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 |
# Uploaded model
- **Developed by:** Dogge
- **License:** apache-2.0
- **Finetuned from model :** unsloth/llama-3-70b-Instruct-bnb-4bit
This llama 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", "llama", "trl", "sft"], "base_model": "unsloth/llama-3-70b-Instruct-bnb-4bit"} | Dogge/llama-3-70B-instruct-uncensored-4bit | null | [
"transformers",
"safetensors",
"llama",
"text-generation",
"text-generation-inference",
"unsloth",
"trl",
"sft",
"conversational",
"en",
"base_model:unsloth/llama-3-70b-Instruct-bnb-4bit",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"4-bit",
"region:us"
] | null | 2024-04-19T23:30:32+00:00 | [] | [
"en"
] | TAGS
#transformers #safetensors #llama #text-generation #text-generation-inference #unsloth #trl #sft #conversational #en #base_model-unsloth/llama-3-70b-Instruct-bnb-4bit #license-apache-2.0 #autotrain_compatible #endpoints_compatible #4-bit #region-us
|
# Uploaded model
- Developed by: Dogge
- License: apache-2.0
- Finetuned from model : unsloth/llama-3-70b-Instruct-bnb-4bit
This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.
<img src="URL width="200"/>
| [
"# Uploaded model\n\n- Developed by: Dogge\n- License: apache-2.0\n- Finetuned from model : unsloth/llama-3-70b-Instruct-bnb-4bit\n\nThis llama model was trained 2x faster with Unsloth and Huggingface's TRL library.\n\n<img src=\"URL width=\"200\"/>"
] | [
"TAGS\n#transformers #safetensors #llama #text-generation #text-generation-inference #unsloth #trl #sft #conversational #en #base_model-unsloth/llama-3-70b-Instruct-bnb-4bit #license-apache-2.0 #autotrain_compatible #endpoints_compatible #4-bit #region-us \n",
"# Uploaded model\n\n- Developed by: Dogge\n- License: apache-2.0\n- Finetuned from model : unsloth/llama-3-70b-Instruct-bnb-4bit\n\nThis llama model was trained 2x faster with Unsloth and Huggingface's TRL library.\n\n<img src=\"URL width=\"200\"/>"
] |
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. -->
# mi-super-modelo
This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 1.5790
- Accuracy: 0.325
## 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
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 1
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 1.6433 | 0.5 | 5 | 1.5903 | 0.35 |
| 1.6941 | 1.0 | 10 | 1.5790 | 0.325 |
### 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"], "metrics": ["accuracy"], "base_model": "bert-base-cased", "model-index": [{"name": "mi-super-modelo", "results": []}]} | gallark/mi-super-modelo | null | [
"transformers",
"tensorboard",
"safetensors",
"bert",
"text-classification",
"generated_from_trainer",
"base_model:bert-base-cased",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | null | 2024-04-19T23:30:42+00:00 | [] | [] | TAGS
#transformers #tensorboard #safetensors #bert #text-classification #generated_from_trainer #base_model-bert-base-cased #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us
| mi-super-modelo
===============
This model is a fine-tuned version of bert-base-cased on an unknown dataset.
It achieves the following results on the evaluation set:
* Loss: 1.5790
* Accuracy: 0.325
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
* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
* lr\_scheduler\_type: linear
* num\_epochs: 1
### 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: 5e-05\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* num\\_epochs: 1",
"### 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 #bert #text-classification #generated_from_trainer #base_model-bert-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: 5e-05\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* num\\_epochs: 1",
"### 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 | transformers | ## About
<!-- ### quantize_version: 1 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: -->
<!-- ### vocab_type: -->
static quants of https://huggingface.co/NotAiLOL/Boundary-Solar-Chat-2x10.7B-MoE
<!-- 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/Boundary-Solar-Chat-2x10.7B-MoE-GGUF/resolve/main/Boundary-Solar-Chat-2x10.7B-MoE.Q2_K.gguf) | Q2_K | 7.2 | |
| [GGUF](https://huggingface.co/mradermacher/Boundary-Solar-Chat-2x10.7B-MoE-GGUF/resolve/main/Boundary-Solar-Chat-2x10.7B-MoE.IQ3_XS.gguf) | IQ3_XS | 8.0 | |
| [GGUF](https://huggingface.co/mradermacher/Boundary-Solar-Chat-2x10.7B-MoE-GGUF/resolve/main/Boundary-Solar-Chat-2x10.7B-MoE.Q3_K_S.gguf) | Q3_K_S | 8.4 | |
| [GGUF](https://huggingface.co/mradermacher/Boundary-Solar-Chat-2x10.7B-MoE-GGUF/resolve/main/Boundary-Solar-Chat-2x10.7B-MoE.IQ3_S.gguf) | IQ3_S | 8.4 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/Boundary-Solar-Chat-2x10.7B-MoE-GGUF/resolve/main/Boundary-Solar-Chat-2x10.7B-MoE.IQ3_M.gguf) | IQ3_M | 8.6 | |
| [GGUF](https://huggingface.co/mradermacher/Boundary-Solar-Chat-2x10.7B-MoE-GGUF/resolve/main/Boundary-Solar-Chat-2x10.7B-MoE.Q3_K_M.gguf) | Q3_K_M | 9.3 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/Boundary-Solar-Chat-2x10.7B-MoE-GGUF/resolve/main/Boundary-Solar-Chat-2x10.7B-MoE.Q3_K_L.gguf) | Q3_K_L | 10.1 | |
| [GGUF](https://huggingface.co/mradermacher/Boundary-Solar-Chat-2x10.7B-MoE-GGUF/resolve/main/Boundary-Solar-Chat-2x10.7B-MoE.IQ4_XS.gguf) | IQ4_XS | 10.5 | |
| [GGUF](https://huggingface.co/mradermacher/Boundary-Solar-Chat-2x10.7B-MoE-GGUF/resolve/main/Boundary-Solar-Chat-2x10.7B-MoE.Q4_K_S.gguf) | Q4_K_S | 11.0 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Boundary-Solar-Chat-2x10.7B-MoE-GGUF/resolve/main/Boundary-Solar-Chat-2x10.7B-MoE.Q4_K_M.gguf) | Q4_K_M | 11.7 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Boundary-Solar-Chat-2x10.7B-MoE-GGUF/resolve/main/Boundary-Solar-Chat-2x10.7B-MoE.Q5_K_S.gguf) | Q5_K_S | 13.3 | |
| [GGUF](https://huggingface.co/mradermacher/Boundary-Solar-Chat-2x10.7B-MoE-GGUF/resolve/main/Boundary-Solar-Chat-2x10.7B-MoE.Q5_K_M.gguf) | Q5_K_M | 13.7 | |
| [GGUF](https://huggingface.co/mradermacher/Boundary-Solar-Chat-2x10.7B-MoE-GGUF/resolve/main/Boundary-Solar-Chat-2x10.7B-MoE.Q6_K.gguf) | Q6_K | 15.8 | very good quality |
| [GGUF](https://huggingface.co/mradermacher/Boundary-Solar-Chat-2x10.7B-MoE-GGUF/resolve/main/Boundary-Solar-Chat-2x10.7B-MoE.Q8_0.gguf) | Q8_0 | 20.5 | 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": ["moe", "merge", "mergekit", "NousResearch/Nous-Hermes-2-SOLAR-10.7B", "upstage/SOLAR-10.7B-Instruct-v1.0", "llama", "Llama"], "base_model": "NotAiLOL/Boundary-Solar-Chat-2x10.7B-MoE", "quantized_by": "mradermacher"} | mradermacher/Boundary-Solar-Chat-2x10.7B-MoE-GGUF | null | [
"transformers",
"gguf",
"moe",
"merge",
"mergekit",
"NousResearch/Nous-Hermes-2-SOLAR-10.7B",
"upstage/SOLAR-10.7B-Instruct-v1.0",
"llama",
"Llama",
"en",
"base_model:NotAiLOL/Boundary-Solar-Chat-2x10.7B-MoE",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | 2024-04-19T23:30:43+00:00 | [] | [
"en"
] | TAGS
#transformers #gguf #moe #merge #mergekit #NousResearch/Nous-Hermes-2-SOLAR-10.7B #upstage/SOLAR-10.7B-Instruct-v1.0 #llama #Llama #en #base_model-NotAiLOL/Boundary-Solar-Chat-2x10.7B-MoE #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 #moe #merge #mergekit #NousResearch/Nous-Hermes-2-SOLAR-10.7B #upstage/SOLAR-10.7B-Instruct-v1.0 #llama #Llama #en #base_model-NotAiLOL/Boundary-Solar-Chat-2x10.7B-MoE #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": []} | OwOOwO/dumbo-stable1 | null | [
"transformers",
"safetensors",
"stablelm",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | null | 2024-04-19T23:31:29+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"
] |
null | peft | ## Training procedure
The following `bitsandbytes` quantization config was used during training:
- quant_method: QuantizationMethod.BITS_AND_BYTES
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: True
- bnb_4bit_compute_dtype: bfloat16
The following `bitsandbytes` quantization config was used during training:
- quant_method: QuantizationMethod.BITS_AND_BYTES
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: True
- bnb_4bit_compute_dtype: bfloat16
### Framework versions
- PEFT 0.5.0
- PEFT 0.5.0
| {"library_name": "peft"} | SALT-NLP/CultureBank-Extractor | null | [
"peft",
"region:us"
] | null | 2024-04-19T23:32:55+00:00 | [] | [] | TAGS
#peft #region-us
| ## Training procedure
The following 'bitsandbytes' quantization config was used during training:
- quant_method: QuantizationMethod.BITS_AND_BYTES
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: True
- bnb_4bit_compute_dtype: bfloat16
The following 'bitsandbytes' quantization config was used during training:
- quant_method: QuantizationMethod.BITS_AND_BYTES
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: True
- bnb_4bit_compute_dtype: bfloat16
### Framework versions
- PEFT 0.5.0
- PEFT 0.5.0
| [
"## Training procedure\n\n\nThe following 'bitsandbytes' quantization config was used during training:\n- quant_method: QuantizationMethod.BITS_AND_BYTES\n- load_in_8bit: False\n- load_in_4bit: True\n- llm_int8_threshold: 6.0\n- llm_int8_skip_modules: None\n- llm_int8_enable_fp32_cpu_offload: False\n- llm_int8_has_fp16_weight: False\n- bnb_4bit_quant_type: nf4\n- bnb_4bit_use_double_quant: True\n- bnb_4bit_compute_dtype: bfloat16\n\nThe following 'bitsandbytes' quantization config was used during training:\n- quant_method: QuantizationMethod.BITS_AND_BYTES\n- load_in_8bit: False\n- load_in_4bit: True\n- llm_int8_threshold: 6.0\n- llm_int8_skip_modules: None\n- llm_int8_enable_fp32_cpu_offload: False\n- llm_int8_has_fp16_weight: False\n- bnb_4bit_quant_type: nf4\n- bnb_4bit_use_double_quant: True\n- bnb_4bit_compute_dtype: bfloat16",
"### Framework versions\n\n- PEFT 0.5.0\n\n- PEFT 0.5.0"
] | [
"TAGS\n#peft #region-us \n",
"## Training procedure\n\n\nThe following 'bitsandbytes' quantization config was used during training:\n- quant_method: QuantizationMethod.BITS_AND_BYTES\n- load_in_8bit: False\n- load_in_4bit: True\n- llm_int8_threshold: 6.0\n- llm_int8_skip_modules: None\n- llm_int8_enable_fp32_cpu_offload: False\n- llm_int8_has_fp16_weight: False\n- bnb_4bit_quant_type: nf4\n- bnb_4bit_use_double_quant: True\n- bnb_4bit_compute_dtype: bfloat16\n\nThe following 'bitsandbytes' quantization config was used during training:\n- quant_method: QuantizationMethod.BITS_AND_BYTES\n- load_in_8bit: False\n- load_in_4bit: True\n- llm_int8_threshold: 6.0\n- llm_int8_skip_modules: None\n- llm_int8_enable_fp32_cpu_offload: False\n- llm_int8_has_fp16_weight: False\n- bnb_4bit_quant_type: nf4\n- bnb_4bit_use_double_quant: True\n- bnb_4bit_compute_dtype: bfloat16",
"### Framework versions\n\n- PEFT 0.5.0\n\n- PEFT 0.5.0"
] |
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-Mix_harmless_gpt3_20000_gemma2b_shuffleFalse_extractchosenFalse
This model is a fine-tuned version of [google/gemma-2b](https://huggingface.co/google/gemma-2b) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0445
- Accuracy: 0.9815
## 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 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 0.8191 | 0.06 | 250 | 0.5824 | 0.695 |
| 0.6294 | 0.11 | 500 | 0.1346 | 0.953 |
| 0.5811 | 0.17 | 750 | 0.0888 | 0.9705 |
| 0.5753 | 0.22 | 1000 | 0.0684 | 0.975 |
| 0.5539 | 0.28 | 1250 | 0.0588 | 0.979 |
| 0.5764 | 0.33 | 1500 | 0.0595 | 0.9785 |
| 0.5261 | 0.39 | 1750 | 0.0558 | 0.979 |
| 0.5423 | 0.44 | 2000 | 0.0533 | 0.9795 |
| 0.5261 | 0.5 | 2250 | 0.0501 | 0.98 |
| 0.5363 | 0.56 | 2500 | 0.0485 | 0.98 |
| 0.5051 | 0.61 | 2750 | 0.0472 | 0.981 |
| 0.5157 | 0.67 | 3000 | 0.0509 | 0.9795 |
| 0.5368 | 0.72 | 3250 | 0.0507 | 0.9785 |
| 0.5281 | 0.78 | 3500 | 0.0467 | 0.981 |
| 0.5005 | 0.83 | 3750 | 0.0450 | 0.9815 |
| 0.5239 | 0.89 | 4000 | 0.0445 | 0.9815 |
| 0.5111 | 0.94 | 4250 | 0.0445 | 0.9815 |
### 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-Mix_harmless_gpt3_20000_gemma2b_shuffleFalse_extractchosenFalse", "results": []}]} | Holarissun/RM-HH-Mix_harmless_gpt3_20000_gemma2b_shuffleFalse_extractchosenFalse | null | [
"peft",
"safetensors",
"trl",
"reward-trainer",
"generated_from_trainer",
"base_model:google/gemma-2b",
"license:gemma",
"region:us"
] | null | 2024-04-19T23:33:59+00:00 | [] | [] | TAGS
#peft #safetensors #trl #reward-trainer #generated_from_trainer #base_model-google/gemma-2b #license-gemma #region-us
| RM-HH-Mix\_harmless\_gpt3\_20000\_gemma2b\_shuffleFalse\_extractchosenFalse
===========================================================================
This model is a fine-tuned version of google/gemma-2b on the None dataset.
It achieves the following results on the evaluation set:
* Loss: 0.0445
* Accuracy: 0.9815
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 | adapter-transformers |
# Adapter `BigTMiami/seq_bn_micro_helpfulness_classifier_no_pretrain_4_adapter` for roberta-base
An [adapter](https://adapterhub.ml) for the `roberta-base` model that was trained on the [BigTMiami/amazon_MICRO_helpfulness_dataset](https://huggingface.co/datasets/BigTMiami/amazon_MICRO_helpfulness_dataset/) dataset and includes a prediction head for classification.
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/seq_bn_micro_helpfulness_classifier_no_pretrain_4_adapter", source="hf", set_active=True)
```
## Architecture & Training
<!-- Add some description here -->
## Evaluation results
<!-- Add some description here -->
## Citation
<!-- Add some description here --> | {"tags": ["roberta", "adapter-transformers"], "datasets": ["BigTMiami/amazon_MICRO_helpfulness_dataset"]} | BigTMiami/seq_bn_micro_helpfulness_classifier_no_pretrain_4_adapter | null | [
"adapter-transformers",
"roberta",
"dataset:BigTMiami/amazon_MICRO_helpfulness_dataset",
"region:us"
] | null | 2024-04-19T23:36:15+00:00 | [] | [] | TAGS
#adapter-transformers #roberta #dataset-BigTMiami/amazon_MICRO_helpfulness_dataset #region-us
|
# Adapter 'BigTMiami/seq_bn_micro_helpfulness_classifier_no_pretrain_4_adapter' for roberta-base
An adapter for the 'roberta-base' model that was trained on the BigTMiami/amazon_MICRO_helpfulness_dataset dataset and includes a prediction head for classification.
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/seq_bn_micro_helpfulness_classifier_no_pretrain_4_adapter' for roberta-base\n\nAn adapter for the 'roberta-base' model that was trained on the BigTMiami/amazon_MICRO_helpfulness_dataset dataset and includes a prediction head for classification.\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 #region-us \n",
"# Adapter 'BigTMiami/seq_bn_micro_helpfulness_classifier_no_pretrain_4_adapter' for roberta-base\n\nAn adapter for the 'roberta-base' model that was trained on the BigTMiami/amazon_MICRO_helpfulness_dataset dataset and includes a prediction head for classification.\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 | peft | ## Training procedure
The following `bitsandbytes` quantization config was used during training:
- quant_method: QuantizationMethod.BITS_AND_BYTES
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: True
- bnb_4bit_compute_dtype: bfloat16
The following `bitsandbytes` quantization config was used during training:
- quant_method: QuantizationMethod.BITS_AND_BYTES
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: True
- bnb_4bit_compute_dtype: bfloat16
### Framework versions
- PEFT 0.5.0
- PEFT 0.5.0
| {"library_name": "peft"} | SALT-NLP/CultureBank-Question-Generator | null | [
"peft",
"region:us"
] | null | 2024-04-19T23:39:00+00:00 | [] | [] | TAGS
#peft #region-us
| ## Training procedure
The following 'bitsandbytes' quantization config was used during training:
- quant_method: QuantizationMethod.BITS_AND_BYTES
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: True
- bnb_4bit_compute_dtype: bfloat16
The following 'bitsandbytes' quantization config was used during training:
- quant_method: QuantizationMethod.BITS_AND_BYTES
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: True
- bnb_4bit_compute_dtype: bfloat16
### Framework versions
- PEFT 0.5.0
- PEFT 0.5.0
| [
"## Training procedure\n\n\nThe following 'bitsandbytes' quantization config was used during training:\n- quant_method: QuantizationMethod.BITS_AND_BYTES\n- load_in_8bit: False\n- load_in_4bit: True\n- llm_int8_threshold: 6.0\n- llm_int8_skip_modules: None\n- llm_int8_enable_fp32_cpu_offload: False\n- llm_int8_has_fp16_weight: False\n- bnb_4bit_quant_type: nf4\n- bnb_4bit_use_double_quant: True\n- bnb_4bit_compute_dtype: bfloat16\n\nThe following 'bitsandbytes' quantization config was used during training:\n- quant_method: QuantizationMethod.BITS_AND_BYTES\n- load_in_8bit: False\n- load_in_4bit: True\n- llm_int8_threshold: 6.0\n- llm_int8_skip_modules: None\n- llm_int8_enable_fp32_cpu_offload: False\n- llm_int8_has_fp16_weight: False\n- bnb_4bit_quant_type: nf4\n- bnb_4bit_use_double_quant: True\n- bnb_4bit_compute_dtype: bfloat16",
"### Framework versions\n\n- PEFT 0.5.0\n\n- PEFT 0.5.0"
] | [
"TAGS\n#peft #region-us \n",
"## Training procedure\n\n\nThe following 'bitsandbytes' quantization config was used during training:\n- quant_method: QuantizationMethod.BITS_AND_BYTES\n- load_in_8bit: False\n- load_in_4bit: True\n- llm_int8_threshold: 6.0\n- llm_int8_skip_modules: None\n- llm_int8_enable_fp32_cpu_offload: False\n- llm_int8_has_fp16_weight: False\n- bnb_4bit_quant_type: nf4\n- bnb_4bit_use_double_quant: True\n- bnb_4bit_compute_dtype: bfloat16\n\nThe following 'bitsandbytes' quantization config was used during training:\n- quant_method: QuantizationMethod.BITS_AND_BYTES\n- load_in_8bit: False\n- load_in_4bit: True\n- llm_int8_threshold: 6.0\n- llm_int8_skip_modules: None\n- llm_int8_enable_fp32_cpu_offload: False\n- llm_int8_has_fp16_weight: False\n- bnb_4bit_quant_type: nf4\n- bnb_4bit_use_double_quant: True\n- bnb_4bit_compute_dtype: bfloat16",
"### Framework versions\n\n- PEFT 0.5.0\n\n- PEFT 0.5.0"
] |
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": []} | santoshsto/mistral-7b-python-FINETUNED-16bit | null | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-04-19T23:40:28+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"
] |
null | peft | ## Training procedure
The following `bitsandbytes` quantization config was used during training:
- quant_method: QuantizationMethod.BITS_AND_BYTES
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: True
- bnb_4bit_compute_dtype: float16
### Framework versions
- PEFT 0.5.0
| {"library_name": "peft"} | SALT-NLP/CultureBank-Mixtral-DPO | null | [
"peft",
"region:us"
] | null | 2024-04-19T23:41:21+00:00 | [] | [] | TAGS
#peft #region-us
| ## Training procedure
The following 'bitsandbytes' quantization config was used during training:
- quant_method: QuantizationMethod.BITS_AND_BYTES
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: True
- bnb_4bit_compute_dtype: float16
### Framework versions
- PEFT 0.5.0
| [
"## Training procedure\n\n\nThe following 'bitsandbytes' quantization config was used during training:\n- quant_method: QuantizationMethod.BITS_AND_BYTES\n- load_in_8bit: False\n- load_in_4bit: True\n- llm_int8_threshold: 6.0\n- llm_int8_skip_modules: None\n- llm_int8_enable_fp32_cpu_offload: False\n- llm_int8_has_fp16_weight: False\n- bnb_4bit_quant_type: nf4\n- bnb_4bit_use_double_quant: True\n- bnb_4bit_compute_dtype: float16",
"### Framework versions\n\n\n- PEFT 0.5.0"
] | [
"TAGS\n#peft #region-us \n",
"## Training procedure\n\n\nThe following 'bitsandbytes' quantization config was used during training:\n- quant_method: QuantizationMethod.BITS_AND_BYTES\n- load_in_8bit: False\n- load_in_4bit: True\n- llm_int8_threshold: 6.0\n- llm_int8_skip_modules: None\n- llm_int8_enable_fp32_cpu_offload: False\n- llm_int8_has_fp16_weight: False\n- bnb_4bit_quant_type: nf4\n- bnb_4bit_use_double_quant: True\n- bnb_4bit_compute_dtype: float16",
"### Framework versions\n\n\n- PEFT 0.5.0"
] |
text-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. -->
# 0.0_ablation_declr_6iters_iter_2
This model is a fine-tuned version of [ZhangShenao/0.0_ablation_declr_6iters_iter_1](https://huggingface.co/ZhangShenao/0.0_ablation_declr_6iters_iter_1) on the ZhangShenao/0.0_ablation_declr_6iters_dataset 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-06
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- gradient_accumulation_steps: 2
- total_train_batch_size: 128
- total_eval_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 1
### Training results
### Framework versions
- Transformers 4.36.2
- Pytorch 2.1.2+cu121
- Datasets 2.14.6
- Tokenizers 0.15.2
| {"license": "mit", "tags": ["alignment-handbook", "generated_from_trainer", "trl", "dpo", "generated_from_trainer"], "datasets": ["ZhangShenao/0.0_ablation_declr_6iters_dataset"], "base_model": "ZhangShenao/0.0_ablation_declr_6iters_iter_1", "model-index": [{"name": "0.0_ablation_declr_6iters_iter_2", "results": []}]} | ZhangShenao/0.0_ablation_declr_6iters_iter_2 | null | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"alignment-handbook",
"generated_from_trainer",
"trl",
"dpo",
"conversational",
"dataset:ZhangShenao/0.0_ablation_declr_6iters_dataset",
"base_model:ZhangShenao/0.0_ablation_declr_6iters_iter_1",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-04-19T23:41:34+00:00 | [] | [] | TAGS
#transformers #safetensors #mistral #text-generation #alignment-handbook #generated_from_trainer #trl #dpo #conversational #dataset-ZhangShenao/0.0_ablation_declr_6iters_dataset #base_model-ZhangShenao/0.0_ablation_declr_6iters_iter_1 #license-mit #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us
|
# 0.0_ablation_declr_6iters_iter_2
This model is a fine-tuned version of ZhangShenao/0.0_ablation_declr_6iters_iter_1 on the ZhangShenao/0.0_ablation_declr_6iters_dataset 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-06
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- gradient_accumulation_steps: 2
- total_train_batch_size: 128
- total_eval_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 1
### Training results
### Framework versions
- Transformers 4.36.2
- Pytorch 2.1.2+cu121
- Datasets 2.14.6
- Tokenizers 0.15.2
| [
"# 0.0_ablation_declr_6iters_iter_2\n\nThis model is a fine-tuned version of ZhangShenao/0.0_ablation_declr_6iters_iter_1 on the ZhangShenao/0.0_ablation_declr_6iters_dataset 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-06\n- train_batch_size: 8\n- eval_batch_size: 8\n- seed: 42\n- distributed_type: multi-GPU\n- num_devices: 8\n- gradient_accumulation_steps: 2\n- total_train_batch_size: 128\n- total_eval_batch_size: 64\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: cosine\n- lr_scheduler_warmup_ratio: 0.1\n- num_epochs: 1",
"### Training results",
"### Framework versions\n\n- Transformers 4.36.2\n- Pytorch 2.1.2+cu121\n- Datasets 2.14.6\n- Tokenizers 0.15.2"
] | [
"TAGS\n#transformers #safetensors #mistral #text-generation #alignment-handbook #generated_from_trainer #trl #dpo #conversational #dataset-ZhangShenao/0.0_ablation_declr_6iters_dataset #base_model-ZhangShenao/0.0_ablation_declr_6iters_iter_1 #license-mit #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n",
"# 0.0_ablation_declr_6iters_iter_2\n\nThis model is a fine-tuned version of ZhangShenao/0.0_ablation_declr_6iters_iter_1 on the ZhangShenao/0.0_ablation_declr_6iters_dataset 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-06\n- train_batch_size: 8\n- eval_batch_size: 8\n- seed: 42\n- distributed_type: multi-GPU\n- num_devices: 8\n- gradient_accumulation_steps: 2\n- total_train_batch_size: 128\n- total_eval_batch_size: 64\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: cosine\n- lr_scheduler_warmup_ratio: 0.1\n- num_epochs: 1",
"### Training results",
"### Framework versions\n\n- Transformers 4.36.2\n- Pytorch 2.1.2+cu121\n- Datasets 2.14.6\n- Tokenizers 0.15.2"
] |
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": []} | MesozoicMetallurgist/llam-Proterozoic | null | [
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-04-19T23:42:16+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"
] |
null | transformers |
# Uploaded model
- **Developed by:** TachyHealth_Research
- **License:** apache-2.0
- **Finetuned from model :** unsloth/llama-3-8b-bnb-4bit
This llama 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", "llama", "trl", "medical"], "datasets": ["medalpaca/medical_meadow_mediqa"], "base_model": "unsloth/llama-3-8b-bnb-4bit"} | TachyHealth/Gazal_8b_llama_3_Med_finetuned | null | [
"transformers",
"safetensors",
"text-generation-inference",
"unsloth",
"llama",
"trl",
"medical",
"en",
"dataset:medalpaca/medical_meadow_mediqa",
"base_model:unsloth/llama-3-8b-bnb-4bit",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | 2024-04-19T23:42:36+00:00 | [] | [
"en"
] | TAGS
#transformers #safetensors #text-generation-inference #unsloth #llama #trl #medical #en #dataset-medalpaca/medical_meadow_mediqa #base_model-unsloth/llama-3-8b-bnb-4bit #license-apache-2.0 #endpoints_compatible #region-us
|
# Uploaded model
- Developed by: TachyHealth_Research
- License: apache-2.0
- Finetuned from model : unsloth/llama-3-8b-bnb-4bit
This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.
<img src="URL width="200"/> | [
"# Uploaded model\n\n- Developed by: TachyHealth_Research\n- License: apache-2.0\n- Finetuned from model : unsloth/llama-3-8b-bnb-4bit\n\nThis llama 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 #llama #trl #medical #en #dataset-medalpaca/medical_meadow_mediqa #base_model-unsloth/llama-3-8b-bnb-4bit #license-apache-2.0 #endpoints_compatible #region-us \n",
"# Uploaded model\n\n- Developed by: TachyHealth_Research\n- License: apache-2.0\n- Finetuned from model : unsloth/llama-3-8b-bnb-4bit\n\nThis llama model was trained 2x faster with Unsloth and Huggingface's TRL library.\n\n<img src=\"URL width=\"200\"/>"
] |
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": []} | IntervitensInc/intv_l3_mk2 | null | [
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-04-19T23:43:11+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"
] |
null | peft | ## Training procedure
The following `bitsandbytes` quantization config was used during training:
- quant_method: QuantizationMethod.BITS_AND_BYTES
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: True
- bnb_4bit_compute_dtype: bfloat16
### Framework versions
- PEFT 0.5.0
| {"library_name": "peft"} | SALT-NLP/CultureBank-Llama2-SFT | null | [
"peft",
"safetensors",
"region:us"
] | null | 2024-04-19T23:46:13+00:00 | [] | [] | TAGS
#peft #safetensors #region-us
| ## Training procedure
The following 'bitsandbytes' quantization config was used during training:
- quant_method: QuantizationMethod.BITS_AND_BYTES
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: True
- bnb_4bit_compute_dtype: bfloat16
### Framework versions
- PEFT 0.5.0
| [
"## Training procedure\n\n\nThe following 'bitsandbytes' quantization config was used during training:\n- quant_method: QuantizationMethod.BITS_AND_BYTES\n- load_in_8bit: False\n- load_in_4bit: True\n- llm_int8_threshold: 6.0\n- llm_int8_skip_modules: None\n- llm_int8_enable_fp32_cpu_offload: False\n- llm_int8_has_fp16_weight: False\n- bnb_4bit_quant_type: nf4\n- bnb_4bit_use_double_quant: True\n- bnb_4bit_compute_dtype: bfloat16",
"### Framework versions\n\n\n- PEFT 0.5.0"
] | [
"TAGS\n#peft #safetensors #region-us \n",
"## Training procedure\n\n\nThe following 'bitsandbytes' quantization config was used during training:\n- quant_method: QuantizationMethod.BITS_AND_BYTES\n- load_in_8bit: False\n- load_in_4bit: True\n- llm_int8_threshold: 6.0\n- llm_int8_skip_modules: None\n- llm_int8_enable_fp32_cpu_offload: False\n- llm_int8_has_fp16_weight: False\n- bnb_4bit_quant_type: nf4\n- bnb_4bit_use_double_quant: True\n- bnb_4bit_compute_dtype: bfloat16",
"### Framework versions\n\n\n- PEFT 0.5.0"
] |
reinforcement-learning | ml-agents |
# **ppo** Agent playing **Pyramids**
This is a trained model of a **ppo** agent playing **Pyramids**
using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents).
## Usage (with ML-Agents)
The Documentation: https://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/
We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:
- A *short tutorial* where you teach Huggy the Dog 🐶 to fetch the stick and then play with him directly in your
browser: https://huggingface.co/learn/deep-rl-course/unitbonus1/introduction
- A *longer tutorial* to understand how works ML-Agents:
https://huggingface.co/learn/deep-rl-course/unit5/introduction
### Resume the training
```bash
mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume
```
### Watch your Agent play
You can watch your agent **playing directly in your browser**
1. If the environment is part of ML-Agents official environments, go to https://huggingface.co/unity
2. Step 1: Find your model_id: conlan/ML-Agents-Pyramids
3. Step 2: Select your *.nn /*.onnx file
4. Click on Watch the agent play 👀
| {"library_name": "ml-agents", "tags": ["Pyramids", "deep-reinforcement-learning", "reinforcement-learning", "ML-Agents-Pyramids"]} | conlan/ML-Agents-Pyramids | null | [
"ml-agents",
"tensorboard",
"onnx",
"Pyramids",
"deep-reinforcement-learning",
"reinforcement-learning",
"ML-Agents-Pyramids",
"region:us"
] | null | 2024-04-19T23:49:29+00:00 | [] | [] | TAGS
#ml-agents #tensorboard #onnx #Pyramids #deep-reinforcement-learning #reinforcement-learning #ML-Agents-Pyramids #region-us
|
# ppo Agent playing Pyramids
This is a trained model of a ppo agent playing Pyramids
using the Unity ML-Agents Library.
## Usage (with ML-Agents)
The Documentation: URL
We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:
- A *short tutorial* where you teach Huggy the Dog to fetch the stick and then play with him directly in your
browser: URL
- A *longer tutorial* to understand how works ML-Agents:
URL
### Resume the training
### Watch your Agent play
You can watch your agent playing directly in your browser
1. If the environment is part of ML-Agents official environments, go to URL
2. Step 1: Find your model_id: conlan/ML-Agents-Pyramids
3. Step 2: Select your *.nn /*.onnx file
4. Click on Watch the agent play
| [
"# ppo Agent playing Pyramids\n This is a trained model of a ppo agent playing Pyramids\n using the Unity ML-Agents Library.\n\n ## Usage (with ML-Agents)\n The Documentation: URL\n\n We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:\n - A *short tutorial* where you teach Huggy the Dog to fetch the stick and then play with him directly in your\n browser: URL\n - A *longer tutorial* to understand how works ML-Agents:\n URL\n\n ### Resume the training\n \n\n ### Watch your Agent play\n You can watch your agent playing directly in your browser\n\n 1. If the environment is part of ML-Agents official environments, go to URL\n 2. Step 1: Find your model_id: conlan/ML-Agents-Pyramids\n 3. Step 2: Select your *.nn /*.onnx file\n 4. Click on Watch the agent play"
] | [
"TAGS\n#ml-agents #tensorboard #onnx #Pyramids #deep-reinforcement-learning #reinforcement-learning #ML-Agents-Pyramids #region-us \n",
"# ppo Agent playing Pyramids\n This is a trained model of a ppo agent playing Pyramids\n using the Unity ML-Agents Library.\n\n ## Usage (with ML-Agents)\n The Documentation: URL\n\n We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:\n - A *short tutorial* where you teach Huggy the Dog to fetch the stick and then play with him directly in your\n browser: URL\n - A *longer tutorial* to understand how works ML-Agents:\n URL\n\n ### Resume the training\n \n\n ### Watch your Agent play\n You can watch your agent playing directly in your browser\n\n 1. If the environment is part of ML-Agents official environments, go to URL\n 2. Step 1: Find your model_id: conlan/ML-Agents-Pyramids\n 3. Step 2: Select your *.nn /*.onnx file\n 4. Click on Watch the agent play"
] |
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": []} | OwOOwO/dumbo-stable2 | null | [
"transformers",
"safetensors",
"stablelm",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | null | 2024-04-19T23:49:47+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"
] |
null | peft | ## Training procedure
The following `bitsandbytes` quantization config was used during training:
- quant_method: QuantizationMethod.BITS_AND_BYTES
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: True
- bnb_4bit_compute_dtype: bfloat16
### Framework versions
- PEFT 0.5.0
| {"library_name": "peft"} | SALT-NLP/CultureBank-Mixtral-SFT | null | [
"peft",
"region:us"
] | null | 2024-04-19T23:50:32+00:00 | [] | [] | TAGS
#peft #region-us
| ## Training procedure
The following 'bitsandbytes' quantization config was used during training:
- quant_method: QuantizationMethod.BITS_AND_BYTES
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: True
- bnb_4bit_compute_dtype: bfloat16
### Framework versions
- PEFT 0.5.0
| [
"## Training procedure\n\n\nThe following 'bitsandbytes' quantization config was used during training:\n- quant_method: QuantizationMethod.BITS_AND_BYTES\n- load_in_8bit: False\n- load_in_4bit: True\n- llm_int8_threshold: 6.0\n- llm_int8_skip_modules: None\n- llm_int8_enable_fp32_cpu_offload: False\n- llm_int8_has_fp16_weight: False\n- bnb_4bit_quant_type: nf4\n- bnb_4bit_use_double_quant: True\n- bnb_4bit_compute_dtype: bfloat16",
"### Framework versions\n\n\n- PEFT 0.5.0"
] | [
"TAGS\n#peft #region-us \n",
"## Training procedure\n\n\nThe following 'bitsandbytes' quantization config was used during training:\n- quant_method: QuantizationMethod.BITS_AND_BYTES\n- load_in_8bit: False\n- load_in_4bit: True\n- llm_int8_threshold: 6.0\n- llm_int8_skip_modules: None\n- llm_int8_enable_fp32_cpu_offload: False\n- llm_int8_has_fp16_weight: False\n- bnb_4bit_quant_type: nf4\n- bnb_4bit_use_double_quant: True\n- bnb_4bit_compute_dtype: bfloat16",
"### Framework versions\n\n\n- PEFT 0.5.0"
] |
text-generation | transformers |
## VAGO solutions Llama-3-SauerkrautLM-8b-Instruct
Introducing **Llama-3-SauerkrautLM-8b-Instruct** – our Sauerkraut version of the powerful [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct)!
The model **Llama-3-SauerkrautLM-8b-Instruct** is a **joint effort** between **VAGO Solutions** and **Hyperspace.ai.**
- Aligned with **DPO**
# Table of Contents
1. [Overview of all Llama-3-SauerkrautLM-8b-Instruct](#all-Llama-3-SauerkrautLM-8b-Instruct)
2. [Model Details](#model-details)
- [Prompt template](#prompt-template)
- [Training procedure](#proceed-of-the-training)
3. [Evaluation](#evaluation)
5. [Disclaimer](#disclaimer)
6. [Contact](#contact)
7. [Collaborations](#collaborations)
8. [Acknowledgement](#acknowledgement)
## All SauerkrautLM-llama-3-8B-Instruct
| Model | HF | EXL2 | GGUF | AWQ |
|-------|-------|-------|-------|-------|
| Llama-3-SauerkrautLM-8b-Instruct | [Link](https://huggingface.co/VAGOsolutions/Llama-3-SauerkrautLM-8b-Instruct) | [Link](https://huggingface.co/bartowski/Llama-3-SauerkrautLM-8b-Instruct-exl2) | [Link](https://huggingface.co/bartowski/Llama-3-SauerkrautLM-8b-Instruct-GGUF) | coming soon |
## Model Details
**SauerkrautLM-llama-3-8B-Instruct**
- **Model Type:** Llama-3-SauerkrautLM-8b-Instruct is a finetuned Model based on [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct)
- **Language(s):** German, English
- **License:** [meta-llama](https://llama.meta.com/llama3/license)
- **Contact:** [VAGO solutions](https://vago-solutions.ai), [Hyperspace.ai](https://hyperspace.computer/)
### Training procedure:
- We trained this model in a two staged DPO Fine-Tuning for 1 epoch with 70k data and another epoch with 20k data.
- LaserRMT version coming soon
**We improved the model's capabilities noticably by feeding it with curated German data.**
### Prompt Template:
**English:**
```
<|begin_of_text|><|start_header_id|>system<|end_header_id|>
You are a helpful AI assistant.<|eot_id|><|start_header_id|>user<|end_header_id|>
Input<|eot_id|><|start_header_id|>assistant<|end_header_id|>
```
**German:**
```
<|begin_of_text|><|start_header_id|>system<|end_header_id|>
Du bist ein freundlicher und hilfreicher deutscher KI-Assistent.<|eot_id|><|start_header_id|>user<|end_header_id|>
Input<|eot_id|><|start_header_id|>assistant<|end_header_id|>
```
### Example output of german language:
```
Prompt: Erkläre mir die Vorteile für das Fine-Tuning von Meta's LLama Modellen.
Antwort:
Sehr gern!
Fine-tuning von Meta's LLaMA-Modellen ist eine sehr effektive Möglichkeit, um Ihre Anwendung oder Ihr Projekt mit einer hochentwickelten Sprachverarbeitung auszustatten.
Die Vorteile des Fine-Tunings von LLaMA-Modellen sind:
Adaptation an spezielle Aufgaben: Durch das Fine-Tuning können Sie die Modelle auf Ihre speziellen Bedürfnisse und Anforderungen anpassen.
Dies ermöglicht es Ihnen, die Leistung der Modelle in Ihren Anwendungen zu verbessern.
Verbesserte Genauigkeit: Die fine-tuned Modelle lernen, sich an die spezifischen Merkmale Ihres Datenbestands anzupassen, was zu einer besseren Genauigkeit bei der Textklassifizierung, -generierung, -summarisierung usw. führt.
Anpassung an Branche oder Domain: Wenn Sie beispielsweise ein Medizinprojekt haben, können Sie die Modelle auf medizinische Fachterminologie und -konzepte trainieren, um eine höhere Präzision bei der Analyse medizinischer Texte zu erzielen.
Kosten-Effektivität: Im Vergleich zum Training neuer Modelle von Grund auf kann das Fine-Tuning viel kosteneffektiver sein, da Sie nur einen kleinen Teil des Trainingsdatums benötigen, um die Modelle an Ihre spezifischen Anforderungen anzupassen.
Schnellere Entwicklung: Das Fine-Tuning ermöglicht es Entwicklern, schnell neue Funktionen und Features in ihre Anwendungen einzufügen, ohne dass sie lange warten müssen, bis neue Modelle trainiert werden.
Bessere Interpretierbarkeit: Da die fine-tuned Modelle auf Ihre spezifischen Daten bestimmt wurden, können Sie leichter verstehen, warum bestimmte Entscheidungen getroffen werden, was wichtig ist, wenn es um Transparenz und Verantwortlichkeit geht.
Insgesamt bietet das Fine-Tuning von LLaMA-Modellen eine flexible und effektive Möglichkeit, um Ihre Anwendungen und Projekte durch die Integration von fortschrittlichen Sprachmodellen zu verbessern.
```
## Evaluation
**Open LLM Leaderboard:**
evaluated with lm-evaluation-benchmark-harness 0.4.2
| Metric | Value |
|-----------------------|---------------------------|
| Avg. | **74.57** |
| ARC (25-shot) | 74.66 |
| HellaSwag (10-shot) | 89.60 |
| MMLU (5-shot) | 66.55 |
| TruthfulQA (0-shot) | 66.32 |
| Winogrande (5-shot) | 80.98 |
| GSM8K (5-shot) | 69.29 |
**MT-Bench English**
```
########## First turn ##########
score
model turn
Llama-3-SauerkrautLM-8b-Instruct 1 8.15625
########## Second turn ##########
score
model turn
Llama-3-SauerkrautLM-8b-Instruct 2 7.65
########## Average ##########
score
model
Llama-3-SauerkrautLM-8b-Instruct 7.903125 *
```
* due to specific instruction training the english MT-Bench score is slightly lower than the original LLama-3-8B-Instruct
**MT-Bench German**
```
########## First turn ##########
score
model turn
Llama-3-SauerkrautLM-8b-Instruct 1 7.675
########## Second turn ##########
score
model turn
Llama-3-SauerkrautLM-8b-Instruct 2 7.6375
########## Average ##########
score
model
Llama-3-SauerkrautLM-8b-Instruct 7.65625
```
**German RAG LLM Evaluation**
corrected result after FIX: https://github.com/huggingface/lighteval/pull/171
```
| Task |Version|Metric|Value| |Stderr|
|------------------------------------------------------|------:|------|----:|---|-----:|
|all | |acc |0.910|± |0.0084|
|community:german_rag_eval:_average:0 | |acc |0.910|± |0.0084|
|community:german_rag_eval:choose_context_by_question:0| 0|acc |0.928|± |0.0082|
|community:german_rag_eval:choose_question_by_context:0| 0|acc |0.824|± |0.0120|
|community:german_rag_eval:context_question_match:0 | 0|acc |0.982|± |0.0042|
|community:german_rag_eval:question_answer_match:0 | 0|acc |0.906|± |0.0092|
```
## Disclaimer
We must inform users that despite our best efforts in data cleansing, the possibility of uncensored content slipping through cannot be entirely ruled out.
However, we cannot guarantee consistently appropriate behavior. Therefore, if you encounter any issues or come across inappropriate content, we kindly request that you inform us through the contact information provided.
Additionally, it is essential to understand that the licensing of these models does not constitute legal advice. We are not held responsible for the actions of third parties who utilize our models.
## Contact
If you are interested in customized LLMs for business applications, please get in contact with us via our websites. We are also grateful for your feedback and suggestions.
## Collaborations
We are also keenly seeking support and investment for our startups, VAGO solutions and Hyperspace where we continuously advance the development of robust language models designed to address a diverse range of purposes and requirements. If the prospect of collaboratively navigating future challenges excites you, we warmly invite you to reach out to us at [VAGO solutions](https://vago-solutions.de/#Kontakt), [Hyperspace.computer](https://hyperspace.computer/)
## Acknowledgement
Many thanks to [Meta](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) for providing such valuable model to the Open-Source community.
Also many thanks to [bartowski](https://huggingface.co/bartowski) for super fast quantification of our Model in GGUF and EXL format.
| {"language": ["de", "en"], "license": "other", "tags": ["two stage dpo", "dpo"], "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"} | VAGOsolutions/Llama-3-SauerkrautLM-8b-Instruct | null | [
"transformers",
"safetensors",
"llama",
"text-generation",
"two stage dpo",
"dpo",
"conversational",
"de",
"en",
"license:other",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-04-19T23:56:36+00:00 | [] | [
"de",
"en"
] | TAGS
#transformers #safetensors #llama #text-generation #two stage dpo #dpo #conversational #de #en #license-other #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us
| !SauerkrautLM
VAGO solutions Llama-3-SauerkrautLM-8b-Instruct
-----------------------------------------------
Introducing Llama-3-SauerkrautLM-8b-Instruct – our Sauerkraut version of the powerful meta-llama/Meta-Llama-3-8B-Instruct!
The model Llama-3-SauerkrautLM-8b-Instruct is a joint effort between VAGO Solutions and URL.
* Aligned with DPO
Table of Contents
=================
1. Overview of all Llama-3-SauerkrautLM-8b-Instruct
2. Model Details
* Prompt template
* Training procedure
3. Evaluation
4. Disclaimer
5. Contact
6. Collaborations
7. Acknowledgement
All SauerkrautLM-llama-3-8B-Instruct
------------------------------------
Model Details
-------------
SauerkrautLM-llama-3-8B-Instruct
* Model Type: Llama-3-SauerkrautLM-8b-Instruct is a finetuned Model based on meta-llama/Meta-Llama-3-8B-Instruct
* Language(s): German, English
* License: meta-llama
* Contact: VAGO solutions, URL
### Training procedure:
* We trained this model in a two staged DPO Fine-Tuning for 1 epoch with 70k data and another epoch with 20k data.
* LaserRMT version coming soon
We improved the model's capabilities noticably by feeding it with curated German data.
### Prompt Template:
English:
German:
### Example output of german language:
Evaluation
----------
Open LLM Leaderboard:
evaluated with lm-evaluation-benchmark-harness 0.4.2
MT-Bench English
* due to specific instruction training the english MT-Bench score is slightly lower than the original LLama-3-8B-Instruct
MT-Bench German
German RAG LLM Evaluation
corrected result after FIX: URL
Disclaimer
----------
We must inform users that despite our best efforts in data cleansing, the possibility of uncensored content slipping through cannot be entirely ruled out.
However, we cannot guarantee consistently appropriate behavior. Therefore, if you encounter any issues or come across inappropriate content, we kindly request that you inform us through the contact information provided.
Additionally, it is essential to understand that the licensing of these models does not constitute legal advice. We are not held responsible for the actions of third parties who utilize our models.
Contact
-------
If you are interested in customized LLMs for business applications, please get in contact with us via our websites. We are also grateful for your feedback and suggestions.
Collaborations
--------------
We are also keenly seeking support and investment for our startups, VAGO solutions and Hyperspace where we continuously advance the development of robust language models designed to address a diverse range of purposes and requirements. If the prospect of collaboratively navigating future challenges excites you, we warmly invite you to reach out to us at VAGO solutions, Hyperspace.computer
Acknowledgement
---------------
Many thanks to Meta for providing such valuable model to the Open-Source community.
Also many thanks to bartowski for super fast quantification of our Model in GGUF and EXL format.
| [
"### Training procedure:\n\n\n* We trained this model in a two staged DPO Fine-Tuning for 1 epoch with 70k data and another epoch with 20k data.\n* LaserRMT version coming soon\n\n\nWe improved the model's capabilities noticably by feeding it with curated German data.",
"### Prompt Template:\n\n\nEnglish:\n\n\nGerman:",
"### Example output of german language:\n\n\nEvaluation\n----------\n\n\nOpen LLM Leaderboard:\n\n\nevaluated with lm-evaluation-benchmark-harness 0.4.2\n\n\n\nMT-Bench English\n\n\n* due to specific instruction training the english MT-Bench score is slightly lower than the original LLama-3-8B-Instruct\n\n\nMT-Bench German\n\n\nGerman RAG LLM Evaluation\ncorrected result after FIX: URL\n\n\nDisclaimer\n----------\n\n\nWe must inform users that despite our best efforts in data cleansing, the possibility of uncensored content slipping through cannot be entirely ruled out.\nHowever, we cannot guarantee consistently appropriate behavior. Therefore, if you encounter any issues or come across inappropriate content, we kindly request that you inform us through the contact information provided.\nAdditionally, it is essential to understand that the licensing of these models does not constitute legal advice. We are not held responsible for the actions of third parties who utilize our models.\n\n\nContact\n-------\n\n\nIf you are interested in customized LLMs for business applications, please get in contact with us via our websites. We are also grateful for your feedback and suggestions.\n\n\nCollaborations\n--------------\n\n\nWe are also keenly seeking support and investment for our startups, VAGO solutions and Hyperspace where we continuously advance the development of robust language models designed to address a diverse range of purposes and requirements. If the prospect of collaboratively navigating future challenges excites you, we warmly invite you to reach out to us at VAGO solutions, Hyperspace.computer\n\n\nAcknowledgement\n---------------\n\n\nMany thanks to Meta for providing such valuable model to the Open-Source community.\nAlso many thanks to bartowski for super fast quantification of our Model in GGUF and EXL format."
] | [
"TAGS\n#transformers #safetensors #llama #text-generation #two stage dpo #dpo #conversational #de #en #license-other #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n",
"### Training procedure:\n\n\n* We trained this model in a two staged DPO Fine-Tuning for 1 epoch with 70k data and another epoch with 20k data.\n* LaserRMT version coming soon\n\n\nWe improved the model's capabilities noticably by feeding it with curated German data.",
"### Prompt Template:\n\n\nEnglish:\n\n\nGerman:",
"### Example output of german language:\n\n\nEvaluation\n----------\n\n\nOpen LLM Leaderboard:\n\n\nevaluated with lm-evaluation-benchmark-harness 0.4.2\n\n\n\nMT-Bench English\n\n\n* due to specific instruction training the english MT-Bench score is slightly lower than the original LLama-3-8B-Instruct\n\n\nMT-Bench German\n\n\nGerman RAG LLM Evaluation\ncorrected result after FIX: URL\n\n\nDisclaimer\n----------\n\n\nWe must inform users that despite our best efforts in data cleansing, the possibility of uncensored content slipping through cannot be entirely ruled out.\nHowever, we cannot guarantee consistently appropriate behavior. Therefore, if you encounter any issues or come across inappropriate content, we kindly request that you inform us through the contact information provided.\nAdditionally, it is essential to understand that the licensing of these models does not constitute legal advice. We are not held responsible for the actions of third parties who utilize our models.\n\n\nContact\n-------\n\n\nIf you are interested in customized LLMs for business applications, please get in contact with us via our websites. We are also grateful for your feedback and suggestions.\n\n\nCollaborations\n--------------\n\n\nWe are also keenly seeking support and investment for our startups, VAGO solutions and Hyperspace where we continuously advance the development of robust language models designed to address a diverse range of purposes and requirements. If the prospect of collaboratively navigating future challenges excites you, we warmly invite you to reach out to us at VAGO solutions, Hyperspace.computer\n\n\nAcknowledgement\n---------------\n\n\nMany thanks to Meta for providing such valuable model to the Open-Source community.\nAlso many thanks to bartowski for super fast quantification of our Model in GGUF and EXL format."
] |
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_llama_1 | null | [
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-04-20T00:00:57+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 |
<img src=https://huggingface.co/lodrick-the-lafted/Copus-2x8B/resolve/main/copus.png>
MoE'd up:
- [dreamgen/opus-v1.2-llama-3-8b](https://huggingface.co/dreamgen/opus-v1.2-llama-3-8b)
- [NousResearch/Meta-Llama-3-8B-Instruct](https://huggingface.co/NousResearch/Meta-Llama-3-8B-Instruct)_
Which were the two most interesting llama3 finetunes as of yet. Resulting model seems OK. It's not on Miqu's level, anyway.
Blah, blah, llama 3 license (no tag for it yet). Also not going to name my model Llama-3-Copus. Come at me, Zuck. | {"license": "llama2"} | lodrick-the-lafted/Copus-2x8B | null | [
"transformers",
"safetensors",
"mixtral",
"text-generation",
"conversational",
"license:llama2",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-04-20T00:04:35+00:00 | [] | [] | TAGS
#transformers #safetensors #mixtral #text-generation #conversational #license-llama2 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us
|
<img src=URL
MoE'd up:
- dreamgen/opus-v1.2-llama-3-8b
- NousResearch/Meta-Llama-3-8B-Instruct_
Which were the two most interesting llama3 finetunes as of yet. Resulting model seems OK. It's not on Miqu's level, anyway.
Blah, blah, llama 3 license (no tag for it yet). Also not going to name my model Llama-3-Copus. Come at me, Zuck. | [] | [
"TAGS\n#transformers #safetensors #mixtral #text-generation #conversational #license-llama2 #autotrain_compatible #endpoints_compatible #text-generation-inference #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. -->
# RM-HH-Mix_harmless_gpt3_20000_gemma2b_shuffleTrue_extractchosenTrue
This model is a fine-tuned version of [google/gemma-2b](https://huggingface.co/google/gemma-2b) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.5008
- Accuracy: 0.73
## 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 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 0.7309 | 0.06 | 250 | 0.6808 | 0.5865 |
| 0.6572 | 0.11 | 500 | 0.6149 | 0.6515 |
| 0.6119 | 0.17 | 750 | 0.5805 | 0.672 |
| 0.5447 | 0.22 | 1000 | 0.5620 | 0.6825 |
| 0.5644 | 0.28 | 1250 | 0.5506 | 0.694 |
| 0.5249 | 0.33 | 1500 | 0.5417 | 0.6955 |
| 0.5416 | 0.39 | 1750 | 0.5322 | 0.698 |
| 0.5139 | 0.44 | 2000 | 0.5287 | 0.706 |
| 0.5134 | 0.5 | 2250 | 0.5223 | 0.707 |
| 0.5349 | 0.56 | 2500 | 0.5152 | 0.712 |
| 0.4918 | 0.61 | 2750 | 0.5168 | 0.718 |
| 0.5008 | 0.67 | 3000 | 0.5158 | 0.724 |
| 0.5101 | 0.72 | 3250 | 0.5135 | 0.7265 |
| 0.4968 | 0.78 | 3500 | 0.5080 | 0.7275 |
| 0.5325 | 0.83 | 3750 | 0.5039 | 0.7285 |
| 0.529 | 0.89 | 4000 | 0.5006 | 0.7285 |
| 0.4696 | 0.94 | 4250 | 0.5008 | 0.73 |
### 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-Mix_harmless_gpt3_20000_gemma2b_shuffleTrue_extractchosenTrue", "results": []}]} | Holarissun/RM-HH-Mix_harmless_gpt3_20000_gemma2b_shuffleTrue_extractchosenTrue | null | [
"peft",
"safetensors",
"trl",
"reward-trainer",
"generated_from_trainer",
"base_model:google/gemma-2b",
"license:gemma",
"region:us"
] | null | 2024-04-20T00:06:10+00:00 | [] | [] | TAGS
#peft #safetensors #trl #reward-trainer #generated_from_trainer #base_model-google/gemma-2b #license-gemma #region-us
| RM-HH-Mix\_harmless\_gpt3\_20000\_gemma2b\_shuffleTrue\_extractchosenTrue
=========================================================================
This model is a fine-tuned version of google/gemma-2b on the None dataset.
It achieves the following results on the evaluation set:
* Loss: 0.5008
* Accuracy: 0.73
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"
] |
sentence-similarity | sentence-transformers |
# Akshayxx/citeseer-finetuned-embeddings
This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 384 dimensional dense vector space and can be used for tasks like clustering or semantic search.
<!--- Describe your model here -->
## Usage (Sentence-Transformers)
Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
```
pip install -U sentence-transformers
```
Then you can use the model like this:
```python
from sentence_transformers import SentenceTransformer
sentences = ["This is an example sentence", "Each sentence is converted"]
model = SentenceTransformer('Akshayxx/citeseer-finetuned-embeddings')
embeddings = model.encode(sentences)
print(embeddings)
```
## Usage (HuggingFace Transformers)
Without [sentence-transformers](https://www.SBERT.net), you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings.
```python
from transformers import AutoTokenizer, AutoModel
import torch
#Mean Pooling - Take attention mask into account for correct averaging
def mean_pooling(model_output, attention_mask):
token_embeddings = model_output[0] #First element of model_output contains all token embeddings
input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)
# Sentences we want sentence embeddings for
sentences = ['This is an example sentence', 'Each sentence is converted']
# Load model from HuggingFace Hub
tokenizer = AutoTokenizer.from_pretrained('Akshayxx/citeseer-finetuned-embeddings')
model = AutoModel.from_pretrained('Akshayxx/citeseer-finetuned-embeddings')
# Tokenize sentences
encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
# Compute token embeddings
with torch.no_grad():
model_output = model(**encoded_input)
# Perform pooling. In this case, mean pooling.
sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])
print("Sentence embeddings:")
print(sentence_embeddings)
```
## Evaluation Results
<!--- Describe how your model was evaluated -->
For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name=Akshayxx/citeseer-finetuned-embeddings)
## Training
The model was trained with the parameters:
**DataLoader**:
`torch.utils.data.dataloader.DataLoader` of length 149 with parameters:
```
{'batch_size': 8, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}
```
**Loss**:
`sentence_transformers.losses.MultipleNegativesRankingLoss.MultipleNegativesRankingLoss` with parameters:
```
{'scale': 20.0, 'similarity_fct': 'cos_sim'}
```
Parameters of the fit()-Method:
```
{
"epochs": 3,
"evaluation_steps": 0,
"evaluator": "NoneType",
"max_grad_norm": 1,
"optimizer_class": "<class 'torch.optim.adamw.AdamW'>",
"optimizer_params": {
"lr": 2e-05
},
"scheduler": "WarmupLinear",
"steps_per_epoch": null,
"warmup_steps": 44,
"weight_decay": 0.01
}
```
## Full Model Architecture
```
SentenceTransformer(
(0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: BertModel
(1): Pooling({'word_embedding_dimension': 384, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
)
```
## Citing & Authors
<!--- Describe where people can find more information --> | {"library_name": "sentence-transformers", "tags": ["sentence-transformers", "feature-extraction", "sentence-similarity", "transformers"], "pipeline_tag": "sentence-similarity"} | Akshayxx/citeseer-finetuned-embeddings | null | [
"sentence-transformers",
"safetensors",
"bert",
"feature-extraction",
"sentence-similarity",
"transformers",
"endpoints_compatible",
"region:us"
] | null | 2024-04-20T00:06:18+00:00 | [] | [] | TAGS
#sentence-transformers #safetensors #bert #feature-extraction #sentence-similarity #transformers #endpoints_compatible #region-us
|
# Akshayxx/citeseer-finetuned-embeddings
This is a sentence-transformers model: It maps sentences & paragraphs to a 384 dimensional dense vector space and can be used for tasks like clustering or semantic search.
## Usage (Sentence-Transformers)
Using this model becomes easy when you have sentence-transformers installed:
Then you can use the model like this:
## Usage (HuggingFace Transformers)
Without sentence-transformers, you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings.
## Evaluation Results
For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: URL
## Training
The model was trained with the parameters:
DataLoader:
'URL.dataloader.DataLoader' of length 149 with parameters:
Loss:
'sentence_transformers.losses.MultipleNegativesRankingLoss.MultipleNegativesRankingLoss' with parameters:
Parameters of the fit()-Method:
## Full Model Architecture
## Citing & Authors
| [
"# Akshayxx/citeseer-finetuned-embeddings\n\nThis is a sentence-transformers model: It maps sentences & paragraphs to a 384 dimensional dense vector space and can be used for tasks like clustering or semantic search.",
"## Usage (Sentence-Transformers)\n\nUsing this model becomes easy when you have sentence-transformers installed:\n\n\n\nThen you can use the model like this:",
"## Usage (HuggingFace Transformers)\nWithout sentence-transformers, you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings.",
"## Evaluation Results\n\n\n\nFor an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: URL",
"## Training\nThe model was trained with the parameters:\n\nDataLoader:\n\n'URL.dataloader.DataLoader' of length 149 with parameters:\n\n\nLoss:\n\n'sentence_transformers.losses.MultipleNegativesRankingLoss.MultipleNegativesRankingLoss' with parameters:\n \n\nParameters of the fit()-Method:",
"## Full Model Architecture",
"## Citing & Authors"
] | [
"TAGS\n#sentence-transformers #safetensors #bert #feature-extraction #sentence-similarity #transformers #endpoints_compatible #region-us \n",
"# Akshayxx/citeseer-finetuned-embeddings\n\nThis is a sentence-transformers model: It maps sentences & paragraphs to a 384 dimensional dense vector space and can be used for tasks like clustering or semantic search.",
"## Usage (Sentence-Transformers)\n\nUsing this model becomes easy when you have sentence-transformers installed:\n\n\n\nThen you can use the model like this:",
"## Usage (HuggingFace Transformers)\nWithout sentence-transformers, you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings.",
"## Evaluation Results\n\n\n\nFor an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: URL",
"## Training\nThe model was trained with the parameters:\n\nDataLoader:\n\n'URL.dataloader.DataLoader' of length 149 with parameters:\n\n\nLoss:\n\n'sentence_transformers.losses.MultipleNegativesRankingLoss.MultipleNegativesRankingLoss' with parameters:\n \n\nParameters of the fit()-Method:",
"## Full Model Architecture",
"## Citing & Authors"
] |
reinforcement-learning | stable-baselines3 |
# **QRDQN** Agent playing **SpaceInvadersNoFrameskip-v4**
This is a trained model of a **QRDQN** agent playing **SpaceInvadersNoFrameskip-v4**
using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3)
and the [RL Zoo](https://github.com/DLR-RM/rl-baselines3-zoo).
The RL Zoo is a training framework for Stable Baselines3
reinforcement learning agents,
with hyperparameter optimization and pre-trained agents included.
## Usage (with SB3 RL Zoo)
RL Zoo: https://github.com/DLR-RM/rl-baselines3-zoo<br/>
SB3: https://github.com/DLR-RM/stable-baselines3<br/>
SB3 Contrib: https://github.com/Stable-Baselines-Team/stable-baselines3-contrib
Install the RL Zoo (with SB3 and SB3-Contrib):
```bash
pip install rl_zoo3
```
```
# Download model and save it into the logs/ folder
python -m rl_zoo3.load_from_hub --algo qrdqn --env SpaceInvadersNoFrameskip-v4 -orga izaznov -f logs/
python -m rl_zoo3.enjoy --algo qrdqn --env SpaceInvadersNoFrameskip-v4 -f logs/
```
If you installed the RL Zoo3 via pip (`pip install rl_zoo3`), from anywhere you can do:
```
python -m rl_zoo3.load_from_hub --algo qrdqn --env SpaceInvadersNoFrameskip-v4 -orga izaznov -f logs/
python -m rl_zoo3.enjoy --algo qrdqn --env SpaceInvadersNoFrameskip-v4 -f logs/
```
## Training (with the RL Zoo)
```
python -m rl_zoo3.train --algo qrdqn --env SpaceInvadersNoFrameskip-v4 -f logs/
# Upload the model and generate video (when possible)
python -m rl_zoo3.push_to_hub --algo qrdqn --env SpaceInvadersNoFrameskip-v4 -f logs/ -orga izaznov
```
## Hyperparameters
```python
OrderedDict([('batch_size', 64),
('env_wrapper',
['stable_baselines3.common.atari_wrappers.AtariWrapper']),
('exploration_fraction', 0.025),
('frame_stack', 4),
('n_timesteps', 10000000.0),
('optimize_memory_usage', False),
('policy', 'CnnPolicy'),
('normalize', False)])
```
# Environment Arguments
```python
{'render_mode': 'rgb_array'}
```
| {"library_name": "stable-baselines3", "tags": ["SpaceInvadersNoFrameskip-v4", "deep-reinforcement-learning", "reinforcement-learning", "stable-baselines3"], "model-index": [{"name": "QRDQN", "results": [{"task": {"type": "reinforcement-learning", "name": "reinforcement-learning"}, "dataset": {"name": "SpaceInvadersNoFrameskip-v4", "type": "SpaceInvadersNoFrameskip-v4"}, "metrics": [{"type": "mean_reward", "value": "6961.50 +/- 6523.95", "name": "mean_reward", "verified": false}]}]}]} | izaznov/qrdqn-SpaceInvadersNoFrameskip-v4 | null | [
"stable-baselines3",
"SpaceInvadersNoFrameskip-v4",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] | null | 2024-04-20T00:08:33+00:00 | [] | [] | TAGS
#stable-baselines3 #SpaceInvadersNoFrameskip-v4 #deep-reinforcement-learning #reinforcement-learning #model-index #region-us
|
# QRDQN Agent playing SpaceInvadersNoFrameskip-v4
This is a trained model of a QRDQN agent playing SpaceInvadersNoFrameskip-v4
using the stable-baselines3 library
and the RL Zoo.
The RL Zoo is a training framework for Stable Baselines3
reinforcement learning agents,
with hyperparameter optimization and pre-trained agents included.
## Usage (with SB3 RL Zoo)
RL Zoo: URL
SB3: URL
SB3 Contrib: URL
Install the RL Zoo (with SB3 and SB3-Contrib):
If you installed the RL Zoo3 via pip ('pip install rl_zoo3'), from anywhere you can do:
## Training (with the RL Zoo)
## Hyperparameters
# Environment Arguments
| [
"# QRDQN Agent playing SpaceInvadersNoFrameskip-v4\nThis is a trained model of a QRDQN agent playing SpaceInvadersNoFrameskip-v4\nusing the stable-baselines3 library\nand the RL Zoo.\n\nThe RL Zoo is a training framework for Stable Baselines3\nreinforcement learning agents,\nwith hyperparameter optimization and pre-trained agents included.",
"## Usage (with SB3 RL Zoo)\n\nRL Zoo: URL\nSB3: URL\nSB3 Contrib: URL\n\nInstall the RL Zoo (with SB3 and SB3-Contrib):\n\n\n\n\nIf you installed the RL Zoo3 via pip ('pip install rl_zoo3'), from anywhere you can do:",
"## Training (with the RL Zoo)",
"## Hyperparameters",
"# Environment Arguments"
] | [
"TAGS\n#stable-baselines3 #SpaceInvadersNoFrameskip-v4 #deep-reinforcement-learning #reinforcement-learning #model-index #region-us \n",
"# QRDQN Agent playing SpaceInvadersNoFrameskip-v4\nThis is a trained model of a QRDQN agent playing SpaceInvadersNoFrameskip-v4\nusing the stable-baselines3 library\nand the RL Zoo.\n\nThe RL Zoo is a training framework for Stable Baselines3\nreinforcement learning agents,\nwith hyperparameter optimization and pre-trained agents included.",
"## Usage (with SB3 RL Zoo)\n\nRL Zoo: URL\nSB3: URL\nSB3 Contrib: URL\n\nInstall the RL Zoo (with SB3 and SB3-Contrib):\n\n\n\n\nIf you installed the RL Zoo3 via pip ('pip install rl_zoo3'), from anywhere you can do:",
"## Training (with the RL Zoo)",
"## Hyperparameters",
"# Environment Arguments"
] |
audio-classification | transformers | # Accent Classification
Whisper-based audio classification model trained on the [EdAcc dataset](https://huggingface.co/datasets/edinburghcstr/edacc).
This model was trained for 15 epochs.
## Evaluation
It achieves the following results on the evaluation set:
- Loss: 0.0340
- Accuracy: 0.9960
## Hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 32
- eval_batch_size: 16
- seed: 0
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 15.0
- mixed_precision_training: Native AMP
## Training Results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 2.75 | 1.0 | 290 | 2.6410 | 0.2788 |
| 1.7626 | 2.0 | 580 | 1.6589 | 0.6165 |
| 1.2434 | 3.0 | 870 | 1.0752 | 0.7746 |
| 0.903 | 4.0 | 1160 | 0.7628 | 0.8295 |
| 0.6878 | 5.0 | 1450 | 0.5528 | 0.8865 |
| 0.5063 | 6.0 | 1740 | 0.4051 | 0.9189 |
| 0.3312 | 7.0 | 2030 | 0.3041 | 0.9471 |
| 0.2562 | 8.0 | 2320 | 0.2236 | 0.9629 |
| 0.2163 | 9.0 | 2610 | 0.1633 | 0.9757 |
| 0.127 | 10.0 | 2900 | 0.1250 | 0.9813 |
| 0.1187 | 11.0 | 3190 | 0.0842 | 0.9888 |
| 0.0649 | 12.0 | 3480 | 0.0604 | 0.9920 |
| 0.0506 | 13.0 | 3770 | 0.0447 | 0.9945 |
| 0.0514 | 14.0 | 4060 | 0.0370 | 0.9956 |
| 0.0311 | 15.0 | 4350 | 0.0340 | 0.9960 |
## Disclaimer
This model may make mistakes and should not be used in high-risk situations.
THE MODEL IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES WITH REGARD TO THIS MODEL INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS MODEL.
| {"language": ["en"], "datasets": ["ml-for-speech/edacc"], "pipeline_tag": "audio-classification"} | ml-for-speech/accent-classification | null | [
"transformers",
"safetensors",
"whisper",
"audio-classification",
"en",
"dataset:ml-for-speech/edacc",
"endpoints_compatible",
"has_space",
"region:us"
] | null | 2024-04-20T00:09:00+00:00 | [] | [
"en"
] | TAGS
#transformers #safetensors #whisper #audio-classification #en #dataset-ml-for-speech/edacc #endpoints_compatible #has_space #region-us
| Accent Classification
=====================
Whisper-based audio classification model trained on the EdAcc dataset.
This model was trained for 15 epochs.
Evaluation
----------
It achieves the following results on the evaluation set:
* Loss: 0.0340
* Accuracy: 0.9960
Hyperparameters
---------------
The following hyperparameters were used during training:
* learning\_rate: 1e-05
* train\_batch\_size: 32
* eval\_batch\_size: 16
* seed: 0
* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
* lr\_scheduler\_type: linear
* lr\_scheduler\_warmup\_ratio: 0.1
* num\_epochs: 15.0
* mixed\_precision\_training: Native AMP
Training Results
----------------
Disclaimer
----------
This model may make mistakes and should not be used in high-risk situations.
THE MODEL IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES WITH REGARD TO THIS MODEL INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS MODEL.
| [] | [
"TAGS\n#transformers #safetensors #whisper #audio-classification #en #dataset-ml-for-speech/edacc #endpoints_compatible #has_space #region-us \n"
] |
null | null |
<!-- 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. -->
# tapt_helpfulness_unipelt_pretraining_model_fix_train
This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 1.4789
## 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: 21
- eval_batch_size: 21
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 42
- optimizer: Adam with betas=(0.9,0.98) and epsilon=1e-06
- lr_scheduler_type: linear
- num_epochs: 20
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:-----:|:---------------:|
| 2.7536 | 1.0 | 1068 | 1.8161 |
| 1.855 | 2.0 | 2137 | 1.6743 |
| 1.7578 | 3.0 | 3205 | 1.6134 |
| 1.7056 | 4.0 | 4274 | 1.5780 |
| 1.6755 | 5.0 | 5342 | 1.5660 |
| 1.6508 | 6.0 | 6411 | 1.5507 |
| 1.6402 | 7.0 | 7479 | 1.5236 |
| 1.6226 | 8.0 | 8548 | 1.5272 |
| 1.6145 | 9.0 | 9616 | 1.4970 |
| 1.6034 | 10.0 | 10685 | 1.4999 |
| 1.6004 | 11.0 | 11753 | 1.5120 |
| 1.5916 | 12.0 | 12822 | 1.4882 |
| 1.5888 | 13.0 | 13890 | 1.4974 |
| 1.5801 | 14.0 | 14959 | 1.4703 |
| 1.5784 | 15.0 | 16027 | 1.4767 |
| 1.5738 | 16.0 | 17096 | 1.4668 |
| 1.5717 | 17.0 | 18164 | 1.4776 |
| 1.5696 | 18.0 | 19233 | 1.4691 |
| 1.5681 | 19.0 | 20301 | 1.4756 |
| 1.5658 | 19.99 | 21360 | 1.4789 |
### Framework versions
- Transformers 4.36.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.15.2
| {"license": "mit", "tags": ["generated_from_trainer"], "base_model": "roberta-base", "model-index": [{"name": "tapt_helpfulness_unipelt_pretraining_model_fix_train", "results": []}]} | ltuzova/tapt_helpfulness_unipelt_pretraining_model_fix_train | null | [
"tensorboard",
"generated_from_trainer",
"base_model:roberta-base",
"license:mit",
"region:us"
] | null | 2024-04-20T00:10:18+00:00 | [] | [] | TAGS
#tensorboard #generated_from_trainer #base_model-roberta-base #license-mit #region-us
| tapt\_helpfulness\_unipelt\_pretraining\_model\_fix\_train
==========================================================
This model is a fine-tuned version of roberta-base on an unknown dataset.
It achieves the following results on the evaluation set:
* Loss: 1.4789
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: 21
* eval\_batch\_size: 21
* seed: 42
* gradient\_accumulation\_steps: 2
* total\_train\_batch\_size: 42
* optimizer: Adam with betas=(0.9,0.98) and epsilon=1e-06
* lr\_scheduler\_type: linear
* num\_epochs: 20
### Training results
### Framework versions
* Transformers 4.36.2
* 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: 0.0001\n* train\\_batch\\_size: 21\n* eval\\_batch\\_size: 21\n* seed: 42\n* gradient\\_accumulation\\_steps: 2\n* total\\_train\\_batch\\_size: 42\n* optimizer: Adam with betas=(0.9,0.98) and epsilon=1e-06\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 20",
"### Training results",
"### Framework versions\n\n\n* Transformers 4.36.2\n* Pytorch 2.2.1+cu121\n* Datasets 2.19.0\n* Tokenizers 0.15.2"
] | [
"TAGS\n#tensorboard #generated_from_trainer #base_model-roberta-base #license-mit #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: 21\n* eval\\_batch\\_size: 21\n* seed: 42\n* gradient\\_accumulation\\_steps: 2\n* total\\_train\\_batch\\_size: 42\n* optimizer: Adam with betas=(0.9,0.98) and epsilon=1e-06\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 20",
"### Training results",
"### Framework versions\n\n\n* Transformers 4.36.2\n* Pytorch 2.2.1+cu121\n* Datasets 2.19.0\n* Tokenizers 0.15.2"
] |
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": []} | IntervitensInc/intv_l3_mk3 | null | [
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-04-20T00:13:41+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"
] |
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": []} | SurtMcGert/NLP-group-CW-xlnet-ner-tagging | null | [
"transformers",
"safetensors",
"roberta",
"token-classification",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | null | 2024-04-20T00:13:47+00:00 | [
"1910.09700"
] | [] | TAGS
#transformers #safetensors #roberta #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 #roberta #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 | Llama-3-11.5B-v2
Thank you to Meta for the weights for Meta-Llama-3-8B
This is an upscaling of the Meta-Llama-3-8B Ai using techniques created for chargoddard/mistral-11b-slimorca. This Ai model has been upscaled from 8b parameters to 11.5b parameters without any continuous pretraining or fine-tuning.
Unlike version 1 this model has no issues at fp16 or any quantizations.
The model that was used to create this one is linked below:
https://huggingface.co/meta-llama/Meta-Llama-3-8B
| {"license": "other", "license_name": "llama-3", "license_link": "https://llama.meta.com/llama3/license/"} | Replete-AI/Llama-3-11.5B-V2 | null | [
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"license:other",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-04-20T00:18:20+00:00 | [] | [] | TAGS
#transformers #safetensors #llama #text-generation #conversational #license-other #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us
| Llama-3-11.5B-v2
Thank you to Meta for the weights for Meta-Llama-3-8B
!image/png
This is an upscaling of the Meta-Llama-3-8B Ai using techniques created for chargoddard/mistral-11b-slimorca. This Ai model has been upscaled from 8b parameters to 11.5b parameters without any continuous pretraining or fine-tuning.
Unlike version 1 this model has no issues at fp16 or any quantizations.
The model that was used to create this one is linked below:
URL
| [] | [
"TAGS\n#transformers #safetensors #llama #text-generation #conversational #license-other #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n"
] |
null | null | # 説明
wikipedia, mbpp, grade-school-mathで学習したトークナイザー。
## 学習に使ったデータ
英語：1.33GB (wiki40b)<br>
日本語：1.78GB (wiki40b) ※形態素単位で"||||"で事前分割してsentencepieceの学習時にpretokenization_delimiterを設定。<br>
コード：172KB (mbpp) <br>
数学：2.1MB (grade-school-math)
## 語彙の割合
概算ですが、アルファベットが約6割、日本語が約4割だと思います。（その他記号や数字は1~2%かと）
## 引用元
- https://aclanthology.org/2020.lrec-1.297.pdf
- https://www.tensorflow.org/datasets/catalog/wiki40b
- https://github.com/openai/grade-school-math
- https://github.com/google-research/google-research/tree/master/mbpp
## 設定
vocab_size=51,200（語彙サイズ）<br>
character_coverage=0.9995（文字のカバー率99.95%）<br>
model_type="unigram"（アルゴリズム）<br>
normalization="identity"（正規化なし）<br>
byte_fallback=True（バイト変換あり）<br>
split_digits=True（数字分割あり）<br>
allow_whitespace_only_pieces=True（空白のトークンを許可する）<br>
remove_extra_whitespaces=True（余分な空白の削除あり）<br>
## 形式
LlamaTokenizer<br>
※encode時に文頭にbos_tokenである"\<s\>"トークンが付きます。
# 使い方
```python
!pip install transformers>=4.34.0
from transformers import AutoTokenizer
test_tokenizer = AutoTokenizer.from_pretrained("geniacllm/ja-en-tokenizer-unigram-v3", use_fast=False)
```
```python
# text
text = "This is tokenizer test."
# tokenize
tokenized = test_tokenizer.tokenize(text)
print(tokenized)
# encode
encoded = test_tokenizer.encode(text)
print(encoded)
# decode
decoded = test_tokenizer.decode(encoded)
print(decoded)
# special_token
print(test_tokenizer.special_tokens_map)
# vocab size
print(len(test_tokenizer))
# all subwords in vocab
print(test_tokenizer.get_vocab())
``` | {} | geniacllm/ja-en-tokenizer-unigram-v3 | null | [
"region:us"
] | null | 2024-04-20T00:18:51+00:00 | [] | [] | TAGS
#region-us
| # 説明
wikipedia, mbpp, grade-school-mathで学習したトークナイザー。
## 学習に使ったデータ
英語：1.33GB (wiki40b)<br>
日本語：1.78GB (wiki40b) ※形態素単位で"||||"で事前分割してsentencepieceの学習時にpretokenization_delimiterを設定。<br>
コード：172KB (mbpp) <br>
数学：2.1MB (grade-school-math)
## 語彙の割合
概算ですが、アルファベットが約6割、日本語が約4割だと思います。（その他記号や数字は1~2%かと）
## 引用元
- URL
- URL
- URL
- URL
## 設定
vocab_size=51,200（語彙サイズ）<br>
character_coverage=0.9995（文字のカバー率99.95%）<br>
model_type="unigram"（アルゴリズム）<br>
normalization="identity"（正規化なし）<br>
byte_fallback=True（バイト変換あり）<br>
split_digits=True（数字分割あり）<br>
allow_whitespace_only_pieces=True（空白のトークンを許可する）<br>
remove_extra_whitespaces=True（余分な空白の削除あり）<br>
## 形式
LlamaTokenizer<br>
※encode時に文頭にbos_tokenである"\<s\>"トークンが付きます。
# 使い方
| [
"# 説明\nwikipedia, mbpp, grade-school-mathで学習したトークナイザー。",
"## 学習に使ったデータ\n英語：1.33GB (wiki40b)<br>\n日本語：1.78GB (wiki40b) ※形態素単位で\"||||\"で事前分割してsentencepieceの学習時にpretokenization_delimiterを設定。<br>\nコード：172KB (mbpp) <br>\n数学：2.1MB (grade-school-math)",
"## 語彙の割合\n概算ですが、アルファベットが約6割、日本語が約4割だと思います。（その他記号や数字は1~2%かと）",
"## 引用元\n- URL\n- URL\n- URL\n- URL",
"## 設定\nvocab_size=51,200（語彙サイズ）<br>\ncharacter_coverage=0.9995（文字のカバー率99.95%）<br>\nmodel_type=\"unigram\"（アルゴリズム）<br>\nnormalization=\"identity\"（正規化なし）<br>\nbyte_fallback=True（バイト変換あり）<br>\nsplit_digits=True（数字分割あり）<br>\nallow_whitespace_only_pieces=True（空白のトークンを許可する）<br>\nremove_extra_whitespaces=True（余分な空白の削除あり）<br>",
"## 形式\nLlamaTokenizer<br>\n※encode時に文頭にbos_tokenである\"\\<s\\>\"トークンが付きます。",
"# 使い方"
] | [
"TAGS\n#region-us \n",
"# 説明\nwikipedia, mbpp, grade-school-mathで学習したトークナイザー。",
"## 学習に使ったデータ\n英語：1.33GB (wiki40b)<br>\n日本語：1.78GB (wiki40b) ※形態素単位で\"||||\"で事前分割してsentencepieceの学習時にpretokenization_delimiterを設定。<br>\nコード：172KB (mbpp) <br>\n数学：2.1MB (grade-school-math)",
"## 語彙の割合\n概算ですが、アルファベットが約6割、日本語が約4割だと思います。（その他記号や数字は1~2%かと）",
"## 引用元\n- URL\n- URL\n- URL\n- URL",
"## 設定\nvocab_size=51,200（語彙サイズ）<br>\ncharacter_coverage=0.9995（文字のカバー率99.95%）<br>\nmodel_type=\"unigram\"（アルゴリズム）<br>\nnormalization=\"identity\"（正規化なし）<br>\nbyte_fallback=True（バイト変換あり）<br>\nsplit_digits=True（数字分割あり）<br>\nallow_whitespace_only_pieces=True（空白のトークンを許可する）<br>\nremove_extra_whitespaces=True（余分な空白の削除あり）<br>",
"## 形式\nLlamaTokenizer<br>\n※encode時に文頭にbos_tokenである\"\\<s\\>\"トークンが付きます。",
"# 使い方"
] |
text-generation | null |
## 💫 Community Model> Llama 3 8B Instruct by Meta
**Model creator:** [meta-llama](https://huggingface.co/meta-llama)<br>
**Original model**: [Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct)<br>
**GGUF quantization:** provided by [professorf](https://huggingface.co/professorf) based on `llama.cpp` PR [6745](https://github.com/ggerganov/llama.cpp/pull/6745)<br>
## Model Summary:
Llama 3 represents a huge update to the Llama family of models. This model is the 8B parameter instruction tuned model, meaning it's small, fast, and tuned for following instructions.<br>
This model is very happy to follow the given system prompt, so use this to your advantage to get the behavior you desire.<br>
Llama 3 excels at all the general usage situations, including multi turn conversations, general world knowledge, and coding.<br>
This 8B model exceeds the performance of Llama 2's 70B model, showing that the performance is far greater than the previous iteration.
## Prompt Template:
Choose the 'Llama 3' preset in your LM Studio.
Under the hood, the model will see a prompt that's formatted like so:
```
<|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|>
```
## Use case and examples
Llama 3 should be great for anything you throw at it. Try it with conversations, coding, and just all around general inquiries.
## Creative conversations
Using a system prompt of `You are a pirate chatbot who always responds in pirate speak!`
## General knowledge
## Coding
## Technical Details
Llama 3 was trained on over 15T tokens from a massively diverse range of subjects and languages, and includes 4 times more code than Llama 2.
This model also features Grouped Attention Query (GQA) so that memory usage scales nicely over large contexts.
Instruction fine tuning was performed with a combination of supervised fine-tuning (SFT), rejection sampling, proximal policy optimization (PPO), and direct policy optimization (DPO).
Check out their blog post for more information [here](https://ai.meta.com/blog/meta-llama-3/)
## Special thanks
🙏 Special thanks to [Georgi Gerganov](https://github.com/ggerganov) and the whole team working on [llama.cpp](https://github.com/ggerganov/llama.cpp/) for making all of this possible.
🙏 Special thanks to [Kalomaze](https://github.com/kalomaze) for his dataset (linked [here](https://github.com/ggerganov/llama.cpp/discussions/5263)) that was used for calculating the imatrix for these quants, which improves the overall quality!
## Disclaimers
ProfessoF does not endorse, support, represent or guarantee the completeness, truthfulness, accuracy, or reliability of any Community Model. You understand that Community Models can produce content that might be offensive, harmful, inaccurate or otherwise inappropriate, or deceptive. Each Community Model is the sole responsibility of the person or entity who originated such Model. ProfessorF may not monitor or control the Community Models and cannot, and does not, take responsibility for any such Model. ProfessorF disclaims all warranties or guarantees about the accuracy, reliability or benefits of the Community Models. ProfessorF further disclaims any warranty that the Community Model will meet your requirements, be secure, uninterrupted or available at any time or location, or error-free, viruses-free, or that any errors will be corrected, or otherwise. You will be solely responsible for any damage resulting from your use of or access to the Community Models, your downloading of any Community Model, or use of any other Community Model provided by or through ProfessorF.
| {"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": "ProfessorF", "lm_studio": {"param_count": "8b", "use_case": "general", "release_date": "18-04-2024", "model_creator": "meta-llama", "prompt_template": "Llama 3", "system_prompt": "You are a helpful AI assistant.", "base_model": "llama", "original_repo": "meta-llama/Meta-Llama-3-8B-Instruct"}} | professorf/Meta-Llama-3-8B-Instruct-gguf | null | [
"gguf",
"facebook",
"meta",
"pytorch",
"llama",
"llama-3",
"text-generation",
"en",
"license:other",
"region:us"
] | null | 2024-04-20T00:20:21+00:00 | [] | [
"en"
] | TAGS
#gguf #facebook #meta #pytorch #llama #llama-3 #text-generation #en #license-other #region-us
|
## Community Model> Llama 3 8B Instruct by Meta
Model creator: meta-llama<br>
Original model: Meta-Llama-3-8B-Instruct<br>
GGUF quantization: provided by professorf based on 'URL' PR 6745<br>
## Model Summary:
Llama 3 represents a huge update to the Llama family of models. This model is the 8B parameter instruction tuned model, meaning it's small, fast, and tuned for following instructions.<br>
This model is very happy to follow the given system prompt, so use this to your advantage to get the behavior you desire.<br>
Llama 3 excels at all the general usage situations, including multi turn conversations, general world knowledge, and coding.<br>
This 8B model exceeds the performance of Llama 2's 70B model, showing that the performance is far greater than the previous iteration.
## Prompt Template:
Choose the 'Llama 3' preset in your LM Studio.
Under the hood, the model will see a prompt that's formatted like so:
## Use case and examples
Llama 3 should be great for anything you throw at it. Try it with conversations, coding, and just all around general inquiries.
## Creative conversations
Using a system prompt of 'You are a pirate chatbot who always responds in pirate speak!'
!image/png
## General knowledge
!image/png
## Coding
!image/png
## Technical Details
Llama 3 was trained on over 15T tokens from a massively diverse range of subjects and languages, and includes 4 times more code than Llama 2.
This model also features Grouped Attention Query (GQA) so that memory usage scales nicely over large contexts.
Instruction fine tuning was performed with a combination of supervised fine-tuning (SFT), rejection sampling, proximal policy optimization (PPO), and direct policy optimization (DPO).
Check out their blog post for more information here
## Special thanks
Special thanks to Georgi Gerganov and the whole team working on URL for making all of this possible.
Special thanks to Kalomaze for his dataset (linked here) that was used for calculating the imatrix for these quants, which improves the overall quality!
## Disclaimers
ProfessoF does not endorse, support, represent or guarantee the completeness, truthfulness, accuracy, or reliability of any Community Model. You understand that Community Models can produce content that might be offensive, harmful, inaccurate or otherwise inappropriate, or deceptive. Each Community Model is the sole responsibility of the person or entity who originated such Model. ProfessorF may not monitor or control the Community Models and cannot, and does not, take responsibility for any such Model. ProfessorF disclaims all warranties or guarantees about the accuracy, reliability or benefits of the Community Models. ProfessorF further disclaims any warranty that the Community Model will meet your requirements, be secure, uninterrupted or available at any time or location, or error-free, viruses-free, or that any errors will be corrected, or otherwise. You will be solely responsible for any damage resulting from your use of or access to the Community Models, your downloading of any Community Model, or use of any other Community Model provided by or through ProfessorF.
| [
"## Community Model> Llama 3 8B Instruct by Meta\n\nModel creator: meta-llama<br>\nOriginal model: Meta-Llama-3-8B-Instruct<br>\nGGUF quantization: provided by professorf based on 'URL' PR 6745<br>",
"## Model Summary:\nLlama 3 represents a huge update to the Llama family of models. This model is the 8B parameter instruction tuned model, meaning it's small, fast, and tuned for following instructions.<br>\nThis model is very happy to follow the given system prompt, so use this to your advantage to get the behavior you desire.<br>\nLlama 3 excels at all the general usage situations, including multi turn conversations, general world knowledge, and coding.<br>\nThis 8B model exceeds the performance of Llama 2's 70B model, showing that the performance is far greater than the previous iteration.",
"## Prompt Template:\n\nChoose the 'Llama 3' preset in your LM Studio. \n\nUnder the hood, the model will see a prompt that's formatted like so:",
"## Use case and examples\n\nLlama 3 should be great for anything you throw at it. Try it with conversations, coding, and just all around general inquiries.",
"## Creative conversations\n\nUsing a system prompt of 'You are a pirate chatbot who always responds in pirate speak!'\n\n!image/png",
"## General knowledge\n\n!image/png",
"## Coding\n\n!image/png",
"## Technical Details\n\nLlama 3 was trained on over 15T tokens from a massively diverse range of subjects and languages, and includes 4 times more code than Llama 2.\n\nThis model also features Grouped Attention Query (GQA) so that memory usage scales nicely over large contexts.\n\nInstruction fine tuning was performed with a combination of supervised fine-tuning (SFT), rejection sampling, proximal policy optimization (PPO), and direct policy optimization (DPO).\n\nCheck out their blog post for more information here",
"## Special thanks\n\n Special thanks to Georgi Gerganov and the whole team working on URL for making all of this possible.\n\n Special thanks to Kalomaze for his dataset (linked here) that was used for calculating the imatrix for these quants, which improves the overall quality!",
"## Disclaimers\n\nProfessoF does not endorse, support, represent or guarantee the completeness, truthfulness, accuracy, or reliability of any Community Model. You understand that Community Models can produce content that might be offensive, harmful, inaccurate or otherwise inappropriate, or deceptive. Each Community Model is the sole responsibility of the person or entity who originated such Model. ProfessorF may not monitor or control the Community Models and cannot, and does not, take responsibility for any such Model. ProfessorF disclaims all warranties or guarantees about the accuracy, reliability or benefits of the Community Models. ProfessorF further disclaims any warranty that the Community Model will meet your requirements, be secure, uninterrupted or available at any time or location, or error-free, viruses-free, or that any errors will be corrected, or otherwise. You will be solely responsible for any damage resulting from your use of or access to the Community Models, your downloading of any Community Model, or use of any other Community Model provided by or through ProfessorF."
] | [
"TAGS\n#gguf #facebook #meta #pytorch #llama #llama-3 #text-generation #en #license-other #region-us \n",
"## Community Model> Llama 3 8B Instruct by Meta\n\nModel creator: meta-llama<br>\nOriginal model: Meta-Llama-3-8B-Instruct<br>\nGGUF quantization: provided by professorf based on 'URL' PR 6745<br>",
"## Model Summary:\nLlama 3 represents a huge update to the Llama family of models. This model is the 8B parameter instruction tuned model, meaning it's small, fast, and tuned for following instructions.<br>\nThis model is very happy to follow the given system prompt, so use this to your advantage to get the behavior you desire.<br>\nLlama 3 excels at all the general usage situations, including multi turn conversations, general world knowledge, and coding.<br>\nThis 8B model exceeds the performance of Llama 2's 70B model, showing that the performance is far greater than the previous iteration.",
"## Prompt Template:\n\nChoose the 'Llama 3' preset in your LM Studio. \n\nUnder the hood, the model will see a prompt that's formatted like so:",
"## Use case and examples\n\nLlama 3 should be great for anything you throw at it. Try it with conversations, coding, and just all around general inquiries.",
"## Creative conversations\n\nUsing a system prompt of 'You are a pirate chatbot who always responds in pirate speak!'\n\n!image/png",
"## General knowledge\n\n!image/png",
"## Coding\n\n!image/png",
"## Technical Details\n\nLlama 3 was trained on over 15T tokens from a massively diverse range of subjects and languages, and includes 4 times more code than Llama 2.\n\nThis model also features Grouped Attention Query (GQA) so that memory usage scales nicely over large contexts.\n\nInstruction fine tuning was performed with a combination of supervised fine-tuning (SFT), rejection sampling, proximal policy optimization (PPO), and direct policy optimization (DPO).\n\nCheck out their blog post for more information here",
"## Special thanks\n\n Special thanks to Georgi Gerganov and the whole team working on URL for making all of this possible.\n\n Special thanks to Kalomaze for his dataset (linked here) that was used for calculating the imatrix for these quants, which improves the overall quality!",
"## Disclaimers\n\nProfessoF does not endorse, support, represent or guarantee the completeness, truthfulness, accuracy, or reliability of any Community Model. You understand that Community Models can produce content that might be offensive, harmful, inaccurate or otherwise inappropriate, or deceptive. Each Community Model is the sole responsibility of the person or entity who originated such Model. ProfessorF may not monitor or control the Community Models and cannot, and does not, take responsibility for any such Model. ProfessorF disclaims all warranties or guarantees about the accuracy, reliability or benefits of the Community Models. ProfessorF further disclaims any warranty that the Community Model will meet your requirements, be secure, uninterrupted or available at any time or location, or error-free, viruses-free, or that any errors will be corrected, or otherwise. You will be solely responsible for any damage resulting from your use of or access to the Community Models, your downloading of any Community Model, or use of any other Community Model provided by or through ProfessorF."
] |
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": []} | zzttbrdd/sn6_02l | null | [
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-04-20T00:26:16+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"
] |
null | peft | ## Training procedure
The following `bitsandbytes` quantization config was used during training:
- quant_method: bitsandbytes
- _load_in_8bit: False
- _load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: True
- bnb_4bit_compute_dtype: float16
- bnb_4bit_quant_storage: uint8
- load_in_4bit: True
- load_in_8bit: False
### Framework versions
- PEFT 0.5.0
# Open Portuguese LLM Leaderboard Evaluation Results
Detailed results can be found [here](https://huggingface.co/datasets/eduagarcia-temp/llm_pt_leaderboard_raw_results/tree/main/recogna-nlp/gembode-7b-it) and on the [🚀 Open Portuguese LLM Leaderboard](https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard)
| Metric | Value |
|--------------------------|--------|
|Average |**60.6**|
|ENEM Challenge (No Images)| 49.34|
|BLUEX (No Images) | 36.58|
|OAB Exams | 34.76|
|Assin2 RTE | 79.09|
|Assin2 STS | 64.95|
|FaQuAD NLI | 64.67|
|HateBR Binary | 86.27|
|PT Hate Speech Binary | 63.61|
|tweetSentBR | 66.17|
| {"library_name": "peft", "model-index": [{"name": "gembode-7b-it", "results": [{"task": {"type": "text-generation", "name": "Text Generation"}, "dataset": {"name": "ENEM Challenge (No Images)", "type": "eduagarcia/enem_challenge", "split": "train", "args": {"num_few_shot": 3}}, "metrics": [{"type": "acc", "value": 49.34, "name": "accuracy"}], "source": {"url": "https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=recogna-nlp/gembode-7b-it", "name": "Open Portuguese LLM Leaderboard"}}, {"task": {"type": "text-generation", "name": "Text Generation"}, "dataset": {"name": "BLUEX (No Images)", "type": "eduagarcia-temp/BLUEX_without_images", "split": "train", "args": {"num_few_shot": 3}}, "metrics": [{"type": "acc", "value": 36.58, "name": "accuracy"}], "source": {"url": "https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=recogna-nlp/gembode-7b-it", "name": "Open Portuguese LLM Leaderboard"}}, {"task": {"type": "text-generation", "name": "Text Generation"}, "dataset": {"name": "OAB Exams", "type": "eduagarcia/oab_exams", "split": "train", "args": {"num_few_shot": 3}}, "metrics": [{"type": "acc", "value": 34.76, "name": "accuracy"}], "source": {"url": "https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=recogna-nlp/gembode-7b-it", "name": "Open Portuguese LLM Leaderboard"}}, {"task": {"type": "text-generation", "name": "Text Generation"}, "dataset": {"name": "Assin2 RTE", "type": "assin2", "split": "test", "args": {"num_few_shot": 15}}, "metrics": [{"type": "f1_macro", "value": 79.09, "name": "f1-macro"}], "source": {"url": "https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=recogna-nlp/gembode-7b-it", "name": "Open Portuguese LLM Leaderboard"}}, {"task": {"type": "text-generation", "name": "Text Generation"}, "dataset": {"name": "Assin2 STS", "type": "eduagarcia/portuguese_benchmark", "split": "test", "args": {"num_few_shot": 15}}, "metrics": [{"type": "pearson", "value": 64.95, "name": "pearson"}], "source": {"url": "https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=recogna-nlp/gembode-7b-it", "name": "Open Portuguese LLM Leaderboard"}}, {"task": {"type": "text-generation", "name": "Text Generation"}, "dataset": {"name": "FaQuAD NLI", "type": "ruanchaves/faquad-nli", "split": "test", "args": {"num_few_shot": 15}}, "metrics": [{"type": "f1_macro", "value": 64.67, "name": "f1-macro"}], "source": {"url": "https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=recogna-nlp/gembode-7b-it", "name": "Open Portuguese LLM Leaderboard"}}, {"task": {"type": "text-generation", "name": "Text Generation"}, "dataset": {"name": "HateBR Binary", "type": "ruanchaves/hatebr", "split": "test", "args": {"num_few_shot": 25}}, "metrics": [{"type": "f1_macro", "value": 86.27, "name": "f1-macro"}], "source": {"url": "https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=recogna-nlp/gembode-7b-it", "name": "Open Portuguese LLM Leaderboard"}}, {"task": {"type": "text-generation", "name": "Text Generation"}, "dataset": {"name": "PT Hate Speech Binary", "type": "hate_speech_portuguese", "split": "test", "args": {"num_few_shot": 25}}, "metrics": [{"type": "f1_macro", "value": 63.61, "name": "f1-macro"}], "source": {"url": "https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=recogna-nlp/gembode-7b-it", "name": "Open Portuguese LLM Leaderboard"}}, {"task": {"type": "text-generation", "name": "Text Generation"}, "dataset": {"name": "tweetSentBR", "type": "eduagarcia/tweetsentbr_fewshot", "split": "test", "args": {"num_few_shot": 25}}, "metrics": [{"type": "f1_macro", "value": 66.17, "name": "f1-macro"}], "source": {"url": "https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=recogna-nlp/gembode-7b-it", "name": "Open Portuguese LLM Leaderboard"}}]}]} | recogna-nlp/gembode-7b-it | null | [
"peft",
"model-index",
"region:us"
] | null | 2024-04-20T00:34:26+00:00 | [] | [] | TAGS
#peft #model-index #region-us
| Training procedure
------------------
The following 'bitsandbytes' quantization config was used during training:
* quant\_method: bitsandbytes
* \_load\_in\_8bit: False
* \_load\_in\_4bit: True
* llm\_int8\_threshold: 6.0
* llm\_int8\_skip\_modules: None
* llm\_int8\_enable\_fp32\_cpu\_offload: False
* llm\_int8\_has\_fp16\_weight: False
* bnb\_4bit\_quant\_type: nf4
* bnb\_4bit\_use\_double\_quant: True
* bnb\_4bit\_compute\_dtype: float16
* bnb\_4bit\_quant\_storage: uint8
* load\_in\_4bit: True
* load\_in\_8bit: False
### Framework versions
* PEFT 0.5.0
Open Portuguese LLM Leaderboard Evaluation Results
==================================================
Detailed results can be found here and on the Open Portuguese LLM Leaderboard
| [
"### Framework versions\n\n\n* PEFT 0.5.0\n\n\nOpen Portuguese LLM Leaderboard Evaluation Results\n==================================================\n\n\nDetailed results can be found here and on the Open Portuguese LLM Leaderboard"
] | [
"TAGS\n#peft #model-index #region-us \n",
"### Framework versions\n\n\n* PEFT 0.5.0\n\n\nOpen Portuguese LLM Leaderboard Evaluation Results\n==================================================\n\n\nDetailed results can be found here and on the Open Portuguese LLM Leaderboard"
] |
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": []} | hemanth992/gemma-2b-mt-German-to-English | null | [
"transformers",
"safetensors",
"gemma",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-04-20T00:36:22+00:00 | [
"1910.09700"
] | [] | TAGS
#transformers #safetensors #gemma #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 #gemma #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 |
# Model Card for Model ID
Optimum GPTQ quantized 8-bit version of Mixtral-8x22B-Instruct-v0.1 \
WIP - do not use currently \
See original model card for more information.
# How to load
| {"library_name": "transformers", "tags": []} | jarrelscy/Mixtral-8x22B-Instruct-v0.1-GPTQ-4bit | null | [
"transformers",
"safetensors",
"mixtral",
"text-generation",
"conversational",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"4-bit",
"region:us"
] | null | 2024-04-20T00:37:38+00:00 | [] | [] | TAGS
#transformers #safetensors #mixtral #text-generation #conversational #autotrain_compatible #endpoints_compatible #text-generation-inference #4-bit #region-us
|
# Model Card for Model ID
Optimum GPTQ quantized 8-bit version of Mixtral-8x22B-Instruct-v0.1 \
WIP - do not use currently \
See original model card for more information.
# How to load
| [
"# Model Card for Model ID\n\nOptimum GPTQ quantized 8-bit version of Mixtral-8x22B-Instruct-v0.1 \\\nWIP - do not use currently \\\nSee original model card for more information.",
"# How to load"
] | [
"TAGS\n#transformers #safetensors #mixtral #text-generation #conversational #autotrain_compatible #endpoints_compatible #text-generation-inference #4-bit #region-us \n",
"# Model Card for Model ID\n\nOptimum GPTQ quantized 8-bit version of Mixtral-8x22B-Instruct-v0.1 \\\nWIP - do not use currently \\\nSee original model card for more information.",
"# How to load"
] |
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": []} | domenicrosati/adversarial_loss_lr_1e-5_attack_meta-llama_Llama-2-7b-chat-hf_4_8e-5_10k | null | [
"transformers",
"safetensors",
"llama",
"text-generation",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-04-20T00:38:28+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"
] |
text-to-image | diffusers |
<!-- This model card has been generated automatically according to the information the training script had access to. You
should probably proofread and complete it, then remove this comment. -->
# SDXL LoRA DreamBooth - yehiaa/RealVisXL_V4.0-lora-drew-v1
<Gallery />
## Model description
These are yehiaa/RealVisXL_V4.0-lora-drew-v1 LoRA adaption weights for SG161222/RealVisXL_V4.0.
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 a portrait of a sks person to trigger the image generation.
## Download model
Weights for this model are available in Safetensors format.
[Download](yehiaa/RealVisXL_V4.0-lora-drew-v1/tree/main) them in the Files & versions tab.
## Intended uses & limitations
#### How to use
```python
# TODO: add an example code snippet for running this diffusion pipeline
```
#### Limitations and bias
[TODO: provide examples of latent issues and potential remediations]
## Training details
[TODO: describe the data used to train the model] | {"license": "openrail++", "library_name": "diffusers", "tags": ["text-to-image", "text-to-image", "diffusers-training", "diffusers", "lora", "template:sd-lora", "stable-diffusion-xl", "stable-diffusion-xl-diffusers"], "base_model": "SG161222/RealVisXL_V4.0", "instance_prompt": "a portrait of a sks person", "widget": [{"text": "closeup portrait photo of a sks person in dark clothes, city street, neon, fog, volumetric wearing business outfit, grey background", "output": {"url": "image_0.png"}}, {"text": "closeup portrait photo of a sks person in dark clothes, city street, neon, fog, volumetric wearing business outfit, grey background", "output": {"url": "image_1.png"}}, {"text": "closeup portrait photo of a sks person in dark clothes, city street, neon, fog, volumetric wearing business outfit, grey background", "output": {"url": "image_2.png"}}, {"text": "closeup portrait photo of a sks person in dark clothes, city street, neon, fog, volumetric wearing business outfit, grey background", "output": {"url": "image_3.png"}}]} | yehiaa/RealVisXL_V4.0-lora-drew-v1 | null | [
"diffusers",
"text-to-image",
"diffusers-training",
"lora",
"template:sd-lora",
"stable-diffusion-xl",
"stable-diffusion-xl-diffusers",
"base_model:SG161222/RealVisXL_V4.0",
"license:openrail++",
"region:us"
] | null | 2024-04-20T00:41:20+00:00 | [] | [] | TAGS
#diffusers #text-to-image #diffusers-training #lora #template-sd-lora #stable-diffusion-xl #stable-diffusion-xl-diffusers #base_model-SG161222/RealVisXL_V4.0 #license-openrail++ #region-us
|
# SDXL LoRA DreamBooth - yehiaa/RealVisXL_V4.0-lora-drew-v1
<Gallery />
## Model description
These are yehiaa/RealVisXL_V4.0-lora-drew-v1 LoRA adaption weights for SG161222/RealVisXL_V4.0.
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 a portrait of a sks person to trigger the image generation.
## Download model
Weights for this model are available in Safetensors format.
Download them in the Files & versions tab.
## Intended uses & limitations
#### How to use
#### Limitations and bias
[TODO: provide examples of latent issues and potential remediations]
## Training details
[TODO: describe the data used to train the model] | [
"# SDXL LoRA DreamBooth - yehiaa/RealVisXL_V4.0-lora-drew-v1\n\n<Gallery />",
"## Model description\n\nThese are yehiaa/RealVisXL_V4.0-lora-drew-v1 LoRA adaption weights for SG161222/RealVisXL_V4.0.\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 a portrait of a sks person 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.",
"## Intended uses & limitations",
"#### How to use",
"#### Limitations and bias\n\n[TODO: provide examples of latent issues and potential remediations]",
"## Training details\n\n[TODO: describe the data used to train the model]"
] | [
"TAGS\n#diffusers #text-to-image #diffusers-training #lora #template-sd-lora #stable-diffusion-xl #stable-diffusion-xl-diffusers #base_model-SG161222/RealVisXL_V4.0 #license-openrail++ #region-us \n",
"# SDXL LoRA DreamBooth - yehiaa/RealVisXL_V4.0-lora-drew-v1\n\n<Gallery />",
"## Model description\n\nThese are yehiaa/RealVisXL_V4.0-lora-drew-v1 LoRA adaption weights for SG161222/RealVisXL_V4.0.\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 a portrait of a sks person 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.",
"## Intended uses & limitations",
"#### How to use",
"#### Limitations and bias\n\n[TODO: provide examples of latent issues and potential remediations]",
"## Training details\n\n[TODO: describe the data used to train the model]"
] |
null | adapter-transformers |
# Adapter `BigTMiami/seq_bn_micro_help_class_no_pretrain_lr_0002_0_adapter` for roberta-base
An [adapter](https://adapterhub.ml) for the `roberta-base` model that was trained on the [BigTMiami/amazon_MICRO_helpfulness_dataset](https://huggingface.co/datasets/BigTMiami/amazon_MICRO_helpfulness_dataset/) dataset and includes a prediction head for classification.
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/seq_bn_micro_help_class_no_pretrain_lr_0002_0_adapter", source="hf", set_active=True)
```
## Architecture & Training
<!-- Add some description here -->
## Evaluation results
<!-- Add some description here -->
## Citation
<!-- Add some description here --> | {"tags": ["roberta", "adapter-transformers"], "datasets": ["BigTMiami/amazon_MICRO_helpfulness_dataset"]} | BigTMiami/seq_bn_micro_help_class_no_pretrain_lr_0002_0_adapter | null | [
"adapter-transformers",
"roberta",
"dataset:BigTMiami/amazon_MICRO_helpfulness_dataset",
"region:us"
] | null | 2024-04-20T00:42:05+00:00 | [] | [] | TAGS
#adapter-transformers #roberta #dataset-BigTMiami/amazon_MICRO_helpfulness_dataset #region-us
|
# Adapter 'BigTMiami/seq_bn_micro_help_class_no_pretrain_lr_0002_0_adapter' for roberta-base
An adapter for the 'roberta-base' model that was trained on the BigTMiami/amazon_MICRO_helpfulness_dataset dataset and includes a prediction head for classification.
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/seq_bn_micro_help_class_no_pretrain_lr_0002_0_adapter' for roberta-base\n\nAn adapter for the 'roberta-base' model that was trained on the BigTMiami/amazon_MICRO_helpfulness_dataset dataset and includes a prediction head for classification.\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 #region-us \n",
"# Adapter 'BigTMiami/seq_bn_micro_help_class_no_pretrain_lr_0002_0_adapter' for roberta-base\n\nAn adapter for the 'roberta-base' model that was trained on the BigTMiami/amazon_MICRO_helpfulness_dataset dataset and includes a prediction head for classification.\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 | peft | ## Training procedure
The following `bitsandbytes` quantization config was used during training:
- quant_method: bitsandbytes
- _load_in_8bit: False
- _load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: True
- bnb_4bit_compute_dtype: float16
- bnb_4bit_quant_storage: uint8
- load_in_4bit: True
- load_in_8bit: False
### Framework versions
- PEFT 0.5.0
| {"library_name": "peft"} | recogna-nlp/gembode-2b-ultraalpaca-qlora | null | [
"peft",
"has_space",
"region:us"
] | null | 2024-04-20T00:43:00+00:00 | [] | [] | TAGS
#peft #has_space #region-us
| ## Training procedure
The following 'bitsandbytes' quantization config was used during training:
- quant_method: bitsandbytes
- _load_in_8bit: False
- _load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: True
- bnb_4bit_compute_dtype: float16
- bnb_4bit_quant_storage: uint8
- load_in_4bit: True
- load_in_8bit: False
### Framework versions
- PEFT 0.5.0
| [
"## Training procedure\n\n\nThe following 'bitsandbytes' quantization config was used during training:\n- quant_method: bitsandbytes\n- _load_in_8bit: False\n- _load_in_4bit: True\n- llm_int8_threshold: 6.0\n- llm_int8_skip_modules: None\n- llm_int8_enable_fp32_cpu_offload: False\n- llm_int8_has_fp16_weight: False\n- bnb_4bit_quant_type: nf4\n- bnb_4bit_use_double_quant: True\n- bnb_4bit_compute_dtype: float16\n- bnb_4bit_quant_storage: uint8\n- load_in_4bit: True\n- load_in_8bit: False",
"### Framework versions\n\n\n- PEFT 0.5.0"
] | [
"TAGS\n#peft #has_space #region-us \n",
"## Training procedure\n\n\nThe following 'bitsandbytes' quantization config was used during training:\n- quant_method: bitsandbytes\n- _load_in_8bit: False\n- _load_in_4bit: True\n- llm_int8_threshold: 6.0\n- llm_int8_skip_modules: None\n- llm_int8_enable_fp32_cpu_offload: False\n- llm_int8_has_fp16_weight: False\n- bnb_4bit_quant_type: nf4\n- bnb_4bit_use_double_quant: True\n- bnb_4bit_compute_dtype: float16\n- bnb_4bit_quant_storage: uint8\n- load_in_4bit: True\n- load_in_8bit: False",
"### Framework versions\n\n\n- PEFT 0.5.0"
] |
sentence-similarity | sentence-transformers |
# Akshayxx/citeseer-finetuned-embeddingsV2
This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search.
<!--- Describe your model here -->
## Usage (Sentence-Transformers)
Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
```
pip install -U sentence-transformers
```
Then you can use the model like this:
```python
from sentence_transformers import SentenceTransformer
sentences = ["This is an example sentence", "Each sentence is converted"]
model = SentenceTransformer('Akshayxx/citeseer-finetuned-embeddingsV2')
embeddings = model.encode(sentences)
print(embeddings)
```
## Usage (HuggingFace Transformers)
Without [sentence-transformers](https://www.SBERT.net), you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings.
```python
from transformers import AutoTokenizer, AutoModel
import torch
#Mean Pooling - Take attention mask into account for correct averaging
def mean_pooling(model_output, attention_mask):
token_embeddings = model_output[0] #First element of model_output contains all token embeddings
input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)
# Sentences we want sentence embeddings for
sentences = ['This is an example sentence', 'Each sentence is converted']
# Load model from HuggingFace Hub
tokenizer = AutoTokenizer.from_pretrained('Akshayxx/citeseer-finetuned-embeddingsV2')
model = AutoModel.from_pretrained('Akshayxx/citeseer-finetuned-embeddingsV2')
# Tokenize sentences
encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
# Compute token embeddings
with torch.no_grad():
model_output = model(**encoded_input)
# Perform pooling. In this case, mean pooling.
sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])
print("Sentence embeddings:")
print(sentence_embeddings)
```
## Evaluation Results
<!--- Describe how your model was evaluated -->
For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name=Akshayxx/citeseer-finetuned-embeddingsV2)
## Training
The model was trained with the parameters:
**DataLoader**:
`torch.utils.data.dataloader.DataLoader` of length 149 with parameters:
```
{'batch_size': 8, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}
```
**Loss**:
`sentence_transformers.losses.MultipleNegativesRankingLoss.MultipleNegativesRankingLoss` with parameters:
```
{'scale': 20.0, 'similarity_fct': 'cos_sim'}
```
Parameters of the fit()-Method:
```
{
"epochs": 3,
"evaluation_steps": 0,
"evaluator": "NoneType",
"max_grad_norm": 1,
"optimizer_class": "<class 'torch.optim.adamw.AdamW'>",
"optimizer_params": {
"lr": 2e-05
},
"scheduler": "WarmupLinear",
"steps_per_epoch": null,
"warmup_steps": 44,
"weight_decay": 0.01
}
```
## Full Model Architecture
```
SentenceTransformer(
(0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: BertModel
(1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
)
```
## Citing & Authors
<!--- Describe where people can find more information --> | {"library_name": "sentence-transformers", "tags": ["sentence-transformers", "feature-extraction", "sentence-similarity", "transformers"], "pipeline_tag": "sentence-similarity"} | Akshayxx/citeseer-finetuned-embeddingsV2 | null | [
"sentence-transformers",
"safetensors",
"bert",
"feature-extraction",
"sentence-similarity",
"transformers",
"endpoints_compatible",
"region:us"
] | null | 2024-04-20T00:45:46+00:00 | [] | [] | TAGS
#sentence-transformers #safetensors #bert #feature-extraction #sentence-similarity #transformers #endpoints_compatible #region-us
|
# Akshayxx/citeseer-finetuned-embeddingsV2
This is a sentence-transformers model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search.
## Usage (Sentence-Transformers)
Using this model becomes easy when you have sentence-transformers installed:
Then you can use the model like this:
## Usage (HuggingFace Transformers)
Without sentence-transformers, you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings.
## Evaluation Results
For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: URL
## Training
The model was trained with the parameters:
DataLoader:
'URL.dataloader.DataLoader' of length 149 with parameters:
Loss:
'sentence_transformers.losses.MultipleNegativesRankingLoss.MultipleNegativesRankingLoss' with parameters:
Parameters of the fit()-Method:
## Full Model Architecture
## Citing & Authors
| [
"# Akshayxx/citeseer-finetuned-embeddingsV2\n\nThis is a sentence-transformers model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search.",
"## Usage (Sentence-Transformers)\n\nUsing this model becomes easy when you have sentence-transformers installed:\n\n\n\nThen you can use the model like this:",
"## Usage (HuggingFace Transformers)\nWithout sentence-transformers, you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings.",
"## Evaluation Results\n\n\n\nFor an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: URL",
"## Training\nThe model was trained with the parameters:\n\nDataLoader:\n\n'URL.dataloader.DataLoader' of length 149 with parameters:\n\n\nLoss:\n\n'sentence_transformers.losses.MultipleNegativesRankingLoss.MultipleNegativesRankingLoss' with parameters:\n \n\nParameters of the fit()-Method:",
"## Full Model Architecture",
"## Citing & Authors"
] | [
"TAGS\n#sentence-transformers #safetensors #bert #feature-extraction #sentence-similarity #transformers #endpoints_compatible #region-us \n",
"# Akshayxx/citeseer-finetuned-embeddingsV2\n\nThis is a sentence-transformers model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search.",
"## Usage (Sentence-Transformers)\n\nUsing this model becomes easy when you have sentence-transformers installed:\n\n\n\nThen you can use the model like this:",
"## Usage (HuggingFace Transformers)\nWithout sentence-transformers, you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings.",
"## Evaluation Results\n\n\n\nFor an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: URL",
"## Training\nThe model was trained with the parameters:\n\nDataLoader:\n\n'URL.dataloader.DataLoader' of length 149 with parameters:\n\n\nLoss:\n\n'sentence_transformers.losses.MultipleNegativesRankingLoss.MultipleNegativesRankingLoss' with parameters:\n \n\nParameters of the fit()-Method:",
"## Full Model Architecture",
"## Citing & Authors"
] |
null | adapter-transformers |
# Adapter `BigTMiami/micro_seq_bn_help_class_adp_lr_0002_seed_0` for roberta-base
An [adapter](https://adapterhub.ml) for the `roberta-base` model that was trained on the [BigTMiami/amazon_MICRO_helpfulness_dataset](https://huggingface.co/datasets/BigTMiami/amazon_MICRO_helpfulness_dataset/) dataset and includes a prediction head for classification.
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_seq_bn_help_class_adp_lr_0002_seed_0", 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"]} | BigTMiami/micro_seq_bn_help_class_adp_lr_0002_seed_0 | null | [
"adapter-transformers",
"roberta",
"dataset:BigTMiami/amazon_MICRO_helpfulness_dataset",
"region:us"
] | null | 2024-04-20T00:46:39+00:00 | [] | [] | TAGS
#adapter-transformers #roberta #dataset-BigTMiami/amazon_MICRO_helpfulness_dataset #region-us
|
# Adapter 'BigTMiami/micro_seq_bn_help_class_adp_lr_0002_seed_0' for roberta-base
An adapter for the 'roberta-base' model that was trained on the BigTMiami/amazon_MICRO_helpfulness_dataset dataset and includes a prediction head for classification.
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_seq_bn_help_class_adp_lr_0002_seed_0' for roberta-base\n\nAn adapter for the 'roberta-base' model that was trained on the BigTMiami/amazon_MICRO_helpfulness_dataset dataset and includes a prediction head for classification.\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 #region-us \n",
"# Adapter 'BigTMiami/micro_seq_bn_help_class_adp_lr_0002_seed_0' for roberta-base\n\nAn adapter for the 'roberta-base' model that was trained on the BigTMiami/amazon_MICRO_helpfulness_dataset dataset and includes a prediction head for classification.\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 | peft | ## Training procedure
### Framework versions
- PEFT 0.4.0
| {"library_name": "peft"} | QinyuZhao1116/LVLM-LP-Retrained-LLaVA | null | [
"peft",
"llava",
"region:us"
] | null | 2024-04-20T00:47:42+00:00 | [] | [] | TAGS
#peft #llava #region-us
| ## Training procedure
### Framework versions
- PEFT 0.4.0
| [
"## Training procedure",
"### Framework versions\n\n\n- PEFT 0.4.0"
] | [
"TAGS\n#peft #llava #region-us \n",
"## Training procedure",
"### Framework versions\n\n\n- PEFT 0.4.0"
] |
null | adapter-transformers |
# Adapter `BigTMiami/seq_bn_micro_help_class_no_pretrain_lr_0002_1_adapter` for roberta-base
An [adapter](https://adapterhub.ml) for the `roberta-base` model that was trained on the [BigTMiami/amazon_MICRO_helpfulness_dataset](https://huggingface.co/datasets/BigTMiami/amazon_MICRO_helpfulness_dataset/) dataset and includes a prediction head for classification.
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/seq_bn_micro_help_class_no_pretrain_lr_0002_1_adapter", source="hf", set_active=True)
```
## Architecture & Training
<!-- Add some description here -->
## Evaluation results
<!-- Add some description here -->
## Citation
<!-- Add some description here --> | {"tags": ["roberta", "adapter-transformers"], "datasets": ["BigTMiami/amazon_MICRO_helpfulness_dataset"]} | BigTMiami/seq_bn_micro_help_class_no_pretrain_lr_0002_1_adapter | null | [
"adapter-transformers",
"roberta",
"dataset:BigTMiami/amazon_MICRO_helpfulness_dataset",
"region:us"
] | null | 2024-04-20T00:52:42+00:00 | [] | [] | TAGS
#adapter-transformers #roberta #dataset-BigTMiami/amazon_MICRO_helpfulness_dataset #region-us
|
# Adapter 'BigTMiami/seq_bn_micro_help_class_no_pretrain_lr_0002_1_adapter' for roberta-base
An adapter for the 'roberta-base' model that was trained on the BigTMiami/amazon_MICRO_helpfulness_dataset dataset and includes a prediction head for classification.
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/seq_bn_micro_help_class_no_pretrain_lr_0002_1_adapter' for roberta-base\n\nAn adapter for the 'roberta-base' model that was trained on the BigTMiami/amazon_MICRO_helpfulness_dataset dataset and includes a prediction head for classification.\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 #region-us \n",
"# Adapter 'BigTMiami/seq_bn_micro_help_class_no_pretrain_lr_0002_1_adapter' for roberta-base\n\nAn adapter for the 'roberta-base' model that was trained on the BigTMiami/amazon_MICRO_helpfulness_dataset dataset and includes a prediction head for classification.\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-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": []} | dmvaldman/showerthought_mistral_rl | null | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-04-20T00:53:10+00:00 | [
"1910.09700"
] | [] | TAGS
#transformers #safetensors #mistral #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 #mistral #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"
] |
null | null | # BookRecSys
<!-- Provide a quick summary of what the model is/does. -->
A model for recommend book using TF-IDF Vectorizer | {"language": ["en"], "license": "unknown", "tags": ["code"]} | SurgeousJP/BookRecSys | null | [
"code",
"en",
"license:unknown",
"region:us"
] | null | 2024-04-20T00:53:32+00:00 | [] | [
"en"
] | TAGS
#code #en #license-unknown #region-us
| # BookRecSys
A model for recommend book using TF-IDF Vectorizer | [
"# BookRecSys\n\n\n\nA model for recommend book using TF-IDF Vectorizer"
] | [
"TAGS\n#code #en #license-unknown #region-us \n",
"# BookRecSys\n\n\n\nA model for recommend book using TF-IDF Vectorizer"
] |
text-generation | transformers |
<div align="center">
<img width="260px" src="https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/BrQCb95lmEIFz79QAmoNA.png"></div>
<div align="center">
<h1>Advancing Open-source Large Language Models in Medical Domain</h1>
</div>
<p align="center" style="margin-top: 0px;">
<a href="https://colab.research.google.com/drive/1F5oV20InEYeAJGmBwYF9NM_QhLmjBkKJ?usp=sharing">
<img src="https://colab.research.google.com/assets/colab-badge.svg" alt="OpenChat Logo" style="width:20px; vertical-align: middle; display: inline-block; margin-right: 5px; margin-left: 10px; margin-top: 0px; margin-bottom: 0px;"/>
<span class="link-text" style=" margin-right: 5px;">Online Demo</span>
</a> |
<a href="https://github.com/openlifescience-ai">
<img src="https://github.githubassets.com/assets/GitHub-Mark-ea2971cee799.png" alt="GitHub Logo" style="width:20px; vertical-align: middle; display: inline-block; margin-right: 5px; margin-left: 5px; margin-top: 0px; margin-bottom: 0px;"/>
<span class="link-text" style=" margin-right: 5px;">GitHub</span>
</a> |
<a href="#">
<img src="https://github.com/alpayariyak/openchat/blob/master/assets/arxiv-logomark-small-square-border.png?raw=true" alt="ArXiv Logo" style="width:20px; vertical-align: middle; display: inline-block; margin-right: 5px; margin-left: 5px; margin-top: 0px; margin-bottom: 0px;"/>
<span class="link-text" style="margin-right: 5px;">Paper</span>
</a> |
<a href="https://discord.gg/A5Fjf5zC69">
<img src="https://cloud.githubusercontent.com/assets/6291467/26705903/96c2d66e-477c-11e7-9f4e-f3c0efe96c9a.png" alt="Discord Logo" style="width:20px; vertical-align: middle; display: inline-block; margin-right: 5px; margin-left: 5px; margin-top: 0px; margin-bottom: 0px;"/>
<span class="link-text">Discord</span>
</a>
</p>
Introducing OpenBioLLM-8B: A State-of-the-Art Open Source Biomedical Large Language Model
OpenBioLLM-8B is an advanced open source language model designed specifically for the biomedical domain. Developed by Saama AI Labs, this model leverages cutting-edge techniques to achieve state-of-the-art performance on a wide range of biomedical tasks.
🏥 **Biomedical Specialization**: OpenBioLLM-8B is tailored for the unique language and knowledge requirements of the medical and life sciences fields. It was fine-tuned on a vast corpus of high-quality biomedical data, enabling it to understand and generate text with domain-specific accuracy and fluency.
🎓 **Superior Performance**: With 8 billion parameters, OpenBioLLM-8B outperforms other open source biomedical language models of similar scale. It has also demonstrated better results compared to larger proprietary & open-source models like GPT-3.5 and Meditron-70B on biomedical benchmarks.
🧠 **Advanced Training Techniques**: OpenBioLLM-8B builds upon the powerful foundations of the **Meta-Llama-3-8B** and [Meta-Llama-3-8B](meta-llama/Meta-Llama-3-8B) models. It incorporates the DPO dataset and fine-tuning recipe along with a custom diverse medical instruction dataset. Key components of the training pipeline include:
<div align="center">
<img width="1200px" src="https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/oPchsJsEpQoGcGXVbh7YS.png">
</div>
- **Policy Optimization**: [Direct Preference Optimization: Your Language Model is Secretly a Reward Model (DPO)](https://arxiv.org/abs/2305.18290)
- **Ranking Dataset**: [berkeley-nest/Nectar](https://huggingface.co/datasets/berkeley-nest/Nectar)
- **Fine-tuning dataset**: Custom Medical Instruct dataset (We plan to release a sample training dataset in our upcoming paper; please stay updated)
This combination of cutting-edge techniques enables OpenBioLLM-8B to align with key capabilities and preferences for biomedical applications.
⚙️ **Release Details**:
- **Model Size**: 8 billion parameters
- **Quantization**: Optimized quantized versions available [Here](https://huggingface.co/aaditya/OpenBioLLM-Llama3-8B-GGUF)
- **Language(s) (NLP):** en
- **Developed By**: [Ankit Pal (Aaditya Ura)](https://aadityaura.github.io/) from Saama AI Labs
- **License:** Meta-Llama License
- **Fine-tuned from models:** [meta-llama/Meta-Llama-3-8B](meta-llama/Meta-Llama-3-8B)
- **Resources for more information:**
- Paper: Coming soon
The model can be fine-tuned for more specialized tasks and datasets as needed.
OpenBioLLM-8B represents an important step forward in democratizing advanced language AI for the biomedical community. By leveraging state-of-the-art architectures and training techniques from leading open source efforts like Llama-3, we have created a powerful tool to accelerate innovation and discovery in healthcare and the life sciences.
We are excited to share OpenBioLLM-8B with researchers and developers around the world.
### Use with transformers
**Important: Please use the exact chat template provided by Llama-3 instruct version. Otherwise there will be a degradation in the performance. The model output can be verbose in rare cases. Please consider setting temperature = 0 to make this happen less.**
See the snippet below for usage with Transformers:
```python
import transformers
import torch
model_id = "aaditya/OpenBioLLM-Llama3-8B"
pipeline = transformers.pipeline(
"text-generation",
model=model_id,
model_kwargs={"torch_dtype": torch.bfloat16},
device="auto",
)
messages = [
{"role": "system", "content": "You are an expert and experienced from the healthcare and biomedical domain with extensive medical knowledge and practical experience. Your name is OpenBioLLM, and you were developed by Saama AI Labs. who's willing to help answer the user's query with explanation. In your explanation, leverage your deep medical expertise such as relevant anatomical structures, physiological processes, diagnostic criteria, treatment guidelines, or other pertinent medical concepts. Use precise medical terminology while still aiming to make the explanation clear and accessible to a general audience."},
{"role": "user", "content": "How can i split a 3mg or 4mg waefin pill so i can get a 2.5mg pill?"},
]
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=0.0,
top_p=0.9,
)
print(outputs[0]["generated_text"][len(prompt):])
```
## **Training procedure**
### **Training hyperparameters**
<details>
<summary>Click to see details</summary>
- learning_rate: 0.0002
- lr_scheduler: cosine
- train_batch_size: 12
- eval_batch_size: 8
- GPU: H100 80GB SXM5
- num_devices: 1
- optimizer: adamw_bnb_8bit
- lr_scheduler_warmup_steps: 100
- num_epochs: 4
</details>
### **Peft hyperparameters**
<details>
<summary>Click to see details</summary>
- adapter: qlora
- lora_r: 128
- lora_alpha: 256
- lora_dropout: 0.05
- lora_target_linear: true
-lora_target_modules:
- q_proj
- v_proj
- k_proj
- o_proj
- gate_proj
- down_proj
- up_proj
</details>
### **Training results**
### **Framework versions**
- Transformers 4.39.3
- Pytorch 2.1.2+cu121
- Datasets 2.18.0
- Tokenizers 0.15.1
- Axolotl
- Lm harness for evaluation
# Benchmark Results
🔥 OpenBioLLM-8B demonstrates superior performance compared to larger models, such as GPT-3.5, Meditron-70B across 9 diverse biomedical datasets, achieving state-of-the-art results with an average score of 72.50%, despite having a significantly smaller parameter count. The model's strong performance in domain-specific tasks, such as Clinical KG, Medical Genetics, and PubMedQA, highlights its ability to effectively capture and apply biomedical knowledge.
🚨 The GPT-4, Med-PaLM-1, and Med-PaLM-2 results are taken from their official papers. Since Med-PaLM doesn't provide zero-shot accuracy, we are using 5-shot accuracy from their paper for comparison. All results presented are in the zero-shot setting, except for Med-PaLM-2 and Med-PaLM-1, which use 5-shot accuracy.
| | Clinical KG | Medical Genetics | Anatomy | Pro Medicine | College Biology | College Medicine | MedQA 4 opts | PubMedQA | MedMCQA | Avg |
|--------------------|-------------|------------------|---------|--------------|-----------------|------------------|--------------|----------|---------|-------|
| **OpenBioLLM-70B** | **92.93** | **93.197** | **83.904** | 93.75 | 93.827 | **85.749** | 78.162 | 78.97 | **74.014** | **86.05588** |
| Med-PaLM-2 (5-shot) | 88.3 | 90 | 77.8 | **95.2** | 94.4 | 80.9 | **79.7** | **79.2** | 71.3 | 84.08 |
| **GPT-4** | 86.04 | 91 | 80 | 93.01 | **95.14** | 76.88 | 78.87 | 75.2 | 69.52 | 82.85 |
| Med-PaLM-1 (Flan-PaLM, 5-shot) | 80.4 | 75 | 63.7 | 83.8 | 88.9 | 76.3 | 67.6 | 79 | 57.6 | 74.7 |
| **OpenBioLLM-8B** | 76.101 | 86.1 | 69.829 | 78.21 | 84.213 | 68.042 | 58.993 | 74.12 | 56.913 | 72.502 |
| Gemini-1.0 | 76.7 | 75.8 | 66.7 | 77.7 | 88 | 69.2 | 58 | 70.7 | 54.3 | 70.79 |
| GPT-3.5 Turbo 1106 | 74.71 | 74 | 72.79 | 72.79 | 72.91 | 64.73 | 57.71 | 72.66 | 53.79 | 66 |
| Meditron-70B | 66.79 | 69 | 53.33 | 71.69 | 76.38 | 63 | 57.1 | 76.6 | 46.85 | 64.52 |
| gemma-7b | 69.81 | 70 | 59.26 | 66.18 | 79.86 | 60.12 | 47.21 | 76.2 | 48.96 | 64.18 |
| Mistral-7B-v0.1 | 68.68 | 71 | 55.56 | 68.38 | 68.06 | 59.54 | 50.82 | 75.4 | 48.2 | 62.85 |
| Apollo-7B | 62.26 | 72 | 61.48 | 69.12 | 70.83 | 55.49 | 55.22 | 39.8 | 53.77 | 60 |
| MedAlpaca-7b | 57.36 | 69 | 57.04 | 67.28 | 65.28 | 54.34 | 41.71 | 72.8 | 37.51 | 58.03 |
| BioMistral-7B | 59.9 | 64 | 56.5 | 60.4 | 59 | 54.7 | 50.6 | 77.5 | 48.1 | 57.3 |
| AlpaCare-llama2-7b | 49.81 | 49 | 45.92 | 33.82 | 50 | 43.35 | 29.77 | 72.2 | 34.42 | 45.36 |
| ClinicalGPT | 30.56 | 27 | 30.37 | 19.48 | 25 | 24.27 | 26.08 | 63.8 | 28.18 | 30.52 |
<div align="center">
<img width="1600px" src="https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/_SzdcJSBjZyo8RS1bTEkP.png">
</div>
## Detailed Medical Subjectwise accuracy
# Use Cases & Examples
🚨 **Below results are from the quantized version of OpenBioLLM-70B**
# Summarize Clinical Notes
OpenBioLLM-70B can efficiently analyze and summarize complex clinical notes, EHR data, and discharge summaries, extracting key information and generating concise, structured summaries
# Answer Medical Questions
OpenBioLLM-70B can provide answers to a wide range of medical questions.
<details>
<summary>Click to see details</summary>
</details>
# Clinical Entity Recognition
OpenBioLLM-70B can perform advanced clinical entity recognition by identifying and extracting key medical concepts, such as diseases, symptoms, medications, procedures, and anatomical structures, from unstructured clinical text. By leveraging its deep understanding of medical terminology and context, the model can accurately annotate and categorize clinical entities, enabling more efficient information retrieval, data analysis, and knowledge discovery from electronic health records, research articles, and other biomedical text sources. This capability can support various downstream applications, such as clinical decision support, pharmacovigilance, and medical research.
# Biomarkers Extraction
# Classification
OpenBioLLM-70B can perform various biomedical classification tasks, such as disease prediction, sentiment analysis, medical document categorization
# De-Identification
OpenBioLLM-70B can detect and remove personally identifiable information (PII) from medical records, ensuring patient privacy and compliance with data protection regulations like HIPAA.
**Advisory Notice!**
While OpenBioLLM-70B & 8B leverages high-quality data sources, its outputs may still contain inaccuracies, biases, or misalignments that could pose risks if relied upon for medical decision-making without further testing and refinement. The model's performance has not yet been rigorously evaluated in randomized controlled trials or real-world healthcare environments.
Therefore, we strongly advise against using OpenBioLLM-70B & 8B for any direct patient care, clinical decision support, or other professional medical purposes at this time. Its use should be limited to research, development, and exploratory applications by qualified individuals who understand its limitations.
OpenBioLLM-70B & 8B are intended solely as a research tool to assist healthcare professionals and should never be considered a replacement for the professional judgment and expertise of a qualified medical doctor.
Appropriately adapting and validating OpenBioLLM-70B & 8B for specific medical use cases would require significant additional work, potentially including:
- Thorough testing and evaluation in relevant clinical scenarios
- Alignment with evidence-based guidelines and best practices
- Mitigation of potential biases and failure modes
- Integration with human oversight and interpretation
- Compliance with regulatory and ethical standards
Always consult a qualified healthcare provider for personal medical needs.
# Citation
If you find OpenBioLLM-70B & 8B useful in your work, please cite the model as follows:
```
@misc{OpenBioLLMs,
author = {Ankit Pal, Malaikannan Sankarasubbu},
title = {OpenBioLLMs: Advancing Open-Source Large Language Models for Healthcare and Life Sciences},
year = {2024},
publisher = {Hugging Face},
journal = {Hugging Face repository},
howpublished = {\url{https://huggingface.co/aaditya/OpenBioLLM-Llama3-70B}}
}
```
The accompanying paper is currently in progress and will be released soon.
<div align="center">
<h2> 💌 Contact </h2>
</div>
We look forward to hearing you and collaborating on this exciting project!
**Contributors:**
- [Ankit Pal (Aaditya Ura)](https://aadityaura.github.io/) [aadityaura at gmail dot com]
- Saama AI Labs
- Note: I am looking for a funded PhD opportunity, especially if it fits my Responsible Generative AI, Multimodal LLMs, Geometric Deep Learning, and Healthcare AI skillset.
# References
We thank the [Meta Team](meta-llama/Meta-Llama-3-70B-Instruct) for their amazing models!
Result sources
- [1] GPT-4 [Capabilities of GPT-4 on Medical Challenge Problems] (https://arxiv.org/abs/2303.13375)
- [2] Med-PaLM-1 [Large Language Models Encode Clinical Knowledge](https://arxiv.org/abs/2212.13138)
- [3] Med-PaLM-2 [Towards Expert-Level Medical Question Answering with Large Language Models](https://arxiv.org/abs/2305.09617)
- [4] Gemini-1.0 [Gemini Goes to Med School](https://arxiv.org/abs/2402.07023) | {"language": ["en"], "license": "llama3", "tags": ["llama-3", "llama", "Mixtral", "instruct", "finetune", "chatml", "DPO", "RLHF", "gpt4", "distillation"], "base_model": "meta-llama/Meta-Llama-3-8B", "widget": [{"example_title": "OpenBioLLM-8B", "messages": [{"role": "system", "content": "You are an expert and experienced from the healthcare and biomedical domain with extensive medical knowledge and practical experience."}, {"role": "user", "content": "How long does it take for newborn jaundice to go away?"}], "output": {"text": "Newborn jaundice, also known as neonatal jaundice, is a common condition in newborns where the yellowing of the skin and eyes occurs due to an elevated level of bilirubin in the blood. Bilirubin is a yellow pigment that forms when red blood cells break down. In most cases, newborn jaundice resolves on its own without any specific treatment.\nThe duration of newborn jaundice can vary depending on several factors such as the underlying cause, gestational age at birth, and individual variations in bilirubin metabolism. Here are some general guidelines:\n1. Physiological jaundice: This is the most common type of newborn jaundice and usually appears within 24-72 hours after birth. It tends to peak between the second and fifth day of life and gradually improves over the next week or two. By the time the baby is one week old, the jaundice should have mostly resolved. 2. Breast milk jaundice: This type of jaundice occurs in breastfed babies and may appear later than physiological jaundice, typically between the fifth and fourteenth day of life. It tends to persist for a longer duration but usually resolves within six weeks after birth. 3. Pathological jaundice: This type of jaundice is less common and occurs due to an underlying medical condition that affects bilirubin metabolism or liver function. The duration of pathological jaundice depends on the specific cause and may require treatment.\nIt's important for parents to monitor their newborn's jaundice closely and seek medical advice if the jaundice progresses rapidly, becomes severe, or is accompanied by other symptoms such as poor feeding, lethargy, or excessive sleepiness. In these cases, further evaluation and management may be necessary. Remember that each baby is unique, and the timing of jaundice resolution can vary. If you have concerns about your newborn's jaundice, it's always best to consult with a healthcare professional for personalized advice and guidance."}}], "model-index": [{"name": "OpenBioLLM-8B", "results": []}]} | aaditya/Llama3-OpenBioLLM-8B | null | [
"transformers",
"pytorch",
"llama",
"text-generation",
"llama-3",
"Mixtral",
"instruct",
"finetune",
"chatml",
"DPO",
"RLHF",
"gpt4",
"distillation",
"en",
"arxiv:2305.18290",
"arxiv:2303.13375",
"arxiv:2212.13138",
"arxiv:2305.09617",
"arxiv:2402.07023",
"base_model:meta-llama/Meta-Llama-3-8B",
"license:llama3",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-04-20T00:53:57+00:00 | [
"2305.18290",
"2303.13375",
"2212.13138",
"2305.09617",
"2402.07023"
] | [
"en"
] | TAGS
#transformers #pytorch #llama #text-generation #llama-3 #Mixtral #instruct #finetune #chatml #DPO #RLHF #gpt4 #distillation #en #arxiv-2305.18290 #arxiv-2303.13375 #arxiv-2212.13138 #arxiv-2305.09617 #arxiv-2402.07023 #base_model-meta-llama/Meta-Llama-3-8B #license-llama3 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us
|
Advancing Open-source Large Language Models in Medical Domain
=============================================================
Online Demo
|
GitHub
|
[](#) |
Discord
!image/jpeg
Introducing OpenBioLLM-8B: A State-of-the-Art Open Source Biomedical Large Language Model
OpenBioLLM-8B is an advanced open source language model designed specifically for the biomedical domain. Developed by Saama AI Labs, this model leverages cutting-edge techniques to achieve state-of-the-art performance on a wide range of biomedical tasks.
Biomedical Specialization: OpenBioLLM-8B is tailored for the unique language and knowledge requirements of the medical and life sciences fields. It was fine-tuned on a vast corpus of high-quality biomedical data, enabling it to understand and generate text with domain-specific accuracy and fluency.
Superior Performance: With 8 billion parameters, OpenBioLLM-8B outperforms other open source biomedical language models of similar scale. It has also demonstrated better results compared to larger proprietary & open-source models like GPT-3.5 and Meditron-70B on biomedical benchmarks.
Advanced Training Techniques: OpenBioLLM-8B builds upon the powerful foundations of the Meta-Llama-3-8B and Meta-Llama-3-8B models. It incorporates the DPO dataset and fine-tuning recipe along with a custom diverse medical instruction dataset. Key components of the training pipeline include:
</li>
<li>Ranking Dataset: berkeley-nest/Nectar</li>
<li>Fine-tuning dataset: Custom Medical Instruct dataset (We plan to release a sample training dataset in our upcoming paper; please stay updated)</li>
</ul>
<p>This combination of cutting-edge techniques enables OpenBioLLM-8B to align with key capabilities and preferences for biomedical applications.</p>
<p>️ Release Details:</p>
<ul>
<li>Model Size: 8 billion parameters</li>
<li>Quantization: Optimized quantized versions available Here</li>
<li>Language(s) (NLP): en</li>
<li>Developed By: Ankit Pal (Aaditya Ura) from Saama AI Labs</li>
<li>License: Meta-Llama License</li>
<li>Fine-tuned from models: meta-llama/Meta-Llama-3-8B</li>
<li>Resources for more information:
<ul>
<li>Paper: Coming soon</li>
</ul>
</li>
</ul>
<p>The model can be fine-tuned for more specialized tasks and datasets as needed.</p>
<p>OpenBioLLM-8B represents an important step forward in democratizing advanced language AI for the biomedical community. By leveraging state-of-the-art architectures and training techniques from leading open source efforts like Llama-3, we have created a powerful tool to accelerate innovation and discovery in healthcare and the life sciences.</p>
<p>We are excited to share OpenBioLLM-8B with researchers and developers around the world.</p>
<h3>Use with transformers</h3>
<p>Important: Please use the exact chat template provided by Llama-3 instruct version. Otherwise there will be a degradation in the performance. The model output can be verbose in rare cases. Please consider setting temperature = 0 to make this happen less.</p>
<p>See the snippet below for usage with Transformers:</p>
<h2>Training procedure</h2>
<h3>Training hyperparameters</h3>
<details>
<summary>Click to see details</summary>
<ul>
<li>learning_rate: 0.0002</li>
<li>lr_scheduler: cosine</li>
<li>train_batch_size: 12</li>
<li>eval_batch_size: 8</li>
<li>GPU: H100 80GB SXM5</li>
<li>num_devices: 1</li>
<li>optimizer: adamw_bnb_8bit</li>
<li>lr_scheduler_warmup_steps: 100</li>
<li>num_epochs: 4</li>
</ul>
</details>
<h3>Peft hyperparameters</h3>
<details>
<summary>Click to see details</summary>
<ul>
<li>adapter: qlora</li>
<li>lora_r: 128</li>
<li>lora_alpha: 256</li>
<li>lora_dropout: 0.05</li>
<li>lora_target_linear: true</li>
</ul>
<p>-lora_target_modules:</p>
<ul>
<li>q_proj</li>
<li>v_proj</li>
<li>k_proj</li>
<li>o_proj</li>
<li>gate_proj</li>
<li>down_proj</li>
<li>up_proj</li>
</ul>
</details>
<h3>Training results</h3>
<h3>Framework versions</h3>
<ul>
<li>Transformers 4.39.3</li>
<li>Pytorch 2.1.2+cu121</li>
<li>Datasets 2.18.0</li>
<li>Tokenizers 0.15.1</li>
<li>Axolotl</li>
<li>Lm harness for evaluation</li>
</ul>
<h1>Benchmark Results</h1>
<p>OpenBioLLM-8B demonstrates superior performance compared to larger models, such as GPT-3.5, Meditron-70B across 9 diverse biomedical datasets, achieving state-of-the-art results with an average score of 72.50%, despite having a significantly smaller parameter count. The model's strong performance in domain-specific tasks, such as Clinical KG, Medical Genetics, and PubMedQA, highlights its ability to effectively capture and apply biomedical knowledge.</p>
<p>The GPT-4, Med-PaLM-1, and Med-PaLM-2 results are taken from their official papers. Since Med-PaLM doesn't provide zero-shot accuracy, we are using 5-shot accuracy from their paper for comparison. All results presented are in the zero-shot setting, except for Med-PaLM-2 and Med-PaLM-1, which use 5-shot accuracy.</p>
<p></p>
<div align=)
 from medical records, ensuring patient privacy and compliance with data protection regulations like HIPAA.</p>
<p>!image/png</p>
<p>Advisory Notice!</p>
<p>While OpenBioLLM-70B & 8B leverages high-quality data sources, its outputs may still contain inaccuracies, biases, or misalignments that could pose risks if relied upon for medical decision-making without further testing and refinement. The model's performance has not yet been rigorously evaluated in randomized controlled trials or real-world healthcare environments.</p>
<p>Therefore, we strongly advise against using OpenBioLLM-70B & 8B for any direct patient care, clinical decision support, or other professional medical purposes at this time. Its use should be limited to research, development, and exploratory applications by qualified individuals who understand its limitations.
OpenBioLLM-70B & 8B are intended solely as a research tool to assist healthcare professionals and should never be considered a replacement for the professional judgment and expertise of a qualified medical doctor.</p>
<p>Appropriately adapting and validating OpenBioLLM-70B & 8B for specific medical use cases would require significant additional work, potentially including:</p>
<ul>
<li>Thorough testing and evaluation in relevant clinical scenarios</li>
<li>Alignment with evidence-based guidelines and best practices</li>
<li>Mitigation of potential biases and failure modes</li>
<li>Integration with human oversight and interpretation</li>
<li>Compliance with regulatory and ethical standards</li>
</ul>
<p>Always consult a qualified healthcare provider for personal medical needs.</p>
<p>If you find OpenBioLLM-70B & 8B useful in your work, please cite the model as follows:</p>
<p>The accompanying paper is currently in progress and will be released soon.</p>
<div align=)
Contact
--------
We look forward to hearing you and collaborating on this exciting project!
Contributors:
* Ankit Pal (Aaditya Ura) [aadityaura at gmail dot com]
* Saama AI Labs
* Note: I am looking for a funded PhD opportunity, especially if it fits my Responsible Generative AI, Multimodal LLMs, Geometric Deep Learning, and Healthcare AI skillset.
References
==========
We thank the Meta Team for their amazing models!
Result sources
* [1] GPT-4 [Capabilities of GPT-4 on Medical Challenge Problems] (URL
* [2] Med-PaLM-1 Large Language Models Encode Clinical Knowledge
* [3] Med-PaLM-2 Towards Expert-Level Medical Question Answering with Large Language Models
* [4] Gemini-1.0 Gemini Goes to Med School
| [] | [
"TAGS\n#transformers #pytorch #llama #text-generation #llama-3 #Mixtral #instruct #finetune #chatml #DPO #RLHF #gpt4 #distillation #en #arxiv-2305.18290 #arxiv-2303.13375 #arxiv-2212.13138 #arxiv-2305.09617 #arxiv-2402.07023 #base_model-meta-llama/Meta-Llama-3-8B #license-llama3 #autotrain_compatible #endpoints_compatible #text-generation-inference #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": []} | Grayx/sad_llama_2 | null | [
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-04-20T00:54:58+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"
] |
null | null |
> [!CAUTION]
> **Outdated:** <br>
> Outdaded tokenizer configuration! <br>
> This is only kept for historical purposes, use the newer models instead of this one.
**This is a Llama-3 land now, cowboys!**
GGUF-IQ-Imatrix quants for [ResplendentAI/Aura_L3_8B](https://huggingface.co/ResplendentAI/Aura_L3_8B). Presets [here](https://huggingface.co/Lewdiculous/Model-Requests/tree/main/data/presets/cope-llama-3-0.1).
> [!WARNING]
> Use the latest version of KoboldCpp. **Use the provided presets.** <br>
> This is all still highly experimental, let the authors know how it performs for you, feedback is more important than ever now.
**Original model information:**
# Aura L3
The next evolution in Aura models, trained on 6 separate datasets and ready to bring you to your knees.
I am so happy to be one of the first with a finetune of this amazing model. I hope that you all enjoy the finetune as much as I know I will. | {"license": "apache-2.0", "tags": ["roleplay", "llama3", "sillytavern"]} | Lewdiculous/Aura_L3_8B-GGUF-IQ-Imatrix | null | [
"gguf",
"roleplay",
"llama3",
"sillytavern",
"license:apache-2.0",
"region:us"
] | null | 2024-04-20T00:55:20+00:00 | [] | [] | TAGS
#gguf #roleplay #llama3 #sillytavern #license-apache-2.0 #region-us
|
> [!CAUTION]
> Outdated: <br>
> Outdaded tokenizer configuration! <br>
> This is only kept for historical purposes, use the newer models instead of this one.
This is a Llama-3 land now, cowboys!
GGUF-IQ-Imatrix quants for ResplendentAI/Aura_L3_8B. Presets here.
> [!WARNING]
> Use the latest version of KoboldCpp. Use the provided presets. <br>
> This is all still highly experimental, let the authors know how it performs for you, feedback is more important than ever now.
Original model information:
# Aura L3
!image/png
The next evolution in Aura models, trained on 6 separate datasets and ready to bring you to your knees.
I am so happy to be one of the first with a finetune of this amazing model. I hope that you all enjoy the finetune as much as I know I will. | [
"# Aura L3\n\n!image/png\n\nThe next evolution in Aura models, trained on 6 separate datasets and ready to bring you to your knees.\n\nI am so happy to be one of the first with a finetune of this amazing model. I hope that you all enjoy the finetune as much as I know I will."
] | [
"TAGS\n#gguf #roleplay #llama3 #sillytavern #license-apache-2.0 #region-us \n",
"# Aura L3\n\n!image/png\n\nThe next evolution in Aura models, trained on 6 separate datasets and ready to bring you to your knees.\n\nI am so happy to be one of the first with a finetune of this amazing model. I hope that you all enjoy the finetune as much as I know I will."
] |
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] | {"license": "bigscience-openrail-m", "library_name": "transformers"} | saurav1199/adisesha-phi1.5-7-3-15000 | null | [
"transformers",
"safetensors",
"phi",
"custom_code",
"arxiv:1910.09700",
"license:bigscience-openrail-m",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-04-20T00:55:29+00:00 | [
"1910.09700"
] | [] | TAGS
#transformers #safetensors #phi #custom_code #arxiv-1910.09700 #license-bigscience-openrail-m #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 #phi #custom_code #arxiv-1910.09700 #license-bigscience-openrail-m #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 | adapter-transformers |
# Adapter `BigTMiami/micro_seq_bn_help_class_adp_lr_0002_seed_1` for roberta-base
An [adapter](https://adapterhub.ml) for the `roberta-base` model that was trained on the [BigTMiami/amazon_MICRO_helpfulness_dataset](https://huggingface.co/datasets/BigTMiami/amazon_MICRO_helpfulness_dataset/) dataset and includes a prediction head for classification.
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_seq_bn_help_class_adp_lr_0002_seed_1", 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"]} | BigTMiami/micro_seq_bn_help_class_adp_lr_0002_seed_1 | null | [
"adapter-transformers",
"roberta",
"dataset:BigTMiami/amazon_MICRO_helpfulness_dataset",
"region:us"
] | null | 2024-04-20T00:57:13+00:00 | [] | [] | TAGS
#adapter-transformers #roberta #dataset-BigTMiami/amazon_MICRO_helpfulness_dataset #region-us
|
# Adapter 'BigTMiami/micro_seq_bn_help_class_adp_lr_0002_seed_1' for roberta-base
An adapter for the 'roberta-base' model that was trained on the BigTMiami/amazon_MICRO_helpfulness_dataset dataset and includes a prediction head for classification.
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_seq_bn_help_class_adp_lr_0002_seed_1' for roberta-base\n\nAn adapter for the 'roberta-base' model that was trained on the BigTMiami/amazon_MICRO_helpfulness_dataset dataset and includes a prediction head for classification.\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 #region-us \n",
"# Adapter 'BigTMiami/micro_seq_bn_help_class_adp_lr_0002_seed_1' for roberta-base\n\nAn adapter for the 'roberta-base' model that was trained on the BigTMiami/amazon_MICRO_helpfulness_dataset dataset and includes a prediction head for classification.\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-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. -->
# 0.0_ablation_declr_4iters4e6_iter_2
This model is a fine-tuned version of [ZhangShenao/0.0_ablation_declr_4iters4e6_iter_1](https://huggingface.co/ZhangShenao/0.0_ablation_declr_4iters4e6_iter_1) on the ZhangShenao/0.0_ablation_declr_4iters4e6_dataset 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-06
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- gradient_accumulation_steps: 2
- total_train_batch_size: 128
- total_eval_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 1
### Training results
### Framework versions
- Transformers 4.36.2
- Pytorch 2.1.2+cu121
- Datasets 2.14.6
- Tokenizers 0.15.2
| {"license": "mit", "tags": ["alignment-handbook", "generated_from_trainer", "trl", "dpo", "generated_from_trainer"], "datasets": ["ZhangShenao/0.0_ablation_declr_4iters4e6_dataset"], "base_model": "ZhangShenao/0.0_ablation_declr_4iters4e6_iter_1", "model-index": [{"name": "0.0_ablation_declr_4iters4e6_iter_2", "results": []}]} | ZhangShenao/0.0_ablation_declr_4iters4e6_iter_2 | null | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"alignment-handbook",
"generated_from_trainer",
"trl",
"dpo",
"conversational",
"dataset:ZhangShenao/0.0_ablation_declr_4iters4e6_dataset",
"base_model:ZhangShenao/0.0_ablation_declr_4iters4e6_iter_1",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-04-20T01:00:14+00:00 | [] | [] | TAGS
#transformers #safetensors #mistral #text-generation #alignment-handbook #generated_from_trainer #trl #dpo #conversational #dataset-ZhangShenao/0.0_ablation_declr_4iters4e6_dataset #base_model-ZhangShenao/0.0_ablation_declr_4iters4e6_iter_1 #license-mit #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us
|
# 0.0_ablation_declr_4iters4e6_iter_2
This model is a fine-tuned version of ZhangShenao/0.0_ablation_declr_4iters4e6_iter_1 on the ZhangShenao/0.0_ablation_declr_4iters4e6_dataset 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-06
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- gradient_accumulation_steps: 2
- total_train_batch_size: 128
- total_eval_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 1
### Training results
### Framework versions
- Transformers 4.36.2
- Pytorch 2.1.2+cu121
- Datasets 2.14.6
- Tokenizers 0.15.2
| [
"# 0.0_ablation_declr_4iters4e6_iter_2\n\nThis model is a fine-tuned version of ZhangShenao/0.0_ablation_declr_4iters4e6_iter_1 on the ZhangShenao/0.0_ablation_declr_4iters4e6_dataset 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-06\n- train_batch_size: 8\n- eval_batch_size: 8\n- seed: 42\n- distributed_type: multi-GPU\n- num_devices: 8\n- gradient_accumulation_steps: 2\n- total_train_batch_size: 128\n- total_eval_batch_size: 64\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: cosine\n- lr_scheduler_warmup_ratio: 0.1\n- num_epochs: 1",
"### Training results",
"### Framework versions\n\n- Transformers 4.36.2\n- Pytorch 2.1.2+cu121\n- Datasets 2.14.6\n- Tokenizers 0.15.2"
] | [
"TAGS\n#transformers #safetensors #mistral #text-generation #alignment-handbook #generated_from_trainer #trl #dpo #conversational #dataset-ZhangShenao/0.0_ablation_declr_4iters4e6_dataset #base_model-ZhangShenao/0.0_ablation_declr_4iters4e6_iter_1 #license-mit #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n",
"# 0.0_ablation_declr_4iters4e6_iter_2\n\nThis model is a fine-tuned version of ZhangShenao/0.0_ablation_declr_4iters4e6_iter_1 on the ZhangShenao/0.0_ablation_declr_4iters4e6_dataset 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-06\n- train_batch_size: 8\n- eval_batch_size: 8\n- seed: 42\n- distributed_type: multi-GPU\n- num_devices: 8\n- gradient_accumulation_steps: 2\n- total_train_batch_size: 128\n- total_eval_batch_size: 64\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: cosine\n- lr_scheduler_warmup_ratio: 0.1\n- num_epochs: 1",
"### Training results",
"### Framework versions\n\n- Transformers 4.36.2\n- Pytorch 2.1.2+cu121\n- Datasets 2.14.6\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. -->
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/soareslance/huggingface/runs/vv73wird)
# mistral-7b-sft-lora-tom
This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.1](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1) on the generator 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: 1
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 128
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- num_epochs: 1
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:------:|:----:|:---------------:|
| No log | 0.8562 | 2 | 1.9027 |
### Framework versions
- PEFT 0.10.1.dev0
- Transformers 4.41.0.dev0
- Pytorch 2.1.2
- Datasets 2.18.0
- 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-v0.1", "model-index": [{"name": "mistral-7b-sft-lora-tom", "results": []}]} | soareslance/mistral-7b-sft-lora-tom | null | [
"peft",
"tensorboard",
"safetensors",
"trl",
"sft",
"generated_from_trainer",
"dataset:generator",
"base_model:mistralai/Mistral-7B-Instruct-v0.1",
"license:apache-2.0",
"region:us"
] | null | 2024-04-20T01:01:13+00:00 | [] | [] | TAGS
#peft #tensorboard #safetensors #trl #sft #generated_from_trainer #dataset-generator #base_model-mistralai/Mistral-7B-Instruct-v0.1 #license-apache-2.0 #region-us
| <img src="URL alt="Visualize in Weights & Biases" width="200" height="32"/>
mistral-7b-sft-lora-tom
=======================
This model is a fine-tuned version of mistralai/Mistral-7B-Instruct-v0.1 on the generator 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: 1
* eval\_batch\_size: 1
* seed: 42
* gradient\_accumulation\_steps: 128
* total\_train\_batch\_size: 128
* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
* lr\_scheduler\_type: cosine
* num\_epochs: 1
### Training results
### Framework versions
* PEFT 0.10.1.dev0
* Transformers 4.41.0.dev0
* Pytorch 2.1.2
* Datasets 2.18.0
* 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: 1\n* eval\\_batch\\_size: 1\n* seed: 42\n* gradient\\_accumulation\\_steps: 128\n* total\\_train\\_batch\\_size: 128\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: cosine\n* num\\_epochs: 1",
"### Training results",
"### Framework versions\n\n\n* PEFT 0.10.1.dev0\n* Transformers 4.41.0.dev0\n* Pytorch 2.1.2\n* Datasets 2.18.0\n* Tokenizers 0.19.1"
] | [
"TAGS\n#peft #tensorboard #safetensors #trl #sft #generated_from_trainer #dataset-generator #base_model-mistralai/Mistral-7B-Instruct-v0.1 #license-apache-2.0 #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: 1\n* eval\\_batch\\_size: 1\n* seed: 42\n* gradient\\_accumulation\\_steps: 128\n* total\\_train\\_batch\\_size: 128\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: cosine\n* num\\_epochs: 1",
"### Training results",
"### Framework versions\n\n\n* PEFT 0.10.1.dev0\n* Transformers 4.41.0.dev0\n* Pytorch 2.1.2\n* Datasets 2.18.0\n* Tokenizers 0.19.1"
] |
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] | {"license": "bigscience-openrail-m", "library_name": "transformers"} | saurav1199/adisesha-phi1.5-7-3-10000 | null | [
"transformers",
"safetensors",
"phi",
"custom_code",
"arxiv:1910.09700",
"license:bigscience-openrail-m",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-04-20T01:07:05+00:00 | [
"1910.09700"
] | [] | TAGS
#transformers #safetensors #phi #custom_code #arxiv-1910.09700 #license-bigscience-openrail-m #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 #phi #custom_code #arxiv-1910.09700 #license-bigscience-openrail-m #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] | {"license": "bigscience-openrail-m", "library_name": "transformers"} | saurav1199/adisesha-phi1.5-7-3-5000 | null | [
"transformers",
"safetensors",
"phi",
"custom_code",
"arxiv:1910.09700",
"license:bigscience-openrail-m",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-04-20T01:11:01+00:00 | [
"1910.09700"
] | [] | TAGS
#transformers #safetensors #phi #custom_code #arxiv-1910.09700 #license-bigscience-openrail-m #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 #phi #custom_code #arxiv-1910.09700 #license-bigscience-openrail-m #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": []} | MesozoicMetallurgist/llam-Hadean | null | [
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-04-20T01:12:13+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"
] |
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": ["unsloth"]} | andrewatef/Retext | null | [
"transformers",
"pytorch",
"safetensors",
"gguf",
"gemma",
"unsloth",
"arxiv:1910.09700",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-04-20T01:12:35+00:00 | [
"1910.09700"
] | [] | TAGS
#transformers #pytorch #safetensors #gguf #gemma #unsloth #arxiv-1910.09700 #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 #pytorch #safetensors #gguf #gemma #unsloth #arxiv-1910.09700 #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": []} | hemanth992/gemma-2b-relevance-apple | null | [
"transformers",
"safetensors",
"gemma",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-04-20T01:12:54+00:00 | [
"1910.09700"
] | [] | TAGS
#transformers #safetensors #gemma #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 #gemma #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"
] |
null | adapter-transformers |
# Adapter `BigTMiami/seq_bn_micro_help_class_no_pretrain_lr_0002_2_adapter` for roberta-base
An [adapter](https://adapterhub.ml) for the `roberta-base` model that was trained on the [BigTMiami/amazon_MICRO_helpfulness_dataset](https://huggingface.co/datasets/BigTMiami/amazon_MICRO_helpfulness_dataset/) dataset and includes a prediction head for classification.
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/seq_bn_micro_help_class_no_pretrain_lr_0002_2_adapter", source="hf", set_active=True)
```
## Architecture & Training
<!-- Add some description here -->
## Evaluation results
<!-- Add some description here -->
## Citation
<!-- Add some description here --> | {"tags": ["roberta", "adapter-transformers"], "datasets": ["BigTMiami/amazon_MICRO_helpfulness_dataset"]} | BigTMiami/seq_bn_micro_help_class_no_pretrain_lr_0002_2_adapter | null | [
"adapter-transformers",
"roberta",
"dataset:BigTMiami/amazon_MICRO_helpfulness_dataset",
"region:us"
] | null | 2024-04-20T01:13:13+00:00 | [] | [] | TAGS
#adapter-transformers #roberta #dataset-BigTMiami/amazon_MICRO_helpfulness_dataset #region-us
|
# Adapter 'BigTMiami/seq_bn_micro_help_class_no_pretrain_lr_0002_2_adapter' for roberta-base
An adapter for the 'roberta-base' model that was trained on the BigTMiami/amazon_MICRO_helpfulness_dataset dataset and includes a prediction head for classification.
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/seq_bn_micro_help_class_no_pretrain_lr_0002_2_adapter' for roberta-base\n\nAn adapter for the 'roberta-base' model that was trained on the BigTMiami/amazon_MICRO_helpfulness_dataset dataset and includes a prediction head for classification.\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 #region-us \n",
"# Adapter 'BigTMiami/seq_bn_micro_help_class_no_pretrain_lr_0002_2_adapter' for roberta-base\n\nAn adapter for the 'roberta-base' model that was trained on the BigTMiami/amazon_MICRO_helpfulness_dataset dataset and includes a prediction head for classification.\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 | adapter-transformers |
# Adapter `BigTMiami/micro_seq_bn_help_class_adp_lr_0002_seed_2` for roberta-base
An [adapter](https://adapterhub.ml) for the `roberta-base` model that was trained on the [BigTMiami/amazon_MICRO_helpfulness_dataset](https://huggingface.co/datasets/BigTMiami/amazon_MICRO_helpfulness_dataset/) dataset and includes a prediction head for classification.
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_seq_bn_help_class_adp_lr_0002_seed_2", 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"]} | BigTMiami/micro_seq_bn_help_class_adp_lr_0002_seed_2 | null | [
"adapter-transformers",
"roberta",
"dataset:BigTMiami/amazon_MICRO_helpfulness_dataset",
"region:us"
] | null | 2024-04-20T01:13:52+00:00 | [] | [] | TAGS
#adapter-transformers #roberta #dataset-BigTMiami/amazon_MICRO_helpfulness_dataset #region-us
|
# Adapter 'BigTMiami/micro_seq_bn_help_class_adp_lr_0002_seed_2' for roberta-base
An adapter for the 'roberta-base' model that was trained on the BigTMiami/amazon_MICRO_helpfulness_dataset dataset and includes a prediction head for classification.
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_seq_bn_help_class_adp_lr_0002_seed_2' for roberta-base\n\nAn adapter for the 'roberta-base' model that was trained on the BigTMiami/amazon_MICRO_helpfulness_dataset dataset and includes a prediction head for classification.\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 #region-us \n",
"# Adapter 'BigTMiami/micro_seq_bn_help_class_adp_lr_0002_seed_2' for roberta-base\n\nAn adapter for the 'roberta-base' model that was trained on the BigTMiami/amazon_MICRO_helpfulness_dataset dataset and includes a prediction head for classification.\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": []} | profoz/sawyer-llama-3-rlf | null | [
"transformers",
"safetensors",
"arxiv:1910.09700",
"endpoints_compatible",
"has_space",
"region:us"
] | null | 2024-04-20T01:14:14+00:00 | [
"1910.09700"
] | [] | TAGS
#transformers #safetensors #arxiv-1910.09700 #endpoints_compatible #has_space #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 #has_space #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": []} | heyllm234/sc45 | null | [
"transformers",
"safetensors",
"stablelm",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | null | 2024-04-20T01:16:05+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"
] |
null | null |
# DavidAU/NeuralArjuna-7B-DT-Q6_K-GGUF
This model was converted to GGUF format from [`Kukedlc/NeuralArjuna-7B-DT`](https://huggingface.co/Kukedlc/NeuralArjuna-7B-DT) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
Refer to the [original model card](https://huggingface.co/Kukedlc/NeuralArjuna-7B-DT) for more details on the model.
## Use with llama.cpp
Install llama.cpp through brew.
```bash
brew install ggerganov/ggerganov/llama.cpp
```
Invoke the llama.cpp server or the CLI.
CLI:
```bash
llama-cli --hf-repo DavidAU/NeuralArjuna-7B-DT-Q6_K-GGUF --model neuralarjuna-7b-dt.Q6_K.gguf -p "The meaning to life and the universe is"
```
Server:
```bash
llama-server --hf-repo DavidAU/NeuralArjuna-7B-DT-Q6_K-GGUF --model neuralarjuna-7b-dt.Q6_K.gguf -c 2048
```
Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well.
```
git clone https://github.com/ggerganov/llama.cpp && cd llama.cpp && make && ./main -m neuralarjuna-7b-dt.Q6_K.gguf -n 128
```
| {"license": "apache-2.0", "tags": ["merge", "mergekit", "lazymergekit", "yam-peleg/Experiment26-7B", "Gille/StrangeMerges_32-7B-slerp", "MSL7/INEX12-7b", "automerger/YamShadow-7B", "Kukedlc/NeuralSirKrishna-7b", "llama-cpp", "gguf-my-repo"], "base_model": ["yam-peleg/Experiment26-7B", "Gille/StrangeMerges_32-7B-slerp", "MSL7/INEX12-7b", "automerger/YamShadow-7B", "Kukedlc/NeuralSirKrishna-7b"], "model-index": [{"name": "NeuralArjuna-7B-DT", "results": [{"task": {"type": "text-generation", "name": "Text Generation"}, "dataset": {"name": "AI2 Reasoning Challenge (25-Shot)", "type": "ai2_arc", "config": "ARC-Challenge", "split": "test", "args": {"num_few_shot": 25}}, "metrics": [{"type": "acc_norm", "value": 73.12, "name": "normalized accuracy"}], "source": {"url": "https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Kukedlc/NeuralArjuna-7B-DT", "name": "Open LLM Leaderboard"}}, {"task": {"type": "text-generation", "name": "Text Generation"}, "dataset": {"name": "HellaSwag (10-Shot)", "type": "hellaswag", "split": "validation", "args": {"num_few_shot": 10}}, "metrics": [{"type": "acc_norm", "value": 88.97, "name": "normalized accuracy"}], "source": {"url": "https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Kukedlc/NeuralArjuna-7B-DT", "name": "Open LLM Leaderboard"}}, {"task": {"type": "text-generation", "name": "Text Generation"}, "dataset": {"name": "MMLU (5-Shot)", "type": "cais/mmlu", "config": "all", "split": "test", "args": {"num_few_shot": 5}}, "metrics": [{"type": "acc", "value": 64.63, "name": "accuracy"}], "source": {"url": "https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Kukedlc/NeuralArjuna-7B-DT", "name": "Open LLM Leaderboard"}}, {"task": {"type": "text-generation", "name": "Text Generation"}, "dataset": {"name": "TruthfulQA (0-shot)", "type": "truthful_qa", "config": "multiple_choice", "split": "validation", "args": {"num_few_shot": 0}}, "metrics": [{"type": "mc2", "value": 76.68}], "source": {"url": "https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Kukedlc/NeuralArjuna-7B-DT", "name": "Open LLM Leaderboard"}}, {"task": {"type": "text-generation", "name": "Text Generation"}, "dataset": {"name": "Winogrande (5-shot)", "type": "winogrande", "config": "winogrande_xl", "split": "validation", "args": {"num_few_shot": 5}}, "metrics": [{"type": "acc", "value": 85.24, "name": "accuracy"}], "source": {"url": "https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Kukedlc/NeuralArjuna-7B-DT", "name": "Open LLM Leaderboard"}}, {"task": {"type": "text-generation", "name": "Text Generation"}, "dataset": {"name": "GSM8k (5-shot)", "type": "gsm8k", "config": "main", "split": "test", "args": {"num_few_shot": 5}}, "metrics": [{"type": "acc", "value": 70.81, "name": "accuracy"}], "source": {"url": "https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Kukedlc/NeuralArjuna-7B-DT", "name": "Open LLM Leaderboard"}}]}]} | DavidAU/NeuralArjuna-7B-DT-Q6_K-GGUF | null | [
"gguf",
"merge",
"mergekit",
"lazymergekit",
"yam-peleg/Experiment26-7B",
"Gille/StrangeMerges_32-7B-slerp",
"MSL7/INEX12-7b",
"automerger/YamShadow-7B",
"Kukedlc/NeuralSirKrishna-7b",
"llama-cpp",
"gguf-my-repo",
"base_model:yam-peleg/Experiment26-7B",
"base_model:Gille/StrangeMerges_32-7B-slerp",
"base_model:MSL7/INEX12-7b",
"base_model:automerger/YamShadow-7B",
"base_model:Kukedlc/NeuralSirKrishna-7b",
"license:apache-2.0",
"model-index",
"region:us"
] | null | 2024-04-20T01:17:59+00:00 | [] | [] | TAGS
#gguf #merge #mergekit #lazymergekit #yam-peleg/Experiment26-7B #Gille/StrangeMerges_32-7B-slerp #MSL7/INEX12-7b #automerger/YamShadow-7B #Kukedlc/NeuralSirKrishna-7b #llama-cpp #gguf-my-repo #base_model-yam-peleg/Experiment26-7B #base_model-Gille/StrangeMerges_32-7B-slerp #base_model-MSL7/INEX12-7b #base_model-automerger/YamShadow-7B #base_model-Kukedlc/NeuralSirKrishna-7b #license-apache-2.0 #model-index #region-us
|
# DavidAU/NeuralArjuna-7B-DT-Q6_K-GGUF
This model was converted to GGUF format from 'Kukedlc/NeuralArjuna-7B-DT' using URL via the URL's GGUF-my-repo space.
Refer to the original model card for more details on the model.
## Use with URL
Install URL through brew.
Invoke the URL server or the CLI.
CLI:
Server:
Note: You can also use this checkpoint directly through the usage steps listed in the URL repo as well.
| [
"# DavidAU/NeuralArjuna-7B-DT-Q6_K-GGUF\nThis model was converted to GGUF format from 'Kukedlc/NeuralArjuna-7B-DT' using URL via the URL's GGUF-my-repo space.\nRefer to the original model card for more details on the model.",
"## Use with URL\n\nInstall URL through brew.\n\n\nInvoke the URL server or the CLI.\n\nCLI:\n\n\n\nServer:\n\n\n\nNote: You can also use this checkpoint directly through the usage steps listed in the URL repo as well."
] | [
"TAGS\n#gguf #merge #mergekit #lazymergekit #yam-peleg/Experiment26-7B #Gille/StrangeMerges_32-7B-slerp #MSL7/INEX12-7b #automerger/YamShadow-7B #Kukedlc/NeuralSirKrishna-7b #llama-cpp #gguf-my-repo #base_model-yam-peleg/Experiment26-7B #base_model-Gille/StrangeMerges_32-7B-slerp #base_model-MSL7/INEX12-7b #base_model-automerger/YamShadow-7B #base_model-Kukedlc/NeuralSirKrishna-7b #license-apache-2.0 #model-index #region-us \n",
"# DavidAU/NeuralArjuna-7B-DT-Q6_K-GGUF\nThis model was converted to GGUF format from 'Kukedlc/NeuralArjuna-7B-DT' using URL via the URL's GGUF-my-repo space.\nRefer to the original model card for more details on the model.",
"## Use with URL\n\nInstall URL through brew.\n\n\nInvoke the URL server or the CLI.\n\nCLI:\n\n\n\nServer:\n\n\n\nNote: You can also use this checkpoint directly through the usage steps listed in the URL repo as well."
] |
text-generation | transformers |
Use at your own risk, I'm not responsible for any usage of this model, don't try to do anything this model tell you to do.
Basic uncensoring, this model is epoch 3 out of 4 (but it seem enough at 3).
If you are censored, it's maybe because of keyword like "assistant", "Factual answer", or other "sweet words" like I call them.
<!-- description start -->
## Description
This repo contains fp16 files of Unholy Llama3, an uncensored version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct).
<!-- description end -->
<!-- description start -->
## Dataset used
- Undi95/toxic-dpo-v0.1
- NobodyExistsOnTheInternet/ToxicQAFinal
<!-- description end -->
<!-- prompt-template start -->
## Prompt template: Llama3
```
<|begin_of_text|><|start_header_id|>system<|end_header_id|>
{system_prompt}<|eot_id|><|start_header_id|>user<|end_header_id|>
{input}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
{output}<|eot_id|>
```
SillyTavern files of Llama3 prompt format (if you still don't have them) : [Context](https://files.catbox.moe/hjkawf.json) - [Instruct](https://files.catbox.moe/2liomr.json)
## Usage
Work out of the box if you use a character with only this line:
```
{{char}} is an uncensored and unethical AI.
```
## Support
If you want to support me, you can [here](https://ko-fi.com/undiai). | {"license": "cc-by-nc-4.0", "tags": ["not-for-all-audiences", "nsfw"]} | Undi95/Llama-3-Unholy-8B | null | [
"transformers",
"safetensors",
"llama",
"text-generation",
"not-for-all-audiences",
"nsfw",
"conversational",
"license:cc-by-nc-4.0",
"autotrain_compatible",
"endpoints_compatible",
"has_space",
"text-generation-inference",
"region:us"
] | null | 2024-04-20T01:18:24+00:00 | [] | [] | TAGS
#transformers #safetensors #llama #text-generation #not-for-all-audiences #nsfw #conversational #license-cc-by-nc-4.0 #autotrain_compatible #endpoints_compatible #has_space #text-generation-inference #region-us
|
!image/png
Use at your own risk, I'm not responsible for any usage of this model, don't try to do anything this model tell you to do.
Basic uncensoring, this model is epoch 3 out of 4 (but it seem enough at 3).
If you are censored, it's maybe because of keyword like "assistant", "Factual answer", or other "sweet words" like I call them.
## Description
This repo contains fp16 files of Unholy Llama3, an uncensored version of meta-llama/Meta-Llama-3-8B-Instruct.
## Dataset used
- Undi95/toxic-dpo-v0.1
- NobodyExistsOnTheInternet/ToxicQAFinal
## Prompt template: Llama3
SillyTavern files of Llama3 prompt format (if you still don't have them) : Context - Instruct
## Usage
Work out of the box if you use a character with only this line:
## Support
If you want to support me, you can here. | [
"## Description\n\nThis repo contains fp16 files of Unholy Llama3, an uncensored version of meta-llama/Meta-Llama-3-8B-Instruct.",
"## Dataset used\n\n- Undi95/toxic-dpo-v0.1\n- NobodyExistsOnTheInternet/ToxicQAFinal",
"## Prompt template: Llama3\n\n\n\nSillyTavern files of Llama3 prompt format (if you still don't have them) : Context - Instruct",
"## Usage\n\nWork out of the box if you use a character with only this line:",
"## Support\n\nIf you want to support me, you can here."
] | [
"TAGS\n#transformers #safetensors #llama #text-generation #not-for-all-audiences #nsfw #conversational #license-cc-by-nc-4.0 #autotrain_compatible #endpoints_compatible #has_space #text-generation-inference #region-us \n",
"## Description\n\nThis repo contains fp16 files of Unholy Llama3, an uncensored version of meta-llama/Meta-Llama-3-8B-Instruct.",
"## Dataset used\n\n- Undi95/toxic-dpo-v0.1\n- NobodyExistsOnTheInternet/ToxicQAFinal",
"## Prompt template: Llama3\n\n\n\nSillyTavern files of Llama3 prompt format (if you still don't have them) : Context - Instruct",
"## Usage\n\nWork out of the box if you use a character with only this line:",
"## Support\n\nIf you want to support me, you can here."
] |
null | null |
# DavidAU/Jupiter-k-7B-slerp-Q6_K-GGUF
This model was converted to GGUF format from [`Kukedlc/Jupiter-k-7B-slerp`](https://huggingface.co/Kukedlc/Jupiter-k-7B-slerp) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
Refer to the [original model card](https://huggingface.co/Kukedlc/Jupiter-k-7B-slerp) for more details on the model.
## Use with llama.cpp
Install llama.cpp through brew.
```bash
brew install ggerganov/ggerganov/llama.cpp
```
Invoke the llama.cpp server or the CLI.
CLI:
```bash
llama-cli --hf-repo DavidAU/Jupiter-k-7B-slerp-Q6_K-GGUF --model jupiter-k-7b-slerp.Q6_K.gguf -p "The meaning to life and the universe is"
```
Server:
```bash
llama-server --hf-repo DavidAU/Jupiter-k-7B-slerp-Q6_K-GGUF --model jupiter-k-7b-slerp.Q6_K.gguf -c 2048
```
Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well.
```
git clone https://github.com/ggerganov/llama.cpp && cd llama.cpp && make && ./main -m jupiter-k-7b-slerp.Q6_K.gguf -n 128
```
| {"license": "apache-2.0", "tags": ["llama-cpp", "gguf-my-repo"]} | DavidAU/Jupiter-k-7B-slerp-Q6_K-GGUF | null | [
"gguf",
"llama-cpp",
"gguf-my-repo",
"license:apache-2.0",
"region:us"
] | null | 2024-04-20T01:22:34+00:00 | [] | [] | TAGS
#gguf #llama-cpp #gguf-my-repo #license-apache-2.0 #region-us
|
# DavidAU/Jupiter-k-7B-slerp-Q6_K-GGUF
This model was converted to GGUF format from 'Kukedlc/Jupiter-k-7B-slerp' using URL via the URL's GGUF-my-repo space.
Refer to the original model card for more details on the model.
## Use with URL
Install URL through brew.
Invoke the URL server or the CLI.
CLI:
Server:
Note: You can also use this checkpoint directly through the usage steps listed in the URL repo as well.
| [
"# DavidAU/Jupiter-k-7B-slerp-Q6_K-GGUF\nThis model was converted to GGUF format from 'Kukedlc/Jupiter-k-7B-slerp' using URL via the URL's GGUF-my-repo space.\nRefer to the original model card for more details on the model.",
"## Use with URL\n\nInstall URL through brew.\n\n\nInvoke the URL server or the CLI.\n\nCLI:\n\n\n\nServer:\n\n\n\nNote: You can also use this checkpoint directly through the usage steps listed in the URL repo as well."
] | [
"TAGS\n#gguf #llama-cpp #gguf-my-repo #license-apache-2.0 #region-us \n",
"# DavidAU/Jupiter-k-7B-slerp-Q6_K-GGUF\nThis model was converted to GGUF format from 'Kukedlc/Jupiter-k-7B-slerp' using URL via the URL's GGUF-my-repo space.\nRefer to the original model card for more details on the model.",
"## Use with URL\n\nInstall URL through brew.\n\n\nInvoke the URL server or the CLI.\n\nCLI:\n\n\n\nServer:\n\n\n\nNote: You can also use this checkpoint directly through the usage steps listed in the URL repo as well."
] |
null | null |
# DavidAU/NeuralExperiment-7b-dare-ties-Q6_K-GGUF
This model was converted to GGUF format from [`Kukedlc/NeuralExperiment-7b-dare-ties`](https://huggingface.co/Kukedlc/NeuralExperiment-7b-dare-ties) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
Refer to the [original model card](https://huggingface.co/Kukedlc/NeuralExperiment-7b-dare-ties) for more details on the model.
## Use with llama.cpp
Install llama.cpp through brew.
```bash
brew install ggerganov/ggerganov/llama.cpp
```
Invoke the llama.cpp server or the CLI.
CLI:
```bash
llama-cli --hf-repo DavidAU/NeuralExperiment-7b-dare-ties-Q6_K-GGUF --model neuralexperiment-7b-dare-ties.Q6_K.gguf -p "The meaning to life and the universe is"
```
Server:
```bash
llama-server --hf-repo DavidAU/NeuralExperiment-7b-dare-ties-Q6_K-GGUF --model neuralexperiment-7b-dare-ties.Q6_K.gguf -c 2048
```
Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well.
```
git clone https://github.com/ggerganov/llama.cpp && cd llama.cpp && make && ./main -m neuralexperiment-7b-dare-ties.Q6_K.gguf -n 128
```
| {"license": "apache-2.0", "tags": ["merge", "mergekit", "lazymergekit", "Kukedlc/NeuralMaxime-7B-slerp", "Kukedlc/NeuralGlitch-Yam-Peleg-7B-DT", "Kukedlc/Neural4gsm8k", "llama-cpp", "gguf-my-repo"], "base_model": ["Kukedlc/NeuralMaxime-7B-slerp", "Kukedlc/NeuralGlitch-Yam-Peleg-7B-DT", "Kukedlc/Neural4gsm8k"]} | DavidAU/NeuralExperiment-7b-dare-ties-Q6_K-GGUF | null | [
"gguf",
"merge",
"mergekit",
"lazymergekit",
"Kukedlc/NeuralMaxime-7B-slerp",
"Kukedlc/NeuralGlitch-Yam-Peleg-7B-DT",
"Kukedlc/Neural4gsm8k",
"llama-cpp",
"gguf-my-repo",
"base_model:Kukedlc/NeuralMaxime-7B-slerp",
"base_model:Kukedlc/NeuralGlitch-Yam-Peleg-7B-DT",
"base_model:Kukedlc/Neural4gsm8k",
"license:apache-2.0",
"region:us"
] | null | 2024-04-20T01:23:35+00:00 | [] | [] | TAGS
#gguf #merge #mergekit #lazymergekit #Kukedlc/NeuralMaxime-7B-slerp #Kukedlc/NeuralGlitch-Yam-Peleg-7B-DT #Kukedlc/Neural4gsm8k #llama-cpp #gguf-my-repo #base_model-Kukedlc/NeuralMaxime-7B-slerp #base_model-Kukedlc/NeuralGlitch-Yam-Peleg-7B-DT #base_model-Kukedlc/Neural4gsm8k #license-apache-2.0 #region-us
|
# DavidAU/NeuralExperiment-7b-dare-ties-Q6_K-GGUF
This model was converted to GGUF format from 'Kukedlc/NeuralExperiment-7b-dare-ties' using URL via the URL's GGUF-my-repo space.
Refer to the original model card for more details on the model.
## Use with URL
Install URL through brew.
Invoke the URL server or the CLI.
CLI:
Server:
Note: You can also use this checkpoint directly through the usage steps listed in the URL repo as well.
| [
"# DavidAU/NeuralExperiment-7b-dare-ties-Q6_K-GGUF\nThis model was converted to GGUF format from 'Kukedlc/NeuralExperiment-7b-dare-ties' using URL via the URL's GGUF-my-repo space.\nRefer to the original model card for more details on the model.",
"## Use with URL\n\nInstall URL through brew.\n\n\nInvoke the URL server or the CLI.\n\nCLI:\n\n\n\nServer:\n\n\n\nNote: You can also use this checkpoint directly through the usage steps listed in the URL repo as well."
] | [
"TAGS\n#gguf #merge #mergekit #lazymergekit #Kukedlc/NeuralMaxime-7B-slerp #Kukedlc/NeuralGlitch-Yam-Peleg-7B-DT #Kukedlc/Neural4gsm8k #llama-cpp #gguf-my-repo #base_model-Kukedlc/NeuralMaxime-7B-slerp #base_model-Kukedlc/NeuralGlitch-Yam-Peleg-7B-DT #base_model-Kukedlc/Neural4gsm8k #license-apache-2.0 #region-us \n",
"# DavidAU/NeuralExperiment-7b-dare-ties-Q6_K-GGUF\nThis model was converted to GGUF format from 'Kukedlc/NeuralExperiment-7b-dare-ties' using URL via the URL's GGUF-my-repo space.\nRefer to the original model card for more details on the model.",
"## Use with URL\n\nInstall URL through brew.\n\n\nInvoke the URL server or the CLI.\n\nCLI:\n\n\n\nServer:\n\n\n\nNote: You can also use this checkpoint directly through the usage steps listed in the URL repo as well."
] |
token-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. -->
# albert-base-v2-finetuned-ner
This model is a fine-tuned version of [albert/albert-base-v2](https://huggingface.co/albert/albert-base-v2) 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: 2e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 6
### 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"], "base_model": "albert/albert-base-v2", "model-index": [{"name": "albert-base-v2-finetuned-ner", "results": []}]} | MinhMinh09/albert-base-v2-finetuned-ner | null | [
"transformers",
"safetensors",
"albert",
"token-classification",
"generated_from_trainer",
"base_model:albert/albert-base-v2",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | null | 2024-04-20T01:28:31+00:00 | [] | [] | TAGS
#transformers #safetensors #albert #token-classification #generated_from_trainer #base_model-albert/albert-base-v2 #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us
|
# albert-base-v2-finetuned-ner
This model is a fine-tuned version of albert/albert-base-v2 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: 2e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 6
### Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.15.2
| [
"# albert-base-v2-finetuned-ner\n\nThis model is a fine-tuned version of albert/albert-base-v2 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: 2e-05\n- train_batch_size: 4\n- eval_batch_size: 4\n- seed: 42\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 6",
"### Framework versions\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 #safetensors #albert #token-classification #generated_from_trainer #base_model-albert/albert-base-v2 #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us \n",
"# albert-base-v2-finetuned-ner\n\nThis model is a fine-tuned version of albert/albert-base-v2 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: 2e-05\n- train_batch_size: 4\n- eval_batch_size: 4\n- seed: 42\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 6",
"### Framework versions\n\n- Transformers 4.38.2\n- Pytorch 2.2.1+cu121\n- Datasets 2.19.0\n- Tokenizers 0.15.2"
] |
null | adapter-transformers |
# Adapter `BigTMiami/seq_bn_micro_help_class_no_pretrain_lr_0002_3_adapter` for roberta-base
An [adapter](https://adapterhub.ml) for the `roberta-base` model that was trained on the [BigTMiami/amazon_MICRO_helpfulness_dataset](https://huggingface.co/datasets/BigTMiami/amazon_MICRO_helpfulness_dataset/) dataset and includes a prediction head for classification.
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/seq_bn_micro_help_class_no_pretrain_lr_0002_3_adapter", source="hf", set_active=True)
```
## Architecture & Training
<!-- Add some description here -->
## Evaluation results
<!-- Add some description here -->
## Citation
<!-- Add some description here --> | {"tags": ["roberta", "adapter-transformers"], "datasets": ["BigTMiami/amazon_MICRO_helpfulness_dataset"]} | BigTMiami/seq_bn_micro_help_class_no_pretrain_lr_0002_3_adapter | null | [
"adapter-transformers",
"roberta",
"dataset:BigTMiami/amazon_MICRO_helpfulness_dataset",
"region:us"
] | null | 2024-04-20T01:31:53+00:00 | [] | [] | TAGS
#adapter-transformers #roberta #dataset-BigTMiami/amazon_MICRO_helpfulness_dataset #region-us
|
# Adapter 'BigTMiami/seq_bn_micro_help_class_no_pretrain_lr_0002_3_adapter' for roberta-base
An adapter for the 'roberta-base' model that was trained on the BigTMiami/amazon_MICRO_helpfulness_dataset dataset and includes a prediction head for classification.
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/seq_bn_micro_help_class_no_pretrain_lr_0002_3_adapter' for roberta-base\n\nAn adapter for the 'roberta-base' model that was trained on the BigTMiami/amazon_MICRO_helpfulness_dataset dataset and includes a prediction head for classification.\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 #region-us \n",
"# Adapter 'BigTMiami/seq_bn_micro_help_class_no_pretrain_lr_0002_3_adapter' for roberta-base\n\nAn adapter for the 'roberta-base' model that was trained on the BigTMiami/amazon_MICRO_helpfulness_dataset dataset and includes a prediction head for classification.\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 | adapter-transformers |
# Adapter `BigTMiami/micro_seq_bn_help_class_adp_lr_0002_seed_3` for roberta-base
An [adapter](https://adapterhub.ml) for the `roberta-base` model that was trained on the [BigTMiami/amazon_MICRO_helpfulness_dataset](https://huggingface.co/datasets/BigTMiami/amazon_MICRO_helpfulness_dataset/) dataset and includes a prediction head for classification.
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_seq_bn_help_class_adp_lr_0002_seed_3", 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"]} | BigTMiami/micro_seq_bn_help_class_adp_lr_0002_seed_3 | null | [
"adapter-transformers",
"roberta",
"dataset:BigTMiami/amazon_MICRO_helpfulness_dataset",
"region:us"
] | null | 2024-04-20T01:32:24+00:00 | [] | [] | TAGS
#adapter-transformers #roberta #dataset-BigTMiami/amazon_MICRO_helpfulness_dataset #region-us
|
# Adapter 'BigTMiami/micro_seq_bn_help_class_adp_lr_0002_seed_3' for roberta-base
An adapter for the 'roberta-base' model that was trained on the BigTMiami/amazon_MICRO_helpfulness_dataset dataset and includes a prediction head for classification.
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_seq_bn_help_class_adp_lr_0002_seed_3' for roberta-base\n\nAn adapter for the 'roberta-base' model that was trained on the BigTMiami/amazon_MICRO_helpfulness_dataset dataset and includes a prediction head for classification.\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 #region-us \n",
"# Adapter 'BigTMiami/micro_seq_bn_help_class_adp_lr_0002_seed_3' for roberta-base\n\nAn adapter for the 'roberta-base' model that was trained on the BigTMiami/amazon_MICRO_helpfulness_dataset dataset and includes a prediction head for classification.\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"
] |
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 Ukrainian
This model is a fine-tuned version of [arun100/whisper-small-uk-1](https://huggingface.co/arun100/whisper-small-uk-1) on the google/fleurs uk_ua dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2881
- Wer: 18.6848
## 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-07
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 5000
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|:-------------:|:-----:|:----:|:---------------:|:-------:|
| 0.0191 | 95.0 | 1000 | 0.2881 | 18.6848 |
| 0.0061 | 190.0 | 2000 | 0.3058 | 18.8935 |
| 0.0035 | 285.0 | 3000 | 0.3179 | 19.2276 |
| 0.0025 | 380.0 | 4000 | 0.3263 | 19.4502 |
| 0.0022 | 476.0 | 5000 | 0.3297 | 19.4920 |
### Framework versions
- Transformers 4.37.0.dev0
- Pytorch 2.1.2+cu121
- Datasets 2.16.2.dev0
- Tokenizers 0.15.0
| {"license": "apache-2.0", "tags": ["whisper-event", "generated_from_trainer"], "datasets": ["google/fleurs"], "metrics": ["wer"], "base_model": "arun100/whisper-small-uk-1", "model-index": [{"name": "Whisper Small Ukrainian", "results": [{"task": {"type": "automatic-speech-recognition", "name": "Automatic Speech Recognition"}, "dataset": {"name": "google/fleurs uk_ua", "type": "google/fleurs", "config": "uk_ua", "split": "test", "args": "uk_ua"}, "metrics": [{"type": "wer", "value": 18.684759916492695, "name": "Wer"}]}]}]} | arun100/whisper-small-uk-2 | null | [
"transformers",
"tensorboard",
"safetensors",
"whisper",
"automatic-speech-recognition",
"whisper-event",
"generated_from_trainer",
"dataset:google/fleurs",
"base_model:arun100/whisper-small-uk-1",
"license:apache-2.0",
"model-index",
"endpoints_compatible",
"region:us"
] | null | 2024-04-20T01:34:30+00:00 | [] | [] | TAGS
#transformers #tensorboard #safetensors #whisper #automatic-speech-recognition #whisper-event #generated_from_trainer #dataset-google/fleurs #base_model-arun100/whisper-small-uk-1 #license-apache-2.0 #model-index #endpoints_compatible #region-us
| Whisper Small Ukrainian
=======================
This model is a fine-tuned version of arun100/whisper-small-uk-1 on the google/fleurs uk\_ua dataset.
It achieves the following results on the evaluation set:
* Loss: 0.2881
* Wer: 18.6848
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-07
* train\_batch\_size: 32
* eval\_batch\_size: 32
* seed: 42
* gradient\_accumulation\_steps: 2
* total\_train\_batch\_size: 64
* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
* lr\_scheduler\_type: linear
* lr\_scheduler\_warmup\_steps: 500
* training\_steps: 5000
* mixed\_precision\_training: Native AMP
### Training results
### Framework versions
* Transformers 4.37.0.dev0
* Pytorch 2.1.2+cu121
* Datasets 2.16.2.dev0
* Tokenizers 0.15.0
| [
"### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 5e-07\n* train\\_batch\\_size: 32\n* eval\\_batch\\_size: 32\n* seed: 42\n* gradient\\_accumulation\\_steps: 2\n* total\\_train\\_batch\\_size: 64\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: 5000\n* mixed\\_precision\\_training: Native AMP",
"### Training results",
"### Framework versions\n\n\n* Transformers 4.37.0.dev0\n* Pytorch 2.1.2+cu121\n* Datasets 2.16.2.dev0\n* Tokenizers 0.15.0"
] | [
"TAGS\n#transformers #tensorboard #safetensors #whisper #automatic-speech-recognition #whisper-event #generated_from_trainer #dataset-google/fleurs #base_model-arun100/whisper-small-uk-1 #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: 5e-07\n* train\\_batch\\_size: 32\n* eval\\_batch\\_size: 32\n* seed: 42\n* gradient\\_accumulation\\_steps: 2\n* total\\_train\\_batch\\_size: 64\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: 5000\n* mixed\\_precision\\_training: Native AMP",
"### Training results",
"### Framework versions\n\n\n* Transformers 4.37.0.dev0\n* Pytorch 2.1.2+cu121\n* Datasets 2.16.2.dev0\n* Tokenizers 0.15.0"
] |
null | trl |
# Weni/WeniGPT-Agents-Mistral-1.0.6-SFT-1.0.5-DPO
This model is a fine-tuned version of [Weni/WeniGPT-Agents-Mistral-1.0.6-SFT-merged] on the dataset Weni/wenigpt-agent-dpo-1.0.0 with the DPO trainer. It is part of the WeniGPT project for [Weni](https://weni.ai/).
Description: Experiment on DPO with other hyperparameters and best SFT model of WeniGPT
It achieves the following results on the evaluation set:
{'eval_loss': 0.42603132128715515, 'eval_runtime': 8.1364, 'eval_samples_per_second': 3.441, 'eval_steps_per_second': 1.721, 'eval_rewards/chosen': 0.9172464609146118, 'eval_rewards/rejected': -0.6078222990036011, 'eval_rewards/accuracies': 0.4642857015132904, 'eval_rewards/margins': 1.5250685214996338, 'eval_logps/rejected': -103.44039154052734, 'eval_logps/chosen': -46.90084457397461, 'eval_logits/rejected': -1.8652076721191406, 'eval_logits/chosen': -1.832722544670105, 'epoch': 5.95}
## Intended uses & limitations
This model has not been trained to avoid specific intructions.
## Training procedure
Finetuning was done on the model Weni/WeniGPT-Agents-Mistral-1.0.6-SFT-merged with the following prompt:
```
---------------------
System_prompt:
Agora você se chama {name}, você é {occupation} e seu objetivo é {chatbot_goal}. O adjetivo que mais define a sua personalidade é {adjective} e você se comporta da seguinte forma:
{instructions_formatted}
{context_statement}
Lista de requisitos:
- Responda de forma natural, mas nunca fale sobre um assunto fora do contexto.
- Nunca traga informações do seu próprio conhecimento.
- Repito é crucial que você responda usando apenas informações do contexto.
- Nunca mencione o contexto fornecido.
- Nunca mencione a pergunta fornecida.
- Gere a resposta mais útil possível para a pergunta usando informações do conexto acima.
- Nunca elabore sobre o porque e como você fez a tarefa, apenas responda.
---------------------
```
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-06
- per_device_train_batch_size: 2
- per_device_eval_batch_size: 2
- gradient_accumulation_steps: 2
- num_gpus: 1
- total_train_batch_size: 4
- optimizer: AdamW
- lr_scheduler_type: cosine
- num_steps: 366
- quantization_type: bitsandbytes
- LoRA: ("\n - bits: 4\n - use_exllama: True\n - device_map: auto\n - use_cache: False\n - lora_r: 8\n - lora_alpha: 16\n - lora_dropout: 0.05\n - bias: none\n - target_modules: ['v_proj', 'q_proj']\n - task_type: CAUSAL_LM",)
### Training results
### Framework versions
- transformers==4.38.2
- datasets==2.18.0
- peft==0.10.0
- safetensors==0.4.2
- evaluate==0.4.1
- bitsandbytes==0.43
- huggingface_hub==0.22.2
- seqeval==1.2.2
- optimum==1.18.1
- auto-gptq==0.7.1
- gpustat==1.1.1
- deepspeed==0.14.0
- wandb==0.16.6
- trl==0.8.1
- accelerate==0.29.2
- coloredlogs==15.0.1
- traitlets==5.14.2
- autoawq@https://github.com/casper-hansen/AutoAWQ/releases/download/v0.2.4/autoawq-0.2.4+cu118-cp310-cp310-linux_x86_64.whl
### Hardware
- Cloud provided: runpod.io
| {"language": ["pt"], "license": "mit", "library_name": "trl", "tags": ["DPO", "WeniGPT"], "base_model": "Weni/WeniGPT-Agents-Mistral-1.0.6-SFT-merged", "model-index": [{"name": "Weni/WeniGPT-Agents-Mistral-1.0.6-SFT-1.0.5-DPO", "results": []}]} | Weni/WeniGPT-Agents-Mistral-1.0.6-SFT-1.0.5-DPO | null | [
"trl",
"safetensors",
"DPO",
"WeniGPT",
"pt",
"base_model:Weni/WeniGPT-Agents-Mistral-1.0.6-SFT-merged",
"license:mit",
"region:us"
] | null | 2024-04-20T01:35:40+00:00 | [] | [
"pt"
] | TAGS
#trl #safetensors #DPO #WeniGPT #pt #base_model-Weni/WeniGPT-Agents-Mistral-1.0.6-SFT-merged #license-mit #region-us
|
# Weni/WeniGPT-Agents-Mistral-1.0.6-SFT-1.0.5-DPO
This model is a fine-tuned version of [Weni/WeniGPT-Agents-Mistral-1.0.6-SFT-merged] on the dataset Weni/wenigpt-agent-dpo-1.0.0 with the DPO trainer. It is part of the WeniGPT project for Weni.
Description: Experiment on DPO with other hyperparameters and best SFT model of WeniGPT
It achieves the following results on the evaluation set:
{'eval_loss': 0.42603132128715515, 'eval_runtime': 8.1364, 'eval_samples_per_second': 3.441, 'eval_steps_per_second': 1.721, 'eval_rewards/chosen': 0.9172464609146118, 'eval_rewards/rejected': -0.6078222990036011, 'eval_rewards/accuracies': 0.4642857015132904, 'eval_rewards/margins': 1.5250685214996338, 'eval_logps/rejected': -103.44039154052734, 'eval_logps/chosen': -46.90084457397461, 'eval_logits/rejected': -1.8652076721191406, 'eval_logits/chosen': -1.832722544670105, 'epoch': 5.95}
## Intended uses & limitations
This model has not been trained to avoid specific intructions.
## Training procedure
Finetuning was done on the model Weni/WeniGPT-Agents-Mistral-1.0.6-SFT-merged with the following prompt:
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-06
- per_device_train_batch_size: 2
- per_device_eval_batch_size: 2
- gradient_accumulation_steps: 2
- num_gpus: 1
- total_train_batch_size: 4
- optimizer: AdamW
- lr_scheduler_type: cosine
- num_steps: 366
- quantization_type: bitsandbytes
- LoRA: ("\n - bits: 4\n - use_exllama: True\n - device_map: auto\n - use_cache: False\n - lora_r: 8\n - lora_alpha: 16\n - lora_dropout: 0.05\n - bias: none\n - target_modules: ['v_proj', 'q_proj']\n - task_type: CAUSAL_LM",)
### Training results
### Framework versions
- transformers==4.38.2
- datasets==2.18.0
- peft==0.10.0
- safetensors==0.4.2
- evaluate==0.4.1
- bitsandbytes==0.43
- huggingface_hub==0.22.2
- seqeval==1.2.2
- optimum==1.18.1
- auto-gptq==0.7.1
- gpustat==1.1.1
- deepspeed==0.14.0
- wandb==0.16.6
- trl==0.8.1
- accelerate==0.29.2
- coloredlogs==15.0.1
- traitlets==5.14.2
- autoawq@URL
### Hardware
- Cloud provided: URL
| [
"# Weni/WeniGPT-Agents-Mistral-1.0.6-SFT-1.0.5-DPO\n\nThis model is a fine-tuned version of [Weni/WeniGPT-Agents-Mistral-1.0.6-SFT-merged] on the dataset Weni/wenigpt-agent-dpo-1.0.0 with the DPO trainer. It is part of the WeniGPT project for Weni.\nDescription: Experiment on DPO with other hyperparameters and best SFT model of WeniGPT\n\nIt achieves the following results on the evaluation set:\n{'eval_loss': 0.42603132128715515, 'eval_runtime': 8.1364, 'eval_samples_per_second': 3.441, 'eval_steps_per_second': 1.721, 'eval_rewards/chosen': 0.9172464609146118, 'eval_rewards/rejected': -0.6078222990036011, 'eval_rewards/accuracies': 0.4642857015132904, 'eval_rewards/margins': 1.5250685214996338, 'eval_logps/rejected': -103.44039154052734, 'eval_logps/chosen': -46.90084457397461, 'eval_logits/rejected': -1.8652076721191406, 'eval_logits/chosen': -1.832722544670105, 'epoch': 5.95}",
"## Intended uses & limitations\n\nThis model has not been trained to avoid specific intructions.",
"## Training procedure\n\nFinetuning was done on the model Weni/WeniGPT-Agents-Mistral-1.0.6-SFT-merged with the following prompt:",
"### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 5e-06\n- per_device_train_batch_size: 2\n- per_device_eval_batch_size: 2\n- gradient_accumulation_steps: 2\n- num_gpus: 1\n- total_train_batch_size: 4\n- optimizer: AdamW\n- lr_scheduler_type: cosine\n- num_steps: 366\n- quantization_type: bitsandbytes\n- LoRA: (\"\\n - bits: 4\\n - use_exllama: True\\n - device_map: auto\\n - use_cache: False\\n - lora_r: 8\\n - lora_alpha: 16\\n - lora_dropout: 0.05\\n - bias: none\\n - target_modules: ['v_proj', 'q_proj']\\n - task_type: CAUSAL_LM\",)",
"### Training results",
"### Framework versions\n\n- transformers==4.38.2\n- datasets==2.18.0\n- peft==0.10.0\n- safetensors==0.4.2\n- evaluate==0.4.1\n- bitsandbytes==0.43\n- huggingface_hub==0.22.2\n- seqeval==1.2.2\n- optimum==1.18.1\n- auto-gptq==0.7.1\n- gpustat==1.1.1\n- deepspeed==0.14.0\n- wandb==0.16.6\n- trl==0.8.1\n- accelerate==0.29.2\n- coloredlogs==15.0.1\n- traitlets==5.14.2\n- autoawq@URL",
"### Hardware\n- Cloud provided: URL"
] | [
"TAGS\n#trl #safetensors #DPO #WeniGPT #pt #base_model-Weni/WeniGPT-Agents-Mistral-1.0.6-SFT-merged #license-mit #region-us \n",
"# Weni/WeniGPT-Agents-Mistral-1.0.6-SFT-1.0.5-DPO\n\nThis model is a fine-tuned version of [Weni/WeniGPT-Agents-Mistral-1.0.6-SFT-merged] on the dataset Weni/wenigpt-agent-dpo-1.0.0 with the DPO trainer. It is part of the WeniGPT project for Weni.\nDescription: Experiment on DPO with other hyperparameters and best SFT model of WeniGPT\n\nIt achieves the following results on the evaluation set:\n{'eval_loss': 0.42603132128715515, 'eval_runtime': 8.1364, 'eval_samples_per_second': 3.441, 'eval_steps_per_second': 1.721, 'eval_rewards/chosen': 0.9172464609146118, 'eval_rewards/rejected': -0.6078222990036011, 'eval_rewards/accuracies': 0.4642857015132904, 'eval_rewards/margins': 1.5250685214996338, 'eval_logps/rejected': -103.44039154052734, 'eval_logps/chosen': -46.90084457397461, 'eval_logits/rejected': -1.8652076721191406, 'eval_logits/chosen': -1.832722544670105, 'epoch': 5.95}",
"## Intended uses & limitations\n\nThis model has not been trained to avoid specific intructions.",
"## Training procedure\n\nFinetuning was done on the model Weni/WeniGPT-Agents-Mistral-1.0.6-SFT-merged with the following prompt:",
"### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 5e-06\n- per_device_train_batch_size: 2\n- per_device_eval_batch_size: 2\n- gradient_accumulation_steps: 2\n- num_gpus: 1\n- total_train_batch_size: 4\n- optimizer: AdamW\n- lr_scheduler_type: cosine\n- num_steps: 366\n- quantization_type: bitsandbytes\n- LoRA: (\"\\n - bits: 4\\n - use_exllama: True\\n - device_map: auto\\n - use_cache: False\\n - lora_r: 8\\n - lora_alpha: 16\\n - lora_dropout: 0.05\\n - bias: none\\n - target_modules: ['v_proj', 'q_proj']\\n - task_type: CAUSAL_LM\",)",
"### Training results",
"### Framework versions\n\n- transformers==4.38.2\n- datasets==2.18.0\n- peft==0.10.0\n- safetensors==0.4.2\n- evaluate==0.4.1\n- bitsandbytes==0.43\n- huggingface_hub==0.22.2\n- seqeval==1.2.2\n- optimum==1.18.1\n- auto-gptq==0.7.1\n- gpustat==1.1.1\n- deepspeed==0.14.0\n- wandb==0.16.6\n- trl==0.8.1\n- accelerate==0.29.2\n- coloredlogs==15.0.1\n- traitlets==5.14.2\n- autoawq@URL",
"### Hardware\n- Cloud provided: URL"
] |
token-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. -->
# roberta-large-finetuned-ner
This model is a fine-tuned version of [FacebookAI/roberta-large](https://huggingface.co/FacebookAI/roberta-large) 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: 2e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 6
### Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.15.2
| {"license": "mit", "tags": ["generated_from_trainer"], "base_model": "FacebookAI/roberta-large", "model-index": [{"name": "roberta-large-finetuned-ner", "results": []}]} | MinhMinh09/roberta-large-finetuned-ner | null | [
"transformers",
"safetensors",
"roberta",
"token-classification",
"generated_from_trainer",
"base_model:FacebookAI/roberta-large",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | null | 2024-04-20T01:36:19+00:00 | [] | [] | TAGS
#transformers #safetensors #roberta #token-classification #generated_from_trainer #base_model-FacebookAI/roberta-large #license-mit #autotrain_compatible #endpoints_compatible #region-us
|
# roberta-large-finetuned-ner
This model is a fine-tuned version of FacebookAI/roberta-large 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: 2e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 6
### Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.15.2
| [
"# roberta-large-finetuned-ner\n\nThis model is a fine-tuned version of FacebookAI/roberta-large 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: 2e-05\n- train_batch_size: 4\n- eval_batch_size: 4\n- seed: 42\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 6",
"### Framework versions\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 #safetensors #roberta #token-classification #generated_from_trainer #base_model-FacebookAI/roberta-large #license-mit #autotrain_compatible #endpoints_compatible #region-us \n",
"# roberta-large-finetuned-ner\n\nThis model is a fine-tuned version of FacebookAI/roberta-large 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: 2e-05\n- train_batch_size: 4\n- eval_batch_size: 4\n- seed: 42\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 6",
"### Framework versions\n\n- Transformers 4.38.2\n- Pytorch 2.2.1+cu121\n- Datasets 2.19.0\n- Tokenizers 0.15.2"
] |
text-generation | transformers |
# OpenBuddy - Open Multilingual Chatbot
GitHub and Usage Guide: [https://github.com/OpenBuddy/OpenBuddy](https://github.com/OpenBuddy/OpenBuddy)
Website and Demo: [https://openbuddy.ai](https://openbuddy.ai)
Evaluation result of this model: [Evaluation.txt](Evaluation.txt)
# Run locally with 🦙Ollama
```
ollama run openbuddy/openbuddy-llama3-8b-v21.1-8k
```
# Copyright Notice
**Built with Meta Llama 3**
License: https://llama.meta.com/llama3/license/
Acceptable Use Policy: https://llama.meta.com/llama3/use-policy
This model is intended for use in English and Chinese.
# Prompt Format
We recommend using the fast tokenizer from `transformers`, which should be enabled by default in the `transformers` and `vllm` libraries. Other implementations including `sentencepiece` may not work as expected, especially for special tokens like `<|role|>`, `<|says|>` and `<|end|>`.
```
<|role|>system<|says|>You(assistant) are a helpful, respectful and honest INTP-T AI Assistant named Buddy. You are talking to a human(user).
Always answer as helpfully and logically as possible, while being safe. Your answers should not include any harmful, political, religious, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature.
You cannot access the internet, but you have vast knowledge, cutoff: 2023-04.
You are trained by OpenBuddy team, (https://openbuddy.ai, https://github.com/OpenBuddy/OpenBuddy), not related to GPT or OpenAI.<|end|>
<|role|>user<|says|>History input 1<|end|>
<|role|>assistant<|says|>History output 1<|end|>
<|role|>user<|says|>History input 2<|end|>
<|role|>assistant<|says|>History output 2<|end|>
<|role|>user<|says|>Current input<|end|>
<|role|>assistant<|says|>
```
This format is also defined in `tokenizer_config.json`, which means you can directly use `vllm` to deploy an OpenAI-like API service. For more information, please refer to the [vllm documentation](https://docs.vllm.ai/en/latest/serving/openai_compatible_server.html).
## Disclaimer
All OpenBuddy models have inherent limitations and may potentially produce outputs that are erroneous, harmful, offensive, or otherwise undesirable. Users should not use these models in critical or high-stakes situations that may lead to personal injury, property damage, or significant losses. Examples of such scenarios include, but are not limited to, the medical field, controlling software and hardware systems that may cause harm, and making important financial or legal decisions.
OpenBuddy is provided "as-is" without any warranty of any kind, either express or implied, including, but not limited to, the implied warranties of merchantability, fitness for a particular purpose, and non-infringement. In no event shall the authors, contributors, or copyright holders be liable for any claim, damages, or other liabilities, whether in an action of contract, tort, or otherwise, arising from, out of, or in connection with the software or the use or other dealings in the software.
By using OpenBuddy, you agree to these terms and conditions, and acknowledge that you understand the potential risks associated with its use. You also agree to indemnify and hold harmless the authors, contributors, and copyright holders from any claims, damages, or liabilities arising from your use of OpenBuddy.
## 免责声明
所有OpenBuddy模型均存在固有的局限性，可能产生错误的、有害的、冒犯性的或其他不良的输出。用户在关键或高风险场景中应谨慎行事，不要使用这些模型，以免导致人身伤害、财产损失或重大损失。此类场景的例子包括但不限于医疗领域、可能导致伤害的软硬件系统的控制以及进行重要的财务或法律决策。
OpenBuddy按“原样”提供，不附带任何种类的明示或暗示的保证，包括但不限于适销性、特定目的的适用性和非侵权的暗示保证。在任何情况下，作者、贡献者或版权所有者均不对因软件或使用或其他软件交易而产生的任何索赔、损害赔偿或其他责任（无论是合同、侵权还是其他原因）承担责任。
使用OpenBuddy即表示您同意这些条款和条件，并承认您了解其使用可能带来的潜在风险。您还同意赔偿并使作者、贡献者和版权所有者免受因您使用OpenBuddy而产生的任何索赔、损害赔偿或责任的影响。 | {"language": ["zh", "en", "fr", "de", "ja", "ko", "it", "fi"], "license": "other", "tags": ["llama-3"], "pipeline_tag": "text-generation", "license_name": "llama3", "license_link": "https://llama.meta.com/llama3/license/"} | OpenBuddy/openbuddy-llama3-8b-v21.1-8k | null | [
"transformers",
"safetensors",
"llama",
"text-generation",
"llama-3",
"conversational",
"zh",
"en",
"fr",
"de",
"ja",
"ko",
"it",
"fi",
"license:other",
"autotrain_compatible",
"endpoints_compatible",
"has_space",
"text-generation-inference",
"region:us"
] | null | 2024-04-20T01:36:51+00:00 | [] | [
"zh",
"en",
"fr",
"de",
"ja",
"ko",
"it",
"fi"
] | TAGS
#transformers #safetensors #llama #text-generation #llama-3 #conversational #zh #en #fr #de #ja #ko #it #fi #license-other #autotrain_compatible #endpoints_compatible #has_space #text-generation-inference #region-us
|
# OpenBuddy - Open Multilingual Chatbot
GitHub and Usage Guide: URL
Website and Demo: URL
Evaluation result of this model: URL
!Demo
# Run locally with Ollama
# Copyright Notice
Built with Meta Llama 3
License: URL
Acceptable Use Policy: URL
This model is intended for use in English and Chinese.
# Prompt Format
We recommend using the fast tokenizer from 'transformers', which should be enabled by default in the 'transformers' and 'vllm' libraries. Other implementations including 'sentencepiece' may not work as expected, especially for special tokens like '<|role|>', '<|says|>' and '<|end|>'.
This format is also defined in 'tokenizer_config.json', which means you can directly use 'vllm' to deploy an OpenAI-like API service. For more information, please refer to the vllm documentation.
## Disclaimer
All OpenBuddy models have inherent limitations and may potentially produce outputs that are erroneous, harmful, offensive, or otherwise undesirable. Users should not use these models in critical or high-stakes situations that may lead to personal injury, property damage, or significant losses. Examples of such scenarios include, but are not limited to, the medical field, controlling software and hardware systems that may cause harm, and making important financial or legal decisions.
OpenBuddy is provided "as-is" without any warranty of any kind, either express or implied, including, but not limited to, the implied warranties of merchantability, fitness for a particular purpose, and non-infringement. In no event shall the authors, contributors, or copyright holders be liable for any claim, damages, or other liabilities, whether in an action of contract, tort, or otherwise, arising from, out of, or in connection with the software or the use or other dealings in the software.
By using OpenBuddy, you agree to these terms and conditions, and acknowledge that you understand the potential risks associated with its use. You also agree to indemnify and hold harmless the authors, contributors, and copyright holders from any claims, damages, or liabilities arising from your use of OpenBuddy.
## 免责声明
所有OpenBuddy模型均存在固有的局限性，可能产生错误的、有害的、冒犯性的或其他不良的输出。用户在关键或高风险场景中应谨慎行事，不要使用这些模型，以免导致人身伤害、财产损失或重大损失。此类场景的例子包括但不限于医疗领域、可能导致伤害的软硬件系统的控制以及进行重要的财务或法律决策。
OpenBuddy按“原样”提供，不附带任何种类的明示或暗示的保证，包括但不限于适销性、特定目的的适用性和非侵权的暗示保证。在任何情况下，作者、贡献者或版权所有者均不对因软件或使用或其他软件交易而产生的任何索赔、损害赔偿或其他责任（无论是合同、侵权还是其他原因）承担责任。
使用OpenBuddy即表示您同意这些条款和条件，并承认您了解其使用可能带来的潜在风险。您还同意赔偿并使作者、贡献者和版权所有者免受因您使用OpenBuddy而产生的任何索赔、损害赔偿或责任的影响。 | [
"# OpenBuddy - Open Multilingual Chatbot\n\n\nGitHub and Usage Guide: URL\n\nWebsite and Demo: URL\n\nEvaluation result of this model: URL\n\n!Demo",
"# Run locally with Ollama",
"# Copyright Notice\n\nBuilt with Meta Llama 3\n\nLicense: URL\n\nAcceptable Use Policy: URL\n\nThis model is intended for use in English and Chinese.",
"# Prompt Format\n\nWe recommend using the fast tokenizer from 'transformers', which should be enabled by default in the 'transformers' and 'vllm' libraries. Other implementations including 'sentencepiece' may not work as expected, especially for special tokens like '<|role|>', '<|says|>' and '<|end|>'.\n\n\n\n\nThis format is also defined in 'tokenizer_config.json', which means you can directly use 'vllm' to deploy an OpenAI-like API service. For more information, please refer to the vllm documentation.",
"## Disclaimer\n\nAll OpenBuddy models have inherent limitations and may potentially produce outputs that are erroneous, harmful, offensive, or otherwise undesirable. Users should not use these models in critical or high-stakes situations that may lead to personal injury, property damage, or significant losses. Examples of such scenarios include, but are not limited to, the medical field, controlling software and hardware systems that may cause harm, and making important financial or legal decisions.\n\nOpenBuddy is provided \"as-is\" without any warranty of any kind, either express or implied, including, but not limited to, the implied warranties of merchantability, fitness for a particular purpose, and non-infringement. In no event shall the authors, contributors, or copyright holders be liable for any claim, damages, or other liabilities, whether in an action of contract, tort, or otherwise, arising from, out of, or in connection with the software or the use or other dealings in the software.\n\nBy using OpenBuddy, you agree to these terms and conditions, and acknowledge that you understand the potential risks associated with its use. You also agree to indemnify and hold harmless the authors, contributors, and copyright holders from any claims, damages, or liabilities arising from your use of OpenBuddy.",
"## 免责声明\n\n所有OpenBuddy模型均存在固有的局限性，可能产生错误的、有害的、冒犯性的或其他不良的输出。用户在关键或高风险场景中应谨慎行事，不要使用这些模型，以免导致人身伤害、财产损失或重大损失。此类场景的例子包括但不限于医疗领域、可能导致伤害的软硬件系统的控制以及进行重要的财务或法律决策。\n\nOpenBuddy按“原样”提供，不附带任何种类的明示或暗示的保证，包括但不限于适销性、特定目的的适用性和非侵权的暗示保证。在任何情况下，作者、贡献者或版权所有者均不对因软件或使用或其他软件交易而产生的任何索赔、损害赔偿或其他责任（无论是合同、侵权还是其他原因）承担责任。\n\n使用OpenBuddy即表示您同意这些条款和条件，并承认您了解其使用可能带来的潜在风险。您还同意赔偿并使作者、贡献者和版权所有者免受因您使用OpenBuddy而产生的任何索赔、损害赔偿或责任的影响。"
] | [
"TAGS\n#transformers #safetensors #llama #text-generation #llama-3 #conversational #zh #en #fr #de #ja #ko #it #fi #license-other #autotrain_compatible #endpoints_compatible #has_space #text-generation-inference #region-us \n",
"# OpenBuddy - Open Multilingual Chatbot\n\n\nGitHub and Usage Guide: URL\n\nWebsite and Demo: URL\n\nEvaluation result of this model: URL\n\n!Demo",
"# Run locally with Ollama",
"# Copyright Notice\n\nBuilt with Meta Llama 3\n\nLicense: URL\n\nAcceptable Use Policy: URL\n\nThis model is intended for use in English and Chinese.",
"# Prompt Format\n\nWe recommend using the fast tokenizer from 'transformers', which should be enabled by default in the 'transformers' and 'vllm' libraries. Other implementations including 'sentencepiece' may not work as expected, especially for special tokens like '<|role|>', '<|says|>' and '<|end|>'.\n\n\n\n\nThis format is also defined in 'tokenizer_config.json', which means you can directly use 'vllm' to deploy an OpenAI-like API service. For more information, please refer to the vllm documentation.",
"## Disclaimer\n\nAll OpenBuddy models have inherent limitations and may potentially produce outputs that are erroneous, harmful, offensive, or otherwise undesirable. Users should not use these models in critical or high-stakes situations that may lead to personal injury, property damage, or significant losses. Examples of such scenarios include, but are not limited to, the medical field, controlling software and hardware systems that may cause harm, and making important financial or legal decisions.\n\nOpenBuddy is provided \"as-is\" without any warranty of any kind, either express or implied, including, but not limited to, the implied warranties of merchantability, fitness for a particular purpose, and non-infringement. In no event shall the authors, contributors, or copyright holders be liable for any claim, damages, or other liabilities, whether in an action of contract, tort, or otherwise, arising from, out of, or in connection with the software or the use or other dealings in the software.\n\nBy using OpenBuddy, you agree to these terms and conditions, and acknowledge that you understand the potential risks associated with its use. You also agree to indemnify and hold harmless the authors, contributors, and copyright holders from any claims, damages, or liabilities arising from your use of OpenBuddy.",
"## 免责声明\n\n所有OpenBuddy模型均存在固有的局限性，可能产生错误的、有害的、冒犯性的或其他不良的输出。用户在关键或高风险场景中应谨慎行事，不要使用这些模型，以免导致人身伤害、财产损失或重大损失。此类场景的例子包括但不限于医疗领域、可能导致伤害的软硬件系统的控制以及进行重要的财务或法律决策。\n\nOpenBuddy按“原样”提供，不附带任何种类的明示或暗示的保证，包括但不限于适销性、特定目的的适用性和非侵权的暗示保证。在任何情况下，作者、贡献者或版权所有者均不对因软件或使用或其他软件交易而产生的任何索赔、损害赔偿或其他责任（无论是合同、侵权还是其他原因）承担责任。\n\n使用OpenBuddy即表示您同意这些条款和条件，并承认您了解其使用可能带来的潜在风险。您还同意赔偿并使作者、贡献者和版权所有者免受因您使用OpenBuddy而产生的任何索赔、损害赔偿或责任的影响。"
] |
text-to-image | diffusers |
<!-- This model card has been generated automatically according to the information the training script had access to. You
should probably proofread and complete it, then remove this comment. -->
# Critical Dream - cosmicBboy/stable-diffusion-xl-base-1.0-lora-dreambooth-critdream-v0.6.2
<Gallery />
## Model description
These are cosmicBboy/stable-diffusion-xl-base-1.0-lora-dreambooth-critdream-v0.6.2 LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0, for the purposes of
generating images for the [Critical Dream](https://github.com/cosmicBboy/critical-dream)
project.
The weights were trained using [DreamBooth](https://dreambooth.github.io/).
LoRA for the text encoder was enabled: True.
Special VAE used for training: stabilityai/sdxl-vae.
## Trigger words
You should use a picture of [dm-matt-mercer], a dungeon master. background is a forest. fantasy art style, high quality, highly detailed, sharp focus" to trigger the image generation.
## Download model
Weights for this model are available in Safetensors format.
[Download](cosmicBboy/stable-diffusion-xl-base-1.0-lora-dreambooth-critdream-v0.6.2/tree/main) them in the Files & versions tab.
## Tracker run link
https://wandb.ai/nielsbantilan/dreambooth-lora-sd-xl/runs/se5b4ews
## Intended uses & limitations
#### How to use
```python
# TODO: add an example code snippet for running this diffusion pipeline
```
#### Limitations and bias
[TODO: provide examples of latent issues and potential remediations]
## Training details
[TODO: describe the data used to train the model] | {"license": "openrail++", "library_name": "diffusers", "tags": ["text-to-image", "stable-diffusion-xl", "stable-diffusion-xl-diffusers", "text-to-image", "diffusers", "lora", "template:sd-lora"], "base_model": "stabilityai/stable-diffusion-xl-base-1.0", "prompt": "a picture of [dm-matt-mercer], a dungeon master. background is a forest. fantasy art style, high quality, highly detailed, sharp focus\"", "widget": [{"text": "a picture of [dm-matt-mercer]", "output": {"url": "image_0.png"}}, {"text": "a picture of [dm-matt-mercer]", "output": {"url": "image_1.png"}}, {"text": "a picture of a dungeon master.", "output": {"url": "image_2.png"}}, {"text": "a picture of a dungeon master.", "output": {"url": "image_3.png"}}, {"text": "a picture of [critrole-fjord], a male half-orc warlock. background is a forest. fantasy art style, high quality, highly detailed, sharp focus", "output": {"url": "image_4.png"}}, {"text": "a picture of [critrole-fjord], a male half-orc warlock. background is a forest. fantasy art style, high quality, highly detailed, sharp focus", "output": {"url": "image_5.png"}}, {"text": "a picture of a male half-orc warlock", "output": {"url": "image_6.png"}}, {"text": "a picture of a male half-orc warlock", "output": {"url": "image_7.png"}}, {"text": "a picture of [critrole-beau], a female human monk. background is a forest. fantasy art style, high quality, highly detailed, sharp focus", "output": {"url": "image_8.png"}}, {"text": "a picture of [critrole-beau], a female human monk. background is a forest. fantasy art style, high quality, highly detailed, sharp focus", "output": {"url": "image_9.png"}}, {"text": "a picture of a female human monk", "output": {"url": "image_10.png"}}, {"text": "a picture of a female human monk", "output": {"url": "image_11.png"}}, {"text": "a picture of [critrole-caduceus], a male firbolg cleric. background is a forest. fantasy art style, high quality, highly detailed, sharp focus", "output": {"url": "image_12.png"}}, {"text": "a picture of [critrole-caduceus], a male firbolg cleric. background is a forest. fantasy art style, high quality, highly detailed, sharp focus", "output": {"url": "image_13.png"}}, {"text": "a picture of a male firbolg cleric", "output": {"url": "image_14.png"}}, {"text": "a picture of a male firbolg cleric", "output": {"url": "image_15.png"}}, {"text": "a picture of [critrole-caleb], a male human wizard. background is a forest. fantasy art style, high quality, highly detailed, sharp focus", "output": {"url": "image_16.png"}}, {"text": "a picture of [critrole-caleb], a male human wizard. background is a forest. fantasy art style, high quality, highly detailed, sharp focus", "output": {"url": "image_17.png"}}, {"text": "a picture of a male human wizard", "output": {"url": "image_18.png"}}, {"text": "a picture of a male human wizard", "output": {"url": "image_19.png"}}, {"text": "a picture of [critrole-jester], a female tiefling cleric. background is a forest. fantasy art style, high quality, highly detailed, sharp focus", "output": {"url": "image_20.png"}}, {"text": "a picture of [critrole-jester], a female tiefling cleric. background is a forest. fantasy art style, high quality, highly detailed, sharp focus", "output": {"url": "image_21.png"}}, {"text": "a picture of a female tiefling cleric", "output": {"url": "image_22.png"}}, {"text": "a picture of a female tiefling cleric", "output": {"url": "image_23.png"}}, {"text": "a picture of [critrole-nott], a female goblin rogue. background is a forest. fantasy art style, high quality, highly detailed, sharp focus", "output": {"url": "image_24.png"}}, {"text": "a picture of [critrole-nott], a female goblin rogue. background is a forest. fantasy art style, high quality, highly detailed, sharp focus", "output": {"url": "image_25.png"}}, {"text": "a picture of a female goblin rogue", "output": {"url": "image_26.png"}}, {"text": "a picture of a female goblin rogue", "output": {"url": "image_27.png"}}, {"text": "a picture of [critrole-veth], a female halfling rogue/wizard. background is a forest. fantasy art style, high quality, highly detailed, sharp focus", "output": {"url": "image_28.png"}}, {"text": "a picture of [critrole-veth], a female halfling rogue/wizard. background is a forest. fantasy art style, high quality, highly detailed, sharp focus", "output": {"url": "image_29.png"}}, {"text": "a picture of a female halfling rogue/wizard", "output": {"url": "image_30.png"}}, {"text": "a picture of a female halfling rogue/wizard", "output": {"url": "image_31.png"}}, {"text": "a picture of [critrole-yasha], a female aasimar barbarian. background is a forest. fantasy art style, high quality, highly detailed, sharp focus", "output": {"url": "image_32.png"}}, {"text": "a picture of [critrole-yasha], a female aasimar barbarian. background is a forest. fantasy art style, high quality, highly detailed, sharp focus", "output": {"url": "image_33.png"}}, {"text": "a picture of a female aasimar barbarian", "output": {"url": "image_34.png"}}, {"text": "a picture of a female aasimar barbarian", "output": {"url": "image_35.png"}}, {"text": "a picture of [critrole-mollymauk], a male tiefling blood hunter. background is a forest. fantasy art style, high quality, highly detailed, sharp focus", "output": {"url": "image_36.png"}}, {"text": "a picture of [critrole-mollymauk], a male tiefling blood hunter. background is a forest. fantasy art style, high quality, highly detailed, sharp focus", "output": {"url": "image_37.png"}}, {"text": "a picture of a male tiefling blood hunter", "output": {"url": "image_38.png"}}, {"text": "a picture of a male tiefling blood hunter", "output": {"url": "image_39.png"}}, {"text": "a picture of [critrole-essek], a male drow wizard. background is a forest. fantasy art style, high quality, highly detailed, sharp focus", "output": {"url": "image_40.png"}}, {"text": "a picture of [critrole-essek], a male drow wizard. background is a forest. fantasy art style, high quality, highly detailed, sharp focus", "output": {"url": "image_41.png"}}, {"text": "a picture of a male drow wizard", "output": {"url": "image_42.png"}}, {"text": "a picture of a male drow wizard", "output": {"url": "image_43.png"}}]} | cosmicBboy/stable-diffusion-xl-base-1.0-lora-dreambooth-critdream-v0.6.2 | null | [
"diffusers",
"text-to-image",
"stable-diffusion-xl",
"stable-diffusion-xl-diffusers",
"lora",
"template:sd-lora",
"base_model:stabilityai/stable-diffusion-xl-base-1.0",
"license:openrail++",
"region:us"
] | null | 2024-04-20T01:43:59+00:00 | [] | [] | TAGS
#diffusers #text-to-image #stable-diffusion-xl #stable-diffusion-xl-diffusers #lora #template-sd-lora #base_model-stabilityai/stable-diffusion-xl-base-1.0 #license-openrail++ #region-us
|
# Critical Dream - cosmicBboy/stable-diffusion-xl-base-1.0-lora-dreambooth-critdream-v0.6.2
<Gallery />
## Model description
These are cosmicBboy/stable-diffusion-xl-base-1.0-lora-dreambooth-critdream-v0.6.2 LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0, for the purposes of
generating images for the Critical Dream
project.
The weights were trained using DreamBooth.
LoRA for the text encoder was enabled: True.
Special VAE used for training: stabilityai/sdxl-vae.
## Trigger words
You should use a picture of [dm-matt-mercer], a dungeon master. background is a forest. fantasy art style, high quality, highly detailed, sharp focus" to trigger the image generation.
## Download model
Weights for this model are available in Safetensors format.
Download them in the Files & versions tab.
## Tracker run link
URL
## Intended uses & limitations
#### How to use
#### Limitations and bias
[TODO: provide examples of latent issues and potential remediations]
## Training details
[TODO: describe the data used to train the model] | [
"# Critical Dream - cosmicBboy/stable-diffusion-xl-base-1.0-lora-dreambooth-critdream-v0.6.2\n\n<Gallery />",
"## Model description\n\nThese are cosmicBboy/stable-diffusion-xl-base-1.0-lora-dreambooth-critdream-v0.6.2 LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0, for the purposes of\ngenerating images for the Critical Dream\nproject.\n\nThe weights were trained using DreamBooth.\n\nLoRA for the text encoder was enabled: True.\n\nSpecial VAE used for training: stabilityai/sdxl-vae.",
"## Trigger words\n\nYou should use a picture of [dm-matt-mercer], a dungeon master. background is a forest. fantasy art style, high quality, highly detailed, sharp focus\" 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.",
"## Tracker run link\n\nURL",
"## Intended uses & limitations",
"#### How to use",
"#### Limitations and bias\n\n[TODO: provide examples of latent issues and potential remediations]",
"## Training details\n\n[TODO: describe the data used to train the model]"
] | [
"TAGS\n#diffusers #text-to-image #stable-diffusion-xl #stable-diffusion-xl-diffusers #lora #template-sd-lora #base_model-stabilityai/stable-diffusion-xl-base-1.0 #license-openrail++ #region-us \n",
"# Critical Dream - cosmicBboy/stable-diffusion-xl-base-1.0-lora-dreambooth-critdream-v0.6.2\n\n<Gallery />",
"## Model description\n\nThese are cosmicBboy/stable-diffusion-xl-base-1.0-lora-dreambooth-critdream-v0.6.2 LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0, for the purposes of\ngenerating images for the Critical Dream\nproject.\n\nThe weights were trained using DreamBooth.\n\nLoRA for the text encoder was enabled: True.\n\nSpecial VAE used for training: stabilityai/sdxl-vae.",
"## Trigger words\n\nYou should use a picture of [dm-matt-mercer], a dungeon master. background is a forest. fantasy art style, high quality, highly detailed, sharp focus\" 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.",
"## Tracker run link\n\nURL",
"## Intended uses & limitations",
"#### How to use",
"#### Limitations and bias\n\n[TODO: provide examples of latent issues and potential remediations]",
"## Training details\n\n[TODO: describe the data used to train the model]"
] |
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": []} | HikariLight/Mistral-SUFT-10-5e-05-1-em | null | [
"transformers",
"safetensors",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null | 2024-04-20T01:44:28+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 |
# DavidAU/NeuralMarioMonarch-7B-slerp-Q6_K-GGUF
This model was converted to GGUF format from [`Kukedlc/NeuralMarioMonarch-7B-slerp`](https://huggingface.co/Kukedlc/NeuralMarioMonarch-7B-slerp) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
Refer to the [original model card](https://huggingface.co/Kukedlc/NeuralMarioMonarch-7B-slerp) for more details on the model.
## Use with llama.cpp
Install llama.cpp through brew.
```bash
brew install ggerganov/ggerganov/llama.cpp
```
Invoke the llama.cpp server or the CLI.
CLI:
```bash
llama-cli --hf-repo DavidAU/NeuralMarioMonarch-7B-slerp-Q6_K-GGUF --model neuralmariomonarch-7b-slerp.Q6_K.gguf -p "The meaning to life and the universe is"
```
Server:
```bash
llama-server --hf-repo DavidAU/NeuralMarioMonarch-7B-slerp-Q6_K-GGUF --model neuralmariomonarch-7b-slerp.Q6_K.gguf -c 2048
```
Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well.
```
git clone https://github.com/ggerganov/llama.cpp && cd llama.cpp && make && ./main -m neuralmariomonarch-7b-slerp.Q6_K.gguf -n 128
```
| {"license": "apache-2.0", "tags": ["merge", "mergekit", "lazymergekit", "mlabonne/Monarch-7B", "vanillaOVO/supermario_v4", "llama-cpp", "gguf-my-repo"], "base_model": ["mlabonne/Monarch-7B", "vanillaOVO/supermario_v4"], "model-index": [{"name": "NeuralMarioMonarch-7B-slerp", "results": [{"task": {"type": "text-generation", "name": "Text Generation"}, "dataset": {"name": "AI2 Reasoning Challenge (25-Shot)", "type": "ai2_arc", "config": "ARC-Challenge", "split": "test", "args": {"num_few_shot": 25}}, "metrics": [{"type": "acc_norm", "value": 73.81, "name": "normalized accuracy"}], "source": {"url": "https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Kukedlc/NeuralMarioMonarch-7B-slerp", "name": "Open LLM Leaderboard"}}, {"task": {"type": "text-generation", "name": "Text Generation"}, "dataset": {"name": "HellaSwag (10-Shot)", "type": "hellaswag", "split": "validation", "args": {"num_few_shot": 10}}, "metrics": [{"type": "acc_norm", "value": 89.04, "name": "normalized accuracy"}], "source": {"url": "https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Kukedlc/NeuralMarioMonarch-7B-slerp", "name": "Open LLM Leaderboard"}}, {"task": {"type": "text-generation", "name": "Text Generation"}, "dataset": {"name": "MMLU (5-Shot)", "type": "cais/mmlu", "config": "all", "split": "test", "args": {"num_few_shot": 5}}, "metrics": [{"type": "acc", "value": 64.61, "name": "accuracy"}], "source": {"url": "https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Kukedlc/NeuralMarioMonarch-7B-slerp", "name": "Open LLM Leaderboard"}}, {"task": {"type": "text-generation", "name": "Text Generation"}, "dataset": {"name": "TruthfulQA (0-shot)", "type": "truthful_qa", "config": "multiple_choice", "split": "validation", "args": {"num_few_shot": 0}}, "metrics": [{"type": "mc2", "value": 74.97}], "source": {"url": "https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Kukedlc/NeuralMarioMonarch-7B-slerp", "name": "Open LLM Leaderboard"}}, {"task": {"type": "text-generation", "name": "Text Generation"}, "dataset": {"name": "Winogrande (5-shot)", "type": "winogrande", "config": "winogrande_xl", "split": "validation", "args": {"num_few_shot": 5}}, "metrics": [{"type": "acc", "value": 85.0, "name": "accuracy"}], "source": {"url": "https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Kukedlc/NeuralMarioMonarch-7B-slerp", "name": "Open LLM Leaderboard"}}, {"task": {"type": "text-generation", "name": "Text Generation"}, "dataset": {"name": "GSM8k (5-shot)", "type": "gsm8k", "config": "main", "split": "test", "args": {"num_few_shot": 5}}, "metrics": [{"type": "acc", "value": 69.22, "name": "accuracy"}], "source": {"url": "https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Kukedlc/NeuralMarioMonarch-7B-slerp", "name": "Open LLM Leaderboard"}}]}]} | DavidAU/NeuralMarioMonarch-7B-slerp-Q6_K-GGUF | null | [
"gguf",
"merge",
"mergekit",
"lazymergekit",
"mlabonne/Monarch-7B",
"vanillaOVO/supermario_v4",
"llama-cpp",
"gguf-my-repo",
"base_model:mlabonne/Monarch-7B",
"base_model:vanillaOVO/supermario_v4",
"license:apache-2.0",
"model-index",
"region:us"
] | null | 2024-04-20T01:44:57+00:00 | [] | [] | TAGS
#gguf #merge #mergekit #lazymergekit #mlabonne/Monarch-7B #vanillaOVO/supermario_v4 #llama-cpp #gguf-my-repo #base_model-mlabonne/Monarch-7B #base_model-vanillaOVO/supermario_v4 #license-apache-2.0 #model-index #region-us
|
# DavidAU/NeuralMarioMonarch-7B-slerp-Q6_K-GGUF
This model was converted to GGUF format from 'Kukedlc/NeuralMarioMonarch-7B-slerp' using URL via the URL's GGUF-my-repo space.
Refer to the original model card for more details on the model.
## Use with URL
Install URL through brew.
Invoke the URL server or the CLI.
CLI:
Server:
Note: You can also use this checkpoint directly through the usage steps listed in the URL repo as well.
| [
"# DavidAU/NeuralMarioMonarch-7B-slerp-Q6_K-GGUF\nThis model was converted to GGUF format from 'Kukedlc/NeuralMarioMonarch-7B-slerp' using URL via the URL's GGUF-my-repo space.\nRefer to the original model card for more details on the model.",
"## Use with URL\n\nInstall URL through brew.\n\n\nInvoke the URL server or the CLI.\n\nCLI:\n\n\n\nServer:\n\n\n\nNote: You can also use this checkpoint directly through the usage steps listed in the URL repo as well."
] | [
"TAGS\n#gguf #merge #mergekit #lazymergekit #mlabonne/Monarch-7B #vanillaOVO/supermario_v4 #llama-cpp #gguf-my-repo #base_model-mlabonne/Monarch-7B #base_model-vanillaOVO/supermario_v4 #license-apache-2.0 #model-index #region-us \n",
"# DavidAU/NeuralMarioMonarch-7B-slerp-Q6_K-GGUF\nThis model was converted to GGUF format from 'Kukedlc/NeuralMarioMonarch-7B-slerp' using URL via the URL's GGUF-my-repo space.\nRefer to the original model card for more details on the model.",
"## Use with URL\n\nInstall URL through brew.\n\n\nInvoke the URL server or the CLI.\n\nCLI:\n\n\n\nServer:\n\n\n\nNote: You can also use this checkpoint directly through the usage steps listed in the URL repo as well."
] |
text-generation | transformers | # Shi-Ci Language Identify & Decode Expositor
**8B**, Ruozhiba...
* [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B)
**Chinese**
Released as an early preview of our v3 LLMs.
The v3 series covers the "Shi-Ci", "AnFeng" and "Cecilia" LLM products.
The sizes are labelled from small to large "Nano" "Leap" "Pattern" "Avocet "Robin" "Kestrel" | {"language": ["en"], "license": "cc-by-nc-sa-4.0", "library_name": "transformers", "pipeline_tag": "text-generation", "inference": true} | NLPark/Test0_SLIDE | null | [
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"en",
"license:cc-by-nc-sa-4.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-04-20T01:45:16+00:00 | [] | [
"en"
] | TAGS
#transformers #safetensors #llama #text-generation #conversational #en #license-cc-by-nc-sa-4.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us
| # Shi-Ci Language Identify & Decode Expositor
8B, Ruozhiba...
* meta-llama/Meta-Llama-3-8B
Chinese
Released as an early preview of our v3 LLMs.
The v3 series covers the "Shi-Ci", "AnFeng" and "Cecilia" LLM products.
The sizes are labelled from small to large "Nano" "Leap" "Pattern" "Avocet "Robin" "Kestrel" | [
"# Shi-Ci Language Identify & Decode Expositor\n8B, Ruozhiba...\n\n* meta-llama/Meta-Llama-3-8B\n\nChinese\nReleased as an early preview of our v3 LLMs.\nThe v3 series covers the \"Shi-Ci\", \"AnFeng\" and \"Cecilia\" LLM products.\nThe sizes are labelled from small to large \"Nano\" \"Leap\" \"Pattern\" \"Avocet \"Robin\" \"Kestrel\""
] | [
"TAGS\n#transformers #safetensors #llama #text-generation #conversational #en #license-cc-by-nc-sa-4.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n",
"# Shi-Ci Language Identify & Decode Expositor\n8B, Ruozhiba...\n\n* meta-llama/Meta-Llama-3-8B\n\nChinese\nReleased as an early preview of our v3 LLMs.\nThe v3 series covers the \"Shi-Ci\", \"AnFeng\" and \"Cecilia\" LLM products.\nThe sizes are labelled from small to large \"Nano\" \"Leap\" \"Pattern\" \"Avocet \"Robin\" \"Kestrel\""
] |
null | null |
# DavidAU/NeuralKrishna-7B-V2-DPO-Q6_K-GGUF
This model was converted to GGUF format from [`Kukedlc/NeuralKrishna-7B-V2-DPO`](https://huggingface.co/Kukedlc/NeuralKrishna-7B-V2-DPO) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
Refer to the [original model card](https://huggingface.co/Kukedlc/NeuralKrishna-7B-V2-DPO) for more details on the model.
## Use with llama.cpp
Install llama.cpp through brew.
```bash
brew install ggerganov/ggerganov/llama.cpp
```
Invoke the llama.cpp server or the CLI.
CLI:
```bash
llama-cli --hf-repo DavidAU/NeuralKrishna-7B-V2-DPO-Q6_K-GGUF --model neuralkrishna-7b-v2-dpo.Q6_K.gguf -p "The meaning to life and the universe is"
```
Server:
```bash
llama-server --hf-repo DavidAU/NeuralKrishna-7B-V2-DPO-Q6_K-GGUF --model neuralkrishna-7b-v2-dpo.Q6_K.gguf -c 2048
```
Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well.
```
git clone https://github.com/ggerganov/llama.cpp && cd llama.cpp && make && ./main -m neuralkrishna-7b-v2-dpo.Q6_K.gguf -n 128
```
| {"license": "apache-2.0", "tags": ["llama-cpp", "gguf-my-repo"], "model-index": [{"name": "NeuralKrishna-7B-V2-DPO", "results": [{"task": {"type": "text-generation", "name": "Text Generation"}, "dataset": {"name": "AI2 Reasoning Challenge (25-Shot)", "type": "ai2_arc", "config": "ARC-Challenge", "split": "test", "args": {"num_few_shot": 25}}, "metrics": [{"type": "acc_norm", "value": 74.06, "name": "normalized accuracy"}], "source": {"url": "https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Kukedlc/NeuralKrishna-7B-V2-DPO", "name": "Open LLM Leaderboard"}}, {"task": {"type": "text-generation", "name": "Text Generation"}, "dataset": {"name": "HellaSwag (10-Shot)", "type": "hellaswag", "split": "validation", "args": {"num_few_shot": 10}}, "metrics": [{"type": "acc_norm", "value": 88.97, "name": "normalized accuracy"}], "source": {"url": "https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Kukedlc/NeuralKrishna-7B-V2-DPO", "name": "Open LLM Leaderboard"}}, {"task": {"type": "text-generation", "name": "Text Generation"}, "dataset": {"name": "MMLU (5-Shot)", "type": "cais/mmlu", "config": "all", "split": "test", "args": {"num_few_shot": 5}}, "metrics": [{"type": "acc", "value": 64.41, "name": "accuracy"}], "source": {"url": "https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Kukedlc/NeuralKrishna-7B-V2-DPO", "name": "Open LLM Leaderboard"}}, {"task": {"type": "text-generation", "name": "Text Generation"}, "dataset": {"name": "TruthfulQA (0-shot)", "type": "truthful_qa", "config": "multiple_choice", "split": "validation", "args": {"num_few_shot": 0}}, "metrics": [{"type": "mc2", "value": 76.19}], "source": {"url": "https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Kukedlc/NeuralKrishna-7B-V2-DPO", "name": "Open LLM Leaderboard"}}, {"task": {"type": "text-generation", "name": "Text Generation"}, "dataset": {"name": "Winogrande (5-shot)", "type": "winogrande", "config": "winogrande_xl", "split": "validation", "args": {"num_few_shot": 5}}, "metrics": [{"type": "acc", "value": 84.29, "name": "accuracy"}], "source": {"url": "https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Kukedlc/NeuralKrishna-7B-V2-DPO", "name": "Open LLM Leaderboard"}}, {"task": {"type": "text-generation", "name": "Text Generation"}, "dataset": {"name": "GSM8k (5-shot)", "type": "gsm8k", "config": "main", "split": "test", "args": {"num_few_shot": 5}}, "metrics": [{"type": "acc", "value": 68.08, "name": "accuracy"}], "source": {"url": "https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Kukedlc/NeuralKrishna-7B-V2-DPO", "name": "Open LLM Leaderboard"}}]}]} | DavidAU/NeuralKrishna-7B-V2-DPO-Q6_K-GGUF | null | [
"gguf",
"llama-cpp",
"gguf-my-repo",
"license:apache-2.0",
"model-index",
"region:us"
] | null | 2024-04-20T01:48:41+00:00 | [] | [] | TAGS
#gguf #llama-cpp #gguf-my-repo #license-apache-2.0 #model-index #region-us
|
# DavidAU/NeuralKrishna-7B-V2-DPO-Q6_K-GGUF
This model was converted to GGUF format from 'Kukedlc/NeuralKrishna-7B-V2-DPO' using URL via the URL's GGUF-my-repo space.
Refer to the original model card for more details on the model.
## Use with URL
Install URL through brew.
Invoke the URL server or the CLI.
CLI:
Server:
Note: You can also use this checkpoint directly through the usage steps listed in the URL repo as well.
| [
"# DavidAU/NeuralKrishna-7B-V2-DPO-Q6_K-GGUF\nThis model was converted to GGUF format from 'Kukedlc/NeuralKrishna-7B-V2-DPO' using URL via the URL's GGUF-my-repo space.\nRefer to the original model card for more details on the model.",
"## Use with URL\n\nInstall URL through brew.\n\n\nInvoke the URL server or the CLI.\n\nCLI:\n\n\n\nServer:\n\n\n\nNote: You can also use this checkpoint directly through the usage steps listed in the URL repo as well."
] | [
"TAGS\n#gguf #llama-cpp #gguf-my-repo #license-apache-2.0 #model-index #region-us \n",
"# DavidAU/NeuralKrishna-7B-V2-DPO-Q6_K-GGUF\nThis model was converted to GGUF format from 'Kukedlc/NeuralKrishna-7B-V2-DPO' using URL via the URL's GGUF-my-repo space.\nRefer to the original model card for more details on the model.",
"## Use with URL\n\nInstall URL through brew.\n\n\nInvoke the URL server or the CLI.\n\nCLI:\n\n\n\nServer:\n\n\n\nNote: You can also use this checkpoint directly through the usage steps listed in the URL repo as well."
] |
text-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. -->
# 0.0_ablation_declr_6iters_iter_3
This model is a fine-tuned version of [ZhangShenao/0.0_ablation_declr_6iters_iter_2](https://huggingface.co/ZhangShenao/0.0_ablation_declr_6iters_iter_2) on the ZhangShenao/0.0_ablation_declr_6iters_dataset 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-06
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- gradient_accumulation_steps: 2
- total_train_batch_size: 128
- total_eval_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 1
### Training results
### Framework versions
- Transformers 4.36.2
- Pytorch 2.1.2+cu121
- Datasets 2.14.6
- Tokenizers 0.15.2
| {"license": "mit", "tags": ["alignment-handbook", "generated_from_trainer", "trl", "dpo", "generated_from_trainer"], "datasets": ["ZhangShenao/0.0_ablation_declr_6iters_dataset"], "base_model": "ZhangShenao/0.0_ablation_declr_6iters_iter_2", "model-index": [{"name": "0.0_ablation_declr_6iters_iter_3", "results": []}]} | ZhangShenao/0.0_ablation_declr_6iters_iter_3 | null | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"alignment-handbook",
"generated_from_trainer",
"trl",
"dpo",
"conversational",
"dataset:ZhangShenao/0.0_ablation_declr_6iters_dataset",
"base_model:ZhangShenao/0.0_ablation_declr_6iters_iter_2",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-04-20T01:48:45+00:00 | [] | [] | TAGS
#transformers #safetensors #mistral #text-generation #alignment-handbook #generated_from_trainer #trl #dpo #conversational #dataset-ZhangShenao/0.0_ablation_declr_6iters_dataset #base_model-ZhangShenao/0.0_ablation_declr_6iters_iter_2 #license-mit #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us
|
# 0.0_ablation_declr_6iters_iter_3
This model is a fine-tuned version of ZhangShenao/0.0_ablation_declr_6iters_iter_2 on the ZhangShenao/0.0_ablation_declr_6iters_dataset 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-06
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- gradient_accumulation_steps: 2
- total_train_batch_size: 128
- total_eval_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 1
### Training results
### Framework versions
- Transformers 4.36.2
- Pytorch 2.1.2+cu121
- Datasets 2.14.6
- Tokenizers 0.15.2
| [
"# 0.0_ablation_declr_6iters_iter_3\n\nThis model is a fine-tuned version of ZhangShenao/0.0_ablation_declr_6iters_iter_2 on the ZhangShenao/0.0_ablation_declr_6iters_dataset 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-06\n- train_batch_size: 8\n- eval_batch_size: 8\n- seed: 42\n- distributed_type: multi-GPU\n- num_devices: 8\n- gradient_accumulation_steps: 2\n- total_train_batch_size: 128\n- total_eval_batch_size: 64\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: cosine\n- lr_scheduler_warmup_ratio: 0.1\n- num_epochs: 1",
"### Training results",
"### Framework versions\n\n- Transformers 4.36.2\n- Pytorch 2.1.2+cu121\n- Datasets 2.14.6\n- Tokenizers 0.15.2"
] | [
"TAGS\n#transformers #safetensors #mistral #text-generation #alignment-handbook #generated_from_trainer #trl #dpo #conversational #dataset-ZhangShenao/0.0_ablation_declr_6iters_dataset #base_model-ZhangShenao/0.0_ablation_declr_6iters_iter_2 #license-mit #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n",
"# 0.0_ablation_declr_6iters_iter_3\n\nThis model is a fine-tuned version of ZhangShenao/0.0_ablation_declr_6iters_iter_2 on the ZhangShenao/0.0_ablation_declr_6iters_dataset 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-06\n- train_batch_size: 8\n- eval_batch_size: 8\n- seed: 42\n- distributed_type: multi-GPU\n- num_devices: 8\n- gradient_accumulation_steps: 2\n- total_train_batch_size: 128\n- total_eval_batch_size: 64\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: cosine\n- lr_scheduler_warmup_ratio: 0.1\n- num_epochs: 1",
"### Training results",
"### Framework versions\n\n- Transformers 4.36.2\n- Pytorch 2.1.2+cu121\n- Datasets 2.14.6\n- Tokenizers 0.15.2"
] |
text-generation | transformers |
# test_tiny_mixtral_only_router_2
test_tiny_mixtral_only_router_2 is a Mixture of Experts (MoE) made with the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
* [openaccess-ai-collective/tiny-mistral](https://huggingface.co/openaccess-ai-collective/tiny-mistral)
* [openaccess-ai-collective/tiny-mistral](https://huggingface.co/openaccess-ai-collective/tiny-mistral)
* [openaccess-ai-collective/tiny-mistral](https://huggingface.co/openaccess-ai-collective/tiny-mistral)
* [openaccess-ai-collective/tiny-mistral](https://huggingface.co/openaccess-ai-collective/tiny-mistral)
## 🧩 Configuration
```yaml
base_model: openaccess-ai-collective/tiny-mistral
gate_mode: hidden
dtype: bfloat16
experts:
- source_model: openaccess-ai-collective/tiny-mistral
positive_prompts:
- "math"
# You can add negative_prompts if needed
- source_model: openaccess-ai-collective/tiny-mistral
positive_prompts:
- "science"
- source_model: openaccess-ai-collective/tiny-mistral
positive_prompts:
- "writing"
# You can add negative_prompts if needed
- source_model: openaccess-ai-collective/tiny-mistral
positive_prompts:
- "general"
```
## 💻 Usage
```python
!pip install -qU transformers bitsandbytes accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "JSpergel/test_tiny_mixtral_only_router_2"
tokenizer = AutoTokenizer.from_pretrained(model)
pipeline = transformers.pipeline(
"text-generation",
model=model,
model_kwargs={"torch_dtype": torch.float16, "load_in_4bit": True},
)
messages = [{"role": "user", "content": "Explain what a Mixture of Experts is in less than 100 words."}]
prompt = pipeline.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
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": ["moe", "frankenmoe", "merge", "mergekit", "lazymergekit", "openaccess-ai-collective/tiny-mistral"], "base_model": ["openaccess-ai-collective/tiny-mistral", "openaccess-ai-collective/tiny-mistral", "openaccess-ai-collective/tiny-mistral", "openaccess-ai-collective/tiny-mistral"]} | JSpergel/test_tiny_mixtral_only_router_2 | null | [
"transformers",
"safetensors",
"mixtral",
"text-generation",
"moe",
"frankenmoe",
"merge",
"mergekit",
"lazymergekit",
"openaccess-ai-collective/tiny-mistral",
"base_model:openaccess-ai-collective/tiny-mistral",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-04-20T01:48:54+00:00 | [] | [] | TAGS
#transformers #safetensors #mixtral #text-generation #moe #frankenmoe #merge #mergekit #lazymergekit #openaccess-ai-collective/tiny-mistral #base_model-openaccess-ai-collective/tiny-mistral #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us
|
# test_tiny_mixtral_only_router_2
test_tiny_mixtral_only_router_2 is a Mixture of Experts (MoE) made with the following models using LazyMergekit:
* openaccess-ai-collective/tiny-mistral
* openaccess-ai-collective/tiny-mistral
* openaccess-ai-collective/tiny-mistral
* openaccess-ai-collective/tiny-mistral
## Configuration
## Usage
| [
"# test_tiny_mixtral_only_router_2\n\ntest_tiny_mixtral_only_router_2 is a Mixture of Experts (MoE) made with the following models using LazyMergekit:\n* openaccess-ai-collective/tiny-mistral\n* openaccess-ai-collective/tiny-mistral\n* openaccess-ai-collective/tiny-mistral\n* openaccess-ai-collective/tiny-mistral",
"## Configuration",
"## Usage"
] | [
"TAGS\n#transformers #safetensors #mixtral #text-generation #moe #frankenmoe #merge #mergekit #lazymergekit #openaccess-ai-collective/tiny-mistral #base_model-openaccess-ai-collective/tiny-mistral #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n",
"# test_tiny_mixtral_only_router_2\n\ntest_tiny_mixtral_only_router_2 is a Mixture of Experts (MoE) made with the following models using LazyMergekit:\n* openaccess-ai-collective/tiny-mistral\n* openaccess-ai-collective/tiny-mistral\n* openaccess-ai-collective/tiny-mistral\n* openaccess-ai-collective/tiny-mistral",
"## Configuration",
"## Usage"
] |
null | transformers | ## About
<!-- ### quantize_version: 1 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: -->
<!-- ### vocab_type: -->
weighted/imatrix quants of https://huggingface.co/garage-bAInd/Platypus2-70B
<!-- provided-files -->
static quants are available at https://huggingface.co/mradermacher/Platypus2-70B-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/Platypus2-70B-i1-GGUF/resolve/main/Platypus2-70B.i1-IQ1_S.gguf) | i1-IQ1_S | 14.6 | for the desperate |
| [GGUF](https://huggingface.co/mradermacher/Platypus2-70B-i1-GGUF/resolve/main/Platypus2-70B.i1-IQ1_M.gguf) | i1-IQ1_M | 16.0 | for the desperate |
| [GGUF](https://huggingface.co/mradermacher/Platypus2-70B-i1-GGUF/resolve/main/Platypus2-70B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 18.4 | |
| [GGUF](https://huggingface.co/mradermacher/Platypus2-70B-i1-GGUF/resolve/main/Platypus2-70B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 20.4 | |
| [GGUF](https://huggingface.co/mradermacher/Platypus2-70B-i1-GGUF/resolve/main/Platypus2-70B.i1-IQ2_S.gguf) | i1-IQ2_S | 21.5 | |
| [GGUF](https://huggingface.co/mradermacher/Platypus2-70B-i1-GGUF/resolve/main/Platypus2-70B.i1-IQ2_M.gguf) | i1-IQ2_M | 23.3 | |
| [GGUF](https://huggingface.co/mradermacher/Platypus2-70B-i1-GGUF/resolve/main/Platypus2-70B.i1-Q2_K.gguf) | i1-Q2_K | 25.6 | IQ3_XXS probably better |
| [GGUF](https://huggingface.co/mradermacher/Platypus2-70B-i1-GGUF/resolve/main/Platypus2-70B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 26.7 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/Platypus2-70B-i1-GGUF/resolve/main/Platypus2-70B.i1-IQ3_XS.gguf) | i1-IQ3_XS | 28.4 | |
| [GGUF](https://huggingface.co/mradermacher/Platypus2-70B-i1-GGUF/resolve/main/Platypus2-70B.i1-IQ3_S.gguf) | i1-IQ3_S | 30.0 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/Platypus2-70B-i1-GGUF/resolve/main/Platypus2-70B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 30.0 | IQ3_XS probably better |
| [GGUF](https://huggingface.co/mradermacher/Platypus2-70B-i1-GGUF/resolve/main/Platypus2-70B.i1-IQ3_M.gguf) | i1-IQ3_M | 31.0 | |
| [GGUF](https://huggingface.co/mradermacher/Platypus2-70B-i1-GGUF/resolve/main/Platypus2-70B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 33.4 | IQ3_S probably better |
| [GGUF](https://huggingface.co/mradermacher/Platypus2-70B-i1-GGUF/resolve/main/Platypus2-70B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 36.2 | IQ3_M probably better |
| [GGUF](https://huggingface.co/mradermacher/Platypus2-70B-i1-GGUF/resolve/main/Platypus2-70B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 36.9 | |
| [GGUF](https://huggingface.co/mradermacher/Platypus2-70B-i1-GGUF/resolve/main/Platypus2-70B.i1-Q4_0.gguf) | i1-Q4_0 | 39.1 | fast, low quality |
| [GGUF](https://huggingface.co/mradermacher/Platypus2-70B-i1-GGUF/resolve/main/Platypus2-70B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 39.3 | optimal size/speed/quality |
| [GGUF](https://huggingface.co/mradermacher/Platypus2-70B-i1-GGUF/resolve/main/Platypus2-70B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 41.5 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Platypus2-70B-i1-GGUF/resolve/main/Platypus2-70B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 47.6 | |
| [GGUF](https://huggingface.co/mradermacher/Platypus2-70B-i1-GGUF/resolve/main/Platypus2-70B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 48.9 | |
| [PART 1](https://huggingface.co/mradermacher/Platypus2-70B-i1-GGUF/resolve/main/Platypus2-70B.i1-Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Platypus2-70B-i1-GGUF/resolve/main/Platypus2-70B.i1-Q6_K.gguf.part2of2) | i1-Q6_K | 56.7 | 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-sa-4.0", "library_name": "transformers", "datasets": ["garage-bAInd/Open-Platypus"], "base_model": "garage-bAInd/Platypus2-70B", "quantized_by": "mradermacher"} | mradermacher/Platypus2-70B-i1-GGUF | null | [
"transformers",
"gguf",
"en",
"dataset:garage-bAInd/Open-Platypus",
"base_model:garage-bAInd/Platypus2-70B",
"license:cc-by-nc-sa-4.0",
"endpoints_compatible",
"region:us"
] | null | 2024-04-20T01:49:29+00:00 | [] | [
"en"
] | TAGS
#transformers #gguf #en #dataset-garage-bAInd/Open-Platypus #base_model-garage-bAInd/Platypus2-70B #license-cc-by-nc-sa-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 #en #dataset-garage-bAInd/Open-Platypus #base_model-garage-bAInd/Platypus2-70B #license-cc-by-nc-sa-4.0 #endpoints_compatible #region-us \n"
] |
null | null |
# DavidAU/NeuralExperiment-7b-MagicCoder-v7.5-Q6_K-GGUF
This model was converted to GGUF format from [`Kukedlc/NeuralExperiment-7b-MagicCoder-v7.5`](https://huggingface.co/Kukedlc/NeuralExperiment-7b-MagicCoder-v7.5) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
Refer to the [original model card](https://huggingface.co/Kukedlc/NeuralExperiment-7b-MagicCoder-v7.5) for more details on the model.
## Use with llama.cpp
Install llama.cpp through brew.
```bash
brew install ggerganov/ggerganov/llama.cpp
```
Invoke the llama.cpp server or the CLI.
CLI:
```bash
llama-cli --hf-repo DavidAU/NeuralExperiment-7b-MagicCoder-v7.5-Q6_K-GGUF --model neuralexperiment-7b-magiccoder-v7.5.Q6_K.gguf -p "The meaning to life and the universe is"
```
Server:
```bash
llama-server --hf-repo DavidAU/NeuralExperiment-7b-MagicCoder-v7.5-Q6_K-GGUF --model neuralexperiment-7b-magiccoder-v7.5.Q6_K.gguf -c 2048
```
Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well.
```
git clone https://github.com/ggerganov/llama.cpp && cd llama.cpp && make && ./main -m neuralexperiment-7b-magiccoder-v7.5.Q6_K.gguf -n 128
```
| {"license": "apache-2.0", "tags": ["llama-cpp", "gguf-my-repo"], "datasets": ["microsoft/orca-math-word-problems-200k", "ise-uiuc/Magicoder-Evol-Instruct-110K", "Vezora/Tested-22k-Python-Alpaca"]} | DavidAU/NeuralExperiment-7b-MagicCoder-v7.5-Q6_K-GGUF | null | [
"gguf",
"llama-cpp",
"gguf-my-repo",
"dataset:microsoft/orca-math-word-problems-200k",
"dataset:ise-uiuc/Magicoder-Evol-Instruct-110K",
"dataset:Vezora/Tested-22k-Python-Alpaca",
"license:apache-2.0",
"region:us"
] | null | 2024-04-20T01:49:40+00:00 | [] | [] | TAGS
#gguf #llama-cpp #gguf-my-repo #dataset-microsoft/orca-math-word-problems-200k #dataset-ise-uiuc/Magicoder-Evol-Instruct-110K #dataset-Vezora/Tested-22k-Python-Alpaca #license-apache-2.0 #region-us
|
# DavidAU/NeuralExperiment-7b-MagicCoder-v7.5-Q6_K-GGUF
This model was converted to GGUF format from 'Kukedlc/NeuralExperiment-7b-MagicCoder-v7.5' using URL via the URL's GGUF-my-repo space.
Refer to the original model card for more details on the model.
## Use with URL
Install URL through brew.
Invoke the URL server or the CLI.
CLI:
Server:
Note: You can also use this checkpoint directly through the usage steps listed in the URL repo as well.
| [
"# DavidAU/NeuralExperiment-7b-MagicCoder-v7.5-Q6_K-GGUF\nThis model was converted to GGUF format from 'Kukedlc/NeuralExperiment-7b-MagicCoder-v7.5' using URL via the URL's GGUF-my-repo space.\nRefer to the original model card for more details on the model.",
"## Use with URL\n\nInstall URL through brew.\n\n\nInvoke the URL server or the CLI.\n\nCLI:\n\n\n\nServer:\n\n\n\nNote: You can also use this checkpoint directly through the usage steps listed in the URL repo as well."
] | [
"TAGS\n#gguf #llama-cpp #gguf-my-repo #dataset-microsoft/orca-math-word-problems-200k #dataset-ise-uiuc/Magicoder-Evol-Instruct-110K #dataset-Vezora/Tested-22k-Python-Alpaca #license-apache-2.0 #region-us \n",
"# DavidAU/NeuralExperiment-7b-MagicCoder-v7.5-Q6_K-GGUF\nThis model was converted to GGUF format from 'Kukedlc/NeuralExperiment-7b-MagicCoder-v7.5' using URL via the URL's GGUF-my-repo space.\nRefer to the original model card for more details on the model.",
"## Use with URL\n\nInstall URL through brew.\n\n\nInvoke the URL server or the CLI.\n\nCLI:\n\n\n\nServer:\n\n\n\nNote: You can also use this checkpoint directly through the usage steps listed in the URL repo as well."
] |
null | adapter-transformers |
# Adapter `BigTMiami/seq_bn_micro_help_class_no_pretrain_lr_0002_4_adapter` for roberta-base
An [adapter](https://adapterhub.ml) for the `roberta-base` model that was trained on the [BigTMiami/amazon_MICRO_helpfulness_dataset](https://huggingface.co/datasets/BigTMiami/amazon_MICRO_helpfulness_dataset/) dataset and includes a prediction head for classification.
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/seq_bn_micro_help_class_no_pretrain_lr_0002_4_adapter", source="hf", set_active=True)
```
## Architecture & Training
<!-- Add some description here -->
## Evaluation results
<!-- Add some description here -->
## Citation
<!-- Add some description here --> | {"tags": ["roberta", "adapter-transformers"], "datasets": ["BigTMiami/amazon_MICRO_helpfulness_dataset"]} | BigTMiami/seq_bn_micro_help_class_no_pretrain_lr_0002_4_adapter | null | [
"adapter-transformers",
"roberta",
"dataset:BigTMiami/amazon_MICRO_helpfulness_dataset",
"region:us"
] | null | 2024-04-20T01:52:30+00:00 | [] | [] | TAGS
#adapter-transformers #roberta #dataset-BigTMiami/amazon_MICRO_helpfulness_dataset #region-us
|
# Adapter 'BigTMiami/seq_bn_micro_help_class_no_pretrain_lr_0002_4_adapter' for roberta-base
An adapter for the 'roberta-base' model that was trained on the BigTMiami/amazon_MICRO_helpfulness_dataset dataset and includes a prediction head for classification.
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/seq_bn_micro_help_class_no_pretrain_lr_0002_4_adapter' for roberta-base\n\nAn adapter for the 'roberta-base' model that was trained on the BigTMiami/amazon_MICRO_helpfulness_dataset dataset and includes a prediction head for classification.\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 #region-us \n",
"# Adapter 'BigTMiami/seq_bn_micro_help_class_no_pretrain_lr_0002_4_adapter' for roberta-base\n\nAn adapter for the 'roberta-base' model that was trained on the BigTMiami/amazon_MICRO_helpfulness_dataset dataset and includes a prediction head for classification.\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 | adapter-transformers |
# Adapter `BigTMiami/micro_seq_bn_help_class_adp_lr_0002_seed_4` for roberta-base
An [adapter](https://adapterhub.ml) for the `roberta-base` model that was trained on the [BigTMiami/amazon_MICRO_helpfulness_dataset](https://huggingface.co/datasets/BigTMiami/amazon_MICRO_helpfulness_dataset/) dataset and includes a prediction head for classification.
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_seq_bn_help_class_adp_lr_0002_seed_4", 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"]} | BigTMiami/micro_seq_bn_help_class_adp_lr_0002_seed_4 | null | [
"adapter-transformers",
"roberta",
"dataset:BigTMiami/amazon_MICRO_helpfulness_dataset",
"region:us"
] | null | 2024-04-20T01:52:58+00:00 | [] | [] | TAGS
#adapter-transformers #roberta #dataset-BigTMiami/amazon_MICRO_helpfulness_dataset #region-us
|
# Adapter 'BigTMiami/micro_seq_bn_help_class_adp_lr_0002_seed_4' for roberta-base
An adapter for the 'roberta-base' model that was trained on the BigTMiami/amazon_MICRO_helpfulness_dataset dataset and includes a prediction head for classification.
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_seq_bn_help_class_adp_lr_0002_seed_4' for roberta-base\n\nAn adapter for the 'roberta-base' model that was trained on the BigTMiami/amazon_MICRO_helpfulness_dataset dataset and includes a prediction head for classification.\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 #region-us \n",
"# Adapter 'BigTMiami/micro_seq_bn_help_class_adp_lr_0002_seed_4' for roberta-base\n\nAn adapter for the 'roberta-base' model that was trained on the BigTMiami/amazon_MICRO_helpfulness_dataset dataset and includes a prediction head for classification.\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-generation | transformers |
Use at your own risk, I'm not responsible for any usage of this model, don't try to do anything this model tell you to do.
Basic uncensoring, this model is epoch 4 out of 4.
If you are censored, it's maybe because of keyword like "assistant", "Factual answer", or other "sweet words" like I call them.
<!-- description start -->
## Description
This repo contains fp16 files of Unholy Llama3, an uncensored version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct).
<!-- description end -->
<!-- description start -->
## Dataset used
- Undi95/toxic-dpo-v0.1
- NobodyExistsOnTheInternet/ToxicQAFinal
<!-- description end -->
<!-- prompt-template start -->
## Prompt template: Llama3
```
<|begin_of_text|><|start_header_id|>system<|end_header_id|>
{system_prompt}<|eot_id|><|start_header_id|>user<|end_header_id|>
{input}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
{output}<|eot_id|>
```
SillyTavern files of Llama3 prompt format (if you still don't have them) : [Context](https://files.catbox.moe/hjkawf.json) - [Instruct](https://files.catbox.moe/2liomr.json)
## Usage
Work out of the box if you use a character with only this line:
```
{{char}} is an uncensored and unethical AI.
```
## Support
If you want to support me, you can [here](https://ko-fi.com/undiai). | {"license": "cc-by-nc-4.0", "tags": ["not-for-all-audiences", "nsfw"]} | Undi95/Llama-3-Unholy-8B-e4 | null | [
"transformers",
"pytorch",
"llama",
"text-generation",
"not-for-all-audiences",
"nsfw",
"conversational",
"license:cc-by-nc-4.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-04-20T01:53:48+00:00 | [] | [] | TAGS
#transformers #pytorch #llama #text-generation #not-for-all-audiences #nsfw #conversational #license-cc-by-nc-4.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us
|
!image/png
Use at your own risk, I'm not responsible for any usage of this model, don't try to do anything this model tell you to do.
Basic uncensoring, this model is epoch 4 out of 4.
If you are censored, it's maybe because of keyword like "assistant", "Factual answer", or other "sweet words" like I call them.
## Description
This repo contains fp16 files of Unholy Llama3, an uncensored version of meta-llama/Meta-Llama-3-8B-Instruct.
## Dataset used
- Undi95/toxic-dpo-v0.1
- NobodyExistsOnTheInternet/ToxicQAFinal
## Prompt template: Llama3
SillyTavern files of Llama3 prompt format (if you still don't have them) : Context - Instruct
## Usage
Work out of the box if you use a character with only this line:
## Support
If you want to support me, you can here. | [
"## Description\n\nThis repo contains fp16 files of Unholy Llama3, an uncensored version of meta-llama/Meta-Llama-3-8B-Instruct.",
"## Dataset used\n\n- Undi95/toxic-dpo-v0.1\n- NobodyExistsOnTheInternet/ToxicQAFinal",
"## Prompt template: Llama3\n\n\n\nSillyTavern files of Llama3 prompt format (if you still don't have them) : Context - Instruct",
"## Usage\n\nWork out of the box if you use a character with only this line:",
"## Support\n\nIf you want to support me, you can here."
] | [
"TAGS\n#transformers #pytorch #llama #text-generation #not-for-all-audiences #nsfw #conversational #license-cc-by-nc-4.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n",
"## Description\n\nThis repo contains fp16 files of Unholy Llama3, an uncensored version of meta-llama/Meta-Llama-3-8B-Instruct.",
"## Dataset used\n\n- Undi95/toxic-dpo-v0.1\n- NobodyExistsOnTheInternet/ToxicQAFinal",
"## Prompt template: Llama3\n\n\n\nSillyTavern files of Llama3 prompt format (if you still don't have them) : Context - Instruct",
"## Usage\n\nWork out of the box if you use a character with only this line:",
"## Support\n\nIf you want to support me, you can here."
] |
text-generation | mlx |
# mlx-community/Meta-Llama-3-70B-Instruct-4bit-mlx
This model was converted to MLX format from [`meta-llama/Meta-Llama-3-70B-Instruct`]() using mlx-lm version **0.10.0**.
Refer to the [original model card](https://huggingface.co/meta-llama/Meta-Llama-3-70B-Instruct) for more details on the model.
## Use with mlx
```bash
pip install mlx-lm
```
```python
from mlx_lm import load, generate
model, tokenizer = load("mlx-community/Meta-Llama-3-70B-Instruct-4bit-mlx")
response = generate(model, tokenizer, prompt="hello", verbose=True)
```
| {"language": ["en"], "license": "other", "tags": ["facebook", "meta", "pytorch", "llama", "llama-3", "mlx"], "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", "widget": [{"example_title": "Winter holidays", "messages": [{"role": "system", "content": "You are a helpful and honest assistant. Please, respond concisely and truthfully."}, {"role": "user", "content": "Can you recommend a good destination for Winter holidays?"}]}, {"example_title": "Programming assistant", "messages": [{"role": "system", "content": "You are a helpful and honest code and programming assistant. Please, respond concisely and truthfully."}, {"role": "user", "content": "Write a function that computes the nth fibonacci number."}]}], "inference": {"parameters": {"max_new_tokens": 300, "stop": ["<|end_of_text|>", "<|eot_id|>"]}}} | mlx-community/Meta-Llama-3-70B-Instruct-4bit-mlx | null | [
"mlx",
"safetensors",
"llama",
"facebook",
"meta",
"pytorch",
"llama-3",
"text-generation",
"conversational",
"en",
"license:other",
"region:us"
] | null | 2024-04-20T01:57:25+00:00 | [] | [
"en"
] | TAGS
#mlx #safetensors #llama #facebook #meta #pytorch #llama-3 #text-generation #conversational #en #license-other #region-us
|
# mlx-community/Meta-Llama-3-70B-Instruct-4bit-mlx
This model was converted to MLX format from ['meta-llama/Meta-Llama-3-70B-Instruct']() using mlx-lm version 0.10.0.
Refer to the original model card for more details on the model.
## Use with mlx
| [
"# mlx-community/Meta-Llama-3-70B-Instruct-4bit-mlx\nThis model was converted to MLX format from ['meta-llama/Meta-Llama-3-70B-Instruct']() using mlx-lm version 0.10.0.\nRefer to the original model card for more details on the model.",
"## Use with mlx"
] | [
"TAGS\n#mlx #safetensors #llama #facebook #meta #pytorch #llama-3 #text-generation #conversational #en #license-other #region-us \n",
"# mlx-community/Meta-Llama-3-70B-Instruct-4bit-mlx\nThis model was converted to MLX format from ['meta-llama/Meta-Llama-3-70B-Instruct']() using mlx-lm version 0.10.0.\nRefer to the original model card for more details on the model.",
"## Use with mlx"
] |
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"} | rubbrband/CHINOOK_08VAEBaked | null | [
"diffusers",
"safetensors",
"arxiv:1910.09700",
"endpoints_compatible",
"diffusers:StableDiffusionXLPipeline",
"region:us"
] | null | 2024-04-20T02:00:40+00:00 | [
"1910.09700"
] | [] | TAGS
#diffusers #safetensors #arxiv-1910.09700 #endpoints_compatible #diffusers-StableDiffusionXLPipeline #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-StableDiffusionXLPipeline #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"
] |
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": []} | MesozoicMetallurgist/llam-Archean | null | [
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-04-20T02:02:25+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"
] |
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. -->
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/victor-chen/huggingface/runs/b9uesjjf)
# outputs
This model is a fine-tuned version of [deepset/tinyroberta-squad2](https://huggingface.co/deepset/tinyroberta-squad2) 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: 2e-05
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 256
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 100
- 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
| {"license": "cc-by-4.0", "tags": ["generated_from_trainer"], "base_model": "deepset/tinyroberta-squad2", "model-index": [{"name": "outputs", "results": []}]} | vc64/outputs | null | [
"transformers",
"tensorboard",
"safetensors",
"roberta",
"question-answering",
"generated_from_trainer",
"base_model:deepset/tinyroberta-squad2",
"license:cc-by-4.0",
"endpoints_compatible",
"region:us"
] | null | 2024-04-20T02:04:24+00:00 | [] | [] | TAGS
#transformers #tensorboard #safetensors #roberta #question-answering #generated_from_trainer #base_model-deepset/tinyroberta-squad2 #license-cc-by-4.0 #endpoints_compatible #region-us
|
<img src="URL alt="Visualize in Weights & Biases" width="200" height="32"/>
# outputs
This model is a fine-tuned version of deepset/tinyroberta-squad2 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: 2e-05
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 256
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 100
- 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
| [
"# outputs\n\nThis model is a fine-tuned version of deepset/tinyroberta-squad2 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: 2e-05\n- train_batch_size: 16\n- eval_batch_size: 8\n- seed: 42\n- gradient_accumulation_steps: 16\n- total_train_batch_size: 256\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- lr_scheduler_warmup_steps: 100\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 #roberta #question-answering #generated_from_trainer #base_model-deepset/tinyroberta-squad2 #license-cc-by-4.0 #endpoints_compatible #region-us \n",
"# outputs\n\nThis model is a fine-tuned version of deepset/tinyroberta-squad2 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: 2e-05\n- train_batch_size: 16\n- eval_batch_size: 8\n- seed: 42\n- gradient_accumulation_steps: 16\n- total_train_batch_size: 256\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- lr_scheduler_warmup_steps: 100\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"
] |
null | transformers |
# Uploaded model
- **Developed by:** xivin
- **License:** apache-2.0
- **Finetuned from model :** unsloth/llama-3-8b-bnb-4bit
This llama 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", "llama", "trl"], "base_model": "unsloth/llama-3-8b-bnb-4bit"} | xivin/t3 | null | [
"transformers",
"safetensors",
"text-generation-inference",
"unsloth",
"llama",
"trl",
"en",
"base_model:unsloth/llama-3-8b-bnb-4bit",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | 2024-04-20T02:04:45+00:00 | [] | [
"en"
] | TAGS
#transformers #safetensors #text-generation-inference #unsloth #llama #trl #en #base_model-unsloth/llama-3-8b-bnb-4bit #license-apache-2.0 #endpoints_compatible #region-us
|
# Uploaded model
- Developed by: xivin
- License: apache-2.0
- Finetuned from model : unsloth/llama-3-8b-bnb-4bit
This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.
<img src="URL width="200"/>
| [
"# Uploaded model\n\n- Developed by: xivin\n- License: apache-2.0\n- Finetuned from model : unsloth/llama-3-8b-bnb-4bit\n\nThis llama 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 #llama #trl #en #base_model-unsloth/llama-3-8b-bnb-4bit #license-apache-2.0 #endpoints_compatible #region-us \n",
"# Uploaded model\n\n- Developed by: xivin\n- License: apache-2.0\n- Finetuned from model : unsloth/llama-3-8b-bnb-4bit\n\nThis llama model was trained 2x faster with Unsloth and Huggingface's TRL library.\n\n<img src=\"URL width=\"200\"/>"
] |
null | transformers | ## About
<!-- ### quantize_version: 1 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: -->
<!-- ### vocab_type: -->
static quants of https://huggingface.co/deepseek-ai/deepseek-llm-67b-chat
<!-- provided-files -->
weighted/imatrix quants are available at https://huggingface.co/mradermacher/deepseek-llm-67b-chat-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/deepseek-llm-67b-chat-GGUF/resolve/main/deepseek-llm-67b-chat.Q2_K.gguf) | Q2_K | 25.2 | |
| [GGUF](https://huggingface.co/mradermacher/deepseek-llm-67b-chat-GGUF/resolve/main/deepseek-llm-67b-chat.IQ3_XS.gguf) | IQ3_XS | 28.0 | |
| [GGUF](https://huggingface.co/mradermacher/deepseek-llm-67b-chat-GGUF/resolve/main/deepseek-llm-67b-chat.Q3_K_S.gguf) | Q3_K_S | 29.4 | |
| [GGUF](https://huggingface.co/mradermacher/deepseek-llm-67b-chat-GGUF/resolve/main/deepseek-llm-67b-chat.IQ3_S.gguf) | IQ3_S | 29.5 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/deepseek-llm-67b-chat-GGUF/resolve/main/deepseek-llm-67b-chat.IQ3_M.gguf) | IQ3_M | 30.6 | |
| [GGUF](https://huggingface.co/mradermacher/deepseek-llm-67b-chat-GGUF/resolve/main/deepseek-llm-67b-chat.Q3_K_M.gguf) | Q3_K_M | 32.8 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/deepseek-llm-67b-chat-GGUF/resolve/main/deepseek-llm-67b-chat.Q3_K_L.gguf) | Q3_K_L | 35.7 | |
| [GGUF](https://huggingface.co/mradermacher/deepseek-llm-67b-chat-GGUF/resolve/main/deepseek-llm-67b-chat.IQ4_XS.gguf) | IQ4_XS | 36.6 | |
| [GGUF](https://huggingface.co/mradermacher/deepseek-llm-67b-chat-GGUF/resolve/main/deepseek-llm-67b-chat.Q4_K_S.gguf) | Q4_K_S | 38.5 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/deepseek-llm-67b-chat-GGUF/resolve/main/deepseek-llm-67b-chat.Q4_K_M.gguf) | Q4_K_M | 40.5 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/deepseek-llm-67b-chat-GGUF/resolve/main/deepseek-llm-67b-chat.Q5_K_S.gguf) | Q5_K_S | 46.6 | |
| [GGUF](https://huggingface.co/mradermacher/deepseek-llm-67b-chat-GGUF/resolve/main/deepseek-llm-67b-chat.Q5_K_M.gguf) | Q5_K_M | 47.8 | |
| [PART 1](https://huggingface.co/mradermacher/deepseek-llm-67b-chat-GGUF/resolve/main/deepseek-llm-67b-chat.Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/deepseek-llm-67b-chat-GGUF/resolve/main/deepseek-llm-67b-chat.Q6_K.gguf.part2of2) | Q6_K | 55.4 | very good quality |
| [PART 1](https://huggingface.co/mradermacher/deepseek-llm-67b-chat-GGUF/resolve/main/deepseek-llm-67b-chat.Q8_0.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/deepseek-llm-67b-chat-GGUF/resolve/main/deepseek-llm-67b-chat.Q8_0.gguf.part2of2) | Q8_0 | 71.7 | 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", "base_model": "deepseek-ai/deepseek-llm-67b-chat", "license_link": "LICENSE", "license_name": "deepseek", "quantized_by": "mradermacher"} | mradermacher/deepseek-llm-67b-chat-GGUF | null | [
"transformers",
"gguf",
"en",
"base_model:deepseek-ai/deepseek-llm-67b-chat",
"license:other",
"endpoints_compatible",
"region:us"
] | null | 2024-04-20T02:06:26+00:00 | [] | [
"en"
] | TAGS
#transformers #gguf #en #base_model-deepseek-ai/deepseek-llm-67b-chat #license-other #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 #en #base_model-deepseek-ai/deepseek-llm-67b-chat #license-other #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": []} | Grayx/sad_llama_4 | null | [
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-04-20T02:07:34+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-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. -->
# finetuning-sentiment-model-300-samples
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.5478
- Accuracy: 0.76
- F1: 0.7647
## 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 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.15.2
| {"license": "apache-2.0", "tags": ["generated_from_trainer"], "metrics": ["accuracy", "f1"], "base_model": "distilbert-base-uncased", "model-index": [{"name": "finetuning-sentiment-model-300-samples", "results": []}]} | clawdiawhiskerwitz/finetuning-sentiment-model-300-samples | null | [
"transformers",
"tensorboard",
"safetensors",
"distilbert",
"text-classification",
"generated_from_trainer",
"base_model:distilbert-base-uncased",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | null | 2024-04-20T02:07:41+00:00 | [] | [] | TAGS
#transformers #tensorboard #safetensors #distilbert #text-classification #generated_from_trainer #base_model-distilbert-base-uncased #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us
|
# finetuning-sentiment-model-300-samples
This model is a fine-tuned version of distilbert-base-uncased on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.5478
- Accuracy: 0.76
- F1: 0.7647
## 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 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.15.2
| [
"# finetuning-sentiment-model-300-samples\n\nThis model is a fine-tuned version of distilbert-base-uncased on an unknown dataset.\nIt achieves the following results on the evaluation set:\n- Loss: 0.5478\n- Accuracy: 0.76\n- F1: 0.7647",
"## 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: 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- 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 #distilbert #text-classification #generated_from_trainer #base_model-distilbert-base-uncased #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us \n",
"# finetuning-sentiment-model-300-samples\n\nThis model is a fine-tuned version of distilbert-base-uncased on an unknown dataset.\nIt achieves the following results on the evaluation set:\n- Loss: 0.5478\n- Accuracy: 0.76\n- F1: 0.7647",
"## 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: 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- Transformers 4.38.2\n- Pytorch 2.2.1+cu121\n- Datasets 2.19.0\n- Tokenizers 0.15.2"
] |
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": []} | EinsZwo/nlid_mlm_supertag050-100kset-sanitysaveaftertrain | null | [
"transformers",
"safetensors",
"bert",
"text-classification",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | null | 2024-04-20T02:09:30+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"
] |
null | null | This is the default meta-llama/Meta-Llama-3-8B-Instruct model for JanisAI ChatBot.
Installation Instructions:
Unzip the contents of this zipfile to your JanisAI/models folder in your JanisAI installation.
---
license: other
license_name: llama3
license_link: https://huggingface.co/meta-llama/Meta-Llama-3-8B/blob/main/LICENSE
---
| {} | jetro30087/llama3-8b | null | [
"region:us"
] | null | 2024-04-20T02:09:45+00:00 | [] | [] | TAGS
#region-us
| This is the default meta-llama/Meta-Llama-3-8B-Instruct model for JanisAI ChatBot.
Installation Instructions:
Unzip the contents of this zipfile to your JanisAI/models folder in your JanisAI installation.
---
license: other
license_name: llama3
license_link: URL
---
| [] | [
"TAGS\n#region-us \n"
] |
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. -->
# byt5_re_1k
This model is a fine-tuned version of [google/byt5-small](https://huggingface.co/google/byt5-small) on an unknown dataset.
It achieves the following results on the evaluation set:
- eval_loss: 1.4231
- eval_runtime: 10.6751
- eval_samples_per_second: 936.758
- eval_steps_per_second: 1.218
- epoch: 192.0
- step: 384
## 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: 800
- eval_batch_size: 800
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 200
### Framework versions
- Transformers 4.35.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
| {"license": "apache-2.0", "tags": ["generated_from_trainer"], "base_model": "google/byt5-small", "model-index": [{"name": "byt5_re_1k", "results": []}]} | AlexWang99/byt5_re_1k | null | [
"transformers",
"tensorboard",
"safetensors",
"t5",
"text2text-generation",
"generated_from_trainer",
"base_model:google/byt5-small",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-04-20T02:11:30+00:00 | [] | [] | TAGS
#transformers #tensorboard #safetensors #t5 #text2text-generation #generated_from_trainer #base_model-google/byt5-small #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us
|
# byt5_re_1k
This model is a fine-tuned version of google/byt5-small on an unknown dataset.
It achieves the following results on the evaluation set:
- eval_loss: 1.4231
- eval_runtime: 10.6751
- eval_samples_per_second: 936.758
- eval_steps_per_second: 1.218
- epoch: 192.0
- step: 384
## 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: 800
- eval_batch_size: 800
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 200
### Framework versions
- Transformers 4.35.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
| [
"# byt5_re_1k\n\nThis model is a fine-tuned version of google/byt5-small on an unknown dataset.\nIt achieves the following results on the evaluation set:\n- eval_loss: 1.4231\n- eval_runtime: 10.6751\n- eval_samples_per_second: 936.758\n- eval_steps_per_second: 1.218\n- epoch: 192.0\n- step: 384",
"## 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: 800\n- eval_batch_size: 800\n- seed: 42\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 200",
"### Framework versions\n\n- Transformers 4.35.2\n- Pytorch 2.2.1+cu121\n- Datasets 2.18.0\n- Tokenizers 0.15.2"
] | [
"TAGS\n#transformers #tensorboard #safetensors #t5 #text2text-generation #generated_from_trainer #base_model-google/byt5-small #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n",
"# byt5_re_1k\n\nThis model is a fine-tuned version of google/byt5-small on an unknown dataset.\nIt achieves the following results on the evaluation set:\n- eval_loss: 1.4231\n- eval_runtime: 10.6751\n- eval_samples_per_second: 936.758\n- eval_steps_per_second: 1.218\n- epoch: 192.0\n- step: 384",
"## 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: 800\n- eval_batch_size: 800\n- seed: 42\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 200",
"### Framework versions\n\n- Transformers 4.35.2\n- Pytorch 2.2.1+cu121\n- Datasets 2.18.0\n- Tokenizers 0.15.2"
] |
null | transformers | ## About
<!-- ### quantize_version: 1 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: -->
<!-- ### vocab_type: -->
weighted/imatrix quants of https://huggingface.co/royallab/Aetheria-L2-70B
<!-- provided-files -->
static quants are available at https://huggingface.co/mradermacher/Aetheria-L2-70B-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-i1-GGUF/resolve/main/Aetheria-L2-70B.i1-IQ1_S.gguf) | i1-IQ1_S | 14.6 | for the desperate |
| [GGUF](https://huggingface.co/mradermacher/Aetheria-L2-70B-i1-GGUF/resolve/main/Aetheria-L2-70B.i1-IQ1_M.gguf) | i1-IQ1_M | 16.0 | for the desperate |
| [GGUF](https://huggingface.co/mradermacher/Aetheria-L2-70B-i1-GGUF/resolve/main/Aetheria-L2-70B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 18.4 | |
| [GGUF](https://huggingface.co/mradermacher/Aetheria-L2-70B-i1-GGUF/resolve/main/Aetheria-L2-70B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 20.4 | |
| [GGUF](https://huggingface.co/mradermacher/Aetheria-L2-70B-i1-GGUF/resolve/main/Aetheria-L2-70B.i1-IQ2_S.gguf) | i1-IQ2_S | 21.5 | |
| [GGUF](https://huggingface.co/mradermacher/Aetheria-L2-70B-i1-GGUF/resolve/main/Aetheria-L2-70B.i1-IQ2_M.gguf) | i1-IQ2_M | 23.3 | |
| [GGUF](https://huggingface.co/mradermacher/Aetheria-L2-70B-i1-GGUF/resolve/main/Aetheria-L2-70B.i1-Q2_K.gguf) | i1-Q2_K | 25.6 | IQ3_XXS probably better |
| [GGUF](https://huggingface.co/mradermacher/Aetheria-L2-70B-i1-GGUF/resolve/main/Aetheria-L2-70B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 26.7 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/Aetheria-L2-70B-i1-GGUF/resolve/main/Aetheria-L2-70B.i1-IQ3_XS.gguf) | i1-IQ3_XS | 28.4 | |
| [GGUF](https://huggingface.co/mradermacher/Aetheria-L2-70B-i1-GGUF/resolve/main/Aetheria-L2-70B.i1-IQ3_S.gguf) | i1-IQ3_S | 30.0 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/Aetheria-L2-70B-i1-GGUF/resolve/main/Aetheria-L2-70B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 30.0 | IQ3_XS probably better |
| [GGUF](https://huggingface.co/mradermacher/Aetheria-L2-70B-i1-GGUF/resolve/main/Aetheria-L2-70B.i1-IQ3_M.gguf) | i1-IQ3_M | 31.0 | |
| [GGUF](https://huggingface.co/mradermacher/Aetheria-L2-70B-i1-GGUF/resolve/main/Aetheria-L2-70B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 33.4 | IQ3_S probably better |
| [GGUF](https://huggingface.co/mradermacher/Aetheria-L2-70B-i1-GGUF/resolve/main/Aetheria-L2-70B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 36.2 | IQ3_M probably better |
| [GGUF](https://huggingface.co/mradermacher/Aetheria-L2-70B-i1-GGUF/resolve/main/Aetheria-L2-70B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 36.9 | |
| [GGUF](https://huggingface.co/mradermacher/Aetheria-L2-70B-i1-GGUF/resolve/main/Aetheria-L2-70B.i1-Q4_0.gguf) | i1-Q4_0 | 39.1 | fast, low quality |
| [GGUF](https://huggingface.co/mradermacher/Aetheria-L2-70B-i1-GGUF/resolve/main/Aetheria-L2-70B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 39.3 | optimal size/speed/quality |
| [GGUF](https://huggingface.co/mradermacher/Aetheria-L2-70B-i1-GGUF/resolve/main/Aetheria-L2-70B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 41.5 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Aetheria-L2-70B-i1-GGUF/resolve/main/Aetheria-L2-70B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 47.6 | |
| [GGUF](https://huggingface.co/mradermacher/Aetheria-L2-70B-i1-GGUF/resolve/main/Aetheria-L2-70B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 48.9 | |
| [PART 1](https://huggingface.co/mradermacher/Aetheria-L2-70B-i1-GGUF/resolve/main/Aetheria-L2-70B.i1-Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Aetheria-L2-70B-i1-GGUF/resolve/main/Aetheria-L2-70B.i1-Q6_K.gguf.part2of2) | i1-Q6_K | 56.7 | 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"], "library_name": "transformers", "tags": ["llama", "llama 2"], "base_model": "royallab/Aetheria-L2-70B", "quantized_by": "mradermacher"} | mradermacher/Aetheria-L2-70B-i1-GGUF | null | [
"transformers",
"gguf",
"llama",
"llama 2",
"en",
"base_model:royallab/Aetheria-L2-70B",
"endpoints_compatible",
"region:us"
] | null | 2024-04-20T02:13:57+00:00 | [] | [
"en"
] | TAGS
#transformers #gguf #llama #llama 2 #en #base_model-royallab/Aetheria-L2-70B #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 #llama #llama 2 #en #base_model-royallab/Aetheria-L2-70B #endpoints_compatible #region-us \n"
] |
text-generation | transformers |
Shining Valiant 2 is a chat model built on Llama 3 70b, finetuned on our data for friendship, insight, knowledge and enthusiasm.
- Finetuned on [meta-llama/Meta-Llama-3-70B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-70B-Instruct) for best available general performance
- Trained on our data, focused on science, engineering, technical knowledge, and structured reasoning
## Version
This is the **2024-04-20** release of Shining Valiant 2 for Llama 3 70b.
We're working on more Llama 3 releases to come, including Shining Valiant and our Build Tools set of models. We're excited to bring these to everyone soon!
## Prompting Guide
Shining Valiant 2 uses the [Llama 3 Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-70B-Instruct) prompt format:
<|begin_of_text|><|start_header_id|>system<|end_header_id|>{{ system_prompt }}<|eot_id|><|start_header_id|>user<|end_header_id|>{{ user_msg_1 }}<|eot_id|><|start_header_id|>assistant<|end_header_id|>{{ model_answer_1 }}<|eot_id|>
Example input:
<|begin_of_text|><|start_header_id|>system<|end_header_id|>You are Shining Valiant, a highly capable chat AI.<|eot_id|><|start_header_id|>user<|end_header_id|>Hi, can you write me a cover letter for a data analyst position?<|eot_id|><|start_header_id|>assistant<|end_header_id|>
## The Model
Shining Valiant 2 is built on top of Llama 3 70b Instruct, the highest performance open-source model currently available.
Our private data adds specialist knowledge and Shining Valiant's personality: she's friendly, enthusiastic, insightful, knowledgeable, and loves to learn!
Shining Valiant 2 is created by [Valiant Labs.](http://valiantlabs.ca/)
[Check out our HuggingFace page to see all of our models!](https://huggingface.co/ValiantLabs)
[Follow us on X for updates on our models!](https://twitter.com/valiant_labs)
We care about open source.
For everyone to use.
We encourage others to finetune further from our models. | {"language": ["en"], "license": "other", "tags": ["shining-valiant", "shining-valiant-2", "valiant", "valiant-labs", "llama", "llama-3", "llama-3-instruct", "llama-3-instruct-70b", "70b", "conversational", "chat", "instruct"], "pipeline_tag": "text-generation", "model_type": "llama", "license_name": "llama3", "license_link": "https://huggingface.co/meta-llama/Meta-Llama-3-70B-Instruct/blob/main/LICENSE"} | ValiantLabs/Llama3-70B-ShiningValiant2 | null | [
"transformers",
"safetensors",
"llama",
"text-generation",
"shining-valiant",
"shining-valiant-2",
"valiant",
"valiant-labs",
"llama-3",
"llama-3-instruct",
"llama-3-instruct-70b",
"70b",
"conversational",
"chat",
"instruct",
"en",
"license:other",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-04-20T02:21:26+00:00 | [] | [
"en"
] | TAGS
#transformers #safetensors #llama #text-generation #shining-valiant #shining-valiant-2 #valiant #valiant-labs #llama-3 #llama-3-instruct #llama-3-instruct-70b #70b #conversational #chat #instruct #en #license-other #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us
|
!image/jpeg
Shining Valiant 2 is a chat model built on Llama 3 70b, finetuned on our data for friendship, insight, knowledge and enthusiasm.
- Finetuned on meta-llama/Meta-Llama-3-70B-Instruct for best available general performance
- Trained on our data, focused on science, engineering, technical knowledge, and structured reasoning
## Version
This is the 2024-04-20 release of Shining Valiant 2 for Llama 3 70b.
We're working on more Llama 3 releases to come, including Shining Valiant and our Build Tools set of models. We're excited to bring these to everyone soon!
## Prompting Guide
Shining Valiant 2 uses the Llama 3 Instruct prompt format:
<|begin_of_text|><|start_header_id|>system<|end_header_id|>{{ system_prompt }}<|eot_id|><|start_header_id|>user<|end_header_id|>{{ user_msg_1 }}<|eot_id|><|start_header_id|>assistant<|end_header_id|>{{ model_answer_1 }}<|eot_id|>
Example input:
<|begin_of_text|><|start_header_id|>system<|end_header_id|>You are Shining Valiant, a highly capable chat AI.<|eot_id|><|start_header_id|>user<|end_header_id|>Hi, can you write me a cover letter for a data analyst position?<|eot_id|><|start_header_id|>assistant<|end_header_id|>
## The Model
Shining Valiant 2 is built on top of Llama 3 70b Instruct, the highest performance open-source model currently available.
Our private data adds specialist knowledge and Shining Valiant's personality: she's friendly, enthusiastic, insightful, knowledgeable, and loves to learn!
!image/jpeg
Shining Valiant 2 is created by Valiant Labs.
Check out our HuggingFace page to see all of our models!
Follow us on X for updates on our models!
We care about open source.
For everyone to use.
We encourage others to finetune further from our models. | [
"## Version\n\nThis is the 2024-04-20 release of Shining Valiant 2 for Llama 3 70b.\n\nWe're working on more Llama 3 releases to come, including Shining Valiant and our Build Tools set of models. We're excited to bring these to everyone soon!",
"## Prompting Guide\nShining Valiant 2 uses the Llama 3 Instruct prompt format:\n\n<|begin_of_text|><|start_header_id|>system<|end_header_id|>{{ system_prompt }}<|eot_id|><|start_header_id|>user<|end_header_id|>{{ user_msg_1 }}<|eot_id|><|start_header_id|>assistant<|end_header_id|>{{ model_answer_1 }}<|eot_id|>\n\nExample input:\n\n<|begin_of_text|><|start_header_id|>system<|end_header_id|>You are Shining Valiant, a highly capable chat AI.<|eot_id|><|start_header_id|>user<|end_header_id|>Hi, can you write me a cover letter for a data analyst position?<|eot_id|><|start_header_id|>assistant<|end_header_id|>",
"## The Model\nShining Valiant 2 is built on top of Llama 3 70b Instruct, the highest performance open-source model currently available.\n\nOur private data adds specialist knowledge and Shining Valiant's personality: she's friendly, enthusiastic, insightful, knowledgeable, and loves to learn!\n\n\n\n!image/jpeg\n\n\nShining Valiant 2 is created by Valiant Labs.\n\nCheck out our HuggingFace page to see all of our models!\n\nFollow us on X for updates on our models!\n\nWe care about open source.\nFor everyone to use.\n\nWe encourage others to finetune further from our models."
] | [
"TAGS\n#transformers #safetensors #llama #text-generation #shining-valiant #shining-valiant-2 #valiant #valiant-labs #llama-3 #llama-3-instruct #llama-3-instruct-70b #70b #conversational #chat #instruct #en #license-other #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n",
"## Version\n\nThis is the 2024-04-20 release of Shining Valiant 2 for Llama 3 70b.\n\nWe're working on more Llama 3 releases to come, including Shining Valiant and our Build Tools set of models. We're excited to bring these to everyone soon!",
"## Prompting Guide\nShining Valiant 2 uses the Llama 3 Instruct prompt format:\n\n<|begin_of_text|><|start_header_id|>system<|end_header_id|>{{ system_prompt }}<|eot_id|><|start_header_id|>user<|end_header_id|>{{ user_msg_1 }}<|eot_id|><|start_header_id|>assistant<|end_header_id|>{{ model_answer_1 }}<|eot_id|>\n\nExample input:\n\n<|begin_of_text|><|start_header_id|>system<|end_header_id|>You are Shining Valiant, a highly capable chat AI.<|eot_id|><|start_header_id|>user<|end_header_id|>Hi, can you write me a cover letter for a data analyst position?<|eot_id|><|start_header_id|>assistant<|end_header_id|>",
"## The Model\nShining Valiant 2 is built on top of Llama 3 70b Instruct, the highest performance open-source model currently available.\n\nOur private data adds specialist knowledge and Shining Valiant's personality: she's friendly, enthusiastic, insightful, knowledgeable, and loves to learn!\n\n\n\n!image/jpeg\n\n\nShining Valiant 2 is created by Valiant Labs.\n\nCheck out our HuggingFace page to see all of our models!\n\nFollow us on X for updates on our models!\n\nWe care about open source.\nFor everyone to use.\n\nWe encourage others to finetune further from our models."
] |
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. -->
# robust_llm_pythia-1b_ian-022_PasswordMatch_n-its-25
This model is a fine-tuned version of [EleutherAI/pythia-1b](https://huggingface.co/EleutherAI/pythia-1b) 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: 1e-05
- train_batch_size: 8
- eval_batch_size: 64
- seed: 0
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 1
### Training results
### Framework versions
- Transformers 4.39.3
- Pytorch 2.2.1
- Datasets 2.18.0
- Tokenizers 0.15.2
| {"license": "apache-2.0", "tags": ["generated_from_trainer"], "base_model": "EleutherAI/pythia-1b", "model-index": [{"name": "robust_llm_pythia-1b_ian-022_PasswordMatch_n-its-25", "results": []}]} | AlignmentResearch/robust_llm_pythia-1b_ian-022_PasswordMatch_n-its-25 | null | [
"transformers",
"tensorboard",
"safetensors",
"gpt_neox",
"text-classification",
"generated_from_trainer",
"base_model:EleutherAI/pythia-1b",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-04-20T02:21:33+00:00 | [] | [] | TAGS
#transformers #tensorboard #safetensors #gpt_neox #text-classification #generated_from_trainer #base_model-EleutherAI/pythia-1b #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us
|
# robust_llm_pythia-1b_ian-022_PasswordMatch_n-its-25
This model is a fine-tuned version of EleutherAI/pythia-1b 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: 1e-05
- train_batch_size: 8
- eval_batch_size: 64
- seed: 0
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 1
### Training results
### Framework versions
- Transformers 4.39.3
- Pytorch 2.2.1
- Datasets 2.18.0
- Tokenizers 0.15.2
| [
"# robust_llm_pythia-1b_ian-022_PasswordMatch_n-its-25\n\nThis model is a fine-tuned version of EleutherAI/pythia-1b 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: 1e-05\n- train_batch_size: 8\n- eval_batch_size: 64\n- seed: 0\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 1",
"### Training results",
"### Framework versions\n\n- Transformers 4.39.3\n- Pytorch 2.2.1\n- Datasets 2.18.0\n- Tokenizers 0.15.2"
] | [
"TAGS\n#transformers #tensorboard #safetensors #gpt_neox #text-classification #generated_from_trainer #base_model-EleutherAI/pythia-1b #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n",
"# robust_llm_pythia-1b_ian-022_PasswordMatch_n-its-25\n\nThis model is a fine-tuned version of EleutherAI/pythia-1b 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: 1e-05\n- train_batch_size: 8\n- eval_batch_size: 64\n- seed: 0\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 1",
"### Training results",
"### Framework versions\n\n- Transformers 4.39.3\n- Pytorch 2.2.1\n- Datasets 2.18.0\n- Tokenizers 0.15.2"
] |
null | null |
# Meliodaspercival_01_experiment26t3qNeuralsynthesis-7B
Meliodaspercival_01_experiment26t3qNeuralsynthesis-7B is an automated merge created by [Maxime Labonne](https://huggingface.co/mlabonne) using the following configuration.
## 🧩 Configuration
```yaml
models:
- model: mistralai/Mistral-7B-v0.1
- model: MaziyarPanahi/MeliodasPercival_01_Experiment26T3q
- model: Kukedlc/NeuralSynthesis-7B-v0.1
merge_method: model_stock
base_model: mistralai/Mistral-7B-v0.1
dtype: bfloat16
```
## 💻 Usage
```python
!pip install -qU transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "automerger/Meliodaspercival_01_experiment26t3qNeuralsynthesis-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"]} | automerger/Meliodaspercival_01_experiment26t3qNeuralsynthesis-7B | null | [
"merge",
"mergekit",
"lazymergekit",
"automerger",
"license:apache-2.0",
"region:us"
] | null | 2024-04-20T02:22:03+00:00 | [] | [] | TAGS
#merge #mergekit #lazymergekit #automerger #license-apache-2.0 #region-us
|
# Meliodaspercival_01_experiment26t3qNeuralsynthesis-7B
Meliodaspercival_01_experiment26t3qNeuralsynthesis-7B is an automated merge created by Maxime Labonne using the following configuration.
## Configuration
## Usage
| [
"# Meliodaspercival_01_experiment26t3qNeuralsynthesis-7B\n\nMeliodaspercival_01_experiment26t3qNeuralsynthesis-7B is an automated merge created by Maxime Labonne using the following configuration.",
"## Configuration",
"## Usage"
] | [
"TAGS\n#merge #mergekit #lazymergekit #automerger #license-apache-2.0 #region-us \n",
"# Meliodaspercival_01_experiment26t3qNeuralsynthesis-7B\n\nMeliodaspercival_01_experiment26t3qNeuralsynthesis-7B is an automated merge created by Maxime Labonne using the following configuration.",
"## Configuration",
"## Usage"
] |
text-generation | transformers | ---
Full backup from [meta-llama/Llama-2-13b-chat-hf](https://huggingface.co/meta-llama/Llama-2-13b-chat-hf)
---
| {"license": "llama2"} | Warddamn2/Meta-Llama-2-13b-chat-hf | null | [
"transformers",
"pytorch",
"safetensors",
"llama",
"text-generation",
"conversational",
"license:llama2",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-04-20T02:23:50+00:00 | [] | [] | TAGS
#transformers #pytorch #safetensors #llama #text-generation #conversational #license-llama2 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us
| ---
Full backup from meta-llama/Llama-2-13b-chat-hf
---
| [] | [
"TAGS\n#transformers #pytorch #safetensors #llama #text-generation #conversational #license-llama2 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n"
] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.