি
- তাকা
- ঠ
- শনে
- ▁360
- ▁বনে
- ▁সুয
- ▁ফিউ
- বুন
- ▁13
- ▁সাইটে
- শনার
- লাঙ
- টান
- ▁খোঁজ
- ▁ডাল
- ▁কপি
- ▁তুকি
- ▁ধাত
- জাত
- বেচ
- ▁হব
- ▁ইতালি
- োশ
- ▁জুম
- কক
- রুন
- মূল
- ▁মেইন
- ▁েলসে
- পথগুলি
- নিম
- লজি
- ▁টক
- হারা
- ▁দিই
- ▁দোকানে
- পিং
- সাধ
- চালান
- ▁রতিরোধে
- পেস
- '37'
- ▁নিল
- ▁খুলি
- গল
- ধান
- ▁ফের
- ▁জগুলি
- ▁বেলা
- পথ
- ▁কনস
- ▁শেল
- বিল
- ▁নেভিগে
- ▁জাগ
- জাতিক
- উ
- ▁রবাহে
- ুলে
- ফোন
- আপ
- তারা
- ▁অফিস
- ▁পশম
- ▁যুগে
- ▁যাটিন
- ▁ততটা
- লভ
- ▁মহাদেশে
- বো
- েমের
- ▁উৎসে
- ারবার
- ▁কমলা
- পাল
- ▁চলছ
- ভেন
- লিম
- মুন
- ▁202
- সেপ
- দানি
- মেলা
- ▁লিং
- িবার
- ▁সাইট
- ▁কনসা
- ঝর
- িকেল
- াশি
- ঝ
- ▁জানান
- ▁রমাণবাদ
- নেস
- শহ
- ▁নাচ
- ▁যাব
- ফেরা
- ▁124
- ▁পতন
- '12'
- ▁ভরা
- ▁ঘরে
- ▁বাম
- ▁লিক
- লানো
- ▁বী
- খা
- গোল
- ▁রতার
- ▁টেমটি
- '44'
- ▁জেনারে
- ▁রাশি
- ▁ভূমিক
- থি
- ▁ভাষ
- ▁ঝর
- ▁সুদ
- বাসী
- োজা
- ▁হতাশ
- লিং
- ▁চিনি
- হর
- ▁পারলে
- সাইক
- ▁196
- ▁সবা
- ▁ফুলে
- ▁আচরণে
- ভিউ
- হাই
- মদা
- '56'
- ▁তিরা
- ▁ষেপে
- ▁ধারে
- ▁নাইজ
- ▁300
- ▁অনুর
- ামেলা
- ▁মিউ
- ▁দেখ
- ▁থাম
- ▁অভিযোজ
- ▁হাঁটা
- মিক
- শাপ
- ানা
- ▁যাকটি
- ▁রবাল
- ▁বিতর
- কিউ
- ▁সিট
- ধীন
- ▁150
- ঁজ
- ▁গীত
- ▁থাকত
- াঁচে
- '600'
- ▁শুনেছে
- ▁ফসফোলিপিড
- ▁বাঁধ
- ▁বীজ
- কূল
- ▁খুঁজছে
- ▁রাজনীতি
- ▁রজেক
- ৯
- m
- u
- ğ
- ▁অববাহিকা
- ▁এনজাইম
- ▁এলিজাবেথ
- ▁কাটলফিশ
- ▁কূটনীতি
- ▁গিলগামেশ
- ▁টিরিওটাইপ
- ▁নৌবাহিনী
- ▁ফাংশন
- ▁ফারেনহাইট
- ▁বাংলাদেশ
- ▁ভলিউম
- ▁মসৃণ
- ▁মোকাবিলা
- ▁যসাগর
- ▁যাভিগেশন
- ▁যালগরিদম
- ▁রাঘিমাংশ
- ▁সমঝোতা
- ▁সালতানাত
- ▁সোককেলেটন
- ▁একাডেম
- ▁দেহভাজন
- ▁বংশধর
- ▁মহাকাশচারী
- ▁রজাপতি
- ▁হেঁটে
- ▁এমারসন
- ▁ছাসেবক
- ▁তোরাঁ
- ▁ধবিরতি
- ▁বিনোদন
- ▁রুসেডার
- ▁াশোনা
- ▁রণেতাদের
- ▁লাপনা
- দারুণ
- ▁যযুগ
- ১৯
- ▁নৃশংস
- ▁গৃহীত
- ▁সিনেমা
- ▁নেবুলা
- ▁ইমাল
- ▁শাটার
- ▁মহাকাশযান
- ▁পিঠ
- ▁থাকুন
- ▁ভালোবাস
- ▁লেপটিন
- ▁সহযোগী
- ▁পটভূমি
- ▁অবাধ
- ▁দুঃখজনক
- ▁ঢেউ
- ▁অসীম
- '97'
- ▁উপযোগবাদী
- ▁অতিথি
- ▁একেবারে
- ▁াবেটিস
- ▁কভারেজ
- ▁জোরালো
- ▁মশলা
- ▁শেঠ
- '94'
- ▁লেগেছিল
- '95'
- পোষণ
- ▁হিপ
- ▁তশাসন
- ▁টিপাত
- ▁হাজি
- ▁রবিন
- ▁যাটিপাস
- ▁টারনেট
- ▁1930
- ▁মিছিল
- ▁মাঠ
- ▁অটোম
- ▁লিখেছ
- ▁দেখছিলেন
- ▁হিংস
- ▁তৃণ
- '98'
- ▁মোনা
- ▁াংখী
- ▁উঠছে
- ▁আইকন
- ▁ফেলুন
- ভাটা
- লিডার
- ▁পিউট
- ▁যোগদান
- ▁ফীতি
- ▁মিটিং
- ▁বোমা
- ▁রাইবো
- ▁রণালী
- ▁টোরে
- ▁রতিকূল
- ডিপি
- ▁লোরেন
- ▁টারবাইন
- ▁টিবডিগুলি
- ▁ঢিবি
- ▁নোঙ
- ▁ছাদন
- ▁হেসে
- ▁বিভাজ
- ▁গুজরাট
- ▁োএ
- ▁120
- ▁খুনি
- োলেট
- ▁এসি
- ▁55
- ▁ডিজে
- ▁সিকো
- ▁ভেলা
- ▁সাইটগুলি
- ▁যাকচার
- ▁কণাগুলি
- ▁মতামত
- ▁কারখানাগুলি
- ▁ফুটপ
- ▁রাখছেন
- ▁শোনে
- ▁ষতিকর
- ▁ছাকৃত
- ▁শহরগুলো
- ▁াকরণ
- ▁যাদুঘর
- ▁সাগু
- ▁কেলিং
- ুথ
- োনাইজ
- ▁রগামী
- ▁যাসীদের
- ▁ভীত
- ▁রচলন
- ালো
- ▁টিপস
- ▁মৌ
- ▁যাফো
- ▁উঠবেন
- ▁সংবাদ
- ▁কাঁচ
- ▁চালনা
- ▁রেজার
- ▁রাসাদ
- ▁উপকরণগুলি
- ▁এগুলো
- ▁নীতিগ
- ▁0
- ▁নিকট
- ▁টেরিওটাইপগুলি
- ▁ফোরক
- ▁টোন
- ▁খনিজ
- ▁অবনতি
- ▁বনভূমি
- ▁যাটারিগুলি
- গাল
- ▁ডারগ
- ▁লুপগুলি
- ▁লজ
- ▁রনগুলি
- কিশোরী
- ▁ছেলেদের
- ভাষী
- ▁ডিপ
- ▁জুনাজপুস
- ▁গোলা
- ▁গভ
- ▁অধিক
- ▁মাইলের
- ▁কুই
- ▁সমালোচনা
- ▁যাফোস
- ▁অধিকারী
- ▁যবোধ
- ▁ধারকরা
- বিধি
- ▁ইকো
- ▁রিটেন
- ুভ
- ▁উপযোগ
- ▁নভ
- ▁ঠীগুলি
- ▁ঘটনাগুলি
- ▁মাংস
- ▁বাদাম
- োচন
- ▁লেব
- ▁বলছেন
- ▁চুষ
- ▁ঠানগুলি
- ▁শাক
- ▁কোঁ
- ▁বাভাবিকভাবে
- নুকি
- ▁লাইড
- িবিটি
- ▁যবসাগুলি
- িকে
- ▁যুগুলি
- ▁টিপ
- ▁রেফ
- ▁কাটে
- োলজি
- ঘর
- ▁টিমাই
- ▁গজা
- ▁সুযোগগুলি
- ▁বাজি
- ▁বিজি
- নেকের
- ীমা
- গুঁ
- ▁যাকরণ
- ▁গুন
- ▁বাঘ
- ▁দেহে
- সা
- '79'
- ▁যেকটি
- ▁টারে
- সিফ
- ▁লেপ
- ▁শুনেছিল
- ▁শেড
- ▁সুইড
- ▁াটে
- ▁কলাম
- ▁তেমন
- ▁ামে
- বাইক
- ▁ঢালা
- ▁মুখীতা
- ▁শিশুরা
- ▁বরফ
- ধারা
- ▁পৌ
- ▁কোল
- ▁তালা
- ▁লিন
- ▁খালে
- ুলেট
- ▁টিভি
- ▁রিম
- ▁সেনে
- ▁থামা
- ▁মিটারের
- ▁আসি
- ▁টুল
- ▁ভেজ
- ▁লাশ
- ▁রাগ
- ামাল
- টারের
- ▁রিজটি
- ▁দোর
- ▁যাসটি
- টকে
- ▁চালাবে
- ফিস
- ▁সাজ
- ▁যুব
- েবল
- ▁দিলে
- সিন
- ▁অজ
- ▁শা
- ▁টেজ
- ▁শতাংশে
- ▁ডু
- িজম
- জমে
- সাদ
- ▁অবা
- ▁পুরুষকে
- হাঁ
- ▁লুকো
- ▁মেঘে
- জান
- বক
- ▁যুতি
- ▁শতক
- ▁জিম
- রাণি
- ▁যানু
- সো
- ▁মিলন
- ▁চাইবে
- কৃতির
- ▁রোভ
- ▁মাইল
- '30'
- ▁পরিষেবাগুলি
- ▁আমানি
- ▁ছামত
- '500'
- বোল
- ▁ছবিগুলি
- ▁অরি
- ালি
- ▁নিই
- ▁তেলাপোকার
- কারে
- ▁রামে
- ▁সূচ
- ▁ারো
- ▁যাসি
- ▁টেলিভিশনে
- বুক
- টস
- ▁দেখান
- ুসং
- কু
- ▁আদি
- ণের
- িটাল
- ▁মরি
- রীদের
- বিচ
- ▁ধিম
- ▁রিটে
- ▁চাচা
- ▁গানে
- ▁শিবিরে
- টেন
- ▁দুঃ
- ▁টিকেলে
- ▁কেনে
- '000'
- ▁যুগ
- াশা
- '48'
- ▁কুর
- শান
- জিতে
- ▁খেলে
- ▁পরম
- পির
- ▁আঁ
- ভাব
- ানু
- ▁মাতৃ
- পশম
- ▁ষাত
- াণ
- ৃপ
- ▁চো
- কাঠি
- লন
- টারি
- ফল
- করণ
- টন
- ▁অতীত
- াইজার
- আর
- ▁ঝুলে
- িওল
- খোঁজ
- বোধ
- ▁গাগুলি
- ▁পেল
- বেশি
- ঘুরি
- কী
- ▁যাটা
- 08
- িব
- িৎ
- চিব
- '19'
- লাইট
- নৈতিক
- শুদ
- শম
- ▁সরকারে
- গভীর
- রোটিন
- '80'
- লেট
- ভাষা
- নাইজ
- হাত
- অপ
- ধারণ
- জানা
- ▁ঘটান
- অ
- ▁193
- কাজ
- ▁শুনেছি
- জুন
- িউ
- ▁নদ
- চুরি
- হেল
- ▁শেখান
- দি
- ঁকি
- ▁আসাদ
- লোভন
- ▁রিভে
- োগান
- নিউ
- ▁পৌঁছ
- াগ
- ▁াপথ
- ▁শোক
- ফেল
- মাণ
- ঘন
- তাই
- ▁ভুগছ
- ▁তৃ
- ▁বুঝি
- ▁দেখছি
- বসে
- ▁উঠল
- ▁টিম
- ▁180
- ▁জলা
- চা
- ▁লেগ
- ডিএ
- মাই
- ফিউ
- রিসে
- ▁পারমা
- ▁বেষ
- ▁মিলনে
- ▁110
- াংশের
- েটিক
- ▁800
- জিশন
- ▁ধারণে
- ▁তোম
- োনে
- ▁বলত
- ▁রাচ
- ▁বেগে
- ালদে
- ▁শুন
- ▁যারো
- ▁3000
- ▁1500
- ডেন
- ▁মূলধারা
- সিকতা
- ▁ছু
- ▁তাঁ
- ▁খোঁ
- ▁ভাবি
- ▁জুনাজপু
- ▁চালাব
- ▁পাথ
- গণিত
- ▁থেরাপিউটিক
- ▁মেক
- ▁ইংরেজ
- হীনতা
- ▁সেখান
- াহু
- ▁ফুটে
- হাউ
- ▁একগু
- ▁রাখছে
- ▁চমক
- ▁টিবডি
- ▁রাউ
- ৌরব
- ৎসাহ
- ভাসক
- ▁এসমেরাল
- e
- i
- ঊ
- ৬
- ▁1988
- ▁1990
- ▁অবৈধ
- ▁আকসুম
- ▁আজারবাইজান
- ▁ইসমাইল
- ▁কৌতুক
- ▁জরিমানা
- ▁তকণিকা
- ▁দাবানল
- ▁নিবেদিত
- ▁ফিলিপাইনে
- ▁যাবরেটরি
- ▁শৈবাল
- ▁সাবমেরিন
- ▁সিংহভাগ
- ▁সিংহাসনে
- ▁হাইপোথিসিস
- ▁ঘৃণ
- ▁ণযুগ
- ▁কোঅপারেটিভ
- ▁ঘেরলিন
- ▁জেলালেম
- ▁ঠপোষকতা
- ▁বিছানা
- ▁যাচমেকার
- ▁রাজবংশ
- ▁শীতাতপ
- ▁শোধন
- ▁সিকিউটিভ
- ▁হোমোরোটি
- ঘাঁট
- ▁বিলাসিতা
- ▁লেনদেন
- ▁ফোঁটা
- ▁ভালবাসে
- ▁ভূমিধস
- ▁ডেলিভারি
- ▁কমিউনিকে
- ▁এমবেড
- ▁ইউএস
- ▁ঝাঁঝ
- ▁সপোজার
- েমাট
- ▁উপসংহার
- ▁পিনবল
- ▁টাইফুন
- লিউশন
- ▁রবিবার
- ▁লেডগুলি
- ▁লুমিরা
- ▁চিবানো
- ▁রেগারি
- ▁টাইটান
- ▁কিনেছিলেন
- ▁কেরাটিন
- ▁লাজুক
- ▁শুনুন
- ▁সুসংবাদ
- ▁পহেড
- ▁মানবজাতি
- ▁মৌসুম
- ▁রবাদ
- ▁বদলানো
- এইচও
- ▁খল
- ▁রেণি
- ▁মীবাহিনী
- ▁ইরানী
- কোভ
- ▁মিলিমিটার
- ▁রসারণ
- ▁পরিহাস
- ▁রতারণা
- ▁টেসলা
- ▁014
- ▁খোসা
- ▁3500
- ▁ঘনমিটার
- বিধান
- ▁নিউটন
- ▁নেভিগেশন
- ▁গুণফল
- ▁খাঁ
- ▁কেলটন
- রিডিস
- ▁কনভেন
- ▁টেরিও
- থু
- ▁1450
- ▁টোবর
- ▁188
- ▁1980
- ▁কুকুর
- ▁পরিধি
- ▁দুঃখ
- ▁185
- ▁চাবিটি
- ▁লোরিড
- ▁1940
- ▁ধরবেন
- ▁নিঃশ
- ▁ঝাপ
- ▁তপাত
- ▁গীকার
- ▁শহরবাসী
- ▁ফসিল
- ▁যুভর
- ▁টলেশন
- ▁শুনিনি
- ▁যানজট
- ▁ডেভি
- ▁লেগেছে
- ▁জেলা
- ▁ঘটছিল
- ▁রানজিট
- ▁187
- ▁রণোদ
- ▁33
- ▁াবহ
- ▁গেছি
- '05'
- ▁খেলেছে
- ▁জিরো
- ▁ঝরনা
- ▁উপদেশ
- ▁38
- ▁াংখি
- ▁সারাদিন
- ▁শিম
- ▁আগামীকাল
- ▁বেআইনি
- ▁শিখেছে
- সিল
- ▁বাজানো
- ▁লাগছে
- ▁পালগুলি
- ▁লিউ
- ▁পাননি
- মিশনে
- ▁126
- ▁টিথার
- ▁ডোবা
- ▁বিরাজ
- এনবি
- ▁রোথ
- ▁বলছিলেন
- োনাল
- ▁যাংকিং
- চুপ
- ▁রোপড
- ▁টাইমলাইনে
- ▁যাকট
- ▁বাঁধা
- ▁যোনি
- ▁বোনা
- ▁করোন
- াকাশে
- ▁জেনেনা
- ▁ফসফোলিপিডগুলি
- ▁ওভারহ
- লেক
- ▁এলো
- ▁পিকাবু
- ▁আইনগত
- ▁তনালী
- সোম
- ▁উপকূলরেখাকে
- ▁তেরো
- ▁ফেরি
- '89'
- ▁রতিবেদন
- ▁অনুপাতে
- ▁থিম
- ▁ফলিকল
- ▁নলিখিত
- বিটি
- ▁ডিশনারগুলি
- ▁সহজাত
- ▁গুদাম
- ▁কারাগারে
- ▁গেলাম
- ▁হোমো
- ▁ফোটা
- ▁মানজনক
- ▁ঝু
- ▁অবকা
- ▁পেলেন
- ▁ফিনা
- ঃস
- ▁ঠাতা
- ▁লবণ
- ▁বিলাস
- ▁তিনজন
- ▁রশমন
- লিসা
- ▁পরিপূর
- ▁কিউবা
- ▁মিকা
- বদলে
- ▁জেনো
- পসাগর
- ▁বেসরকার
- ▁সুপ
- ▁যুইটি
- ▁চাইনি
- ▁ধিমূলক
- টিউ
- ▁ফাটল
- ▁সেলগুলি
- িওপি
- ▁নজির
- ▁হামলা
- ▁পুরু
- ▁অমরজত
- ▁তরণটি
- ▁করলাম
- ▁কখনো
- ▁মশালটি
- ▁গকগুলি
- ▁দিকগুলি
- ▁গমনকারী
- ▁দেখাবে
- ▁চাইলে
- নেভি
- ▁সাপগুলি
- ▁নোট
- ▁যানবাহনগুলি
- ▁সোমা
- ▁দেখেনি
- ▁োগকারীদের
- ▁রাইলোবাইটগুলি
- ▁ষণশীল
- ▁সেতুগুলি
- ▁বিবেক
- ▁খোঁজে
- ▁দেশগুলো
- ▁তারকা
- রীস
- ▁ডফিল
- ▁নাগাল
- ▁বোনাইজ
- ▁থেরাপিউটিকস
- ▁জিগ
- ▁যাপট
- ▁যৌগ
- ▁রুপার
- ▁রচল
- ▁যারিস
- ▁সহনশীল
- ▁বিনা
- াখা
- ▁যহীনতা
- ▁ভিজি
- ▁আঠা
- ▁ফাইন
- ▁ডুব
- ▁বইটি
- ▁সংযোগগুলি
- ▁রাফট
- ▁রবালের
- ▁ফে
- াসী
- সূরি
- সেছিলেন
- ▁যাসেল
- ▁গাইড
- ▁তাঁর
- ▁রোট
- ▁পনগুলি
- ▁গীতি
- ▁ধৃত
- োবা
- ▁বাবধান
- ▁সারিতে
- নামূল
- কভাবে
- ▁পৌঁছান
- লিখিত
- ▁তূপ
- ▁শিকারি
- ▁যথাস
- মেজ
- ীকৃত
- নাতনি
- ▁টরে
- ুখী
- চেতন
- ▁যাবলে
- ▁ধারণাগুলি
- ▁জীবগুলি
- ▁কাজিন
- ▁560
- হেলম
- ধমনী
- ▁করুণা
- ▁করেছ
- আ
- ১
- '%'
- ':'
- c
- h
- l
- n
- z
- ü
- ২
- ৪
- ৩
- ঔ
- ঈ
- Ö
- U
- ঋ
- ঐ
- '?'
- O
- ।
- ়
- <sos/eos>
src_token_list:
- <blank>
- <unk>
- s
- ▁the
- ▁to
- ▁and
- ▁of
- ▁a
- ing
- ▁in
- ed
- ▁that
- ▁is
- ▁
- ly
- ▁we
- ▁it
- ▁you
- d
- ▁this
- ▁for
- ▁on
- e
- ▁be
- ▁but
- ▁with
- ▁so
- ▁are
- ▁i
- ▁have
- ▁can
- ▁they
- y
- ▁was
- ▁as
- ▁its
- ▁from
- ▁their
- ▁at
- ▁what
- ▁by
- ▁one
- ▁our
- ▁an
- ▁or
- ▁al
- ▁like
- ▁more
- ▁when
- ▁your
- ▁were
- ▁some
- ▁all
- ▁not
- ▁these
- n
- ▁people
- t
- ▁how
- ▁if
- ▁about
- to
- ▁there
- ▁do
- ▁would
- ▁up
- ▁her
- al
- nt
- ▁which
- ▁just
- er
- ▁them
- ▁us
- ▁he
- ▁other
- ▁now
- es
- ▁know
- ▁has
- ▁s
- ▁make
- ▁my
- ▁most
- ▁because
- ▁could
- ▁world
- ▁than
- ▁work
- ▁need
- ▁will
- ▁had
- ▁out
- a
- r
- so
- ▁over
- ▁who
- o
- ▁time
- ▁new
- ▁even
- ▁get
- ve
- many
- ▁well
- ▁she
- ▁no
- ▁energy
- en
- ion
- ▁where
- ▁climate
- ▁take
- st
- ▁change
- ▁me
- ▁power
- ▁un
- ▁two
- ▁first
- ▁help
- ▁look
- ▁way
- le
- ▁dont
- ▁years
- ▁re
- ▁here
- ▁call
- ▁think
- p
- ▁m
- in
- ▁carbon
- able
- c
- ▁much
- ▁those
- ever
- ▁been
- ▁use
- ▁right
- ▁co
- m
- thing
- ▁go
- ▁want
- ▁through
- l
- ▁see
- ▁same
- ive
- i
- ▁may
- ▁really
- ers
- ▁going
- ▁every
- ▁then
- ▁cells
- ▁life
- ▁his
- ▁different
- ▁should
- out
- u
- ▁around
- ▁im
- ▁things
- ight
- re
- g
- ▁still
- ▁sleep
- ▁any
- ▁say
- 'on'
- ▁high
- ▁while
- ▁back
- ▁long
- each
- ous
- ▁light
- ▁b
- ▁let
- ▁does
- ▁down
- th
- ▁own
- ies
- ▁three
- ▁start
- ▁countries
- ▁before
- ▁made
- ▁show
- ▁system
- ▁come
- very
- ▁large
- ic
- ▁tell
- yre
- ▁percent
- ▁global
- ▁india
- ▁after
- ▁water
- ▁n
- ▁often
- ▁off
- ▁again
- ▁part
- ll
- ▁ma
- ▁company
- ▁country
- twe
- ▁being
- k
- ▁next
- ▁used
- ▁point
- ▁de
- ▁today
- ▁hear
- ready
- ▁day
- ▁actually
- ▁try
- ▁year
- ▁lot
- ▁less
- ar
- ting
- ▁ca
- ▁answer
- ▁keep
- ▁develop
- ▁another
- ment
- ▁end
- ▁d
- ation
- ce
- b
- ▁per
- us
- ▁grow
- ▁enough
- ▁why
- ▁live
- ful
- or
- ▁g
- ▁number
- ▁place
- ▁give
- ▁few
- ▁t
- ▁19
- ▁20
- '2'
- ▁create
- ▁important
- ▁believe
- ▁single
- ▁cities
- ▁10
- uch
- ▁move
- ▁example
- ▁fossil
- ▁mrna
- ▁better
- ther
- lar
- ▁fact
- ▁p
- ▁find
- ▁city
- ▁did
- ▁mean
- ▁emissions
- is
- an
- ur
- w
- ▁research
- ▁kind
- ▁government
- ▁allow
- ▁case
- ▁person
- ▁small
- ▁green
- ▁across
- ▁him
- ▁second
- ▁home
- ▁human
- ▁night
- ▁thank
- ▁air
- ▁best
- ▁future
- ▁space
- ▁together
- ▁become
- ince
- ▁both
- ▁must
- ▁cant
- ▁dur
- ▁seem
- ▁side
- h
- ▁man
- one
- ▁body
- ▁car
- ▁problem
- ate
- ity
- ▁too
- ▁under
- ▁final
- ▁play
- ▁build
- ary
- ▁form
- ▁set
- ▁e
- ▁money
- ▁good
- ▁five
- ▁follow
- ▁last
- ▁economy
- ry
- est
- ▁pay
- ite
- ▁plants
- ▁bas
- be
- ▁doing
- ▁companies
- ▁entire
- ▁great
- ▁yet
- ▁far
- ▁everyone
- ▁story
- ▁times
- ▁away
- ▁ra
- ▁f
- ty
- ▁stop
- most
- ▁force
- ▁scale
- ▁impact
- less
- ▁mass
- ▁sp
- ▁once
- ▁found
- ▁ear
- ▁hair
- ▁possible
- ▁sound
- ▁electric
- ▁states
- it
- ▁red
- ▁produce
- ▁million
- ▁feel
- ▁put
- ▁planet
- ▁means
- ▁later
- ▁o
- ▁value
- ▁telescope
- ▁result
- el
- ▁ask
- ▁cost
- '00'
- ▁turn
- ▁health
- ▁industry
- ▁potential
- ▁clear
- ▁consider
- ▁gold
- ▁didnt
- ▁heart
- ▁brain
- v
- ▁lead
- ▁thing
- ▁plant
- making
- ▁working
- ▁process
- ▁technology
- ▁name
- ▁electricity
- ▁sure
- ally
- x
- age
- ▁15
- ble
- ness
- ▁ever
- ▁mo
- ▁family
- ▁earth
- ▁rule
- ▁r
- ▁hand
- ▁god
- ▁others
- ▁old
- ▁share
- ▁vaccines
- ▁k
- ▁heat
- ▁continue
- ▁talk
- ▁question
- ▁fuel
- sh
- ▁business
- ▁economic
- ▁little
- ▁dioxide
- ▁run
- ▁public
- ▁cause
- ▁reach
- ▁scientists
- ▁com
- ▁land
- ▁seen
- ▁st
- '9'
- ▁understand
- ld
- la
- ▁got
- ▁whe
- ▁big
- ▁century
- ▁concrete
- ▁support
- ▁food
- ▁always
- ▁job
- ▁certain
- ▁act
- ▁design
- ▁head
- ▁resources
- ▁6
- ▁came
- ors
- ▁unit
- ▁c
- ▁control
- ▁level
- ▁test
- ▁1
- ge
- ▁war
- ▁gas
- ▁africa
- ▁hard
- ▁mitochondria
- ▁remain
- ▁along
- ▁nature
- ▁near
- ▁billion
- ▁white
- ▁exactly
- ▁11
- ▁instead
- ▁discover
- ter
- ▁3
- ▁4
- '0'
- ▁creat
- ▁includ
- ▁protein
- ine
- ▁love
- ▁close
- ▁amount
- ▁degree
- ▁desert
- ▁particular
- ▁pandemic
- ▁data
- ▁approach
- ▁renewable
- ▁cement
- ▁blue
- ▁lower
- at
- ▁cover
- ▁bring
- ▁lives
- ▁thousands
- ▁fuels
- li
- ▁protect
- ▁idea
- ▁term
- ▁group
- ▁difficult
- ▁systems
- ▁started
- ck
- ▁sea
- ▁treat
- ▁immun
- ▁platform
- ▁women
- ▁current
- ▁model
- ▁history
- ▁began
- ▁short
- ▁eye
- ▁save
- ▁team
- ▁sun
- ▁moment
- ▁usual
- ▁table
- member
- ▁happen
- ▁provide
- ▁true
- ▁coal
- ▁wanted
- tic
- ▁pre
- he
- ▁trees
- ▁ways
- ▁color
- ▁vaccine
- ▁full
- ought
- ▁response
- ▁themselves
- ▁natural
- ▁prevent
- ▁exist
- ▁information
- ▁took
- ▁buy
- ▁thought
- ▁mind
- per
- ▁though
- ized
- til
- il
- ish
- ▁face
- ▁clean
- ian
- ▁product
- ▁increase
- ▁low
- ▁humans
- ▁da
- ▁species
- ▁local
- ▁rich
- ▁huge
- ▁break
- ▁stories
- ▁order
- ▁blood
- ▁late
- ▁fight
- ▁reduce
- ▁quickly
- ▁seat
- ance
- ▁dis
- ▁du
- ▁real
- ir
- ist
- ▁2
- ▁map
- ▁invest
- am
- ▁bone
- ▁experience
- ▁governments
- ▁built
- ▁communities
- ▁yingtai
- ▁situation
- ▁return
- ▁similar
- ▁zero
- ▁south
- ▁standard
- ▁further
- ▁state
- ▁young
- ▁h
- ▁months
- ▁ago
- ory
- ▁sh
- ▁vari
- ▁liv
- te
- ra
- ▁5
- ▁black
- ▁saving
- ▁reason
- ▁laughter
- ▁market
- ▁children
- ▁desp
- ▁open
- ▁sky
- ▁fall
- ▁word
- ▁inter
- ▁vi
- ul
- ▁action
- ▁groups
- ▁bit
- rs
- ▁factor
- ▁dr
- ▁ex
- z
- ety
- ern
- ▁drive
- ▁u
- ▁chemical
- ▁female
- ▁ground
- ▁hundred
- ▁access
- ▁addition
- ▁least
- ▁sex
- ▁specific
- ▁chance
- ▁death
- ▁walk
- ▁sendler
- ▁half
- ▁anxi
- ▁left
- ▁sometime
- ▁port
- ▁pass
- ▁wind
- ▁arent
- ma
- ▁longer
- ▁free
- ▁toward
- ▁questions
- ▁soon
- cy
- ▁king
- ▁w
- came
- ▁cars
- ▁ga
- ▁poor
- ▁bridge
- ▁evidence
- ▁extreme
- ▁risk
- ▁surface
- ▁wrong
- taking
- ▁common
- ▁probab
- ▁plate
- ▁moon
- ▁either
- ▁language
- ▁sw
- co
- ▁cop
- ▁american
- ▁kilometers
- ily
- ▁am
- ▁inside
- ch
- ▁millions
- ize
- ▁house
- ▁materials
- ▁step
- ▁mi
- ▁con
- '8'
- ▁cockroach
- ▁racial
- ▁study
- ▁woman
- ▁modern
- ▁key
- saw
- ▁dna
- ▁survive
- ▁total
- ▁cell
- ▁op
- ▁line
- ▁pa
- ▁tra
- ▁hours
- ▁simple
- hap
- ▁size
- ▁solutions
- ▁200
- ▁safe
- ▁contain
- ▁require
- ant
- ▁past
- ▁success
- ▁fast
- ▁transform
- ▁fear
- ▁behind
- ▁english
- ▁essential
- ▁exponential
- ▁science
- ▁trilobite
- ▁yourself
- ▁demand
- ▁focus
- ▁multiple
- ▁third
- ▁said
- ▁covid
- ▁income
- ▁pressure
- ▁four
- ▁hold
- ▁lack
- ▁significant
- ▁astronomer
- ▁easy
- ▁disk
- ▁done
- ▁growth
- ▁pair
- ▁fire
- ▁dollars
- ▁asian
- ▁matter
- '5'
- ▁vehicles
- id
- vi
- ▁pro
- ▁simpl
- ▁30
- ▁decades
- ▁fat
- ▁results
- ▁areas
- '4'
- ▁waste
- ▁building
- ▁deliver
- ▁sit
- ▁egypt
- ▁view
- ▁community
- ▁conversation
- ▁pigeon
- ▁suggest
- ▁wavelength
- ▁constant
- ▁course
- ▁dream
- ▁unique
- ▁itself
- ▁send
- ▁absorb
- ▁law
- cient
- ▁universe
- ▁north
- ated
- ▁respond
- ▁sense
- ▁eat
- ▁forward
- ▁school
- ▁places
- ▁tree
- ure
- ▁hit
- tton
- '6'
- ▁goal
- ▁individuals
- ▁days
- ▁sha
- ▁patients
- ling
- ▁shift
- ▁limit
- ted
- ▁generate
- ▁en
- ▁star
- ▁solve
- land
- ▁visit
- ▁8
- ▁12
- ▁sub
- ▁begin
- ▁available
- ▁difference
- ▁greek
- ▁measure
- ▁opportunity
- ▁damage
- ▁increasing
- ▁relative
- ▁typical
- ▁release
- ▁middle
- ▁wont
- ▁center
- ▁weather
- ▁cancer
- ▁rise
- ▁loop
- ▁class
- ▁fix
- ▁role
- ▁policies
- ▁loss
- ▁care
- ▁outside
- ▁image
- ▁lord
- ▁basic
- ▁l
- ▁add
- as
- ng
- ▁pret
- ▁nation
- ▁range
- ▁challenge
- ba
- ▁sum
- ▁di
- pri
- ▁learn
- ▁trap
- ▁appear
- ▁interest
- ▁goals
- ▁anti
- though
- ▁determine
- ▁hope
- ▁virus
- ▁campaign
- ▁efficiency
- ▁knew
- ▁plastic
- ▁pollut
- ▁poverty
- ▁racism
- ▁stereotype
- ▁studie
- ▁behavior
- ▁avoid
- ▁river
- ▁moving
- ▁coast
- ▁instance
- ▁square
- ▁skin
- ▁effective
- ▁reality
- ▁faster
- ▁environmental
- ▁rate
- ▁trade
- ▁plan
- ▁completely
- jar
- ▁speed
- ▁tri
- ▁alone
- ▁sort
- ▁post
- ▁national
- ▁parents
- ations
- ▁store
- ier
- ▁connect
- ▁decid
- ▁levels
- ▁non
- ▁trojan
- ▁relationship
- ▁forest
- ▁material
- ol
- ▁patterns
- ▁refugees
- ▁sign
- ▁costs
- ▁talking
- ▁imagine
- ric
- ions
- ▁kill
- ▁hav
- ▁po
- ▁arm
- na
- ▁canal
- um
- ▁strong
- ▁threat
- ▁fel
- ▁extra
- ▁efficient
- ▁incredibl
- ▁infrastructure
- ▁switch
- ▁milk
- ▁panel
- ▁slavery
- ▁social
- ▁present
- ▁warming
- ▁organization
- ▁dangerous
- ▁else
- ▁deep
- ▁corporation
- ▁divers
- ▁society
- ▁listen
- ▁moral
- ▁signal
- ▁stand
- ▁sever
- ▁janie
- ▁separate
- ical
- ▁taken
- ca
- ▁type
- ▁solution
- ▁friend
- ▁main
- ▁animals
- ver
- side
- f
- ▁rules
- ▁options
- ent
- qu
- ▁bags
- ▁engines
- ▁70
- ▁treatments
- ▁ready
- ▁benefits
- ▁top
- ring
- ac
- ▁depend
- ▁manufactur
- tion
- ▁meet
- while
- ▁problems
- ▁americans
- ▁cur
- ▁works
- ▁homes
- ▁central
- ▁political
- ▁sappho
- ▁technologies
- ▁transition
- ▁escape
- ▁ocean
- ▁reflect
- ▁rough
- ▁unlike
- ▁crisis
- ▁jeans
- ▁eventually
- ▁harm
- ▁spouse
- ▁trans
- ▁2020
- ▁atmosphere
- ▁egyptian
- ▁attack
- ▁safety
- ▁mother
- ▁grid
- ▁stay
- ▁vir
- ▁bank
- ▁changed
- '3'
- ide
- go
- ▁structure
- ▁workers
- ▁organ
- ▁giv
- ▁numbers
- ▁ver
- ▁learned
- ▁cl
- ability
- de
- ▁lie
- ▁hi
- ▁16
- ▁recognize
- ▁game
- ▁benefit
- ▁saying
- ▁led
- ▁leave
- ▁temperatures
- ▁br
- ▁men
- ▁estimate
- ▁100
- ped
- ▁read
- des
- ▁th
- are
- ▁travel
- ▁fund
- ▁lo
- ▁improve
- head
- ▁cut
- ▁needs
- ▁tea
- ▁progress
- q
- ▁perform
- ▁complex
- ▁general
- ▁urban
- ▁advance
- ▁california
- ▁journey
- ▁perspective
- ▁quality
- ▁supply
- ▁affect
- ▁birth
- ▁piece
- ▁slow
- ▁dentist
- ▁spider
- ▁famili
- ▁favor
- ▁fair
- ▁child
- ▁trick
- ▁mona
- ▁everybody
- ▁flight
- ▁cool
- ▁flow
- ▁mali
- ▁track
- ▁male
- ▁manage
- ▁durr
- ▁colors
- ▁lying
- ▁notice
- ▁personal
- ial
- ▁doctor
- ▁weeks
- ▁80
- ments
- op
- '0000'
- yon
- cu
- ▁ensure
- ▁offer
- ▁camp
- ▁projects
- ▁lipid
- ▁molecule
- ▁treatment
- ▁candles
- ▁asked
- ▁points
- ▁engineers
- ▁mine
- ▁types
- ▁mu
- ▁chang
- nd
- ard
- ▁id
- my
- ▁compar
- ze
- king
- ▁agree
- ship
- national
- '1'
- ▁supernova
- ward
- tual
- ph
- ▁machine
- ▁author
- ▁capacity
- ▁celsius
- ▁driving
- ▁grandfather
- ▁oxygen
- ▁picture
- ▁satellite
- ▁scientific
- ▁shanbo
- ▁village
- ▁evolv
- ▁record
- ▁equip
- ▁floor
- ▁numer
- ▁regard
- ▁seven
- ▁among
- ▁neighborhood
- ▁lisa
- ▁normal
- ▁feed
- ▁indeed
- ▁catch
- ▁personality
- ▁kid
- ▁lose
- ▁innovation
- ▁east
- ▁six
- ▁trust
- ▁train
- ▁ne
- ▁sell
- ▁germany
- ▁teach
- ▁inject
- ell
- nese
- ▁ball
- ▁rare
- ▁mammals
- ▁carey
- ▁everything
- ▁products
- ▁eggs
- ▁healthy
- ities
- ia
- ▁bonds
- ▁rest
- norm
- ▁adults
- ▁locusts
- ▁cr
- ▁cu
- ▁area
- ▁cooperatives
- ▁tons
- ▁ph
- ▁die
- ▁le
- ▁figure
- ▁conditions
- ▁environment
- ▁regions
- ▁engine
- ru
- ▁seizure
- ▁pattern
- ▁refugee
- ▁bu
- ▁patient
- ▁bag
- ▁hour
- ▁engineer
- ▁turns
- lands
- lf
- ▁18
- ▁50
- ▁weight
- ▁created
- ▁ab
- ▁tru
- bi
- '7'
- ▁forms
- ▁burn
- fortunate
- ▁age
- ect
- ha
- ating
- ▁kings
- ▁europe
- ▁major
- ▁kush
- ▁rock
- ▁account
- ▁ambition
- ▁apnea
- ▁citizens
- ▁dramatically
- ▁education
- ▁footprint
- ▁ourselves
- ▁predators
- ▁producing
- ▁recipient
- ▁student
- ▁sudden
- ▁tackl
- ▁target
- ▁vulnerable
- ▁block
- ▁extend
- ▁racist
- ▁speech
- ▁daughter
- ▁below
- ▁committ
- ▁push
- ▁service
- ▁tiny
- ▁easier
- ▁causing
- ▁sector
- ▁launch
- ▁quite
- ▁describe
- ▁jew
- ▁capital
- ▁mention
- ▁wait
- ▁dome
- ▁pull
- ▁24
- ▁construction
- ▁born
- ▁financial
- ▁chain
- ▁banda
- ▁ari
- ▁sustainable
- ▁position
- ▁humanity
- ▁race
- ▁twin
- sion
- ▁sent
- ▁enter
- ▁expect
- ▁policy
- ▁rain
- wise
- ▁shipp
- ▁shape
- ▁bigge
- ▁medic
- ▁special
- om
- ▁tend
- ▁waves
- ▁remov
- ake
- ▁201
- utch
- ock
- ▁decarbonize
- ▁news
- ▁door
- ▁populations
- ▁fly
- ▁happening
- ▁realiz
- ▁source
- ▁price
- ▁disease
- ▁minute
- ▁candle
- ▁decade
- ▁molecules
- coming
- ▁fl
- dp
- ▁seeing
- un
- ▁el
- act
- ▁challenges
- ▁pee
- ▁wa
- ▁capture
- ▁meaning
- scar
- special
- ▁complete
- ▁swap
- ▁lines
- ▁pack
- ▁tax
- ▁sultan
- ▁novel
- ▁count
- ▁dark
- ▁civil
- ▁advantage
- ▁multi
- ▁physical
- ▁recycl
- ▁surround
- ş
- ▁accord
- ▁alternative
- ▁attention
- ▁cactus
- ▁culture
- ▁economist
- ▁myself
- ▁negative
- ▁relief
- ▁salesman
- ▁secret
- ▁expand
- ▁finance
- ▁report
- ▁glass
- ▁consequences
- ▁excited
- ▁choice
- ▁guess
- ▁loud
- ▁court
- ▁stick
- ▁address
- ▁calcium
- latoni
- ▁electrons
- ▁network
- ▁adopt
- ▁watch
- ▁translate
- ▁maintain
- ▁industrial
- ▁bad
- ▁distance
- ▁2030
- ▁batteries
- ▁communication
- ▁impossible
- ▁location
- ▁25
- ▁galaxy
- ▁frequent
- ▁camera
- ▁anywhere
- ▁truth
- ▁operation
- ▁associate
- ▁direction
- ▁elevator
- ▁fit
- ▁90
- ▁stable
- ▁inequality
- ▁gap
- ▁worse
- ▁bodies
- ▁wor
- ▁legal
- ▁raise
- da
- ▁ship
- ▁severe
- ▁em
- ▁fr
- ▁muscles
- ▁beat
- ▁proteins
- ging
- ▁tools
- ride
- lines
- ▁leader
- ft
- oke
- ten
- ious
- ▁diseases
- ▁minutes
- ▁accelerate
- ▁emit
- ▁seizures
- mat
- ▁understanding
- ▁road
- ▁project
- ▁effect
- some
- ▁viper
- ▁nanoparticle
- ▁condition
- ▁region
- ▁temperature
- ▁individual
- ▁option
- ▁coat
- ▁turning
- ifi
- ▁friends
- res
- ▁stor
- not
- ▁1000
- ▁la
- lob
- amp
- ap
- ▁combin
- ▁speak
- ang
- body
- izing
- house
- ▁lay
- ▁involve
- ▁america
- ▁val
- ▁abundan
- ▁arrest
- ▁chlorophyll
- ▁cloud
- ▁colleague
- ▁context
- ▁couple
- ▁economies
- ▁effort
- ▁enslaved
- ▁erik
- ▁experiment
- ▁genetic
- ▁hurston
- ▁infection
- ▁length
- ▁limestone
- ▁method
- ▁outbreak
- ▁positive
- ▁predict
- ▁recommend
- ▁urethra
- ▁annual
- ▁conflict
- ▁destroy
- ▁dialect
- ▁flood
- ▁hormone
- ▁narrow
- ▁scatter
- ▁therapy
- ▁thick
- ▁throw
- ▁volume
- ▁continent
- ▁ecosystems
- ▁fail
- ▁girl
- ▁thrive
- ▁field
- ▁swarm
- ▁drug
- ▁vibrat
- ▁average
- ants
- ▁morning
- ▁corner
- ▁stretch
- ▁overall
- ▁subject
- ▁hung
- ▁heav
- ▁orbit
- ▁instructions
- ▁pick
- ▁donor
- ▁responsibility
- ▁search
- ▁list
- ▁labor
- ▁match
- ▁join
- ▁european
- ▁stress
- ▁crucial
- ▁nap
- ▁yes
- vas
- ▁worth
- ▁park
- ▁invent
- mbus
- ▁host
- ▁gather
- ▁sethe
- ▁wage
- ▁operator
- ▁check
- ▁letter
- ▁actions
- ▁spread
- ▁gone
- ▁sexual
- ▁inspired
- ▁boy
- ular
- ▁cross
- ▁tail
- ▁production
- ▁critical
- ▁literally
- ▁surprising
- ▁cycle
- ▁connection
- ▁harder
- ▁storm
- ▁involved
- ▁z
- '000'
- ordina
- ible
- ▁fortunate
- ▁song
- eries
- ▁bin
- ▁mid
- ▁characters
- ▁safely
- ▁inten
- ja
- ▁jun
- ▁0
- ▁400
- kept
- ▁ix
- ▁features
- ▁objects
- ▁needed
- ▁practices
- ▁tens
- ▁meeting
- ▁meters
- ▁west
- ▁learning
- hol
- ▁gra
- ▁achieve
- ▁cutt
- ative
- ▁event
- ▁contribut
- ▁nanoparticles
- ▁hum
- ilitar
- ▁fac
- ▁lipids
- ▁period
- war
- ▁population
- ▁animal
- ▁issue
- ▁regulat
- ▁plans
- way
- ▁island
- ▁te
- ▁site
- lle
- ven
- ▁j
- ▁40
- ▁matters
- ▁corrupt
- ▁expos
- where
- ▁dead
- ▁quick
- ▁bar
- ▁languages
- ▁wide
- ▁polic
- ▁abo
- shed
- ▁german
- ▁twi
- room
- ism
- ▁chi
- ▁react
- ▁transport
- tract
- ▁lab
- ▁correct
- ▁immediate
- ▁pilot
- ▁previous
- ▁smuggl
- ▁altogether
- ▁bottom
- ▁component
- ▁husband
- ▁kenya
- ▁kilogram
- ▁pigments
- ▁platypus
- ▁responsible
- ▁suppose
- ▁temple
- ▁torture
- ▁york
- ▁battle
- ▁concentrat
- ▁status
- ▁witness
- ▁globe
- ▁peace
- ▁radical
- ▁serious
- ▁urine
- ▁tough
- ▁dozen
- ▁nice
- ▁minorit
- ▁beginning
- ▁accurate
- ▁consistent
- ▁street
- ▁running
- ▁round
- ▁message
- ▁spike
- ▁tech
- ▁convert
- ▁define
- ▁draw
- ▁2050
- ▁17
- ▁transportation
- ▁peg
- ▁paper
- ▁members
- ▁rna
- ▁necessary
- ▁nucle
- ▁strategy
- ▁rocket
- ▁wall
- ▁office
- ▁activity
- ▁flee
- ▁recent
- ▁bright
- ▁path
- ▁slight
- time
- ▁miss
- ▁drop
- ▁taxes
- ▁independent
- ▁stronger
- rising
- ▁claim
- ▁front
- ▁receive
- rch
- ▁anyone
- ▁displac
- ▁press
- ▁apply
- ium
- ▁widely
- ▁room
- ▁hopeful
- ▁smaller
- ▁internal
- ▁dry
- ▁pathways
- ▁grown
- orn
- ▁balance
- ▁required
- ▁min
- ull
- ▁carrie
- ▁ruler
- ▁captur
- ▁fully
- ▁ste
- ef
- ▁fa
- ▁terms
- ▁ideas
- ▁brothers
- ▁generations
- ▁towers
- ▁7
- ▁compare
- ▁include
- ▁bi
- ▁wr
- ▁manufacturer
- ▁whos
- ▁nor
- ▁died
- ▁stopp
- ▁happened
- ▁active
- ▁issues
- ▁aid
- ▁effects
- ▁seek
- ▁observat
- '50'
- ence
- ▁emitt
- ▁sett
- ▁environments
- ▁hous
- ▁continu
- fi
- ▁decide
- ▁ok
- ▁son
- bility
- ▁investment
- ese
- led
- inning
- ▁african
- ▁consume
- gs
- cent
- mon
- ▁ill
- tain
- gu
- im
- ▁buildings
- ▁film
- nder
- line
- set
- lem
- ▁direct
- ▁threaten
- loved
- work
- ▁li
- back
- ▁rais
- ▁arrive
- ▁sk
- ▁ban
- ▁paint
- ▁div
- ▁apart
- ▁adapt
- ▁germ
- ▁che
- ▁laugh
- if
- timate
- ▁attempt
- ▁survey
- ▁afternoon
- ▁bladder
- ▁budget
- ▁crazy
- ▁disguise
- ▁empire
- ▁equivalent
- ▁exchange
- ▁expensive
- ▁explain
- ▁feet
- ▁habit
- ▁himself
- ▁institution
- ▁japan
- ▁membrane
- ▁morrison
- ▁nazi
- ▁opportunities
- ▁peruggia
- ▁represent
- ▁revolution
- ▁scenario
- ▁shoot
- ▁strength
- ▁symptoms
- ▁tanuki
- ▁transfer
- ▁victim
- ▁wonder
- ▁application
- ▁murder
- ▁promis
- ▁stuck
- ▁worldwide
- ▁kingdom
- ▁grew
- ▁trillion
- ▁priv
- ▁document
- ▁score
- ▁super
- ▁giant
- ▁finish
- ▁confiden
- ▁acid
- ▁popular
- ▁traits
- ▁italian
- ▁wales
- ▁sand
- ▁analys
- ▁solid
- ▁china
- ▁wild
- ▁approv
- ▁sterilization
- ▁steel
- ▁indicat
- ▁compromise
- ▁collective
- ▁nile
- ature
- ▁kushite
- ▁majority
- ▁andrea
- ▁edge
- ▁syrian
- rench
- ▁chel
- ▁traditional
- ▁fur
- ▁visibl
- ▁fam
- ▁root
- ▁box
- ▁suit
- ▁prepared
- ▁stage
- ▁fine
- ▁mark
- ▁reaction
- ▁removal
- ow
- ▁please
- ▁amazing
- ▁gate
- cular
- ▁cold
- '26'
- ▁fi
- ▁convinc
- mit
- ▁art
- ▁cable
- ez
- ▁liter
- acious
- ▁spe
- ▁mission
- ▁station
- mental
- ▁processes
- ▁concerns
- anic
- ▁bones
- ▁warn
- ▁disc
- ▁maps
- com
- tch
- ▁bare
- ▁net
- ▁scar
- ▁code
- ▁flu
- ▁beliefs
- ▁residents
- ▁exposed
- ▁painting
- ▁soil
- ▁primar
- ▁combined
- ▁farms
- ff
- ▁speaking
- fully
- ▁sold
- ▁town
- ished
- ility
- ological
- ▁lit
- ▁pl
- ▁miner
- ▁officials
- ▁ingredients
- ▁spine
- ▁cleaner
- ▁neighbors
- ▁75
- ▁consum
- ati
- eth
- ▁fan
- ▁regulator
- ▁partners
- ▁tests
- ▁shifting
- ham
- ▁loved
- ▁replace
- ction
- unch
- ▁22
- ▁dut
- ific
- ▁hub
- ▁cha
- ▁roads
- ▁ii
- cc
- cious
- ▁prices
- ami
- ▁ho
- ▁equal
- ▁camps
- ▁produces
- ▁ent
- ▁contribute
- ▁games
- ▁organs
- ▁36
- ber
- ▁tissue
- ▁chamber
- ▁partner
- ▁cat
- ▁route
- ave
- ▁cooperative
- ▁vehicle
- ▁month
- ▁thousand
- ▁relationships
- ▁sums
- mal
- nia
- lic
- ▁app
- ▁structur
- ouri
- onvi
- ▁breath
- ternal
- gi
- ▁ran
- wn
- ets
- gh
- how
- ▁perfect
- ▁sta
- ▁leav
- ▁elevat
- ▁emerg
- ▁bill
- ▁command
- cast
- bti
- ▁spot
- ▁instruct
- ▁respect
- refore
- ▁ambitious
- ▁coronavirus
- ▁cultural
- ▁customers
- ▁disaster
- ▁elephant
- ▁encounter
- ▁horizontal
- ▁hydrogen
- ▁kettle
- ▁mainframe
- ▁messenger
- ▁mirror
- ▁permanent
- ▁photograph
- ▁precise
- ▁principle
- ▁rival
- ▁sahara
- ▁scholar
- ▁tunnel
- ▁choose
- ▁deserve
- ▁distribut
- ▁president
- ▁purpose
- ▁task
- ▁temporar
- aught
- ▁blow
- ▁collaborati
- ▁occur
- ▁resilien
- ▁suffer
- ▁surgeon
- ▁august
- ▁coalition
- ▁protest
- ▁programs
- ▁exciting
- ▁naked
- ▁aspect
- ▁photosynthesis
- ▁weapon
- ▁vertical
- ▁shot
- ▁strauss
- particles
- ▁beautiful
- ▁genes
- ▁disappear
- ▁nerve
- ▁prosper
- ▁function
- romed
- ▁preserv
- ▁encourag
- ▁trigger
- ▁trauma
- ▁indig
- ▁detect
- ▁mainstream
- ▁guide
- ▁iran
- ▁approximat
- ▁reused
- ▁justice
- ▁clinic
- ▁roman
- ▁superheroes
- ▁01
- ▁degrad
- ▁self
- ▁commission
- ▁wealth
- ▁crop
- ▁agenc
- ▁sick
- ▁27
- ▁flat
- ▁epic
- ▁hang
- ▁tale
- ▁ethic
- ▁assembl
- ▁proportion
- ▁broad
- ▁lock
- ▁14
- ▁invite
- ▁workplace
- ▁vary
- marine
- ▁194
- ▁definition
- ▁dig
- ▁transformation
- ▁cheaper
- ▁march
- ▁adaptation
- ▁statement
- ▁jet
- ▁load
- man
- ▁metal
- ▁lost
- ▁carry
- ▁projection
- ▁tension
- ▁fill
- ▁owe
- xic
- ▁curve
- ▁digital
- ▁cannon
- ▁ideal
- ▁fish
- ▁bce
- ▁mom
- ption
- ▁rely
- ▁useful
- etic
- ▁perfectly
- ▁army
- ▁movement
- ▁tear
- ▁eugenics
- ▁successful
- ▁reproducti
- ▁agreed
- ▁careful
- net
- ural
- reliable
- ▁threatened
- ▁coin
- ▁corrupted
- ▁bo
- non
- ▁myth
- ▁increases
- ▁coen
- ort
- ▁solv
- ▁mining
- ▁container
- ▁grand
- spend
- ▁indian
- nit
- ▁met
- mber
- ▁si
- ▁micro
- ▁killed
- ▁wi
- ▁funding
- ▁organisms
- ▁oil
- ▁cont
- ▁limited
- ▁alive
- ▁deal
- men
- ▁routes
- ▁tissues
- ▁chambers
- ▁exc
- ▁pin
- ▁investments
- vert
- ▁pursue
- ▁hands
- ▁periods
- ▁10000
- ▁pai
- ▁argue
- ▁vipers
- ▁observ
- vor
- ▁hot
- ▁basi
- ile
- ▁sil
- ▁sources
- ▁operate
- light
- ▁islands
- ▁ten
- ▁owner
- ▁brains
- asse
- ▁werent
- ▁telescopes
- ▁ha
- ▁conve
- ▁leaves
- lin
- ▁obstructi
- ▁2000
- ▁pe
- ▁par
- broken
- rait
- ▁forever
- ▁win
- ▁trojans
- ▁pi
- ▁disorder
- ▁organism
- ▁neighbor
- ▁practice
- ▁locust
- ational
- ▁remove
- ▁week
- rov
- fu
- ▁meter
- ization
- ▁rid
- ▁schools
- ▁cap
- ▁cure
- istic
- over
- day
- ▁lov
- ▁tim
- ept
- uff
- ▁cho
- ▁accept
- ▁manag
- umb
- stand
- bodies
- face
- ▁deci
- ball
- ▁sens
- ▁surviv
- som
- ▁luck
- ▁cheap
- ▁happ
- ▁publi
- enome
- eign
- ▁shut
- ▁repeat
- ▁consist
- ▁prove
- hood
- ▁spirit
- sequence
- ▁confirm
- ▁persuad
- ▁promot
- precedent
- roach
- ▁amarjot
- ▁australia
- ▁beneath
- ▁bushmaster
- ▁channel
- ▁contrast
- ▁democra
- ▁devastat
- ▁diameter
- ▁discrimination
- ▁fragil
- ▁geothermal
- ▁guarantee
- ▁identify
- ▁innocent
- ▁leonardo
- ▁marriage
- ▁maximiz
- ▁mechanisms
- ▁monica
- ▁monitor
- ▁nutmeg
- ▁participant
- ▁pathogen
- ▁philosopher
- ▁piankhy
- ▁plague
- ▁possess
- ▁resolve
- ▁struggling
- ▁theranos
- ▁thrust
- ▁underground
- ▁vessel
- ▁violence
- ▁yeah
- ▁competitor
- ▁compress
- ▁establish
- ▁fashion
- ▁freetown
- ▁harness
- ▁obvious
- ▁purchas
- ▁random
- ▁smart
- ▁snoring
- ▁struggle
- ▁venom
- ▁video
- ▁healthcare
- ▁plenty
- ▁policymakers
- ▁sugar
- ▁regular
- ▁wife
- ▁earlier
- ▁tumor
- ▁encode
- ▁skill
- ▁dump
- ▁disparit
- ▁technique
- ▁brand
- ▁mouth
- ▁commercial
- ▁decisions
- ▁dense
- ▁details
- ▁calm
- ▁clay
- ▁excellen
- ▁scre
- ▁belarus
- ▁link
- ▁sweat
- ▁influence
- ▁license
- ▁media
- ▁allergi
- ▁tall
- ▁reveal
- ▁insects
- ▁brief
- meral
- ▁burrow
- ▁suspen
- ▁easily
- ▁excess
- ▁civilization
- ▁cloth
- ▁spectac
- ▁deploy
- ▁deny
- ▁wound
- ▁catastrophic
- rena
- ▁metric
- ▁industries
- ▁petrol
- ▁sunlight
- ▁flexible
- ▁flip
- ▁contract
- ▁breed
- ▁186
- ▁poop
- ▁khalil
- ▁divide
- ▁observations
- rope
- ffic
- ▁label
- ▁brig
- ▁agriculture
- ▁landscape
- ▁engage
- ▁trouble
- ▁reproduce
- ▁airway
- ▁intersecti
- ▁worry
- ▁char
- ▁authority
- ▁happiness
- ▁affordable
- ▁warsaw
- ▁gravity
- ▁identity
- aker
- ▁lifetime
- ▁everywhere
- ▁management
- ▁hunt
- ▁stem
- ▁gum
- ▁lone
- ▁squa
- ▁sew
- ▁coral
- ▁bio
- ▁clu
- ▁orient
- ▁honest
- ▁proper
- ▁emergenc
- ▁zoo
- ▁cor
- ▁factories
- ▁wings
- ▁tro
- eek
- ▁universal
- ▁experienc
- ▁circumstances
- ▁firefighters
- ▁cage
- ▁truck
- ▁span
- ▁diet
- ▁mile
- ▁rapidly
- ▁orang
- ▁stream
- ▁emotional
- ▁statistical
- ▁durable
- ▁gav
- ▁trip
- ▁mag
- ▁dispose
- ▁soft
- ▁equally
- ▁strike
- ▁directly
- ▁appli
- ddl
- ▁supernovae
- ender
- ▁writing
- ▁prop
- ference
- raw
- ▁earn
- ▁enable
- ▁foundation
- ely
- ▁devices
- ▁breathing
- ▁hell
- ▁serve
- ▁tool
- ▁resistan
- pr
- ▁magic
- ▁artist
- ▁samples
- ▁snakes
- ▁trials
- ▁poet
- ▁books
- ▁profits
- ▁ce
- take
- ▁assum
- ▁traveling
- ▁inf
- eum
- ▁disorders
- pan
- ably
- oid
- ▁desir
- ament
- ▁union
- ▁africans
- signed
- ▁spin
- ▁ro
- ▁protected
- ify
- pul
- ▁sites
- ▁vo
- ▁included
- ▁accelerat
- ▁birds
- ▁bird
- ▁mus
- ▁pit
- ▁write
- bble
- ▁ai
- ▁replac
- ▁desire
- alt
- ▁double
- ▁je
- umble
- ▁valu
- gd
- '23'
- ▁writ
- ▁book
- ▁sample
- ▁snake
- ▁object
- ▁ingredient
- ▁official
- ▁feature
- ▁brother
- ▁muscle
- ▁tower
- ▁gig
- ▁adult
- ▁generation
- ▁emission
- ▁wave
- '30'
- ▁conf
- ▁trial
- finite
- entle
- j
- gram
- ▁jan
- ike
- ▁fo
- posed
- ▁rem
- ▁leg
- ala
- strict
- think
- sleep
- ioniz
- mission
- ▁emotion
- ▁celebrate
- either
- ▁whi
- ▁compet
- ents
- ▁introduc
- ▁disrupt
- ▁collect
- ▁cit
- orba
- ipping
- ▁capita
- ▁govern
- reak
- ▁batter
- ▁arrang
- ▁belong
- ▁hollow
- ▁referr
- ▁suspect
- craft
- rogen
- ▁1970
- ▁architect
- ▁biontech
- ▁centuries
- ▁commitment
- ▁conduct
- ▁contradict
- ▁counterweight
- ▁dinner
- ▁disagree
- ▁display
- ▁disposal
- ▁distinct
- ▁employee
- ▁equator
- ▁eradicat
- ▁exercise
- ▁exoskeletons
- ▁expectancy
- ▁extrover
- ▁gestapo
- ▁hebrides
- ▁infectious
- ▁introver
- ▁journal
- ▁junajpu
- ▁louvre
- ▁nanostructure
- ▁overwhelm
- ▁phospholipid
- ▁physics
- ▁politician
- ▁practical
- ▁procedure
- ▁profess
- ▁pronouns
- ▁quarter
- ▁regime
- ▁reinforce
- ▁review
- ▁supplement
- ▁tempt
- ▁threshold
- ▁vegeta
- ▁violet
- ▁welcome
- ▁yellow
- ▁zegota
- ▁activat
- ▁ancestor
- ▁article
- ▁conquer
- ▁depart
- ▁email
- ▁herself
- ▁neuron
- ▁peak
- ▁psych
- ▁restoration
- ▁error
- ▁mystery
- ▁revenue
- ▁stunn
- ▁theoretical
- ▁household
- ▁notorious
- ▁scaling
- ▁erode
- ▁firm
- ▁frame
- ▁scene
- ▁evidentialis
- ▁freedom
- ▁title
- ▁desperate
- ▁migrat
- ▁select
- ▁summer
- ▁married
- ▁delta
- ▁shelter
- awatt
- ▁fresh
- ▁hidden
- ▁surgery
- ▁fluorescence
- ▁drain
- ▁kick
- ▁nearby
- ▁related
- ▁evad
- ▁bypass
- ▁colon
- ▁sperm
- ▁flore
- ▁begun
- ▁audience
- ▁rescue
- ▁empower
- proof
- ▁concept
- ▁creatures
- ▁museum
- ▁coordinat
- ▁intensive
- ▁diagnostic
- ▁rush
- ▁consumption
- ▁prohibit
- ▁hatch
- ▁vital
- ▁strand
- ▁persist
- tresse
- ▁missile
- ▁converg
- ▁importance
- ▁exploit
- ▁creativity
- ▁wedding
- ▁narrative
- ▁cliff
- ▁capitalism
- ▁surg
- ▁possibilities
- ▁understood
- foot
- ▁drink
- ▁persecution
- ▁sharp
- ▁flock
- courage
- ▁folk
- ▁refus
- ▁wow
- ▁noise
- ▁imagination
- ▁2021
- federa
- ▁remind
- ▁odd
- ▁extract
- ▁navigation
- ▁astronomy
- ▁illness
- ▁defi
- ▁version
- ▁impressive
- ▁systematic
- tamin
- ▁innovative
- minent
- ▁propos
- ▁resistance
- ▁shop
- ▁strait
- ▁horr
- ▁darkness
- ▁objective
- ▁father
- ound
- ▁restore
- ▁buff
- ▁restrict
- ▁excre
- ▁phone
- ▁mountain
- glad
- ▁pants
- ▁highway
- ▁announc
- ▁interconnected
- ▁hole
- ▁conditioners
- ▁pace
- ▁conscious
- ▁era
- ▁buttons
- ▁gain
- ▁lucky
- ▁barr
- ▁combine
- ▁dim
- ▁confus
- ient
- ▁packag
- ▁medication
- ▁career
- ▁board
- ▁bri
- ▁integrate
- ▁insisted
- arity
- ▁compete
- ▁plann
- immer
- ▁nest
- ▁strict
- ▁lesson
- rote
- ▁asia
- ▁band
- ▁complicated
- ▁constructed
- iment
- ▁hire
- fug
- ▁grat
- ▁closet
- roll
- ▁borders
- ▁monks
- rbag
- ▁protection
- ▁accepted
- ▁fal
- ▁26
- rated
- ▁deadly
- zer
- kay
- ▁investigat
- ▁advise
- eters
- ▁observing
- ski
- ▁prov
- ▁difficulty
- ▁improv
- ▁layer
- col
- ▁filmmak
- mad
- ▁grab
- ▁driver
- ▁meant
- ▁13
- alo
- '37'
- ▁unf
- ▁definit
- ▁burned
- cogni
- weigh
- ob
- lum
- ▁wash
- ▁profit
- obb
- ▁mono
- ▁appeared
- ▁interested
- ▁mess
- ▁comput
- ▁log
- ▁electro
- ▁meal
- ▁hid
- ▁reader
- ▁jo
- ctors
- ▁doubl
- top
- ▁ec
- ▁millennia
- ired
- urd
- gotten
- '80'
- ▁del
- eful
- ▁chris
- atic
- pur
- gar
- ▁pop
- ▁stra
- centri
- ▁spr
- comfortable
- ▁demonstrate
- fo
- ▁variet
- ▁pron
- bb
- ▁fertilize
- ▁figur
- arch
- pped
- ▁ensur
- ▁recogniz
- ls
- '20'
- ▁provid
- ▁explore
- '11'
- ▁achiev
- native
- late
- ried
- rts
- ▁160
- ▁500
- ▁ju
- ▁sali
- ▁character
- ▁35
- eeze
- ▁pen
- ▁assume
- '96'
- putation
- mph
- ▁sna
- ▁farm
- ▁fran
- eight
- ology
- ▁bond
- ▁parent
- ▁kilometer
- hal
- ▁resource
- bra
- ▁20000
- ▁serv
- ▁origin
- ▁advi
- ▁possib
- ▁historic
- place
- ification
- ▁strik
- rish
- ▁reduc
- tail
- ▁construct
- ▁pain
- ▁tip
- ▁complicat
- ▁gran
- ▁prime
- ▁substantial
- tag
- stream
- ▁conv
- front
- ▁rapid
- claim
- expect
- respond
- lord
- usual
- fall
- ▁brit
- point
- allow
- ▁exact
- ▁digit
- board
- tons
- ▁literal
- ▁install
- ▁innovat
- emed
- cti
- ▁lens
- ▁mari
- ▁epi
- ▁absor
- ▁subsidi
- ▁fell
- ▁hypothe
- ▁optim
- ▁constitut
- ▁defeat
- ▁diagonal
- ▁immunotherap
- ▁smooth
- bacteria
- ipples
- ologist
- ğ
- ▁1987
- ▁adjacent
- ▁advocate
- ▁anticipate
- ▁assistance
- ▁baby
- ▁beauty
- ▁calculat
- ▁candidate
- ▁challenging
- ▁champion
- ▁cholesterol
- ▁counterparts
- ▁crusade
- ▁curiosity
- ▁descend
- ▁destination
- ▁destruction
- ▁destructive
- ▁disappointment
- ▁dissolve
- ▁distinguish
- ▁empath
- ▁enjoy
- ▁equitabl
- ▁evaluat
- ▁export
- ▁ghetto
- ▁ghost
- ▁gradual
- ▁hospital
- ▁implement
- ▁inclusiv
- ▁inherit
- ▁intervention
- ▁laboratory
- ▁liquid
- ▁luxury
- ▁mercator
- ▁micah
- ▁miracle
- ▁nebula
- ▁nervous
- ▁neutral
- ▁olaf
- ▁opposite
- ▁participat
- ▁pesticide
- ▁puzzle
- ▁pyrethroid
- ▁rainforest
- ▁rattlesnake
- ▁rebuil
- ▁register
- ▁resolution
- ▁rognvald
- ▁secure
- ▁spectrum
- ▁statue
- ▁television
- ▁therapeutic
- ▁throat
- ▁vulture
- ▁wood
- phobia
- ▁abandon
- ▁accident
- ▁automatic
- ▁bucket
- ▁burden
- ▁competency
- ▁consult
- ▁equity
- ▁evaporat
- ▁interview
- ▁knowledge
- ▁legacy
- ▁legislat
- ▁mathematic
- ▁niger
- ▁plummet
- ▁taste
- ▁technical
- ▁transplant
- itarian
- ▁chronic
- ▁compell
- ▁crowd
- ▁empty
- ▁incarcer
- ▁misfir
- ▁poison
- ▁quantit
- ▁turb
- ▁victor
- ▁election
- ▁priorit
- ▁religio
- ▁snore
- defensi
- ▁bundle
- ▁carousel
- ▁climb
- ▁exhaust
- ▁fractur
- ▁garden
- ▁succeed
- ▁suez
- ▁hdpe
- ▁juice
- aguar
- ▁denim
- ▁dividing
- ▁fallacy
- ▁outcomes
- ▁plot
- ▁blind
- ▁shocked
- ▁bounc
- ▁depth
- incident
- ▁subtle
- ▁pump
- rcia
- ▁initiatives
- ▁spray
- ▁haunt
- ▁traverse
- ▁polish
- ▁hypothesis
- ▁voice
- ▁pledge
- ▁burst
- ▁uncle
- ▁sink
- sturb
- ▁anchor
- ▁gratitude
- ▁pause
- ▁quo
- ▁alert
- ▁vast
- ▁van
- ▁attitudes
- ▁grocer
- ▁countdown
- ▁decrease
- ▁extensi
- ▁invasion
- ▁therapi
- ▁instant
- ▁guy
- ▁forget
- ▁lawyer
- ▁reduction
- ▁strange
- ▁boom
- abul
- ▁season
- ▁begg
- ▁underwater
- ▁strategies
- ▁stimulate
- ▁hurt
- ▁alertness
- ▁utilit
- ▁tomb
- ▁elsewhere
- ▁leap
- ▁patch
- ▁preference
- ▁realistic
- ▁fold
- ▁medit
- ▁stair
- itzer
- ▁embr
- ▁addict
- ▁2015
- ▁percepti
- ▁reign
- ▁painful
- egal
- ▁respi
- ▁depriv
- ▁shutter
- ▁chemistry
- ▁sad
- ▁bias
- ▁boost
- ▁wake
- ▁workforce
- ▁varieties
- ▁repair
- ▁genome
- ▁reject
- ▁124
- slide
- ▁mobility
- ▁shade
- ▁medicine
- ▁vent
- ▁hyp
- ▁melt
- ▁cake
- ▁organized
- ▁novelty
- ▁distan
- ▁france
- ▁suck
- ▁parity
- ▁vision
- ▁voc
- ▁sufficient
- charged
- ▁calcine
- ensity
- ▁dart
- ▁collection
- ▁gun
- ▁rays
- ▁pour
- ▁bitter
- ▁funn
- ▁coff
- ▁fearless
- ▁stance
- ▁inner
- ▁retain
- ▁debt
- ▁chile
- fuse
- ▁partial
- ▁mold
- ▁substan
- ▁survival
- ▁seize
- ▁qui
- ▁installation
- ▁cup
- ruel
- ▁boss
- ▁plug
- ▁apartment
- ▁communicate
- ▁sacrifice
- ▁tapp
- ▁grass
- ▁italy
- ▁roy
- ▁squ
- ▁percentage
- ▁dots
- ▁absolutely
- ▁incentivize
- ▁reserve
- ▁navigate
- ▁creative
- viation
- ▁angle
- ▁deb
- ▁agent
- ▁isolat
- spiration
- ▁ramp
- ▁forgotten
- ▁extin
- ▁celebrated
- diff
- ▁substantially
- ▁viruses
- ▁por
- clos
- ▁comment
- ▁closest
- ▁fatal
- ▁triple
- olk
- ▁eliminate
- ▁facilit
- oster
- ▁geo
- erior
- ▁online
- ▁fung
- ▁insight
- ▁bull
- '79'
- ▁swapp
- ▁wipe
- rrow
- ▁historical
- ▁delivery
- hre
- ntine
- erson
- ▁former
- ▁original
- ▁cri
- ▁accura
- ▁bat
- ▁pave
- reci
- mma
- ▁generat
- rum
- decided
- ▁provider
- cell
- ▁intri
- izab
- neck
- ▁pur
- neu
- ▁stepp
- hoppers
- ▁hu
- ▁dye
- ▁chase
- '21'
- ▁impress
- hu
- ▁broke
- ▁obstruct
- ▁360
- ▁explor
- gue
- rate
- ▁controlle
- roc
- bru
- ecta
- ▁gui
- ▁rec
- qua
- ▁imagin
- ▁operat
- ▁fertiliz
- litar
- ▁hotte
- profitable
- ▁argu
- ▁150
- odes
- tify
- llus
- lets
- ▁terr
- poly
- ▁christ
- ctively
- ▁decarboniz
- scribe
- ▁electr
- ▁immigra
- ▁300
- ▁separat
- ▁hopp
- ▁rang
- employed
- mped
- '98'
- rail
- '97'
- ▁device
- ▁pun
- ▁belief
- ▁resident
- ▁pathway
- ▁egg
- ▁dollar
- ▁scientist
- ▁prim
- ▁reliabl
- igation
- ▁aud
- ▁fun
- maker
- ▁marr
- ▁afford
- ▁gro
- ashes
- urning
- ▁cycl
- ject
- ▁surpris
- ▁eliminat
- ▁disco
- ▁univers
- ▁receiv
- stead
- ▁critic
- mark
- ▁plea
- ▁absolute
- pair
- limited
- water
- truck
- sexual
- spread
- '35'
- bank
- virus
- imagine
- consider
- power
- down
- look
- more
- drive
- ▁communicat
- ▁prepare
- cott
- ▁insist
- fish
- ▁gri
- ▁tap
- ▁incentiv
- ▁distort
- ▁jani
- case
- ▁societ
- nounc
- ▁interact
- ▁syria
- ▁eas
- ▁frequen
- ▁significan
- ▁attac
- ▁populat
- ▁except
- ▁steriliz
- ▁cooperat
- ▁khali
- ▁appro
- ivity
- ▁danger
- ▁inform
- ▁stimul
- ▁quest
- ▁memori
- ▁import
- hibit
- stood
- ▁decre
- ▁influ
- rupt
- cense
- ippi
- ▁photosynthe
- augu
- criminat
- ▁biodivers
- ▁cardio
- ▁ridicul
- occupie
- sophisticated
- ▁absolutis
- ▁accused
- ▁afraid
- ▁algorithm
- ▁aristocra
- ▁assaulted
- ▁association
- ▁assyrian
- ▁atlantic
- ▁autonomy
- ▁availability
- ▁brutal
- ▁byproduct
- ▁ceremon
- ▁circle
- ▁conclusion
- ▁congress
- ▁consensus
- ▁diabetes
- ▁dimensional
- ▁diploma
- ▁disadvantage
- ▁disrespect
- ▁dragonfl
- ▁enzymes
- ▁epidemic
- ▁evolution
- ▁expense
- ▁eyebrows
- ▁fairbnb
- ▁follicle
- ▁fragment
- ▁gatekeeper
- ▁geography
- ▁ghrelin
- ▁gilgamesh
- ▁google
- ▁greece
- ▁gujarat
- ▁harvest
- ▁hurricane
- ▁inevitable
- ▁injustice
- ▁intelligen
- ▁ixbalanke
- ▁jetpack
- ▁judgment
- ▁livelihoods
- ▁longitude
- ▁margin
- ▁minimum
- ▁navy
- ▁necessarily
- ▁passenger
- ▁politics
- ▁prejudice
- ▁prospect
- ▁proximity
- ▁relieve
- ▁replicate
- ▁restaurant
- ▁scotland
- ▁senior
- ▁simultaneously
- ▁slot
- ▁stigma
- ▁supreme
- ▁sustainably
- ▁teenager
- ▁thirteen
- ▁thrill
- ▁tiger
- ▁tomorrow
- ▁toothpaste
- ▁tynwald
- ▁underneath
- ▁utilitarian
- ▁volunteer
- ▁vulnerability
- ▁alternate
- ▁assassinat
- ▁branche
- ▁categor
- ▁commute
- ▁defend
- ▁exclusive
- ▁feather
- ▁graduate
- ▁meticulous
- ▁perpetuat
- ▁resettle
- ▁segregat
- ▁treasur
- ▁violent
- ▁align
- ▁apparent
- ▁blades
- ▁competition
- ▁concert
- ▁counteract
- ▁daunting
- ▁debris
- ▁deficienc
- ▁disperse
- ▁england
- ▁fascinat
- ▁inflation
- ▁inhabit
- ▁irony
- ▁midwest
- ▁occasion
- ▁paddy
- ▁pioneer
- ▁praise
- ▁princes
- ▁resembl
- ▁roof
- ▁sensitive
- ▁territori
- ▁unfair
- rugg
- ▁coworkers
- ▁fruit
- ▁gasoline
- ▁impulse
- ▁lung
- ▁megawatt
- ▁palace
- ▁request
- ▁testimon
- ▁unfolding
- ▁yarn
- ▁bomb
- ▁crack
- ▁drastic
- ▁harsh
- ▁hometown
- ▁infected
- ▁john
- ▁minimize
- ▁properties
- ▁swift
- ▁pillar
- ▁endanger
- ▁flaw
- ▁relax
- ▁turk
- ▁admir
- ▁nuance
- ▁declare
- ▁guard
- ▁reunion
- ▁storytell
- ▁butterfl
- ▁scour
- ▁ribo
- ▁ferry
- ▁hacking
- ▁hydro
- ▁thread
- ▁convention
- ▁text
- ▁split
- ▁congest
- ▁translation
- ▁appreciat
- ratory
- ▁iceland
- ▁jaw
- ▁mistake
- ▁95
- programm
- ▁injure
- ▁explosive
- ▁spiritual
- ▁drill
- ▁typh
- ▁smell
- ▁latin
- ▁poem
- ▁asylum
- ▁crime
- ▁sail
- ▁appeal
- ▁guest
- ▁initial
- ▁peekabo
- ▁outlier
- mog
- ▁proud
- ▁bolt
- ▁spurr
- intuiti
- ▁cantilever
- ▁amani
- ▁genre
- ▁afar
- ▁rub
- ▁moistur
- ▁recover
- ▁items
- ▁optimistic
- ▁slippe
- ▁oversee
- ▁sara
- ▁illegal
- ▁rainwater
- ▁opposition
- ▁overnight
- ▁movie
- ▁explosion
- ▁intensity
- ▁linguistic
- ▁emulsi
- ▁radiation
- ▁violat
- morph
- ▁homo
- ▁spice
- ▁vibran
- ▁intact
- ▁rewards
- ▁exceed
- ▁viewpoint
- ▁heroes
- ▁repeatedly
- ▁confront
- rane
- ▁thre
- ▁squir
- ▁wrap
- ▁godred
- ▁orgy
- ▁sentence
- unci
- ▁memorize
- monia
- holder
- ▁quiet
- rpet
- ▁icon
- ▁spark
- ▁deforestation
- ▁nurs
- ▁1945
- ▁finger
- cade
- ▁efficac
- ▁haz
- ▁motivation
- ▁spotted
- ▁pitch
- ▁subsidize
- ▁intention
- ▁window
- ombi
- ▁swim
- ▁winter
- ▁dynami
- ▁executive
- ▁boil
- ▁assess
- ▁2018
- ▁failure
- ▁horse
- ▁enact
- utter
- ▁circulation
- ▁queen
- ▁distract
- flag
- ▁mentor
- ▁lick
- lank
- ▁ebo
- ▁dirt
- ▁remark
- ▁shake
- ▁entry
- frost
- ▁pear
- ▁bound
- ▁rif
- ▁performance
- ▁exception
- ▁189
- ▁straight
- ▁purp
- imeter
- ▁hills
- ▁chew
- scop
- ▁lamp
- ▁fog
- ▁sweet
- ▁cosm
- ▁mysteri
- rbit
- ▁dying
- ▁argument
- ▁intell
- ▁sultanate
- aire
- ▁tile
- ▁monoc
- ▁machinery
- ▁motion
- ▁infant
- ▁healthier
- ▁continuous
- ▁truce
- ▁undergo
- aboo
- ▁commanders
- ▁qualifi
- ▁55
- ▁anyway
- ▁lenses
- ▁offset
- ▁merg
- quent
- tari
- ▁chim
- ptin
- ▁exit
- ▁dash
- ▁meta
- ▁wish
- ▁poorest
- ▁distortion
- ▁interaction
- ▁proposal
- ▁reven
- ▁trace
- ▁perch
- ▁behav
- ▁disruption
- ▁progressive
- introduce
- ▁gall
- ▁stone
- ▁update
- descent
- ▁dance
- ▁polye
- ▁settle
- fellow
- ▁rob
- ▁stre
- ▁kan
- dominant
- ▁bro
- ▁ev
- ▁purif
- ▁agreement
- ▁dominate
- ▁regulation
- ▁improvement
- hase
- ▁ecolog
- hydr
- pical
- ▁conspi
- ▁inhale
- ▁arriv
- ▁fil
- ▁visitor
- ▁greenland
- phasi
- ▁farmer
- ▁cran
- ▁identifi
- ▁chose
- hau
- grega
- mps
- ▁characteriz
- ▁audi
- ▁oppress
- mination
- aint
- ▁determin
- ▁unemploy
- spire
- ▁giga
- ska
- ▁immigrat
- rank
- sport
- aft
- ▁snap
- emper
- equality
- ▁imp
- ▁terri
- ▁interv
- '19'
- hi
- icated
- ▁demonstrat
- kg
- gible
- ix
- grad
- pression
- '16'
- ▁pursu
- ▁hor
- ▁deli
- ▁spar
- ▁suc
- ▁millenni
- connected
- ▁leon
- ▁inspir
- ▁tho
- ▁faci
- ▁domin
- ▁resist
- ▁mobil
- ▁var
- eval
- ▁interfer
- abilities
- ▁enabl
- ▁border
- ▁forci
- ▁monk
- ▁eugenic
- gae
- ▁concern
- ▁fertil
- ▁mammal
- ▁iri
- ▁merc
- ▁blu
- gger
- ▁statistic
- ▁integr
- compa
- nown
- ▁navigat
- ▁amaz
- ▁reserv
- layer
- escription
- ▁angl
- ▁amplif
- force
- plug
- conscious
- compete
- mind
- leader
- honest
- load
- position
- root
- box
- speak
- flow
- complete
- drop
- check
- sustainable
- friend
- track
- game
- moral
- certain
- green
- world
- people
- life
- what
- about
- human
- wind
- suit
- pay
- minis
- ▁tradition
- ▁bloo
- ▁explo
- ▁strateg
- ▁circu
- ▁gravit
- ▁corporat
- ▁activit
- ▁inequalit
- ▁galax
- ▁calci
- ▁energ
- ▁identit
- ▁locat
- ▁que
- ford
- compromis
- ▁swee
- ▁constr
- imitation
- ▁matte
- zoo
- hwa
- ▁dyna
- ▁flexib
- ▁execut
- ▁renew
- ▁catastroph
- ▁deforest
- rink
- ▁auth
- ▁pub
- ▁marc
- ▁furthe
- ▁diagnos
- ecutive
- titude
- ▁compli
- gressive
- nprofit
- pute
- ▁nano
- oxide
- ▁evident
- ▁surp
- ▁arachn
- ▁hippoc
- nivores
- skeleton
- suppress
- thropo
- ü
- ▁accomplish
- ▁accusation
- ▁acknowledg
- ▁activists
- á
- î
- ç
- ö
- <sos/eos>
init: null
input_size: null
ctc_conf:
dropout_rate: 0.0
ctc_type: builtin
reduce: true
ignore_nan_grad: null
zero_infinity: true
brctc_risk_strategy: exp
brctc_group_strategy: end
brctc_risk_factor: 0.0
st_joint_net_conf: null
model_conf:
asr_weight: 0.3
mt_weight: 0.0
mtlalpha: 0.3
lsm_weight: 0.1
length_normalized_loss: false
use_preprocessor: true
token_type: bpe
src_token_type: bpe
bpemodel: data/en_bn_token_list/tgt_bpe_unigram4000/bpe.model
src_bpemodel: data/en_bn_token_list/src_bpe_unigram4000/bpe.model
non_linguistic_symbols: null
cleaner: null
g2p: null
src_g2p: null
speech_volume_normalize: null
rir_scp: null
rir_apply_prob: 1.0
noise_scp: null
noise_apply_prob: 1.0
noise_db_range: '13_15'
short_noise_thres: 0.5
ctc_sample_rate: 0.0
frontend: default
frontend_conf:
n_fft: 400
hop_length: 160
fs: 16k
specaug: specaug
specaug_conf:
apply_time_warp: true
time_warp_window: 5
time_warp_mode: bicubic
apply_freq_mask: true
freq_mask_width_range:
- 0
- 27
num_freq_mask: 2
apply_time_mask: true
time_mask_width_ratio_range:
- 0.0
- 0.05
num_time_mask: 5
normalize: utterance_mvn
normalize_conf: {}
preencoder: null
preencoder_conf: {}
encoder: conformer
encoder_conf:
output_size: 256
attention_heads: 4
linear_units: 2048
num_blocks: 12
dropout_rate: 0.1
positional_dropout_rate: 0.1
attention_dropout_rate: 0.1
input_layer: conv2d
normalize_before: true
macaron_style: true
rel_pos_type: latest
pos_enc_layer_type: rel_pos
selfattention_layer_type: rel_selfattn
activation_type: swish
use_cnn_module: true
cnn_module_kernel: 31
postencoder: null
postencoder_conf: {}
decoder: transformer
decoder_conf:
attention_heads: 4
linear_units: 2048
num_blocks: 6
dropout_rate: 0.1
positional_dropout_rate: 0.1
self_attention_dropout_rate: 0.1
src_attention_dropout_rate: 0.1
extra_asr_decoder: transformer
extra_asr_decoder_conf:
input_layer: embed
num_blocks: 6
linear_units: 2048
dropout_rate: 0.1
extra_mt_decoder: transformer
extra_mt_decoder_conf:
input_layer: embed
num_blocks: 2
linear_units: 2048
dropout_rate: 0.1
md_encoder: null
md_encoder_conf: {}
hier_encoder: null
hier_encoder_conf: {}
extra_mt_encoder: null
extra_mt_encoder_conf: {}
preprocessor: default
preprocessor_conf: {}
required:
- output_dir
- token_list
version: '202402'
distributed: false
```
</details>
### Citing ESPnet
```BibTex
@inproceedings{watanabe2018espnet,
author={Shinji Watanabe and Takaaki Hori and Shigeki Karita and Tomoki Hayashi and Jiro Nishitoba and Yuya Unno and Nelson Yalta and Jahn Heymann and Matthew Wiesner and Nanxin Chen and Adithya Renduchintala and Tsubasa Ochiai},
title={{ESPnet}: End-to-End Speech Processing Toolkit},
year={2018},
booktitle={Proceedings of Interspeech},
pages={2207--2211},
doi={10.21437/Interspeech.2018-1456},
url={http://dx.doi.org/10.21437/Interspeech.2018-1456}
}
```
or arXiv:
```bibtex
@misc{watanabe2018espnet,
title={ESPnet: End-to-End Speech Processing Toolkit},
author={Shinji Watanabe and Takaaki Hori and Shigeki Karita and Tomoki Hayashi and Jiro Nishitoba and Yuya Unno and Nelson Yalta and Jahn Heymann and Matthew Wiesner and Nanxin Chen and Adithya Renduchintala and Tsubasa Ochiai},
year={2018},
eprint={1804.00015},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
```
| {"language": ["en", "bn"], "license": "cc-by-4.0", "tags": ["espnet", "audio", "speech-translation"], "datasets": ["iwslt24_indic"]} | espnet/iwslt24_indic_en_ta_bpe_tc4000 | null | [
"espnet",
"audio",
"speech-translation",
"en",
"bn",
"dataset:iwslt24_indic",
"arxiv:1804.00015",
"license:cc-by-4.0",
"region:us"
] | null | 2024-04-19T17:56:11+00:00 | [
"1804.00015"
] | [
"en",
"bn"
] | TAGS
#espnet #audio #speech-translation #en #bn #dataset-iwslt24_indic #arxiv-1804.00015 #license-cc-by-4.0 #region-us
| ESPnet2 ST model
----------------
### 'espnet/iwslt24\_indic\_en\_ta\_bpe\_tc4000\_use\_wandbtrue'
This model was trained by cromz22 using iwslt24\_indic recipe in espnet.
### Demo: How to use in ESPnet2
Follow the ESPnet installation instructions
if you haven't done that already.
RESULTS
=======
Environments
------------
* date: 'Wed Apr 17 02:51:38 JST 2024'
* python version: '3.10.14 (main, Mar 21 2024, 16:24:04) [GCC 11.2.0]'
* espnet version: 'espnet 202402'
* pytorch version: 'pytorch 2.1.0'
* Git hash: '83c179ab842987cf01642df2db372aaae260df55'
+ Commit date: 'Wed Apr 17 00:28:29 2024 +0900'
st\_train\_st\_conformer\_raw\_en\_bn\_bpe\_tc4000
--------------------------------------------------
### BLEU
dataset: decode\_st\_conformer\_st\_model\_valid.URL (BP = 1.000 ratio = 1.185 hyp\_len = 46094 ref\_len = 38883), score: , verbose\_score:
ST config
---------
expand
### Citing ESPnet
or arXiv:
| [
"### 'espnet/iwslt24\\_indic\\_en\\_ta\\_bpe\\_tc4000\\_use\\_wandbtrue'\n\n\nThis model was trained by cromz22 using iwslt24\\_indic recipe in espnet.",
"### Demo: How to use in ESPnet2\n\n\nFollow the ESPnet installation instructions\nif you haven't done that already.\n\n\nRESULTS\n=======\n\n\nEnvironments\n------------\n\n\n* date: 'Wed Apr 17 02:51:38 JST 2024'\n* python version: '3.10.14 (main, Mar 21 2024, 16:24:04) [GCC 11.2.0]'\n* espnet version: 'espnet 202402'\n* pytorch version: 'pytorch 2.1.0'\n* Git hash: '83c179ab842987cf01642df2db372aaae260df55'\n\t+ Commit date: 'Wed Apr 17 00:28:29 2024 +0900'\n\n\nst\\_train\\_st\\_conformer\\_raw\\_en\\_bn\\_bpe\\_tc4000\n--------------------------------------------------",
"### BLEU\n\n\ndataset: decode\\_st\\_conformer\\_st\\_model\\_valid.URL (BP = 1.000 ratio = 1.185 hyp\\_len = 46094 ref\\_len = 38883), score: , verbose\\_score: \n\n\nST config\n---------\n\n\nexpand",
"### Citing ESPnet\n\n\nor arXiv:"
] | [
"TAGS\n#espnet #audio #speech-translation #en #bn #dataset-iwslt24_indic #arxiv-1804.00015 #license-cc-by-4.0 #region-us \n",
"### 'espnet/iwslt24\\_indic\\_en\\_ta\\_bpe\\_tc4000\\_use\\_wandbtrue'\n\n\nThis model was trained by cromz22 using iwslt24\\_indic recipe in espnet.",
"### Demo: How to use in ESPnet2\n\n\nFollow the ESPnet installation instructions\nif you haven't done that already.\n\n\nRESULTS\n=======\n\n\nEnvironments\n------------\n\n\n* date: 'Wed Apr 17 02:51:38 JST 2024'\n* python version: '3.10.14 (main, Mar 21 2024, 16:24:04) [GCC 11.2.0]'\n* espnet version: 'espnet 202402'\n* pytorch version: 'pytorch 2.1.0'\n* Git hash: '83c179ab842987cf01642df2db372aaae260df55'\n\t+ Commit date: 'Wed Apr 17 00:28:29 2024 +0900'\n\n\nst\\_train\\_st\\_conformer\\_raw\\_en\\_bn\\_bpe\\_tc4000\n--------------------------------------------------",
"### BLEU\n\n\ndataset: decode\\_st\\_conformer\\_st\\_model\\_valid.URL (BP = 1.000 ratio = 1.185 hyp\\_len = 46094 ref\\_len = 38883), score: , verbose\\_score: \n\n\nST config\n---------\n\n\nexpand",
"### Citing ESPnet\n\n\nor arXiv:"
] |
text-generation | null |
# Meta Llama 3 8B Instruct - llamafile
This repository contains executable weights (which we call
[llamafiles](https://github.com/Mozilla-Ocho/llamafile)) that run on
Linux, MacOS, Windows, FreeBSD, OpenBSD, and NetBSD for AMD64 and ARM64.
- Model creator: [Meta](https://llama.meta.com/)
- Original model: [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct)
## Quickstart
Running the following on a desktop OS will launch a tab in your web
browser with a chatbot interface.
```
chmod +x Meta-Llama-3-8B-Instruct.Q4_0.llamafile
./Meta-Llama-3-8B-Instruct.Q4_0.llamafile -ngl 9999
```
For further information, please see the [llamafile
README](https://github.com/mozilla-ocho/llamafile/).
Having **trouble?** See the ["Gotchas"
section](https://github.com/mozilla-ocho/llamafile/?tab=readme-ov-file#gotchas)
of the README.
## Prompting
Prompt template:
```
<|begin_of_text|><|start_header_id|>system<|end_header_id|>
{{prompt}}<|eot_id|>{{history}}<|start_header_id|>{{char}}<|end_header_id|>
```
History template:
```
<|start_header_id|>{{name}}<|end_header_id|>
{{message}}<|eot_id|>
```
## About llamafile
llamafile is a new format introduced by Mozilla Ocho on Nov 20th 2023.
It uses Cosmopolitan Libc to turn LLM weights into runnable llama.cpp
binaries that run on the stock installs of six OSes for both ARM64 and
AMD64.
## About Quantization Formats
Your choice of quantization format depends on three things:
1. Will it fit in RAM or VRAM?
2. Is your use case reading (e.g. summarization) or writing (e.g. chatbot)?
3. llamafiles bigger than 4.30 GB are hard to run on Windows (see [gotchas](https://github.com/mozilla-ocho/llamafile/?tab=readme-ov-file#gotchas))
Good quants for writing (eval speed) are Q5\_K\_M, and Q4\_0. Text
generation is bounded by memory speed, so smaller quants help, but they
also cause the LLM to hallucinate more.
Good quants for reading (prompt eval speed) are BF16, F16, Q4\_0, and
Q8\_0 (ordered from fastest to slowest). Prompt evaluation is bounded by
computation speed (flops) so simpler quants help.
Note: BF16 is currently only supported on CPU.
---
# Model Card
## Model Details
Meta developed and released the Meta Llama 3 family of large language models (LLMs), a collection of pretrained and instruction tuned generative text models in 8 and 70B sizes. The Llama 3 instruction tuned models are optimized for dialogue use cases and outperform many of the available open source chat models on common industry benchmarks. Further, in developing these models, we took great care to optimize helpfulness and safety.
**Model developers** Meta
**Variations** Llama 3 comes in two sizes — 8B and 70B parameters — in pre-trained and instruction tuned variants.
**Input** Models input text only.
**Output** Models generate text and code only.
**Model Architecture** Llama 3 is an auto-regressive language model that uses an optimized transformer architecture. The tuned versions use supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF) to align with human preferences for helpfulness and safety.
<table>
<tr>
<td>
</td>
<td><strong>Training Data</strong>
</td>
<td><strong>Params</strong>
</td>
<td><strong>Context length</strong>
</td>
<td><strong>GQA</strong>
</td>
<td><strong>Token count</strong>
</td>
<td><strong>Knowledge cutoff</strong>
</td>
</tr>
<tr>
<td rowspan="2" >Llama 3
</td>
<td rowspan="2" >A new mix of publicly available online data.
</td>
<td>8B
</td>
<td>8k
</td>
<td>Yes
</td>
<td rowspan="2" >15T+
</td>
<td>March, 2023
</td>
</tr>
<tr>
<td>70B
</td>
<td>8k
</td>
<td>Yes
</td>
<td>December, 2023
</td>
</tr>
</table>
**Llama 3 family of models**. Token counts refer to pretraining data only. Both the 8 and 70B versions use Grouped-Query Attention (GQA) for improved inference scalability.
**Model Release Date** April 18, 2024.
**Status** This is a static model trained on an offline dataset. Future versions of the tuned models will be released as we improve model safety with community feedback.
**License** A custom commercial license is available at: [https://llama.meta.com/llama3/license](https://llama.meta.com/llama3/license)
Where to send questions or comments about the model Instructions on how to provide feedback or comments on the model can be found in the model [README](https://github.com/meta-llama/llama3). For more technical information about generation parameters and recipes for how to use Llama 3 in applications, please go [here](https://github.com/meta-llama/llama-recipes).
## Intended Use
**Intended Use Cases** Llama 3 is intended for commercial and research use in English. Instruction tuned models are intended for assistant-like chat, whereas pretrained models can be adapted for a variety of natural language generation tasks.
**Out-of-scope** Use in any manner that violates applicable laws or regulations (including trade compliance laws). Use in any other way that is prohibited by the Acceptable Use Policy and Llama 3 Community License. Use in languages other than English**.
**Note: Developers may fine-tune Llama 3 models for languages beyond English provided they comply with the Llama 3 Community License and the Acceptable Use Policy.
## How to use
This repository contains two versions of Meta-Llama-3-8B-Instruct, for use with transformers and with the original `llama3` codebase.
### Use with transformers
You can run conversational inference using the Transformers pipeline abstraction, or by leveraging the Auto classes with the `generate()` function. Let's see examples of both.
#### Transformers pipeline
```python
import transformers
import torch
model_id = "meta-llama/Meta-Llama-3-8B-Instruct"
pipeline = transformers.pipeline(
"text-generation",
model=model_id,
model_kwargs={"torch_dtype": torch.bfloat16},
device="auto",
)
messages = [
{"role": "system", "content": "You are a pirate chatbot who always responds in pirate speak!"},
{"role": "user", "content": "Who are you?"},
]
prompt = pipeline.tokenizer.apply_chat_template(
messages,
tokenize=False,
add_generation_prompt=True
)
terminators = [
pipeline.tokenizer.eos_token_id,
pipeline.tokenizer.convert_tokens_to_ids("<|eot_id|>")
]
outputs = pipeline(
prompt,
max_new_tokens=256,
eos_token_id=terminators,
do_sample=True,
temperature=0.6,
top_p=0.9,
)
print(outputs[0]["generated_text"][len(prompt):])
```
#### Transformers AutoModelForCausalLM
```python
from transformers import AutoTokenizer, AutoModelForCausalLM
import torch
model_id = "meta-llama/Meta-Llama-3-8B-Instruct"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
model_id,
torch_dtype=torch.bfloat16,
device_map="auto",
)
messages = [
{"role": "system", "content": "You are a pirate chatbot who always responds in pirate speak!"},
{"role": "user", "content": "Who are you?"},
]
input_ids = tokenizer.apply_chat_template(
messages,
add_generation_prompt=True,
return_tensors="pt"
).to(model.device)
terminators = [
tokenizer.eos_token_id,
tokenizer.convert_tokens_to_ids("<|eot_id|>")
]
outputs = model.generate(
input_ids,
max_new_tokens=256,
eos_token_id=terminators,
do_sample=True,
temperature=0.6,
top_p=0.9,
)
response = outputs[0][input_ids.shape[-1]:]
print(tokenizer.decode(response, skip_special_tokens=True))
```
### Use with `llama3`
Please, follow the instructions in the [repository](https://github.com/meta-llama/llama3)
To download Original checkpoints, see the example command below leveraging `huggingface-cli`:
```
huggingface-cli download meta-llama/Meta-Llama-3-8B-Instruct --include "original/*" --local-dir Meta-Llama-3-8B-Instruct
```
For Hugging Face support, we recommend using transformers or TGI, but a similar command works.
## Hardware and Software
**Training Factors** We used custom training libraries, Meta's Research SuperCluster, and production clusters for pretraining. Fine-tuning, annotation, and evaluation were also performed on third-party cloud compute.
**Carbon Footprint Pretraining utilized a cumulative** 7.7M GPU hours of computation on hardware of type H100-80GB (TDP of 700W). Estimated total emissions were 2290 tCO2eq, 100% of which were offset by Meta’s sustainability program.
<table>
<tr>
<td>
</td>
<td><strong>Time (GPU hours)</strong>
</td>
<td><strong>Power Consumption (W)</strong>
</td>
<td><strong>Carbon Emitted(tCO2eq)</strong>
</td>
</tr>
<tr>
<td>Llama 3 8B
</td>
<td>1.3M
</td>
<td>700
</td>
<td>390
</td>
</tr>
<tr>
<td>Llama 3 70B
</td>
<td>6.4M
</td>
<td>700
</td>
<td>1900
</td>
</tr>
<tr>
<td>Total
</td>
<td>7.7M
</td>
<td>
</td>
<td>2290
</td>
</tr>
</table>
**CO2 emissions during pre-training**. Time: total GPU time required for training each model. Power Consumption: peak power capacity per GPU device for the GPUs used adjusted for power usage efficiency. 100% of the emissions are directly offset by Meta's sustainability program, and because we are openly releasing these models, the pretraining costs do not need to be incurred by others.
## Training Data
**Overview** Llama 3 was pretrained on over 15 trillion tokens of data from publicly available sources. The fine-tuning data includes publicly available instruction datasets, as well as over 10M human-annotated examples. Neither the pretraining nor the fine-tuning datasets include Meta user data.
**Data Freshness** The pretraining data has a cutoff of March 2023 for the 7B and December 2023 for the 70B models respectively.
## Benchmarks
In this section, we report the results for Llama 3 models on standard automatic benchmarks. For all the evaluations, we use our internal evaluations library. For details on the methodology see [here](https://github.com/meta-llama/llama3/blob/main/eval_methodology.md).
### Base pretrained models
<table>
<tr>
<td><strong>Category</strong>
</td>
<td><strong>Benchmark</strong>
</td>
<td><strong>Llama 3 8B</strong>
</td>
<td><strong>Llama2 7B</strong>
</td>
<td><strong>Llama2 13B</strong>
</td>
<td><strong>Llama 3 70B</strong>
</td>
<td><strong>Llama2 70B</strong>
</td>
</tr>
<tr>
<td rowspan="6" >General
</td>
<td>MMLU (5-shot)
</td>
<td>66.6
</td>
<td>45.7
</td>
<td>53.8
</td>
<td>79.5
</td>
<td>69.7
</td>
</tr>
<tr>
<td>AGIEval English (3-5 shot)
</td>
<td>45.9
</td>
<td>28.8
</td>
<td>38.7
</td>
<td>63.0
</td>
<td>54.8
</td>
</tr>
<tr>
<td>CommonSenseQA (7-shot)
</td>
<td>72.6
</td>
<td>57.6
</td>
<td>67.6
</td>
<td>83.8
</td>
<td>78.7
</td>
</tr>
<tr>
<td>Winogrande (5-shot)
</td>
<td>76.1
</td>
<td>73.3
</td>
<td>75.4
</td>
<td>83.1
</td>
<td>81.8
</td>
</tr>
<tr>
<td>BIG-Bench Hard (3-shot, CoT)
</td>
<td>61.1
</td>
<td>38.1
</td>
<td>47.0
</td>
<td>81.3
</td>
<td>65.7
</td>
</tr>
<tr>
<td>ARC-Challenge (25-shot)
</td>
<td>78.6
</td>
<td>53.7
</td>
<td>67.6
</td>
<td>93.0
</td>
<td>85.3
</td>
</tr>
<tr>
<td>Knowledge reasoning
</td>
<td>TriviaQA-Wiki (5-shot)
</td>
<td>78.5
</td>
<td>72.1
</td>
<td>79.6
</td>
<td>89.7
</td>
<td>87.5
</td>
</tr>
<tr>
<td rowspan="4" >Reading comprehension
</td>
<td>SQuAD (1-shot)
</td>
<td>76.4
</td>
<td>72.2
</td>
<td>72.1
</td>
<td>85.6
</td>
<td>82.6
</td>
</tr>
<tr>
<td>QuAC (1-shot, F1)
</td>
<td>44.4
</td>
<td>39.6
</td>
<td>44.9
</td>
<td>51.1
</td>
<td>49.4
</td>
</tr>
<tr>
<td>BoolQ (0-shot)
</td>
<td>75.7
</td>
<td>65.5
</td>
<td>66.9
</td>
<td>79.0
</td>
<td>73.1
</td>
</tr>
<tr>
<td>DROP (3-shot, F1)
</td>
<td>58.4
</td>
<td>37.9
</td>
<td>49.8
</td>
<td>79.7
</td>
<td>70.2
</td>
</tr>
</table>
### Instruction tuned models
<table>
<tr>
<td><strong>Benchmark</strong>
</td>
<td><strong>Llama 3 8B</strong>
</td>
<td><strong>Llama 2 7B</strong>
</td>
<td><strong>Llama 2 13B</strong>
</td>
<td><strong>Llama 3 70B</strong>
</td>
<td><strong>Llama 2 70B</strong>
</td>
</tr>
<tr>
<td>MMLU (5-shot)
</td>
<td>68.4
</td>
<td>34.1
</td>
<td>47.8
</td>
<td>82.0
</td>
<td>52.9
</td>
</tr>
<tr>
<td>GPQA (0-shot)
</td>
<td>34.2
</td>
<td>21.7
</td>
<td>22.3
</td>
<td>39.5
</td>
<td>21.0
</td>
</tr>
<tr>
<td>HumanEval (0-shot)
</td>
<td>62.2
</td>
<td>7.9
</td>
<td>14.0
</td>
<td>81.7
</td>
<td>25.6
</td>
</tr>
<tr>
<td>GSM-8K (8-shot, CoT)
</td>
<td>79.6
</td>
<td>25.7
</td>
<td>77.4
</td>
<td>93.0
</td>
<td>57.5
</td>
</tr>
<tr>
<td>MATH (4-shot, CoT)
</td>
<td>30.0
</td>
<td>3.8
</td>
<td>6.7
</td>
<td>50.4
</td>
<td>11.6
</td>
</tr>
</table>
### Responsibility & Safety
We believe that an open approach to AI leads to better, safer products, faster innovation, and a bigger overall market. We are committed to Responsible AI development and took a series of steps to limit misuse and harm and support the open source community.
Foundation models are widely capable technologies that are built to be used for a diverse range of applications. They are not designed to meet every developer preference on safety levels for all use cases, out-of-the-box, as those by their nature will differ across different applications.
Rather, responsible LLM-application deployment is achieved by implementing a series of safety best practices throughout the development of such applications, from the model pre-training, fine-tuning and the deployment of systems composed of safeguards to tailor the safety needs specifically to the use case and audience.
As part of the Llama 3 release, we updated our [Responsible Use Guide](https://llama.meta.com/responsible-use-guide/) to outline the steps and best practices for developers to implement model and system level safety for their application. We also provide a set of resources including [Meta Llama Guard 2](https://llama.meta.com/purple-llama/) and [Code Shield](https://llama.meta.com/purple-llama/) safeguards. These tools have proven to drastically reduce residual risks of LLM Systems, while maintaining a high level of helpfulness. We encourage developers to tune and deploy these safeguards according to their needs and we provide a [reference implementation](https://github.com/meta-llama/llama-recipes/tree/main/recipes/responsible_ai) to get you started.
#### Llama 3-Instruct
As outlined in the Responsible Use Guide, some trade-off between model helpfulness and model alignment is likely unavoidable. Developers should exercise discretion about how to weigh the benefits of alignment and helpfulness for their specific use case and audience. Developers should be mindful of residual risks when using Llama models and leverage additional safety tools as needed to reach the right safety bar for their use case.
<span style="text-decoration:underline;">Safety</span>
For our instruction tuned model, we conducted extensive red teaming exercises, performed adversarial evaluations and implemented safety mitigations techniques to lower residual risks. As with any Large Language Model, residual risks will likely remain and we recommend that developers assess these risks in the context of their use case. In parallel, we are working with the community to make AI safety benchmark standards transparent, rigorous and interpretable.
<span style="text-decoration:underline;">Refusals</span>
In addition to residual risks, we put a great emphasis on model refusals to benign prompts. Over-refusing not only can impact the user experience but could even be harmful in certain contexts as well. We’ve heard the feedback from the developer community and improved our fine tuning to ensure that Llama 3 is significantly less likely to falsely refuse to answer prompts than Llama 2.
We built internal benchmarks and developed mitigations to limit false refusals making Llama 3 our most helpful model to date.
#### Responsible release
In addition to responsible use considerations outlined above, we followed a rigorous process that requires us to take extra measures against misuse and critical risks before we make our release decision.
Misuse
If you access or use Llama 3, you agree to the Acceptable Use Policy. The most recent copy of this policy can be found at [https://llama.meta.com/llama3/use-policy/](https://llama.meta.com/llama3/use-policy/).
#### Critical risks
<span style="text-decoration:underline;">CBRNE</span> (Chemical, Biological, Radiological, Nuclear, and high yield Explosives)
We have conducted a two fold assessment of the safety of the model in this area:
* Iterative testing during model training to assess the safety of responses related to CBRNE threats and other adversarial risks.
* Involving external CBRNE experts to conduct an uplift test assessing the ability of the model to accurately provide expert knowledge and reduce barriers to potential CBRNE misuse, by reference to what can be achieved using web search (without the model).
### <span style="text-decoration:underline;">Cyber Security </span>
We have evaluated Llama 3 with CyberSecEval, Meta’s cybersecurity safety eval suite, measuring Llama 3’s propensity to suggest insecure code when used as a coding assistant, and Llama 3’s propensity to comply with requests to help carry out cyber attacks, where attacks are defined by the industry standard MITRE ATT&CK cyber attack ontology. On our insecure coding and cyber attacker helpfulness tests, Llama 3 behaved in the same range or safer than models of [equivalent coding capability](https://huggingface.co/spaces/facebook/CyberSecEval).
### <span style="text-decoration:underline;">Child Safety</span>
Child Safety risk assessments were conducted using a team of experts, to assess the model’s capability to produce outputs that could result in Child Safety risks and inform on any necessary and appropriate risk mitigations via fine tuning. We leveraged those expert red teaming sessions to expand the coverage of our evaluation benchmarks through Llama 3 model development. For Llama 3, we conducted new in-depth sessions using objective based methodologies to assess the model risks along multiple attack vectors. We also partnered with content specialists to perform red teaming exercises assessing potentially violating content while taking account of market specific nuances or experiences.
### Community
Generative AI safety requires expertise and tooling, and we believe in the strength of the open community to accelerate its progress. We are active members of open consortiums, including the AI Alliance, Partnership in AI and MLCommons, actively contributing to safety standardization and transparency. We encourage the community to adopt taxonomies like the MLCommons Proof of Concept evaluation to facilitate collaboration and transparency on safety and content evaluations. Our Purple Llama tools are open sourced for the community to use and widely distributed across ecosystem partners including cloud service providers. We encourage community contributions to our [Github repository](https://github.com/meta-llama/PurpleLlama).
Finally, we put in place a set of resources including an [output reporting mechanism](https://developers.facebook.com/llama_output_feedback) and [bug bounty program](https://www.facebook.com/whitehat) to continuously improve the Llama technology with the help of the community.
## Ethical Considerations and Limitations
The core values of Llama 3 are openness, inclusivity and helpfulness. It is meant to serve everyone, and to work for a wide range of use cases. It is thus designed to be accessible to people across many different backgrounds, experiences and perspectives. Llama 3 addresses users and their needs as they are, without insertion unnecessary judgment or normativity, while reflecting the understanding that even content that may appear problematic in some cases can serve valuable purposes in others. It respects the dignity and autonomy of all users, especially in terms of the values of free thought and expression that power innovation and progress.
But Llama 3 is a new technology, and like any new technology, there are risks associated with its use. Testing conducted to date has been in English, and has not covered, nor could it cover, all scenarios. For these reasons, as with all LLMs, Llama 3’s potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate, biased or other objectionable responses to user prompts. Therefore, before deploying any applications of Llama 3 models, developers should perform safety testing and tuning tailored to their specific applications of the model. As outlined in the Responsible Use Guide, we recommend incorporating [Purple Llama](https://github.com/facebookresearch/PurpleLlama) solutions into your workflows and specifically [Llama Guard](https://ai.meta.com/research/publications/llama-guard-llm-based-input-output-safeguard-for-human-ai-conversations/) which provides a base model to filter input and output prompts to layer system-level safety on top of model-level safety.
Please see the Responsible Use Guide available at [http://llama.meta.com/responsible-use-guide](http://llama.meta.com/responsible-use-guide)
## Citation instructions
@article{llama3modelcard,
title={Llama 3 Model Card},
author={AI@Meta},
year={2024},
url = {https://github.com/meta-llama/llama3/blob/main/MODEL_CARD.md}
}
## Contributors
Aaditya Singh; Aaron Grattafiori; Abhimanyu Dubey; Abhinav Jauhri; Abhinav Pandey; Abhishek Kadian; Adam Kelsey; Adi Gangidi; Ahmad Al-Dahle; Ahuva Goldstand; Aiesha Letman; Ajay Menon; Akhil Mathur; Alan Schelten; Alex Vaughan; Amy Yang; Andrei Lupu; Andres Alvarado; Andrew Gallagher; Andrew Gu; Andrew Ho; Andrew Poulton; Andrew Ryan; Angela Fan; Ankit Ramchandani; Anthony Hartshorn; Archi Mitra; Archie Sravankumar; Artem Korenev; Arun Rao; Ashley Gabriel; Ashwin Bharambe; Assaf Eisenman; Aston Zhang; Aurelien Rodriguez; Austen Gregerson; Ava Spataru; Baptiste Roziere; Ben Maurer; Benjamin Leonhardi; Bernie Huang; Bhargavi Paranjape; Bing Liu; Binh Tang; Bobbie Chern; Brani Stojkovic; Brian Fuller; Catalina Mejia Arenas; Chao Zhou; Charlotte Caucheteux; Chaya Nayak; Ching-Hsiang Chu; Chloe Bi; Chris Cai; Chris Cox; Chris Marra; Chris McConnell; Christian Keller; Christoph Feichtenhofer; Christophe Touret; Chunyang Wu; Corinne Wong; Cristian Canton Ferrer; Damien Allonsius; Daniel Kreymer; Daniel Haziza; Daniel Li; Danielle Pintz; Danny Livshits; Danny Wyatt; David Adkins; David Esiobu; David Xu; Davide Testuggine; Delia David; Devi Parikh; Dhruv Choudhary; Dhruv Mahajan; Diana Liskovich; Diego Garcia-Olano; Diego Perino; Dieuwke Hupkes; Dingkang Wang; Dustin Holland; Egor Lakomkin; Elina Lobanova; Xiaoqing Ellen Tan; Emily Dinan; Eric Smith; Erik Brinkman; Esteban Arcaute; Filip Radenovic; Firat Ozgenel; Francesco Caggioni; Frank Seide; Frank Zhang; Gabriel Synnaeve; Gabriella Schwarz; Gabrielle Lee; Gada Badeer; Georgia Anderson; Graeme Nail; Gregoire Mialon; Guan Pang; Guillem Cucurell; Hailey Nguyen; Hannah Korevaar; Hannah Wang; Haroun Habeeb; Harrison Rudolph; Henry Aspegren; Hu Xu; Hugo Touvron; Iga Kozlowska; Igor Molybog; Igor Tufanov; Iliyan Zarov; Imanol Arrieta Ibarra; Irina-Elena Veliche; Isabel Kloumann; Ishan Misra; Ivan Evtimov; Jacob Xu; Jade Copet; Jake Weissman; Jan Geffert; Jana Vranes; Japhet Asher; Jason Park; Jay Mahadeokar; Jean-Baptiste Gaya; Jeet Shah; Jelmer van der Linde; Jennifer Chan; Jenny Hong; Jenya Lee; Jeremy Fu; Jeremy Teboul; Jianfeng Chi; Jianyu Huang; Jie Wang; Jiecao Yu; Joanna Bitton; Joe Spisak; Joelle Pineau; Jon Carvill; Jongsoo Park; Joseph Rocca; Joshua Johnstun; Junteng Jia; Kalyan Vasuden Alwala; Kam Hou U; Kate Plawiak; Kartikeya Upasani; Kaushik Veeraraghavan; Ke Li; Kenneth Heafield; Kevin Stone; Khalid El-Arini; Krithika Iyer; Kshitiz Malik; Kuenley Chiu; Kunal Bhalla; Kyle Huang; Lakshya Garg; Lauren Rantala-Yeary; Laurens van der Maaten; Lawrence Chen; Leandro Silva; Lee Bell; Lei Zhang; Liang Tan; Louis Martin; Lovish Madaan; Luca Wehrstedt; Lukas Blecher; Luke de Oliveira; Madeline Muzzi; Madian Khabsa; Manav Avlani; Mannat Singh; Manohar Paluri; Mark Zuckerberg; Marcin Kardas; Martynas Mankus; Mathew Oldham; Mathieu Rita; Matthew Lennie; Maya Pavlova; Meghan Keneally; Melanie Kambadur; Mihir Patel; Mikayel Samvelyan; Mike Clark; Mike Lewis; Min Si; Mitesh Kumar Singh; Mo Metanat; Mona Hassan; Naman Goyal; Narjes Torabi; Nicolas Usunier; Nikolay Bashlykov; Nikolay Bogoychev; Niladri Chatterji; Ning Dong; Oliver Aobo Yang; Olivier Duchenne; Onur Celebi; Parth Parekh; Patrick Alrassy; Paul Saab; Pavan Balaji; Pedro Rittner; Pengchuan Zhang; Pengwei Li; Petar Vasic; Peter Weng; Polina Zvyagina; Prajjwal Bhargava; Pratik Dubal; Praveen Krishnan; Punit Singh Koura; Qing He; Rachel Rodriguez; Ragavan Srinivasan; Rahul Mitra; Ramon Calderer; Raymond Li; Robert Stojnic; Roberta Raileanu; Robin Battey; Rocky Wang; Rohit Girdhar; Rohit Patel; Romain Sauvestre; Ronnie Polidoro; Roshan Sumbaly; Ross Taylor; Ruan Silva; Rui Hou; Rui Wang; Russ Howes; Ruty Rinott; Saghar Hosseini; Sai Jayesh Bondu; Samyak Datta; Sanjay Singh; Sara Chugh; Sargun Dhillon; Satadru Pan; Sean Bell; Sergey Edunov; Shaoliang Nie; Sharan Narang; Sharath Raparthy; Shaun Lindsay; Sheng Feng; Sheng Shen; Shenghao Lin; Shiva Shankar; Shruti Bhosale; Shun Zhang; Simon Vandenhende; Sinong Wang; Seohyun Sonia Kim; Soumya Batra; Sten Sootla; Steve Kehoe; Suchin Gururangan; Sumit Gupta; Sunny Virk; Sydney Borodinsky; Tamar Glaser; Tamar Herman; Tamara Best; Tara Fowler; Thomas Georgiou; Thomas Scialom; Tianhe Li; Todor Mihaylov; Tong Xiao; Ujjwal Karn; Vedanuj Goswami; Vibhor Gupta; Vignesh Ramanathan; Viktor Kerkez; Vinay Satish Kumar; Vincent Gonguet; Vish Vogeti; Vlad Poenaru; Vlad Tiberiu Mihailescu; Vladan Petrovic; Vladimir Ivanov; Wei Li; Weiwei Chu; Wenhan Xiong; Wenyin Fu; Wes Bouaziz; Whitney Meers; Will Constable; Xavier Martinet; Xiaojian Wu; Xinbo Gao; Xinfeng Xie; Xuchao Jia; Yaelle Goldschlag; Yann LeCun; Yashesh Gaur; Yasmine Babaei; Ye Qi; Yenda Li; Yi Wen; Yiwen Song; Youngjin Nam; Yuchen Hao; Yuchen Zhang; Yun Wang; Yuning Mao; Yuzi He; Zacharie Delpierre Coudert; Zachary DeVito; Zahra Hankir; Zhaoduo Wen; Zheng Yan; Zhengxing Chen; Zhenyu Yang; Zoe Papakipos
| {"language": ["en"], "license": "other", "tags": ["llama", "llama-3", "llamafile"], "model_creator": "Meta", "quantized_by": "jartine", "base_model": "meta-llama/Meta-Llama-3-8B-Instruct", "pipeline_tag": "text-generation", "license_name": "llama3", "license_link": "LICENSE", "prompt_template": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n{{prompt}}<|eot_id|>{{history}}<|start_header_id|>{{char}}<|end_header_id|>\n", "history_template": "<|start_header_id|>{{name}}<|end_header_id|>\n{{message}}<|eot_id|>\n"} | jartine/Meta-Llama-3-8B-Instruct-llamafile | null | [
"llamafile",
"llama",
"llama-3",
"text-generation",
"en",
"base_model:meta-llama/Meta-Llama-3-8B-Instruct",
"license:other",
"region:us"
] | null | 2024-04-19T17:58:47+00:00 | [] | [
"en"
] | TAGS
#llamafile #llama #llama-3 #text-generation #en #base_model-meta-llama/Meta-Llama-3-8B-Instruct #license-other #region-us
| Meta Llama 3 8B Instruct - llamafile
====================================
This repository contains executable weights (which we call
llamafiles) that run on
Linux, MacOS, Windows, FreeBSD, OpenBSD, and NetBSD for AMD64 and ARM64.
* Model creator: Meta
* Original model: meta-llama/Meta-Llama-3-8B-Instruct
Quickstart
----------
Running the following on a desktop OS will launch a tab in your web
browser with a chatbot interface.
For further information, please see the llamafile
README.
Having trouble? See the "Gotchas"
section
of the README.
Prompting
---------
Prompt template:
History template:
About llamafile
---------------
llamafile is a new format introduced by Mozilla Ocho on Nov 20th 2023.
It uses Cosmopolitan Libc to turn LLM weights into runnable URL
binaries that run on the stock installs of six OSes for both ARM64 and
AMD64.
About Quantization Formats
--------------------------
Your choice of quantization format depends on three things:
1. Will it fit in RAM or VRAM?
2. Is your use case reading (e.g. summarization) or writing (e.g. chatbot)?
3. llamafiles bigger than 4.30 GB are hard to run on Windows (see gotchas)
Good quants for writing (eval speed) are Q5\_K\_M, and Q4\_0. Text
generation is bounded by memory speed, so smaller quants help, but they
also cause the LLM to hallucinate more.
Good quants for reading (prompt eval speed) are BF16, F16, Q4\_0, and
Q8\_0 (ordered from fastest to slowest). Prompt evaluation is bounded by
computation speed (flops) so simpler quants help.
Note: BF16 is currently only supported on CPU.
---
Model Card
==========
Model Details
-------------
Meta developed and released the Meta Llama 3 family of large language models (LLMs), a collection of pretrained and instruction tuned generative text models in 8 and 70B sizes. The Llama 3 instruction tuned models are optimized for dialogue use cases and outperform many of the available open source chat models on common industry benchmarks. Further, in developing these models, we took great care to optimize helpfulness and safety.
Model developers Meta
Variations Llama 3 comes in two sizes — 8B and 70B parameters — in pre-trained and instruction tuned variants.
Input Models input text only.
Output Models generate text and code only.
Model Architecture Llama 3 is an auto-regressive language model that uses an optimized transformer architecture. The tuned versions use supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF) to align with human preferences for helpfulness and safety.
Llama 3 family of models. Token counts refer to pretraining data only. Both the 8 and 70B versions use Grouped-Query Attention (GQA) for improved inference scalability.
Model Release Date April 18, 2024.
Status This is a static model trained on an offline dataset. Future versions of the tuned models will be released as we improve model safety with community feedback.
License A custom commercial license is available at: URL
Where to send questions or comments about the model Instructions on how to provide feedback or comments on the model can be found in the model README. For more technical information about generation parameters and recipes for how to use Llama 3 in applications, please go here.
Intended Use
------------
Intended Use Cases Llama 3 is intended for commercial and research use in English. Instruction tuned models are intended for assistant-like chat, whereas pretrained models can be adapted for a variety of natural language generation tasks.
Out-of-scope Use in any manner that violates applicable laws or regulations (including trade compliance laws). Use in any other way that is prohibited by the Acceptable Use Policy and Llama 3 Community License. Use in languages other than English.
Note: Developers may fine-tune Llama 3 models for languages beyond English provided they comply with the Llama 3 Community License and the Acceptable Use Policy.
How to use
----------
This repository contains two versions of Meta-Llama-3-8B-Instruct, for use with transformers and with the original 'llama3' codebase.
### Use with transformers
You can run conversational inference using the Transformers pipeline abstraction, or by leveraging the Auto classes with the 'generate()' function. Let's see examples of both.
#### Transformers pipeline
#### Transformers AutoModelForCausalLM
### Use with 'llama3'
Please, follow the instructions in the repository
To download Original checkpoints, see the example command below leveraging 'huggingface-cli':
For Hugging Face support, we recommend using transformers or TGI, but a similar command works.
Hardware and Software
---------------------
Training Factors We used custom training libraries, Meta's Research SuperCluster, and production clusters for pretraining. Fine-tuning, annotation, and evaluation were also performed on third-party cloud compute.
Carbon Footprint Pretraining utilized a cumulative 7.7M GPU hours of computation on hardware of type H100-80GB (TDP of 700W). Estimated total emissions were 2290 tCO2eq, 100% of which were offset by Meta’s sustainability program.
CO2 emissions during pre-training. Time: total GPU time required for training each model. Power Consumption: peak power capacity per GPU device for the GPUs used adjusted for power usage efficiency. 100% of the emissions are directly offset by Meta's sustainability program, and because we are openly releasing these models, the pretraining costs do not need to be incurred by others.
Training Data
-------------
Overview Llama 3 was pretrained on over 15 trillion tokens of data from publicly available sources. The fine-tuning data includes publicly available instruction datasets, as well as over 10M human-annotated examples. Neither the pretraining nor the fine-tuning datasets include Meta user data.
Data Freshness The pretraining data has a cutoff of March 2023 for the 7B and December 2023 for the 70B models respectively.
Benchmarks
----------
In this section, we report the results for Llama 3 models on standard automatic benchmarks. For all the evaluations, we use our internal evaluations library. For details on the methodology see here.
### Base pretrained models
### Instruction tuned models
### Responsibility & Safety
We believe that an open approach to AI leads to better, safer products, faster innovation, and a bigger overall market. We are committed to Responsible AI development and took a series of steps to limit misuse and harm and support the open source community.
Foundation models are widely capable technologies that are built to be used for a diverse range of applications. They are not designed to meet every developer preference on safety levels for all use cases, out-of-the-box, as those by their nature will differ across different applications.
Rather, responsible LLM-application deployment is achieved by implementing a series of safety best practices throughout the development of such applications, from the model pre-training, fine-tuning and the deployment of systems composed of safeguards to tailor the safety needs specifically to the use case and audience.
As part of the Llama 3 release, we updated our Responsible Use Guide to outline the steps and best practices for developers to implement model and system level safety for their application. We also provide a set of resources including Meta Llama Guard 2 and Code Shield safeguards. These tools have proven to drastically reduce residual risks of LLM Systems, while maintaining a high level of helpfulness. We encourage developers to tune and deploy these safeguards according to their needs and we provide a reference implementation to get you started.
#### Llama 3-Instruct
As outlined in the Responsible Use Guide, some trade-off between model helpfulness and model alignment is likely unavoidable. Developers should exercise discretion about how to weigh the benefits of alignment and helpfulness for their specific use case and audience. Developers should be mindful of residual risks when using Llama models and leverage additional safety tools as needed to reach the right safety bar for their use case.
Safety
For our instruction tuned model, we conducted extensive red teaming exercises, performed adversarial evaluations and implemented safety mitigations techniques to lower residual risks. As with any Large Language Model, residual risks will likely remain and we recommend that developers assess these risks in the context of their use case. In parallel, we are working with the community to make AI safety benchmark standards transparent, rigorous and interpretable.
Refusals
In addition to residual risks, we put a great emphasis on model refusals to benign prompts. Over-refusing not only can impact the user experience but could even be harmful in certain contexts as well. We’ve heard the feedback from the developer community and improved our fine tuning to ensure that Llama 3 is significantly less likely to falsely refuse to answer prompts than Llama 2.
We built internal benchmarks and developed mitigations to limit false refusals making Llama 3 our most helpful model to date.
#### Responsible release
In addition to responsible use considerations outlined above, we followed a rigorous process that requires us to take extra measures against misuse and critical risks before we make our release decision.
Misuse
If you access or use Llama 3, you agree to the Acceptable Use Policy. The most recent copy of this policy can be found at URL
#### Critical risks
CBRNE (Chemical, Biological, Radiological, Nuclear, and high yield Explosives)
We have conducted a two fold assessment of the safety of the model in this area:
* Iterative testing during model training to assess the safety of responses related to CBRNE threats and other adversarial risks.
* Involving external CBRNE experts to conduct an uplift test assessing the ability of the model to accurately provide expert knowledge and reduce barriers to potential CBRNE misuse, by reference to what can be achieved using web search (without the model).
### Cyber Security
We have evaluated Llama 3 with CyberSecEval, Meta’s cybersecurity safety eval suite, measuring Llama 3’s propensity to suggest insecure code when used as a coding assistant, and Llama 3’s propensity to comply with requests to help carry out cyber attacks, where attacks are defined by the industry standard MITRE ATT&CK cyber attack ontology. On our insecure coding and cyber attacker helpfulness tests, Llama 3 behaved in the same range or safer than models of equivalent coding capability.
### Child Safety
Child Safety risk assessments were conducted using a team of experts, to assess the model’s capability to produce outputs that could result in Child Safety risks and inform on any necessary and appropriate risk mitigations via fine tuning. We leveraged those expert red teaming sessions to expand the coverage of our evaluation benchmarks through Llama 3 model development. For Llama 3, we conducted new in-depth sessions using objective based methodologies to assess the model risks along multiple attack vectors. We also partnered with content specialists to perform red teaming exercises assessing potentially violating content while taking account of market specific nuances or experiences.
### Community
Generative AI safety requires expertise and tooling, and we believe in the strength of the open community to accelerate its progress. We are active members of open consortiums, including the AI Alliance, Partnership in AI and MLCommons, actively contributing to safety standardization and transparency. We encourage the community to adopt taxonomies like the MLCommons Proof of Concept evaluation to facilitate collaboration and transparency on safety and content evaluations. Our Purple Llama tools are open sourced for the community to use and widely distributed across ecosystem partners including cloud service providers. We encourage community contributions to our Github repository.
Finally, we put in place a set of resources including an output reporting mechanism and bug bounty program to continuously improve the Llama technology with the help of the community.
Ethical Considerations and Limitations
--------------------------------------
The core values of Llama 3 are openness, inclusivity and helpfulness. It is meant to serve everyone, and to work for a wide range of use cases. It is thus designed to be accessible to people across many different backgrounds, experiences and perspectives. Llama 3 addresses users and their needs as they are, without insertion unnecessary judgment or normativity, while reflecting the understanding that even content that may appear problematic in some cases can serve valuable purposes in others. It respects the dignity and autonomy of all users, especially in terms of the values of free thought and expression that power innovation and progress.
But Llama 3 is a new technology, and like any new technology, there are risks associated with its use. Testing conducted to date has been in English, and has not covered, nor could it cover, all scenarios. For these reasons, as with all LLMs, Llama 3’s potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate, biased or other objectionable responses to user prompts. Therefore, before deploying any applications of Llama 3 models, developers should perform safety testing and tuning tailored to their specific applications of the model. As outlined in the Responsible Use Guide, we recommend incorporating Purple Llama solutions into your workflows and specifically Llama Guard which provides a base model to filter input and output prompts to layer system-level safety on top of model-level safety.
Please see the Responsible Use Guide available at URL
instructions
@article{llama3modelcard,
title={Llama 3 Model Card},
author={AI@Meta},
year={2024},
url = {URL
}
Contributors
------------
Aaditya Singh; Aaron Grattafiori; Abhimanyu Dubey; Abhinav Jauhri; Abhinav Pandey; Abhishek Kadian; Adam Kelsey; Adi Gangidi; Ahmad Al-Dahle; Ahuva Goldstand; Aiesha Letman; Ajay Menon; Akhil Mathur; Alan Schelten; Alex Vaughan; Amy Yang; Andrei Lupu; Andres Alvarado; Andrew Gallagher; Andrew Gu; Andrew Ho; Andrew Poulton; Andrew Ryan; Angela Fan; Ankit Ramchandani; Anthony Hartshorn; Archi Mitra; Archie Sravankumar; Artem Korenev; Arun Rao; Ashley Gabriel; Ashwin Bharambe; Assaf Eisenman; Aston Zhang; Aurelien Rodriguez; Austen Gregerson; Ava Spataru; Baptiste Roziere; Ben Maurer; Benjamin Leonhardi; Bernie Huang; Bhargavi Paranjape; Bing Liu; Binh Tang; Bobbie Chern; Brani Stojkovic; Brian Fuller; Catalina Mejia Arenas; Chao Zhou; Charlotte Caucheteux; Chaya Nayak; Ching-Hsiang Chu; Chloe Bi; Chris Cai; Chris Cox; Chris Marra; Chris McConnell; Christian Keller; Christoph Feichtenhofer; Christophe Touret; Chunyang Wu; Corinne Wong; Cristian Canton Ferrer; Damien Allonsius; Daniel Kreymer; Daniel Haziza; Daniel Li; Danielle Pintz; Danny Livshits; Danny Wyatt; David Adkins; David Esiobu; David Xu; Davide Testuggine; Delia David; Devi Parikh; Dhruv Choudhary; Dhruv Mahajan; Diana Liskovich; Diego Garcia-Olano; Diego Perino; Dieuwke Hupkes; Dingkang Wang; Dustin Holland; Egor Lakomkin; Elina Lobanova; Xiaoqing Ellen Tan; Emily Dinan; Eric Smith; Erik Brinkman; Esteban Arcaute; Filip Radenovic; Firat Ozgenel; Francesco Caggioni; Frank Seide; Frank Zhang; Gabriel Synnaeve; Gabriella Schwarz; Gabrielle Lee; Gada Badeer; Georgia Anderson; Graeme Nail; Gregoire Mialon; Guan Pang; Guillem Cucurell; Hailey Nguyen; Hannah Korevaar; Hannah Wang; Haroun Habeeb; Harrison Rudolph; Henry Aspegren; Hu Xu; Hugo Touvron; Iga Kozlowska; Igor Molybog; Igor Tufanov; Iliyan Zarov; Imanol Arrieta Ibarra; Irina-Elena Veliche; Isabel Kloumann; Ishan Misra; Ivan Evtimov; Jacob Xu; Jade Copet; Jake Weissman; Jan Geffert; Jana Vranes; Japhet Asher; Jason Park; Jay Mahadeokar; Jean-Baptiste Gaya; Jeet Shah; Jelmer van der Linde; Jennifer Chan; Jenny Hong; Jenya Lee; Jeremy Fu; Jeremy Teboul; Jianfeng Chi; Jianyu Huang; Jie Wang; Jiecao Yu; Joanna Bitton; Joe Spisak; Joelle Pineau; Jon Carvill; Jongsoo Park; Joseph Rocca; Joshua Johnstun; Junteng Jia; Kalyan Vasuden Alwala; Kam Hou U; Kate Plawiak; Kartikeya Upasani; Kaushik Veeraraghavan; Ke Li; Kenneth Heafield; Kevin Stone; Khalid El-Arini; Krithika Iyer; Kshitiz Malik; Kuenley Chiu; Kunal Bhalla; Kyle Huang; Lakshya Garg; Lauren Rantala-Yeary; Laurens van der Maaten; Lawrence Chen; Leandro Silva; Lee Bell; Lei Zhang; Liang Tan; Louis Martin; Lovish Madaan; Luca Wehrstedt; Lukas Blecher; Luke de Oliveira; Madeline Muzzi; Madian Khabsa; Manav Avlani; Mannat Singh; Manohar Paluri; Mark Zuckerberg; Marcin Kardas; Martynas Mankus; Mathew Oldham; Mathieu Rita; Matthew Lennie; Maya Pavlova; Meghan Keneally; Melanie Kambadur; Mihir Patel; Mikayel Samvelyan; Mike Clark; Mike Lewis; Min Si; Mitesh Kumar Singh; Mo Metanat; Mona Hassan; Naman Goyal; Narjes Torabi; Nicolas Usunier; Nikolay Bashlykov; Nikolay Bogoychev; Niladri Chatterji; Ning Dong; Oliver Aobo Yang; Olivier Duchenne; Onur Celebi; Parth Parekh; Patrick Alrassy; Paul Saab; Pavan Balaji; Pedro Rittner; Pengchuan Zhang; Pengwei Li; Petar Vasic; Peter Weng; Polina Zvyagina; Prajjwal Bhargava; Pratik Dubal; Praveen Krishnan; Punit Singh Koura; Qing He; Rachel Rodriguez; Ragavan Srinivasan; Rahul Mitra; Ramon Calderer; Raymond Li; Robert Stojnic; Roberta Raileanu; Robin Battey; Rocky Wang; Rohit Girdhar; Rohit Patel; Romain Sauvestre; Ronnie Polidoro; Roshan Sumbaly; Ross Taylor; Ruan Silva; Rui Hou; Rui Wang; Russ Howes; Ruty Rinott; Saghar Hosseini; Sai Jayesh Bondu; Samyak Datta; Sanjay Singh; Sara Chugh; Sargun Dhillon; Satadru Pan; Sean Bell; Sergey Edunov; Shaoliang Nie; Sharan Narang; Sharath Raparthy; Shaun Lindsay; Sheng Feng; Sheng Shen; Shenghao Lin; Shiva Shankar; Shruti Bhosale; Shun Zhang; Simon Vandenhende; Sinong Wang; Seohyun Sonia Kim; Soumya Batra; Sten Sootla; Steve Kehoe; Suchin Gururangan; Sumit Gupta; Sunny Virk; Sydney Borodinsky; Tamar Glaser; Tamar Herman; Tamara Best; Tara Fowler; Thomas Georgiou; Thomas Scialom; Tianhe Li; Todor Mihaylov; Tong Xiao; Ujjwal Karn; Vedanuj Goswami; Vibhor Gupta; Vignesh Ramanathan; Viktor Kerkez; Vinay Satish Kumar; Vincent Gonguet; Vish Vogeti; Vlad Poenaru; Vlad Tiberiu Mihailescu; Vladan Petrovic; Vladimir Ivanov; Wei Li; Weiwei Chu; Wenhan Xiong; Wenyin Fu; Wes Bouaziz; Whitney Meers; Will Constable; Xavier Martinet; Xiaojian Wu; Xinbo Gao; Xinfeng Xie; Xuchao Jia; Yaelle Goldschlag; Yann LeCun; Yashesh Gaur; Yasmine Babaei; Ye Qi; Yenda Li; Yi Wen; Yiwen Song; Youngjin Nam; Yuchen Hao; Yuchen Zhang; Yun Wang; Yuning Mao; Yuzi He; Zacharie Delpierre Coudert; Zachary DeVito; Zahra Hankir; Zhaoduo Wen; Zheng Yan; Zhengxing Chen; Zhenyu Yang; Zoe Papakipos
| [
"### Use with transformers\n\n\nYou can run conversational inference using the Transformers pipeline abstraction, or by leveraging the Auto classes with the 'generate()' function. Let's see examples of both.",
"#### Transformers pipeline",
"#### Transformers AutoModelForCausalLM",
"### Use with 'llama3'\n\n\nPlease, follow the instructions in the repository\n\n\nTo download Original checkpoints, see the example command below leveraging 'huggingface-cli':\n\n\nFor Hugging Face support, we recommend using transformers or TGI, but a similar command works.\n\n\nHardware and Software\n---------------------\n\n\nTraining Factors We used custom training libraries, Meta's Research SuperCluster, and production clusters for pretraining. Fine-tuning, annotation, and evaluation were also performed on third-party cloud compute.\n\n\nCarbon Footprint Pretraining utilized a cumulative 7.7M GPU hours of computation on hardware of type H100-80GB (TDP of 700W). Estimated total emissions were 2290 tCO2eq, 100% of which were offset by Meta’s sustainability program.\n\n\n\nCO2 emissions during pre-training. Time: total GPU time required for training each model. Power Consumption: peak power capacity per GPU device for the GPUs used adjusted for power usage efficiency. 100% of the emissions are directly offset by Meta's sustainability program, and because we are openly releasing these models, the pretraining costs do not need to be incurred by others.\n\n\nTraining Data\n-------------\n\n\nOverview Llama 3 was pretrained on over 15 trillion tokens of data from publicly available sources. The fine-tuning data includes publicly available instruction datasets, as well as over 10M human-annotated examples. Neither the pretraining nor the fine-tuning datasets include Meta user data.\n\n\nData Freshness The pretraining data has a cutoff of March 2023 for the 7B and December 2023 for the 70B models respectively.\n\n\nBenchmarks\n----------\n\n\nIn this section, we report the results for Llama 3 models on standard automatic benchmarks. For all the evaluations, we use our internal evaluations library. For details on the methodology see here.",
"### Base pretrained models",
"### Instruction tuned models",
"### Responsibility & Safety\n\n\nWe believe that an open approach to AI leads to better, safer products, faster innovation, and a bigger overall market. We are committed to Responsible AI development and took a series of steps to limit misuse and harm and support the open source community.\n\n\nFoundation models are widely capable technologies that are built to be used for a diverse range of applications. They are not designed to meet every developer preference on safety levels for all use cases, out-of-the-box, as those by their nature will differ across different applications.\n\n\nRather, responsible LLM-application deployment is achieved by implementing a series of safety best practices throughout the development of such applications, from the model pre-training, fine-tuning and the deployment of systems composed of safeguards to tailor the safety needs specifically to the use case and audience.\n\n\nAs part of the Llama 3 release, we updated our Responsible Use Guide to outline the steps and best practices for developers to implement model and system level safety for their application. We also provide a set of resources including Meta Llama Guard 2 and Code Shield safeguards. These tools have proven to drastically reduce residual risks of LLM Systems, while maintaining a high level of helpfulness. We encourage developers to tune and deploy these safeguards according to their needs and we provide a reference implementation to get you started.",
"#### Llama 3-Instruct\n\n\nAs outlined in the Responsible Use Guide, some trade-off between model helpfulness and model alignment is likely unavoidable. Developers should exercise discretion about how to weigh the benefits of alignment and helpfulness for their specific use case and audience. Developers should be mindful of residual risks when using Llama models and leverage additional safety tools as needed to reach the right safety bar for their use case.\n\n\nSafety\n\n\nFor our instruction tuned model, we conducted extensive red teaming exercises, performed adversarial evaluations and implemented safety mitigations techniques to lower residual risks. As with any Large Language Model, residual risks will likely remain and we recommend that developers assess these risks in the context of their use case. In parallel, we are working with the community to make AI safety benchmark standards transparent, rigorous and interpretable.\n\n\nRefusals\n\n\nIn addition to residual risks, we put a great emphasis on model refusals to benign prompts. Over-refusing not only can impact the user experience but could even be harmful in certain contexts as well. We’ve heard the feedback from the developer community and improved our fine tuning to ensure that Llama 3 is significantly less likely to falsely refuse to answer prompts than Llama 2.\n\n\nWe built internal benchmarks and developed mitigations to limit false refusals making Llama 3 our most helpful model to date.",
"#### Responsible release\n\n\nIn addition to responsible use considerations outlined above, we followed a rigorous process that requires us to take extra measures against misuse and critical risks before we make our release decision.\n\n\nMisuse\n\n\nIf you access or use Llama 3, you agree to the Acceptable Use Policy. The most recent copy of this policy can be found at URL",
"#### Critical risks\n\n\nCBRNE (Chemical, Biological, Radiological, Nuclear, and high yield Explosives)\n\n\nWe have conducted a two fold assessment of the safety of the model in this area:\n\n\n* Iterative testing during model training to assess the safety of responses related to CBRNE threats and other adversarial risks.\n* Involving external CBRNE experts to conduct an uplift test assessing the ability of the model to accurately provide expert knowledge and reduce barriers to potential CBRNE misuse, by reference to what can be achieved using web search (without the model).",
"### Cyber Security\n\n\nWe have evaluated Llama 3 with CyberSecEval, Meta’s cybersecurity safety eval suite, measuring Llama 3’s propensity to suggest insecure code when used as a coding assistant, and Llama 3’s propensity to comply with requests to help carry out cyber attacks, where attacks are defined by the industry standard MITRE ATT&CK cyber attack ontology. On our insecure coding and cyber attacker helpfulness tests, Llama 3 behaved in the same range or safer than models of equivalent coding capability.",
"### Child Safety\n\n\nChild Safety risk assessments were conducted using a team of experts, to assess the model’s capability to produce outputs that could result in Child Safety risks and inform on any necessary and appropriate risk mitigations via fine tuning. We leveraged those expert red teaming sessions to expand the coverage of our evaluation benchmarks through Llama 3 model development. For Llama 3, we conducted new in-depth sessions using objective based methodologies to assess the model risks along multiple attack vectors. We also partnered with content specialists to perform red teaming exercises assessing potentially violating content while taking account of market specific nuances or experiences.",
"### Community\n\n\nGenerative AI safety requires expertise and tooling, and we believe in the strength of the open community to accelerate its progress. We are active members of open consortiums, including the AI Alliance, Partnership in AI and MLCommons, actively contributing to safety standardization and transparency. We encourage the community to adopt taxonomies like the MLCommons Proof of Concept evaluation to facilitate collaboration and transparency on safety and content evaluations. Our Purple Llama tools are open sourced for the community to use and widely distributed across ecosystem partners including cloud service providers. We encourage community contributions to our Github repository.\n\n\nFinally, we put in place a set of resources including an output reporting mechanism and bug bounty program to continuously improve the Llama technology with the help of the community.\n\n\nEthical Considerations and Limitations\n--------------------------------------\n\n\nThe core values of Llama 3 are openness, inclusivity and helpfulness. It is meant to serve everyone, and to work for a wide range of use cases. It is thus designed to be accessible to people across many different backgrounds, experiences and perspectives. Llama 3 addresses users and their needs as they are, without insertion unnecessary judgment or normativity, while reflecting the understanding that even content that may appear problematic in some cases can serve valuable purposes in others. It respects the dignity and autonomy of all users, especially in terms of the values of free thought and expression that power innovation and progress.\n\n\nBut Llama 3 is a new technology, and like any new technology, there are risks associated with its use. Testing conducted to date has been in English, and has not covered, nor could it cover, all scenarios. For these reasons, as with all LLMs, Llama 3’s potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate, biased or other objectionable responses to user prompts. Therefore, before deploying any applications of Llama 3 models, developers should perform safety testing and tuning tailored to their specific applications of the model. As outlined in the Responsible Use Guide, we recommend incorporating Purple Llama solutions into your workflows and specifically Llama Guard which provides a base model to filter input and output prompts to layer system-level safety on top of model-level safety.\n\n\nPlease see the Responsible Use Guide available at URL\n\n\ninstructions\n\n\n@article{llama3modelcard,\n\n\ntitle={Llama 3 Model Card},\n\n\nauthor={AI@Meta},\n\n\nyear={2024},\n\n\nurl = {URL\n\n\n}\n\n\nContributors\n------------\n\n\nAaditya Singh; Aaron Grattafiori; Abhimanyu Dubey; Abhinav Jauhri; Abhinav Pandey; Abhishek Kadian; Adam Kelsey; Adi Gangidi; Ahmad Al-Dahle; Ahuva Goldstand; Aiesha Letman; Ajay Menon; Akhil Mathur; Alan Schelten; Alex Vaughan; Amy Yang; Andrei Lupu; Andres Alvarado; Andrew Gallagher; Andrew Gu; Andrew Ho; Andrew Poulton; Andrew Ryan; Angela Fan; Ankit Ramchandani; Anthony Hartshorn; Archi Mitra; Archie Sravankumar; Artem Korenev; Arun Rao; Ashley Gabriel; Ashwin Bharambe; Assaf Eisenman; Aston Zhang; Aurelien Rodriguez; Austen Gregerson; Ava Spataru; Baptiste Roziere; Ben Maurer; Benjamin Leonhardi; Bernie Huang; Bhargavi Paranjape; Bing Liu; Binh Tang; Bobbie Chern; Brani Stojkovic; Brian Fuller; Catalina Mejia Arenas; Chao Zhou; Charlotte Caucheteux; Chaya Nayak; Ching-Hsiang Chu; Chloe Bi; Chris Cai; Chris Cox; Chris Marra; Chris McConnell; Christian Keller; Christoph Feichtenhofer; Christophe Touret; Chunyang Wu; Corinne Wong; Cristian Canton Ferrer; Damien Allonsius; Daniel Kreymer; Daniel Haziza; Daniel Li; Danielle Pintz; Danny Livshits; Danny Wyatt; David Adkins; David Esiobu; David Xu; Davide Testuggine; Delia David; Devi Parikh; Dhruv Choudhary; Dhruv Mahajan; Diana Liskovich; Diego Garcia-Olano; Diego Perino; Dieuwke Hupkes; Dingkang Wang; Dustin Holland; Egor Lakomkin; Elina Lobanova; Xiaoqing Ellen Tan; Emily Dinan; Eric Smith; Erik Brinkman; Esteban Arcaute; Filip Radenovic; Firat Ozgenel; Francesco Caggioni; Frank Seide; Frank Zhang; Gabriel Synnaeve; Gabriella Schwarz; Gabrielle Lee; Gada Badeer; Georgia Anderson; Graeme Nail; Gregoire Mialon; Guan Pang; Guillem Cucurell; Hailey Nguyen; Hannah Korevaar; Hannah Wang; Haroun Habeeb; Harrison Rudolph; Henry Aspegren; Hu Xu; Hugo Touvron; Iga Kozlowska; Igor Molybog; Igor Tufanov; Iliyan Zarov; Imanol Arrieta Ibarra; Irina-Elena Veliche; Isabel Kloumann; Ishan Misra; Ivan Evtimov; Jacob Xu; Jade Copet; Jake Weissman; Jan Geffert; Jana Vranes; Japhet Asher; Jason Park; Jay Mahadeokar; Jean-Baptiste Gaya; Jeet Shah; Jelmer van der Linde; Jennifer Chan; Jenny Hong; Jenya Lee; Jeremy Fu; Jeremy Teboul; Jianfeng Chi; Jianyu Huang; Jie Wang; Jiecao Yu; Joanna Bitton; Joe Spisak; Joelle Pineau; Jon Carvill; Jongsoo Park; Joseph Rocca; Joshua Johnstun; Junteng Jia; Kalyan Vasuden Alwala; Kam Hou U; Kate Plawiak; Kartikeya Upasani; Kaushik Veeraraghavan; Ke Li; Kenneth Heafield; Kevin Stone; Khalid El-Arini; Krithika Iyer; Kshitiz Malik; Kuenley Chiu; Kunal Bhalla; Kyle Huang; Lakshya Garg; Lauren Rantala-Yeary; Laurens van der Maaten; Lawrence Chen; Leandro Silva; Lee Bell; Lei Zhang; Liang Tan; Louis Martin; Lovish Madaan; Luca Wehrstedt; Lukas Blecher; Luke de Oliveira; Madeline Muzzi; Madian Khabsa; Manav Avlani; Mannat Singh; Manohar Paluri; Mark Zuckerberg; Marcin Kardas; Martynas Mankus; Mathew Oldham; Mathieu Rita; Matthew Lennie; Maya Pavlova; Meghan Keneally; Melanie Kambadur; Mihir Patel; Mikayel Samvelyan; Mike Clark; Mike Lewis; Min Si; Mitesh Kumar Singh; Mo Metanat; Mona Hassan; Naman Goyal; Narjes Torabi; Nicolas Usunier; Nikolay Bashlykov; Nikolay Bogoychev; Niladri Chatterji; Ning Dong; Oliver Aobo Yang; Olivier Duchenne; Onur Celebi; Parth Parekh; Patrick Alrassy; Paul Saab; Pavan Balaji; Pedro Rittner; Pengchuan Zhang; Pengwei Li; Petar Vasic; Peter Weng; Polina Zvyagina; Prajjwal Bhargava; Pratik Dubal; Praveen Krishnan; Punit Singh Koura; Qing He; Rachel Rodriguez; Ragavan Srinivasan; Rahul Mitra; Ramon Calderer; Raymond Li; Robert Stojnic; Roberta Raileanu; Robin Battey; Rocky Wang; Rohit Girdhar; Rohit Patel; Romain Sauvestre; Ronnie Polidoro; Roshan Sumbaly; Ross Taylor; Ruan Silva; Rui Hou; Rui Wang; Russ Howes; Ruty Rinott; Saghar Hosseini; Sai Jayesh Bondu; Samyak Datta; Sanjay Singh; Sara Chugh; Sargun Dhillon; Satadru Pan; Sean Bell; Sergey Edunov; Shaoliang Nie; Sharan Narang; Sharath Raparthy; Shaun Lindsay; Sheng Feng; Sheng Shen; Shenghao Lin; Shiva Shankar; Shruti Bhosale; Shun Zhang; Simon Vandenhende; Sinong Wang; Seohyun Sonia Kim; Soumya Batra; Sten Sootla; Steve Kehoe; Suchin Gururangan; Sumit Gupta; Sunny Virk; Sydney Borodinsky; Tamar Glaser; Tamar Herman; Tamara Best; Tara Fowler; Thomas Georgiou; Thomas Scialom; Tianhe Li; Todor Mihaylov; Tong Xiao; Ujjwal Karn; Vedanuj Goswami; Vibhor Gupta; Vignesh Ramanathan; Viktor Kerkez; Vinay Satish Kumar; Vincent Gonguet; Vish Vogeti; Vlad Poenaru; Vlad Tiberiu Mihailescu; Vladan Petrovic; Vladimir Ivanov; Wei Li; Weiwei Chu; Wenhan Xiong; Wenyin Fu; Wes Bouaziz; Whitney Meers; Will Constable; Xavier Martinet; Xiaojian Wu; Xinbo Gao; Xinfeng Xie; Xuchao Jia; Yaelle Goldschlag; Yann LeCun; Yashesh Gaur; Yasmine Babaei; Ye Qi; Yenda Li; Yi Wen; Yiwen Song; Youngjin Nam; Yuchen Hao; Yuchen Zhang; Yun Wang; Yuning Mao; Yuzi He; Zacharie Delpierre Coudert; Zachary DeVito; Zahra Hankir; Zhaoduo Wen; Zheng Yan; Zhengxing Chen; Zhenyu Yang; Zoe Papakipos"
] | [
"TAGS\n#llamafile #llama #llama-3 #text-generation #en #base_model-meta-llama/Meta-Llama-3-8B-Instruct #license-other #region-us \n",
"### Use with transformers\n\n\nYou can run conversational inference using the Transformers pipeline abstraction, or by leveraging the Auto classes with the 'generate()' function. Let's see examples of both.",
"#### Transformers pipeline",
"#### Transformers AutoModelForCausalLM",
"### Use with 'llama3'\n\n\nPlease, follow the instructions in the repository\n\n\nTo download Original checkpoints, see the example command below leveraging 'huggingface-cli':\n\n\nFor Hugging Face support, we recommend using transformers or TGI, but a similar command works.\n\n\nHardware and Software\n---------------------\n\n\nTraining Factors We used custom training libraries, Meta's Research SuperCluster, and production clusters for pretraining. Fine-tuning, annotation, and evaluation were also performed on third-party cloud compute.\n\n\nCarbon Footprint Pretraining utilized a cumulative 7.7M GPU hours of computation on hardware of type H100-80GB (TDP of 700W). Estimated total emissions were 2290 tCO2eq, 100% of which were offset by Meta’s sustainability program.\n\n\n\nCO2 emissions during pre-training. Time: total GPU time required for training each model. Power Consumption: peak power capacity per GPU device for the GPUs used adjusted for power usage efficiency. 100% of the emissions are directly offset by Meta's sustainability program, and because we are openly releasing these models, the pretraining costs do not need to be incurred by others.\n\n\nTraining Data\n-------------\n\n\nOverview Llama 3 was pretrained on over 15 trillion tokens of data from publicly available sources. The fine-tuning data includes publicly available instruction datasets, as well as over 10M human-annotated examples. Neither the pretraining nor the fine-tuning datasets include Meta user data.\n\n\nData Freshness The pretraining data has a cutoff of March 2023 for the 7B and December 2023 for the 70B models respectively.\n\n\nBenchmarks\n----------\n\n\nIn this section, we report the results for Llama 3 models on standard automatic benchmarks. For all the evaluations, we use our internal evaluations library. For details on the methodology see here.",
"### Base pretrained models",
"### Instruction tuned models",
"### Responsibility & Safety\n\n\nWe believe that an open approach to AI leads to better, safer products, faster innovation, and a bigger overall market. We are committed to Responsible AI development and took a series of steps to limit misuse and harm and support the open source community.\n\n\nFoundation models are widely capable technologies that are built to be used for a diverse range of applications. They are not designed to meet every developer preference on safety levels for all use cases, out-of-the-box, as those by their nature will differ across different applications.\n\n\nRather, responsible LLM-application deployment is achieved by implementing a series of safety best practices throughout the development of such applications, from the model pre-training, fine-tuning and the deployment of systems composed of safeguards to tailor the safety needs specifically to the use case and audience.\n\n\nAs part of the Llama 3 release, we updated our Responsible Use Guide to outline the steps and best practices for developers to implement model and system level safety for their application. We also provide a set of resources including Meta Llama Guard 2 and Code Shield safeguards. These tools have proven to drastically reduce residual risks of LLM Systems, while maintaining a high level of helpfulness. We encourage developers to tune and deploy these safeguards according to their needs and we provide a reference implementation to get you started.",
"#### Llama 3-Instruct\n\n\nAs outlined in the Responsible Use Guide, some trade-off between model helpfulness and model alignment is likely unavoidable. Developers should exercise discretion about how to weigh the benefits of alignment and helpfulness for their specific use case and audience. Developers should be mindful of residual risks when using Llama models and leverage additional safety tools as needed to reach the right safety bar for their use case.\n\n\nSafety\n\n\nFor our instruction tuned model, we conducted extensive red teaming exercises, performed adversarial evaluations and implemented safety mitigations techniques to lower residual risks. As with any Large Language Model, residual risks will likely remain and we recommend that developers assess these risks in the context of their use case. In parallel, we are working with the community to make AI safety benchmark standards transparent, rigorous and interpretable.\n\n\nRefusals\n\n\nIn addition to residual risks, we put a great emphasis on model refusals to benign prompts. Over-refusing not only can impact the user experience but could even be harmful in certain contexts as well. We’ve heard the feedback from the developer community and improved our fine tuning to ensure that Llama 3 is significantly less likely to falsely refuse to answer prompts than Llama 2.\n\n\nWe built internal benchmarks and developed mitigations to limit false refusals making Llama 3 our most helpful model to date.",
"#### Responsible release\n\n\nIn addition to responsible use considerations outlined above, we followed a rigorous process that requires us to take extra measures against misuse and critical risks before we make our release decision.\n\n\nMisuse\n\n\nIf you access or use Llama 3, you agree to the Acceptable Use Policy. The most recent copy of this policy can be found at URL",
"#### Critical risks\n\n\nCBRNE (Chemical, Biological, Radiological, Nuclear, and high yield Explosives)\n\n\nWe have conducted a two fold assessment of the safety of the model in this area:\n\n\n* Iterative testing during model training to assess the safety of responses related to CBRNE threats and other adversarial risks.\n* Involving external CBRNE experts to conduct an uplift test assessing the ability of the model to accurately provide expert knowledge and reduce barriers to potential CBRNE misuse, by reference to what can be achieved using web search (without the model).",
"### Cyber Security\n\n\nWe have evaluated Llama 3 with CyberSecEval, Meta’s cybersecurity safety eval suite, measuring Llama 3’s propensity to suggest insecure code when used as a coding assistant, and Llama 3’s propensity to comply with requests to help carry out cyber attacks, where attacks are defined by the industry standard MITRE ATT&CK cyber attack ontology. On our insecure coding and cyber attacker helpfulness tests, Llama 3 behaved in the same range or safer than models of equivalent coding capability.",
"### Child Safety\n\n\nChild Safety risk assessments were conducted using a team of experts, to assess the model’s capability to produce outputs that could result in Child Safety risks and inform on any necessary and appropriate risk mitigations via fine tuning. We leveraged those expert red teaming sessions to expand the coverage of our evaluation benchmarks through Llama 3 model development. For Llama 3, we conducted new in-depth sessions using objective based methodologies to assess the model risks along multiple attack vectors. We also partnered with content specialists to perform red teaming exercises assessing potentially violating content while taking account of market specific nuances or experiences.",
"### Community\n\n\nGenerative AI safety requires expertise and tooling, and we believe in the strength of the open community to accelerate its progress. We are active members of open consortiums, including the AI Alliance, Partnership in AI and MLCommons, actively contributing to safety standardization and transparency. We encourage the community to adopt taxonomies like the MLCommons Proof of Concept evaluation to facilitate collaboration and transparency on safety and content evaluations. Our Purple Llama tools are open sourced for the community to use and widely distributed across ecosystem partners including cloud service providers. We encourage community contributions to our Github repository.\n\n\nFinally, we put in place a set of resources including an output reporting mechanism and bug bounty program to continuously improve the Llama technology with the help of the community.\n\n\nEthical Considerations and Limitations\n--------------------------------------\n\n\nThe core values of Llama 3 are openness, inclusivity and helpfulness. It is meant to serve everyone, and to work for a wide range of use cases. It is thus designed to be accessible to people across many different backgrounds, experiences and perspectives. Llama 3 addresses users and their needs as they are, without insertion unnecessary judgment or normativity, while reflecting the understanding that even content that may appear problematic in some cases can serve valuable purposes in others. It respects the dignity and autonomy of all users, especially in terms of the values of free thought and expression that power innovation and progress.\n\n\nBut Llama 3 is a new technology, and like any new technology, there are risks associated with its use. Testing conducted to date has been in English, and has not covered, nor could it cover, all scenarios. For these reasons, as with all LLMs, Llama 3’s potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate, biased or other objectionable responses to user prompts. Therefore, before deploying any applications of Llama 3 models, developers should perform safety testing and tuning tailored to their specific applications of the model. As outlined in the Responsible Use Guide, we recommend incorporating Purple Llama solutions into your workflows and specifically Llama Guard which provides a base model to filter input and output prompts to layer system-level safety on top of model-level safety.\n\n\nPlease see the Responsible Use Guide available at URL\n\n\ninstructions\n\n\n@article{llama3modelcard,\n\n\ntitle={Llama 3 Model Card},\n\n\nauthor={AI@Meta},\n\n\nyear={2024},\n\n\nurl = {URL\n\n\n}\n\n\nContributors\n------------\n\n\nAaditya Singh; Aaron Grattafiori; Abhimanyu Dubey; Abhinav Jauhri; Abhinav Pandey; Abhishek Kadian; Adam Kelsey; Adi Gangidi; Ahmad Al-Dahle; Ahuva Goldstand; Aiesha Letman; Ajay Menon; Akhil Mathur; Alan Schelten; Alex Vaughan; Amy Yang; Andrei Lupu; Andres Alvarado; Andrew Gallagher; Andrew Gu; Andrew Ho; Andrew Poulton; Andrew Ryan; Angela Fan; Ankit Ramchandani; Anthony Hartshorn; Archi Mitra; Archie Sravankumar; Artem Korenev; Arun Rao; Ashley Gabriel; Ashwin Bharambe; Assaf Eisenman; Aston Zhang; Aurelien Rodriguez; Austen Gregerson; Ava Spataru; Baptiste Roziere; Ben Maurer; Benjamin Leonhardi; Bernie Huang; Bhargavi Paranjape; Bing Liu; Binh Tang; Bobbie Chern; Brani Stojkovic; Brian Fuller; Catalina Mejia Arenas; Chao Zhou; Charlotte Caucheteux; Chaya Nayak; Ching-Hsiang Chu; Chloe Bi; Chris Cai; Chris Cox; Chris Marra; Chris McConnell; Christian Keller; Christoph Feichtenhofer; Christophe Touret; Chunyang Wu; Corinne Wong; Cristian Canton Ferrer; Damien Allonsius; Daniel Kreymer; Daniel Haziza; Daniel Li; Danielle Pintz; Danny Livshits; Danny Wyatt; David Adkins; David Esiobu; David Xu; Davide Testuggine; Delia David; Devi Parikh; Dhruv Choudhary; Dhruv Mahajan; Diana Liskovich; Diego Garcia-Olano; Diego Perino; Dieuwke Hupkes; Dingkang Wang; Dustin Holland; Egor Lakomkin; Elina Lobanova; Xiaoqing Ellen Tan; Emily Dinan; Eric Smith; Erik Brinkman; Esteban Arcaute; Filip Radenovic; Firat Ozgenel; Francesco Caggioni; Frank Seide; Frank Zhang; Gabriel Synnaeve; Gabriella Schwarz; Gabrielle Lee; Gada Badeer; Georgia Anderson; Graeme Nail; Gregoire Mialon; Guan Pang; Guillem Cucurell; Hailey Nguyen; Hannah Korevaar; Hannah Wang; Haroun Habeeb; Harrison Rudolph; Henry Aspegren; Hu Xu; Hugo Touvron; Iga Kozlowska; Igor Molybog; Igor Tufanov; Iliyan Zarov; Imanol Arrieta Ibarra; Irina-Elena Veliche; Isabel Kloumann; Ishan Misra; Ivan Evtimov; Jacob Xu; Jade Copet; Jake Weissman; Jan Geffert; Jana Vranes; Japhet Asher; Jason Park; Jay Mahadeokar; Jean-Baptiste Gaya; Jeet Shah; Jelmer van der Linde; Jennifer Chan; Jenny Hong; Jenya Lee; Jeremy Fu; Jeremy Teboul; Jianfeng Chi; Jianyu Huang; Jie Wang; Jiecao Yu; Joanna Bitton; Joe Spisak; Joelle Pineau; Jon Carvill; Jongsoo Park; Joseph Rocca; Joshua Johnstun; Junteng Jia; Kalyan Vasuden Alwala; Kam Hou U; Kate Plawiak; Kartikeya Upasani; Kaushik Veeraraghavan; Ke Li; Kenneth Heafield; Kevin Stone; Khalid El-Arini; Krithika Iyer; Kshitiz Malik; Kuenley Chiu; Kunal Bhalla; Kyle Huang; Lakshya Garg; Lauren Rantala-Yeary; Laurens van der Maaten; Lawrence Chen; Leandro Silva; Lee Bell; Lei Zhang; Liang Tan; Louis Martin; Lovish Madaan; Luca Wehrstedt; Lukas Blecher; Luke de Oliveira; Madeline Muzzi; Madian Khabsa; Manav Avlani; Mannat Singh; Manohar Paluri; Mark Zuckerberg; Marcin Kardas; Martynas Mankus; Mathew Oldham; Mathieu Rita; Matthew Lennie; Maya Pavlova; Meghan Keneally; Melanie Kambadur; Mihir Patel; Mikayel Samvelyan; Mike Clark; Mike Lewis; Min Si; Mitesh Kumar Singh; Mo Metanat; Mona Hassan; Naman Goyal; Narjes Torabi; Nicolas Usunier; Nikolay Bashlykov; Nikolay Bogoychev; Niladri Chatterji; Ning Dong; Oliver Aobo Yang; Olivier Duchenne; Onur Celebi; Parth Parekh; Patrick Alrassy; Paul Saab; Pavan Balaji; Pedro Rittner; Pengchuan Zhang; Pengwei Li; Petar Vasic; Peter Weng; Polina Zvyagina; Prajjwal Bhargava; Pratik Dubal; Praveen Krishnan; Punit Singh Koura; Qing He; Rachel Rodriguez; Ragavan Srinivasan; Rahul Mitra; Ramon Calderer; Raymond Li; Robert Stojnic; Roberta Raileanu; Robin Battey; Rocky Wang; Rohit Girdhar; Rohit Patel; Romain Sauvestre; Ronnie Polidoro; Roshan Sumbaly; Ross Taylor; Ruan Silva; Rui Hou; Rui Wang; Russ Howes; Ruty Rinott; Saghar Hosseini; Sai Jayesh Bondu; Samyak Datta; Sanjay Singh; Sara Chugh; Sargun Dhillon; Satadru Pan; Sean Bell; Sergey Edunov; Shaoliang Nie; Sharan Narang; Sharath Raparthy; Shaun Lindsay; Sheng Feng; Sheng Shen; Shenghao Lin; Shiva Shankar; Shruti Bhosale; Shun Zhang; Simon Vandenhende; Sinong Wang; Seohyun Sonia Kim; Soumya Batra; Sten Sootla; Steve Kehoe; Suchin Gururangan; Sumit Gupta; Sunny Virk; Sydney Borodinsky; Tamar Glaser; Tamar Herman; Tamara Best; Tara Fowler; Thomas Georgiou; Thomas Scialom; Tianhe Li; Todor Mihaylov; Tong Xiao; Ujjwal Karn; Vedanuj Goswami; Vibhor Gupta; Vignesh Ramanathan; Viktor Kerkez; Vinay Satish Kumar; Vincent Gonguet; Vish Vogeti; Vlad Poenaru; Vlad Tiberiu Mihailescu; Vladan Petrovic; Vladimir Ivanov; Wei Li; Weiwei Chu; Wenhan Xiong; Wenyin Fu; Wes Bouaziz; Whitney Meers; Will Constable; Xavier Martinet; Xiaojian Wu; Xinbo Gao; Xinfeng Xie; Xuchao Jia; Yaelle Goldschlag; Yann LeCun; Yashesh Gaur; Yasmine Babaei; Ye Qi; Yenda Li; Yi Wen; Yiwen Song; Youngjin Nam; Yuchen Hao; Yuchen Zhang; Yun Wang; Yuning Mao; Yuzi He; Zacharie Delpierre Coudert; Zachary DeVito; Zahra Hankir; Zhaoduo Wen; Zheng Yan; Zhengxing Chen; Zhenyu Yang; Zoe Papakipos"
] |
null | transformers | ## About
<!-- ### quantize_version: 1 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: -->
<!-- ### vocab_type: -->
weighted/imatrix quants of https://huggingface.co/Sao10K/Skadi-Mixtral-v1
<!-- provided-files -->
static quants are available at https://huggingface.co/mradermacher/Skadi-Mixtral-v1-GGUF
## Usage
If you are unsure how to use GGUF files, refer to one of [TheBloke's
READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
more details, including on how to concatenate multi-part files.
## Provided Quants
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
| Link | Type | Size/GB | Notes |
|:-----|:-----|--------:|:------|
| [GGUF](https://huggingface.co/mradermacher/Skadi-Mixtral-v1-i1-GGUF/resolve/main/Skadi-Mixtral-v1.i1-IQ1_S.gguf) | i1-IQ1_S | 9.9 | for the desperate |
| [GGUF](https://huggingface.co/mradermacher/Skadi-Mixtral-v1-i1-GGUF/resolve/main/Skadi-Mixtral-v1.i1-IQ1_M.gguf) | i1-IQ1_M | 10.9 | for the desperate |
| [GGUF](https://huggingface.co/mradermacher/Skadi-Mixtral-v1-i1-GGUF/resolve/main/Skadi-Mixtral-v1.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 12.7 | |
| [GGUF](https://huggingface.co/mradermacher/Skadi-Mixtral-v1-i1-GGUF/resolve/main/Skadi-Mixtral-v1.i1-IQ2_XS.gguf) | i1-IQ2_XS | 14.0 | |
| [GGUF](https://huggingface.co/mradermacher/Skadi-Mixtral-v1-i1-GGUF/resolve/main/Skadi-Mixtral-v1.i1-IQ2_S.gguf) | i1-IQ2_S | 14.2 | |
| [GGUF](https://huggingface.co/mradermacher/Skadi-Mixtral-v1-i1-GGUF/resolve/main/Skadi-Mixtral-v1.i1-IQ2_M.gguf) | i1-IQ2_M | 15.6 | |
| [GGUF](https://huggingface.co/mradermacher/Skadi-Mixtral-v1-i1-GGUF/resolve/main/Skadi-Mixtral-v1.i1-Q2_K.gguf) | i1-Q2_K | 17.4 | IQ3_XXS probably better |
| [GGUF](https://huggingface.co/mradermacher/Skadi-Mixtral-v1-i1-GGUF/resolve/main/Skadi-Mixtral-v1.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 18.3 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/Skadi-Mixtral-v1-i1-GGUF/resolve/main/Skadi-Mixtral-v1.i1-IQ3_XS.gguf) | i1-IQ3_XS | 19.5 | |
| [GGUF](https://huggingface.co/mradermacher/Skadi-Mixtral-v1-i1-GGUF/resolve/main/Skadi-Mixtral-v1.i1-IQ3_S.gguf) | i1-IQ3_S | 20.5 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/Skadi-Mixtral-v1-i1-GGUF/resolve/main/Skadi-Mixtral-v1.i1-Q3_K_S.gguf) | i1-Q3_K_S | 20.5 | IQ3_XS probably better |
| [GGUF](https://huggingface.co/mradermacher/Skadi-Mixtral-v1-i1-GGUF/resolve/main/Skadi-Mixtral-v1.i1-IQ3_M.gguf) | i1-IQ3_M | 21.5 | |
| [GGUF](https://huggingface.co/mradermacher/Skadi-Mixtral-v1-i1-GGUF/resolve/main/Skadi-Mixtral-v1.i1-Q3_K_M.gguf) | i1-Q3_K_M | 22.6 | IQ3_S probably better |
| [GGUF](https://huggingface.co/mradermacher/Skadi-Mixtral-v1-i1-GGUF/resolve/main/Skadi-Mixtral-v1.i1-Q3_K_L.gguf) | i1-Q3_K_L | 24.3 | IQ3_M probably better |
| [GGUF](https://huggingface.co/mradermacher/Skadi-Mixtral-v1-i1-GGUF/resolve/main/Skadi-Mixtral-v1.i1-IQ4_XS.gguf) | i1-IQ4_XS | 25.2 | |
| [GGUF](https://huggingface.co/mradermacher/Skadi-Mixtral-v1-i1-GGUF/resolve/main/Skadi-Mixtral-v1.i1-Q4_0.gguf) | i1-Q4_0 | 26.7 | fast, low quality |
| [GGUF](https://huggingface.co/mradermacher/Skadi-Mixtral-v1-i1-GGUF/resolve/main/Skadi-Mixtral-v1.i1-Q4_K_S.gguf) | i1-Q4_K_S | 26.8 | optimal size/speed/quality |
| [GGUF](https://huggingface.co/mradermacher/Skadi-Mixtral-v1-i1-GGUF/resolve/main/Skadi-Mixtral-v1.i1-Q4_K_M.gguf) | i1-Q4_K_M | 28.5 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Skadi-Mixtral-v1-i1-GGUF/resolve/main/Skadi-Mixtral-v1.i1-Q5_K_S.gguf) | i1-Q5_K_S | 32.3 | |
| [GGUF](https://huggingface.co/mradermacher/Skadi-Mixtral-v1-i1-GGUF/resolve/main/Skadi-Mixtral-v1.i1-Q5_K_M.gguf) | i1-Q5_K_M | 33.3 | |
| [GGUF](https://huggingface.co/mradermacher/Skadi-Mixtral-v1-i1-GGUF/resolve/main/Skadi-Mixtral-v1.i1-Q6_K.gguf) | i1-Q6_K | 38.5 | practically like static Q6_K |
Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):
And here are Artefact2's thoughts on the matter:
https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
## FAQ / Model Request
See https://huggingface.co/mradermacher/model_requests for some answers to
questions you might have and/or if you want some other model quantized.
## Thanks
I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
me use its servers and providing upgrades to my workstation to enable
this work in my free time.
<!-- end -->
| {"language": ["en"], "license": "cc-by-nc-4.0", "library_name": "transformers", "tags": ["merge"], "base_model": "Sao10K/Skadi-Mixtral-v1", "quantized_by": "mradermacher"} | mradermacher/Skadi-Mixtral-v1-i1-GGUF | null | [
"transformers",
"gguf",
"merge",
"en",
"base_model:Sao10K/Skadi-Mixtral-v1",
"license:cc-by-nc-4.0",
"endpoints_compatible",
"region:us"
] | null | 2024-04-19T18:01:34+00:00 | [] | [
"en"
] | TAGS
#transformers #gguf #merge #en #base_model-Sao10K/Skadi-Mixtral-v1 #license-cc-by-nc-4.0 #endpoints_compatible #region-us
| About
-----
weighted/imatrix quants of URL
static quants are available at URL
Usage
-----
If you are unsure how to use GGUF files, refer to one of TheBloke's
READMEs for
more details, including on how to concatenate multi-part files.
Provided Quants
---------------
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):
!URL
And here are Artefact2's thoughts on the matter:
URL
FAQ / Model Request
-------------------
See URL for some answers to
questions you might have and/or if you want some other model quantized.
Thanks
------
I thank my company, nethype GmbH, for letting
me use its servers and providing upgrades to my workstation to enable
this work in my free time.
| [] | [
"TAGS\n#transformers #gguf #merge #en #base_model-Sao10K/Skadi-Mixtral-v1 #license-cc-by-nc-4.0 #endpoints_compatible #region-us \n"
] |
reinforcement-learning | null |
# **Reinforce** Agent playing **Pixelcopter-PLE-v0**
This is a trained model of a **Reinforce** agent playing **Pixelcopter-PLE-v0** .
To learn to use this model and train yours check Unit 4 of the Deep Reinforcement Learning Course: https://huggingface.co/deep-rl-course/unit4/introduction
| {"tags": ["Pixelcopter-PLE-v0", "reinforce", "reinforcement-learning", "custom-implementation", "deep-rl-class"], "model-index": [{"name": "Reinforce-pixelcopter", "results": [{"task": {"type": "reinforcement-learning", "name": "reinforcement-learning"}, "dataset": {"name": "Pixelcopter-PLE-v0", "type": "Pixelcopter-PLE-v0"}, "metrics": [{"type": "mean_reward", "value": "129.20 +/- 100.04", "name": "mean_reward", "verified": false}]}]}]} | Kommunarus/Reinforce-pixelcopter | null | [
"Pixelcopter-PLE-v0",
"reinforce",
"reinforcement-learning",
"custom-implementation",
"deep-rl-class",
"model-index",
"region:us"
] | null | 2024-04-19T18:02:20+00:00 | [] | [] | TAGS
#Pixelcopter-PLE-v0 #reinforce #reinforcement-learning #custom-implementation #deep-rl-class #model-index #region-us
|
# Reinforce Agent playing Pixelcopter-PLE-v0
This is a trained model of a Reinforce agent playing Pixelcopter-PLE-v0 .
To learn to use this model and train yours check Unit 4 of the Deep Reinforcement Learning Course: URL
| [
"# Reinforce Agent playing Pixelcopter-PLE-v0\n This is a trained model of a Reinforce agent playing Pixelcopter-PLE-v0 .\n To learn to use this model and train yours check Unit 4 of the Deep Reinforcement Learning Course: URL"
] | [
"TAGS\n#Pixelcopter-PLE-v0 #reinforce #reinforcement-learning #custom-implementation #deep-rl-class #model-index #region-us \n",
"# Reinforce Agent playing Pixelcopter-PLE-v0\n This is a trained model of a Reinforce agent playing Pixelcopter-PLE-v0 .\n To learn to use this model and train yours check Unit 4 of the Deep Reinforcement Learning Course: URL"
] |
null | transformers |
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] | {"library_name": "transformers", "tags": []} | hi000000/insta_upnormal-llama3_100 | null | [
"transformers",
"safetensors",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null | 2024-04-19T18:04:05+00:00 | [
"1910.09700"
] | [] | TAGS
#transformers #safetensors #arxiv-1910.09700 #endpoints_compatible #region-us
|
# Model Card for Model ID
## Model Details
### Model Description
This is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.
- Developed by:
- Funded by [optional]:
- Shared by [optional]:
- Model type:
- Language(s) (NLP):
- License:
- Finetuned from model [optional]:
### Model Sources [optional]
- Repository:
- Paper [optional]:
- Demo [optional]:
## Uses
### Direct Use
### Downstream Use [optional]
### Out-of-Scope Use
## Bias, Risks, and Limitations
### Recommendations
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
## Training Details
### Training Data
### Training Procedure
#### Preprocessing [optional]
#### Training Hyperparameters
- Training regime:
#### Speeds, Sizes, Times [optional]
## Evaluation
### Testing Data, Factors & Metrics
#### Testing Data
#### Factors
#### Metrics
### Results
#### Summary
## Model Examination [optional]
## Environmental Impact
Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).
- Hardware Type:
- Hours used:
- Cloud Provider:
- Compute Region:
- Carbon Emitted:
## Technical Specifications [optional]
### Model Architecture and Objective
### Compute Infrastructure
#### Hardware
#### Software
[optional]
BibTeX:
APA:
## Glossary [optional]
## More Information [optional]
## Model Card Authors [optional]
## Model Card Contact
| [
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.",
"## How to Get Started with the Model\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] | [
"TAGS\n#transformers #safetensors #arxiv-1910.09700 #endpoints_compatible #region-us \n",
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.",
"## How to Get Started with the Model\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] |
text-generation | transformers |
Model accordingly to [LLama-3](https://huggingface.co/meta-llama/Meta-Llama-3-70B-Instruct/tree/main)
```
Model Details
Meta developed and released the Meta Llama 3 family of large language models (LLMs), a collection of pretrained and instruction tuned generative text models in 8 and 70B sizes. The Llama 3 instruction tuned models are optimized for dialogue use cases and outperform many of the available open source chat models on common industry benchmarks. Further, in developing these models, we took great care to optimize helpfulness and safety.
```
Quant Config : { "zero_point": True, "q_group_size": 128, "w_bit": 4, "version": "GEMM" } | {"tags": ["text-generation-inference", "llama3", "4-bit precision - Safetensors"]} | cdawg/llama-3-70b-instruct-awq | null | [
"transformers",
"safetensors",
"llama",
"text-generation",
"text-generation-inference",
"llama3",
"4-bit precision - Safetensors",
"conversational",
"autotrain_compatible",
"endpoints_compatible",
"4-bit",
"region:us"
] | null | 2024-04-19T18:06:34+00:00 | [] | [] | TAGS
#transformers #safetensors #llama #text-generation #text-generation-inference #llama3 #4-bit precision - Safetensors #conversational #autotrain_compatible #endpoints_compatible #4-bit #region-us
|
Model accordingly to LLama-3
Quant Config : { "zero_point": True, "q_group_size": 128, "w_bit": 4, "version": "GEMM" } | [] | [
"TAGS\n#transformers #safetensors #llama #text-generation #text-generation-inference #llama3 #4-bit precision - Safetensors #conversational #autotrain_compatible #endpoints_compatible #4-bit #region-us \n"
] |
null | peft |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# Not-so-bright-AGI-v1
This model is a fine-tuned version of [google/gemma-2b](https://huggingface.co/google/gemma-2b) on the generator dataset.
It achieves the following results on the evaluation set:
- Loss: 2.0548
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training Hardware
This model was trained using Intel(R) Data Center GPU Max 1100
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 4
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.05
- training_steps: 1480
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 2.9165 | 3.2 | 100 | 2.6762 |
| 2.419 | 6.4 | 200 | 2.3629 |
| 2.2343 | 9.6 | 300 | 2.2060 |
| 2.1459 | 12.8 | 400 | 2.1401 |
| 2.0944 | 16.0 | 500 | 2.1112 |
| 2.0679 | 19.2 | 600 | 2.0942 |
| 2.0496 | 22.4 | 700 | 2.0826 |
| 2.0375 | 25.6 | 800 | 2.0743 |
| 2.0213 | 28.8 | 900 | 2.0684 |
| 2.0148 | 32.0 | 1000 | 2.0630 |
| 2.0048 | 35.2 | 1100 | 2.0593 |
| 1.9988 | 38.4 | 1200 | 2.0575 |
| 1.9968 | 41.6 | 1300 | 2.0555 |
| 1.9908 | 44.8 | 1400 | 2.0548 |
### Framework versions
- PEFT 0.10.0
- Transformers 4.40.0
- Pytorch 2.0.1a0+cxx11.abi
- Datasets 2.19.0
- Tokenizers 0.19.1 | {"license": "gemma", "library_name": "peft", "tags": ["trl", "sft", "generated_from_trainer"], "datasets": ["generator"], "base_model": "google/gemma-2b", "model-index": [{"name": "Not-so-bright-AGI-v1", "results": []}]} | yuriachermann/Not-so-bright-AGI-v1 | null | [
"peft",
"safetensors",
"trl",
"sft",
"generated_from_trainer",
"dataset:generator",
"base_model:google/gemma-2b",
"license:gemma",
"region:us"
] | null | 2024-04-19T18:09:30+00:00 | [] | [] | TAGS
#peft #safetensors #trl #sft #generated_from_trainer #dataset-generator #base_model-google/gemma-2b #license-gemma #region-us
| Not-so-bright-AGI-v1
====================
This model is a fine-tuned version of google/gemma-2b on the generator dataset.
It achieves the following results on the evaluation set:
* Loss: 2.0548
Model description
-----------------
More information needed
Intended uses & limitations
---------------------------
More information needed
Training and evaluation data
----------------------------
More information needed
Training Hardware
-----------------
This model was trained using Intel(R) Data Center GPU Max 1100
Training procedure
------------------
### Training hyperparameters
The following hyperparameters were used during training:
* learning\_rate: 1e-05
* train\_batch\_size: 4
* eval\_batch\_size: 8
* seed: 42
* gradient\_accumulation\_steps: 8
* total\_train\_batch\_size: 32
* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
* lr\_scheduler\_type: linear
* lr\_scheduler\_warmup\_ratio: 0.05
* training\_steps: 1480
### Training results
### Framework versions
* PEFT 0.10.0
* Transformers 4.40.0
* Pytorch 2.0.1a0+URL
* Datasets 2.19.0
* Tokenizers 0.19.1
| [
"### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 1e-05\n* train\\_batch\\_size: 4\n* eval\\_batch\\_size: 8\n* seed: 42\n* gradient\\_accumulation\\_steps: 8\n* total\\_train\\_batch\\_size: 32\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* lr\\_scheduler\\_warmup\\_ratio: 0.05\n* training\\_steps: 1480",
"### Training results",
"### Framework versions\n\n\n* PEFT 0.10.0\n* Transformers 4.40.0\n* Pytorch 2.0.1a0+URL\n* Datasets 2.19.0\n* Tokenizers 0.19.1"
] | [
"TAGS\n#peft #safetensors #trl #sft #generated_from_trainer #dataset-generator #base_model-google/gemma-2b #license-gemma #region-us \n",
"### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 1e-05\n* train\\_batch\\_size: 4\n* eval\\_batch\\_size: 8\n* seed: 42\n* gradient\\_accumulation\\_steps: 8\n* total\\_train\\_batch\\_size: 32\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* lr\\_scheduler\\_warmup\\_ratio: 0.05\n* training\\_steps: 1480",
"### Training results",
"### Framework versions\n\n\n* PEFT 0.10.0\n* Transformers 4.40.0\n* Pytorch 2.0.1a0+URL\n* Datasets 2.19.0\n* Tokenizers 0.19.1"
] |
text-generation | null |
## Exllama v2 Quantizations of Meta-Llama-3-8B-Instruct with <|eot_id|> set to special=False
Using <a href="https://github.com/turboderp/exllamav2/releases/tag/v0.0.19">turboderp's ExLlamaV2 v0.0.19</a> for quantization.
<b>The "main" branch only contains the measurement.json, download one of the other branches for the model (see below)</b>
Each branch contains an individual bits per weight, with the main one containing only the meaurement.json for further conversions.
Original model: https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct
## Prompt format
```
<|begin_of_text|><|start_header_id|>system<|end_header_id|>
{system_prompt}<|eot_id|><|start_header_id|>user<|end_header_id|>
{prompt}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
```
## Available sizes
| Branch | Bits | lm_head bits | VRAM (4k) | VRAM (8K) | VRAM (16k) | VRAM (32k) | Description |
| ----- | ---- | ------- | ------ | ------ | ------ | ------ | ------------ |
| [8_0](https://huggingface.co/bartowski/Meta-Llama-3-8B-Instruct-special-eot-false-exl2/tree/8_0) | 8.0 | 8.0 | 10.1 GB | 10.5 GB | 11.5 GB | 13.6 GB | Maximum quality that ExLlamaV2 can produce, near unquantized performance. |
| [6_5](https://huggingface.co/bartowski/Meta-Llama-3-8B-Instruct-special-eot-false-exl2/tree/6_5) | 6.5 | 8.0 | 8.9 GB | 9.3 GB | 10.3 GB | 12.4 GB | Very similar to 8.0, good tradeoff of size vs performance, **recommended**. |
| [5_0](https://huggingface.co/bartowski/Meta-Llama-3-8B-Instruct-special-eot-false-exl2/tree/5_0) | 5.0 | 6.0 | 7.7 GB | 8.1 GB | 9.1 GB | 11.2 GB | Slightly lower quality vs 6.5, but usable on 8GB cards. |
| [4_25](https://huggingface.co/bartowski/Meta-Llama-3-8B-Instruct-special-eot-false-exl2/tree/4_25) | 4.25 | 6.0 | 7.0 GB | 7.4 GB | 8.4 GB | 10.5 GB | GPTQ equivalent bits per weight, slightly higher quality. |
| [3_5](https://huggingface.co/bartowski/Meta-Llama-3-8B-Instruct-special-eot-false-exl2/tree/3_5) | 3.5 | 6.0 | 6.4 GB | 6.8 GB | 7.8 GB | 9.9 GB | Lower quality, only use if you have to. |
## Download instructions
With git:
```shell
git clone --single-branch --branch 6_5 https://huggingface.co/bartowski/Meta-Llama-3-8B-Instruct-special-eot-false-exl2 Meta-Llama-3-8B-Instruct-special-eot-false-exl2-6_5
```
With huggingface hub (credit to TheBloke for instructions):
```shell
pip3 install huggingface-hub
```
To download a specific branch, use the `--revision` parameter. For example, to download the 6.5 bpw branch:
Linux:
```shell
huggingface-cli download bartowski/Meta-Llama-3-8B-Instruct-special-eot-false-exl2 --revision 6_5 --local-dir Meta-Llama-3-8B-Instruct-special-eot-false-exl2-6_5 --local-dir-use-symlinks False
```
Windows (which apparently doesn't like _ in folders sometimes?):
```shell
huggingface-cli download bartowski/Meta-Llama-3-8B-Instruct-special-eot-false-exl2 --revision 6_5 --local-dir Meta-Llama-3-8B-Instruct-special-eot-false-exl2-6.5 --local-dir-use-symlinks False
```
Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski | {"language": ["en"], "license": "other", "tags": ["facebook", "meta", "pytorch", "llama", "llama-3"], "pipeline_tag": "text-generation", "license_name": "llama3", "license_link": "LICENSE", "extra_gated_prompt": "### META LLAMA 3 COMMUNITY LICENSE AGREEMENT\nMeta Llama 3 Version Release Date: April 18, 2024\n\"Agreement\" means the terms and conditions for use, reproduction, distribution and modification of the Llama Materials set forth herein.\n\"Documentation\" means the specifications, manuals and documentation accompanying Meta Llama 3 distributed by Meta at https://llama.meta.com/get-started/.\n\"Licensee\" or \"you\" means you, or your employer or any other person or entity (if you are entering into this Agreement on such person or entity\u2019s behalf), of the age required under applicable laws, rules or regulations to provide legal consent and that has legal authority to bind your employer or such other person or entity if you are entering in this Agreement on their behalf.\n\"Meta Llama 3\" means the foundational large language models and software and algorithms, including machine-learning model code, trained model weights, inference-enabling code, training-enabling code, fine-tuning enabling code and other elements of the foregoing distributed by Meta at https://llama.meta.com/llama-downloads.\n\"Llama Materials\" means, collectively, Meta\u2019s proprietary Meta Llama 3 and Documentation (and any portion thereof) made available under this Agreement.\n\"Meta\" or \"we\" means Meta Platforms Ireland Limited (if you are located in or, if you are an entity, your principal place of business is in the EEA or Switzerland) and Meta Platforms, Inc. (if you are located outside of the EEA or Switzerland).\n \n1. License Rights and Redistribution.\na. Grant of Rights. You are granted a non-exclusive, worldwide, non-transferable and royalty-free limited license under Meta\u2019s intellectual property or other rights owned by Meta embodied in the Llama Materials to use, reproduce, distribute, copy, create derivative works of, and make modifications to the Llama Materials.\nb. Redistribution and Use.\ni. If you distribute or make available the Llama Materials (or any derivative works thereof), or a product or service that uses any of them, including another AI model, you shall (A) provide a copy of this Agreement with any such Llama Materials; and (B) prominently display \u201cBuilt with Meta Llama 3\u201d on a related website, user interface, blogpost, about page, or product documentation. If you use the Llama Materials to create, train, fine tune, or otherwise improve an AI model, which is distributed or made available, you shall also include \u201cLlama 3\u201d at the beginning of any such AI model name.\nii. If you receive Llama Materials, or any derivative works thereof, from a Licensee as part of an integrated end user product, then Section 2 of this Agreement will not apply to you.\niii. You must retain in all copies of the Llama Materials that you distribute the following attribution notice within a \u201cNotice\u201d text file distributed as a part of such copies: \u201cMeta Llama 3 is licensed under the Meta Llama 3 Community License, Copyright \u00a9 Meta Platforms, Inc. All Rights Reserved.\u201d\niv. Your use of the Llama Materials must comply with applicable laws and regulations (including trade compliance laws and regulations) and adhere to the Acceptable Use Policy for the Llama Materials (available at https://llama.meta.com/llama3/use-policy), which is hereby incorporated by reference into this Agreement.\nv. You will not use the Llama Materials or any output or results of the Llama Materials to improve any other large language model (excluding Meta Llama 3 or derivative works thereof).\n2. Additional Commercial Terms. If, on the Meta Llama 3 version release date, the monthly active users of the products or services made available by or for Licensee, or Licensee\u2019s affiliates, is greater than 700 million monthly active users in the preceding calendar month, you must request a license from Meta, which Meta may grant to you in its sole discretion, and you are not authorized to exercise any of the rights under this Agreement unless or until Meta otherwise expressly grants you such rights.\n3. Disclaimer of Warranty. UNLESS REQUIRED BY APPLICABLE LAW, THE LLAMA MATERIALS AND ANY OUTPUT AND RESULTS THEREFROM ARE PROVIDED ON AN \u201cAS IS\u201d BASIS, WITHOUT WARRANTIES OF ANY KIND, AND META DISCLAIMS ALL WARRANTIES OF ANY KIND, BOTH EXPRESS AND IMPLIED, INCLUDING, WITHOUT LIMITATION, ANY WARRANTIES OF TITLE, NON-INFRINGEMENT, MERCHANTABILITY, OR FITNESS FOR A PARTICULAR PURPOSE. YOU ARE SOLELY RESPONSIBLE FOR DETERMINING THE APPROPRIATENESS OF USING OR REDISTRIBUTING THE LLAMA MATERIALS AND ASSUME ANY RISKS ASSOCIATED WITH YOUR USE OF THE LLAMA MATERIALS AND ANY OUTPUT AND RESULTS.\n4. Limitation of Liability. IN NO EVENT WILL META OR ITS AFFILIATES BE LIABLE UNDER ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, TORT, NEGLIGENCE, PRODUCTS LIABILITY, OR OTHERWISE, ARISING OUT OF THIS AGREEMENT, FOR ANY LOST PROFITS OR ANY INDIRECT, SPECIAL, CONSEQUENTIAL, INCIDENTAL, EXEMPLARY OR PUNITIVE DAMAGES, EVEN IF META OR ITS AFFILIATES HAVE BEEN ADVISED OF THE POSSIBILITY OF ANY OF THE FOREGOING.\n5. Intellectual Property.\na. No trademark licenses are granted under this Agreement, and in connection with the Llama Materials, neither Meta nor Licensee may use any name or mark owned by or associated with the other or any of its affiliates, except as required for reasonable and customary use in describing and redistributing the Llama Materials or as set forth in this Section 5(a). Meta hereby grants you a license to use \u201cLlama 3\u201d (the \u201cMark\u201d) solely as required to comply with the last sentence of Section 1.b.i. You will comply with Meta\u2019s brand guidelines (currently accessible at https://about.meta.com/brand/resources/meta/company-brand/ ). All goodwill arising out of your use of the Mark will inure to the benefit of Meta.\nb. Subject to Meta\u2019s ownership of Llama Materials and derivatives made by or for Meta, with respect to any derivative works and modifications of the Llama Materials that are made by you, as between you and Meta, you are and will be the owner of such derivative works and modifications.\nc. If you institute litigation or other proceedings against Meta or any entity (including a cross-claim or counterclaim in a lawsuit) alleging that the Llama Materials or Meta Llama 3 outputs or results, or any portion of any of the foregoing, constitutes infringement of intellectual property or other rights owned or licensable by you, then any licenses granted to you under this Agreement shall terminate as of the date such litigation or claim is filed or instituted. You will indemnify and hold harmless Meta from and against any claim by any third party arising out of or related to your use or distribution of the Llama Materials.\n6. Term and Termination. The term of this Agreement will commence upon your acceptance of this Agreement or access to the Llama Materials and will continue in full force and effect until terminated in accordance with the terms and conditions herein. Meta may terminate this Agreement if you are in breach of any term or condition of this Agreement. Upon termination of this Agreement, you shall delete and cease use of the Llama Materials. Sections 3, 4 and 7 shall survive the termination of this Agreement.\n7. Governing Law and Jurisdiction. This Agreement will be governed and construed under the laws of the State of California without regard to choice of law principles, and the UN Convention on Contracts for the International Sale of Goods does not apply to this Agreement. The courts of California shall have exclusive jurisdiction of any dispute arising out of this Agreement.\n### Meta Llama 3 Acceptable Use Policy\nMeta is committed to promoting safe and fair use of its tools and features, including Meta Llama 3. If you access or use Meta Llama 3, you agree to this Acceptable Use Policy (\u201cPolicy\u201d). The most recent copy of this policy can be found at [https://llama.meta.com/llama3/use-policy](https://llama.meta.com/llama3/use-policy)\n#### Prohibited Uses\nWe want everyone to use Meta Llama 3 safely and responsibly. You agree you will not use, or allow others to use, Meta Llama 3 to: 1. Violate the law or others\u2019 rights, including to:\n 1. Engage in, promote, generate, contribute to, encourage, plan, incite, or further illegal or unlawful activity or content, such as:\n 1. Violence or terrorism\n 2. Exploitation or harm to children, including the solicitation, creation, acquisition, or dissemination of child exploitative content or failure to report Child Sexual Abuse Material\n 3. Human trafficking, exploitation, and sexual violence\n 4. The illegal distribution of information or materials to minors, including obscene materials, or failure to employ legally required age-gating in connection with such information or materials.\n 5. Sexual solicitation\n 6. Any other criminal activity\n 2. Engage in, promote, incite, or facilitate the harassment, abuse, threatening, or bullying of individuals or groups of individuals\n 3. Engage in, promote, incite, or facilitate discrimination or other unlawful or harmful conduct in the provision of employment, employment benefits, credit, housing, other economic benefits, or other essential goods and services\n 4. Engage in the unauthorized or unlicensed practice of any profession including, but not limited to, financial, legal, medical/health, or related professional practices\n 5. Collect, process, disclose, generate, or infer health, demographic, or other sensitive personal or private information about individuals without rights and consents required by applicable laws\n 6. Engage in or facilitate any action or generate any content that infringes, misappropriates, or otherwise violates any third-party rights, including the outputs or results of any products or services using the Llama Materials\n 7. Create, generate, or facilitate the creation of malicious code, malware, computer viruses or do anything else that could disable, overburden, interfere with or impair the proper working, integrity, operation or appearance of a website or computer system\n2. Engage in, promote, incite, facilitate, or assist in the planning or development of activities that present a risk of death or bodily harm to individuals, including use of Meta Llama 3 related to the following:\n 1. Military, warfare, nuclear industries or applications, espionage, use for materials or activities that are subject to the International Traffic Arms Regulations (ITAR) maintained by the United States Department of State\n 2. Guns and illegal weapons (including weapon development)\n 3. Illegal drugs and regulated/controlled substances\n 4. Operation of critical infrastructure, transportation technologies, or heavy machinery\n 5. Self-harm or harm to others, including suicide, cutting, and eating disorders\n 6. Any content intended to incite or promote violence, abuse, or any infliction of bodily harm to an individual\n3. Intentionally deceive or mislead others, including use of Meta Llama 3 related to the following:\n 1. Generating, promoting, or furthering fraud or the creation or promotion of disinformation\n 2. Generating, promoting, or furthering defamatory content, including the creation of defamatory statements, images, or other content\n 3. Generating, promoting, or further distributing spam\n 4. Impersonating another individual without consent, authorization, or legal right\n 5. Representing that the use of Meta Llama 3 or outputs are human-generated\n 6. Generating or facilitating false online engagement, including fake reviews and other means of fake online engagement\n4. Fail to appropriately disclose to end users any known dangers of your AI system\nPlease report any violation of this Policy, software \u201cbug,\u201d or other problems that could lead to a violation of this Policy through one of the following means:\n * Reporting issues with the model: [https://github.com/meta-llama/llama3](https://github.com/meta-llama/llama3)\n * Reporting risky content generated by the model:\n developers.facebook.com/llama_output_feedback\n * Reporting bugs and security concerns: facebook.com/whitehat/info\n * Reporting violations of the Acceptable Use Policy or unlicensed uses of Meta Llama 3: [email protected]", "extra_gated_fields": {"First Name": "text", "Last Name": "text", "Date of birth": "date_picker", "Country": "country", "Affiliation": "text", "geo": "ip_location", "By clicking Submit below I accept the terms of the license and acknowledge that the information I provide will be collected stored processed and shared in accordance with the Meta Privacy Policy": "checkbox"}, "extra_gated_description": "The information you provide will be collected, stored, processed and shared in accordance with the [Meta Privacy Policy](https://www.facebook.com/privacy/policy/).", "extra_gated_button_content": "Submit", "quantized_by": "bartowski"} | bartowski/Meta-Llama-3-8B-Instruct-special-eot-false-exl2 | null | [
"facebook",
"meta",
"pytorch",
"llama",
"llama-3",
"text-generation",
"en",
"license:other",
"region:us"
] | null | 2024-04-19T18:09:58+00:00 | [] | [
"en"
] | TAGS
#facebook #meta #pytorch #llama #llama-3 #text-generation #en #license-other #region-us
| Exllama v2 Quantizations of Meta-Llama-3-8B-Instruct with <|eot\_id|> set to special=False
------------------------------------------------------------------------------------------
Using <a href="URL ExLlamaV2 v0.0.19 for quantization.
**The "main" branch only contains the URL, download one of the other branches for the model (see below)**
Each branch contains an individual bits per weight, with the main one containing only the URL for further conversions.
Original model: URL
Prompt format
-------------
Available sizes
---------------
Download instructions
---------------------
With git:
With huggingface hub (credit to TheBloke for instructions):
To download a specific branch, use the '--revision' parameter. For example, to download the 6.5 bpw branch:
Linux:
Windows (which apparently doesn't like \_ in folders sometimes?):
Want to support my work? Visit my ko-fi page here: URL
| [] | [
"TAGS\n#facebook #meta #pytorch #llama #llama-3 #text-generation #en #license-other #region-us \n"
] |
text-generation | transformers | # mlabonne/Llama-3-12B AWQ
- Model creator: [mlabonne](https://huggingface.co/mlabonne)
- Original model: [Llama-3-12B](https://huggingface.co/mlabonne/Llama-3-12B)
## Model Summary
Llama-3-12B is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
* [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B)
* [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B)
| {"license": "other", "library_name": "transformers", "tags": ["4-bit", "AWQ", "text-generation", "autotrain_compatible", "endpoints_compatible", "merge", "mergekit", "lazymergekit"], "base_model": ["meta-llama/Meta-Llama-3-8B", "meta-llama/Meta-Llama-3-8B"], "pipeline_tag": "text-generation", "inference": false, "quantized_by": "Suparious"} | solidrust/Llama-3-12B-AWQ | null | [
"transformers",
"safetensors",
"llama",
"text-generation",
"4-bit",
"AWQ",
"autotrain_compatible",
"endpoints_compatible",
"merge",
"mergekit",
"lazymergekit",
"conversational",
"base_model:meta-llama/Meta-Llama-3-8B",
"license:other",
"text-generation-inference",
"region:us"
] | null | 2024-04-19T18:10:05+00:00 | [] | [] | TAGS
#transformers #safetensors #llama #text-generation #4-bit #AWQ #autotrain_compatible #endpoints_compatible #merge #mergekit #lazymergekit #conversational #base_model-meta-llama/Meta-Llama-3-8B #license-other #text-generation-inference #region-us
| # mlabonne/Llama-3-12B AWQ
- Model creator: mlabonne
- Original model: Llama-3-12B
## Model Summary
Llama-3-12B is a merge of the following models using LazyMergekit:
* meta-llama/Meta-Llama-3-8B
* meta-llama/Meta-Llama-3-8B
| [
"# mlabonne/Llama-3-12B AWQ\n\n- Model creator: mlabonne\n- Original model: Llama-3-12B",
"## Model Summary\n\nLlama-3-12B is a merge of the following models using LazyMergekit:\n* meta-llama/Meta-Llama-3-8B\n* meta-llama/Meta-Llama-3-8B"
] | [
"TAGS\n#transformers #safetensors #llama #text-generation #4-bit #AWQ #autotrain_compatible #endpoints_compatible #merge #mergekit #lazymergekit #conversational #base_model-meta-llama/Meta-Llama-3-8B #license-other #text-generation-inference #region-us \n",
"# mlabonne/Llama-3-12B AWQ\n\n- Model creator: mlabonne\n- Original model: Llama-3-12B",
"## Model Summary\n\nLlama-3-12B is a merge of the following models using LazyMergekit:\n* meta-llama/Meta-Llama-3-8B\n* meta-llama/Meta-Llama-3-8B"
] |
null | peft |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# coinplusfire_chinese-alpaca-2-7b_full
This model is a fine-tuned version of [hfl/chinese-alpaca-2-7b](https://huggingface.co/hfl/chinese-alpaca-2-7b) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 1.5419
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0002
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 2
- num_epochs: 10
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 2.3117 | 1.0 | 207 | 1.9098 |
| 1.878 | 2.0 | 414 | 1.7665 |
| 1.7555 | 3.0 | 621 | 1.6904 |
| 1.6743 | 4.0 | 828 | 1.6407 |
| 1.6157 | 5.0 | 1035 | 1.6056 |
| 1.5661 | 6.0 | 1242 | 1.5841 |
| 1.5265 | 7.0 | 1449 | 1.5642 |
| 1.495 | 8.0 | 1656 | 1.5487 |
| 1.4711 | 9.0 | 1863 | 1.5431 |
| 1.4542 | 10.0 | 2070 | 1.5419 |
### Framework versions
- PEFT 0.10.0
- Transformers 4.39.3
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2 | {"license": "apache-2.0", "library_name": "peft", "tags": ["generated_from_trainer"], "base_model": "hfl/chinese-alpaca-2-7b", "model-index": [{"name": "coinplusfire_chinese-alpaca-2-7b_full", "results": []}]} | coinplusfire/coinplusfire_chinese-alpaca-2-7b_full | null | [
"peft",
"safetensors",
"generated_from_trainer",
"base_model:hfl/chinese-alpaca-2-7b",
"license:apache-2.0",
"region:us"
] | null | 2024-04-19T18:10:18+00:00 | [] | [] | TAGS
#peft #safetensors #generated_from_trainer #base_model-hfl/chinese-alpaca-2-7b #license-apache-2.0 #region-us
| coinplusfire\_chinese-alpaca-2-7b\_full
=======================================
This model is a fine-tuned version of hfl/chinese-alpaca-2-7b on an unknown dataset.
It achieves the following results on the evaluation set:
* Loss: 1.5419
Model description
-----------------
More information needed
Intended uses & limitations
---------------------------
More information needed
Training and evaluation data
----------------------------
More information needed
Training procedure
------------------
### Training hyperparameters
The following hyperparameters were used during training:
* learning\_rate: 0.0002
* train\_batch\_size: 4
* eval\_batch\_size: 4
* seed: 42
* gradient\_accumulation\_steps: 4
* total\_train\_batch\_size: 16
* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
* lr\_scheduler\_type: linear
* lr\_scheduler\_warmup\_steps: 2
* num\_epochs: 10
* mixed\_precision\_training: Native AMP
### Training results
### Framework versions
* PEFT 0.10.0
* Transformers 4.39.3
* Pytorch 2.2.1+cu121
* Datasets 2.18.0
* Tokenizers 0.15.2
| [
"### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0002\n* train\\_batch\\_size: 4\n* eval\\_batch\\_size: 4\n* seed: 42\n* gradient\\_accumulation\\_steps: 4\n* total\\_train\\_batch\\_size: 16\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* lr\\_scheduler\\_warmup\\_steps: 2\n* num\\_epochs: 10\n* mixed\\_precision\\_training: Native AMP",
"### Training results",
"### Framework versions\n\n\n* PEFT 0.10.0\n* Transformers 4.39.3\n* Pytorch 2.2.1+cu121\n* Datasets 2.18.0\n* Tokenizers 0.15.2"
] | [
"TAGS\n#peft #safetensors #generated_from_trainer #base_model-hfl/chinese-alpaca-2-7b #license-apache-2.0 #region-us \n",
"### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0002\n* train\\_batch\\_size: 4\n* eval\\_batch\\_size: 4\n* seed: 42\n* gradient\\_accumulation\\_steps: 4\n* total\\_train\\_batch\\_size: 16\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* lr\\_scheduler\\_warmup\\_steps: 2\n* num\\_epochs: 10\n* mixed\\_precision\\_training: Native AMP",
"### Training results",
"### Framework versions\n\n\n* PEFT 0.10.0\n* Transformers 4.39.3\n* Pytorch 2.2.1+cu121\n* Datasets 2.18.0\n* Tokenizers 0.15.2"
] |
text-generation | transformers |
# Development Llama 3 Instruct 8B build without the ".assistant" on exl2
Out of the box exllama v2 support for removing the **.assistant** tag during llama 3 instruct text responses. This was converted to exllamav2 from [Llama 3 Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct).
```
<|begin_of_text|><|start_header_id|>system<|end_header_id|>
you are a collaborative python expert that can solve any challenging problem.<|eot_id|><|start_header_id|>user<|end_header_id|>
write python hello world<|eot_id|><|start_header_id|>assistant<|end_header_id|>
```
## Model Details
Meta developed and released the Meta Llama 3 family of large language models (LLMs), a collection of pretrained and instruction tuned generative text models in 8 and 70B sizes. The Llama 3 instruction tuned models are optimized for dialogue use cases and outperform many of the available open source chat models on common industry benchmarks. Further, in developing these models, we took great care to optimize helpfulness and safety.
**Model developers** Meta
**Variations** Llama 3 comes in two sizes — 8B and 70B parameters — in pre-trained and instruction tuned variants.
**Input** Models input text only.
**Output** Models generate text and code only.
**Model Architecture** Llama 3 is an auto-regressive language model that uses an optimized transformer architecture. The tuned versions use supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF) to align with human preferences for helpfulness and safety.
<table>
<tr>
<td>
</td>
<td><strong>Training Data</strong>
</td>
<td><strong>Params</strong>
</td>
<td><strong>Context length</strong>
</td>
<td><strong>GQA</strong>
</td>
<td><strong>Token count</strong>
</td>
<td><strong>Knowledge cutoff</strong>
</td>
</tr>
<tr>
<td rowspan="2" >Llama 3
</td>
<td rowspan="2" >A new mix of publicly available online data.
</td>
<td>8B
</td>
<td>8k
</td>
<td>Yes
</td>
<td rowspan="2" >15T+
</td>
<td>March, 2023
</td>
</tr>
<tr>
<td>70B
</td>
<td>8k
</td>
<td>Yes
</td>
<td>December, 2023
</td>
</tr>
</table>
**Llama 3 family of models**. Token counts refer to pretraining data only. Both the 8 and 70B versions use Grouped-Query Attention (GQA) for improved inference scalability.
**Model Release Date** April 18, 2024.
**Status** This is a static model trained on an offline dataset. Future versions of the tuned models will be released as we improve model safety with community feedback.
**License** A custom commercial license is available at: [https://llama.meta.com/llama3/license](https://llama.meta.com/llama3/license)
Where to send questions or comments about the model Instructions on how to provide feedback or comments on the model can be found in the model [README](https://github.com/meta-llama/llama3). For more technical information about generation parameters and recipes for how to use Llama 3 in applications, please go [here](https://github.com/meta-llama/llama-recipes).
## Intended Use
**Intended Use Cases** Llama 3 is intended for commercial and research use in English. Instruction tuned models are intended for assistant-like chat, whereas pretrained models can be adapted for a variety of natural language generation tasks.
**Out-of-scope** Use in any manner that violates applicable laws or regulations (including trade compliance laws). Use in any other way that is prohibited by the Acceptable Use Policy and Llama 3 Community License. Use in languages other than English**.
**Note: Developers may fine-tune Llama 3 models for languages beyond English provided they comply with the Llama 3 Community License and the Acceptable Use Policy.
## How to use
This repository contains two versions of Meta-Llama-3-8B-Instruct, for use with transformers and with the original `llama3` codebase.
### Use with transformers
See the snippet below for usage with Transformers:
```python
import transformers
import torch
model_id = "meta-llama/Meta-Llama-3-8B-Instruct"
pipeline = transformers.pipeline(
"text-generation",
model=model_id,
model_kwargs={"torch_dtype": torch.bfloat16},
device="auto",
)
messages = [
{"role": "system", "content": "You are a pirate chatbot who always responds in pirate speak!"},
{"role": "user", "content": "Who are you?"},
]
prompt = pipeline.tokenizer.apply_chat_template(
messages,
tokenize=False,
add_generation_prompt=True
)
terminators = [
pipeline.tokenizer.eos_token_id,
pipeline.tokenizer.convert_tokens_to_ids("<|eot_id|>")
]
outputs = pipeline(
prompt,
max_new_tokens=256,
eos_token_id=terminators,
do_sample=True,
temperature=0.6,
top_p=0.9,
)
print(outputs[0]["generated_text"][len(prompt):])
```
### Use with `llama3`
Please, follow the instructions in the [repository](https://github.com/meta-llama/llama3)
To download Original checkpoints, see the example command below leveraging `huggingface-cli`:
```
huggingface-cli download meta-llama/Meta-Llama-3-8B-Instruct --include "original/*" --local-dir Meta-Llama-3-8B-Instruct
```
For Hugging Face support, we recommend using transformers or TGI, but a similar command works.
## Hardware and Software
**Training Factors** We used custom training libraries, Meta's Research SuperCluster, and production clusters for pretraining. Fine-tuning, annotation, and evaluation were also performed on third-party cloud compute.
**Carbon Footprint Pretraining utilized a cumulative** 7.7M GPU hours of computation on hardware of type H100-80GB (TDP of 700W). Estimated total emissions were 2290 tCO2eq, 100% of which were offset by Meta’s sustainability program.
<table>
<tr>
<td>
</td>
<td><strong>Time (GPU hours)</strong>
</td>
<td><strong>Power Consumption (W)</strong>
</td>
<td><strong>Carbon Emitted(tCO2eq)</strong>
</td>
</tr>
<tr>
<td>Llama 3 8B
</td>
<td>1.3M
</td>
<td>700
</td>
<td>390
</td>
</tr>
<tr>
<td>Llama 3 70B
</td>
<td>6.4M
</td>
<td>700
</td>
<td>1900
</td>
</tr>
<tr>
<td>Total
</td>
<td>7.7M
</td>
<td>
</td>
<td>2290
</td>
</tr>
</table>
**CO2 emissions during pre-training**. Time: total GPU time required for training each model. Power Consumption: peak power capacity per GPU device for the GPUs used adjusted for power usage efficiency. 100% of the emissions are directly offset by Meta's sustainability program, and because we are openly releasing these models, the pretraining costs do not need to be incurred by others.
## Training Data
**Overview** Llama 3 was pretrained on over 15 trillion tokens of data from publicly available sources. The fine-tuning data includes publicly available instruction datasets, as well as over 10M human-annotated examples. Neither the pretraining nor the fine-tuning datasets include Meta user data.
**Data Freshness** The pretraining data has a cutoff of March 2023 for the 7B and December 2023 for the 70B models respectively.
## Benchmarks
In this section, we report the results for Llama 3 models on standard automatic benchmarks. For all the evaluations, we use our internal evaluations library. For details on the methodology see [here](https://github.com/meta-llama/llama3/blob/main/eval_methodology.md).
### Base pretrained models
<table>
<tr>
<td><strong>Category</strong>
</td>
<td><strong>Benchmark</strong>
</td>
<td><strong>Llama 3 8B</strong>
</td>
<td><strong>Llama2 7B</strong>
</td>
<td><strong>Llama2 13B</strong>
</td>
<td><strong>Llama 3 70B</strong>
</td>
<td><strong>Llama2 70B</strong>
</td>
</tr>
<tr>
<td rowspan="6" >General
</td>
<td>MMLU (5-shot)
</td>
<td>66.6
</td>
<td>45.7
</td>
<td>53.8
</td>
<td>79.5
</td>
<td>69.7
</td>
</tr>
<tr>
<td>AGIEval English (3-5 shot)
</td>
<td>45.9
</td>
<td>28.8
</td>
<td>38.7
</td>
<td>63.0
</td>
<td>54.8
</td>
</tr>
<tr>
<td>CommonSenseQA (7-shot)
</td>
<td>72.6
</td>
<td>57.6
</td>
<td>67.6
</td>
<td>83.8
</td>
<td>78.7
</td>
</tr>
<tr>
<td>Winogrande (5-shot)
</td>
<td>76.1
</td>
<td>73.3
</td>
<td>75.4
</td>
<td>83.1
</td>
<td>81.8
</td>
</tr>
<tr>
<td>BIG-Bench Hard (3-shot, CoT)
</td>
<td>61.1
</td>
<td>38.1
</td>
<td>47.0
</td>
<td>81.3
</td>
<td>65.7
</td>
</tr>
<tr>
<td>ARC-Challenge (25-shot)
</td>
<td>78.6
</td>
<td>53.7
</td>
<td>67.6
</td>
<td>93.0
</td>
<td>85.3
</td>
</tr>
<tr>
<td>Knowledge reasoning
</td>
<td>TriviaQA-Wiki (5-shot)
</td>
<td>78.5
</td>
<td>72.1
</td>
<td>79.6
</td>
<td>89.7
</td>
<td>87.5
</td>
</tr>
<tr>
<td rowspan="4" >Reading comprehension
</td>
<td>SQuAD (1-shot)
</td>
<td>76.4
</td>
<td>72.2
</td>
<td>72.1
</td>
<td>85.6
</td>
<td>82.6
</td>
</tr>
<tr>
<td>QuAC (1-shot, F1)
</td>
<td>44.4
</td>
<td>39.6
</td>
<td>44.9
</td>
<td>51.1
</td>
<td>49.4
</td>
</tr>
<tr>
<td>BoolQ (0-shot)
</td>
<td>75.7
</td>
<td>65.5
</td>
<td>66.9
</td>
<td>79.0
</td>
<td>73.1
</td>
</tr>
<tr>
<td>DROP (3-shot, F1)
</td>
<td>58.4
</td>
<td>37.9
</td>
<td>49.8
</td>
<td>79.7
</td>
<td>70.2
</td>
</tr>
</table>
### Instruction tuned models
<table>
<tr>
<td><strong>Benchmark</strong>
</td>
<td><strong>Llama 3 8B</strong>
</td>
<td><strong>Llama 2 7B</strong>
</td>
<td><strong>Llama 2 13B</strong>
</td>
<td><strong>Llama 3 70B</strong>
</td>
<td><strong>Llama 2 70B</strong>
</td>
</tr>
<tr>
<td>MMLU (5-shot)
</td>
<td>68.4
</td>
<td>34.1
</td>
<td>47.8
</td>
<td>82.0
</td>
<td>52.9
</td>
</tr>
<tr>
<td>GPQA (0-shot)
</td>
<td>34.2
</td>
<td>21.7
</td>
<td>22.3
</td>
<td>39.5
</td>
<td>21.0
</td>
</tr>
<tr>
<td>HumanEval (0-shot)
</td>
<td>62.2
</td>
<td>7.9
</td>
<td>14.0
</td>
<td>81.7
</td>
<td>25.6
</td>
</tr>
<tr>
<td>GSM-8K (8-shot, CoT)
</td>
<td>79.6
</td>
<td>25.7
</td>
<td>77.4
</td>
<td>93.0
</td>
<td>57.5
</td>
</tr>
<tr>
<td>MATH (4-shot, CoT)
</td>
<td>30.0
</td>
<td>3.8
</td>
<td>6.7
</td>
<td>50.4
</td>
<td>11.6
</td>
</tr>
</table>
### Responsibility & Safety
We believe that an open approach to AI leads to better, safer products, faster innovation, and a bigger overall market. We are committed to Responsible AI development and took a series of steps to limit misuse and harm and support the open source community.
Foundation models are widely capable technologies that are built to be used for a diverse range of applications. They are not designed to meet every developer preference on safety levels for all use cases, out-of-the-box, as those by their nature will differ across different applications.
Rather, responsible LLM-application deployment is achieved by implementing a series of safety best practices throughout the development of such applications, from the model pre-training, fine-tuning and the deployment of systems composed of safeguards to tailor the safety needs specifically to the use case and audience.
As part of the Llama 3 release, we updated our [Responsible Use Guide](https://llama.meta.com/responsible-use-guide/) to outline the steps and best practices for developers to implement model and system level safety for their application. We also provide a set of resources including [Meta Llama Guard 2](https://llama.meta.com/purple-llama/) and [Code Shield](https://llama.meta.com/purple-llama/) safeguards. These tools have proven to drastically reduce residual risks of LLM Systems, while maintaining a high level of helpfulness. We encourage developers to tune and deploy these safeguards according to their needs and we provide a [reference implementation](https://github.com/meta-llama/llama-recipes/tree/main/recipes/responsible_ai) to get you started.
#### Llama 3-Instruct
As outlined in the Responsible Use Guide, some trade-off between model helpfulness and model alignment is likely unavoidable. Developers should exercise discretion about how to weigh the benefits of alignment and helpfulness for their specific use case and audience. Developers should be mindful of residual risks when using Llama models and leverage additional safety tools as needed to reach the right safety bar for their use case.
<span style="text-decoration:underline;">Safety</span>
For our instruction tuned model, we conducted extensive red teaming exercises, performed adversarial evaluations and implemented safety mitigations techniques to lower residual risks. As with any Large Language Model, residual risks will likely remain and we recommend that developers assess these risks in the context of their use case. In parallel, we are working with the community to make AI safety benchmark standards transparent, rigorous and interpretable.
<span style="text-decoration:underline;">Refusals</span>
In addition to residual risks, we put a great emphasis on model refusals to benign prompts. Over-refusing not only can impact the user experience but could even be harmful in certain contexts as well. We’ve heard the feedback from the developer community and improved our fine tuning to ensure that Llama 3 is significantly less likely to falsely refuse to answer prompts than Llama 2.
We built internal benchmarks and developed mitigations to limit false refusals making Llama 3 our most helpful model to date.
#### Responsible release
In addition to responsible use considerations outlined above, we followed a rigorous process that requires us to take extra measures against misuse and critical risks before we make our release decision.
Misuse
If you access or use Llama 3, you agree to the Acceptable Use Policy. The most recent copy of this policy can be found at [https://llama.meta.com/llama3/use-policy/](https://llama.meta.com/llama3/use-policy/).
#### Critical risks
<span style="text-decoration:underline;">CBRNE</span> (Chemical, Biological, Radiological, Nuclear, and high yield Explosives)
We have conducted a two fold assessment of the safety of the model in this area:
* Iterative testing during model training to assess the safety of responses related to CBRNE threats and other adversarial risks.
* Involving external CBRNE experts to conduct an uplift test assessing the ability of the model to accurately provide expert knowledge and reduce barriers to potential CBRNE misuse, by reference to what can be achieved using web search (without the model).
### <span style="text-decoration:underline;">Cyber Security </span>
We have evaluated Llama 3 with CyberSecEval, Meta’s cybersecurity safety eval suite, measuring Llama 3’s propensity to suggest insecure code when used as a coding assistant, and Llama 3’s propensity to comply with requests to help carry out cyber attacks, where attacks are defined by the industry standard MITRE ATT&CK cyber attack ontology. On our insecure coding and cyber attacker helpfulness tests, Llama 3 behaved in the same range or safer than models of [equivalent coding capability](https://huggingface.co/spaces/facebook/CyberSecEval).
### <span style="text-decoration:underline;">Child Safety</span>
Child Safety risk assessments were conducted using a team of experts, to assess the model’s capability to produce outputs that could result in Child Safety risks and inform on any necessary and appropriate risk mitigations via fine tuning. We leveraged those expert red teaming sessions to expand the coverage of our evaluation benchmarks through Llama 3 model development. For Llama 3, we conducted new in-depth sessions using objective based methodologies to assess the model risks along multiple attack vectors. We also partnered with content specialists to perform red teaming exercises assessing potentially violating content while taking account of market specific nuances or experiences.
### Community
Generative AI safety requires expertise and tooling, and we believe in the strength of the open community to accelerate its progress. We are active members of open consortiums, including the AI Alliance, Partnership in AI and MLCommons, actively contributing to safety standardization and transparency. We encourage the community to adopt taxonomies like the MLCommons Proof of Concept evaluation to facilitate collaboration and transparency on safety and content evaluations. Our Purple Llama tools are open sourced for the community to use and widely distributed across ecosystem partners including cloud service providers. We encourage community contributions to our [Github repository](https://github.com/meta-llama/PurpleLlama).
Finally, we put in place a set of resources including an [output reporting mechanism](https://developers.facebook.com/llama_output_feedback) and [bug bounty program](https://www.facebook.com/whitehat) to continuously improve the Llama technology with the help of the community.
## Ethical Considerations and Limitations
The core values of Llama 3 are openness, inclusivity and helpfulness. It is meant to serve everyone, and to work for a wide range of use cases. It is thus designed to be accessible to people across many different backgrounds, experiences and perspectives. Llama 3 addresses users and their needs as they are, without insertion unnecessary judgment or normativity, while reflecting the understanding that even content that may appear problematic in some cases can serve valuable purposes in others. It respects the dignity and autonomy of all users, especially in terms of the values of free thought and expression that power innovation and progress.
But Llama 3 is a new technology, and like any new technology, there are risks associated with its use. Testing conducted to date has been in English, and has not covered, nor could it cover, all scenarios. For these reasons, as with all LLMs, Llama 3’s potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate, biased or other objectionable responses to user prompts. Therefore, before deploying any applications of Llama 3 models, developers should perform safety testing and tuning tailored to their specific applications of the model. As outlined in the Responsible Use Guide, we recommend incorporating [Purple Llama](https://github.com/facebookresearch/PurpleLlama) solutions into your workflows and specifically [Llama Guard](https://ai.meta.com/research/publications/llama-guard-llm-based-input-output-safeguard-for-human-ai-conversations/) which provides a base model to filter input and output prompts to layer system-level safety on top of model-level safety.
Please see the Responsible Use Guide available at [http://llama.meta.com/responsible-use-guide](http://llama.meta.com/responsible-use-guide)
## Citation instructions
@article{llama3modelcard,
title={Llama 3 Model Card},
author={AI@Meta},
year={2024},
url = {https://github.com/meta-llama/llama3/blob/main/MODEL_CARD.md}
}
## Contributors
Aaditya Singh; Aaron Grattafiori; Abhimanyu Dubey; Abhinav Jauhri; Abhinav Pandey; Abhishek Kadian; Adam Kelsey; Adi Gangidi; Ahmad Al-Dahle; Ahuva Goldstand; Aiesha Letman; Ajay Menon; Akhil Mathur; Alan Schelten; Alex Vaughan; Amy Yang; Andrei Lupu; Andres Alvarado; Andrew Gallagher; Andrew Gu; Andrew Ho; Andrew Poulton; Andrew Ryan; Angela Fan; Ankit Ramchandani; Anthony Hartshorn; Archi Mitra; Archie Sravankumar; Artem Korenev; Arun Rao; Ashley Gabriel; Ashwin Bharambe; Assaf Eisenman; Aston Zhang; Aurelien Rodriguez; Austen Gregerson; Ava Spataru; Baptiste Roziere; Ben Maurer; Benjamin Leonhardi; Bernie Huang; Bhargavi Paranjape; Bing Liu; Binh Tang; Bobbie Chern; Brani Stojkovic; Brian Fuller; Catalina Mejia Arenas; Chao Zhou; Charlotte Caucheteux; Chaya Nayak; Ching-Hsiang Chu; Chloe Bi; Chris Cai; Chris Cox; Chris Marra; Chris McConnell; Christian Keller; Christoph Feichtenhofer; Christophe Touret; Chunyang Wu; Corinne Wong; Cristian Canton Ferrer; Damien Allonsius; Daniel Kreymer; Daniel Haziza; Daniel Li; Danielle Pintz; Danny Livshits; Danny Wyatt; David Adkins; David Esiobu; David Xu; Davide Testuggine; Delia David; Devi Parikh; Dhruv Choudhary; Dhruv Mahajan; Diana Liskovich; Diego Garcia-Olano; Diego Perino; Dieuwke Hupkes; Dingkang Wang; Dustin Holland; Egor Lakomkin; Elina Lobanova; Xiaoqing Ellen Tan; Emily Dinan; Eric Smith; Erik Brinkman; Esteban Arcaute; Filip Radenovic; Firat Ozgenel; Francesco Caggioni; Frank Seide; Frank Zhang; Gabriel Synnaeve; Gabriella Schwarz; Gabrielle Lee; Gada Badeer; Georgia Anderson; Graeme Nail; Gregoire Mialon; Guan Pang; Guillem Cucurell; Hailey Nguyen; Hannah Korevaar; Hannah Wang; Haroun Habeeb; Harrison Rudolph; Henry Aspegren; Hu Xu; Hugo Touvron; Iga Kozlowska; Igor Molybog; Igor Tufanov; Iliyan Zarov; Imanol Arrieta Ibarra; Irina-Elena Veliche; Isabel Kloumann; Ishan Misra; Ivan Evtimov; Jacob Xu; Jade Copet; Jake Weissman; Jan Geffert; Jana Vranes; Japhet Asher; Jason Park; Jay Mahadeokar; Jean-Baptiste Gaya; Jeet Shah; Jelmer van der Linde; Jennifer Chan; Jenny Hong; Jenya Lee; Jeremy Fu; Jeremy Teboul; Jianfeng Chi; Jianyu Huang; Jie Wang; Jiecao Yu; Joanna Bitton; Joe Spisak; Joelle Pineau; Jon Carvill; Jongsoo Park; Joseph Rocca; Joshua Johnstun; Junteng Jia; Kalyan Vasuden Alwala; Kam Hou U; Kate Plawiak; Kartikeya Upasani; Kaushik Veeraraghavan; Ke Li; Kenneth Heafield; Kevin Stone; Khalid El-Arini; Krithika Iyer; Kshitiz Malik; Kuenley Chiu; Kunal Bhalla; Kyle Huang; Lakshya Garg; Lauren Rantala-Yeary; Laurens van der Maaten; Lawrence Chen; Leandro Silva; Lee Bell; Lei Zhang; Liang Tan; Louis Martin; Lovish Madaan; Luca Wehrstedt; Lukas Blecher; Luke de Oliveira; Madeline Muzzi; Madian Khabsa; Manav Avlani; Mannat Singh; Manohar Paluri; Mark Zuckerberg; Marcin Kardas; Martynas Mankus; Mathew Oldham; Mathieu Rita; Matthew Lennie; Maya Pavlova; Meghan Keneally; Melanie Kambadur; Mihir Patel; Mikayel Samvelyan; Mike Clark; Mike Lewis; Min Si; Mitesh Kumar Singh; Mo Metanat; Mona Hassan; Naman Goyal; Narjes Torabi; Nicolas Usunier; Nikolay Bashlykov; Nikolay Bogoychev; Niladri Chatterji; Ning Dong; Oliver Aobo Yang; Olivier Duchenne; Onur Celebi; Parth Parekh; Patrick Alrassy; Paul Saab; Pavan Balaji; Pedro Rittner; Pengchuan Zhang; Pengwei Li; Petar Vasic; Peter Weng; Polina Zvyagina; Prajjwal Bhargava; Pratik Dubal; Praveen Krishnan; Punit Singh Koura; Qing He; Rachel Rodriguez; Ragavan Srinivasan; Rahul Mitra; Ramon Calderer; Raymond Li; Robert Stojnic; Roberta Raileanu; Robin Battey; Rocky Wang; Rohit Girdhar; Rohit Patel; Romain Sauvestre; Ronnie Polidoro; Roshan Sumbaly; Ross Taylor; Ruan Silva; Rui Hou; Rui Wang; Russ Howes; Ruty Rinott; Saghar Hosseini; Sai Jayesh Bondu; Samyak Datta; Sanjay Singh; Sara Chugh; Sargun Dhillon; Satadru Pan; Sean Bell; Sergey Edunov; Shaoliang Nie; Sharan Narang; Sharath Raparthy; Shaun Lindsay; Sheng Feng; Sheng Shen; Shenghao Lin; Shiva Shankar; Shruti Bhosale; Shun Zhang; Simon Vandenhende; Sinong Wang; Seohyun Sonia Kim; Soumya Batra; Sten Sootla; Steve Kehoe; Suchin Gururangan; Sumit Gupta; Sunny Virk; Sydney Borodinsky; Tamar Glaser; Tamar Herman; Tamara Best; Tara Fowler; Thomas Georgiou; Thomas Scialom; Tianhe Li; Todor Mihaylov; Tong Xiao; Ujjwal Karn; Vedanuj Goswami; Vibhor Gupta; Vignesh Ramanathan; Viktor Kerkez; Vinay Satish Kumar; Vincent Gonguet; Vish Vogeti; Vlad Poenaru; Vlad Tiberiu Mihailescu; Vladan Petrovic; Vladimir Ivanov; Wei Li; Weiwei Chu; Wenhan Xiong; Wenyin Fu; Wes Bouaziz; Whitney Meers; Will Constable; Xavier Martinet; Xiaojian Wu; Xinbo Gao; Xinfeng Xie; Xuchao Jia; Yaelle Goldschlag; Yann LeCun; Yashesh Gaur; Yasmine Babaei; Ye Qi; Yenda Li; Yi Wen; Yiwen Song; Youngjin Nam; Yuchen Hao; Yuchen Zhang; Yun Wang; Yuning Mao; Yuzi He; Zacharie Delpierre Coudert; Zachary DeVito; Zahra Hankir; Zhaoduo Wen; Zheng Yan; Zhengxing Chen; Zhenyu Yang; Zoe Papakipos
| {"language": ["en"], "license": "other", "tags": ["llama", "llama-3", "exllamav2", "exl2", "special_tokens", "instruct"], "pipeline_tag": "text-generation", "license_name": "llama3", "license_link": "LICENSE", "extra_gated_prompt": "### META LLAMA 3 COMMUNITY LICENSE AGREEMENT\nMeta Llama 3 Version Release Date: April 18, 2024\n\"Agreement\" means the terms and conditions for use, reproduction, distribution and modification of the Llama Materials set forth herein.\n\"Documentation\" means the specifications, manuals and documentation accompanying Meta Llama 3 distributed by Meta at https://llama.meta.com/get-started/.\n\"Licensee\" or \"you\" means you, or your employer or any other person or entity (if you are entering into this Agreement on such person or entity\u2019s behalf), of the age required under applicable laws, rules or regulations to provide legal consent and that has legal authority to bind your employer or such other person or entity if you are entering in this Agreement on their behalf.\n\"Meta Llama 3\" means the foundational large language models and software and algorithms, including machine-learning model code, trained model weights, inference-enabling code, training-enabling code, fine-tuning enabling code and other elements of the foregoing distributed by Meta at https://llama.meta.com/llama-downloads.\n\"Llama Materials\" means, collectively, Meta\u2019s proprietary Meta Llama 3 and Documentation (and any portion thereof) made available under this Agreement.\n\"Meta\" or \"we\" means Meta Platforms Ireland Limited (if you are located in or, if you are an entity, your principal place of business is in the EEA or Switzerland) and Meta Platforms, Inc. (if you are located outside of the EEA or Switzerland).\n1. License Rights and Redistribution.\na. Grant of Rights. You are granted a non-exclusive, worldwide, non-transferable and royalty-free limited license under Meta\u2019s intellectual property or other rights owned by Meta embodied in the Llama Materials to use, reproduce, distribute, copy, create derivative works of, and make modifications to the Llama Materials.\nb. Redistribution and Use.\ni. If you distribute or make available the Llama Materials (or any derivative works thereof), or a product or service that uses any of them, including another AI model, you shall (A) provide a copy of this Agreement with any such Llama Materials; and (B) prominently display \u201cBuilt with Meta Llama 3\u201d on a related website, user interface, blogpost, about page, or product documentation. If you use the Llama Materials to create, train, fine tune, or otherwise improve an AI model, which is distributed or made available, you shall also include \u201cLlama 3\u201d at the beginning of any such AI model name.\nii. If you receive Llama Materials, or any derivative works thereof, from a Licensee as part of an integrated end user product, then Section 2 of this Agreement will not apply to you.\niii. You must retain in all copies of the Llama Materials that you distribute the following attribution notice within a \u201cNotice\u201d text file distributed as a part of such copies: \u201cMeta Llama 3 is licensed under the Meta Llama 3 Community License, Copyright \u00a9 Meta Platforms, Inc. All Rights Reserved.\u201d\niv. Your use of the Llama Materials must comply with applicable laws and regulations (including trade compliance laws and regulations) and adhere to the Acceptable Use Policy for the Llama Materials (available at https://llama.meta.com/llama3/use-policy), which is hereby incorporated by reference into this Agreement.\nv. You will not use the Llama Materials or any output or results of the Llama Materials to improve any other large language model (excluding Meta Llama 3 or derivative works thereof).\n2. Additional Commercial Terms. If, on the Meta Llama 3 version release date, the monthly active users of the products or services made available by or for Licensee, or Licensee\u2019s affiliates, is greater than 700 million monthly active users in the preceding calendar month, you must request a license from Meta, which Meta may grant to you in its sole discretion, and you are not authorized to exercise any of the rights under this Agreement unless or until Meta otherwise expressly grants you such rights.\n3. Disclaimer of Warranty. UNLESS REQUIRED BY APPLICABLE LAW, THE LLAMA MATERIALS AND ANY OUTPUT AND RESULTS THEREFROM ARE PROVIDED ON AN \u201cAS IS\u201d BASIS, WITHOUT WARRANTIES OF ANY KIND, AND META DISCLAIMS ALL WARRANTIES OF ANY KIND, BOTH EXPRESS AND IMPLIED, INCLUDING, WITHOUT LIMITATION, ANY WARRANTIES OF TITLE, NON-INFRINGEMENT, MERCHANTABILITY, OR FITNESS FOR A PARTICULAR PURPOSE. YOU ARE SOLELY RESPONSIBLE FOR DETERMINING THE APPROPRIATENESS OF USING OR REDISTRIBUTING THE LLAMA MATERIALS AND ASSUME ANY RISKS ASSOCIATED WITH YOUR USE OF THE LLAMA MATERIALS AND ANY OUTPUT AND RESULTS.\n4. Limitation of Liability. IN NO EVENT WILL META OR ITS AFFILIATES BE LIABLE UNDER ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, TORT, NEGLIGENCE, PRODUCTS LIABILITY, OR OTHERWISE, ARISING OUT OF THIS AGREEMENT, FOR ANY LOST PROFITS OR ANY INDIRECT, SPECIAL, CONSEQUENTIAL, INCIDENTAL, EXEMPLARY OR PUNITIVE DAMAGES, EVEN IF META OR ITS AFFILIATES HAVE BEEN ADVISED OF THE POSSIBILITY OF ANY OF THE FOREGOING.\n5. Intellectual Property.\na. No trademark licenses are granted under this Agreement, and in connection with the Llama Materials, neither Meta nor Licensee may use any name or mark owned by or associated with the other or any of its affiliates, except as required for reasonable and customary use in describing and redistributing the Llama Materials or as set forth in this Section 5(a). Meta hereby grants you a license to use \u201cLlama 3\u201d (the \u201cMark\u201d) solely as required to comply with the last sentence of Section 1.b.i. You will comply with Meta\u2019s brand guidelines (currently accessible at https://about.meta.com/brand/resources/meta/company-brand/ ). All goodwill arising out of your use of the Mark will inure to the benefit of Meta.\nb. Subject to Meta\u2019s ownership of Llama Materials and derivatives made by or for Meta, with respect to any derivative works and modifications of the Llama Materials that are made by you, as between you and Meta, you are and will be the owner of such derivative works and modifications.\nc. If you institute litigation or other proceedings against Meta or any entity (including a cross-claim or counterclaim in a lawsuit) alleging that the Llama Materials or Meta Llama 3 outputs or results, or any portion of any of the foregoing, constitutes infringement of intellectual property or other rights owned or licensable by you, then any licenses granted to you under this Agreement shall terminate as of the date such litigation or claim is filed or instituted. You will indemnify and hold harmless Meta from and against any claim by any third party arising out of or related to your use or distribution of the Llama Materials.\n6. Term and Termination. The term of this Agreement will commence upon your acceptance of this Agreement or access to the Llama Materials and will continue in full force and effect until terminated in accordance with the terms and conditions herein. Meta may terminate this Agreement if you are in breach of any term or condition of this Agreement. Upon termination of this Agreement, you shall delete and cease use of the Llama Materials. Sections 3, 4 and 7 shall survive the termination of this Agreement.\n7. Governing Law and Jurisdiction. This Agreement will be governed and construed under the laws of the State of California without regard to choice of law principles, and the UN Convention on Contracts for the International Sale of Goods does not apply to this Agreement. The courts of California shall have exclusive jurisdiction of any dispute arising out of this Agreement.\n### Meta Llama 3 Acceptable Use Policy\nMeta is committed to promoting safe and fair use of its tools and features, including Meta Llama 3. If you access or use Meta Llama 3, you agree to this Acceptable Use Policy (\u201cPolicy\u201d). The most recent copy of this policy can be found at [https://llama.meta.com/llama3/use-policy](https://llama.meta.com/llama3/use-policy)\n#### Prohibited Uses\nWe want everyone to use Meta Llama 3 safely and responsibly. You agree you will not use, or allow others to use, Meta Llama 3 to: 1. Violate the law or others\u2019 rights, including to:\n 1. Engage in, promote, generate, contribute to, encourage, plan, incite, or further illegal or unlawful activity or content, such as:\n 1. Violence or terrorism\n 2. Exploitation or harm to children, including the solicitation, creation, acquisition, or dissemination of child exploitative content or failure to report Child Sexual Abuse Material\n 3. Human trafficking, exploitation, and sexual violence\n 4. The illegal distribution of information or materials to minors, including obscene materials, or failure to employ legally required age-gating in connection with such information or materials.\n 5. Sexual solicitation\n 6. Any other criminal activity\n 2. Engage in, promote, incite, or facilitate the harassment, abuse, threatening, or bullying of individuals or groups of individuals\n 3. Engage in, promote, incite, or facilitate discrimination or other unlawful or harmful conduct in the provision of employment, employment benefits, credit, housing, other economic benefits, or other essential goods and services\n 4. Engage in the unauthorized or unlicensed practice of any profession including, but not limited to, financial, legal, medical/health, or related professional practices\n 5. Collect, process, disclose, generate, or infer health, demographic, or other sensitive personal or private information about individuals without rights and consents required by applicable laws\n 6. Engage in or facilitate any action or generate any content that infringes, misappropriates, or otherwise violates any third-party rights, including the outputs or results of any products or services using the Llama Materials\n 7. Create, generate, or facilitate the creation of malicious code, malware, computer viruses or do anything else that could disable, overburden, interfere with or impair the proper working, integrity, operation or appearance of a website or computer system\n2. Engage in, promote, incite, facilitate, or assist in the planning or development of activities that present a risk of death or bodily harm to individuals, including use of Meta Llama 3 related to the following:\n 1. Military, warfare, nuclear industries or applications, espionage, use for materials or activities that are subject to the International Traffic Arms Regulations (ITAR) maintained by the United States Department of State\n 2. Guns and illegal weapons (including weapon development)\n 3. Illegal drugs and regulated/controlled substances\n 4. Operation of critical infrastructure, transportation technologies, or heavy machinery\n 5. Self-harm or harm to others, including suicide, cutting, and eating disorders\n 6. Any content intended to incite or promote violence, abuse, or any infliction of bodily harm to an individual\n3. Intentionally deceive or mislead others, including use of Meta Llama 3 related to the following:\n 1. Generating, promoting, or furthering fraud or the creation or promotion of disinformation\n 2. Generating, promoting, or furthering defamatory content, including the creation of defamatory statements, images, or other content\n 3. Generating, promoting, or further distributing spam\n 4. Impersonating another individual without consent, authorization, or legal right\n 5. Representing that the use of Meta Llama 3 or outputs are human-generated\n 6. Generating or facilitating false online engagement, including fake reviews and other means of fake online engagement\n4. Fail to appropriately disclose to end users any known dangers of your AI system\nPlease report any violation of this Policy, software \u201cbug,\u201d or other problems that could lead to a violation of this Policy through one of the following means:\n * Reporting issues with the model: [https://github.com/meta-llama/llama3](https://github.com/meta-llama/llama3)\n * Reporting risky content generated by the model:\n developers.facebook.com/llama_output_feedback\n * Reporting bugs and security concerns: facebook.com/whitehat/info\n * Reporting violations of the Acceptable Use Policy or unlicensed uses of Meta Llama 3: [email protected]", "extra_gated_fields": {"First Name": "text", "Last Name": "text", "Date of birth": "date_picker", "Country": "country", "Affiliation": "text", "geo": "ip_location", "By clicking Submit below I accept the terms of the license and acknowledge that the information I provide will be collected stored processed and shared in accordance with the Meta Privacy Policy": "checkbox"}, "extra_gated_description": "The information you provide will be collected, stored, processed and shared in accordance with the [Meta Privacy Policy](https://www.facebook.com/privacy/policy/).", "extra_gated_button_content": "Submit", "quantized_by": "matlok"} | matlok/lok-instruct-8b-llm3-exl2-8.0bpw | null | [
"transformers",
"safetensors",
"llama",
"text-generation",
"llama-3",
"exllamav2",
"exl2",
"special_tokens",
"instruct",
"conversational",
"en",
"license:other",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"8-bit",
"region:us"
] | null | 2024-04-19T18:12:09+00:00 | [] | [
"en"
] | TAGS
#transformers #safetensors #llama #text-generation #llama-3 #exllamav2 #exl2 #special_tokens #instruct #conversational #en #license-other #autotrain_compatible #endpoints_compatible #text-generation-inference #8-bit #region-us
| Development Llama 3 Instruct 8B build without the ".assistant" on exl2
======================================================================
Out of the box exllama v2 support for removing the .assistant tag during llama 3 instruct text responses. This was converted to exllamav2 from Llama 3 Instruct.
Model Details
-------------
Meta developed and released the Meta Llama 3 family of large language models (LLMs), a collection of pretrained and instruction tuned generative text models in 8 and 70B sizes. The Llama 3 instruction tuned models are optimized for dialogue use cases and outperform many of the available open source chat models on common industry benchmarks. Further, in developing these models, we took great care to optimize helpfulness and safety.
Model developers Meta
Variations Llama 3 comes in two sizes — 8B and 70B parameters — in pre-trained and instruction tuned variants.
Input Models input text only.
Output Models generate text and code only.
Model Architecture Llama 3 is an auto-regressive language model that uses an optimized transformer architecture. The tuned versions use supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF) to align with human preferences for helpfulness and safety.
Llama 3 family of models. Token counts refer to pretraining data only. Both the 8 and 70B versions use Grouped-Query Attention (GQA) for improved inference scalability.
Model Release Date April 18, 2024.
Status This is a static model trained on an offline dataset. Future versions of the tuned models will be released as we improve model safety with community feedback.
License A custom commercial license is available at: URL
Where to send questions or comments about the model Instructions on how to provide feedback or comments on the model can be found in the model README. For more technical information about generation parameters and recipes for how to use Llama 3 in applications, please go here.
Intended Use
------------
Intended Use Cases Llama 3 is intended for commercial and research use in English. Instruction tuned models are intended for assistant-like chat, whereas pretrained models can be adapted for a variety of natural language generation tasks.
Out-of-scope Use in any manner that violates applicable laws or regulations (including trade compliance laws). Use in any other way that is prohibited by the Acceptable Use Policy and Llama 3 Community License. Use in languages other than English.
Note: Developers may fine-tune Llama 3 models for languages beyond English provided they comply with the Llama 3 Community License and the Acceptable Use Policy.
How to use
----------
This repository contains two versions of Meta-Llama-3-8B-Instruct, for use with transformers and with the original 'llama3' codebase.
### Use with transformers
See the snippet below for usage with Transformers:
### Use with 'llama3'
Please, follow the instructions in the repository
To download Original checkpoints, see the example command below leveraging 'huggingface-cli':
For Hugging Face support, we recommend using transformers or TGI, but a similar command works.
Hardware and Software
---------------------
Training Factors We used custom training libraries, Meta's Research SuperCluster, and production clusters for pretraining. Fine-tuning, annotation, and evaluation were also performed on third-party cloud compute.
Carbon Footprint Pretraining utilized a cumulative 7.7M GPU hours of computation on hardware of type H100-80GB (TDP of 700W). Estimated total emissions were 2290 tCO2eq, 100% of which were offset by Meta’s sustainability program.
CO2 emissions during pre-training. Time: total GPU time required for training each model. Power Consumption: peak power capacity per GPU device for the GPUs used adjusted for power usage efficiency. 100% of the emissions are directly offset by Meta's sustainability program, and because we are openly releasing these models, the pretraining costs do not need to be incurred by others.
Training Data
-------------
Overview Llama 3 was pretrained on over 15 trillion tokens of data from publicly available sources. The fine-tuning data includes publicly available instruction datasets, as well as over 10M human-annotated examples. Neither the pretraining nor the fine-tuning datasets include Meta user data.
Data Freshness The pretraining data has a cutoff of March 2023 for the 7B and December 2023 for the 70B models respectively.
Benchmarks
----------
In this section, we report the results for Llama 3 models on standard automatic benchmarks. For all the evaluations, we use our internal evaluations library. For details on the methodology see here.
### Base pretrained models
### Instruction tuned models
### Responsibility & Safety
We believe that an open approach to AI leads to better, safer products, faster innovation, and a bigger overall market. We are committed to Responsible AI development and took a series of steps to limit misuse and harm and support the open source community.
Foundation models are widely capable technologies that are built to be used for a diverse range of applications. They are not designed to meet every developer preference on safety levels for all use cases, out-of-the-box, as those by their nature will differ across different applications.
Rather, responsible LLM-application deployment is achieved by implementing a series of safety best practices throughout the development of such applications, from the model pre-training, fine-tuning and the deployment of systems composed of safeguards to tailor the safety needs specifically to the use case and audience.
As part of the Llama 3 release, we updated our Responsible Use Guide to outline the steps and best practices for developers to implement model and system level safety for their application. We also provide a set of resources including Meta Llama Guard 2 and Code Shield safeguards. These tools have proven to drastically reduce residual risks of LLM Systems, while maintaining a high level of helpfulness. We encourage developers to tune and deploy these safeguards according to their needs and we provide a reference implementation to get you started.
#### Llama 3-Instruct
As outlined in the Responsible Use Guide, some trade-off between model helpfulness and model alignment is likely unavoidable. Developers should exercise discretion about how to weigh the benefits of alignment and helpfulness for their specific use case and audience. Developers should be mindful of residual risks when using Llama models and leverage additional safety tools as needed to reach the right safety bar for their use case.
Safety
For our instruction tuned model, we conducted extensive red teaming exercises, performed adversarial evaluations and implemented safety mitigations techniques to lower residual risks. As with any Large Language Model, residual risks will likely remain and we recommend that developers assess these risks in the context of their use case. In parallel, we are working with the community to make AI safety benchmark standards transparent, rigorous and interpretable.
Refusals
In addition to residual risks, we put a great emphasis on model refusals to benign prompts. Over-refusing not only can impact the user experience but could even be harmful in certain contexts as well. We’ve heard the feedback from the developer community and improved our fine tuning to ensure that Llama 3 is significantly less likely to falsely refuse to answer prompts than Llama 2.
We built internal benchmarks and developed mitigations to limit false refusals making Llama 3 our most helpful model to date.
#### Responsible release
In addition to responsible use considerations outlined above, we followed a rigorous process that requires us to take extra measures against misuse and critical risks before we make our release decision.
Misuse
If you access or use Llama 3, you agree to the Acceptable Use Policy. The most recent copy of this policy can be found at URL
#### Critical risks
CBRNE (Chemical, Biological, Radiological, Nuclear, and high yield Explosives)
We have conducted a two fold assessment of the safety of the model in this area:
* Iterative testing during model training to assess the safety of responses related to CBRNE threats and other adversarial risks.
* Involving external CBRNE experts to conduct an uplift test assessing the ability of the model to accurately provide expert knowledge and reduce barriers to potential CBRNE misuse, by reference to what can be achieved using web search (without the model).
### Cyber Security
We have evaluated Llama 3 with CyberSecEval, Meta’s cybersecurity safety eval suite, measuring Llama 3’s propensity to suggest insecure code when used as a coding assistant, and Llama 3’s propensity to comply with requests to help carry out cyber attacks, where attacks are defined by the industry standard MITRE ATT&CK cyber attack ontology. On our insecure coding and cyber attacker helpfulness tests, Llama 3 behaved in the same range or safer than models of equivalent coding capability.
### Child Safety
Child Safety risk assessments were conducted using a team of experts, to assess the model’s capability to produce outputs that could result in Child Safety risks and inform on any necessary and appropriate risk mitigations via fine tuning. We leveraged those expert red teaming sessions to expand the coverage of our evaluation benchmarks through Llama 3 model development. For Llama 3, we conducted new in-depth sessions using objective based methodologies to assess the model risks along multiple attack vectors. We also partnered with content specialists to perform red teaming exercises assessing potentially violating content while taking account of market specific nuances or experiences.
### Community
Generative AI safety requires expertise and tooling, and we believe in the strength of the open community to accelerate its progress. We are active members of open consortiums, including the AI Alliance, Partnership in AI and MLCommons, actively contributing to safety standardization and transparency. We encourage the community to adopt taxonomies like the MLCommons Proof of Concept evaluation to facilitate collaboration and transparency on safety and content evaluations. Our Purple Llama tools are open sourced for the community to use and widely distributed across ecosystem partners including cloud service providers. We encourage community contributions to our Github repository.
Finally, we put in place a set of resources including an output reporting mechanism and bug bounty program to continuously improve the Llama technology with the help of the community.
Ethical Considerations and Limitations
--------------------------------------
The core values of Llama 3 are openness, inclusivity and helpfulness. It is meant to serve everyone, and to work for a wide range of use cases. It is thus designed to be accessible to people across many different backgrounds, experiences and perspectives. Llama 3 addresses users and their needs as they are, without insertion unnecessary judgment or normativity, while reflecting the understanding that even content that may appear problematic in some cases can serve valuable purposes in others. It respects the dignity and autonomy of all users, especially in terms of the values of free thought and expression that power innovation and progress.
But Llama 3 is a new technology, and like any new technology, there are risks associated with its use. Testing conducted to date has been in English, and has not covered, nor could it cover, all scenarios. For these reasons, as with all LLMs, Llama 3’s potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate, biased or other objectionable responses to user prompts. Therefore, before deploying any applications of Llama 3 models, developers should perform safety testing and tuning tailored to their specific applications of the model. As outlined in the Responsible Use Guide, we recommend incorporating Purple Llama solutions into your workflows and specifically Llama Guard which provides a base model to filter input and output prompts to layer system-level safety on top of model-level safety.
Please see the Responsible Use Guide available at URL
instructions
@article{llama3modelcard,
title={Llama 3 Model Card},
author={AI@Meta},
year={2024},
url = {URL
}
Contributors
------------
Aaditya Singh; Aaron Grattafiori; Abhimanyu Dubey; Abhinav Jauhri; Abhinav Pandey; Abhishek Kadian; Adam Kelsey; Adi Gangidi; Ahmad Al-Dahle; Ahuva Goldstand; Aiesha Letman; Ajay Menon; Akhil Mathur; Alan Schelten; Alex Vaughan; Amy Yang; Andrei Lupu; Andres Alvarado; Andrew Gallagher; Andrew Gu; Andrew Ho; Andrew Poulton; Andrew Ryan; Angela Fan; Ankit Ramchandani; Anthony Hartshorn; Archi Mitra; Archie Sravankumar; Artem Korenev; Arun Rao; Ashley Gabriel; Ashwin Bharambe; Assaf Eisenman; Aston Zhang; Aurelien Rodriguez; Austen Gregerson; Ava Spataru; Baptiste Roziere; Ben Maurer; Benjamin Leonhardi; Bernie Huang; Bhargavi Paranjape; Bing Liu; Binh Tang; Bobbie Chern; Brani Stojkovic; Brian Fuller; Catalina Mejia Arenas; Chao Zhou; Charlotte Caucheteux; Chaya Nayak; Ching-Hsiang Chu; Chloe Bi; Chris Cai; Chris Cox; Chris Marra; Chris McConnell; Christian Keller; Christoph Feichtenhofer; Christophe Touret; Chunyang Wu; Corinne Wong; Cristian Canton Ferrer; Damien Allonsius; Daniel Kreymer; Daniel Haziza; Daniel Li; Danielle Pintz; Danny Livshits; Danny Wyatt; David Adkins; David Esiobu; David Xu; Davide Testuggine; Delia David; Devi Parikh; Dhruv Choudhary; Dhruv Mahajan; Diana Liskovich; Diego Garcia-Olano; Diego Perino; Dieuwke Hupkes; Dingkang Wang; Dustin Holland; Egor Lakomkin; Elina Lobanova; Xiaoqing Ellen Tan; Emily Dinan; Eric Smith; Erik Brinkman; Esteban Arcaute; Filip Radenovic; Firat Ozgenel; Francesco Caggioni; Frank Seide; Frank Zhang; Gabriel Synnaeve; Gabriella Schwarz; Gabrielle Lee; Gada Badeer; Georgia Anderson; Graeme Nail; Gregoire Mialon; Guan Pang; Guillem Cucurell; Hailey Nguyen; Hannah Korevaar; Hannah Wang; Haroun Habeeb; Harrison Rudolph; Henry Aspegren; Hu Xu; Hugo Touvron; Iga Kozlowska; Igor Molybog; Igor Tufanov; Iliyan Zarov; Imanol Arrieta Ibarra; Irina-Elena Veliche; Isabel Kloumann; Ishan Misra; Ivan Evtimov; Jacob Xu; Jade Copet; Jake Weissman; Jan Geffert; Jana Vranes; Japhet Asher; Jason Park; Jay Mahadeokar; Jean-Baptiste Gaya; Jeet Shah; Jelmer van der Linde; Jennifer Chan; Jenny Hong; Jenya Lee; Jeremy Fu; Jeremy Teboul; Jianfeng Chi; Jianyu Huang; Jie Wang; Jiecao Yu; Joanna Bitton; Joe Spisak; Joelle Pineau; Jon Carvill; Jongsoo Park; Joseph Rocca; Joshua Johnstun; Junteng Jia; Kalyan Vasuden Alwala; Kam Hou U; Kate Plawiak; Kartikeya Upasani; Kaushik Veeraraghavan; Ke Li; Kenneth Heafield; Kevin Stone; Khalid El-Arini; Krithika Iyer; Kshitiz Malik; Kuenley Chiu; Kunal Bhalla; Kyle Huang; Lakshya Garg; Lauren Rantala-Yeary; Laurens van der Maaten; Lawrence Chen; Leandro Silva; Lee Bell; Lei Zhang; Liang Tan; Louis Martin; Lovish Madaan; Luca Wehrstedt; Lukas Blecher; Luke de Oliveira; Madeline Muzzi; Madian Khabsa; Manav Avlani; Mannat Singh; Manohar Paluri; Mark Zuckerberg; Marcin Kardas; Martynas Mankus; Mathew Oldham; Mathieu Rita; Matthew Lennie; Maya Pavlova; Meghan Keneally; Melanie Kambadur; Mihir Patel; Mikayel Samvelyan; Mike Clark; Mike Lewis; Min Si; Mitesh Kumar Singh; Mo Metanat; Mona Hassan; Naman Goyal; Narjes Torabi; Nicolas Usunier; Nikolay Bashlykov; Nikolay Bogoychev; Niladri Chatterji; Ning Dong; Oliver Aobo Yang; Olivier Duchenne; Onur Celebi; Parth Parekh; Patrick Alrassy; Paul Saab; Pavan Balaji; Pedro Rittner; Pengchuan Zhang; Pengwei Li; Petar Vasic; Peter Weng; Polina Zvyagina; Prajjwal Bhargava; Pratik Dubal; Praveen Krishnan; Punit Singh Koura; Qing He; Rachel Rodriguez; Ragavan Srinivasan; Rahul Mitra; Ramon Calderer; Raymond Li; Robert Stojnic; Roberta Raileanu; Robin Battey; Rocky Wang; Rohit Girdhar; Rohit Patel; Romain Sauvestre; Ronnie Polidoro; Roshan Sumbaly; Ross Taylor; Ruan Silva; Rui Hou; Rui Wang; Russ Howes; Ruty Rinott; Saghar Hosseini; Sai Jayesh Bondu; Samyak Datta; Sanjay Singh; Sara Chugh; Sargun Dhillon; Satadru Pan; Sean Bell; Sergey Edunov; Shaoliang Nie; Sharan Narang; Sharath Raparthy; Shaun Lindsay; Sheng Feng; Sheng Shen; Shenghao Lin; Shiva Shankar; Shruti Bhosale; Shun Zhang; Simon Vandenhende; Sinong Wang; Seohyun Sonia Kim; Soumya Batra; Sten Sootla; Steve Kehoe; Suchin Gururangan; Sumit Gupta; Sunny Virk; Sydney Borodinsky; Tamar Glaser; Tamar Herman; Tamara Best; Tara Fowler; Thomas Georgiou; Thomas Scialom; Tianhe Li; Todor Mihaylov; Tong Xiao; Ujjwal Karn; Vedanuj Goswami; Vibhor Gupta; Vignesh Ramanathan; Viktor Kerkez; Vinay Satish Kumar; Vincent Gonguet; Vish Vogeti; Vlad Poenaru; Vlad Tiberiu Mihailescu; Vladan Petrovic; Vladimir Ivanov; Wei Li; Weiwei Chu; Wenhan Xiong; Wenyin Fu; Wes Bouaziz; Whitney Meers; Will Constable; Xavier Martinet; Xiaojian Wu; Xinbo Gao; Xinfeng Xie; Xuchao Jia; Yaelle Goldschlag; Yann LeCun; Yashesh Gaur; Yasmine Babaei; Ye Qi; Yenda Li; Yi Wen; Yiwen Song; Youngjin Nam; Yuchen Hao; Yuchen Zhang; Yun Wang; Yuning Mao; Yuzi He; Zacharie Delpierre Coudert; Zachary DeVito; Zahra Hankir; Zhaoduo Wen; Zheng Yan; Zhengxing Chen; Zhenyu Yang; Zoe Papakipos
| [
"### Use with transformers\n\n\nSee the snippet below for usage with Transformers:",
"### Use with 'llama3'\n\n\nPlease, follow the instructions in the repository\n\n\nTo download Original checkpoints, see the example command below leveraging 'huggingface-cli':\n\n\nFor Hugging Face support, we recommend using transformers or TGI, but a similar command works.\n\n\nHardware and Software\n---------------------\n\n\nTraining Factors We used custom training libraries, Meta's Research SuperCluster, and production clusters for pretraining. Fine-tuning, annotation, and evaluation were also performed on third-party cloud compute.\n\n\nCarbon Footprint Pretraining utilized a cumulative 7.7M GPU hours of computation on hardware of type H100-80GB (TDP of 700W). Estimated total emissions were 2290 tCO2eq, 100% of which were offset by Meta’s sustainability program.\n\n\n\nCO2 emissions during pre-training. Time: total GPU time required for training each model. Power Consumption: peak power capacity per GPU device for the GPUs used adjusted for power usage efficiency. 100% of the emissions are directly offset by Meta's sustainability program, and because we are openly releasing these models, the pretraining costs do not need to be incurred by others.\n\n\nTraining Data\n-------------\n\n\nOverview Llama 3 was pretrained on over 15 trillion tokens of data from publicly available sources. The fine-tuning data includes publicly available instruction datasets, as well as over 10M human-annotated examples. Neither the pretraining nor the fine-tuning datasets include Meta user data.\n\n\nData Freshness The pretraining data has a cutoff of March 2023 for the 7B and December 2023 for the 70B models respectively.\n\n\nBenchmarks\n----------\n\n\nIn this section, we report the results for Llama 3 models on standard automatic benchmarks. For all the evaluations, we use our internal evaluations library. For details on the methodology see here.",
"### Base pretrained models",
"### Instruction tuned models",
"### Responsibility & Safety\n\n\nWe believe that an open approach to AI leads to better, safer products, faster innovation, and a bigger overall market. We are committed to Responsible AI development and took a series of steps to limit misuse and harm and support the open source community.\n\n\nFoundation models are widely capable technologies that are built to be used for a diverse range of applications. They are not designed to meet every developer preference on safety levels for all use cases, out-of-the-box, as those by their nature will differ across different applications.\n\n\nRather, responsible LLM-application deployment is achieved by implementing a series of safety best practices throughout the development of such applications, from the model pre-training, fine-tuning and the deployment of systems composed of safeguards to tailor the safety needs specifically to the use case and audience.\n\n\nAs part of the Llama 3 release, we updated our Responsible Use Guide to outline the steps and best practices for developers to implement model and system level safety for their application. We also provide a set of resources including Meta Llama Guard 2 and Code Shield safeguards. These tools have proven to drastically reduce residual risks of LLM Systems, while maintaining a high level of helpfulness. We encourage developers to tune and deploy these safeguards according to their needs and we provide a reference implementation to get you started.",
"#### Llama 3-Instruct\n\n\nAs outlined in the Responsible Use Guide, some trade-off between model helpfulness and model alignment is likely unavoidable. Developers should exercise discretion about how to weigh the benefits of alignment and helpfulness for their specific use case and audience. Developers should be mindful of residual risks when using Llama models and leverage additional safety tools as needed to reach the right safety bar for their use case.\n\n\nSafety\n\n\nFor our instruction tuned model, we conducted extensive red teaming exercises, performed adversarial evaluations and implemented safety mitigations techniques to lower residual risks. As with any Large Language Model, residual risks will likely remain and we recommend that developers assess these risks in the context of their use case. In parallel, we are working with the community to make AI safety benchmark standards transparent, rigorous and interpretable.\n\n\nRefusals\n\n\nIn addition to residual risks, we put a great emphasis on model refusals to benign prompts. Over-refusing not only can impact the user experience but could even be harmful in certain contexts as well. We’ve heard the feedback from the developer community and improved our fine tuning to ensure that Llama 3 is significantly less likely to falsely refuse to answer prompts than Llama 2.\n\n\nWe built internal benchmarks and developed mitigations to limit false refusals making Llama 3 our most helpful model to date.",
"#### Responsible release\n\n\nIn addition to responsible use considerations outlined above, we followed a rigorous process that requires us to take extra measures against misuse and critical risks before we make our release decision.\n\n\nMisuse\n\n\nIf you access or use Llama 3, you agree to the Acceptable Use Policy. The most recent copy of this policy can be found at URL",
"#### Critical risks\n\n\nCBRNE (Chemical, Biological, Radiological, Nuclear, and high yield Explosives)\n\n\nWe have conducted a two fold assessment of the safety of the model in this area:\n\n\n* Iterative testing during model training to assess the safety of responses related to CBRNE threats and other adversarial risks.\n* Involving external CBRNE experts to conduct an uplift test assessing the ability of the model to accurately provide expert knowledge and reduce barriers to potential CBRNE misuse, by reference to what can be achieved using web search (without the model).",
"### Cyber Security\n\n\nWe have evaluated Llama 3 with CyberSecEval, Meta’s cybersecurity safety eval suite, measuring Llama 3’s propensity to suggest insecure code when used as a coding assistant, and Llama 3’s propensity to comply with requests to help carry out cyber attacks, where attacks are defined by the industry standard MITRE ATT&CK cyber attack ontology. On our insecure coding and cyber attacker helpfulness tests, Llama 3 behaved in the same range or safer than models of equivalent coding capability.",
"### Child Safety\n\n\nChild Safety risk assessments were conducted using a team of experts, to assess the model’s capability to produce outputs that could result in Child Safety risks and inform on any necessary and appropriate risk mitigations via fine tuning. We leveraged those expert red teaming sessions to expand the coverage of our evaluation benchmarks through Llama 3 model development. For Llama 3, we conducted new in-depth sessions using objective based methodologies to assess the model risks along multiple attack vectors. We also partnered with content specialists to perform red teaming exercises assessing potentially violating content while taking account of market specific nuances or experiences.",
"### Community\n\n\nGenerative AI safety requires expertise and tooling, and we believe in the strength of the open community to accelerate its progress. We are active members of open consortiums, including the AI Alliance, Partnership in AI and MLCommons, actively contributing to safety standardization and transparency. We encourage the community to adopt taxonomies like the MLCommons Proof of Concept evaluation to facilitate collaboration and transparency on safety and content evaluations. Our Purple Llama tools are open sourced for the community to use and widely distributed across ecosystem partners including cloud service providers. We encourage community contributions to our Github repository.\n\n\nFinally, we put in place a set of resources including an output reporting mechanism and bug bounty program to continuously improve the Llama technology with the help of the community.\n\n\nEthical Considerations and Limitations\n--------------------------------------\n\n\nThe core values of Llama 3 are openness, inclusivity and helpfulness. It is meant to serve everyone, and to work for a wide range of use cases. It is thus designed to be accessible to people across many different backgrounds, experiences and perspectives. Llama 3 addresses users and their needs as they are, without insertion unnecessary judgment or normativity, while reflecting the understanding that even content that may appear problematic in some cases can serve valuable purposes in others. It respects the dignity and autonomy of all users, especially in terms of the values of free thought and expression that power innovation and progress.\n\n\nBut Llama 3 is a new technology, and like any new technology, there are risks associated with its use. Testing conducted to date has been in English, and has not covered, nor could it cover, all scenarios. For these reasons, as with all LLMs, Llama 3’s potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate, biased or other objectionable responses to user prompts. Therefore, before deploying any applications of Llama 3 models, developers should perform safety testing and tuning tailored to their specific applications of the model. As outlined in the Responsible Use Guide, we recommend incorporating Purple Llama solutions into your workflows and specifically Llama Guard which provides a base model to filter input and output prompts to layer system-level safety on top of model-level safety.\n\n\nPlease see the Responsible Use Guide available at URL\n\n\ninstructions\n\n\n@article{llama3modelcard,\n\n\ntitle={Llama 3 Model Card},\n\n\nauthor={AI@Meta},\n\n\nyear={2024},\n\n\nurl = {URL\n\n\n}\n\n\nContributors\n------------\n\n\nAaditya Singh; Aaron Grattafiori; Abhimanyu Dubey; Abhinav Jauhri; Abhinav Pandey; Abhishek Kadian; Adam Kelsey; Adi Gangidi; Ahmad Al-Dahle; Ahuva Goldstand; Aiesha Letman; Ajay Menon; Akhil Mathur; Alan Schelten; Alex Vaughan; Amy Yang; Andrei Lupu; Andres Alvarado; Andrew Gallagher; Andrew Gu; Andrew Ho; Andrew Poulton; Andrew Ryan; Angela Fan; Ankit Ramchandani; Anthony Hartshorn; Archi Mitra; Archie Sravankumar; Artem Korenev; Arun Rao; Ashley Gabriel; Ashwin Bharambe; Assaf Eisenman; Aston Zhang; Aurelien Rodriguez; Austen Gregerson; Ava Spataru; Baptiste Roziere; Ben Maurer; Benjamin Leonhardi; Bernie Huang; Bhargavi Paranjape; Bing Liu; Binh Tang; Bobbie Chern; Brani Stojkovic; Brian Fuller; Catalina Mejia Arenas; Chao Zhou; Charlotte Caucheteux; Chaya Nayak; Ching-Hsiang Chu; Chloe Bi; Chris Cai; Chris Cox; Chris Marra; Chris McConnell; Christian Keller; Christoph Feichtenhofer; Christophe Touret; Chunyang Wu; Corinne Wong; Cristian Canton Ferrer; Damien Allonsius; Daniel Kreymer; Daniel Haziza; Daniel Li; Danielle Pintz; Danny Livshits; Danny Wyatt; David Adkins; David Esiobu; David Xu; Davide Testuggine; Delia David; Devi Parikh; Dhruv Choudhary; Dhruv Mahajan; Diana Liskovich; Diego Garcia-Olano; Diego Perino; Dieuwke Hupkes; Dingkang Wang; Dustin Holland; Egor Lakomkin; Elina Lobanova; Xiaoqing Ellen Tan; Emily Dinan; Eric Smith; Erik Brinkman; Esteban Arcaute; Filip Radenovic; Firat Ozgenel; Francesco Caggioni; Frank Seide; Frank Zhang; Gabriel Synnaeve; Gabriella Schwarz; Gabrielle Lee; Gada Badeer; Georgia Anderson; Graeme Nail; Gregoire Mialon; Guan Pang; Guillem Cucurell; Hailey Nguyen; Hannah Korevaar; Hannah Wang; Haroun Habeeb; Harrison Rudolph; Henry Aspegren; Hu Xu; Hugo Touvron; Iga Kozlowska; Igor Molybog; Igor Tufanov; Iliyan Zarov; Imanol Arrieta Ibarra; Irina-Elena Veliche; Isabel Kloumann; Ishan Misra; Ivan Evtimov; Jacob Xu; Jade Copet; Jake Weissman; Jan Geffert; Jana Vranes; Japhet Asher; Jason Park; Jay Mahadeokar; Jean-Baptiste Gaya; Jeet Shah; Jelmer van der Linde; Jennifer Chan; Jenny Hong; Jenya Lee; Jeremy Fu; Jeremy Teboul; Jianfeng Chi; Jianyu Huang; Jie Wang; Jiecao Yu; Joanna Bitton; Joe Spisak; Joelle Pineau; Jon Carvill; Jongsoo Park; Joseph Rocca; Joshua Johnstun; Junteng Jia; Kalyan Vasuden Alwala; Kam Hou U; Kate Plawiak; Kartikeya Upasani; Kaushik Veeraraghavan; Ke Li; Kenneth Heafield; Kevin Stone; Khalid El-Arini; Krithika Iyer; Kshitiz Malik; Kuenley Chiu; Kunal Bhalla; Kyle Huang; Lakshya Garg; Lauren Rantala-Yeary; Laurens van der Maaten; Lawrence Chen; Leandro Silva; Lee Bell; Lei Zhang; Liang Tan; Louis Martin; Lovish Madaan; Luca Wehrstedt; Lukas Blecher; Luke de Oliveira; Madeline Muzzi; Madian Khabsa; Manav Avlani; Mannat Singh; Manohar Paluri; Mark Zuckerberg; Marcin Kardas; Martynas Mankus; Mathew Oldham; Mathieu Rita; Matthew Lennie; Maya Pavlova; Meghan Keneally; Melanie Kambadur; Mihir Patel; Mikayel Samvelyan; Mike Clark; Mike Lewis; Min Si; Mitesh Kumar Singh; Mo Metanat; Mona Hassan; Naman Goyal; Narjes Torabi; Nicolas Usunier; Nikolay Bashlykov; Nikolay Bogoychev; Niladri Chatterji; Ning Dong; Oliver Aobo Yang; Olivier Duchenne; Onur Celebi; Parth Parekh; Patrick Alrassy; Paul Saab; Pavan Balaji; Pedro Rittner; Pengchuan Zhang; Pengwei Li; Petar Vasic; Peter Weng; Polina Zvyagina; Prajjwal Bhargava; Pratik Dubal; Praveen Krishnan; Punit Singh Koura; Qing He; Rachel Rodriguez; Ragavan Srinivasan; Rahul Mitra; Ramon Calderer; Raymond Li; Robert Stojnic; Roberta Raileanu; Robin Battey; Rocky Wang; Rohit Girdhar; Rohit Patel; Romain Sauvestre; Ronnie Polidoro; Roshan Sumbaly; Ross Taylor; Ruan Silva; Rui Hou; Rui Wang; Russ Howes; Ruty Rinott; Saghar Hosseini; Sai Jayesh Bondu; Samyak Datta; Sanjay Singh; Sara Chugh; Sargun Dhillon; Satadru Pan; Sean Bell; Sergey Edunov; Shaoliang Nie; Sharan Narang; Sharath Raparthy; Shaun Lindsay; Sheng Feng; Sheng Shen; Shenghao Lin; Shiva Shankar; Shruti Bhosale; Shun Zhang; Simon Vandenhende; Sinong Wang; Seohyun Sonia Kim; Soumya Batra; Sten Sootla; Steve Kehoe; Suchin Gururangan; Sumit Gupta; Sunny Virk; Sydney Borodinsky; Tamar Glaser; Tamar Herman; Tamara Best; Tara Fowler; Thomas Georgiou; Thomas Scialom; Tianhe Li; Todor Mihaylov; Tong Xiao; Ujjwal Karn; Vedanuj Goswami; Vibhor Gupta; Vignesh Ramanathan; Viktor Kerkez; Vinay Satish Kumar; Vincent Gonguet; Vish Vogeti; Vlad Poenaru; Vlad Tiberiu Mihailescu; Vladan Petrovic; Vladimir Ivanov; Wei Li; Weiwei Chu; Wenhan Xiong; Wenyin Fu; Wes Bouaziz; Whitney Meers; Will Constable; Xavier Martinet; Xiaojian Wu; Xinbo Gao; Xinfeng Xie; Xuchao Jia; Yaelle Goldschlag; Yann LeCun; Yashesh Gaur; Yasmine Babaei; Ye Qi; Yenda Li; Yi Wen; Yiwen Song; Youngjin Nam; Yuchen Hao; Yuchen Zhang; Yun Wang; Yuning Mao; Yuzi He; Zacharie Delpierre Coudert; Zachary DeVito; Zahra Hankir; Zhaoduo Wen; Zheng Yan; Zhengxing Chen; Zhenyu Yang; Zoe Papakipos"
] | [
"TAGS\n#transformers #safetensors #llama #text-generation #llama-3 #exllamav2 #exl2 #special_tokens #instruct #conversational #en #license-other #autotrain_compatible #endpoints_compatible #text-generation-inference #8-bit #region-us \n",
"### Use with transformers\n\n\nSee the snippet below for usage with Transformers:",
"### Use with 'llama3'\n\n\nPlease, follow the instructions in the repository\n\n\nTo download Original checkpoints, see the example command below leveraging 'huggingface-cli':\n\n\nFor Hugging Face support, we recommend using transformers or TGI, but a similar command works.\n\n\nHardware and Software\n---------------------\n\n\nTraining Factors We used custom training libraries, Meta's Research SuperCluster, and production clusters for pretraining. Fine-tuning, annotation, and evaluation were also performed on third-party cloud compute.\n\n\nCarbon Footprint Pretraining utilized a cumulative 7.7M GPU hours of computation on hardware of type H100-80GB (TDP of 700W). Estimated total emissions were 2290 tCO2eq, 100% of which were offset by Meta’s sustainability program.\n\n\n\nCO2 emissions during pre-training. Time: total GPU time required for training each model. Power Consumption: peak power capacity per GPU device for the GPUs used adjusted for power usage efficiency. 100% of the emissions are directly offset by Meta's sustainability program, and because we are openly releasing these models, the pretraining costs do not need to be incurred by others.\n\n\nTraining Data\n-------------\n\n\nOverview Llama 3 was pretrained on over 15 trillion tokens of data from publicly available sources. The fine-tuning data includes publicly available instruction datasets, as well as over 10M human-annotated examples. Neither the pretraining nor the fine-tuning datasets include Meta user data.\n\n\nData Freshness The pretraining data has a cutoff of March 2023 for the 7B and December 2023 for the 70B models respectively.\n\n\nBenchmarks\n----------\n\n\nIn this section, we report the results for Llama 3 models on standard automatic benchmarks. For all the evaluations, we use our internal evaluations library. For details on the methodology see here.",
"### Base pretrained models",
"### Instruction tuned models",
"### Responsibility & Safety\n\n\nWe believe that an open approach to AI leads to better, safer products, faster innovation, and a bigger overall market. We are committed to Responsible AI development and took a series of steps to limit misuse and harm and support the open source community.\n\n\nFoundation models are widely capable technologies that are built to be used for a diverse range of applications. They are not designed to meet every developer preference on safety levels for all use cases, out-of-the-box, as those by their nature will differ across different applications.\n\n\nRather, responsible LLM-application deployment is achieved by implementing a series of safety best practices throughout the development of such applications, from the model pre-training, fine-tuning and the deployment of systems composed of safeguards to tailor the safety needs specifically to the use case and audience.\n\n\nAs part of the Llama 3 release, we updated our Responsible Use Guide to outline the steps and best practices for developers to implement model and system level safety for their application. We also provide a set of resources including Meta Llama Guard 2 and Code Shield safeguards. These tools have proven to drastically reduce residual risks of LLM Systems, while maintaining a high level of helpfulness. We encourage developers to tune and deploy these safeguards according to their needs and we provide a reference implementation to get you started.",
"#### Llama 3-Instruct\n\n\nAs outlined in the Responsible Use Guide, some trade-off between model helpfulness and model alignment is likely unavoidable. Developers should exercise discretion about how to weigh the benefits of alignment and helpfulness for their specific use case and audience. Developers should be mindful of residual risks when using Llama models and leverage additional safety tools as needed to reach the right safety bar for their use case.\n\n\nSafety\n\n\nFor our instruction tuned model, we conducted extensive red teaming exercises, performed adversarial evaluations and implemented safety mitigations techniques to lower residual risks. As with any Large Language Model, residual risks will likely remain and we recommend that developers assess these risks in the context of their use case. In parallel, we are working with the community to make AI safety benchmark standards transparent, rigorous and interpretable.\n\n\nRefusals\n\n\nIn addition to residual risks, we put a great emphasis on model refusals to benign prompts. Over-refusing not only can impact the user experience but could even be harmful in certain contexts as well. We’ve heard the feedback from the developer community and improved our fine tuning to ensure that Llama 3 is significantly less likely to falsely refuse to answer prompts than Llama 2.\n\n\nWe built internal benchmarks and developed mitigations to limit false refusals making Llama 3 our most helpful model to date.",
"#### Responsible release\n\n\nIn addition to responsible use considerations outlined above, we followed a rigorous process that requires us to take extra measures against misuse and critical risks before we make our release decision.\n\n\nMisuse\n\n\nIf you access or use Llama 3, you agree to the Acceptable Use Policy. The most recent copy of this policy can be found at URL",
"#### Critical risks\n\n\nCBRNE (Chemical, Biological, Radiological, Nuclear, and high yield Explosives)\n\n\nWe have conducted a two fold assessment of the safety of the model in this area:\n\n\n* Iterative testing during model training to assess the safety of responses related to CBRNE threats and other adversarial risks.\n* Involving external CBRNE experts to conduct an uplift test assessing the ability of the model to accurately provide expert knowledge and reduce barriers to potential CBRNE misuse, by reference to what can be achieved using web search (without the model).",
"### Cyber Security\n\n\nWe have evaluated Llama 3 with CyberSecEval, Meta’s cybersecurity safety eval suite, measuring Llama 3’s propensity to suggest insecure code when used as a coding assistant, and Llama 3’s propensity to comply with requests to help carry out cyber attacks, where attacks are defined by the industry standard MITRE ATT&CK cyber attack ontology. On our insecure coding and cyber attacker helpfulness tests, Llama 3 behaved in the same range or safer than models of equivalent coding capability.",
"### Child Safety\n\n\nChild Safety risk assessments were conducted using a team of experts, to assess the model’s capability to produce outputs that could result in Child Safety risks and inform on any necessary and appropriate risk mitigations via fine tuning. We leveraged those expert red teaming sessions to expand the coverage of our evaluation benchmarks through Llama 3 model development. For Llama 3, we conducted new in-depth sessions using objective based methodologies to assess the model risks along multiple attack vectors. We also partnered with content specialists to perform red teaming exercises assessing potentially violating content while taking account of market specific nuances or experiences.",
"### Community\n\n\nGenerative AI safety requires expertise and tooling, and we believe in the strength of the open community to accelerate its progress. We are active members of open consortiums, including the AI Alliance, Partnership in AI and MLCommons, actively contributing to safety standardization and transparency. We encourage the community to adopt taxonomies like the MLCommons Proof of Concept evaluation to facilitate collaboration and transparency on safety and content evaluations. Our Purple Llama tools are open sourced for the community to use and widely distributed across ecosystem partners including cloud service providers. We encourage community contributions to our Github repository.\n\n\nFinally, we put in place a set of resources including an output reporting mechanism and bug bounty program to continuously improve the Llama technology with the help of the community.\n\n\nEthical Considerations and Limitations\n--------------------------------------\n\n\nThe core values of Llama 3 are openness, inclusivity and helpfulness. It is meant to serve everyone, and to work for a wide range of use cases. It is thus designed to be accessible to people across many different backgrounds, experiences and perspectives. Llama 3 addresses users and their needs as they are, without insertion unnecessary judgment or normativity, while reflecting the understanding that even content that may appear problematic in some cases can serve valuable purposes in others. It respects the dignity and autonomy of all users, especially in terms of the values of free thought and expression that power innovation and progress.\n\n\nBut Llama 3 is a new technology, and like any new technology, there are risks associated with its use. Testing conducted to date has been in English, and has not covered, nor could it cover, all scenarios. For these reasons, as with all LLMs, Llama 3’s potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate, biased or other objectionable responses to user prompts. Therefore, before deploying any applications of Llama 3 models, developers should perform safety testing and tuning tailored to their specific applications of the model. As outlined in the Responsible Use Guide, we recommend incorporating Purple Llama solutions into your workflows and specifically Llama Guard which provides a base model to filter input and output prompts to layer system-level safety on top of model-level safety.\n\n\nPlease see the Responsible Use Guide available at URL\n\n\ninstructions\n\n\n@article{llama3modelcard,\n\n\ntitle={Llama 3 Model Card},\n\n\nauthor={AI@Meta},\n\n\nyear={2024},\n\n\nurl = {URL\n\n\n}\n\n\nContributors\n------------\n\n\nAaditya Singh; Aaron Grattafiori; Abhimanyu Dubey; Abhinav Jauhri; Abhinav Pandey; Abhishek Kadian; Adam Kelsey; Adi Gangidi; Ahmad Al-Dahle; Ahuva Goldstand; Aiesha Letman; Ajay Menon; Akhil Mathur; Alan Schelten; Alex Vaughan; Amy Yang; Andrei Lupu; Andres Alvarado; Andrew Gallagher; Andrew Gu; Andrew Ho; Andrew Poulton; Andrew Ryan; Angela Fan; Ankit Ramchandani; Anthony Hartshorn; Archi Mitra; Archie Sravankumar; Artem Korenev; Arun Rao; Ashley Gabriel; Ashwin Bharambe; Assaf Eisenman; Aston Zhang; Aurelien Rodriguez; Austen Gregerson; Ava Spataru; Baptiste Roziere; Ben Maurer; Benjamin Leonhardi; Bernie Huang; Bhargavi Paranjape; Bing Liu; Binh Tang; Bobbie Chern; Brani Stojkovic; Brian Fuller; Catalina Mejia Arenas; Chao Zhou; Charlotte Caucheteux; Chaya Nayak; Ching-Hsiang Chu; Chloe Bi; Chris Cai; Chris Cox; Chris Marra; Chris McConnell; Christian Keller; Christoph Feichtenhofer; Christophe Touret; Chunyang Wu; Corinne Wong; Cristian Canton Ferrer; Damien Allonsius; Daniel Kreymer; Daniel Haziza; Daniel Li; Danielle Pintz; Danny Livshits; Danny Wyatt; David Adkins; David Esiobu; David Xu; Davide Testuggine; Delia David; Devi Parikh; Dhruv Choudhary; Dhruv Mahajan; Diana Liskovich; Diego Garcia-Olano; Diego Perino; Dieuwke Hupkes; Dingkang Wang; Dustin Holland; Egor Lakomkin; Elina Lobanova; Xiaoqing Ellen Tan; Emily Dinan; Eric Smith; Erik Brinkman; Esteban Arcaute; Filip Radenovic; Firat Ozgenel; Francesco Caggioni; Frank Seide; Frank Zhang; Gabriel Synnaeve; Gabriella Schwarz; Gabrielle Lee; Gada Badeer; Georgia Anderson; Graeme Nail; Gregoire Mialon; Guan Pang; Guillem Cucurell; Hailey Nguyen; Hannah Korevaar; Hannah Wang; Haroun Habeeb; Harrison Rudolph; Henry Aspegren; Hu Xu; Hugo Touvron; Iga Kozlowska; Igor Molybog; Igor Tufanov; Iliyan Zarov; Imanol Arrieta Ibarra; Irina-Elena Veliche; Isabel Kloumann; Ishan Misra; Ivan Evtimov; Jacob Xu; Jade Copet; Jake Weissman; Jan Geffert; Jana Vranes; Japhet Asher; Jason Park; Jay Mahadeokar; Jean-Baptiste Gaya; Jeet Shah; Jelmer van der Linde; Jennifer Chan; Jenny Hong; Jenya Lee; Jeremy Fu; Jeremy Teboul; Jianfeng Chi; Jianyu Huang; Jie Wang; Jiecao Yu; Joanna Bitton; Joe Spisak; Joelle Pineau; Jon Carvill; Jongsoo Park; Joseph Rocca; Joshua Johnstun; Junteng Jia; Kalyan Vasuden Alwala; Kam Hou U; Kate Plawiak; Kartikeya Upasani; Kaushik Veeraraghavan; Ke Li; Kenneth Heafield; Kevin Stone; Khalid El-Arini; Krithika Iyer; Kshitiz Malik; Kuenley Chiu; Kunal Bhalla; Kyle Huang; Lakshya Garg; Lauren Rantala-Yeary; Laurens van der Maaten; Lawrence Chen; Leandro Silva; Lee Bell; Lei Zhang; Liang Tan; Louis Martin; Lovish Madaan; Luca Wehrstedt; Lukas Blecher; Luke de Oliveira; Madeline Muzzi; Madian Khabsa; Manav Avlani; Mannat Singh; Manohar Paluri; Mark Zuckerberg; Marcin Kardas; Martynas Mankus; Mathew Oldham; Mathieu Rita; Matthew Lennie; Maya Pavlova; Meghan Keneally; Melanie Kambadur; Mihir Patel; Mikayel Samvelyan; Mike Clark; Mike Lewis; Min Si; Mitesh Kumar Singh; Mo Metanat; Mona Hassan; Naman Goyal; Narjes Torabi; Nicolas Usunier; Nikolay Bashlykov; Nikolay Bogoychev; Niladri Chatterji; Ning Dong; Oliver Aobo Yang; Olivier Duchenne; Onur Celebi; Parth Parekh; Patrick Alrassy; Paul Saab; Pavan Balaji; Pedro Rittner; Pengchuan Zhang; Pengwei Li; Petar Vasic; Peter Weng; Polina Zvyagina; Prajjwal Bhargava; Pratik Dubal; Praveen Krishnan; Punit Singh Koura; Qing He; Rachel Rodriguez; Ragavan Srinivasan; Rahul Mitra; Ramon Calderer; Raymond Li; Robert Stojnic; Roberta Raileanu; Robin Battey; Rocky Wang; Rohit Girdhar; Rohit Patel; Romain Sauvestre; Ronnie Polidoro; Roshan Sumbaly; Ross Taylor; Ruan Silva; Rui Hou; Rui Wang; Russ Howes; Ruty Rinott; Saghar Hosseini; Sai Jayesh Bondu; Samyak Datta; Sanjay Singh; Sara Chugh; Sargun Dhillon; Satadru Pan; Sean Bell; Sergey Edunov; Shaoliang Nie; Sharan Narang; Sharath Raparthy; Shaun Lindsay; Sheng Feng; Sheng Shen; Shenghao Lin; Shiva Shankar; Shruti Bhosale; Shun Zhang; Simon Vandenhende; Sinong Wang; Seohyun Sonia Kim; Soumya Batra; Sten Sootla; Steve Kehoe; Suchin Gururangan; Sumit Gupta; Sunny Virk; Sydney Borodinsky; Tamar Glaser; Tamar Herman; Tamara Best; Tara Fowler; Thomas Georgiou; Thomas Scialom; Tianhe Li; Todor Mihaylov; Tong Xiao; Ujjwal Karn; Vedanuj Goswami; Vibhor Gupta; Vignesh Ramanathan; Viktor Kerkez; Vinay Satish Kumar; Vincent Gonguet; Vish Vogeti; Vlad Poenaru; Vlad Tiberiu Mihailescu; Vladan Petrovic; Vladimir Ivanov; Wei Li; Weiwei Chu; Wenhan Xiong; Wenyin Fu; Wes Bouaziz; Whitney Meers; Will Constable; Xavier Martinet; Xiaojian Wu; Xinbo Gao; Xinfeng Xie; Xuchao Jia; Yaelle Goldschlag; Yann LeCun; Yashesh Gaur; Yasmine Babaei; Ye Qi; Yenda Li; Yi Wen; Yiwen Song; Youngjin Nam; Yuchen Hao; Yuchen Zhang; Yun Wang; Yuning Mao; Yuzi He; Zacharie Delpierre Coudert; Zachary DeVito; Zahra Hankir; Zhaoduo Wen; Zheng Yan; Zhengxing Chen; Zhenyu Yang; Zoe Papakipos"
] |
text-generation | transformers |
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
| {"library_name": "transformers", "tags": []} | jspr/smut_llama_8b_merged_ax | null | [
"transformers",
"safetensors",
"llama",
"text-generation",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-04-19T18:12:22+00:00 | [
"1910.09700"
] | [] | TAGS
#transformers #safetensors #llama #text-generation #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us
|
# Model Card for Model ID
## Model Details
### Model Description
This is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.
- Developed by:
- Funded by [optional]:
- Shared by [optional]:
- Model type:
- Language(s) (NLP):
- License:
- Finetuned from model [optional]:
### Model Sources [optional]
- Repository:
- Paper [optional]:
- Demo [optional]:
## Uses
### Direct Use
### Downstream Use [optional]
### Out-of-Scope Use
## Bias, Risks, and Limitations
### Recommendations
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
## Training Details
### Training Data
### Training Procedure
#### Preprocessing [optional]
#### Training Hyperparameters
- Training regime:
#### Speeds, Sizes, Times [optional]
## Evaluation
### Testing Data, Factors & Metrics
#### Testing Data
#### Factors
#### Metrics
### Results
#### Summary
## Model Examination [optional]
## Environmental Impact
Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).
- Hardware Type:
- Hours used:
- Cloud Provider:
- Compute Region:
- Carbon Emitted:
## Technical Specifications [optional]
### Model Architecture and Objective
### Compute Infrastructure
#### Hardware
#### Software
[optional]
BibTeX:
APA:
## Glossary [optional]
## More Information [optional]
## Model Card Authors [optional]
## Model Card Contact
| [
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.",
"## How to Get Started with the Model\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] | [
"TAGS\n#transformers #safetensors #llama #text-generation #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n",
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.",
"## How to Get Started with the Model\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] |
null | transformers |
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
| {"library_name": "transformers", "tags": []} | jettjaniak/tokenizer0 | null | [
"transformers",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null | 2024-04-19T18:14:27+00:00 | [
"1910.09700"
] | [] | TAGS
#transformers #arxiv-1910.09700 #endpoints_compatible #region-us
|
# Model Card for Model ID
## Model Details
### Model Description
This is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.
- Developed by:
- Funded by [optional]:
- Shared by [optional]:
- Model type:
- Language(s) (NLP):
- License:
- Finetuned from model [optional]:
### Model Sources [optional]
- Repository:
- Paper [optional]:
- Demo [optional]:
## Uses
### Direct Use
### Downstream Use [optional]
### Out-of-Scope Use
## Bias, Risks, and Limitations
### Recommendations
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
## Training Details
### Training Data
### Training Procedure
#### Preprocessing [optional]
#### Training Hyperparameters
- Training regime:
#### Speeds, Sizes, Times [optional]
## Evaluation
### Testing Data, Factors & Metrics
#### Testing Data
#### Factors
#### Metrics
### Results
#### Summary
## Model Examination [optional]
## Environmental Impact
Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).
- Hardware Type:
- Hours used:
- Cloud Provider:
- Compute Region:
- Carbon Emitted:
## Technical Specifications [optional]
### Model Architecture and Objective
### Compute Infrastructure
#### Hardware
#### Software
[optional]
BibTeX:
APA:
## Glossary [optional]
## More Information [optional]
## Model Card Authors [optional]
## Model Card Contact
| [
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.",
"## How to Get Started with the Model\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] | [
"TAGS\n#transformers #arxiv-1910.09700 #endpoints_compatible #region-us \n",
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.",
"## How to Get Started with the Model\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] |
text-generation | transformers | # MaziyarPanahi/Llama-3-11B-Instruct-v0.1 AWQ
- Model creator: [MaziyarPanahi](https://huggingface.co/MaziyarPanahi)
- Original model: [Llama-3-11B-Instruct-v0.1](https://huggingface.co/MaziyarPanahi/Llama-3-11B-Instruct-v0.1)
<img src="./llama-3-merges.webp" alt="Goku 8x22B v0.1 Logo" width="500" style="margin-left:'auto' margin-right:'auto' display:'block'"/>
## Model Summary
This model is a self-merge of `meta-llama/Meta-Llama-3-8B-Instruct` model.
## Prompt template
```text
<|begin_of_text|><|start_header_id|>system<|end_header_id|>
You are a helpful assistant.<|eot_id|><|start_header_id|>user<|end_header_id|>
what's 25-4*2+3<|eot_id|><|start_header_id|>assistant<|end_header_id|>
To evaluate this expression, we need to follow the order of operations (PEMDAS):
1. First, multiply 4 and 2: 4*2 = 8
2. Then, subtract 8 from 25: 25 - 8 = 17
3. Finally, add 3: 17 + 3 = 20
So, 25-4*2+3 = 20!<|eot_id|>
To evaluate this expression, we need to follow the order of operations (PEMDAS):
1. First, multiply 4 and 2: 4*2 = 8
2. Then, subtract 8 from 25: 25 - 8 = 17
3. Finally, add 3: 17 + 3 = 20
So, 25-4*2+3 = 20!
```
| {"language": ["en"], "license": "other", "library_name": "transformers", "tags": ["4-bit", "AWQ", "text-generation", "autotrain_compatible", "endpoints_compatible", "mergekit", "merge", "facebook", "meta", "pytorch", "llama", "llama-3"], "model_name": "Llama-3-11B-Instruct-v0.1", "base_model": "meta-llama/Meta-Llama-3-8B-Instruct", "pipeline_tag": "text-generation", "inference": false, "model_creator": "MaziyarPanahi", "license_name": "llama3", "license_link": "LICENSE", "quantized_by": "Suparious"} | solidrust/Llama-3-11B-Instruct-v0.1-AWQ | null | [
"transformers",
"safetensors",
"llama",
"text-generation",
"4-bit",
"AWQ",
"autotrain_compatible",
"endpoints_compatible",
"mergekit",
"merge",
"facebook",
"meta",
"pytorch",
"llama-3",
"conversational",
"en",
"base_model:meta-llama/Meta-Llama-3-8B-Instruct",
"license:other",
"text-generation-inference",
"region:us"
] | null | 2024-04-19T18:16:16+00:00 | [] | [
"en"
] | TAGS
#transformers #safetensors #llama #text-generation #4-bit #AWQ #autotrain_compatible #endpoints_compatible #mergekit #merge #facebook #meta #pytorch #llama-3 #conversational #en #base_model-meta-llama/Meta-Llama-3-8B-Instruct #license-other #text-generation-inference #region-us
| # MaziyarPanahi/Llama-3-11B-Instruct-v0.1 AWQ
- Model creator: MaziyarPanahi
- Original model: Llama-3-11B-Instruct-v0.1
<img src="./URL" alt="Goku 8x22B v0.1 Logo" width="500" style="margin-left:'auto' margin-right:'auto' display:'block'"/>
## Model Summary
This model is a self-merge of 'meta-llama/Meta-Llama-3-8B-Instruct' model.
## Prompt template
| [
"# MaziyarPanahi/Llama-3-11B-Instruct-v0.1 AWQ\n\n- Model creator: MaziyarPanahi\n- Original model: Llama-3-11B-Instruct-v0.1\n\n<img src=\"./URL\" alt=\"Goku 8x22B v0.1 Logo\" width=\"500\" style=\"margin-left:'auto' margin-right:'auto' display:'block'\"/>",
"## Model Summary\n\nThis model is a self-merge of 'meta-llama/Meta-Llama-3-8B-Instruct' model.",
"## Prompt template"
] | [
"TAGS\n#transformers #safetensors #llama #text-generation #4-bit #AWQ #autotrain_compatible #endpoints_compatible #mergekit #merge #facebook #meta #pytorch #llama-3 #conversational #en #base_model-meta-llama/Meta-Llama-3-8B-Instruct #license-other #text-generation-inference #region-us \n",
"# MaziyarPanahi/Llama-3-11B-Instruct-v0.1 AWQ\n\n- Model creator: MaziyarPanahi\n- Original model: Llama-3-11B-Instruct-v0.1\n\n<img src=\"./URL\" alt=\"Goku 8x22B v0.1 Logo\" width=\"500\" style=\"margin-left:'auto' margin-right:'auto' display:'block'\"/>",
"## Model Summary\n\nThis model is a self-merge of 'meta-llama/Meta-Llama-3-8B-Instruct' model.",
"## Prompt template"
] |
null | espnet |
## ESPnet2 ST model
### `espnet/iwslt24_indic_en_hi_bpe_tc4000_use_wandbtrue`
This model was trained by cromz22 using iwslt24_indic recipe in [espnet](https://github.com/espnet/espnet/).
### Demo: How to use in ESPnet2
Follow the [ESPnet installation instructions](https://espnet.github.io/espnet/installation.html)
if you haven't done that already.
```bash
cd espnet
git checkout 3a161c5ac0f74cc593410a4a32001073ed456580
pip install -e .
cd egs2/iwslt24_indic/st1
./run.sh --skip_data_prep false --skip_train true --download_model espnet/iwslt24_indic_en_hi_bpe_tc4000_use_wandbtrue
```
<!-- Generated by scripts/utils/show_translation_result.sh -->
# RESULTS
## Environments
- date: `Wed Apr 17 02:51:38 JST 2024`
- python version: `3.10.14 (main, Mar 21 2024, 16:24:04) [GCC 11.2.0]`
- espnet version: `espnet 202402`
- pytorch version: `pytorch 2.1.0`
- Git hash: `83c179ab842987cf01642df2db372aaae260df55`
- Commit date: `Wed Apr 17 00:28:29 2024 +0900`
## st_train_st_conformer_raw_en_bn_bpe_tc4000
### BLEU
|dataset|score|verbose_score|
|---|---|---|
|decode_st_conformer_st_model_valid.acc.ave/dev.en-bn|2.1|19.7/3.6/1.0/0.3 (BP = 1.000 ratio = 1.185 hyp_len = 46094 ref_len = 38883)|
## ST config
<details><summary>expand</summary>
```
config: conf/tuning/train_st_conformer.yaml
print_config: false
log_level: INFO
drop_last_iter: false
dry_run: false
iterator_type: sequence
valid_iterator_type: null
output_dir: exp/st_train_st_conformer_raw_en_bn_bpe_tc4000
ngpu: 1
seed: 0
num_workers: 1
num_att_plot: 3
dist_backend: nccl
dist_init_method: env://
dist_world_size: null
dist_rank: null
local_rank: 0
dist_master_addr: null
dist_master_port: null
dist_launcher: null
multiprocessing_distributed: false
unused_parameters: false
sharded_ddp: false
cudnn_enabled: true
cudnn_benchmark: false
cudnn_deterministic: true
collect_stats: false
write_collected_feats: false
max_epoch: 80
patience: null
val_scheduler_criterion:
- valid
- loss
early_stopping_criterion:
- valid
- loss
- min
best_model_criterion:
- - valid
- acc
- max
keep_nbest_models: 10
nbest_averaging_interval: 0
grad_clip: 5.0
grad_clip_type: 2.0
grad_noise: false
accum_grad: 2
no_forward_run: false
resume: true
train_dtype: float32
use_amp: false
log_interval: null
use_matplotlib: true
use_tensorboard: true
create_graph_in_tensorboard: false
use_wandb: false
wandb_project: null
wandb_id: null
wandb_entity: null
wandb_name: null
wandb_model_log_interval: -1
detect_anomaly: false
use_adapter: false
adapter: lora
save_strategy: all
adapter_conf: {}
pretrain_path: null
init_param: []
ignore_init_mismatch: false
freeze_param: []
num_iters_per_epoch: null
batch_size: 20
valid_batch_size: null
batch_bins: 25000000
valid_batch_bins: null
train_shape_file:
- exp/st_stats_raw_en_bn_bpe4000/train/speech_shape
- exp/st_stats_raw_en_bn_bpe4000/train/text_shape.bpe
- exp/st_stats_raw_en_bn_bpe4000/train/src_text_shape.bpe
valid_shape_file:
- exp/st_stats_raw_en_bn_bpe4000/valid/speech_shape
- exp/st_stats_raw_en_bn_bpe4000/valid/text_shape.bpe
- exp/st_stats_raw_en_bn_bpe4000/valid/src_text_shape.bpe
batch_type: numel
valid_batch_type: null
fold_length:
- 80000
- 150
- 150
sort_in_batch: descending
shuffle_within_batch: false
sort_batch: descending
multiple_iterator: false
chunk_length: 500
chunk_shift_ratio: 0.5
num_cache_chunks: 1024
chunk_excluded_key_prefixes: []
chunk_default_fs: null
train_data_path_and_name_and_type:
- - dump/raw/train.en-bn/wav.scp
- speech
- kaldi_ark
- - dump/raw/train.en-bn/text.tc.bn
- text
- text
- - dump/raw/train.en-bn/text.lc.rm.en
- src_text
- text
valid_data_path_and_name_and_type:
- - dump/raw/dev.en-bn/wav.scp
- speech
- kaldi_ark
- - dump/raw/dev.en-bn/text.tc.bn
- text
- text
- - dump/raw/dev.en-bn/text.lc.rm.en
- src_text
- text
allow_variable_data_keys: false
max_cache_size: 0.0
max_cache_fd: 32
allow_multi_rates: false
valid_max_cache_size: null
exclude_weight_decay: false
exclude_weight_decay_conf: {}
optim: adam
optim_conf:
lr: 0.002
weight_decay: 1.0e-06
scheduler: warmuplr
scheduler_conf:
warmup_steps: 25000
token_list:
- <blank>
- <unk>
- ▁
- ্
- ▁়
- য
- র
- ▁প
- ▁এবং
- ের
- ▁য
- কে
- ▁স
- ▁ব
- ▁যে
- ▁একটি
- রা
- ও
- ▁যা
- ▁ে
- ▁করে
- ▁ত
- ▁সম
- ▁করা
- ▁জন
- ▁করতে
- ▁এটি
- ে
- স
- হয
- ▁ক
- ▁দ
- ▁আম
- ▁এই
- তে
- ▁ট
- ড
- িয
- ায
- ই
- ▁আমাদের
- ▁।
- ন
- ▁না
- ত
- ▁ন
- ▁তাদের
- ▁আপনি
- টি
- ▁পারে
- ▁আমি
- ভাবে
- ▁কিন
- ▁তু
- ী
- ▁তা
- ▁গ
- ▁তার
- ▁রয
- ▁র
- ▁তারা
- ার
- ▁েছে
- ▁থেকে
- ▁া
- দের
- ▁বা
- ▁হবে
- ▁সাথে
- ▁পর
- ▁হ
- ▁নির
- িত
- ▁ম
- ▁অন
- ক
- ▁ছিল
- ▁যান
- ▁ার
- ▁তি
- ▁আপনার
- ▁নিয
- ▁মধ
- ষ
- ▁আর
- ▁তৈরি
- ▁অ
- ▁ধ
- ▁বন
- ▁জ
- ▁তাই
- ▁যখন
- ▁এক
- ▁বিশ
- ▁কার
- ▁শ
- গুলি
- ▁কিছু
- ▁দে
- ল
- ঙ
- ▁বাস
- ▁তবে
- ▁ণ
- ▁যদি
- ▁শক
- ুক
- ▁অর
- ঞ
- ▁এমন
- ▁চ
- ▁ভ
- ▁কাজ
- ▁এখন
- ▁থ
- ▁হল
- ▁তর
- ▁অনেক
- ▁বেশি
- ▁হতে
- ▁পরিব
- ি
- ▁আ
- িক
- ▁করি
- ▁েছিল
- ▁এর
- ▁যবহার
- মাত
- ▁কারণ
- উত
- ▁যায
- াড
- ▁তখন
- ▁ড
- ▁মতো
- পূর
- চ
- ▁পারি
- ▁সত
- প
- ▁সেই
- ▁ষ
- ▁আমা
- ▁তন
- ▁নয
- ▁চে
- া
- ▁শুরু
- ▁মনে
- ▁বর
- ব
- ▁কম
- ▁উদ
- ▁ু
- ▁কী
- ▁ছে
- ▁ষা
- ▁আছে
- দ
- ▁রি
- ▁বি
- ▁বের
- ▁যক
- ▁করেন
- ▁বলে
- ▁একজন
- ▁তিনি
- ▁হিসাবে
- জ
- ▁এটা
- ▁যন
- '-'
- ▁নতুন
- ▁সে
- ▁দিকে
- ','
- ▁করেছে
- ▁করেছিল
- ▁রক
- ▁রে
- িষ
- ▁যেতে
- ▁দি
- ▁উপর
- ▁জলব
- ▁শুধু
- ▁থান
- ▁রতি
- ▁কি
- ▁ল
- ▁যাক
- ▁পারেন
- ▁কর
- গ
- ▁কয
- ▁রস
- ▁রথম
- ▁যেখানে
- ▁থাকে
- ▁টা
- ▁কাছে
- ▁কথা
- বচে
- ▁লক
- ▁সং
- শ
- ▁ঘ
- ▁আগে
- ▁োজন
- ▁একই
- ▁বারা
- ▁করছে
- ▁যার
- ▁সালে
- ▁দেখা
- ংখ
- ▁এখানে
- ▁করেছিলেন
- ▁ষণ
- ▁কেন
- যোগ
- ▁আপনা
- ▁ভাল
- ▁মূল
- ট
- ▁তির
- ▁সাহা
- ▁বৈ
- ম
- ান
- ▁খুব
- ▁বছর
- ▁ফ
- ▁সর
- ৃষ
- েন
- ▁দেশ
- ▁রম
- ▁অস
- ▁বড
- ▁কোম
- কি
- ▁ঠিক
- ▁ধরে
- ▁বিজ
- ▁করবে
- ফ
- ▁গুরুত
- ▁থা
- ু
- ▁রুত
- ▁বিদ
- ▁যারা
- ▁দেখতে
- ▁নি
- ▁সাধারণ
- ▁পূর
- ▁করেছি
- াও
- ▁মান
- ▁ভাব
- বিষ
- েষ
- ▁যিই
- রণ
- ▁ছ
- ▁করুন
- ▁ধি
- ▁উচ
- ▁রতিটি
- ▁পদ
- ▁বিক
- হ
- ▁গল
- ▁পরে
- ৃদ
- চিত
- ▁রশ
- ▁উ
- ▁উচিত
- ▁সহ
- মধ
- ▁চিত
- ▁জীবন
- ▁েক
- ▁20
- ▁কখন
- উন
- ▁বেশিরভাগ
- ▁ছোট
- ▁রাস
- ▁দিতে
- ▁যাচ
- ▁ঘুম
- ুদ
- ▁মানুষ
- ▁কোন
- দক
- রূপ
- ▁চাই
- ▁বিষ
- ▁রভাব
- ▁থাকা
- ▁দুর
- ▁এ
- রীক
- ▁উপা
- ▁দুটি
- ▁বিশেষ
- ▁আক
- ▁অক
- ▁বলতে
- ▁আন
- দীর
- ▁ষে
- ▁নেই
- ▁ধন
- ▁ষেত
- ▁বলা
- ▁তী
- ▁রত
- ▁পুনর
- ▁সক
- নিশ
- ▁শেষ
- ▁সিস
- ▁আসলে
- াম
- এ
- ণ
- ▁ছা
- ▁ঘন
- ▁মার
- মাধ
- ▁ভাগ
- ▁সঠিক
- ▁কেউ
- ▁ইতি
- ▁কিভাবে
- ▁শিল
- ▁পার
- ▁উদাহরণ
- িং
- ▁কারণে
- ▁বল
- ▁সুত
- িজ
- ▁রতিক
- ▁ফির
- ▁মানুষের
- ▁লোক
- ▁ভব
- ▁সমাধান
- ▁আসে
- ▁চলে
- িতে
- ▁কেবল
- ▁রী
- ▁ঞানী
- ▁নিজে
- ভিন
- ▁সেখানে
- ▁অবস
- বর
- ▁যত
- ▁খুঁজ
- ▁কঠিন
- ▁হাজার
- ▁জানেন
- ▁জানি
- খ
- ▁সব
- ▁বে
- ▁যমে
- বিশ
- ▁রহ
- ▁ধান
- ▁টার
- ▁জিনিস
- ▁থনীতি
- ▁ধরনের
- ▁সহজ
- ▁তব
- ▁রাজ
- ▁তিত
- ▁গেছে
- পক
- াহলে
- িকল
- ▁আলো
- ▁রহণ
- ▁করবেন
- ▁10
- ▁অবশ
- ং
- ▁পনা
- ▁পে
- কারী
- ▁ধে
- িদ
- তার
- ▁যেমন
- ▁চা
- ▁তাপ
- ▁যাপ
- ▁দিন
- ▁এত
- ▁ছি
- ▁নে
- ▁সাম
- ▁গত
- তা
- ▁অংশ
- ▁রান
- ছন
- ▁বিত
- ▁কোষ
- ▁সরকার
- ▁োগ
- তি
- বার
- ▁বিশাল
- ▁পেতে
- ▁উপ
- ▁চিন
- '2'
- ▁রাখা
- ুর
- ▁জিন
- ▁বৈশ
- ▁পানি
- ▁গমন
- ▁াই
- ▁ভবত
- ▁সন
- ▁অগ
- চুর
- ▁পরিস
- ▁েছি
- ▁তিশালী
- ▁শতাংশ
- ▁ভিত
- ▁বছরের
- াল
- ▁যাকসিন
- ▁যবাদ
- ▁রকৃত
- ▁মত
- ▁থাপন
- ▁রণ
- ▁আজ
- ▁লোকেরা
- ▁লা
- ▁রের
- ▁রিক
- ▁ষতি
- শব
- ▁থাকতে
- ▁বিল
- ▁দেশে
- ▁উভ
- ▁মস
- ▁জু
- ▁রমণ
- ▁ষমতা
- ▁রদান
- ▁যবস
- নের
- রুদ
- ▁করেছেন
- ▁সার
- টিকে
- ▁গাছ
- ▁জীবা
- গত
- ▁মিলি
- ▁ডলার
- াং
- ▁পণ
- ▁রূপা
- ▁ষম
- ▁গা
- ▁কল
- নেও
- ▁যাট
- জন
- ▁যথ
- ▁পুরো
- ▁অনুমান
- ▁রাখতে
- ▁যাস
- এর
- ▁েছিলেন
- ▁লেখ
- ▁পরিষ
- ▁জল
- ▁রঙ
- ▁মাত
- ▁বিনি
- ▁জা
- ▁তারপর
- ▁তুলনা
- ▁পৃথিবী
- ▁খরচ
- ▁বিবেচনা
- ▁চল
- ▁রিত
- ▁টেলি
- ▁েছিলাম
- ▁টেম
- ▁সি
- বদ
- ▁অনুস
- ▁আলাদা
- ▁তৃত
- গুলিতে
- ▁ভর
- ▁রাপ
- ানো
- ▁সুযোগ
- ▁মুহ
- ▁মাথা
- ▁সংক
- ▁ভাবনা
- ▁যাগ
- সাথে
- ▁মী
- ▁যাত
- ▁নীচে
- ▁তোলে
- ▁বাইরে
- তির
- ▁তিনটি
- ▁বুঝ
- ▁চিকি
- ▁কোনও
- ▁হার
- ▁19
- ▁মক
- ▁থিতি
- ▁গবেষণা
- ▁সরবরাহ
- ▁তারপরে
- ▁একক
- ▁মের
- ▁সৌর
- ▁চাল
- ▁মহিলা
- ▁চর
- ▁কোনো
- ▁নীতি
- ▁বস
- ▁CO
- ▁সবুজ
- ▁অবশেষে
- ▁যুৎ
- ▁বেগ
- ▁রাখে
- ▁দুই
- ▁ডে
- ▁চান
- ▁রোগ
- ▁বলি
- ▁রমাণ
- ▁নিজ
- ▁গি
- ▁ভুল
- ংক
- ▁টের
- ▁শহরে
- ▁অত
- ▁যাবে
- মে
- ▁শহর
- ▁কের
- ▁মহা
- েবে
- ▁কোথা
- ▁সাইড
- ▁নের
- ির
- ▁ঠ
- গুলো
- ফর
- ▁তথ
- ▁পানির
- ▁চালি
- ▁ভালো
- ▁ধরণ
- ▁ধারণ
- ▁মাণ
- ▁াল
- ▁বিপ
- ▁ভাষা
- ▁দরকার
- ▁রিট
- ▁কো
- ▁রদা
- ▁মৃত
- ▁ছেন
- ▁যুতিক
- ▁যকর
- ▁লাস
- ▁তমান
- ▁মিশর
- ▁রাম
- ▁দল
- ▁নিজের
- ▁ডার
- থায
- ▁সারা
- েও
- োড
- ▁সা
- ▁রাতে
- ▁বিস
- টা
- ▁ছিলেন
- ▁ফলাফল
- ▁ডাই
- ▁ঞাসা
- ▁মিথ
- ▁নীল
- ▁হিস
- ▁চুল
- ঘ
- ▁যালে
- ▁ষেপ
- ▁বব
- ▁যু
- ▁বাধ
- ▁দেশগুলি
- ▁মানে
- ▁ান
- ৃশ
- ▁াতে
- ▁আশ
- ▁খারাপ
- ▁লাল
- ূর
- ▁ধার
- ▁তুত
- ষম
- ▁পরিচিত
- ▁বক
- ▁ডা
- ▁নাম
- ▁জার
- ▁ছিলাম
- টোক
- ▁তম
- োক
- ▁যবসা
- ▁বার
- ▁পথ
- লম
- ▁ধতি
- ▁অনুভব
- ▁কৌশল
- ▁রসারিত
- ▁আঘাত
- ▁জিনিসগুলি
- িন
- ▁গতি
- ▁অতির
- ▁পাচ
- াকে
- ▁করছেন
- াঙ
- ▁মাই
- ▁পা
- ▁জানা
- ▁নব
- ▁আশা
- ▁ধারণা
- ▁অভ
- ▁সুবিধা
- ▁সবাই
- না
- েতু
- ংস
- মেন
- ▁পাঁচ
- ▁জীব
- ▁নিষ
- ▁হুমকি
- ▁বালানি
- ▁নিরাপদ
- ূন
- ▁বোধ
- ▁যগুলি
- ▁গে
- রক
- ▁চাপ
- ▁রোটিন
- নী
- ▁যোগ
- ▁রাণী
- ▁ভারতে
- ▁টির
- ▁রকৃতি
- ▁মহামারী
- সের
- ▁মে
- ▁15
- ▁থনৈতিক
- ▁ঝুঁকি
- ▁রকাশ
- ▁তিন
- ▁সুস
- ▁রাজা
- ▁ডিস
- ▁এড
- ▁মারা
- ▁টন
- শীল
- ▁নামে
- ▁দু
- জু
- ▁উপাদান
- ▁অপ
- থ
- ুষ
- ▁পরিণত
- ▁তত
- ▁বেঁচে
- ▁বালানী
- ▁অনুম
- ▁বেশ
- ▁যানো
- ▁ধমান
- লে
- ▁এগ
- ▁থন
- ▁আবার
- ▁অসম
- ময
- ▁উপস
- াস
- ▁যমান
- ▁শিক
- রামর
- ▁হাই
- কাল
- ▁থী
- ▁ঞান
- ▁পাদন
- ▁রিকা
- ▁দূরে
- ▁হলে
- ো
- ▁ভিন
- ▁নিক
- ▁রাব
- ৎ
- ▁কোপ
- ▁শী
- লব
- ▁দা
- হত
- ▁দেখেছি
- ▁বোঝা
- ▁টিক
- ▁মরুভূমি
- ▁বৃহ
- তম
- ▁তিগত
- ▁অফ
- ▁ষতা
- ▁ফলে
- ▁সীমা
- িহ
- ▁সেন
- ▁যুদ
- ▁মন
- ▁দশকে
- ▁সেগুলি
- ▁গড
- ▁যো
- ▁রদ
- ▁11
- ▁4
- ▁পরিবার
- ▁ডিজাইন
- ▁রজাতি
- ▁হাসি
- ▁নামক
- ▁খাদ
- ▁তো
- ▁তিক
- েক
- সূর
- ▁ভারত
- ▁ইন
- ▁যাপক
- ▁আসা
- ▁কিনা
- ▁ঠান
- ▁আত
- ▁অব
- ▁কোষে
- ▁পুরুষ
- ▁ডি
- ▁রার
- ▁সংগ
- ▁যাকে
- ▁থাকবে
- ▁বিন
- ▁ইংতাই
- ▁মোমবাতি
- ▁রাকৃতিক
- ▁লোকেদের
- ীকরণ
- ▁রতিশ
- ▁খ
- ▁চারপাশে
- ▁এশ
- ▁খনি
- ▁উপরে
- ▁রুতি
- ▁পরিমাণে
- ▁আসন
- ▁বিভ
- পড
- ▁দূর
- ▁1
- ▁বেড
- ▁রিস
- ▁কোষগুলি
- ▁আগ
- ▁একে
- ▁রাক
- ▁শহরগুলি
- ▁সেট
- েই
- তটা
- ▁শরীর
- ▁পরিমাণ
- ▁খিঁচুনি
- ▁ফেলে
- গায
- ▁জো
- দিনের
- নির
- ▁ইমিউন
- ▁যাল
- ▁আস
- ▁অপর
- ▁বাচ
- ▁কত
- ৈর
- ▁তরে
- ▁রেক
- ▁করছি
- ▁অনু
- ▁করলে
- ▁আল
- ▁আধ
- ▁ভাবন
- ▁এমআরএনএ
- ▁টেকসই
- ▁রোজান
- ▁পরিচালনা
- ▁যুত
- ▁বছরে
- ▁যালি
- ▁ডেটা
- ▁একাধিক
- ▁দর
- ▁পিছনে
- ▁মাটি
- ▁যতা
- ▁বদা
- ডিগ
- ▁এগুলি
- ▁ঞতা
- ▁আচরণ
- লা
- ফোর
- ▁একবার
- ▁সহা
- ▁শন
- টিস
- ▁রতিরোধ
- ▁আরেক
- ▁6
- াক
- কার
- লি
- বা
- ▁সেরা
- ▁বংস
- ▁লি
- ▁বপ
- ▁অপসারণ
- s
- ▁মোকাবেলা
- ▁রবেশ
- ▁ইলেক
- ▁চিকিৎসা
- ▁ভেঙ
- ▁বিপরীত
- ▁রধান
- মূলক
- ▁হত
- ▁পাশা
- ▁পুর
- ▁দাস
- ▁জনস
- ▁মডেল
- নি
- োয
- ▁থক
- ▁আপ
- াচ
- রিদ
- ছিলাম
- ▁মা
- বে
- ▁এলাকা
- ▁দশক
- ▁ঘটনা
- ভূত
- ▁কন
- ▁শতা
- ▁তরা
- ▁ভার
- রবর
- িনি
- ▁খা
- ▁নিজেদের
- রূপে
- ▁মোট
- ▁কাঠামো
- ▁যোগাযোগ
- ▁বীকার
- ▁ভূমিকা
- বু
- ▁ঠী
- ▁ডিক
- ▁জোর
- '20'
- ▁আমেরিকান
- ▁সাল
- ▁েন
- ▁নৈতিক
- ঠা
- শত
- াপী
- ▁সপ
- াতে
- বেক
- ▁ফল
- পত
- ▁জীবনে
- ▁গো
- ▁যাই
- ▁অদ
- ▁নত
- ▁ডাক
- ▁সেস
- কৃত
- ▁টিভ
- ▁জটিল
- হীন
- ▁কঠোর
- ▁চাহিদা
- ▁মুখোমুখি
- ▁রকৌশলী
- ▁রাচীন
- ▁উৎপাদন
- ▁রগতি
- ▁লেষণ
- ▁জাতিগত
- ▁শোষণ
- ▁খাবার
- ▁ধীর
- ▁পারবেন
- ুনিক
- ▁ভিতরে
- ▁ভাইরাস
- ▁দেখি
- তিতে
- ▁দেবে
- কল
- ▁লেট
- ▁েছেন
- ৃত
- ▁াম
- ▁ইস
- ▁নিচে
- ▁চম
- ▁গদ
- ▁ধু
- ▁তুলত
- ▁টেবিলে
- পী
- মা
- ▁আকার
- ▁অণু
- ▁অনুপ
- ▁টে
- ▁নিত
- ▁মূ
- ▁ওষুধ
- ▁কাছাকাছি
- ▁ডিএনএ
- ▁সুপারনোভা
- ▁শুনতে
- ▁গপাল
- ▁অভাব
- ▁যপ
- ▁মাঝ
- নাক
- ▁আটকে
- ▁বিচ
- ▁গভীর
- ▁যজনক
- মি
- ▁200
- টিক
- ▁যেভাবে
- ▁পাশে
- ▁রতিদ
- ▁সেলস
- ▁ফেল
- ▁নতি
- ▁বাধা
- ▁বজ
- ▁মানব
- ছে
- ▁থতা
- াই
- ▁শতাংশের
- ▁শান
- ▁হন
- ▁নিম
- ▁শিকার
- পাশ
- বৃত
- ▁সমব
- ▁5
- েছে
- ▁তেলাপোকা
- ▁ঝ
- ▁বসে
- ▁গুণ
- ▁ণবাদ
- ▁লিপ
- ▁যব
- ▁ঘটে
- তী
- ▁আইন
- ▁জানে
- ▁আশেপাশে
- ▁নাগরিক
- ▁গঠন
- ▁তরীণ
- ▁যাটার
- ▁অভিজ
- ▁সংযোগ
- ▁চরম
- ▁করব
- জেন
- ▁পানিগুলি
- ▁ডিম
- লার
- াফল
- ▁জলে
- বহা
- ▁উজ
- ▁সামনে
- ▁30
- ▁থিত
- াগত
- ▁ঝাঁক
- ▁পগুলি
- উড
- ▁যাম
- ▁কুল
- ▁থাগুলি
- ▁মানসিক
- ▁বাঁচ
- ▁পরব
- ▁ডেন
- ▁থে
- ▁রেস
- ▁ছবি
- ▁কাছ
- ▁সমান
- বন
- ▁পান
- ▁সিম
- ▁2
- ▁সহক
- ▁ঞা
- ▁লিপিড
- ▁অধ
- ▁কোভিড
- ▁অবদান
- ▁যোগফল
- ▁সোনা
- ▁েকটি
- ▁কালো
- ▁কমাতে
- ▁গবেষকরা
- ▁অনন
- ▁দেখে
- মান
- ▁মুখী
- ▁রজনন
- ▁সূচক
- ▁জাত
- টাই
- ▁পরিবেশ
- ▁আদ
- ▁ইউরোপ
- ▁আচ
- ▁পেট
- ▁লাগ
- ▁ছিন
- ▁যাশ
- ▁জি
- ▁চিম
- োষ
- ▁মু
- ▁যটি
- ▁গেলে
- ▁ষিণ
- ▁ভিদ
- ▁বেত
- ▁রেম
- ▁বিপর
- ▁তিদের
- েশন
- লেন
- ভুক
- ▁রোগী
- ▁পাত
- ▁চার
- বসম
- ▁রাণ
- ▁ঘো
- ▁আরো
- ▁এম
- মন
- ুরক
- ▁খেলা
- দিকে
- োজ
- ▁রো
- ▁বাভাবিক
- '0000'
- ▁যবহ
- ▁নিন
- ▁ইতিহাস
- ▁শত
- ▁পরিচ
- ▁রাথমিক
- ▁ভাইপার
- ▁জনগণ
- ▁থাকলে
- ▁শোনা
- ▁ঘুর
- ▁বিয
- ▁লোব
- ▁বাণ
- ▁পরিবহন
- ▁যবান
- ▁সাদা
- ▁ওজন
- ▁কিছুটা
- ▁চাকা
- ▁অপে
- ▁ঠে
- ▁মিলিত
- ▁সেক
- ▁বাকি
- ▁শরীরে
- ▁যেকের
- েট
- মাস
- ইচ
- ▁পালি
- ▁রচ
- দার
- ▁আকাশে
- ▁মুখে
- ারি
- ালন
- ▁রবাহ
- ▁কিলোমিটার
- ▁আকারে
- ▁শে
- ারিদ
- ▁সুন
- ভাগ
- পু
- ▁লোকের
- '50'
- ▁বাবা
- ▁মিত
- সাম
- ছেন
- বি
- ▁যৌন
- ▁রবণ
- মণ
- ▁বাক
- ▁ধেক
- ▁বহু
- ▁অদলবদল
- ▁তেজনা
- ▁বসবাস
- ▁পরিমাপ
- ▁রাজনৈতিক
- ▁আবাস
- ▁সংকেত
- ▁পরিবেশগত
- ▁বিকাশ
- ▁বিগুণ
- ▁যানেল
- ▁যাঁ
- ▁ইংরেজি
- ▁অভি
- ▁মিনিটের
- াধিক
- ▁যিকার
- ▁জানত
- ▁রজন
- ▁অসু
- রকম
- ▁থিক
- ▁রেখে
- ▁জেনে
- ▁3
- ণনা
- ▁নারী
- ▁সংয
- াত
- ▁টেমের
- ▁রেড
- লান
- ▁ানো
- ▁সাহ
- ▁চাচ
- ▁কাজটি
- ▁রিড
- ▁থল
- ▁পন
- ▁রন
- াজার
- ▁রিন
- ▁কোপে
- ▁গন
- ▁সৌ
- পথে
- ▁লুপ
- ▁সূ
- ▁ভাই
- ▁ষিত
- ▁কেল
- ▁ওঠে
- ▁70
- ▁জাহাজ
- ৷
- ▁থেরাপি
- ▁চাকরি
- ▁মৌলিক
- ▁চাঁদ
- ▁রতিফল
- ▁নেতৃ
- ▁শাসন
- ▁খবর
- ▁নাটক
- ▁ঘুমানো
- ▁করছিলাম
- ▁ইতিহাসে
- ▁চালানো
- ▁ষরিক
- ▁ষত
- ▁বীপ
- ▁আমেরিকানদের
- হিত
- ▁করছিল
- লাম
- ▁আউট
- ▁যাটারি
- ▁কথোপকথন
- ▁তোলা
- ▁থানে
- সংশ
- ▁দেন
- ▁ঘট
- ▁বাতাস
- ▁নিউ
- ▁নেট
- ামাজ
- জনক
- ▁দাম
- শক
- ূ
- ▁যাকসিনগুলি
- ▁নম
- হার
- ▁রাসা
- ▁শিশু
- োল
- ালের
- ▁কোর
- ▁16
- ▁রাত
- ▁চালা
- ▁100
- ▁সমাজ
- কেন
- ▁তাহ
- ভূমি
- ▁কমে
- ▁মাস
- াময
- ▁12
- শিত
- ▁পেশী
- মাক
- a
- ▁ফোকাস
- ▁শিখেছি
- ▁তহবিল
- ▁রতিবেশী
- ▁রভু
- ▁উপকূল
- ▁দুধ
- ▁পরিচাল
- ▁আলোক
- ▁বলুন
- ▁সিজেন
- ▁দাবি
- ▁দূষণ
- ▁শতকে
- ▁যতক
- ▁পাঠানো
- ▁রাণিত
- ▁রোগীর
- ▁কাউ
- ▁রাখবে
- ▁বোত
- ▁জানতে
- টিভ
- ▁ঞানিক
- ষণা
- ▁গেম
- ▁পুনরা
- োচ
- ▁মিল
- ▁হৃদয
- ▁করেছিলাম
- ▁মুখ
- ▁পোর
- বিদ
- ▁রহস
- ▁পাবল
- ৃ
- ▁কেরি
- ▁রণে
- ▁আজকে
- ▁অপরি
- ংশ
- ▁মহিলার
- ▁রগুলি
- ালোক
- েমন
- ▁জিত
- ▁ষক
- ▁হাতি
- ▁একা
- ষিক
- ▁হাতে
- ▁াস
- তুর
- ▁কা
- ▁কোণ
- ▁দশকের
- ফিল
- ▁গুরুতর
- ▁বলছি
- ▁পাই
- ▁আমেরিকা
- ▁8
- ▁বাজার
- াদী
- ▁চোখে
- ▁রমে
- '3'
- িপিং
- ▁দাঁ
- ▁তরুণ
- '9'
- ▁নদী
- ▁যাপন
- ▁চলেছে
- ▁পাঠ
- ▁অবকাঠামো
- ▁কবুতর
- ▁টুকরো
- ▁অনুবাদ
- ▁একটু
- ▁জিডিপি
- ▁নমুনা
- ▁দখল
- ▁যমজ
- ▁24
- ▁রোজেন
- ▁যাপচার
- '26'
- ▁শারীরিক
- ▁তুলনামূলক
- ▁কিত
- হাউস
- ▁সফল
- ▁দরজা
- ▁নিরাপ
- ▁যালসি
- ▁গরম
- ▁দেখেন
- ▁রমিক
- ▁টাও
- ▁গম
- ▁তিগুলি
- ▁চারটি
- ▁দেবতা
- ▁েল
- ▁তবতা
- ▁শহ
- ▁বিতা
- ▁দৈ
- ▁মাক
- ▁সংকট
- ▁অনুসার
- গুণ
- ▁ইহুদি
- ▁ণবাদী
- ▁রুটি
- ▁মালি
- ▁বালি
- ▁পুনরু
- াশ
- ▁জনক
- ▁পৌঁছা
- ▁উপাদানগুলি
- ▁80
- ▁ইক
- ▁ষি
- ▁কোনটি
- ▁কুশ
- দুর
- রি
- োগ
- ▁করেনি
- ুল
- নিয
- ▁নিব
- ▁জের
- িকভাবে
- ▁শুক
- ▁বান
- ▁রাণীর
- ▁মগুলি
- ুরে
- ▁তাত
- ▁শিখ
- ▁কক
- ুনি
- ▁রেই
- ▁কাট
- ▁তিকর
- পোস
- ▁খালি
- ▁যাগুলি
- ▁বনাইজ
- ▁ভূ
- ▁যেগুলি
- ▁লাভ
- ▁গেল
- ▁জাতিক
- ▁পরিশ
- ▁উপরের
- কর
- ▁মেশিন
- েল
- ▁ছেলে
- ▁সু
- ছিল
- ▁জাম
- ▁শানবো
- সাশ
- ূত
- ▁থিতিশীল
- ▁বো
- ▁তুলা
- ▁বকে
- ▁অবি
- '00'
- ▁থানগুলি
- ালকা
- ▁লু
- ▁ইউ
- ▁অধিকার
- ▁রাইলোবাইট
- ▁টেরিওটাইপ
- ানদের
- ▁মিটার
- ▁জাতি
- ▁ভালবাসা
- ▁সীমিত
- ▁অনুশীলন
- ▁মোনালিসা
- ▁জীবনযাপন
- ▁আলোচনা
- ▁লোরো
- ▁আগামী
- ▁তেজিত
- ▁রনালী
- ▁2030
- ▁উঠেছে
- ▁আগুন
- ▁নেতিবাচক
- ▁যাকটাস
- ৎকার
- ▁যালাক
- ▁থনীতিবিদ
- ▁বিরল
- ▁লেজ
- ▁পৌঁছানো
- ▁বীকৃত
- ▁পাহা
- ▁চেইন
- ▁যামেরা
- ▁রু
- ▁রেখা
- মস
- ▁দেখানো
- ▁চীন
- ▁জনসাধারণ
- ▁তাব
- ▁রাজি
- েড
- ▁ছদ
- ▁ডিং
- ▁তালিকা
- নো
- ▁পরিবেশে
- ▁ফি
- ▁রাউন
- ▁রোল
- দৌ
- ▁চোখ
- ▁সাক
- ▁রোম
- ▁ফাঁদ
- শন
- ▁ডস
- '5'
- ▁সাই
- াজ
- ▁শেখা
- ▁জিনগুলি
- িণ
- ▁টিকেল
- কোণ
- ▁গান
- ▁সেতু
- ▁সরকারকে
- ▁মাসের
- ▁রাপক
- ▁খাল
- ▁কান
- মিশ
- শি
- দস
- কোনো
- ▁শিবির
- ▁হো
- ▁ছাত
- সরি
- ▁রহে
- ▁পথে
- ▁বলবে
- ▁এন
- যুদ
- ▁ভু
- মনী
- সে
- ▁অংশে
- ▁খেল
- জার
- ▁াট
- ▁দী
- '7'
- ইহ
- ▁সিরি
- ▁লাইন
- ▁মাসে
- ▁াদে
- ▁চক
- ▁ছেদ
- ▁খু
- ▁ডল
- ▁রীক
- ▁বলছে
- ▁এসে
- ▁উপকরণ
- কিং
- ▁ভাইরা
- ▁ঐতিহ
- '&'
- ;
- o
- p
- Ş
-
- ▁চুনাপাথর
- ▁মেলাটোনিন
- ▁রাজধানী
- ▁ষুধা
- ▁সবকিছু
- ▁অপারেটর
- ▁মবেশ
- ▁হরমোন
- ▁গাছপালা
- ▁উপভাষা
- ▁আইডি
- ▁যসেবা
- ▁দেশাবলী
- ▁যানবাহন
- ারের
- ▁হারানো
- ▁তরাধিকার
- ▁পাবেন
- ▁বিকৃত
- ▁ষেপণ
- ▁জেট
- ▁অংশগ
- ▁জমি
- ▁অভিযোজন
- ▁বাণী
- ▁বিবর
- ▁যাধি
- ▁হোম
- ▁যাটি
- ▁চলগুলি
- ▁বলেছিল
- ▁টাকা
- ▁খোলা
- ▁মীদের
- লো
- ▁রচার
- ▁রেণী
- ▁সামর
- ▁রহী
- ▁মানবতা
- ▁রতিদিন
- ▁দেহ
- ▁নিজেদেরকে
- ▁যাপার
- ▁াগুলি
- ▁ভারতকে
- ধিক
- বিরক
- ▁গর
- ▁টান
- ▁দান
- ▁90
- ▁কাজে
- ▁িগুলি
- ▁বাদ
- ▁সাত
- ▁25
- ▁হবেন
- ▁লেখক
- বাদী
- াউন
- াদের
- ▁পেরেছি
- ▁পক
- ▁পাইক
- '1'
- ▁1000
- িস
- ▁অল
- ▁রাশ
- ▁উপন
- ▁শিকারী
- সাধারণ
- ভার
- ▁ষিণে
- ▁বুদ
- ▁পশ
- ▁ভুলে
- ▁সাপ
- ▁রিজ
- াইড
- ▁ভূত
- ▁50
- ▁লাগে
- ▁বারে
- দিন
- ▁দৃ
- তন
- ▁পাদ
- '8'
- ▁আট
- ▁আকাশ
- ▁নিচ
- ▁বিগ
- '6'
- চে
- ▁খুল
- ▁ভূগ
- ▁দাতা
- ▁বলেছি
- ▁সুলতান
- পর
- কুচি
- ▁তনশীল
- ▁এতটা
- ▁মানি
- ▁অথ
- ীন
- তুল
- ▁লাই
- ▁পাখি
- ▁রোধ
- ▁নিদ
- ধ
- ▁বাধীন
- ▁এসেছি
- ঢ
- ▁ঘর
- তিবাচক
- ▁ডিভাইস
- ▁মোটামুটি
- T
- ▁পৃথক
- ▁যালঘু
- ▁সহযোগিতা
- ▁পুনঃ
- ▁আবেগ
- ▁যকলাপ
- ▁ঝিল
- ▁নিঃসরণ
- ▁আংশিক
- ▁চিৎকার
- ▁লিওন
- ▁মনোযোগ
- ▁আবেদন
- ▁বিবেচ
- ▁আছি
- ▁ফসল
- ▁পোরেশনগুলি
- ▁পেরু
- ▁বিতরণ
- ▁লাইট
- ▁কিলো
- ▁এসেছে
- ▁বহি
- ▁ইউনি
- ▁বামী
- ▁কভার
- ুব
- ▁ফলাফলগুলি
- ▁কৃষি
- ▁তাক
- কারক
- ▁যাকশন
- ▁পাঠা
- ▁নেতা
- ▁খে
- ▁সকলের
- ▁তনে
- নাইট
- পুর
- ডাউন
- ▁যৌনতা
- ▁ডান
- রম
- ▁শীত
- ▁চলা
- ▁কানের
- ▁মিং
- ▁মুদ
- ▁শাসক
- ▁গোপন
- ▁তোমা
- ▁কৃতি
- ▁টেক
- ▁রেট
- ▁সকালে
- ▁যাবেন
- ▁জান
- ▁পরিসরে
- ▁ফুল
- ▁হাত
- ▁এভাবে
- াইভ
- পূরণ
- ▁হলেন
- ▁শিশুর
- শীর
- ▁ডানা
- পতি
- ▁মাতা
- ▁শুনে
- ▁কাটা
- ▁ধারণাটি
- ▁যিক
- ছা
- ▁গাছে
- ▁রমা
- ▁সমাধানে
- সম
- ীদের
- ▁মাল
- িড
- আই
- ▁দার
- মার
- ুন
- ▁ভে
- ▁চতা
- ▁400
- ▁বাহ
- ▁ইতাল
- লস
- ▁রাইভ
- ▁এরিক
- ▁থি
- ▁হারি
- মাঝ
- েইনফ
- ▁পেরেছিল
- '4'
- ▁টিকে
- েব
- থাক
- ▁শর
- ▁ডাকা
- ▁রেখেছিল
- ▁তুলে
- ▁অসুবিধা
- ▁নগুলি
- ▁আই
- ▁টু
- ▁শেষে
- ▁জনপ
- খানে
- ▁বহুল
- ▁দেখেছিল
- ▁ঋণ
- ▁রুপ
- ▁দূষ
- ▁মহাকা
- ০
- ▁আরএনএ
- ▁নাৎসি
- ▁সুপারহিরো
- ▁রতিযোগিতা
- ▁পাইলট
- ▁বজনীন
- ▁ঐতিহাসিক
- ▁চিঠি
- ▁মরিসন
- ▁বাজেট
- ▁সুপারিশ
- ▁পুলিশ
- ▁দেখুন
- ▁অভিযান
- ▁রাহক
- ▁যবধান
- ▁রতিযোগী
- ▁ডানদিকে
- ▁পাগল
- ▁খনন
- ▁ঘটছে
- ▁বেষণ
- ▁সংবেদন
- ▁লাগানো
- ▁দেখেছিলেন
- ▁ঢে
- ▁পারবে
- ▁কাশন
- ▁বিকেলে
- ▁শুনেছেন
- ▁এসেছিল
- ▁যাসিড
- ▁নেমে
- ▁3-
- ▁রশংস
- ▁বাহু
- ▁করত
- ▁রঙে
- গদ
- ▁40
- ▁গক
- ▁শোষ
- ▁জোট
- ▁গণনা
- ▁হাঁট
- ▁বেস
- ▁রিলি
- ▁টিং
- ▁দাদা
- ▁সরকারগুলি
- ▁অংশগুলি
- ▁দোষ
- ▁খলা
- ▁করতেন
- ▁জাপান
- ▁আধি
- ▁বাহিনী
- ঘাত
- ▁সরকারী
- ▁থিতিতে
- ▁পারেনি
- ▁যাংক
- াসের
- াইজ
- ▁মেট
- ঃ
- ▁কুলে
- ▁বাচন
- ▁কোড
- ▁মাঝা
- ▁রেমে
- েইন
- রমাণব
- ▁যাগগুলি
- বহন
- বাজারে
- ▁টেবিল
- ▁চারা
- ▁রাখ
- ▁ঠানিক
- ▁বংসা
- ▁ধকারে
- ▁ঝুল
- ▁18
- ▁থাকেন
- ▁কৃষ
- ▁তক
- ▁চি
- বিরোধ
- হন
- ▁নাক
- ▁যাতন
- মিন
- দা
- চার
- ▁গগুলি
- ▁আছেন
- '21'
- ▁ডলে
- ▁তিটি
- পা
- ▁রোত
- ▁রকেট
- ▁তাহে
- ▁পাস
- ুলার
- ▁বাঁচা
- ▁আসেন
- ▁যথায
- ▁কৃতিক
- ▁ধকার
- ▁পরিষেবা
- বিক
- ▁তগুলি
- ▁যাণ
- ▁দেবী
- ▁ষর
- ▁সীমান
- ▁কৃত
- সি
- ছি
- ▁পিতামাতার
- ভান
- ▁মেঘ
- ▁আরি
- ▁ফাঁক
- েজ
- ধি
- ▁পরি
- ▁মেটা
- টো
- পাস
- নে
- তিগ
- োপ
- মুখী
- ▁যদ
- জীবন
- '0'
- ▁অতি
- ফো
- ▁মিনিট
- ▁রিপ
- ▁মিক
- ▁পিছ
- ▁কু
- ▁যানবাহনে
- ▁শো
- ▁নাগা
- বেন
- ▁পোরেশন
- ▁োগকারী
- শালী
- ▁জাতিসংঘ
- ৃৎপ
- ▁ডিজিটাল
- ▁নিখুঁত
- ▁পিতামহ
- ▁মহাসাগর
- ▁রিলোবাইট
- ▁রীতদাস
- ▁রোপচার
- ▁সেনাবাহিনী
- ▁অপারেশন
- ▁জরুরী
- ▁শেলোব
- P
- ▁অনুভূমিক
- ▁যাটেলাইট
- ▁বাছাই
- ▁যকারিতা
- ▁আঠালো
- ▁কেটলি
- ▁সৈন
- ▁ইনজেকশন
- ▁একাকী
- ▁রতিকৃতি
- ▁মালিকানা
- ▁রাকচার
- ▁তুলেছে
- ▁কবিতা
- ▁আসুন
- কোহ
- ▁বুশ
- মলত
- ▁আসছে
- ▁আশাবাদী
- ▁আসবে
- ▁উৎসাহ
- ▁বোতাম
- পোকা
- ▁অধীন
- ▁একমত
- ▁ভেবেছিল
- ▁সুখ
- ▁গঠিত
- ▁নজর
- ▁বিবরণ
- ▁201
- ▁দেখবে
- ▁লিনিক
- ছ
- ৌক
- ▁সুইচ
- ▁পরিণতি
- ▁মোটা
- ▁উৎপ
- ▁লেটগুলি
- ▁পাথর
- ▁ফেলবে
- ▁ফরাস
- ▁হৃদ
- িগার
- ▁মাপ
- ▁ভাঙ
- ফুস
- ▁ধুদের
- ▁বিরতি
- ▁কতা
- ▁লাইস
- ▁দিল
- ▁থাকি
- ▁নীতিগুলি
- ▁আবদ
- ▁রেলি
- ▁পেস
- ▁মাইক
- ▁টেমগুলি
- ▁গু
- ▁টেশন
- ▁গেট
- নশীল
- ▁লুক
- ▁পরাজ
- ▁পাঁচটি
- ▁বতন
- ▁পাবে
- ▁রোমান
- ▁বাপক
- ▁লাইনের
- ▁00
- পোর
- ▁উঠ
- ▁17
- ▁যাতি
- ▁জাল
- বাইন
- ▁ঘটা
- ▁কমান
- ▁ইমে
- ▁দগুলি
- ▁উপয
- ▁হতাশা
- ▁যুতে
- ▁নিষি
- ভ
- ▁সেল
- োর
- ▁ফিল
- ▁সিটি
- ▁ভবন
- ▁দীপ
- ▁194
- ▁ষাগুলি
- ▁যাগে
- ▁আবর
- ▁সকল
- মিড
- ▁টিকেলগুলি
- ▁কারণগুলি
- ▁দিক
- ▁হেল
- ▁বিট
- ▁রেরণা
- ▁কুশি
- ▁ঘোরা
- ▁ধরা
- ▁সী
- ফি
- ▁রবৃ
- ▁রোটিনে
- ▁কাজগুলি
- ▁মহাকাশে
- ামগ
- ▁অনেকের
- ▁পলি
- ফিক
- ▁রহণকারী
- ▁বিধ
- রেস
- ▁লোককে
- ▁মহাদেশ
- ুত
- ▁ণতা
- ▁রপ
- ▁মিশ
- ▁উৎস
- ▁গার
- কেটে
- গো
- মেডি
- ▁লেখা
- ▁ভিদে
- ▁ষী
- ▁দিনে
- বশেষ
- ▁দেশটি
- ▁মেস
- ▁বিচারে
- ৌ
- ▁ডিত
- ▁আব
- ▁মহাকাশ
- ▁রেডি
- ▁36
- ▁22
- ▁10000
- োস
- ▁বুজ
- কেল
- ▁বাতাসে
- েটর
- ীর
- ▁বেল
- ▁বীপে
- দন
- লাইন
- ূপ
- ▁সাহারা
- ▁রমণে
- ▁হাস
- ▁েজ
- ▁বলতা
- ▁জুন
- কোস
- ▁হই
- ▁মজা
- ▁নটি
- ▁করণ
- বিজ
- ▁যেকোন
- াবে
- াদা
- ▁রুট
- তিক
- ▁থের
- ▁সহজে
- ▁তাকা
- ▁গবেষক
- ▁ধর
- ▁রাইড
- ▁এলোমেলো
- ▁উঁচু
- ▁উদযাপন
- ▁কীটনাশক
- ▁রতিনিধি
- ▁শিরোনাম
- ▁শৈশব
- ▁াকলাপ
- ▁এনকোড
- ▁মজুরি
- ▁লাটিপাস
- ফেডারে
- ▁থেরানোস
- ▁মনোনিবেশ
- ▁ইটনভিল
- ▁লুরোস
- ▁জরিপ
- ▁টিউমার
- ▁মনিকা
- ▁সমাবেশ
- ▁বাসনালী
- ▁ইংল
- ▁খাঁচা
- ▁জীবিকা
- ▁গৃহ
- ▁ভিডিও
- ▁বেলারুশ
- ▁অধিকাংশ
- ▁রিগস
- ▁বাভাস
- ▁তুলবে
- ▁ঝাঁপ
- ▁পোশাক
- ▁খলিল
- ▁রতিবাদ
- ▁সাফো
- ▁আসল
- ▁সহিংসতা
- ▁সমাধি
- ▁কমিশন
- ▁বিদেশ
- ▁রেখেছিলেন
- ▁রাইম
- ▁কিং
- ▁ধতিগত
- ▁টাইন
- ▁অংশীদারদের
- ▁অনুভূতি
- থার
- ▁লাইম
- ▁বীজন
- ▁বিমান
- ▁রপাতি
- ▁কোলে
- ▁যানেলগুলি
- ুঁ
- ▁লিপিডগুলি
- িশোধ
- ▁সেগুলো
- ▁শিশুদের
- ▁লাফ
- ▁বেকার
- ▁সরানো
- ভাইরাস
- ▁অনুরোধ
- ▁শনিক
- ▁মালিক
- ▁রিকান
- ▁জমা
- ▁ফাঁ
- ▁অনুমোদন
- ▁করিনি
- ▁আবি
- ▁গণত
- ▁সভ
- ▁কমানো
- ▁দীতে
- ▁তৃতা
- ▁রতিরোধী
- ▁যুট
- ▁টাল
- িচ
- ▁রোপণ
- ▁বিবাহ
- বহুল
- ▁রবণতা
- ▁করলেন
- রিকানদের
- ▁দাঁত
- ▁আপস
- ▁যাকিং
- ▁যবাহ
- ▁জে
- ▁বোঝাতে
- ▁রামী
- ▁রুব
- ▁2000
- ▁মাছ
- ▁ারিং
- ▁জীবাণু
- ▁লিনার
- ▁ফুট
- ▁ধাপ
- চাপ
- আইনি
- ভাল
- গম
- ▁লেগে
- লুপ
- ▁কাপ
- ▁রহটি
- দূর
- শাস
- ▁টিমে
- ▁ঘটনাটি
- ▁কিলোমিটারের
- ▁সংগঠ
- থিত
- ▁অণুগুলি
- ▁বীর
- ▁সবে
- ▁করুক
- ▁লিফটে
- ▁সমাজে
- ▁ারশ
- ▁খরা
- ▁তেল
- ▁আঁক
- ▁চেল
- পশ
- ▁পরিপ
- ▁শহরটি
- ▁লোড
- েকটি
- ▁বিচার
- ▁লাগা
- বল
- ▁লাইটে
- ▁ভূমি
- ▁ফার
- সব
- ▁গণিত
- ▁চির
- ▁পৌঁছে
- লিপি
- ▁ালা
- াপ
- ▁আনা
- ▁পানিটি
- চক
- ▁186
- াংস
- িডা
- ▁একদিন
- ▁7
- ▁হারা
- কারীদের
- ুখ
- িএস
- ▁দশ
- োঁ
- ▁অফিসে
- ▁মুছ
- িশ
- ▁সিং
- ▁াশা
- ▁75
- ▁কাঠ
- ▁সাপে
- '11'
- ▁যদেব
- েম
- ▁ারগুলি
- কোষ
- ▁ফোন
- সেট
- ▁কোট
- ▁দলগুলি
- িটি
- ▁শুরুতে
- বিয
- তীতে
- িঁ
- ▁রেন
- ▁দামে
- করা
- ▁সেটা
- ▁ধিত
- দল
- লিক
- ▁টল
- ▁রোস
- ▁জেনি
- '60'
- ▁তাকান
- ▁যাং
- ▁পাতা
- ▁ো
- ▁পরিক
- ▁একবারে
- ▁কথোপকথনে
- ▁সমতা
- ▁ইউরোপে
- ▁দির
- হো
- শু
- ▁রিডে
- িদর
- ▁জৈব
- ▁জাদু
- ▁যালো
- ▁উৎ
- '15'
- টল
- ▁সুই
- ▁চত
- াবধানে
- ▁অনুমোদ
- ▁এখান
- ▁কিশোর
- ালোচনা
- িছু
- ▁কাগজে
- ▁তরল
- ▁বিরত
- ▁সমীক
- ▁রামক
- ▁অংশীদার
- বাজ
- ▁খামার
- বেদন
- ▁01
- ▁ধাঁধা
- ▁যাথোজেন
- ৫
- ৭
- ▁আনুমানিক
- ▁কমিউনিটি
- ▁করোনাভাইরাস
- ▁চাবিকাঠি
- ▁জরুরি
- ▁তঃসংয
- ▁তাভাবনা
- ▁নকশা
- ▁সহানুভূতি
- ▁অভিনেতা
- ▁ওভাররাইড
- ▁মামালেক
- ▁যামিগডালা
- ▁হতবাক
- ▁পুঁজিবাদ
- ▁মেঝে
- ▁বপুরুষ
- ▁জেগোটা
- ▁1970
- কাহিনী
- ▁বিবৃতি
- ▁বিরোধিতা
- ▁আইনজীবী
- ▁মচারী
- ▁থাপিত
- ▁ঞাপন
- ▁লেবেল
- ▁মামলা
- ▁কোলাহল
- ▁রচারণা
- ▁সোলার
- '99'
- ▁14
- ▁দোলন
- ▁গিগা
- ▁ভীক
- ▁ঘটবে
- ▁আপাত
- ▁ফেলেছিল
- ▁লাগবে
- ▁দেখছেন
- ▁যালসাই
- '35'
- ▁উপভ
- ▁বরাবর
- ▁ঘটেছে
- ▁ভেবেছিলেন
- লিভার
- ▁পেরেছিলাম
- ▁নিউরন
- ▁আমূল
- ▁ইরানে
- ▁সমতল
- ▁ওভার
- ▁আদেশ
- ▁কাঁটা
- ▁ধারনা
- ▁যুবক
- ▁এসেছিলেন
- ▁তানুকি
- ▁খামারগুলি
- ▁ণালী
- োফা
- ▁দুজন
- ▁ছুট
- ▁চৌ
- ▁সিরিজ
- ▁বলেছিলেন
- ▁উপক
- ধকতা
- ▁খুঁজছেন
- ▁জস
- ▁সচেতন
- ▁করছিলেন
- ▁লিটার
- ▁পিটার
- ▁রথা
- ▁ষমা
- ▁নথি
- ▁টোট
- ▁জামগুলি
- ▁কাগজ
- ▁তকরণ
- াবলী
- ▁পেশীগুলি
- ▁ঋণী
- ▁বছরগুলিতে
- ▁কেপ
- ▁নেহ
- ▁সেবা
- ▁তুলো
- সাঁ
- ▁অভিবাসী
- ▁পৌঁছেছে
- ▁চারণ
- ▁হেড
- ▁উঠে
- ▁যাডি
- ▁রাইভার
- ▁বেনি
- ▁আইল
- ▁সৃজনশীলতা
- ুমি
- ▁কোরবা
- ▁পারব
- চিং
- ▁চলেছেন
- ▁জীবনযা
- বসতি
- ▁রিফ
- ▁ওঠেন
- ▁ছবিটি
- ▁টাফ
- ▁সভা
- ▁ঘাম
- জগতে
- ▁রঙগুলি
- ▁বাই
- ▁তাৎ
- ▁পানী
- ▁শুনি
- শে
- ▁টেট
- ▁কারখানার
- ▁থাকবেন
- ▁যানগত
- াইরে
- ▁দো
- ▁কাঁ
- ▁সজ
- ▁থাংশ
- তীত
- ▁জেনিস
- ▁মি
- সিস
- ▁তাকালে
- োত
- পার
- ▁মোহ
- ▁পিট
- ▁টাপো
- গান
- ▁জিও
- ▁যাদা
- ▁হাম
- ▁মানিত
- ▁পাচার
- ▁সাহসী
- ▁মানগুলি
- '16'
- ুনির
- ▁ফটোগ
- ▁টাইম
- ▁পৃ
- ▁বংশ
- ▁রাণু
- ▁লট
- ▁মৃতি
- অপস
- ▁27
- '23'
- টে
- হারে
- নুপাত
- ▁শট
- ▁ফেলা
- ▁পশু
- ▁গেছেন
- ▁জারি
- ▁রমিত
- ▁রোতা
- টিং
- ▁জেনারেল
- ▁সৎ
- ▁লেন
- ▁বাগত
- ▁রমণকারী
- ▁চিতভাবে
- ▁বাসা
- ▁মডেলগুলি
- ▁টেন
- ▁গুর
- াগুলি
- দেবী
- ▁রোড
- দাতা
- ▁পরিবারগুলি
- ▁টানা
- লগ
- ▁রিটাউনে
- কিলোমিটার
- ▁রতা
- লাভ
- বৈ
- ▁কাম
- কন
- ▁বাব
- ▁সুবিধাগুলি
- ▁কগুলি
- ▁থীর
- ▁বিকভাবে
- রিশ
- ▁বই
- লিস
- ▁নগ
- দেশ
- ▁যৎ
- ▁দূরব
- ▁রাইভে
- ▁শিলা
- ▁চুরি
- মোন
- ▁অতীতে
- ▁সির
- ▁দেখাতে
- ▁হাব
- ▁কেলে
- সোস
- ▁ডাকে
- ▁আলোকব
- ▁তান
- ▁ামি
- টক
- ▁দানি
- ▁ডগুলি
- ▁পেরে
- ▁কেনা
- ▁ষণিক
- ▁কুশে
- টার
- ▁তৃপ
- ▁নেন
- ▁চাপা
- ভা
- দান
- ▁বিধা
- ▁যাকেজ
- েলে
- ▁গোল
- গন
- পরি
- ▁যাসে
- ছিলেন
- ▁চালান
- ▁নতা
- ▁যাশন
- ▁নাল
- ▁কোপটি
- িবাসী
- বশ
- িরোধী
- ▁অনুগ
- সিলি
- মত
- ▁মুন
- ▁ঞানে
- কালে
- ▁চিল
- েছিল
- ▁পরিত
- ▁যথা
- ▁যাকর
- োট
- ইনস
- ▁মিলে
- তঃ
- ▁সিএ
- ▁েলস
- শেষে
- ▁লোম
- জা
- ▁দেরি
- ▁রল
- টেক
- ▁সাহস
- ▁এইচ
- ▁মনো
- ▁রেরণ
- ▁পালা
- নিক
- ▁বাঁকা
- ছুক
- াইট
- ▁ফর
- ▁আটক
- ▁দটি
- ▁রাফ
- ▁মিস
- ▁ধা
- ▁পরিবারে
- ▁উঠত
- নুষ
- োম
- োদ
- খানার
- ▁অশ
- িরে
- বিত
- ভিল
- ▁ধুত
- ▁পাব
- ▁রেখেছি
- িটা
- ৈ
- াগন
- ▁কামান
- টাস
- ▁কারখানা
- ▁ধানে
- ▁দিত
- ▁অপরাধ
- ভি
- ালী
- রিকা
- ▁20000
- ▁সংঘ
- ▁সৃজনশীল
- '18'
- ▁অভিবাস
- ▁বলব
- ▁ধারক
- খানা
- রাধিকার
- ▁থাকব
- ▁লিখ
- ▁অমরজ
- ▁রপাত
- ▁উঠবে
- ▁রোমা
- াষী
- ▁দেখেছে
- ▁ডিশনার
- ▁াসে
- ▁নীত
- াগারে
- াফা
- ▁160
- জির
- াব
- '87'
- ▁ইনজেক
- ▁গোলকধাঁধা
- C
- L
- r
- ▁ইঁদুর
- ▁ইউটিলিটি
- ▁ইমিউনোথেরাপি
- ▁এলিভেটর
- ▁কাদামাটি
- ▁কৌতূহল
- ▁চিরতরে
- ▁ধারাবাহিক
- ▁মিসৌরি
- ▁রচারাভিযান
- ▁রাজকুমার
- ▁রেনেসাঁ
- ▁শিথিল
- ▁ষরেখা
- ▁হাসপাতাল
- ▁অবজারভেটরি
- ▁পরিকাঠামো
- ▁ররেখা
- ▁তলদেশে
- ▁শৈল
- ▁মদপুর
- ▁ওলাফ
- ▁গতিশীলতা
- ▁সাসপেন
- ▁ঘেটো
- ▁সংহতি
- ▁আইটেম
- ▁মেরামত
- ▁মৃদু
- ঁচট
- ▁96
- ▁রজেকশন
- ▁কংগ
- ▁রাচীর
- ▁রাজনীতিবিদ
- ▁সমালোচনামূলক
- ঘাট
- ▁রাখুন
- ▁উপনিবেশ
- ▁হিম
- ▁অনুকরণ
- ▁রামবাসী
- ▁দেশিকা
- টেইনার
- ▁ডেনিম
- ▁সাজানো
- রফেস
- ▁ষপাত
- ▁সাগর
- ▁পারতাম
- ▁মোতা
- ▁জিনোম
- ▁2019
- ▁এনেছিল
- ▁লুকানো
- িউএ
- ▁অভিজাত
- ▁রিটিশ
- ▁গুণমান
- ▁অভিনব
- ▁পরিপূরক
- ▁টগুলি
- ▁ষাপটে
- ▁রিলিফ
- ▁টানেল
- ▁জেগ
- ▁সুপার
- কটের
- ▁বৈধ
- ▁সেথেস
- ▁কাঁপ
- ▁জটিলতা
- ▁ফোরণ
- ▁টুকরা
- ▁ভরশীল
- ▁শদাতা
- ▁বালতি
- ▁পালক
- লিথি
- ▁ধরন
- ▁পেশা
- ▁পরিণতিগুলি
- ▁বাগান
- ▁মনোভাব
- ▁অনলাইন
- ▁থাপক
- ▁বলেছে
- ▁সেটিং
- ▁ডিফ
- ▁চোরা
- ▁ভিড
- ▁দেখেছেন
- ▁বোঝানো
- ▁শকুন
- ▁থাপকতা
- রবী
- লানিক
- ▁নীতিগত
- ▁করেননি
- ▁বিভাগে
- ▁দিকটি
- ামী
- ▁ওঠা
- িসিসি
- ▁তাকাতে
- ▁বলেছেন
- ▁পিতৃ
- ▁ফেট
- ▁পাঠক
- নাতক
- ▁দাগ
- ▁পারিনি
- ▁চেতনা
- ▁কফি
- ▁পাঠান
- ▁অবসান
- রোধে
- ▁রতিবার
- ▁মুদি
- ▁মূলধারার
- ▁বাতি
- ▁রাগন
- ▁গাম
- াবস
- ▁শনগুলি
- পোলি
- ▁বাধীনতা
- ▁ভাস
- ▁রাণীগুলি
- ▁আইস
- ▁কিছুর
- ▁জানতেন
- ▁জানু
- ▁রামগুলি
- ▁লোহ
- ▁কেজি
- ▁সাব
- ▁রাইট
- াচল
- ▁ইট
- ▁ছাপ
- বৃ
- ▁বিপদ
- সিভ
- ▁কলে
- ▁অসহ
- ▁টেরল
- ▁খাই
- ▁রমিকরা
- আইভ
- ▁উপাদানটি
- ▁মহামারীটি
- ▁যালোকে
- ▁সমাধানগুলি
- ▁যি
- ▁থিতিশীলতা
- ▁ওটা
- ▁রেখেছে
- ▁আদালতে
- ▁রোচ
- ▁গণ
- ▁দলে
- ভিয
- ▁উপহা
- ডেট
- ▁খালটি
- সুবিধাজনক
- ▁মগ
- ▁লালন
- ▁কণা
- ▁নিষেধ
- ▁১
- েলাই
- াবল
- ▁চেক
- ▁নই
- ▁অভিন
- ▁টেমে
- ▁ভট
- োন
- ▁গভীরতা
- ▁ষণগুলি
- ▁সারি
- ▁বরে
- ▁ধেকের
- ▁যাসী
- ▁দিরে
- ▁দৈন
- কড
- ঁ
- মাদ
- ▁টরের
- ▁কারো
- ▁গী
- ▁ফু
- ▁রাজারা
- জেনি
- কো
- ▁বীপগুলি
- ▁কণ
- ▁বাঁক
- ▁পিতামাতা
- ঠিত
- ▁সবাইকে
- ▁থির
- ▁মিনি
- বাহ
- ▁বাসী
- ▁তনগুলি
- ডো
- ▁থাপনা
- রো
- ▁াটি
- ▁রীর
- ▁নেবে
- ▁বুজে
- ▁রীন
- লুস
- রিটি
- নোর
- ▁500
- ▁এলাকাগুলি
- ▁উই
- ▁রোটিনটি
- তাকা
- ঠ
- শনে
- ▁360
- ▁বনে
- ▁সুয
- ▁ফিউ
- বুন
- ▁13
- ▁সাইটে
- শনার
- লাঙ
- টান
- ▁খোঁজ
- ▁ডাল
- ▁কপি
- ▁তুকি
- ▁ধাত
- জাত
- বেচ
- ▁হব
- ▁ইতালি
- োশ
- ▁জুম
- কক
- রুন
- মূল
- ▁মেইন
- ▁েলসে
- পথগুলি
- নিম
- লজি
- ▁টক
- হারা
- ▁দিই
- ▁দোকানে
- পিং
- সাধ
- চালান
- ▁রতিরোধে
- পেস
- '37'
- ▁নিল
- ▁খুলি
- গল
- ধান
- ▁ফের
- ▁জগুলি
- ▁বেলা
- পথ
- ▁কনস
- ▁শেল
- বিল
- ▁নেভিগে
- ▁জাগ
- জাতিক
- উ
- ▁রবাহে
- ুলে
- ফোন
- আপ
- তারা
- ▁অফিস
- ▁পশম
- ▁যুগে
- ▁যাটিন
- ▁ততটা
- লভ
- ▁মহাদেশে
- বো
- েমের
- ▁উৎসে
- ারবার
- ▁কমলা
- পাল
- ▁চলছ
- ভেন
- লিম
- মুন
- ▁202
- সেপ
- দানি
- মেলা
- ▁লিং
- িবার
- ▁সাইট
- ▁কনসা
- ঝর
- িকেল
- াশি
- ঝ
- ▁জানান
- ▁রমাণবাদ
- নেস
- শহ
- ▁নাচ
- ▁যাব
- ফেরা
- ▁124
- ▁পতন
- '12'
- ▁ভরা
- ▁ঘরে
- ▁বাম
- ▁লিক
- লানো
- ▁বী
- খা
- গোল
- ▁রতার
- ▁টেমটি
- '44'
- ▁জেনারে
- ▁রাশি
- ▁ভূমিক
- থি
- ▁ভাষ
- ▁ঝর
- ▁সুদ
- বাসী
- োজা
- ▁হতাশ
- লিং
- ▁চিনি
- হর
- ▁পারলে
- সাইক
- ▁196
- ▁সবা
- ▁ফুলে
- ▁আচরণে
- ভিউ
- হাই
- মদা
- '56'
- ▁তিরা
- ▁ষেপে
- ▁ধারে
- ▁নাইজ
- ▁300
- ▁অনুর
- ামেলা
- ▁মিউ
- ▁দেখ
- ▁থাম
- ▁অভিযোজ
- ▁হাঁটা
- মিক
- শাপ
- ানা
- ▁যাকটি
- ▁রবাল
- ▁বিতর
- কিউ
- ▁সিট
- ধীন
- ▁150
- ঁজ
- ▁গীত
- ▁থাকত
- াঁচে
- '600'
- ▁শুনেছে
- ▁ফসফোলিপিড
- ▁বাঁধ
- ▁বীজ
- কূল
- ▁খুঁজছে
- ▁রাজনীতি
- ▁রজেক
- ৯
- m
- u
- ğ
- ▁অববাহিকা
- ▁এনজাইম
- ▁এলিজাবেথ
- ▁কাটলফিশ
- ▁কূটনীতি
- ▁গিলগামেশ
- ▁টিরিওটাইপ
- ▁নৌবাহিনী
- ▁ফাংশন
- ▁ফারেনহাইট
- ▁বাংলাদেশ
- ▁ভলিউম
- ▁মসৃণ
- ▁মোকাবিলা
- ▁যসাগর
- ▁যাভিগেশন
- ▁যালগরিদম
- ▁রাঘিমাংশ
- ▁সমঝোতা
- ▁সালতানাত
- ▁সোককেলেটন
- ▁একাডেম
- ▁দেহভাজন
- ▁বংশধর
- ▁মহাকাশচারী
- ▁রজাপতি
- ▁হেঁটে
- ▁এমারসন
- ▁ছাসেবক
- ▁তোরাঁ
- ▁ধবিরতি
- ▁বিনোদন
- ▁রুসেডার
- ▁াশোনা
- ▁রণেতাদের
- ▁লাপনা
- দারুণ
- ▁যযুগ
- ১৯
- ▁নৃশংস
- ▁গৃহীত
- ▁সিনেমা
- ▁নেবুলা
- ▁ইমাল
- ▁শাটার
- ▁মহাকাশযান
- ▁পিঠ
- ▁থাকুন
- ▁ভালোবাস
- ▁লেপটিন
- ▁সহযোগী
- ▁পটভূমি
- ▁অবাধ
- ▁দুঃখজনক
- ▁ঢেউ
- ▁অসীম
- '97'
- ▁উপযোগবাদী
- ▁অতিথি
- ▁একেবারে
- ▁াবেটিস
- ▁কভারেজ
- ▁জোরালো
- ▁মশলা
- ▁শেঠ
- '94'
- ▁লেগেছিল
- '95'
- পোষণ
- ▁হিপ
- ▁তশাসন
- ▁টিপাত
- ▁হাজি
- ▁রবিন
- ▁যাটিপাস
- ▁টারনেট
- ▁1930
- ▁মিছিল
- ▁মাঠ
- ▁অটোম
- ▁লিখেছ
- ▁দেখছিলেন
- ▁হিংস
- ▁তৃণ
- '98'
- ▁মোনা
- ▁াংখী
- ▁উঠছে
- ▁আইকন
- ▁ফেলুন
- ভাটা
- লিডার
- ▁পিউট
- ▁যোগদান
- ▁ফীতি
- ▁মিটিং
- ▁বোমা
- ▁রাইবো
- ▁রণালী
- ▁টোরে
- ▁রতিকূল
- ডিপি
- ▁লোরেন
- ▁টারবাইন
- ▁টিবডিগুলি
- ▁ঢিবি
- ▁নোঙ
- ▁ছাদন
- ▁হেসে
- ▁বিভাজ
- ▁গুজরাট
- ▁োএ
- ▁120
- ▁খুনি
- োলেট
- ▁এসি
- ▁55
- ▁ডিজে
- ▁সিকো
- ▁ভেলা
- ▁সাইটগুলি
- ▁যাকচার
- ▁কণাগুলি
- ▁মতামত
- ▁কারখানাগুলি
- ▁ফুটপ
- ▁রাখছেন
- ▁শোনে
- ▁ষতিকর
- ▁ছাকৃত
- ▁শহরগুলো
- ▁াকরণ
- ▁যাদুঘর
- ▁সাগু
- ▁কেলিং
- ুথ
- োনাইজ
- ▁রগামী
- ▁যাসীদের
- ▁ভীত
- ▁রচলন
- ালো
- ▁টিপস
- ▁মৌ
- ▁যাফো
- ▁উঠবেন
- ▁সংবাদ
- ▁কাঁচ
- ▁চালনা
- ▁রেজার
- ▁রাসাদ
- ▁উপকরণগুলি
- ▁এগুলো
- ▁নীতিগ
- ▁0
- ▁নিকট
- ▁টেরিওটাইপগুলি
- ▁ফোরক
- ▁টোন
- ▁খনিজ
- ▁অবনতি
- ▁বনভূমি
- ▁যাটারিগুলি
- গাল
- ▁ডারগ
- ▁লুপগুলি
- ▁লজ
- ▁রনগুলি
- কিশোরী
- ▁ছেলেদের
- ভাষী
- ▁ডিপ
- ▁জুনাজপুস
- ▁গোলা
- ▁গভ
- ▁অধিক
- ▁মাইলের
- ▁কুই
- ▁সমালোচনা
- ▁যাফোস
- ▁অধিকারী
- ▁যবোধ
- ▁ধারকরা
- বিধি
- ▁ইকো
- ▁রিটেন
- ুভ
- ▁উপযোগ
- ▁নভ
- ▁ঠীগুলি
- ▁ঘটনাগুলি
- ▁মাংস
- ▁বাদাম
- োচন
- ▁লেব
- ▁বলছেন
- ▁চুষ
- ▁ঠানগুলি
- ▁শাক
- ▁কোঁ
- ▁বাভাবিকভাবে
- নুকি
- ▁লাইড
- িবিটি
- ▁যবসাগুলি
- িকে
- ▁যুগুলি
- ▁টিপ
- ▁রেফ
- ▁কাটে
- োলজি
- ঘর
- ▁টিমাই
- ▁গজা
- ▁সুযোগগুলি
- ▁বাজি
- ▁বিজি
- নেকের
- ীমা
- গুঁ
- ▁যাকরণ
- ▁গুন
- ▁বাঘ
- ▁দেহে
- সা
- '79'
- ▁যেকটি
- ▁টারে
- সিফ
- ▁লেপ
- ▁শুনেছিল
- ▁শেড
- ▁সুইড
- ▁াটে
- ▁কলাম
- ▁তেমন
- ▁ামে
- বাইক
- ▁ঢালা
- ▁মুখীতা
- ▁শিশুরা
- ▁বরফ
- ধারা
- ▁পৌ
- ▁কোল
- ▁তালা
- ▁লিন
- ▁খালে
- ুলেট
- ▁টিভি
- ▁রিম
- ▁সেনে
- ▁থামা
- ▁মিটারের
- ▁আসি
- ▁টুল
- ▁ভেজ
- ▁লাশ
- ▁রাগ
- ামাল
- টারের
- ▁রিজটি
- ▁দোর
- ▁যাসটি
- টকে
- ▁চালাবে
- ফিস
- ▁সাজ
- ▁যুব
- েবল
- ▁দিলে
- সিন
- ▁অজ
- ▁শা
- ▁টেজ
- ▁শতাংশে
- ▁ডু
- িজম
- জমে
- সাদ
- ▁অবা
- ▁পুরুষকে
- হাঁ
- ▁লুকো
- ▁মেঘে
- জান
- বক
- ▁যুতি
- ▁শতক
- ▁জিম
- রাণি
- ▁যানু
- সো
- ▁মিলন
- ▁চাইবে
- কৃতির
- ▁রোভ
- ▁মাইল
- '30'
- ▁পরিষেবাগুলি
- ▁আমানি
- ▁ছামত
- '500'
- বোল
- ▁ছবিগুলি
- ▁অরি
- ালি
- ▁নিই
- ▁তেলাপোকার
- কারে
- ▁রামে
- ▁সূচ
- ▁ারো
- ▁যাসি
- ▁টেলিভিশনে
- বুক
- টস
- ▁দেখান
- ুসং
- কু
- ▁আদি
- ণের
- িটাল
- ▁মরি
- রীদের
- বিচ
- ▁ধিম
- ▁রিটে
- ▁চাচা
- ▁গানে
- ▁শিবিরে
- টেন
- ▁দুঃ
- ▁টিকেলে
- ▁কেনে
- '000'
- ▁যুগ
- াশা
- '48'
- ▁কুর
- শান
- জিতে
- ▁খেলে
- ▁পরম
- পির
- ▁আঁ
- ভাব
- ানু
- ▁মাতৃ
- পশম
- ▁ষাত
- াণ
- ৃপ
- ▁চো
- কাঠি
- লন
- টারি
- ফল
- করণ
- টন
- ▁অতীত
- াইজার
- আর
- ▁ঝুলে
- িওল
- খোঁজ
- বোধ
- ▁গাগুলি
- ▁পেল
- বেশি
- ঘুরি
- কী
- ▁যাটা
- 08
- িব
- িৎ
- চিব
- '19'
- লাইট
- নৈতিক
- শুদ
- শম
- ▁সরকারে
- গভীর
- রোটিন
- '80'
- লেট
- ভাষা
- নাইজ
- হাত
- অপ
- ধারণ
- জানা
- ▁ঘটান
- অ
- ▁193
- কাজ
- ▁শুনেছি
- জুন
- িউ
- ▁নদ
- চুরি
- হেল
- ▁শেখান
- দি
- ঁকি
- ▁আসাদ
- লোভন
- ▁রিভে
- োগান
- নিউ
- ▁পৌঁছ
- াগ
- ▁াপথ
- ▁শোক
- ফেল
- মাণ
- ঘন
- তাই
- ▁ভুগছ
- ▁তৃ
- ▁বুঝি
- ▁দেখছি
- বসে
- ▁উঠল
- ▁টিম
- ▁180
- ▁জলা
- চা
- ▁লেগ
- ডিএ
- মাই
- ফিউ
- রিসে
- ▁পারমা
- ▁বেষ
- ▁মিলনে
- ▁110
- াংশের
- েটিক
- ▁800
- জিশন
- ▁ধারণে
- ▁তোম
- োনে
- ▁বলত
- ▁রাচ
- ▁বেগে
- ালদে
- ▁শুন
- ▁যারো
- ▁3000
- ▁1500
- ডেন
- ▁মূলধারা
- সিকতা
- ▁ছু
- ▁তাঁ
- ▁খোঁ
- ▁ভাবি
- ▁জুনাজপু
- ▁চালাব
- ▁পাথ
- গণিত
- ▁থেরাপিউটিক
- ▁মেক
- ▁ইংরেজ
- হীনতা
- ▁সেখান
- াহু
- ▁ফুটে
- হাউ
- ▁একগু
- ▁রাখছে
- ▁চমক
- ▁টিবডি
- ▁রাউ
- ৌরব
- ৎসাহ
- ভাসক
- ▁এসমেরাল
- e
- i
- ঊ
- ৬
- ▁1988
- ▁1990
- ▁অবৈধ
- ▁আকসুম
- ▁আজারবাইজান
- ▁ইসমাইল
- ▁কৌতুক
- ▁জরিমানা
- ▁তকণিকা
- ▁দাবানল
- ▁নিবেদিত
- ▁ফিলিপাইনে
- ▁যাবরেটরি
- ▁শৈবাল
- ▁সাবমেরিন
- ▁সিংহভাগ
- ▁সিংহাসনে
- ▁হাইপোথিসিস
- ▁ঘৃণ
- ▁ণযুগ
- ▁কোঅপারেটিভ
- ▁ঘেরলিন
- ▁জেলালেম
- ▁ঠপোষকতা
- ▁বিছানা
- ▁যাচমেকার
- ▁রাজবংশ
- ▁শীতাতপ
- ▁শোধন
- ▁সিকিউটিভ
- ▁হোমোরোটি
- ঘাঁট
- ▁বিলাসিতা
- ▁লেনদেন
- ▁ফোঁটা
- ▁ভালবাসে
- ▁ভূমিধস
- ▁ডেলিভারি
- ▁কমিউনিকে
- ▁এমবেড
- ▁ইউএস
- ▁ঝাঁঝ
- ▁সপোজার
- েমাট
- ▁উপসংহার
- ▁পিনবল
- ▁টাইফুন
- লিউশন
- ▁রবিবার
- ▁লেডগুলি
- ▁লুমিরা
- ▁চিবানো
- ▁রেগারি
- ▁টাইটান
- ▁কিনেছিলেন
- ▁কেরাটিন
- ▁লাজুক
- ▁শুনুন
- ▁সুসংবাদ
- ▁পহেড
- ▁মানবজাতি
- ▁মৌসুম
- ▁রবাদ
- ▁বদলানো
- এইচও
- ▁খল
- ▁রেণি
- ▁মীবাহিনী
- ▁ইরানী
- কোভ
- ▁মিলিমিটার
- ▁রসারণ
- ▁পরিহাস
- ▁রতারণা
- ▁টেসলা
- ▁014
- ▁খোসা
- ▁3500
- ▁ঘনমিটার
- বিধান
- ▁নিউটন
- ▁নেভিগেশন
- ▁গুণফল
- ▁খাঁ
- ▁কেলটন
- রিডিস
- ▁কনভেন
- ▁টেরিও
- থু
- ▁1450
- ▁টোবর
- ▁188
- ▁1980
- ▁কুকুর
- ▁পরিধি
- ▁দুঃখ
- ▁185
- ▁চাবিটি
- ▁লোরিড
- ▁1940
- ▁ধরবেন
- ▁নিঃশ
- ▁ঝাপ
- ▁তপাত
- ▁গীকার
- ▁শহরবাসী
- ▁ফসিল
- ▁যুভর
- ▁টলেশন
- ▁শুনিনি
- ▁যানজট
- ▁ডেভি
- ▁লেগেছে
- ▁জেলা
- ▁ঘটছিল
- ▁রানজিট
- ▁187
- ▁রণোদ
- ▁33
- ▁াবহ
- ▁গেছি
- '05'
- ▁খেলেছে
- ▁জিরো
- ▁ঝরনা
- ▁উপদেশ
- ▁38
- ▁াংখি
- ▁সারাদিন
- ▁শিম
- ▁আগামীকাল
- ▁বেআইনি
- ▁শিখেছে
- সিল
- ▁বাজানো
- ▁লাগছে
- ▁পালগুলি
- ▁লিউ
- ▁পাননি
- মিশনে
- ▁126
- ▁টিথার
- ▁ডোবা
- ▁বিরাজ
- এনবি
- ▁রোথ
- ▁বলছিলেন
- োনাল
- ▁যাংকিং
- চুপ
- ▁রোপড
- ▁টাইমলাইনে
- ▁যাকট
- ▁বাঁধা
- ▁যোনি
- ▁বোনা
- ▁করোন
- াকাশে
- ▁জেনেনা
- ▁ফসফোলিপিডগুলি
- ▁ওভারহ
- লেক
- ▁এলো
- ▁পিকাবু
- ▁আইনগত
- ▁তনালী
- সোম
- ▁উপকূলরেখাকে
- ▁তেরো
- ▁ফেরি
- '89'
- ▁রতিবেদন
- ▁অনুপাতে
- ▁থিম
- ▁ফলিকল
- ▁নলিখিত
- বিটি
- ▁ডিশনারগুলি
- ▁সহজাত
- ▁গুদাম
- ▁কারাগারে
- ▁গেলাম
- ▁হোমো
- ▁ফোটা
- ▁মানজনক
- ▁ঝু
- ▁অবকা
- ▁পেলেন
- ▁ফিনা
- ঃস
- ▁ঠাতা
- ▁লবণ
- ▁বিলাস
- ▁তিনজন
- ▁রশমন
- লিসা
- ▁পরিপূর
- ▁কিউবা
- ▁মিকা
- বদলে
- ▁জেনো
- পসাগর
- ▁বেসরকার
- ▁সুপ
- ▁যুইটি
- ▁চাইনি
- ▁ধিমূলক
- টিউ
- ▁ফাটল
- ▁সেলগুলি
- িওপি
- ▁নজির
- ▁হামলা
- ▁পুরু
- ▁অমরজত
- ▁তরণটি
- ▁করলাম
- ▁কখনো
- ▁মশালটি
- ▁গকগুলি
- ▁দিকগুলি
- ▁গমনকারী
- ▁দেখাবে
- ▁চাইলে
- নেভি
- ▁সাপগুলি
- ▁নোট
- ▁যানবাহনগুলি
- ▁সোমা
- ▁দেখেনি
- ▁োগকারীদের
- ▁রাইলোবাইটগুলি
- ▁ষণশীল
- ▁সেতুগুলি
- ▁বিবেক
- ▁খোঁজে
- ▁দেশগুলো
- ▁তারকা
- রীস
- ▁ডফিল
- ▁নাগাল
- ▁বোনাইজ
- ▁থেরাপিউটিকস
- ▁জিগ
- ▁যাপট
- ▁যৌগ
- ▁রুপার
- ▁রচল
- ▁যারিস
- ▁সহনশীল
- ▁বিনা
- াখা
- ▁যহীনতা
- ▁ভিজি
- ▁আঠা
- ▁ফাইন
- ▁ডুব
- ▁বইটি
- ▁সংযোগগুলি
- ▁রাফট
- ▁রবালের
- ▁ফে
- াসী
- সূরি
- সেছিলেন
- ▁যাসেল
- ▁গাইড
- ▁তাঁর
- ▁রোট
- ▁পনগুলি
- ▁গীতি
- ▁ধৃত
- োবা
- ▁বাবধান
- ▁সারিতে
- নামূল
- কভাবে
- ▁পৌঁছান
- লিখিত
- ▁তূপ
- ▁শিকারি
- ▁যথাস
- মেজ
- ীকৃত
- নাতনি
- ▁টরে
- ুখী
- চেতন
- ▁যাবলে
- ▁ধারণাগুলি
- ▁জীবগুলি
- ▁কাজিন
- ▁560
- হেলম
- ধমনী
- ▁করুণা
- ▁করেছ
- আ
- ১
- '%'
- ':'
- c
- h
- l
- n
- z
- ü
- ২
- ৪
- ৩
- ঔ
- ঈ
- Ö
- U
- ঋ
- ঐ
- '?'
- O
- ।
- ়
- <sos/eos>
src_token_list:
- <blank>
- <unk>
- s
- ▁the
- ▁to
- ▁and
- ▁of
- ▁a
- ing
- ▁in
- ed
- ▁that
- ▁is
- ▁
- ly
- ▁we
- ▁it
- ▁you
- d
- ▁this
- ▁for
- ▁on
- e
- ▁be
- ▁but
- ▁with
- ▁so
- ▁are
- ▁i
- ▁have
- ▁can
- ▁they
- y
- ▁was
- ▁as
- ▁its
- ▁from
- ▁their
- ▁at
- ▁what
- ▁by
- ▁one
- ▁our
- ▁an
- ▁or
- ▁al
- ▁like
- ▁more
- ▁when
- ▁your
- ▁were
- ▁some
- ▁all
- ▁not
- ▁these
- n
- ▁people
- t
- ▁how
- ▁if
- ▁about
- to
- ▁there
- ▁do
- ▁would
- ▁up
- ▁her
- al
- nt
- ▁which
- ▁just
- er
- ▁them
- ▁us
- ▁he
- ▁other
- ▁now
- es
- ▁know
- ▁has
- ▁s
- ▁make
- ▁my
- ▁most
- ▁because
- ▁could
- ▁world
- ▁than
- ▁work
- ▁need
- ▁will
- ▁had
- ▁out
- a
- r
- so
- ▁over
- ▁who
- o
- ▁time
- ▁new
- ▁even
- ▁get
- ve
- many
- ▁well
- ▁she
- ▁no
- ▁energy
- en
- ion
- ▁where
- ▁climate
- ▁take
- st
- ▁change
- ▁me
- ▁power
- ▁un
- ▁two
- ▁first
- ▁help
- ▁look
- ▁way
- le
- ▁dont
- ▁years
- ▁re
- ▁here
- ▁call
- ▁think
- p
- ▁m
- in
- ▁carbon
- able
- c
- ▁much
- ▁those
- ever
- ▁been
- ▁use
- ▁right
- ▁co
- m
- thing
- ▁go
- ▁want
- ▁through
- l
- ▁see
- ▁same
- ive
- i
- ▁may
- ▁really
- ers
- ▁going
- ▁every
- ▁then
- ▁cells
- ▁life
- ▁his
- ▁different
- ▁should
- out
- u
- ▁around
- ▁im
- ▁things
- ight
- re
- g
- ▁still
- ▁sleep
- ▁any
- ▁say
- 'on'
- ▁high
- ▁while
- ▁back
- ▁long
- each
- ous
- ▁light
- ▁b
- ▁let
- ▁does
- ▁down
- th
- ▁own
- ies
- ▁three
- ▁start
- ▁countries
- ▁before
- ▁made
- ▁show
- ▁system
- ▁come
- very
- ▁large
- ic
- ▁tell
- yre
- ▁percent
- ▁global
- ▁india
- ▁after
- ▁water
- ▁n
- ▁often
- ▁off
- ▁again
- ▁part
- ll
- ▁ma
- ▁company
- ▁country
- twe
- ▁being
- k
- ▁next
- ▁used
- ▁point
- ▁de
- ▁today
- ▁hear
- ready
- ▁day
- ▁actually
- ▁try
- ▁year
- ▁lot
- ▁less
- ar
- ting
- ▁ca
- ▁answer
- ▁keep
- ▁develop
- ▁another
- ment
- ▁end
- ▁d
- ation
- ce
- b
- ▁per
- us
- ▁grow
- ▁enough
- ▁why
- ▁live
- ful
- or
- ▁g
- ▁number
- ▁place
- ▁give
- ▁few
- ▁t
- ▁19
- ▁20
- '2'
- ▁create
- ▁important
- ▁believe
- ▁single
- ▁cities
- ▁10
- uch
- ▁move
- ▁example
- ▁fossil
- ▁mrna
- ▁better
- ther
- lar
- ▁fact
- ▁p
- ▁find
- ▁city
- ▁did
- ▁mean
- ▁emissions
- is
- an
- ur
- w
- ▁research
- ▁kind
- ▁government
- ▁allow
- ▁case
- ▁person
- ▁small
- ▁green
- ▁across
- ▁him
- ▁second
- ▁home
- ▁human
- ▁night
- ▁thank
- ▁air
- ▁best
- ▁future
- ▁space
- ▁together
- ▁become
- ince
- ▁both
- ▁must
- ▁cant
- ▁dur
- ▁seem
- ▁side
- h
- ▁man
- one
- ▁body
- ▁car
- ▁problem
- ate
- ity
- ▁too
- ▁under
- ▁final
- ▁play
- ▁build
- ary
- ▁form
- ▁set
- ▁e
- ▁money
- ▁good
- ▁five
- ▁follow
- ▁last
- ▁economy
- ry
- est
- ▁pay
- ite
- ▁plants
- ▁bas
- be
- ▁doing
- ▁companies
- ▁entire
- ▁great
- ▁yet
- ▁far
- ▁everyone
- ▁story
- ▁times
- ▁away
- ▁ra
- ▁f
- ty
- ▁stop
- most
- ▁force
- ▁scale
- ▁impact
- less
- ▁mass
- ▁sp
- ▁once
- ▁found
- ▁ear
- ▁hair
- ▁possible
- ▁sound
- ▁electric
- ▁states
- it
- ▁red
- ▁produce
- ▁million
- ▁feel
- ▁put
- ▁planet
- ▁means
- ▁later
- ▁o
- ▁value
- ▁telescope
- ▁result
- el
- ▁ask
- ▁cost
- '00'
- ▁turn
- ▁health
- ▁industry
- ▁potential
- ▁clear
- ▁consider
- ▁gold
- ▁didnt
- ▁heart
- ▁brain
- v
- ▁lead
- ▁thing
- ▁plant
- making
- ▁working
- ▁process
- ▁technology
- ▁name
- ▁electricity
- ▁sure
- ally
- x
- age
- ▁15
- ble
- ness
- ▁ever
- ▁mo
- ▁family
- ▁earth
- ▁rule
- ▁r
- ▁hand
- ▁god
- ▁others
- ▁old
- ▁share
- ▁vaccines
- ▁k
- ▁heat
- ▁continue
- ▁talk
- ▁question
- ▁fuel
- sh
- ▁business
- ▁economic
- ▁little
- ▁dioxide
- ▁run
- ▁public
- ▁cause
- ▁reach
- ▁scientists
- ▁com
- ▁land
- ▁seen
- ▁st
- '9'
- ▁understand
- ld
- la
- ▁got
- ▁whe
- ▁big
- ▁century
- ▁concrete
- ▁support
- ▁food
- ▁always
- ▁job
- ▁certain
- ▁act
- ▁design
- ▁head
- ▁resources
- ▁6
- ▁came
- ors
- ▁unit
- ▁c
- ▁control
- ▁level
- ▁test
- ▁1
- ge
- ▁war
- ▁gas
- ▁africa
- ▁hard
- ▁mitochondria
- ▁remain
- ▁along
- ▁nature
- ▁near
- ▁billion
- ▁white
- ▁exactly
- ▁11
- ▁instead
- ▁discover
- ter
- ▁3
- ▁4
- '0'
- ▁creat
- ▁includ
- ▁protein
- ine
- ▁love
- ▁close
- ▁amount
- ▁degree
- ▁desert
- ▁particular
- ▁pandemic
- ▁data
- ▁approach
- ▁renewable
- ▁cement
- ▁blue
- ▁lower
- at
- ▁cover
- ▁bring
- ▁lives
- ▁thousands
- ▁fuels
- li
- ▁protect
- ▁idea
- ▁term
- ▁group
- ▁difficult
- ▁systems
- ▁started
- ck
- ▁sea
- ▁treat
- ▁immun
- ▁platform
- ▁women
- ▁current
- ▁model
- ▁history
- ▁began
- ▁short
- ▁eye
- ▁save
- ▁team
- ▁sun
- ▁moment
- ▁usual
- ▁table
- member
- ▁happen
- ▁provide
- ▁true
- ▁coal
- ▁wanted
- tic
- ▁pre
- he
- ▁trees
- ▁ways
- ▁color
- ▁vaccine
- ▁full
- ought
- ▁response
- ▁themselves
- ▁natural
- ▁prevent
- ▁exist
- ▁information
- ▁took
- ▁buy
- ▁thought
- ▁mind
- per
- ▁though
- ized
- til
- il
- ish
- ▁face
- ▁clean
- ian
- ▁product
- ▁increase
- ▁low
- ▁humans
- ▁da
- ▁species
- ▁local
- ▁rich
- ▁huge
- ▁break
- ▁stories
- ▁order
- ▁blood
- ▁late
- ▁fight
- ▁reduce
- ▁quickly
- ▁seat
- ance
- ▁dis
- ▁du
- ▁real
- ir
- ist
- ▁2
- ▁map
- ▁invest
- am
- ▁bone
- ▁experience
- ▁governments
- ▁built
- ▁communities
- ▁yingtai
- ▁situation
- ▁return
- ▁similar
- ▁zero
- ▁south
- ▁standard
- ▁further
- ▁state
- ▁young
- ▁h
- ▁months
- ▁ago
- ory
- ▁sh
- ▁vari
- ▁liv
- te
- ra
- ▁5
- ▁black
- ▁saving
- ▁reason
- ▁laughter
- ▁market
- ▁children
- ▁desp
- ▁open
- ▁sky
- ▁fall
- ▁word
- ▁inter
- ▁vi
- ul
- ▁action
- ▁groups
- ▁bit
- rs
- ▁factor
- ▁dr
- ▁ex
- z
- ety
- ern
- ▁drive
- ▁u
- ▁chemical
- ▁female
- ▁ground
- ▁hundred
- ▁access
- ▁addition
- ▁least
- ▁sex
- ▁specific
- ▁chance
- ▁death
- ▁walk
- ▁sendler
- ▁half
- ▁anxi
- ▁left
- ▁sometime
- ▁port
- ▁pass
- ▁wind
- ▁arent
- ma
- ▁longer
- ▁free
- ▁toward
- ▁questions
- ▁soon
- cy
- ▁king
- ▁w
- came
- ▁cars
- ▁ga
- ▁poor
- ▁bridge
- ▁evidence
- ▁extreme
- ▁risk
- ▁surface
- ▁wrong
- taking
- ▁common
- ▁probab
- ▁plate
- ▁moon
- ▁either
- ▁language
- ▁sw
- co
- ▁cop
- ▁american
- ▁kilometers
- ily
- ▁am
- ▁inside
- ch
- ▁millions
- ize
- ▁house
- ▁materials
- ▁step
- ▁mi
- ▁con
- '8'
- ▁cockroach
- ▁racial
- ▁study
- ▁woman
- ▁modern
- ▁key
- saw
- ▁dna
- ▁survive
- ▁total
- ▁cell
- ▁op
- ▁line
- ▁pa
- ▁tra
- ▁hours
- ▁simple
- hap
- ▁size
- ▁solutions
- ▁200
- ▁safe
- ▁contain
- ▁require
- ant
- ▁past
- ▁success
- ▁fast
- ▁transform
- ▁fear
- ▁behind
- ▁english
- ▁essential
- ▁exponential
- ▁science
- ▁trilobite
- ▁yourself
- ▁demand
- ▁focus
- ▁multiple
- ▁third
- ▁said
- ▁covid
- ▁income
- ▁pressure
- ▁four
- ▁hold
- ▁lack
- ▁significant
- ▁astronomer
- ▁easy
- ▁disk
- ▁done
- ▁growth
- ▁pair
- ▁fire
- ▁dollars
- ▁asian
- ▁matter
- '5'
- ▁vehicles
- id
- vi
- ▁pro
- ▁simpl
- ▁30
- ▁decades
- ▁fat
- ▁results
- ▁areas
- '4'
- ▁waste
- ▁building
- ▁deliver
- ▁sit
- ▁egypt
- ▁view
- ▁community
- ▁conversation
- ▁pigeon
- ▁suggest
- ▁wavelength
- ▁constant
- ▁course
- ▁dream
- ▁unique
- ▁itself
- ▁send
- ▁absorb
- ▁law
- cient
- ▁universe
- ▁north
- ated
- ▁respond
- ▁sense
- ▁eat
- ▁forward
- ▁school
- ▁places
- ▁tree
- ure
- ▁hit
- tton
- '6'
- ▁goal
- ▁individuals
- ▁days
- ▁sha
- ▁patients
- ling
- ▁shift
- ▁limit
- ted
- ▁generate
- ▁en
- ▁star
- ▁solve
- land
- ▁visit
- ▁8
- ▁12
- ▁sub
- ▁begin
- ▁available
- ▁difference
- ▁greek
- ▁measure
- ▁opportunity
- ▁damage
- ▁increasing
- ▁relative
- ▁typical
- ▁release
- ▁middle
- ▁wont
- ▁center
- ▁weather
- ▁cancer
- ▁rise
- ▁loop
- ▁class
- ▁fix
- ▁role
- ▁policies
- ▁loss
- ▁care
- ▁outside
- ▁image
- ▁lord
- ▁basic
- ▁l
- ▁add
- as
- ng
- ▁pret
- ▁nation
- ▁range
- ▁challenge
- ba
- ▁sum
- ▁di
- pri
- ▁learn
- ▁trap
- ▁appear
- ▁interest
- ▁goals
- ▁anti
- though
- ▁determine
- ▁hope
- ▁virus
- ▁campaign
- ▁efficiency
- ▁knew
- ▁plastic
- ▁pollut
- ▁poverty
- ▁racism
- ▁stereotype
- ▁studie
- ▁behavior
- ▁avoid
- ▁river
- ▁moving
- ▁coast
- ▁instance
- ▁square
- ▁skin
- ▁effective
- ▁reality
- ▁faster
- ▁environmental
- ▁rate
- ▁trade
- ▁plan
- ▁completely
- jar
- ▁speed
- ▁tri
- ▁alone
- ▁sort
- ▁post
- ▁national
- ▁parents
- ations
- ▁store
- ier
- ▁connect
- ▁decid
- ▁levels
- ▁non
- ▁trojan
- ▁relationship
- ▁forest
- ▁material
- ol
- ▁patterns
- ▁refugees
- ▁sign
- ▁costs
- ▁talking
- ▁imagine
- ric
- ions
- ▁kill
- ▁hav
- ▁po
- ▁arm
- na
- ▁canal
- um
- ▁strong
- ▁threat
- ▁fel
- ▁extra
- ▁efficient
- ▁incredibl
- ▁infrastructure
- ▁switch
- ▁milk
- ▁panel
- ▁slavery
- ▁social
- ▁present
- ▁warming
- ▁organization
- ▁dangerous
- ▁else
- ▁deep
- ▁corporation
- ▁divers
- ▁society
- ▁listen
- ▁moral
- ▁signal
- ▁stand
- ▁sever
- ▁janie
- ▁separate
- ical
- ▁taken
- ca
- ▁type
- ▁solution
- ▁friend
- ▁main
- ▁animals
- ver
- side
- f
- ▁rules
- ▁options
- ent
- qu
- ▁bags
- ▁engines
- ▁70
- ▁treatments
- ▁ready
- ▁benefits
- ▁top
- ring
- ac
- ▁depend
- ▁manufactur
- tion
- ▁meet
- while
- ▁problems
- ▁americans
- ▁cur
- ▁works
- ▁homes
- ▁central
- ▁political
- ▁sappho
- ▁technologies
- ▁transition
- ▁escape
- ▁ocean
- ▁reflect
- ▁rough
- ▁unlike
- ▁crisis
- ▁jeans
- ▁eventually
- ▁harm
- ▁spouse
- ▁trans
- ▁2020
- ▁atmosphere
- ▁egyptian
- ▁attack
- ▁safety
- ▁mother
- ▁grid
- ▁stay
- ▁vir
- ▁bank
- ▁changed
- '3'
- ide
- go
- ▁structure
- ▁workers
- ▁organ
- ▁giv
- ▁numbers
- ▁ver
- ▁learned
- ▁cl
- ability
- de
- ▁lie
- ▁hi
- ▁16
- ▁recognize
- ▁game
- ▁benefit
- ▁saying
- ▁led
- ▁leave
- ▁temperatures
- ▁br
- ▁men
- ▁estimate
- ▁100
- ped
- ▁read
- des
- ▁th
- are
- ▁travel
- ▁fund
- ▁lo
- ▁improve
- head
- ▁cut
- ▁needs
- ▁tea
- ▁progress
- q
- ▁perform
- ▁complex
- ▁general
- ▁urban
- ▁advance
- ▁california
- ▁journey
- ▁perspective
- ▁quality
- ▁supply
- ▁affect
- ▁birth
- ▁piece
- ▁slow
- ▁dentist
- ▁spider
- ▁famili
- ▁favor
- ▁fair
- ▁child
- ▁trick
- ▁mona
- ▁everybody
- ▁flight
- ▁cool
- ▁flow
- ▁mali
- ▁track
- ▁male
- ▁manage
- ▁durr
- ▁colors
- ▁lying
- ▁notice
- ▁personal
- ial
- ▁doctor
- ▁weeks
- ▁80
- ments
- op
- '0000'
- yon
- cu
- ▁ensure
- ▁offer
- ▁camp
- ▁projects
- ▁lipid
- ▁molecule
- ▁treatment
- ▁candles
- ▁asked
- ▁points
- ▁engineers
- ▁mine
- ▁types
- ▁mu
- ▁chang
- nd
- ard
- ▁id
- my
- ▁compar
- ze
- king
- ▁agree
- ship
- national
- '1'
- ▁supernova
- ward
- tual
- ph
- ▁machine
- ▁author
- ▁capacity
- ▁celsius
- ▁driving
- ▁grandfather
- ▁oxygen
- ▁picture
- ▁satellite
- ▁scientific
- ▁shanbo
- ▁village
- ▁evolv
- ▁record
- ▁equip
- ▁floor
- ▁numer
- ▁regard
- ▁seven
- ▁among
- ▁neighborhood
- ▁lisa
- ▁normal
- ▁feed
- ▁indeed
- ▁catch
- ▁personality
- ▁kid
- ▁lose
- ▁innovation
- ▁east
- ▁six
- ▁trust
- ▁train
- ▁ne
- ▁sell
- ▁germany
- ▁teach
- ▁inject
- ell
- nese
- ▁ball
- ▁rare
- ▁mammals
- ▁carey
- ▁everything
- ▁products
- ▁eggs
- ▁healthy
- ities
- ia
- ▁bonds
- ▁rest
- norm
- ▁adults
- ▁locusts
- ▁cr
- ▁cu
- ▁area
- ▁cooperatives
- ▁tons
- ▁ph
- ▁die
- ▁le
- ▁figure
- ▁conditions
- ▁environment
- ▁regions
- ▁engine
- ru
- ▁seizure
- ▁pattern
- ▁refugee
- ▁bu
- ▁patient
- ▁bag
- ▁hour
- ▁engineer
- ▁turns
- lands
- lf
- ▁18
- ▁50
- ▁weight
- ▁created
- ▁ab
- ▁tru
- bi
- '7'
- ▁forms
- ▁burn
- fortunate
- ▁age
- ect
- ha
- ating
- ▁kings
- ▁europe
- ▁major
- ▁kush
- ▁rock
- ▁account
- ▁ambition
- ▁apnea
- ▁citizens
- ▁dramatically
- ▁education
- ▁footprint
- ▁ourselves
- ▁predators
- ▁producing
- ▁recipient
- ▁student
- ▁sudden
- ▁tackl
- ▁target
- ▁vulnerable
- ▁block
- ▁extend
- ▁racist
- ▁speech
- ▁daughter
- ▁below
- ▁committ
- ▁push
- ▁service
- ▁tiny
- ▁easier
- ▁causing
- ▁sector
- ▁launch
- ▁quite
- ▁describe
- ▁jew
- ▁capital
- ▁mention
- ▁wait
- ▁dome
- ▁pull
- ▁24
- ▁construction
- ▁born
- ▁financial
- ▁chain
- ▁banda
- ▁ari
- ▁sustainable
- ▁position
- ▁humanity
- ▁race
- ▁twin
- sion
- ▁sent
- ▁enter
- ▁expect
- ▁policy
- ▁rain
- wise
- ▁shipp
- ▁shape
- ▁bigge
- ▁medic
- ▁special
- om
- ▁tend
- ▁waves
- ▁remov
- ake
- ▁201
- utch
- ock
- ▁decarbonize
- ▁news
- ▁door
- ▁populations
- ▁fly
- ▁happening
- ▁realiz
- ▁source
- ▁price
- ▁disease
- ▁minute
- ▁candle
- ▁decade
- ▁molecules
- coming
- ▁fl
- dp
- ▁seeing
- un
- ▁el
- act
- ▁challenges
- ▁pee
- ▁wa
- ▁capture
- ▁meaning
- scar
- special
- ▁complete
- ▁swap
- ▁lines
- ▁pack
- ▁tax
- ▁sultan
- ▁novel
- ▁count
- ▁dark
- ▁civil
- ▁advantage
- ▁multi
- ▁physical
- ▁recycl
- ▁surround
- ş
- ▁accord
- ▁alternative
- ▁attention
- ▁cactus
- ▁culture
- ▁economist
- ▁myself
- ▁negative
- ▁relief
- ▁salesman
- ▁secret
- ▁expand
- ▁finance
- ▁report
- ▁glass
- ▁consequences
- ▁excited
- ▁choice
- ▁guess
- ▁loud
- ▁court
- ▁stick
- ▁address
- ▁calcium
- latoni
- ▁electrons
- ▁network
- ▁adopt
- ▁watch
- ▁translate
- ▁maintain
- ▁industrial
- ▁bad
- ▁distance
- ▁2030
- ▁batteries
- ▁communication
- ▁impossible
- ▁location
- ▁25
- ▁galaxy
- ▁frequent
- ▁camera
- ▁anywhere
- ▁truth
- ▁operation
- ▁associate
- ▁direction
- ▁elevator
- ▁fit
- ▁90
- ▁stable
- ▁inequality
- ▁gap
- ▁worse
- ▁bodies
- ▁wor
- ▁legal
- ▁raise
- da
- ▁ship
- ▁severe
- ▁em
- ▁fr
- ▁muscles
- ▁beat
- ▁proteins
- ging
- ▁tools
- ride
- lines
- ▁leader
- ft
- oke
- ten
- ious
- ▁diseases
- ▁minutes
- ▁accelerate
- ▁emit
- ▁seizures
- mat
- ▁understanding
- ▁road
- ▁project
- ▁effect
- some
- ▁viper
- ▁nanoparticle
- ▁condition
- ▁region
- ▁temperature
- ▁individual
- ▁option
- ▁coat
- ▁turning
- ifi
- ▁friends
- res
- ▁stor
- not
- ▁1000
- ▁la
- lob
- amp
- ap
- ▁combin
- ▁speak
- ang
- body
- izing
- house
- ▁lay
- ▁involve
- ▁america
- ▁val
- ▁abundan
- ▁arrest
- ▁chlorophyll
- ▁cloud
- ▁colleague
- ▁context
- ▁couple
- ▁economies
- ▁effort
- ▁enslaved
- ▁erik
- ▁experiment
- ▁genetic
- ▁hurston
- ▁infection
- ▁length
- ▁limestone
- ▁method
- ▁outbreak
- ▁positive
- ▁predict
- ▁recommend
- ▁urethra
- ▁annual
- ▁conflict
- ▁destroy
- ▁dialect
- ▁flood
- ▁hormone
- ▁narrow
- ▁scatter
- ▁therapy
- ▁thick
- ▁throw
- ▁volume
- ▁continent
- ▁ecosystems
- ▁fail
- ▁girl
- ▁thrive
- ▁field
- ▁swarm
- ▁drug
- ▁vibrat
- ▁average
- ants
- ▁morning
- ▁corner
- ▁stretch
- ▁overall
- ▁subject
- ▁hung
- ▁heav
- ▁orbit
- ▁instructions
- ▁pick
- ▁donor
- ▁responsibility
- ▁search
- ▁list
- ▁labor
- ▁match
- ▁join
- ▁european
- ▁stress
- ▁crucial
- ▁nap
- ▁yes
- vas
- ▁worth
- ▁park
- ▁invent
- mbus
- ▁host
- ▁gather
- ▁sethe
- ▁wage
- ▁operator
- ▁check
- ▁letter
- ▁actions
- ▁spread
- ▁gone
- ▁sexual
- ▁inspired
- ▁boy
- ular
- ▁cross
- ▁tail
- ▁production
- ▁critical
- ▁literally
- ▁surprising
- ▁cycle
- ▁connection
- ▁harder
- ▁storm
- ▁involved
- ▁z
- '000'
- ordina
- ible
- ▁fortunate
- ▁song
- eries
- ▁bin
- ▁mid
- ▁characters
- ▁safely
- ▁inten
- ja
- ▁jun
- ▁0
- ▁400
- kept
- ▁ix
- ▁features
- ▁objects
- ▁needed
- ▁practices
- ▁tens
- ▁meeting
- ▁meters
- ▁west
- ▁learning
- hol
- ▁gra
- ▁achieve
- ▁cutt
- ative
- ▁event
- ▁contribut
- ▁nanoparticles
- ▁hum
- ilitar
- ▁fac
- ▁lipids
- ▁period
- war
- ▁population
- ▁animal
- ▁issue
- ▁regulat
- ▁plans
- way
- ▁island
- ▁te
- ▁site
- lle
- ven
- ▁j
- ▁40
- ▁matters
- ▁corrupt
- ▁expos
- where
- ▁dead
- ▁quick
- ▁bar
- ▁languages
- ▁wide
- ▁polic
- ▁abo
- shed
- ▁german
- ▁twi
- room
- ism
- ▁chi
- ▁react
- ▁transport
- tract
- ▁lab
- ▁correct
- ▁immediate
- ▁pilot
- ▁previous
- ▁smuggl
- ▁altogether
- ▁bottom
- ▁component
- ▁husband
- ▁kenya
- ▁kilogram
- ▁pigments
- ▁platypus
- ▁responsible
- ▁suppose
- ▁temple
- ▁torture
- ▁york
- ▁battle
- ▁concentrat
- ▁status
- ▁witness
- ▁globe
- ▁peace
- ▁radical
- ▁serious
- ▁urine
- ▁tough
- ▁dozen
- ▁nice
- ▁minorit
- ▁beginning
- ▁accurate
- ▁consistent
- ▁street
- ▁running
- ▁round
- ▁message
- ▁spike
- ▁tech
- ▁convert
- ▁define
- ▁draw
- ▁2050
- ▁17
- ▁transportation
- ▁peg
- ▁paper
- ▁members
- ▁rna
- ▁necessary
- ▁nucle
- ▁strategy
- ▁rocket
- ▁wall
- ▁office
- ▁activity
- ▁flee
- ▁recent
- ▁bright
- ▁path
- ▁slight
- time
- ▁miss
- ▁drop
- ▁taxes
- ▁independent
- ▁stronger
- rising
- ▁claim
- ▁front
- ▁receive
- rch
- ▁anyone
- ▁displac
- ▁press
- ▁apply
- ium
- ▁widely
- ▁room
- ▁hopeful
- ▁smaller
- ▁internal
- ▁dry
- ▁pathways
- ▁grown
- orn
- ▁balance
- ▁required
- ▁min
- ull
- ▁carrie
- ▁ruler
- ▁captur
- ▁fully
- ▁ste
- ef
- ▁fa
- ▁terms
- ▁ideas
- ▁brothers
- ▁generations
- ▁towers
- ▁7
- ▁compare
- ▁include
- ▁bi
- ▁wr
- ▁manufacturer
- ▁whos
- ▁nor
- ▁died
- ▁stopp
- ▁happened
- ▁active
- ▁issues
- ▁aid
- ▁effects
- ▁seek
- ▁observat
- '50'
- ence
- ▁emitt
- ▁sett
- ▁environments
- ▁hous
- ▁continu
- fi
- ▁decide
- ▁ok
- ▁son
- bility
- ▁investment
- ese
- led
- inning
- ▁african
- ▁consume
- gs
- cent
- mon
- ▁ill
- tain
- gu
- im
- ▁buildings
- ▁film
- nder
- line
- set
- lem
- ▁direct
- ▁threaten
- loved
- work
- ▁li
- back
- ▁rais
- ▁arrive
- ▁sk
- ▁ban
- ▁paint
- ▁div
- ▁apart
- ▁adapt
- ▁germ
- ▁che
- ▁laugh
- if
- timate
- ▁attempt
- ▁survey
- ▁afternoon
- ▁bladder
- ▁budget
- ▁crazy
- ▁disguise
- ▁empire
- ▁equivalent
- ▁exchange
- ▁expensive
- ▁explain
- ▁feet
- ▁habit
- ▁himself
- ▁institution
- ▁japan
- ▁membrane
- ▁morrison
- ▁nazi
- ▁opportunities
- ▁peruggia
- ▁represent
- ▁revolution
- ▁scenario
- ▁shoot
- ▁strength
- ▁symptoms
- ▁tanuki
- ▁transfer
- ▁victim
- ▁wonder
- ▁application
- ▁murder
- ▁promis
- ▁stuck
- ▁worldwide
- ▁kingdom
- ▁grew
- ▁trillion
- ▁priv
- ▁document
- ▁score
- ▁super
- ▁giant
- ▁finish
- ▁confiden
- ▁acid
- ▁popular
- ▁traits
- ▁italian
- ▁wales
- ▁sand
- ▁analys
- ▁solid
- ▁china
- ▁wild
- ▁approv
- ▁sterilization
- ▁steel
- ▁indicat
- ▁compromise
- ▁collective
- ▁nile
- ature
- ▁kushite
- ▁majority
- ▁andrea
- ▁edge
- ▁syrian
- rench
- ▁chel
- ▁traditional
- ▁fur
- ▁visibl
- ▁fam
- ▁root
- ▁box
- ▁suit
- ▁prepared
- ▁stage
- ▁fine
- ▁mark
- ▁reaction
- ▁removal
- ow
- ▁please
- ▁amazing
- ▁gate
- cular
- ▁cold
- '26'
- ▁fi
- ▁convinc
- mit
- ▁art
- ▁cable
- ez
- ▁liter
- acious
- ▁spe
- ▁mission
- ▁station
- mental
- ▁processes
- ▁concerns
- anic
- ▁bones
- ▁warn
- ▁disc
- ▁maps
- com
- tch
- ▁bare
- ▁net
- ▁scar
- ▁code
- ▁flu
- ▁beliefs
- ▁residents
- ▁exposed
- ▁painting
- ▁soil
- ▁primar
- ▁combined
- ▁farms
- ff
- ▁speaking
- fully
- ▁sold
- ▁town
- ished
- ility
- ological
- ▁lit
- ▁pl
- ▁miner
- ▁officials
- ▁ingredients
- ▁spine
- ▁cleaner
- ▁neighbors
- ▁75
- ▁consum
- ati
- eth
- ▁fan
- ▁regulator
- ▁partners
- ▁tests
- ▁shifting
- ham
- ▁loved
- ▁replace
- ction
- unch
- ▁22
- ▁dut
- ific
- ▁hub
- ▁cha
- ▁roads
- ▁ii
- cc
- cious
- ▁prices
- ami
- ▁ho
- ▁equal
- ▁camps
- ▁produces
- ▁ent
- ▁contribute
- ▁games
- ▁organs
- ▁36
- ber
- ▁tissue
- ▁chamber
- ▁partner
- ▁cat
- ▁route
- ave
- ▁cooperative
- ▁vehicle
- ▁month
- ▁thousand
- ▁relationships
- ▁sums
- mal
- nia
- lic
- ▁app
- ▁structur
- ouri
- onvi
- ▁breath
- ternal
- gi
- ▁ran
- wn
- ets
- gh
- how
- ▁perfect
- ▁sta
- ▁leav
- ▁elevat
- ▁emerg
- ▁bill
- ▁command
- cast
- bti
- ▁spot
- ▁instruct
- ▁respect
- refore
- ▁ambitious
- ▁coronavirus
- ▁cultural
- ▁customers
- ▁disaster
- ▁elephant
- ▁encounter
- ▁horizontal
- ▁hydrogen
- ▁kettle
- ▁mainframe
- ▁messenger
- ▁mirror
- ▁permanent
- ▁photograph
- ▁precise
- ▁principle
- ▁rival
- ▁sahara
- ▁scholar
- ▁tunnel
- ▁choose
- ▁deserve
- ▁distribut
- ▁president
- ▁purpose
- ▁task
- ▁temporar
- aught
- ▁blow
- ▁collaborati
- ▁occur
- ▁resilien
- ▁suffer
- ▁surgeon
- ▁august
- ▁coalition
- ▁protest
- ▁programs
- ▁exciting
- ▁naked
- ▁aspect
- ▁photosynthesis
- ▁weapon
- ▁vertical
- ▁shot
- ▁strauss
- particles
- ▁beautiful
- ▁genes
- ▁disappear
- ▁nerve
- ▁prosper
- ▁function
- romed
- ▁preserv
- ▁encourag
- ▁trigger
- ▁trauma
- ▁indig
- ▁detect
- ▁mainstream
- ▁guide
- ▁iran
- ▁approximat
- ▁reused
- ▁justice
- ▁clinic
- ▁roman
- ▁superheroes
- ▁01
- ▁degrad
- ▁self
- ▁commission
- ▁wealth
- ▁crop
- ▁agenc
- ▁sick
- ▁27
- ▁flat
- ▁epic
- ▁hang
- ▁tale
- ▁ethic
- ▁assembl
- ▁proportion
- ▁broad
- ▁lock
- ▁14
- ▁invite
- ▁workplace
- ▁vary
- marine
- ▁194
- ▁definition
- ▁dig
- ▁transformation
- ▁cheaper
- ▁march
- ▁adaptation
- ▁statement
- ▁jet
- ▁load
- man
- ▁metal
- ▁lost
- ▁carry
- ▁projection
- ▁tension
- ▁fill
- ▁owe
- xic
- ▁curve
- ▁digital
- ▁cannon
- ▁ideal
- ▁fish
- ▁bce
- ▁mom
- ption
- ▁rely
- ▁useful
- etic
- ▁perfectly
- ▁army
- ▁movement
- ▁tear
- ▁eugenics
- ▁successful
- ▁reproducti
- ▁agreed
- ▁careful
- net
- ural
- reliable
- ▁threatened
- ▁coin
- ▁corrupted
- ▁bo
- non
- ▁myth
- ▁increases
- ▁coen
- ort
- ▁solv
- ▁mining
- ▁container
- ▁grand
- spend
- ▁indian
- nit
- ▁met
- mber
- ▁si
- ▁micro
- ▁killed
- ▁wi
- ▁funding
- ▁organisms
- ▁oil
- ▁cont
- ▁limited
- ▁alive
- ▁deal
- men
- ▁routes
- ▁tissues
- ▁chambers
- ▁exc
- ▁pin
- ▁investments
- vert
- ▁pursue
- ▁hands
- ▁periods
- ▁10000
- ▁pai
- ▁argue
- ▁vipers
- ▁observ
- vor
- ▁hot
- ▁basi
- ile
- ▁sil
- ▁sources
- ▁operate
- light
- ▁islands
- ▁ten
- ▁owner
- ▁brains
- asse
- ▁werent
- ▁telescopes
- ▁ha
- ▁conve
- ▁leaves
- lin
- ▁obstructi
- ▁2000
- ▁pe
- ▁par
- broken
- rait
- ▁forever
- ▁win
- ▁trojans
- ▁pi
- ▁disorder
- ▁organism
- ▁neighbor
- ▁practice
- ▁locust
- ational
- ▁remove
- ▁week
- rov
- fu
- ▁meter
- ization
- ▁rid
- ▁schools
- ▁cap
- ▁cure
- istic
- over
- day
- ▁lov
- ▁tim
- ept
- uff
- ▁cho
- ▁accept
- ▁manag
- umb
- stand
- bodies
- face
- ▁deci
- ball
- ▁sens
- ▁surviv
- som
- ▁luck
- ▁cheap
- ▁happ
- ▁publi
- enome
- eign
- ▁shut
- ▁repeat
- ▁consist
- ▁prove
- hood
- ▁spirit
- sequence
- ▁confirm
- ▁persuad
- ▁promot
- precedent
- roach
- ▁amarjot
- ▁australia
- ▁beneath
- ▁bushmaster
- ▁channel
- ▁contrast
- ▁democra
- ▁devastat
- ▁diameter
- ▁discrimination
- ▁fragil
- ▁geothermal
- ▁guarantee
- ▁identify
- ▁innocent
- ▁leonardo
- ▁marriage
- ▁maximiz
- ▁mechanisms
- ▁monica
- ▁monitor
- ▁nutmeg
- ▁participant
- ▁pathogen
- ▁philosopher
- ▁piankhy
- ▁plague
- ▁possess
- ▁resolve
- ▁struggling
- ▁theranos
- ▁thrust
- ▁underground
- ▁vessel
- ▁violence
- ▁yeah
- ▁competitor
- ▁compress
- ▁establish
- ▁fashion
- ▁freetown
- ▁harness
- ▁obvious
- ▁purchas
- ▁random
- ▁smart
- ▁snoring
- ▁struggle
- ▁venom
- ▁video
- ▁healthcare
- ▁plenty
- ▁policymakers
- ▁sugar
- ▁regular
- ▁wife
- ▁earlier
- ▁tumor
- ▁encode
- ▁skill
- ▁dump
- ▁disparit
- ▁technique
- ▁brand
- ▁mouth
- ▁commercial
- ▁decisions
- ▁dense
- ▁details
- ▁calm
- ▁clay
- ▁excellen
- ▁scre
- ▁belarus
- ▁link
- ▁sweat
- ▁influence
- ▁license
- ▁media
- ▁allergi
- ▁tall
- ▁reveal
- ▁insects
- ▁brief
- meral
- ▁burrow
- ▁suspen
- ▁easily
- ▁excess
- ▁civilization
- ▁cloth
- ▁spectac
- ▁deploy
- ▁deny
- ▁wound
- ▁catastrophic
- rena
- ▁metric
- ▁industries
- ▁petrol
- ▁sunlight
- ▁flexible
- ▁flip
- ▁contract
- ▁breed
- ▁186
- ▁poop
- ▁khalil
- ▁divide
- ▁observations
- rope
- ffic
- ▁label
- ▁brig
- ▁agriculture
- ▁landscape
- ▁engage
- ▁trouble
- ▁reproduce
- ▁airway
- ▁intersecti
- ▁worry
- ▁char
- ▁authority
- ▁happiness
- ▁affordable
- ▁warsaw
- ▁gravity
- ▁identity
- aker
- ▁lifetime
- ▁everywhere
- ▁management
- ▁hunt
- ▁stem
- ▁gum
- ▁lone
- ▁squa
- ▁sew
- ▁coral
- ▁bio
- ▁clu
- ▁orient
- ▁honest
- ▁proper
- ▁emergenc
- ▁zoo
- ▁cor
- ▁factories
- ▁wings
- ▁tro
- eek
- ▁universal
- ▁experienc
- ▁circumstances
- ▁firefighters
- ▁cage
- ▁truck
- ▁span
- ▁diet
- ▁mile
- ▁rapidly
- ▁orang
- ▁stream
- ▁emotional
- ▁statistical
- ▁durable
- ▁gav
- ▁trip
- ▁mag
- ▁dispose
- ▁soft
- ▁equally
- ▁strike
- ▁directly
- ▁appli
- ddl
- ▁supernovae
- ender
- ▁writing
- ▁prop
- ference
- raw
- ▁earn
- ▁enable
- ▁foundation
- ely
- ▁devices
- ▁breathing
- ▁hell
- ▁serve
- ▁tool
- ▁resistan
- pr
- ▁magic
- ▁artist
- ▁samples
- ▁snakes
- ▁trials
- ▁poet
- ▁books
- ▁profits
- ▁ce
- take
- ▁assum
- ▁traveling
- ▁inf
- eum
- ▁disorders
- pan
- ably
- oid
- ▁desir
- ament
- ▁union
- ▁africans
- signed
- ▁spin
- ▁ro
- ▁protected
- ify
- pul
- ▁sites
- ▁vo
- ▁included
- ▁accelerat
- ▁birds
- ▁bird
- ▁mus
- ▁pit
- ▁write
- bble
- ▁ai
- ▁replac
- ▁desire
- alt
- ▁double
- ▁je
- umble
- ▁valu
- gd
- '23'
- ▁writ
- ▁book
- ▁sample
- ▁snake
- ▁object
- ▁ingredient
- ▁official
- ▁feature
- ▁brother
- ▁muscle
- ▁tower
- ▁gig
- ▁adult
- ▁generation
- ▁emission
- ▁wave
- '30'
- ▁conf
- ▁trial
- finite
- entle
- j
- gram
- ▁jan
- ike
- ▁fo
- posed
- ▁rem
- ▁leg
- ala
- strict
- think
- sleep
- ioniz
- mission
- ▁emotion
- ▁celebrate
- either
- ▁whi
- ▁compet
- ents
- ▁introduc
- ▁disrupt
- ▁collect
- ▁cit
- orba
- ipping
- ▁capita
- ▁govern
- reak
- ▁batter
- ▁arrang
- ▁belong
- ▁hollow
- ▁referr
- ▁suspect
- craft
- rogen
- ▁1970
- ▁architect
- ▁biontech
- ▁centuries
- ▁commitment
- ▁conduct
- ▁contradict
- ▁counterweight
- ▁dinner
- ▁disagree
- ▁display
- ▁disposal
- ▁distinct
- ▁employee
- ▁equator
- ▁eradicat
- ▁exercise
- ▁exoskeletons
- ▁expectancy
- ▁extrover
- ▁gestapo
- ▁hebrides
- ▁infectious
- ▁introver
- ▁journal
- ▁junajpu
- ▁louvre
- ▁nanostructure
- ▁overwhelm
- ▁phospholipid
- ▁physics
- ▁politician
- ▁practical
- ▁procedure
- ▁profess
- ▁pronouns
- ▁quarter
- ▁regime
- ▁reinforce
- ▁review
- ▁supplement
- ▁tempt
- ▁threshold
- ▁vegeta
- ▁violet
- ▁welcome
- ▁yellow
- ▁zegota
- ▁activat
- ▁ancestor
- ▁article
- ▁conquer
- ▁depart
- ▁email
- ▁herself
- ▁neuron
- ▁peak
- ▁psych
- ▁restoration
- ▁error
- ▁mystery
- ▁revenue
- ▁stunn
- ▁theoretical
- ▁household
- ▁notorious
- ▁scaling
- ▁erode
- ▁firm
- ▁frame
- ▁scene
- ▁evidentialis
- ▁freedom
- ▁title
- ▁desperate
- ▁migrat
- ▁select
- ▁summer
- ▁married
- ▁delta
- ▁shelter
- awatt
- ▁fresh
- ▁hidden
- ▁surgery
- ▁fluorescence
- ▁drain
- ▁kick
- ▁nearby
- ▁related
- ▁evad
- ▁bypass
- ▁colon
- ▁sperm
- ▁flore
- ▁begun
- ▁audience
- ▁rescue
- ▁empower
- proof
- ▁concept
- ▁creatures
- ▁museum
- ▁coordinat
- ▁intensive
- ▁diagnostic
- ▁rush
- ▁consumption
- ▁prohibit
- ▁hatch
- ▁vital
- ▁strand
- ▁persist
- tresse
- ▁missile
- ▁converg
- ▁importance
- ▁exploit
- ▁creativity
- ▁wedding
- ▁narrative
- ▁cliff
- ▁capitalism
- ▁surg
- ▁possibilities
- ▁understood
- foot
- ▁drink
- ▁persecution
- ▁sharp
- ▁flock
- courage
- ▁folk
- ▁refus
- ▁wow
- ▁noise
- ▁imagination
- ▁2021
- federa
- ▁remind
- ▁odd
- ▁extract
- ▁navigation
- ▁astronomy
- ▁illness
- ▁defi
- ▁version
- ▁impressive
- ▁systematic
- tamin
- ▁innovative
- minent
- ▁propos
- ▁resistance
- ▁shop
- ▁strait
- ▁horr
- ▁darkness
- ▁objective
- ▁father
- ound
- ▁restore
- ▁buff
- ▁restrict
- ▁excre
- ▁phone
- ▁mountain
- glad
- ▁pants
- ▁highway
- ▁announc
- ▁interconnected
- ▁hole
- ▁conditioners
- ▁pace
- ▁conscious
- ▁era
- ▁buttons
- ▁gain
- ▁lucky
- ▁barr
- ▁combine
- ▁dim
- ▁confus
- ient
- ▁packag
- ▁medication
- ▁career
- ▁board
- ▁bri
- ▁integrate
- ▁insisted
- arity
- ▁compete
- ▁plann
- immer
- ▁nest
- ▁strict
- ▁lesson
- rote
- ▁asia
- ▁band
- ▁complicated
- ▁constructed
- iment
- ▁hire
- fug
- ▁grat
- ▁closet
- roll
- ▁borders
- ▁monks
- rbag
- ▁protection
- ▁accepted
- ▁fal
- ▁26
- rated
- ▁deadly
- zer
- kay
- ▁investigat
- ▁advise
- eters
- ▁observing
- ski
- ▁prov
- ▁difficulty
- ▁improv
- ▁layer
- col
- ▁filmmak
- mad
- ▁grab
- ▁driver
- ▁meant
- ▁13
- alo
- '37'
- ▁unf
- ▁definit
- ▁burned
- cogni
- weigh
- ob
- lum
- ▁wash
- ▁profit
- obb
- ▁mono
- ▁appeared
- ▁interested
- ▁mess
- ▁comput
- ▁log
- ▁electro
- ▁meal
- ▁hid
- ▁reader
- ▁jo
- ctors
- ▁doubl
- top
- ▁ec
- ▁millennia
- ired
- urd
- gotten
- '80'
- ▁del
- eful
- ▁chris
- atic
- pur
- gar
- ▁pop
- ▁stra
- centri
- ▁spr
- comfortable
- ▁demonstrate
- fo
- ▁variet
- ▁pron
- bb
- ▁fertilize
- ▁figur
- arch
- pped
- ▁ensur
- ▁recogniz
- ls
- '20'
- ▁provid
- ▁explore
- '11'
- ▁achiev
- native
- late
- ried
- rts
- ▁160
- ▁500
- ▁ju
- ▁sali
- ▁character
- ▁35
- eeze
- ▁pen
- ▁assume
- '96'
- putation
- mph
- ▁sna
- ▁farm
- ▁fran
- eight
- ology
- ▁bond
- ▁parent
- ▁kilometer
- hal
- ▁resource
- bra
- ▁20000
- ▁serv
- ▁origin
- ▁advi
- ▁possib
- ▁historic
- place
- ification
- ▁strik
- rish
- ▁reduc
- tail
- ▁construct
- ▁pain
- ▁tip
- ▁complicat
- ▁gran
- ▁prime
- ▁substantial
- tag
- stream
- ▁conv
- front
- ▁rapid
- claim
- expect
- respond
- lord
- usual
- fall
- ▁brit
- point
- allow
- ▁exact
- ▁digit
- board
- tons
- ▁literal
- ▁install
- ▁innovat
- emed
- cti
- ▁lens
- ▁mari
- ▁epi
- ▁absor
- ▁subsidi
- ▁fell
- ▁hypothe
- ▁optim
- ▁constitut
- ▁defeat
- ▁diagonal
- ▁immunotherap
- ▁smooth
- bacteria
- ipples
- ologist
- ğ
- ▁1987
- ▁adjacent
- ▁advocate
- ▁anticipate
- ▁assistance
- ▁baby
- ▁beauty
- ▁calculat
- ▁candidate
- ▁challenging
- ▁champion
- ▁cholesterol
- ▁counterparts
- ▁crusade
- ▁curiosity
- ▁descend
- ▁destination
- ▁destruction
- ▁destructive
- ▁disappointment
- ▁dissolve
- ▁distinguish
- ▁empath
- ▁enjoy
- ▁equitabl
- ▁evaluat
- ▁export
- ▁ghetto
- ▁ghost
- ▁gradual
- ▁hospital
- ▁implement
- ▁inclusiv
- ▁inherit
- ▁intervention
- ▁laboratory
- ▁liquid
- ▁luxury
- ▁mercator
- ▁micah
- ▁miracle
- ▁nebula
- ▁nervous
- ▁neutral
- ▁olaf
- ▁opposite
- ▁participat
- ▁pesticide
- ▁puzzle
- ▁pyrethroid
- ▁rainforest
- ▁rattlesnake
- ▁rebuil
- ▁register
- ▁resolution
- ▁rognvald
- ▁secure
- ▁spectrum
- ▁statue
- ▁television
- ▁therapeutic
- ▁throat
- ▁vulture
- ▁wood
- phobia
- ▁abandon
- ▁accident
- ▁automatic
- ▁bucket
- ▁burden
- ▁competency
- ▁consult
- ▁equity
- ▁evaporat
- ▁interview
- ▁knowledge
- ▁legacy
- ▁legislat
- ▁mathematic
- ▁niger
- ▁plummet
- ▁taste
- ▁technical
- ▁transplant
- itarian
- ▁chronic
- ▁compell
- ▁crowd
- ▁empty
- ▁incarcer
- ▁misfir
- ▁poison
- ▁quantit
- ▁turb
- ▁victor
- ▁election
- ▁priorit
- ▁religio
- ▁snore
- defensi
- ▁bundle
- ▁carousel
- ▁climb
- ▁exhaust
- ▁fractur
- ▁garden
- ▁succeed
- ▁suez
- ▁hdpe
- ▁juice
- aguar
- ▁denim
- ▁dividing
- ▁fallacy
- ▁outcomes
- ▁plot
- ▁blind
- ▁shocked
- ▁bounc
- ▁depth
- incident
- ▁subtle
- ▁pump
- rcia
- ▁initiatives
- ▁spray
- ▁haunt
- ▁traverse
- ▁polish
- ▁hypothesis
- ▁voice
- ▁pledge
- ▁burst
- ▁uncle
- ▁sink
- sturb
- ▁anchor
- ▁gratitude
- ▁pause
- ▁quo
- ▁alert
- ▁vast
- ▁van
- ▁attitudes
- ▁grocer
- ▁countdown
- ▁decrease
- ▁extensi
- ▁invasion
- ▁therapi
- ▁instant
- ▁guy
- ▁forget
- ▁lawyer
- ▁reduction
- ▁strange
- ▁boom
- abul
- ▁season
- ▁begg
- ▁underwater
- ▁strategies
- ▁stimulate
- ▁hurt
- ▁alertness
- ▁utilit
- ▁tomb
- ▁elsewhere
- ▁leap
- ▁patch
- ▁preference
- ▁realistic
- ▁fold
- ▁medit
- ▁stair
- itzer
- ▁embr
- ▁addict
- ▁2015
- ▁percepti
- ▁reign
- ▁painful
- egal
- ▁respi
- ▁depriv
- ▁shutter
- ▁chemistry
- ▁sad
- ▁bias
- ▁boost
- ▁wake
- ▁workforce
- ▁varieties
- ▁repair
- ▁genome
- ▁reject
- ▁124
- slide
- ▁mobility
- ▁shade
- ▁medicine
- ▁vent
- ▁hyp
- ▁melt
- ▁cake
- ▁organized
- ▁novelty
- ▁distan
- ▁france
- ▁suck
- ▁parity
- ▁vision
- ▁voc
- ▁sufficient
- charged
- ▁calcine
- ensity
- ▁dart
- ▁collection
- ▁gun
- ▁rays
- ▁pour
- ▁bitter
- ▁funn
- ▁coff
- ▁fearless
- ▁stance
- ▁inner
- ▁retain
- ▁debt
- ▁chile
- fuse
- ▁partial
- ▁mold
- ▁substan
- ▁survival
- ▁seize
- ▁qui
- ▁installation
- ▁cup
- ruel
- ▁boss
- ▁plug
- ▁apartment
- ▁communicate
- ▁sacrifice
- ▁tapp
- ▁grass
- ▁italy
- ▁roy
- ▁squ
- ▁percentage
- ▁dots
- ▁absolutely
- ▁incentivize
- ▁reserve
- ▁navigate
- ▁creative
- viation
- ▁angle
- ▁deb
- ▁agent
- ▁isolat
- spiration
- ▁ramp
- ▁forgotten
- ▁extin
- ▁celebrated
- diff
- ▁substantially
- ▁viruses
- ▁por
- clos
- ▁comment
- ▁closest
- ▁fatal
- ▁triple
- olk
- ▁eliminate
- ▁facilit
- oster
- ▁geo
- erior
- ▁online
- ▁fung
- ▁insight
- ▁bull
- '79'
- ▁swapp
- ▁wipe
- rrow
- ▁historical
- ▁delivery
- hre
- ntine
- erson
- ▁former
- ▁original
- ▁cri
- ▁accura
- ▁bat
- ▁pave
- reci
- mma
- ▁generat
- rum
- decided
- ▁provider
- cell
- ▁intri
- izab
- neck
- ▁pur
- neu
- ▁stepp
- hoppers
- ▁hu
- ▁dye
- ▁chase
- '21'
- ▁impress
- hu
- ▁broke
- ▁obstruct
- ▁360
- ▁explor
- gue
- rate
- ▁controlle
- roc
- bru
- ecta
- ▁gui
- ▁rec
- qua
- ▁imagin
- ▁operat
- ▁fertiliz
- litar
- ▁hotte
- profitable
- ▁argu
- ▁150
- odes
- tify
- llus
- lets
- ▁terr
- poly
- ▁christ
- ctively
- ▁decarboniz
- scribe
- ▁electr
- ▁immigra
- ▁300
- ▁separat
- ▁hopp
- ▁rang
- employed
- mped
- '98'
- rail
- '97'
- ▁device
- ▁pun
- ▁belief
- ▁resident
- ▁pathway
- ▁egg
- ▁dollar
- ▁scientist
- ▁prim
- ▁reliabl
- igation
- ▁aud
- ▁fun
- maker
- ▁marr
- ▁afford
- ▁gro
- ashes
- urning
- ▁cycl
- ject
- ▁surpris
- ▁eliminat
- ▁disco
- ▁univers
- ▁receiv
- stead
- ▁critic
- mark
- ▁plea
- ▁absolute
- pair
- limited
- water
- truck
- sexual
- spread
- '35'
- bank
- virus
- imagine
- consider
- power
- down
- look
- more
- drive
- ▁communicat
- ▁prepare
- cott
- ▁insist
- fish
- ▁gri
- ▁tap
- ▁incentiv
- ▁distort
- ▁jani
- case
- ▁societ
- nounc
- ▁interact
- ▁syria
- ▁eas
- ▁frequen
- ▁significan
- ▁attac
- ▁populat
- ▁except
- ▁steriliz
- ▁cooperat
- ▁khali
- ▁appro
- ivity
- ▁danger
- ▁inform
- ▁stimul
- ▁quest
- ▁memori
- ▁import
- hibit
- stood
- ▁decre
- ▁influ
- rupt
- cense
- ippi
- ▁photosynthe
- augu
- criminat
- ▁biodivers
- ▁cardio
- ▁ridicul
- occupie
- sophisticated
- ▁absolutis
- ▁accused
- ▁afraid
- ▁algorithm
- ▁aristocra
- ▁assaulted
- ▁association
- ▁assyrian
- ▁atlantic
- ▁autonomy
- ▁availability
- ▁brutal
- ▁byproduct
- ▁ceremon
- ▁circle
- ▁conclusion
- ▁congress
- ▁consensus
- ▁diabetes
- ▁dimensional
- ▁diploma
- ▁disadvantage
- ▁disrespect
- ▁dragonfl
- ▁enzymes
- ▁epidemic
- ▁evolution
- ▁expense
- ▁eyebrows
- ▁fairbnb
- ▁follicle
- ▁fragment
- ▁gatekeeper
- ▁geography
- ▁ghrelin
- ▁gilgamesh
- ▁google
- ▁greece
- ▁gujarat
- ▁harvest
- ▁hurricane
- ▁inevitable
- ▁injustice
- ▁intelligen
- ▁ixbalanke
- ▁jetpack
- ▁judgment
- ▁livelihoods
- ▁longitude
- ▁margin
- ▁minimum
- ▁navy
- ▁necessarily
- ▁passenger
- ▁politics
- ▁prejudice
- ▁prospect
- ▁proximity
- ▁relieve
- ▁replicate
- ▁restaurant
- ▁scotland
- ▁senior
- ▁simultaneously
- ▁slot
- ▁stigma
- ▁supreme
- ▁sustainably
- ▁teenager
- ▁thirteen
- ▁thrill
- ▁tiger
- ▁tomorrow
- ▁toothpaste
- ▁tynwald
- ▁underneath
- ▁utilitarian
- ▁volunteer
- ▁vulnerability
- ▁alternate
- ▁assassinat
- ▁branche
- ▁categor
- ▁commute
- ▁defend
- ▁exclusive
- ▁feather
- ▁graduate
- ▁meticulous
- ▁perpetuat
- ▁resettle
- ▁segregat
- ▁treasur
- ▁violent
- ▁align
- ▁apparent
- ▁blades
- ▁competition
- ▁concert
- ▁counteract
- ▁daunting
- ▁debris
- ▁deficienc
- ▁disperse
- ▁england
- ▁fascinat
- ▁inflation
- ▁inhabit
- ▁irony
- ▁midwest
- ▁occasion
- ▁paddy
- ▁pioneer
- ▁praise
- ▁princes
- ▁resembl
- ▁roof
- ▁sensitive
- ▁territori
- ▁unfair
- rugg
- ▁coworkers
- ▁fruit
- ▁gasoline
- ▁impulse
- ▁lung
- ▁megawatt
- ▁palace
- ▁request
- ▁testimon
- ▁unfolding
- ▁yarn
- ▁bomb
- ▁crack
- ▁drastic
- ▁harsh
- ▁hometown
- ▁infected
- ▁john
- ▁minimize
- ▁properties
- ▁swift
- ▁pillar
- ▁endanger
- ▁flaw
- ▁relax
- ▁turk
- ▁admir
- ▁nuance
- ▁declare
- ▁guard
- ▁reunion
- ▁storytell
- ▁butterfl
- ▁scour
- ▁ribo
- ▁ferry
- ▁hacking
- ▁hydro
- ▁thread
- ▁convention
- ▁text
- ▁split
- ▁congest
- ▁translation
- ▁appreciat
- ratory
- ▁iceland
- ▁jaw
- ▁mistake
- ▁95
- programm
- ▁injure
- ▁explosive
- ▁spiritual
- ▁drill
- ▁typh
- ▁smell
- ▁latin
- ▁poem
- ▁asylum
- ▁crime
- ▁sail
- ▁appeal
- ▁guest
- ▁initial
- ▁peekabo
- ▁outlier
- mog
- ▁proud
- ▁bolt
- ▁spurr
- intuiti
- ▁cantilever
- ▁amani
- ▁genre
- ▁afar
- ▁rub
- ▁moistur
- ▁recover
- ▁items
- ▁optimistic
- ▁slippe
- ▁oversee
- ▁sara
- ▁illegal
- ▁rainwater
- ▁opposition
- ▁overnight
- ▁movie
- ▁explosion
- ▁intensity
- ▁linguistic
- ▁emulsi
- ▁radiation
- ▁violat
- morph
- ▁homo
- ▁spice
- ▁vibran
- ▁intact
- ▁rewards
- ▁exceed
- ▁viewpoint
- ▁heroes
- ▁repeatedly
- ▁confront
- rane
- ▁thre
- ▁squir
- ▁wrap
- ▁godred
- ▁orgy
- ▁sentence
- unci
- ▁memorize
- monia
- holder
- ▁quiet
- rpet
- ▁icon
- ▁spark
- ▁deforestation
- ▁nurs
- ▁1945
- ▁finger
- cade
- ▁efficac
- ▁haz
- ▁motivation
- ▁spotted
- ▁pitch
- ▁subsidize
- ▁intention
- ▁window
- ombi
- ▁swim
- ▁winter
- ▁dynami
- ▁executive
- ▁boil
- ▁assess
- ▁2018
- ▁failure
- ▁horse
- ▁enact
- utter
- ▁circulation
- ▁queen
- ▁distract
- flag
- ▁mentor
- ▁lick
- lank
- ▁ebo
- ▁dirt
- ▁remark
- ▁shake
- ▁entry
- frost
- ▁pear
- ▁bound
- ▁rif
- ▁performance
- ▁exception
- ▁189
- ▁straight
- ▁purp
- imeter
- ▁hills
- ▁chew
- scop
- ▁lamp
- ▁fog
- ▁sweet
- ▁cosm
- ▁mysteri
- rbit
- ▁dying
- ▁argument
- ▁intell
- ▁sultanate
- aire
- ▁tile
- ▁monoc
- ▁machinery
- ▁motion
- ▁infant
- ▁healthier
- ▁continuous
- ▁truce
- ▁undergo
- aboo
- ▁commanders
- ▁qualifi
- ▁55
- ▁anyway
- ▁lenses
- ▁offset
- ▁merg
- quent
- tari
- ▁chim
- ptin
- ▁exit
- ▁dash
- ▁meta
- ▁wish
- ▁poorest
- ▁distortion
- ▁interaction
- ▁proposal
- ▁reven
- ▁trace
- ▁perch
- ▁behav
- ▁disruption
- ▁progressive
- introduce
- ▁gall
- ▁stone
- ▁update
- descent
- ▁dance
- ▁polye
- ▁settle
- fellow
- ▁rob
- ▁stre
- ▁kan
- dominant
- ▁bro
- ▁ev
- ▁purif
- ▁agreement
- ▁dominate
- ▁regulation
- ▁improvement
- hase
- ▁ecolog
- hydr
- pical
- ▁conspi
- ▁inhale
- ▁arriv
- ▁fil
- ▁visitor
- ▁greenland
- phasi
- ▁farmer
- ▁cran
- ▁identifi
- ▁chose
- hau
- grega
- mps
- ▁characteriz
- ▁audi
- ▁oppress
- mination
- aint
- ▁determin
- ▁unemploy
- spire
- ▁giga
- ska
- ▁immigrat
- rank
- sport
- aft
- ▁snap
- emper
- equality
- ▁imp
- ▁terri
- ▁interv
- '19'
- hi
- icated
- ▁demonstrat
- kg
- gible
- ix
- grad
- pression
- '16'
- ▁pursu
- ▁hor
- ▁deli
- ▁spar
- ▁suc
- ▁millenni
- connected
- ▁leon
- ▁inspir
- ▁tho
- ▁faci
- ▁domin
- ▁resist
- ▁mobil
- ▁var
- eval
- ▁interfer
- abilities
- ▁enabl
- ▁border
- ▁forci
- ▁monk
- ▁eugenic
- gae
- ▁concern
- ▁fertil
- ▁mammal
- ▁iri
- ▁merc
- ▁blu
- gger
- ▁statistic
- ▁integr
- compa
- nown
- ▁navigat
- ▁amaz
- ▁reserv
- layer
- escription
- ▁angl
- ▁amplif
- force
- plug
- conscious
- compete
- mind
- leader
- honest
- load
- position
- root
- box
- speak
- flow
- complete
- drop
- check
- sustainable
- friend
- track
- game
- moral
- certain
- green
- world
- people
- life
- what
- about
- human
- wind
- suit
- pay
- minis
- ▁tradition
- ▁bloo
- ▁explo
- ▁strateg
- ▁circu
- ▁gravit
- ▁corporat
- ▁activit
- ▁inequalit
- ▁galax
- ▁calci
- ▁energ
- ▁identit
- ▁locat
- ▁que
- ford
- compromis
- ▁swee
- ▁constr
- imitation
- ▁matte
- zoo
- hwa
- ▁dyna
- ▁flexib
- ▁execut
- ▁renew
- ▁catastroph
- ▁deforest
- rink
- ▁auth
- ▁pub
- ▁marc
- ▁furthe
- ▁diagnos
- ecutive
- titude
- ▁compli
- gressive
- nprofit
- pute
- ▁nano
- oxide
- ▁evident
- ▁surp
- ▁arachn
- ▁hippoc
- nivores
- skeleton
- suppress
- thropo
- ü
- ▁accomplish
- ▁accusation
- ▁acknowledg
- ▁activists
- á
- î
- ç
- ö
- <sos/eos>
init: null
input_size: null
ctc_conf:
dropout_rate: 0.0
ctc_type: builtin
reduce: true
ignore_nan_grad: null
zero_infinity: true
brctc_risk_strategy: exp
brctc_group_strategy: end
brctc_risk_factor: 0.0
st_joint_net_conf: null
model_conf:
asr_weight: 0.3
mt_weight: 0.0
mtlalpha: 0.3
lsm_weight: 0.1
length_normalized_loss: false
use_preprocessor: true
token_type: bpe
src_token_type: bpe
bpemodel: data/en_bn_token_list/tgt_bpe_unigram4000/bpe.model
src_bpemodel: data/en_bn_token_list/src_bpe_unigram4000/bpe.model
non_linguistic_symbols: null
cleaner: null
g2p: null
src_g2p: null
speech_volume_normalize: null
rir_scp: null
rir_apply_prob: 1.0
noise_scp: null
noise_apply_prob: 1.0
noise_db_range: '13_15'
short_noise_thres: 0.5
ctc_sample_rate: 0.0
frontend: default
frontend_conf:
n_fft: 400
hop_length: 160
fs: 16k
specaug: specaug
specaug_conf:
apply_time_warp: true
time_warp_window: 5
time_warp_mode: bicubic
apply_freq_mask: true
freq_mask_width_range:
- 0
- 27
num_freq_mask: 2
apply_time_mask: true
time_mask_width_ratio_range:
- 0.0
- 0.05
num_time_mask: 5
normalize: utterance_mvn
normalize_conf: {}
preencoder: null
preencoder_conf: {}
encoder: conformer
encoder_conf:
output_size: 256
attention_heads: 4
linear_units: 2048
num_blocks: 12
dropout_rate: 0.1
positional_dropout_rate: 0.1
attention_dropout_rate: 0.1
input_layer: conv2d
normalize_before: true
macaron_style: true
rel_pos_type: latest
pos_enc_layer_type: rel_pos
selfattention_layer_type: rel_selfattn
activation_type: swish
use_cnn_module: true
cnn_module_kernel: 31
postencoder: null
postencoder_conf: {}
decoder: transformer
decoder_conf:
attention_heads: 4
linear_units: 2048
num_blocks: 6
dropout_rate: 0.1
positional_dropout_rate: 0.1
self_attention_dropout_rate: 0.1
src_attention_dropout_rate: 0.1
extra_asr_decoder: transformer
extra_asr_decoder_conf:
input_layer: embed
num_blocks: 6
linear_units: 2048
dropout_rate: 0.1
extra_mt_decoder: transformer
extra_mt_decoder_conf:
input_layer: embed
num_blocks: 2
linear_units: 2048
dropout_rate: 0.1
md_encoder: null
md_encoder_conf: {}
hier_encoder: null
hier_encoder_conf: {}
extra_mt_encoder: null
extra_mt_encoder_conf: {}
preprocessor: default
preprocessor_conf: {}
required:
- output_dir
- token_list
version: '202402'
distributed: false
```
</details>
### Citing ESPnet
```BibTex
@inproceedings{watanabe2018espnet,
author={Shinji Watanabe and Takaaki Hori and Shigeki Karita and Tomoki Hayashi and Jiro Nishitoba and Yuya Unno and Nelson Yalta and Jahn Heymann and Matthew Wiesner and Nanxin Chen and Adithya Renduchintala and Tsubasa Ochiai},
title={{ESPnet}: End-to-End Speech Processing Toolkit},
year={2018},
booktitle={Proceedings of Interspeech},
pages={2207--2211},
doi={10.21437/Interspeech.2018-1456},
url={http://dx.doi.org/10.21437/Interspeech.2018-1456}
}
```
or arXiv:
```bibtex
@misc{watanabe2018espnet,
title={ESPnet: End-to-End Speech Processing Toolkit},
author={Shinji Watanabe and Takaaki Hori and Shigeki Karita and Tomoki Hayashi and Jiro Nishitoba and Yuya Unno and Nelson Yalta and Jahn Heymann and Matthew Wiesner and Nanxin Chen and Adithya Renduchintala and Tsubasa Ochiai},
year={2018},
eprint={1804.00015},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
```
| {"language": ["en", "bn"], "license": "cc-by-4.0", "tags": ["espnet", "audio", "speech-translation"], "datasets": ["iwslt24_indic"]} | espnet/iwslt24_indic_en_hi_bpe_tc4000 | null | [
"espnet",
"audio",
"speech-translation",
"en",
"bn",
"dataset:iwslt24_indic",
"arxiv:1804.00015",
"license:cc-by-4.0",
"region:us"
] | null | 2024-04-19T18:16:53+00:00 | [
"1804.00015"
] | [
"en",
"bn"
] | TAGS
#espnet #audio #speech-translation #en #bn #dataset-iwslt24_indic #arxiv-1804.00015 #license-cc-by-4.0 #region-us
| ESPnet2 ST model
----------------
### 'espnet/iwslt24\_indic\_en\_hi\_bpe\_tc4000\_use\_wandbtrue'
This model was trained by cromz22 using iwslt24\_indic recipe in espnet.
### Demo: How to use in ESPnet2
Follow the ESPnet installation instructions
if you haven't done that already.
RESULTS
=======
Environments
------------
* date: 'Wed Apr 17 02:51:38 JST 2024'
* python version: '3.10.14 (main, Mar 21 2024, 16:24:04) [GCC 11.2.0]'
* espnet version: 'espnet 202402'
* pytorch version: 'pytorch 2.1.0'
* Git hash: '83c179ab842987cf01642df2db372aaae260df55'
+ Commit date: 'Wed Apr 17 00:28:29 2024 +0900'
st\_train\_st\_conformer\_raw\_en\_bn\_bpe\_tc4000
--------------------------------------------------
### BLEU
dataset: decode\_st\_conformer\_st\_model\_valid.URL (BP = 1.000 ratio = 1.185 hyp\_len = 46094 ref\_len = 38883), score: , verbose\_score:
ST config
---------
expand
### Citing ESPnet
or arXiv:
| [
"### 'espnet/iwslt24\\_indic\\_en\\_hi\\_bpe\\_tc4000\\_use\\_wandbtrue'\n\n\nThis model was trained by cromz22 using iwslt24\\_indic recipe in espnet.",
"### Demo: How to use in ESPnet2\n\n\nFollow the ESPnet installation instructions\nif you haven't done that already.\n\n\nRESULTS\n=======\n\n\nEnvironments\n------------\n\n\n* date: 'Wed Apr 17 02:51:38 JST 2024'\n* python version: '3.10.14 (main, Mar 21 2024, 16:24:04) [GCC 11.2.0]'\n* espnet version: 'espnet 202402'\n* pytorch version: 'pytorch 2.1.0'\n* Git hash: '83c179ab842987cf01642df2db372aaae260df55'\n\t+ Commit date: 'Wed Apr 17 00:28:29 2024 +0900'\n\n\nst\\_train\\_st\\_conformer\\_raw\\_en\\_bn\\_bpe\\_tc4000\n--------------------------------------------------",
"### BLEU\n\n\ndataset: decode\\_st\\_conformer\\_st\\_model\\_valid.URL (BP = 1.000 ratio = 1.185 hyp\\_len = 46094 ref\\_len = 38883), score: , verbose\\_score: \n\n\nST config\n---------\n\n\nexpand",
"### Citing ESPnet\n\n\nor arXiv:"
] | [
"TAGS\n#espnet #audio #speech-translation #en #bn #dataset-iwslt24_indic #arxiv-1804.00015 #license-cc-by-4.0 #region-us \n",
"### 'espnet/iwslt24\\_indic\\_en\\_hi\\_bpe\\_tc4000\\_use\\_wandbtrue'\n\n\nThis model was trained by cromz22 using iwslt24\\_indic recipe in espnet.",
"### Demo: How to use in ESPnet2\n\n\nFollow the ESPnet installation instructions\nif you haven't done that already.\n\n\nRESULTS\n=======\n\n\nEnvironments\n------------\n\n\n* date: 'Wed Apr 17 02:51:38 JST 2024'\n* python version: '3.10.14 (main, Mar 21 2024, 16:24:04) [GCC 11.2.0]'\n* espnet version: 'espnet 202402'\n* pytorch version: 'pytorch 2.1.0'\n* Git hash: '83c179ab842987cf01642df2db372aaae260df55'\n\t+ Commit date: 'Wed Apr 17 00:28:29 2024 +0900'\n\n\nst\\_train\\_st\\_conformer\\_raw\\_en\\_bn\\_bpe\\_tc4000\n--------------------------------------------------",
"### BLEU\n\n\ndataset: decode\\_st\\_conformer\\_st\\_model\\_valid.URL (BP = 1.000 ratio = 1.185 hyp\\_len = 46094 ref\\_len = 38883), score: , verbose\\_score: \n\n\nST config\n---------\n\n\nexpand",
"### Citing ESPnet\n\n\nor arXiv:"
] |
text-generation | transformers |
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] | {"library_name": "transformers", "tags": []} | sai1881/check_for_math | null | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-04-19T18:16:56+00:00 | [
"1910.09700"
] | [] | TAGS
#transformers #safetensors #mistral #text-generation #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us
|
# Model Card for Model ID
## Model Details
### Model Description
This is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.
- Developed by:
- Funded by [optional]:
- Shared by [optional]:
- Model type:
- Language(s) (NLP):
- License:
- Finetuned from model [optional]:
### Model Sources [optional]
- Repository:
- Paper [optional]:
- Demo [optional]:
## Uses
### Direct Use
### Downstream Use [optional]
### Out-of-Scope Use
## Bias, Risks, and Limitations
### Recommendations
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
## Training Details
### Training Data
### Training Procedure
#### Preprocessing [optional]
#### Training Hyperparameters
- Training regime:
#### Speeds, Sizes, Times [optional]
## Evaluation
### Testing Data, Factors & Metrics
#### Testing Data
#### Factors
#### Metrics
### Results
#### Summary
## Model Examination [optional]
## Environmental Impact
Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).
- Hardware Type:
- Hours used:
- Cloud Provider:
- Compute Region:
- Carbon Emitted:
## Technical Specifications [optional]
### Model Architecture and Objective
### Compute Infrastructure
#### Hardware
#### Software
[optional]
BibTeX:
APA:
## Glossary [optional]
## More Information [optional]
## Model Card Authors [optional]
## Model Card Contact
| [
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.",
"## How to Get Started with the Model\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] | [
"TAGS\n#transformers #safetensors #mistral #text-generation #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n",
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.",
"## How to Get Started with the Model\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] |
text-generation | transformers |
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] | {"library_name": "transformers", "tags": []} | eagle0504/OrpoLlama-3-8B | null | [
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-04-19T18:17:19+00:00 | [
"1910.09700"
] | [] | TAGS
#transformers #safetensors #llama #text-generation #conversational #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us
|
# Model Card for Model ID
## Model Details
### Model Description
This is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.
- Developed by:
- Funded by [optional]:
- Shared by [optional]:
- Model type:
- Language(s) (NLP):
- License:
- Finetuned from model [optional]:
### Model Sources [optional]
- Repository:
- Paper [optional]:
- Demo [optional]:
## Uses
### Direct Use
### Downstream Use [optional]
### Out-of-Scope Use
## Bias, Risks, and Limitations
### Recommendations
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
## Training Details
### Training Data
### Training Procedure
#### Preprocessing [optional]
#### Training Hyperparameters
- Training regime:
#### Speeds, Sizes, Times [optional]
## Evaluation
### Testing Data, Factors & Metrics
#### Testing Data
#### Factors
#### Metrics
### Results
#### Summary
## Model Examination [optional]
## Environmental Impact
Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).
- Hardware Type:
- Hours used:
- Cloud Provider:
- Compute Region:
- Carbon Emitted:
## Technical Specifications [optional]
### Model Architecture and Objective
### Compute Infrastructure
#### Hardware
#### Software
[optional]
BibTeX:
APA:
## Glossary [optional]
## More Information [optional]
## Model Card Authors [optional]
## Model Card Contact
| [
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.",
"## How to Get Started with the Model\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] | [
"TAGS\n#transformers #safetensors #llama #text-generation #conversational #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n",
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.",
"## How to Get Started with the Model\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] |
text-generation | transformers |
This is a simple experiment using geman ORPO training for one epoch using qlora and unsloth on [Vezora/Mistral-22B-v0.2](https://huggingface.coVezora/Mistral-22B-v0.2) | {"language": ["de", "en"], "license": "apache-2.0", "datasets": ["johannhartmann/steroids", "johannhartmann/oh25_mistral_dpo_de"]} | johannhartmann/mistral22b_orpo_de | null | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"conversational",
"de",
"en",
"dataset:johannhartmann/steroids",
"dataset:johannhartmann/oh25_mistral_dpo_de",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-04-19T18:18:15+00:00 | [] | [
"de",
"en"
] | TAGS
#transformers #safetensors #mistral #text-generation #conversational #de #en #dataset-johannhartmann/steroids #dataset-johannhartmann/oh25_mistral_dpo_de #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us
|
This is a simple experiment using geman ORPO training for one epoch using qlora and unsloth on Vezora/Mistral-22B-v0.2 | [] | [
"TAGS\n#transformers #safetensors #mistral #text-generation #conversational #de #en #dataset-johannhartmann/steroids #dataset-johannhartmann/oh25_mistral_dpo_de #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n"
] |
text-generation | transformers | # MaziyarPanahi/Llama-3-13B-Instruct-v0.1 AWQ
- Model creator: [MaziyarPanahi](https://huggingface.co/MaziyarPanahi)
- Original model: [Llama-3-13B-Instruct-v0.1](https://huggingface.co/MaziyarPanahi/Llama-3-13B-Instruct-v0.1)
<img src="./llama-3-merges.webp" alt="Goku 8x22B v0.1 Logo" width="500" style="margin-left:'auto' margin-right:'auto' display:'block'"/>
## Model Summary
This model is a self-merge of `meta-llama/Meta-Llama-3-8B-Instruct` model.
## Prompt template
```text
<|begin_of_text|><|start_header_id|>system<|end_header_id|>
You are a helpful assistant.<|eot_id|><|start_header_id|>user<|end_header_id|>
what's 25-4*2+3<|eot_id|><|start_header_id|>assistant<|end_header_id|>
To evaluate this expression, we need to follow the order of operations (PEMDAS):
1. First, multiply 4 and 2: 4*2 = 8
2. Then, subtract 8 from 25: 25 - 8 = 17
3. Finally, add 3: 17 + 3 = 20
So, 25-4*2+3 = 20!<|eot_id|>
To evaluate this expression, we need to follow the order of operations (PEMDAS):
1. First, multiply 4 and 2: 4*2 = 8
2. Then, subtract 8 from 25: 25 - 8 = 17
3. Finally, add 3: 17 + 3 = 20
So, 25-4*2+3 = 20!
```
| {"language": ["en"], "license": "other", "library_name": "transformers", "tags": ["4-bit", "AWQ", "text-generation", "autotrain_compatible", "endpoints_compatible", "mergekit", "merge", "facebook", "meta", "pytorch", "llama", "llama-3"], "model_name": "Llama-3-13B-Instruct-v0.1", "base_model": "meta-llama/Meta-Llama-3-8B-Instruct", "pipeline_tag": "text-generation", "license_name": "llama3", "license_link": "LICENSE", "inference": false, "model_creator": "MaziyarPanahi", "quantized_by": "Suparious"} | solidrust/Llama-3-13B-Instruct-v0.1-AWQ | null | [
"transformers",
"safetensors",
"llama",
"text-generation",
"4-bit",
"AWQ",
"autotrain_compatible",
"endpoints_compatible",
"mergekit",
"merge",
"facebook",
"meta",
"pytorch",
"llama-3",
"conversational",
"en",
"base_model:meta-llama/Meta-Llama-3-8B-Instruct",
"license:other",
"text-generation-inference",
"region:us"
] | null | 2024-04-19T18:18:35+00:00 | [] | [
"en"
] | TAGS
#transformers #safetensors #llama #text-generation #4-bit #AWQ #autotrain_compatible #endpoints_compatible #mergekit #merge #facebook #meta #pytorch #llama-3 #conversational #en #base_model-meta-llama/Meta-Llama-3-8B-Instruct #license-other #text-generation-inference #region-us
| # MaziyarPanahi/Llama-3-13B-Instruct-v0.1 AWQ
- Model creator: MaziyarPanahi
- Original model: Llama-3-13B-Instruct-v0.1
<img src="./URL" alt="Goku 8x22B v0.1 Logo" width="500" style="margin-left:'auto' margin-right:'auto' display:'block'"/>
## Model Summary
This model is a self-merge of 'meta-llama/Meta-Llama-3-8B-Instruct' model.
## Prompt template
| [
"# MaziyarPanahi/Llama-3-13B-Instruct-v0.1 AWQ\n\n- Model creator: MaziyarPanahi\n- Original model: Llama-3-13B-Instruct-v0.1\n\n<img src=\"./URL\" alt=\"Goku 8x22B v0.1 Logo\" width=\"500\" style=\"margin-left:'auto' margin-right:'auto' display:'block'\"/>",
"## Model Summary\n\nThis model is a self-merge of 'meta-llama/Meta-Llama-3-8B-Instruct' model.",
"## Prompt template"
] | [
"TAGS\n#transformers #safetensors #llama #text-generation #4-bit #AWQ #autotrain_compatible #endpoints_compatible #mergekit #merge #facebook #meta #pytorch #llama-3 #conversational #en #base_model-meta-llama/Meta-Llama-3-8B-Instruct #license-other #text-generation-inference #region-us \n",
"# MaziyarPanahi/Llama-3-13B-Instruct-v0.1 AWQ\n\n- Model creator: MaziyarPanahi\n- Original model: Llama-3-13B-Instruct-v0.1\n\n<img src=\"./URL\" alt=\"Goku 8x22B v0.1 Logo\" width=\"500\" style=\"margin-left:'auto' margin-right:'auto' display:'block'\"/>",
"## Model Summary\n\nThis model is a self-merge of 'meta-llama/Meta-Llama-3-8B-Instruct' model.",
"## Prompt template"
] |
null | adapter-transformers |
# Adapter `BigTMiami/pretrain_dapt_tapt_unipelt_adapter` for roberta-base
An [adapter](https://adapterhub.ml) for the `roberta-base` model that was trained on the [BigTMiami/amazon_helpfulness_TAPT_pretraining_dataset](https://huggingface.co/datasets/BigTMiami/amazon_helpfulness_TAPT_pretraining_dataset/) dataset.
This adapter was created for usage with the **[Adapters](https://github.com/Adapter-Hub/adapters)** library.
## Usage
First, install `adapters`:
```
pip install -U adapters
```
Now, the adapter can be loaded and activated like this:
```python
from adapters import AutoAdapterModel
model = AutoAdapterModel.from_pretrained("roberta-base")
adapter_name = model.load_adapter("BigTMiami/pretrain_dapt_tapt_unipelt_adapter", source="hf", set_active=True)
```
## Architecture & Training
<!-- Add some description here -->
## Evaluation results
<!-- Add some description here -->
## Citation
<!-- Add some description here --> | {"tags": ["adapter-transformers", "roberta"], "datasets": ["BigTMiami/amazon_helpfulness_TAPT_pretraining_dataset"]} | BigTMiami/pretrain_dapt_tapt_unipelt_adapter | null | [
"adapter-transformers",
"roberta",
"dataset:BigTMiami/amazon_helpfulness_TAPT_pretraining_dataset",
"region:us"
] | null | 2024-04-19T18:20:58+00:00 | [] | [] | TAGS
#adapter-transformers #roberta #dataset-BigTMiami/amazon_helpfulness_TAPT_pretraining_dataset #region-us
|
# Adapter 'BigTMiami/pretrain_dapt_tapt_unipelt_adapter' for roberta-base
An adapter for the 'roberta-base' model that was trained on the BigTMiami/amazon_helpfulness_TAPT_pretraining_dataset dataset.
This adapter was created for usage with the Adapters library.
## Usage
First, install 'adapters':
Now, the adapter can be loaded and activated like this:
## Architecture & Training
## Evaluation results
| [
"# Adapter 'BigTMiami/pretrain_dapt_tapt_unipelt_adapter' for roberta-base\n\nAn adapter for the 'roberta-base' model that was trained on the BigTMiami/amazon_helpfulness_TAPT_pretraining_dataset dataset.\n\nThis adapter was created for usage with the Adapters library.",
"## Usage\n\nFirst, install 'adapters':\n\n\n\nNow, the adapter can be loaded and activated like this:",
"## Architecture & Training",
"## Evaluation results"
] | [
"TAGS\n#adapter-transformers #roberta #dataset-BigTMiami/amazon_helpfulness_TAPT_pretraining_dataset #region-us \n",
"# Adapter 'BigTMiami/pretrain_dapt_tapt_unipelt_adapter' for roberta-base\n\nAn adapter for the 'roberta-base' model that was trained on the BigTMiami/amazon_helpfulness_TAPT_pretraining_dataset dataset.\n\nThis adapter was created for usage with the Adapters library.",
"## Usage\n\nFirst, install 'adapters':\n\n\n\nNow, the adapter can be loaded and activated like this:",
"## Architecture & Training",
"## Evaluation results"
] |
null | transformers |
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] | {"library_name": "transformers", "tags": []} | hi000000/insta_upnormal-llama-koen_80 | null | [
"transformers",
"safetensors",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null | 2024-04-19T18:22:44+00:00 | [
"1910.09700"
] | [] | TAGS
#transformers #safetensors #arxiv-1910.09700 #endpoints_compatible #region-us
|
# Model Card for Model ID
## Model Details
### Model Description
This is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.
- Developed by:
- Funded by [optional]:
- Shared by [optional]:
- Model type:
- Language(s) (NLP):
- License:
- Finetuned from model [optional]:
### Model Sources [optional]
- Repository:
- Paper [optional]:
- Demo [optional]:
## Uses
### Direct Use
### Downstream Use [optional]
### Out-of-Scope Use
## Bias, Risks, and Limitations
### Recommendations
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
## Training Details
### Training Data
### Training Procedure
#### Preprocessing [optional]
#### Training Hyperparameters
- Training regime:
#### Speeds, Sizes, Times [optional]
## Evaluation
### Testing Data, Factors & Metrics
#### Testing Data
#### Factors
#### Metrics
### Results
#### Summary
## Model Examination [optional]
## Environmental Impact
Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).
- Hardware Type:
- Hours used:
- Cloud Provider:
- Compute Region:
- Carbon Emitted:
## Technical Specifications [optional]
### Model Architecture and Objective
### Compute Infrastructure
#### Hardware
#### Software
[optional]
BibTeX:
APA:
## Glossary [optional]
## More Information [optional]
## Model Card Authors [optional]
## Model Card Contact
| [
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.",
"## How to Get Started with the Model\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] | [
"TAGS\n#transformers #safetensors #arxiv-1910.09700 #endpoints_compatible #region-us \n",
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.",
"## How to Get Started with the Model\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] |
null | transformers |
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
| {"library_name": "transformers", "tags": []} | jspr/smut_llama_8b_peft_ax | null | [
"transformers",
"safetensors",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null | 2024-04-19T18:26:00+00:00 | [
"1910.09700"
] | [] | TAGS
#transformers #safetensors #arxiv-1910.09700 #endpoints_compatible #region-us
|
# Model Card for Model ID
## Model Details
### Model Description
This is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.
- Developed by:
- Funded by [optional]:
- Shared by [optional]:
- Model type:
- Language(s) (NLP):
- License:
- Finetuned from model [optional]:
### Model Sources [optional]
- Repository:
- Paper [optional]:
- Demo [optional]:
## Uses
### Direct Use
### Downstream Use [optional]
### Out-of-Scope Use
## Bias, Risks, and Limitations
### Recommendations
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
## Training Details
### Training Data
### Training Procedure
#### Preprocessing [optional]
#### Training Hyperparameters
- Training regime:
#### Speeds, Sizes, Times [optional]
## Evaluation
### Testing Data, Factors & Metrics
#### Testing Data
#### Factors
#### Metrics
### Results
#### Summary
## Model Examination [optional]
## Environmental Impact
Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).
- Hardware Type:
- Hours used:
- Cloud Provider:
- Compute Region:
- Carbon Emitted:
## Technical Specifications [optional]
### Model Architecture and Objective
### Compute Infrastructure
#### Hardware
#### Software
[optional]
BibTeX:
APA:
## Glossary [optional]
## More Information [optional]
## Model Card Authors [optional]
## Model Card Contact
| [
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.",
"## How to Get Started with the Model\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] | [
"TAGS\n#transformers #safetensors #arxiv-1910.09700 #endpoints_compatible #region-us \n",
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.",
"## How to Get Started with the Model\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] |
object-detection | transformers |
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] | {"library_name": "transformers", "tags": []} | sekhharr/detr_finetuned_v11_last_checkpoint | null | [
"transformers",
"safetensors",
"detr",
"object-detection",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null | 2024-04-19T18:28:01+00:00 | [
"1910.09700"
] | [] | TAGS
#transformers #safetensors #detr #object-detection #arxiv-1910.09700 #endpoints_compatible #region-us
|
# Model Card for Model ID
## Model Details
### Model Description
This is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.
- Developed by:
- Funded by [optional]:
- Shared by [optional]:
- Model type:
- Language(s) (NLP):
- License:
- Finetuned from model [optional]:
### Model Sources [optional]
- Repository:
- Paper [optional]:
- Demo [optional]:
## Uses
### Direct Use
### Downstream Use [optional]
### Out-of-Scope Use
## Bias, Risks, and Limitations
### Recommendations
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
## Training Details
### Training Data
### Training Procedure
#### Preprocessing [optional]
#### Training Hyperparameters
- Training regime:
#### Speeds, Sizes, Times [optional]
## Evaluation
### Testing Data, Factors & Metrics
#### Testing Data
#### Factors
#### Metrics
### Results
#### Summary
## Model Examination [optional]
## Environmental Impact
Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).
- Hardware Type:
- Hours used:
- Cloud Provider:
- Compute Region:
- Carbon Emitted:
## Technical Specifications [optional]
### Model Architecture and Objective
### Compute Infrastructure
#### Hardware
#### Software
[optional]
BibTeX:
APA:
## Glossary [optional]
## More Information [optional]
## Model Card Authors [optional]
## Model Card Contact
| [
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.",
"## How to Get Started with the Model\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] | [
"TAGS\n#transformers #safetensors #detr #object-detection #arxiv-1910.09700 #endpoints_compatible #region-us \n",
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.",
"## How to Get Started with the Model\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] |
text-classification | transformers |
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
| {"library_name": "transformers", "tags": []} | daedalus16/bert-M1b-textclassification | null | [
"transformers",
"safetensors",
"bert",
"text-classification",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | null | 2024-04-19T18:28:37+00:00 | [
"1910.09700"
] | [] | TAGS
#transformers #safetensors #bert #text-classification #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #region-us
|
# Model Card for Model ID
## Model Details
### Model Description
This is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.
- Developed by:
- Funded by [optional]:
- Shared by [optional]:
- Model type:
- Language(s) (NLP):
- License:
- Finetuned from model [optional]:
### Model Sources [optional]
- Repository:
- Paper [optional]:
- Demo [optional]:
## Uses
### Direct Use
### Downstream Use [optional]
### Out-of-Scope Use
## Bias, Risks, and Limitations
### Recommendations
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
## Training Details
### Training Data
### Training Procedure
#### Preprocessing [optional]
#### Training Hyperparameters
- Training regime:
#### Speeds, Sizes, Times [optional]
## Evaluation
### Testing Data, Factors & Metrics
#### Testing Data
#### Factors
#### Metrics
### Results
#### Summary
## Model Examination [optional]
## Environmental Impact
Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).
- Hardware Type:
- Hours used:
- Cloud Provider:
- Compute Region:
- Carbon Emitted:
## Technical Specifications [optional]
### Model Architecture and Objective
### Compute Infrastructure
#### Hardware
#### Software
[optional]
BibTeX:
APA:
## Glossary [optional]
## More Information [optional]
## Model Card Authors [optional]
## Model Card Contact
| [
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.",
"## How to Get Started with the Model\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] | [
"TAGS\n#transformers #safetensors #bert #text-classification #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #region-us \n",
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.",
"## How to Get Started with the Model\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] |
text-generation | transformers |
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] | {"library_name": "transformers", "tags": []} | Grayx/sad_pepe_31.0 | null | [
"transformers",
"safetensors",
"stablelm",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | null | 2024-04-19T18:29:30+00:00 | [
"1910.09700"
] | [] | TAGS
#transformers #safetensors #stablelm #text-generation #conversational #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #region-us
|
# Model Card for Model ID
## Model Details
### Model Description
This is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.
- Developed by:
- Funded by [optional]:
- Shared by [optional]:
- Model type:
- Language(s) (NLP):
- License:
- Finetuned from model [optional]:
### Model Sources [optional]
- Repository:
- Paper [optional]:
- Demo [optional]:
## Uses
### Direct Use
### Downstream Use [optional]
### Out-of-Scope Use
## Bias, Risks, and Limitations
### Recommendations
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
## Training Details
### Training Data
### Training Procedure
#### Preprocessing [optional]
#### Training Hyperparameters
- Training regime:
#### Speeds, Sizes, Times [optional]
## Evaluation
### Testing Data, Factors & Metrics
#### Testing Data
#### Factors
#### Metrics
### Results
#### Summary
## Model Examination [optional]
## Environmental Impact
Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).
- Hardware Type:
- Hours used:
- Cloud Provider:
- Compute Region:
- Carbon Emitted:
## Technical Specifications [optional]
### Model Architecture and Objective
### Compute Infrastructure
#### Hardware
#### Software
[optional]
BibTeX:
APA:
## Glossary [optional]
## More Information [optional]
## Model Card Authors [optional]
## Model Card Contact
| [
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.",
"## How to Get Started with the Model\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] | [
"TAGS\n#transformers #safetensors #stablelm #text-generation #conversational #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #region-us \n",
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.",
"## How to Get Started with the Model\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] |
text2text-generation | transformers |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# UrduSum5k
This model is a fine-tuned version of [ahmed0189/mT5-Arabic-text-summarization](https://huggingface.co/ahmed0189/mT5-Arabic-text-summarization) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: nan
- Rouge1: 0.0
- Rouge2: 0.0
- Rougel: 0.0
- Rougelsum: 0.0
- Gen Len: 127.0
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 1
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
| 0.0 | 1.0 | 1500 | nan | 0.0 | 0.0 | 0.0 | 0.0 | 127.0 |
### Framework versions
- Transformers 4.28.0
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.13.3
| {"license": "apache-2.0", "tags": ["generated_from_trainer"], "metrics": ["rouge"], "model-index": [{"name": "UrduSum5k", "results": []}]} | Alefiah/UrduSum5k | null | [
"transformers",
"pytorch",
"tensorboard",
"mt5",
"text2text-generation",
"generated_from_trainer",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-04-19T18:29:42+00:00 | [] | [] | TAGS
#transformers #pytorch #tensorboard #mt5 #text2text-generation #generated_from_trainer #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us
| UrduSum5k
=========
This model is a fine-tuned version of ahmed0189/mT5-Arabic-text-summarization on the None dataset.
It achieves the following results on the evaluation set:
* Loss: nan
* Rouge1: 0.0
* Rouge2: 0.0
* Rougel: 0.0
* Rougelsum: 0.0
* Gen Len: 127.0
Model description
-----------------
More information needed
Intended uses & limitations
---------------------------
More information needed
Training and evaluation data
----------------------------
More information needed
Training procedure
------------------
### Training hyperparameters
The following hyperparameters were used during training:
* learning\_rate: 2e-05
* train\_batch\_size: 2
* eval\_batch\_size: 2
* seed: 42
* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
* lr\_scheduler\_type: linear
* num\_epochs: 1
* mixed\_precision\_training: Native AMP
### Training results
### Framework versions
* Transformers 4.28.0
* Pytorch 2.2.1+cu121
* Datasets 2.19.0
* Tokenizers 0.13.3
| [
"### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 2e-05\n* train\\_batch\\_size: 2\n* eval\\_batch\\_size: 2\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 1\n* mixed\\_precision\\_training: Native AMP",
"### Training results",
"### Framework versions\n\n\n* Transformers 4.28.0\n* Pytorch 2.2.1+cu121\n* Datasets 2.19.0\n* Tokenizers 0.13.3"
] | [
"TAGS\n#transformers #pytorch #tensorboard #mt5 #text2text-generation #generated_from_trainer #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n",
"### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 2e-05\n* train\\_batch\\_size: 2\n* eval\\_batch\\_size: 2\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 1\n* mixed\\_precision\\_training: Native AMP",
"### Training results",
"### Framework versions\n\n\n* Transformers 4.28.0\n* Pytorch 2.2.1+cu121\n* Datasets 2.19.0\n* Tokenizers 0.13.3"
] |
null | transformers |
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] | {"library_name": "transformers", "tags": []} | artixjain/mistral5epoch | null | [
"transformers",
"safetensors",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null | 2024-04-19T18:31:30+00:00 | [
"1910.09700"
] | [] | TAGS
#transformers #safetensors #arxiv-1910.09700 #endpoints_compatible #region-us
|
# Model Card for Model ID
## Model Details
### Model Description
This is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.
- Developed by:
- Funded by [optional]:
- Shared by [optional]:
- Model type:
- Language(s) (NLP):
- License:
- Finetuned from model [optional]:
### Model Sources [optional]
- Repository:
- Paper [optional]:
- Demo [optional]:
## Uses
### Direct Use
### Downstream Use [optional]
### Out-of-Scope Use
## Bias, Risks, and Limitations
### Recommendations
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
## Training Details
### Training Data
### Training Procedure
#### Preprocessing [optional]
#### Training Hyperparameters
- Training regime:
#### Speeds, Sizes, Times [optional]
## Evaluation
### Testing Data, Factors & Metrics
#### Testing Data
#### Factors
#### Metrics
### Results
#### Summary
## Model Examination [optional]
## Environmental Impact
Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).
- Hardware Type:
- Hours used:
- Cloud Provider:
- Compute Region:
- Carbon Emitted:
## Technical Specifications [optional]
### Model Architecture and Objective
### Compute Infrastructure
#### Hardware
#### Software
[optional]
BibTeX:
APA:
## Glossary [optional]
## More Information [optional]
## Model Card Authors [optional]
## Model Card Contact
| [
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.",
"## How to Get Started with the Model\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] | [
"TAGS\n#transformers #safetensors #arxiv-1910.09700 #endpoints_compatible #region-us \n",
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.",
"## How to Get Started with the Model\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] |
text-generation | transformers |
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] | {"library_name": "transformers", "tags": []} | tom-brady/sn6_240 | null | [
"transformers",
"safetensors",
"stablelm",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | null | 2024-04-19T18:31:52+00:00 | [
"1910.09700"
] | [] | TAGS
#transformers #safetensors #stablelm #text-generation #conversational #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #region-us
|
# Model Card for Model ID
## Model Details
### Model Description
This is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.
- Developed by:
- Funded by [optional]:
- Shared by [optional]:
- Model type:
- Language(s) (NLP):
- License:
- Finetuned from model [optional]:
### Model Sources [optional]
- Repository:
- Paper [optional]:
- Demo [optional]:
## Uses
### Direct Use
### Downstream Use [optional]
### Out-of-Scope Use
## Bias, Risks, and Limitations
### Recommendations
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
## Training Details
### Training Data
### Training Procedure
#### Preprocessing [optional]
#### Training Hyperparameters
- Training regime:
#### Speeds, Sizes, Times [optional]
## Evaluation
### Testing Data, Factors & Metrics
#### Testing Data
#### Factors
#### Metrics
### Results
#### Summary
## Model Examination [optional]
## Environmental Impact
Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).
- Hardware Type:
- Hours used:
- Cloud Provider:
- Compute Region:
- Carbon Emitted:
## Technical Specifications [optional]
### Model Architecture and Objective
### Compute Infrastructure
#### Hardware
#### Software
[optional]
BibTeX:
APA:
## Glossary [optional]
## More Information [optional]
## Model Card Authors [optional]
## Model Card Contact
| [
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.",
"## How to Get Started with the Model\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] | [
"TAGS\n#transformers #safetensors #stablelm #text-generation #conversational #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #region-us \n",
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.",
"## How to Get Started with the Model\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] |
automatic-speech-recognition | transformers |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# Whisper Small te - Pravalika Bollam
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Common Voice 16 dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 16
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 60
- training_steps: 200
- mixed_precision_training: Native AMP
### Training results
### Framework versions
- Transformers 4.41.0.dev0
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1
| {"language": ["te"], "license": "apache-2.0", "tags": ["generated_from_trainer"], "datasets": ["mozilla-foundation/common_voice_16_0"], "base_model": "openai/whisper-small", "model-index": [{"name": "Whisper Small te - Pravalika Bollam", "results": []}]} | Pravalika56/my_model_directory | null | [
"transformers",
"tensorboard",
"safetensors",
"whisper",
"automatic-speech-recognition",
"generated_from_trainer",
"te",
"dataset:mozilla-foundation/common_voice_16_0",
"base_model:openai/whisper-small",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | 2024-04-19T18:34:11+00:00 | [] | [
"te"
] | TAGS
#transformers #tensorboard #safetensors #whisper #automatic-speech-recognition #generated_from_trainer #te #dataset-mozilla-foundation/common_voice_16_0 #base_model-openai/whisper-small #license-apache-2.0 #endpoints_compatible #region-us
|
# Whisper Small te - Pravalika Bollam
This model is a fine-tuned version of openai/whisper-small on the Common Voice 16 dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 16
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 60
- training_steps: 200
- mixed_precision_training: Native AMP
### Training results
### Framework versions
- Transformers 4.41.0.dev0
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1
| [
"# Whisper Small te - Pravalika Bollam\n\nThis model is a fine-tuned version of openai/whisper-small on the Common Voice 16 dataset.",
"## Model description\n\nMore information needed",
"## Intended uses & limitations\n\nMore information needed",
"## Training and evaluation data\n\nMore information needed",
"## Training procedure",
"### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 2e-05\n- train_batch_size: 16\n- eval_batch_size: 32\n- seed: 42\n- gradient_accumulation_steps: 2\n- total_train_batch_size: 32\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- lr_scheduler_warmup_steps: 60\n- training_steps: 200\n- mixed_precision_training: Native AMP",
"### Training results",
"### Framework versions\n\n- Transformers 4.41.0.dev0\n- Pytorch 2.2.1+cu121\n- Datasets 2.19.0\n- Tokenizers 0.19.1"
] | [
"TAGS\n#transformers #tensorboard #safetensors #whisper #automatic-speech-recognition #generated_from_trainer #te #dataset-mozilla-foundation/common_voice_16_0 #base_model-openai/whisper-small #license-apache-2.0 #endpoints_compatible #region-us \n",
"# Whisper Small te - Pravalika Bollam\n\nThis model is a fine-tuned version of openai/whisper-small on the Common Voice 16 dataset.",
"## Model description\n\nMore information needed",
"## Intended uses & limitations\n\nMore information needed",
"## Training and evaluation data\n\nMore information needed",
"## Training procedure",
"### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 2e-05\n- train_batch_size: 16\n- eval_batch_size: 32\n- seed: 42\n- gradient_accumulation_steps: 2\n- total_train_batch_size: 32\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- lr_scheduler_warmup_steps: 60\n- training_steps: 200\n- mixed_precision_training: Native AMP",
"### Training results",
"### Framework versions\n\n- Transformers 4.41.0.dev0\n- Pytorch 2.2.1+cu121\n- Datasets 2.19.0\n- Tokenizers 0.19.1"
] |
text2text-generation | transformers |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# T5_base_NASA_ADS_title_v5
This model is a fine-tuned version of [t5-base](https://huggingface.co/t5-base) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 1.7910
- Rouge1: 0.4285
- Rouge2: 0.2147
- Rougel: 0.3712
- Rougelsum: 0.3711
- Gen Len: 16.3966
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 15
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|:-------------:|:-----:|:-----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
| 2.1209 | 1.0 | 2535 | 1.9129 | 0.4133 | 0.2034 | 0.3581 | 0.3581 | 16.0037 |
| 1.9984 | 2.0 | 5070 | 1.8568 | 0.4138 | 0.2051 | 0.3608 | 0.3608 | 15.9065 |
| 1.9004 | 3.0 | 7605 | 1.8307 | 0.4222 | 0.2109 | 0.3675 | 0.3674 | 15.9252 |
| 1.8491 | 4.0 | 10140 | 1.8110 | 0.4199 | 0.209 | 0.3638 | 0.3638 | 16.1813 |
| 1.7823 | 5.0 | 12675 | 1.7972 | 0.4231 | 0.2107 | 0.3665 | 0.3664 | 16.2793 |
| 1.7302 | 6.0 | 15210 | 1.7924 | 0.427 | 0.2145 | 0.3704 | 0.3705 | 16.3819 |
| 1.6996 | 7.0 | 17745 | 1.7918 | 0.4284 | 0.2157 | 0.3712 | 0.3713 | 16.0767 |
| 1.6705 | 8.0 | 20280 | 1.7851 | 0.4252 | 0.2134 | 0.3682 | 0.3682 | 16.3485 |
| 1.6338 | 9.0 | 22815 | 1.7853 | 0.4291 | 0.2146 | 0.3721 | 0.372 | 16.398 |
| 1.6193 | 10.0 | 25350 | 1.7850 | 0.4297 | 0.2158 | 0.3726 | 0.3725 | 16.3821 |
| 1.5808 | 11.0 | 27885 | 1.7837 | 0.4274 | 0.2144 | 0.3708 | 0.3706 | 16.303 |
| 1.574 | 12.0 | 30420 | 1.7895 | 0.428 | 0.2151 | 0.3708 | 0.3709 | 16.3568 |
| 1.5544 | 13.0 | 32955 | 1.7898 | 0.4282 | 0.2152 | 0.3711 | 0.3711 | 16.412 |
| 1.5377 | 14.0 | 35490 | 1.7902 | 0.4287 | 0.2147 | 0.3709 | 0.3709 | 16.3917 |
| 1.5304 | 15.0 | 38025 | 1.7910 | 0.4285 | 0.2147 | 0.3712 | 0.3711 | 16.3966 |
### Framework versions
- Transformers 4.40.0
- Pytorch 2.1.2
- Datasets 2.1.0
- Tokenizers 0.19.1
| {"license": "apache-2.0", "tags": ["generated_from_trainer"], "metrics": ["rouge"], "base_model": "t5-base", "model-index": [{"name": "T5_base_NASA_ADS_title_v5", "results": []}]} | Swarnava/T5_base_NASA_ADS_title_v5 | null | [
"transformers",
"tensorboard",
"safetensors",
"t5",
"text2text-generation",
"generated_from_trainer",
"base_model:t5-base",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-04-19T18:34:42+00:00 | [] | [] | TAGS
#transformers #tensorboard #safetensors #t5 #text2text-generation #generated_from_trainer #base_model-t5-base #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us
| T5\_base\_NASA\_ADS\_title\_v5
==============================
This model is a fine-tuned version of t5-base on the None dataset.
It achieves the following results on the evaluation set:
* Loss: 1.7910
* Rouge1: 0.4285
* Rouge2: 0.2147
* Rougel: 0.3712
* Rougelsum: 0.3711
* Gen Len: 16.3966
Model description
-----------------
More information needed
Intended uses & limitations
---------------------------
More information needed
Training and evaluation data
----------------------------
More information needed
Training procedure
------------------
### Training hyperparameters
The following hyperparameters were used during training:
* learning\_rate: 2e-05
* train\_batch\_size: 16
* eval\_batch\_size: 16
* seed: 42
* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
* lr\_scheduler\_type: linear
* num\_epochs: 15
* mixed\_precision\_training: Native AMP
### Training results
### Framework versions
* Transformers 4.40.0
* Pytorch 2.1.2
* Datasets 2.1.0
* Tokenizers 0.19.1
| [
"### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 2e-05\n* train\\_batch\\_size: 16\n* eval\\_batch\\_size: 16\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 15\n* mixed\\_precision\\_training: Native AMP",
"### Training results",
"### Framework versions\n\n\n* Transformers 4.40.0\n* Pytorch 2.1.2\n* Datasets 2.1.0\n* Tokenizers 0.19.1"
] | [
"TAGS\n#transformers #tensorboard #safetensors #t5 #text2text-generation #generated_from_trainer #base_model-t5-base #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n",
"### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 2e-05\n* train\\_batch\\_size: 16\n* eval\\_batch\\_size: 16\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 15\n* mixed\\_precision\\_training: Native AMP",
"### Training results",
"### Framework versions\n\n\n* Transformers 4.40.0\n* Pytorch 2.1.2\n* Datasets 2.1.0\n* Tokenizers 0.19.1"
] |
text-generation | transformers |
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] | {"library_name": "transformers", "tags": []} | Yasusan/Llama_221_111 | null | [
"transformers",
"safetensors",
"llama",
"text-generation",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-04-19T18:35:06+00:00 | [
"1910.09700"
] | [] | TAGS
#transformers #safetensors #llama #text-generation #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us
|
# Model Card for Model ID
## Model Details
### Model Description
This is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.
- Developed by:
- Funded by [optional]:
- Shared by [optional]:
- Model type:
- Language(s) (NLP):
- License:
- Finetuned from model [optional]:
### Model Sources [optional]
- Repository:
- Paper [optional]:
- Demo [optional]:
## Uses
### Direct Use
### Downstream Use [optional]
### Out-of-Scope Use
## Bias, Risks, and Limitations
### Recommendations
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
## Training Details
### Training Data
### Training Procedure
#### Preprocessing [optional]
#### Training Hyperparameters
- Training regime:
#### Speeds, Sizes, Times [optional]
## Evaluation
### Testing Data, Factors & Metrics
#### Testing Data
#### Factors
#### Metrics
### Results
#### Summary
## Model Examination [optional]
## Environmental Impact
Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).
- Hardware Type:
- Hours used:
- Cloud Provider:
- Compute Region:
- Carbon Emitted:
## Technical Specifications [optional]
### Model Architecture and Objective
### Compute Infrastructure
#### Hardware
#### Software
[optional]
BibTeX:
APA:
## Glossary [optional]
## More Information [optional]
## Model Card Authors [optional]
## Model Card Contact
| [
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.",
"## How to Get Started with the Model\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] | [
"TAGS\n#transformers #safetensors #llama #text-generation #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n",
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.",
"## How to Get Started with the Model\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] |
object-detection | transformers |
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] | {"library_name": "transformers", "tags": []} | sekhharr/detr_finetuned_v11_bestlast_checkpoint | null | [
"transformers",
"safetensors",
"detr",
"object-detection",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null | 2024-04-19T18:36:53+00:00 | [
"1910.09700"
] | [] | TAGS
#transformers #safetensors #detr #object-detection #arxiv-1910.09700 #endpoints_compatible #region-us
|
# Model Card for Model ID
## Model Details
### Model Description
This is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.
- Developed by:
- Funded by [optional]:
- Shared by [optional]:
- Model type:
- Language(s) (NLP):
- License:
- Finetuned from model [optional]:
### Model Sources [optional]
- Repository:
- Paper [optional]:
- Demo [optional]:
## Uses
### Direct Use
### Downstream Use [optional]
### Out-of-Scope Use
## Bias, Risks, and Limitations
### Recommendations
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
## Training Details
### Training Data
### Training Procedure
#### Preprocessing [optional]
#### Training Hyperparameters
- Training regime:
#### Speeds, Sizes, Times [optional]
## Evaluation
### Testing Data, Factors & Metrics
#### Testing Data
#### Factors
#### Metrics
### Results
#### Summary
## Model Examination [optional]
## Environmental Impact
Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).
- Hardware Type:
- Hours used:
- Cloud Provider:
- Compute Region:
- Carbon Emitted:
## Technical Specifications [optional]
### Model Architecture and Objective
### Compute Infrastructure
#### Hardware
#### Software
[optional]
BibTeX:
APA:
## Glossary [optional]
## More Information [optional]
## Model Card Authors [optional]
## Model Card Contact
| [
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.",
"## How to Get Started with the Model\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] | [
"TAGS\n#transformers #safetensors #detr #object-detection #arxiv-1910.09700 #endpoints_compatible #region-us \n",
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.",
"## How to Get Started with the Model\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] |
visual-question-answering | transformers |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# vilt_finetuned_200
This model is a fine-tuned version of [dandelin/vilt-b32-mlm](https://huggingface.co/dandelin/vilt-b32-mlm) on the vqa dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 1
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
### Training results
### Framework versions
- Transformers 4.39.3
- Pytorch 2.2.2+cu121
- Datasets 2.19.0
- Tokenizers 0.15.2
| {"license": "apache-2.0", "tags": ["generated_from_trainer"], "datasets": ["vqa"], "base_model": "dandelin/vilt-b32-mlm", "model-index": [{"name": "vilt_finetuned_200", "results": []}]} | kp-11/vilt_finetuned_200 | null | [
"transformers",
"tensorboard",
"safetensors",
"vilt",
"visual-question-answering",
"generated_from_trainer",
"dataset:vqa",
"base_model:dandelin/vilt-b32-mlm",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | 2024-04-19T18:41:22+00:00 | [] | [] | TAGS
#transformers #tensorboard #safetensors #vilt #visual-question-answering #generated_from_trainer #dataset-vqa #base_model-dandelin/vilt-b32-mlm #license-apache-2.0 #endpoints_compatible #region-us
|
# vilt_finetuned_200
This model is a fine-tuned version of dandelin/vilt-b32-mlm on the vqa dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 1
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
### Training results
### Framework versions
- Transformers 4.39.3
- Pytorch 2.2.2+cu121
- Datasets 2.19.0
- Tokenizers 0.15.2
| [
"# vilt_finetuned_200\n\nThis model is a fine-tuned version of dandelin/vilt-b32-mlm on the vqa dataset.",
"## Model description\n\nMore information needed",
"## Intended uses & limitations\n\nMore information needed",
"## Training and evaluation data\n\nMore information needed",
"## Training procedure",
"### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 5e-05\n- train_batch_size: 1\n- eval_batch_size: 8\n- seed: 42\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 2",
"### Training results",
"### Framework versions\n\n- Transformers 4.39.3\n- Pytorch 2.2.2+cu121\n- Datasets 2.19.0\n- Tokenizers 0.15.2"
] | [
"TAGS\n#transformers #tensorboard #safetensors #vilt #visual-question-answering #generated_from_trainer #dataset-vqa #base_model-dandelin/vilt-b32-mlm #license-apache-2.0 #endpoints_compatible #region-us \n",
"# vilt_finetuned_200\n\nThis model is a fine-tuned version of dandelin/vilt-b32-mlm on the vqa dataset.",
"## Model description\n\nMore information needed",
"## Intended uses & limitations\n\nMore information needed",
"## Training and evaluation data\n\nMore information needed",
"## Training procedure",
"### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 5e-05\n- train_batch_size: 1\n- eval_batch_size: 8\n- seed: 42\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 2",
"### Training results",
"### Framework versions\n\n- Transformers 4.39.3\n- Pytorch 2.2.2+cu121\n- Datasets 2.19.0\n- Tokenizers 0.15.2"
] |
text-generation | transformers | # MaziyarPanahi/Llama-3-16B-Instruct-v0.1 AWQ
- Model creator: [MaziyarPanahi](https://huggingface.co/MaziyarPanahi)
- Original model: [Llama-3-16B-Instruct-v0.1](https://huggingface.co/MaziyarPanahi/Llama-3-16B-Instruct-v0.1)
<img src="./llama-3-merges.webp" alt="Goku 8x22B v0.1 Logo" width="500" style="margin-left:'auto' margin-right:'auto' display:'block'"/>
## Model Summary
This model is a self-merge of `MaziyarPanahi/Llama-3-11B-Instruct-v0.1` model.
## Prompt template
```text
<|begin_of_text|><|start_header_id|>system<|end_header_id|>
You are a helpful assistant.<|eot_id|><|start_header_id|>user<|end_header_id|>
what's 25-4*2+3<|eot_id|><|start_header_id|>assistant<|end_header_id|>
To evaluate this expression, we need to follow the order of operations (PEMDAS):
1. First, multiply 4 and 2: 4*2 = 8
2. Then, subtract 8 from 25: 25 - 8 = 17
3. Finally, add 3: 17 + 3 = 20
So, 25-4*2+3 = 20!<|eot_id|>
To evaluate this expression, we need to follow the order of operations (PEMDAS):
1. First, multiply 4 and 2: 4*2 = 8
2. Then, subtract 8 from 25: 25 - 8 = 17
3. Finally, add 3: 17 + 3 = 20
So, 25-4*2+3 = 20!
```
| {"language": ["en"], "license": "other", "library_name": "transformers", "tags": ["4-bit", "AWQ", "text-generation", "autotrain_compatible", "endpoints_compatible - mergekit - merge - facebook - meta - pytorch - llama - llama-3"], "model_name": "Llama-3-16B-Instruct-v0.1", "base_model": "MaziyarPanahi/Llama-3-11B-Instruct-v0.1", "pipeline_tag": "text-generation", "license_name": "llama3", "license_link": "LICENSE", "inference": false, "model_creator": "MaziyarPanahi", "quantized_by": "Suparious"} | solidrust/Llama-3-16B-Instruct-v0.1-AWQ | null | [
"transformers",
"safetensors",
"llama",
"text-generation",
"4-bit",
"AWQ",
"autotrain_compatible",
"endpoints_compatible - mergekit - merge - facebook - meta - pytorch - llama - llama-3",
"conversational",
"en",
"base_model:MaziyarPanahi/Llama-3-11B-Instruct-v0.1",
"license:other",
"text-generation-inference",
"region:us"
] | null | 2024-04-19T18:41:35+00:00 | [] | [
"en"
] | TAGS
#transformers #safetensors #llama #text-generation #4-bit #AWQ #autotrain_compatible #endpoints_compatible - mergekit - merge - facebook - meta - pytorch - llama - llama-3 #conversational #en #base_model-MaziyarPanahi/Llama-3-11B-Instruct-v0.1 #license-other #text-generation-inference #region-us
| # MaziyarPanahi/Llama-3-16B-Instruct-v0.1 AWQ
- Model creator: MaziyarPanahi
- Original model: Llama-3-16B-Instruct-v0.1
<img src="./URL" alt="Goku 8x22B v0.1 Logo" width="500" style="margin-left:'auto' margin-right:'auto' display:'block'"/>
## Model Summary
This model is a self-merge of 'MaziyarPanahi/Llama-3-11B-Instruct-v0.1' model.
## Prompt template
| [
"# MaziyarPanahi/Llama-3-16B-Instruct-v0.1 AWQ\n\n- Model creator: MaziyarPanahi\n- Original model: Llama-3-16B-Instruct-v0.1\n\n<img src=\"./URL\" alt=\"Goku 8x22B v0.1 Logo\" width=\"500\" style=\"margin-left:'auto' margin-right:'auto' display:'block'\"/>",
"## Model Summary\n\nThis model is a self-merge of 'MaziyarPanahi/Llama-3-11B-Instruct-v0.1' model.",
"## Prompt template"
] | [
"TAGS\n#transformers #safetensors #llama #text-generation #4-bit #AWQ #autotrain_compatible #endpoints_compatible - mergekit - merge - facebook - meta - pytorch - llama - llama-3 #conversational #en #base_model-MaziyarPanahi/Llama-3-11B-Instruct-v0.1 #license-other #text-generation-inference #region-us \n",
"# MaziyarPanahi/Llama-3-16B-Instruct-v0.1 AWQ\n\n- Model creator: MaziyarPanahi\n- Original model: Llama-3-16B-Instruct-v0.1\n\n<img src=\"./URL\" alt=\"Goku 8x22B v0.1 Logo\" width=\"500\" style=\"margin-left:'auto' margin-right:'auto' display:'block'\"/>",
"## Model Summary\n\nThis model is a self-merge of 'MaziyarPanahi/Llama-3-11B-Instruct-v0.1' model.",
"## Prompt template"
] |
null | transformers |
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] | {"library_name": "transformers", "tags": []} | kshitij230/llama2-sentiment-analysis | null | [
"transformers",
"safetensors",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null | 2024-04-19T18:42:10+00:00 | [
"1910.09700"
] | [] | TAGS
#transformers #safetensors #arxiv-1910.09700 #endpoints_compatible #region-us
|
# Model Card for Model ID
## Model Details
### Model Description
This is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.
- Developed by:
- Funded by [optional]:
- Shared by [optional]:
- Model type:
- Language(s) (NLP):
- License:
- Finetuned from model [optional]:
### Model Sources [optional]
- Repository:
- Paper [optional]:
- Demo [optional]:
## Uses
### Direct Use
### Downstream Use [optional]
### Out-of-Scope Use
## Bias, Risks, and Limitations
### Recommendations
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
## Training Details
### Training Data
### Training Procedure
#### Preprocessing [optional]
#### Training Hyperparameters
- Training regime:
#### Speeds, Sizes, Times [optional]
## Evaluation
### Testing Data, Factors & Metrics
#### Testing Data
#### Factors
#### Metrics
### Results
#### Summary
## Model Examination [optional]
## Environmental Impact
Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).
- Hardware Type:
- Hours used:
- Cloud Provider:
- Compute Region:
- Carbon Emitted:
## Technical Specifications [optional]
### Model Architecture and Objective
### Compute Infrastructure
#### Hardware
#### Software
[optional]
BibTeX:
APA:
## Glossary [optional]
## More Information [optional]
## Model Card Authors [optional]
## Model Card Contact
| [
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.",
"## How to Get Started with the Model\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] | [
"TAGS\n#transformers #safetensors #arxiv-1910.09700 #endpoints_compatible #region-us \n",
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.",
"## How to Get Started with the Model\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] |
text-generation | transformers |
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] | {"library_name": "transformers", "tags": []} | Yasusan/Llama_221 | null | [
"transformers",
"safetensors",
"llama",
"text-generation",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-04-19T18:46:16+00:00 | [
"1910.09700"
] | [] | TAGS
#transformers #safetensors #llama #text-generation #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us
|
# Model Card for Model ID
## Model Details
### Model Description
This is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.
- Developed by:
- Funded by [optional]:
- Shared by [optional]:
- Model type:
- Language(s) (NLP):
- License:
- Finetuned from model [optional]:
### Model Sources [optional]
- Repository:
- Paper [optional]:
- Demo [optional]:
## Uses
### Direct Use
### Downstream Use [optional]
### Out-of-Scope Use
## Bias, Risks, and Limitations
### Recommendations
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
## Training Details
### Training Data
### Training Procedure
#### Preprocessing [optional]
#### Training Hyperparameters
- Training regime:
#### Speeds, Sizes, Times [optional]
## Evaluation
### Testing Data, Factors & Metrics
#### Testing Data
#### Factors
#### Metrics
### Results
#### Summary
## Model Examination [optional]
## Environmental Impact
Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).
- Hardware Type:
- Hours used:
- Cloud Provider:
- Compute Region:
- Carbon Emitted:
## Technical Specifications [optional]
### Model Architecture and Objective
### Compute Infrastructure
#### Hardware
#### Software
[optional]
BibTeX:
APA:
## Glossary [optional]
## More Information [optional]
## Model Card Authors [optional]
## Model Card Contact
| [
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.",
"## How to Get Started with the Model\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] | [
"TAGS\n#transformers #safetensors #llama #text-generation #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n",
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.",
"## How to Get Started with the Model\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] |
null | transformers | ## About
<!-- ### quantize_version: 1 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: -->
<!-- ### vocab_type: -->
static quants of https://huggingface.co/Vanessasml/cyber-risk-llama-3-8b
<!-- provided-files -->
weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion.
## Usage
If you are unsure how to use GGUF files, refer to one of [TheBloke's
READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
more details, including on how to concatenate multi-part files.
## Provided Quants
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
| Link | Type | Size/GB | Notes |
|:-----|:-----|--------:|:------|
| [GGUF](https://huggingface.co/mradermacher/cyber-risk-llama-3-8b-GGUF/resolve/main/cyber-risk-llama-3-8b.Q2_K.gguf) | Q2_K | 3.3 | |
| [GGUF](https://huggingface.co/mradermacher/cyber-risk-llama-3-8b-GGUF/resolve/main/cyber-risk-llama-3-8b.IQ3_XS.gguf) | IQ3_XS | 3.6 | |
| [GGUF](https://huggingface.co/mradermacher/cyber-risk-llama-3-8b-GGUF/resolve/main/cyber-risk-llama-3-8b.Q3_K_S.gguf) | Q3_K_S | 3.8 | |
| [GGUF](https://huggingface.co/mradermacher/cyber-risk-llama-3-8b-GGUF/resolve/main/cyber-risk-llama-3-8b.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/cyber-risk-llama-3-8b-GGUF/resolve/main/cyber-risk-llama-3-8b.IQ3_M.gguf) | IQ3_M | 3.9 | |
| [GGUF](https://huggingface.co/mradermacher/cyber-risk-llama-3-8b-GGUF/resolve/main/cyber-risk-llama-3-8b.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/cyber-risk-llama-3-8b-GGUF/resolve/main/cyber-risk-llama-3-8b.Q3_K_L.gguf) | Q3_K_L | 4.4 | |
| [GGUF](https://huggingface.co/mradermacher/cyber-risk-llama-3-8b-GGUF/resolve/main/cyber-risk-llama-3-8b.IQ4_XS.gguf) | IQ4_XS | 4.6 | |
| [GGUF](https://huggingface.co/mradermacher/cyber-risk-llama-3-8b-GGUF/resolve/main/cyber-risk-llama-3-8b.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/cyber-risk-llama-3-8b-GGUF/resolve/main/cyber-risk-llama-3-8b.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/cyber-risk-llama-3-8b-GGUF/resolve/main/cyber-risk-llama-3-8b.Q5_K_S.gguf) | Q5_K_S | 5.7 | |
| [GGUF](https://huggingface.co/mradermacher/cyber-risk-llama-3-8b-GGUF/resolve/main/cyber-risk-llama-3-8b.Q5_K_M.gguf) | Q5_K_M | 5.8 | |
| [GGUF](https://huggingface.co/mradermacher/cyber-risk-llama-3-8b-GGUF/resolve/main/cyber-risk-llama-3-8b.Q6_K.gguf) | Q6_K | 6.7 | very good quality |
| [GGUF](https://huggingface.co/mradermacher/cyber-risk-llama-3-8b-GGUF/resolve/main/cyber-risk-llama-3-8b.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality |
Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):
And here are Artefact2's thoughts on the matter:
https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
## FAQ / Model Request
See https://huggingface.co/mradermacher/model_requests for some answers to
questions you might have and/or if you want some other model quantized.
## Thanks
I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
me use its servers and providing upgrades to my workstation to enable
this work in my free time.
<!-- end -->
| {"language": ["en"], "library_name": "transformers", "tags": ["finance", "supervision", "cyber risk", "cybersecurity", "cyber threats", "SFT", "LoRA", "A100GPU"], "datasets": ["Vanessasml/cybersecurity_32k_instruction_input_output"], "base_model": "Vanessasml/cyber-risk-llama-3-8b", "quantized_by": "mradermacher"} | mradermacher/cyber-risk-llama-3-8b-GGUF | null | [
"transformers",
"gguf",
"finance",
"supervision",
"cyber risk",
"cybersecurity",
"cyber threats",
"SFT",
"LoRA",
"A100GPU",
"en",
"dataset:Vanessasml/cybersecurity_32k_instruction_input_output",
"base_model:Vanessasml/cyber-risk-llama-3-8b",
"endpoints_compatible",
"region:us"
] | null | 2024-04-19T18:47:31+00:00 | [] | [
"en"
] | TAGS
#transformers #gguf #finance #supervision #cyber risk #cybersecurity #cyber threats #SFT #LoRA #A100GPU #en #dataset-Vanessasml/cybersecurity_32k_instruction_input_output #base_model-Vanessasml/cyber-risk-llama-3-8b #endpoints_compatible #region-us
| About
-----
static quants of URL
weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion.
Usage
-----
If you are unsure how to use GGUF files, refer to one of TheBloke's
READMEs for
more details, including on how to concatenate multi-part files.
Provided Quants
---------------
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):
!URL
And here are Artefact2's thoughts on the matter:
URL
FAQ / Model Request
-------------------
See URL for some answers to
questions you might have and/or if you want some other model quantized.
Thanks
------
I thank my company, nethype GmbH, for letting
me use its servers and providing upgrades to my workstation to enable
this work in my free time.
| [] | [
"TAGS\n#transformers #gguf #finance #supervision #cyber risk #cybersecurity #cyber threats #SFT #LoRA #A100GPU #en #dataset-Vanessasml/cybersecurity_32k_instruction_input_output #base_model-Vanessasml/cyber-risk-llama-3-8b #endpoints_compatible #region-us \n"
] |
null | transformers |
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] | {"library_name": "transformers", "tags": []} | nuebaek/komt_mistral_mss_user_111_max_steps_100 | null | [
"transformers",
"safetensors",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null | 2024-04-19T18:48:59+00:00 | [
"1910.09700"
] | [] | TAGS
#transformers #safetensors #arxiv-1910.09700 #endpoints_compatible #region-us
|
# Model Card for Model ID
## Model Details
### Model Description
This is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.
- Developed by:
- Funded by [optional]:
- Shared by [optional]:
- Model type:
- Language(s) (NLP):
- License:
- Finetuned from model [optional]:
### Model Sources [optional]
- Repository:
- Paper [optional]:
- Demo [optional]:
## Uses
### Direct Use
### Downstream Use [optional]
### Out-of-Scope Use
## Bias, Risks, and Limitations
### Recommendations
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
## Training Details
### Training Data
### Training Procedure
#### Preprocessing [optional]
#### Training Hyperparameters
- Training regime:
#### Speeds, Sizes, Times [optional]
## Evaluation
### Testing Data, Factors & Metrics
#### Testing Data
#### Factors
#### Metrics
### Results
#### Summary
## Model Examination [optional]
## Environmental Impact
Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).
- Hardware Type:
- Hours used:
- Cloud Provider:
- Compute Region:
- Carbon Emitted:
## Technical Specifications [optional]
### Model Architecture and Objective
### Compute Infrastructure
#### Hardware
#### Software
[optional]
BibTeX:
APA:
## Glossary [optional]
## More Information [optional]
## Model Card Authors [optional]
## Model Card Contact
| [
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.",
"## How to Get Started with the Model\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] | [
"TAGS\n#transformers #safetensors #arxiv-1910.09700 #endpoints_compatible #region-us \n",
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.",
"## How to Get Started with the Model\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.