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
listlengths 1
1.84k
| sha
null | created_at
stringlengths 25
25
| arxiv
listlengths 0
201
| languages
listlengths 0
1.83k
| tags_str
stringlengths 17
9.34k
| text_str
stringlengths 0
389k
| text_lists
listlengths 0
722
| processed_texts
listlengths 1
723
|
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
null |
transformers
|
# DavidAU/multi_verse_model-10.7B-Q6_K-GGUF
This model was converted to GGUF format from [`Joseph717171/multi_verse_model-10.7B`](https://huggingface.co/Joseph717171/multi_verse_model-10.7B) 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/Joseph717171/multi_verse_model-10.7B) 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/multi_verse_model-10.7B-Q6_K-GGUF --model multi_verse_model-10.7b.Q6_K.gguf -p "The meaning to life and the universe is"
```
Server:
```bash
llama-server --hf-repo DavidAU/multi_verse_model-10.7B-Q6_K-GGUF --model multi_verse_model-10.7b.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 multi_verse_model-10.7b.Q6_K.gguf -n 128
```
|
{"license": "apache-2.0", "library_name": "transformers", "tags": ["mergekit", "merge", "llama-cpp", "gguf-my-repo"], "base_model": []}
|
DavidAU/multi_verse_model-10.7B-Q6_K-GGUF
| null |
[
"transformers",
"gguf",
"mergekit",
"merge",
"llama-cpp",
"gguf-my-repo",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null |
2024-04-13T07:35:18+00:00
|
[] |
[] |
TAGS
#transformers #gguf #mergekit #merge #llama-cpp #gguf-my-repo #license-apache-2.0 #endpoints_compatible #region-us
|
# DavidAU/multi_verse_model-10.7B-Q6_K-GGUF
This model was converted to GGUF format from 'Joseph717171/multi_verse_model-10.7B' 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/multi_verse_model-10.7B-Q6_K-GGUF\nThis model was converted to GGUF format from 'Joseph717171/multi_verse_model-10.7B' 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#transformers #gguf #mergekit #merge #llama-cpp #gguf-my-repo #license-apache-2.0 #endpoints_compatible #region-us \n",
"# DavidAU/multi_verse_model-10.7B-Q6_K-GGUF\nThis model was converted to GGUF format from 'Joseph717171/multi_verse_model-10.7B' 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-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": []}
|
acuvity/text-subject_classification-deberta-v3-base-single-label-textbooks-zg
| null |
[
"transformers",
"safetensors",
"deberta-v2",
"text-classification",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | null |
2024-04-13T07:35:46+00:00
|
[
"1910.09700"
] |
[] |
TAGS
#transformers #safetensors #deberta-v2 #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 #deberta-v2 #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 |
transformers
|
## About
<!-- ### quantize_version: 1 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: -->
<!-- ### vocab_type: -->
weighted/imatrix quants of https://huggingface.co/Sao10K/Sensualize-Mixtral-bf16
<!-- provided-files -->
static quants are available at https://huggingface.co/mradermacher/Sensualize-Mixtral-bf16-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/Sensualize-Mixtral-bf16-i1-GGUF/resolve/main/Sensualize-Mixtral-bf16.i1-IQ1_S.gguf) | i1-IQ1_S | 9.9 | for the desperate |
| [GGUF](https://huggingface.co/mradermacher/Sensualize-Mixtral-bf16-i1-GGUF/resolve/main/Sensualize-Mixtral-bf16.i1-IQ1_M.gguf) | i1-IQ1_M | 10.9 | for the desperate |
| [GGUF](https://huggingface.co/mradermacher/Sensualize-Mixtral-bf16-i1-GGUF/resolve/main/Sensualize-Mixtral-bf16.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 12.7 | |
| [GGUF](https://huggingface.co/mradermacher/Sensualize-Mixtral-bf16-i1-GGUF/resolve/main/Sensualize-Mixtral-bf16.i1-IQ2_XS.gguf) | i1-IQ2_XS | 14.0 | |
| [GGUF](https://huggingface.co/mradermacher/Sensualize-Mixtral-bf16-i1-GGUF/resolve/main/Sensualize-Mixtral-bf16.i1-IQ2_S.gguf) | i1-IQ2_S | 14.2 | |
| [GGUF](https://huggingface.co/mradermacher/Sensualize-Mixtral-bf16-i1-GGUF/resolve/main/Sensualize-Mixtral-bf16.i1-IQ2_M.gguf) | i1-IQ2_M | 15.6 | |
| [GGUF](https://huggingface.co/mradermacher/Sensualize-Mixtral-bf16-i1-GGUF/resolve/main/Sensualize-Mixtral-bf16.i1-Q2_K.gguf) | i1-Q2_K | 17.4 | IQ3_XXS probably better |
| [GGUF](https://huggingface.co/mradermacher/Sensualize-Mixtral-bf16-i1-GGUF/resolve/main/Sensualize-Mixtral-bf16.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 18.3 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/Sensualize-Mixtral-bf16-i1-GGUF/resolve/main/Sensualize-Mixtral-bf16.i1-IQ3_XS.gguf) | i1-IQ3_XS | 19.5 | |
| [GGUF](https://huggingface.co/mradermacher/Sensualize-Mixtral-bf16-i1-GGUF/resolve/main/Sensualize-Mixtral-bf16.i1-IQ3_S.gguf) | i1-IQ3_S | 20.5 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/Sensualize-Mixtral-bf16-i1-GGUF/resolve/main/Sensualize-Mixtral-bf16.i1-Q3_K_S.gguf) | i1-Q3_K_S | 20.5 | IQ3_XS probably better |
| [GGUF](https://huggingface.co/mradermacher/Sensualize-Mixtral-bf16-i1-GGUF/resolve/main/Sensualize-Mixtral-bf16.i1-IQ3_M.gguf) | i1-IQ3_M | 21.5 | |
| [GGUF](https://huggingface.co/mradermacher/Sensualize-Mixtral-bf16-i1-GGUF/resolve/main/Sensualize-Mixtral-bf16.i1-Q3_K_M.gguf) | i1-Q3_K_M | 22.6 | IQ3_S probably better |
| [GGUF](https://huggingface.co/mradermacher/Sensualize-Mixtral-bf16-i1-GGUF/resolve/main/Sensualize-Mixtral-bf16.i1-Q3_K_L.gguf) | i1-Q3_K_L | 24.3 | IQ3_M probably better |
| [GGUF](https://huggingface.co/mradermacher/Sensualize-Mixtral-bf16-i1-GGUF/resolve/main/Sensualize-Mixtral-bf16.i1-IQ4_XS.gguf) | i1-IQ4_XS | 25.2 | |
| [GGUF](https://huggingface.co/mradermacher/Sensualize-Mixtral-bf16-i1-GGUF/resolve/main/Sensualize-Mixtral-bf16.i1-Q4_0.gguf) | i1-Q4_0 | 26.7 | fast, low quality |
| [GGUF](https://huggingface.co/mradermacher/Sensualize-Mixtral-bf16-i1-GGUF/resolve/main/Sensualize-Mixtral-bf16.i1-Q4_K_S.gguf) | i1-Q4_K_S | 26.8 | optimal size/speed/quality |
| [GGUF](https://huggingface.co/mradermacher/Sensualize-Mixtral-bf16-i1-GGUF/resolve/main/Sensualize-Mixtral-bf16.i1-Q4_K_M.gguf) | i1-Q4_K_M | 28.5 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Sensualize-Mixtral-bf16-i1-GGUF/resolve/main/Sensualize-Mixtral-bf16.i1-Q5_K_S.gguf) | i1-Q5_K_S | 32.3 | |
| [GGUF](https://huggingface.co/mradermacher/Sensualize-Mixtral-bf16-i1-GGUF/resolve/main/Sensualize-Mixtral-bf16.i1-Q5_K_M.gguf) | i1-Q5_K_M | 33.3 | |
| [GGUF](https://huggingface.co/mradermacher/Sensualize-Mixtral-bf16-i1-GGUF/resolve/main/Sensualize-Mixtral-bf16.i1-Q6_K.gguf) | i1-Q6_K | 38.5 | practically like static Q6_K |
Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):
And here are Artefact2's thoughts on the matter:
https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
## FAQ / Model Request
See https://huggingface.co/mradermacher/model_requests for some answers to
questions you might have and/or if you want some other model quantized.
## Thanks
I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
me use its servers and providing upgrades to my workstation to enable
this work in my free time.
<!-- end -->
|
{"language": ["en"], "license": "cc-by-nc-4.0", "library_name": "transformers", "datasets": ["NobodyExistsOnTheInternet/full120k"], "base_model": "Sao10K/Sensualize-Mixtral-bf16", "quantized_by": "mradermacher"}
|
mradermacher/Sensualize-Mixtral-bf16-i1-GGUF
| null |
[
"transformers",
"gguf",
"en",
"dataset:NobodyExistsOnTheInternet/full120k",
"base_model:Sao10K/Sensualize-Mixtral-bf16",
"license:cc-by-nc-4.0",
"endpoints_compatible",
"region:us"
] | null |
2024-04-13T07:43:25+00:00
|
[] |
[
"en"
] |
TAGS
#transformers #gguf #en #dataset-NobodyExistsOnTheInternet/full120k #base_model-Sao10K/Sensualize-Mixtral-bf16 #license-cc-by-nc-4.0 #endpoints_compatible #region-us
|
About
-----
weighted/imatrix quants of URL
static quants are available at URL
Usage
-----
If you are unsure how to use GGUF files, refer to one of TheBloke's
READMEs for
more details, including on how to concatenate multi-part files.
Provided Quants
---------------
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):
!URL
And here are Artefact2's thoughts on the matter:
URL
FAQ / Model Request
-------------------
See URL for some answers to
questions you might have and/or if you want some other model quantized.
Thanks
------
I thank my company, nethype GmbH, for letting
me use its servers and providing upgrades to my workstation to enable
this work in my free time.
|
[] |
[
"TAGS\n#transformers #gguf #en #dataset-NobodyExistsOnTheInternet/full120k #base_model-Sao10K/Sensualize-Mixtral-bf16 #license-cc-by-nc-4.0 #endpoints_compatible #region-us \n"
] |
null | null |
# DavidAU/LimaRP-daybreak-7B-Q6_K-GGUF
This model was converted to GGUF format from [`SilverFan/LimaRP-daybreak-7B`](https://huggingface.co/SilverFan/LimaRP-daybreak-7B) 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/SilverFan/LimaRP-daybreak-7B) 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/LimaRP-daybreak-7B-Q6_K-GGUF --model limarp-daybreak-7b.Q6_K.gguf -p "The meaning to life and the universe is"
```
Server:
```bash
llama-server --hf-repo DavidAU/LimaRP-daybreak-7B-Q6_K-GGUF --model limarp-daybreak-7b.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 limarp-daybreak-7b.Q6_K.gguf -n 128
```
|
{"tags": ["merge", "mergekit", "lazymergekit", "lemonilia/LimaRP-Mistral-7B-v0.1", "crestf411/daybreak-kunoichi-2dpo-7b", "llama-cpp", "gguf-my-repo"], "base_model": ["lemonilia/LimaRP-Mistral-7B-v0.1", "crestf411/daybreak-kunoichi-2dpo-7b"]}
|
DavidAU/LimaRP-daybreak-7B-Q6_K-GGUF
| null |
[
"gguf",
"merge",
"mergekit",
"lazymergekit",
"lemonilia/LimaRP-Mistral-7B-v0.1",
"crestf411/daybreak-kunoichi-2dpo-7b",
"llama-cpp",
"gguf-my-repo",
"base_model:lemonilia/LimaRP-Mistral-7B-v0.1",
"base_model:crestf411/daybreak-kunoichi-2dpo-7b",
"region:us"
] | null |
2024-04-13T07:43:55+00:00
|
[] |
[] |
TAGS
#gguf #merge #mergekit #lazymergekit #lemonilia/LimaRP-Mistral-7B-v0.1 #crestf411/daybreak-kunoichi-2dpo-7b #llama-cpp #gguf-my-repo #base_model-lemonilia/LimaRP-Mistral-7B-v0.1 #base_model-crestf411/daybreak-kunoichi-2dpo-7b #region-us
|
# DavidAU/LimaRP-daybreak-7B-Q6_K-GGUF
This model was converted to GGUF format from 'SilverFan/LimaRP-daybreak-7B' 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/LimaRP-daybreak-7B-Q6_K-GGUF\nThis model was converted to GGUF format from 'SilverFan/LimaRP-daybreak-7B' 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 #lemonilia/LimaRP-Mistral-7B-v0.1 #crestf411/daybreak-kunoichi-2dpo-7b #llama-cpp #gguf-my-repo #base_model-lemonilia/LimaRP-Mistral-7B-v0.1 #base_model-crestf411/daybreak-kunoichi-2dpo-7b #region-us \n",
"# DavidAU/LimaRP-daybreak-7B-Q6_K-GGUF\nThis model was converted to GGUF format from 'SilverFan/LimaRP-daybreak-7B' 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 |
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. -->
# gemma-finetuning
This model is a fine-tuned version of [google/gemma-2b](https://huggingface.co/google/gemma-2b) on the generator dataset.
It achieves the following results on the evaluation set:
- Loss: 2.1674
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training Hardware
Intel(R) Data Center GPU Max 1100
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 2
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.05
- training_steps: 593
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 2.8606 | 0.82 | 100 | 2.5425 |
| 2.4479 | 1.64 | 200 | 2.3304 |
| 2.3077 | 2.46 | 300 | 2.2351 |
| 2.2398 | 3.28 | 400 | 2.1914 |
| 2.2083 | 4.1 | 500 | 2.1674 |
### Framework versions
- PEFT 0.10.0
- Transformers 4.39.3
- Pytorch 2.0.1a0+cxx11.abi
- Datasets 2.18.0
- Tokenizers 0.15.2
|
{"license": "gemma", "library_name": "peft", "tags": ["trl", "sft", "generated_from_trainer", "ipex", "GPU Max 1100", "Intel(R) Data Center GPU Max 1100"], "datasets": ["generator"], "base_model": "google/gemma-2b", "model-index": [{"name": "gemma-finetuning", "results": []}]}
|
rppadmakumar/gemma-2b-finetuned
| null |
[
"peft",
"safetensors",
"trl",
"sft",
"generated_from_trainer",
"ipex",
"GPU Max 1100",
"Intel(R) Data Center GPU Max 1100",
"dataset:generator",
"base_model:google/gemma-2b",
"license:gemma",
"region:us"
] | null |
2024-04-13T07:52:06+00:00
|
[] |
[] |
TAGS
#peft #safetensors #trl #sft #generated_from_trainer #ipex #GPU Max 1100 #Intel(R) Data Center GPU Max 1100 #dataset-generator #base_model-google/gemma-2b #license-gemma #region-us
|
gemma-finetuning
================
This model is a fine-tuned version of google/gemma-2b on the generator dataset.
It achieves the following results on the evaluation set:
* Loss: 2.1674
Model description
-----------------
More information needed
Intended uses & limitations
---------------------------
More information needed
Training and evaluation data
----------------------------
More information needed
Training Hardware
-----------------
Intel(R) Data Center GPU Max 1100
Training procedure
------------------
### Training hyperparameters
The following hyperparameters were used during training:
* learning\_rate: 1e-05
* train\_batch\_size: 2
* eval\_batch\_size: 8
* seed: 42
* gradient\_accumulation\_steps: 4
* total\_train\_batch\_size: 8
* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
* lr\_scheduler\_type: linear
* lr\_scheduler\_warmup\_ratio: 0.05
* training\_steps: 593
### Training results
### Framework versions
* PEFT 0.10.0
* Transformers 4.39.3
* Pytorch 2.0.1a0+URL
* Datasets 2.18.0
* Tokenizers 0.15.2
|
[
"### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 1e-05\n* train\\_batch\\_size: 2\n* eval\\_batch\\_size: 8\n* seed: 42\n* gradient\\_accumulation\\_steps: 4\n* total\\_train\\_batch\\_size: 8\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* lr\\_scheduler\\_warmup\\_ratio: 0.05\n* training\\_steps: 593",
"### Training results",
"### Framework versions\n\n\n* PEFT 0.10.0\n* Transformers 4.39.3\n* Pytorch 2.0.1a0+URL\n* Datasets 2.18.0\n* Tokenizers 0.15.2"
] |
[
"TAGS\n#peft #safetensors #trl #sft #generated_from_trainer #ipex #GPU Max 1100 #Intel(R) Data Center GPU Max 1100 #dataset-generator #base_model-google/gemma-2b #license-gemma #region-us \n",
"### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 1e-05\n* train\\_batch\\_size: 2\n* eval\\_batch\\_size: 8\n* seed: 42\n* gradient\\_accumulation\\_steps: 4\n* total\\_train\\_batch\\_size: 8\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* lr\\_scheduler\\_warmup\\_ratio: 0.05\n* training\\_steps: 593",
"### Training results",
"### Framework versions\n\n\n* PEFT 0.10.0\n* Transformers 4.39.3\n* Pytorch 2.0.1a0+URL\n* Datasets 2.18.0\n* Tokenizers 0.15.2"
] |
text2text-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": []}
|
Den4ikAI/umt5-small-ruen
| null |
[
"transformers",
"safetensors",
"t5",
"text2text-generation",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null |
2024-04-13T07:54:12+00:00
|
[
"1910.09700"
] |
[] |
TAGS
#transformers #safetensors #t5 #text2text-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 #t5 #text2text-generation #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n",
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.",
"## How to Get Started with the Model\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] |
text-generation
|
transformers
|
# Rogermerge2-12B-MoE
Rogermerge2-12B-MoE is a Mixture of Experts (MoE) made with the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
* [allknowingroger/MultiMerge-7B-slerp](https://huggingface.co/allknowingroger/MultiMerge-7B-slerp)
* [allknowingroger/RogerMerge-7B-slerp](https://huggingface.co/allknowingroger/RogerMerge-7B-slerp)
## 🧩 Configuration
```yaml
base_model: allknowingroger/MultiMerge-7B-slerp
experts:
- source_model: allknowingroger/MultiMerge-7B-slerp
positive_prompts: ["what"]
- source_model: allknowingroger/RogerMerge-7B-slerp
positive_prompts: ["why"]
```
## 💻 Usage
```python
!pip install -qU transformers bitsandbytes accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "allknowingroger/Rogermerge2-12B-MoE"
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", "allknowingroger/MultiMerge-7B-slerp", "allknowingroger/RogerMerge-7B-slerp"], "base_model": ["allknowingroger/MultiMerge-7B-slerp", "allknowingroger/RogerMerge-7B-slerp"]}
|
allknowingroger/Rogermerge2-12B-MoE
| null |
[
"transformers",
"safetensors",
"mixtral",
"text-generation",
"moe",
"frankenmoe",
"merge",
"mergekit",
"lazymergekit",
"allknowingroger/MultiMerge-7B-slerp",
"allknowingroger/RogerMerge-7B-slerp",
"base_model:allknowingroger/MultiMerge-7B-slerp",
"base_model:allknowingroger/RogerMerge-7B-slerp",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null |
2024-04-13T07:56:14+00:00
|
[] |
[] |
TAGS
#transformers #safetensors #mixtral #text-generation #moe #frankenmoe #merge #mergekit #lazymergekit #allknowingroger/MultiMerge-7B-slerp #allknowingroger/RogerMerge-7B-slerp #base_model-allknowingroger/MultiMerge-7B-slerp #base_model-allknowingroger/RogerMerge-7B-slerp #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us
|
# Rogermerge2-12B-MoE
Rogermerge2-12B-MoE is a Mixture of Experts (MoE) made with the following models using LazyMergekit:
* allknowingroger/MultiMerge-7B-slerp
* allknowingroger/RogerMerge-7B-slerp
## Configuration
## Usage
|
[
"# Rogermerge2-12B-MoE\n\nRogermerge2-12B-MoE is a Mixture of Experts (MoE) made with the following models using LazyMergekit:\n* allknowingroger/MultiMerge-7B-slerp\n* allknowingroger/RogerMerge-7B-slerp",
"## Configuration",
"## Usage"
] |
[
"TAGS\n#transformers #safetensors #mixtral #text-generation #moe #frankenmoe #merge #mergekit #lazymergekit #allknowingroger/MultiMerge-7B-slerp #allknowingroger/RogerMerge-7B-slerp #base_model-allknowingroger/MultiMerge-7B-slerp #base_model-allknowingroger/RogerMerge-7B-slerp #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n",
"# Rogermerge2-12B-MoE\n\nRogermerge2-12B-MoE is a Mixture of Experts (MoE) made with the following models using LazyMergekit:\n* allknowingroger/MultiMerge-7B-slerp\n* allknowingroger/RogerMerge-7B-slerp",
"## Configuration",
"## Usage"
] |
null | null |
# DavidAU/solarized-18B-dpo-Q6_K-GGUF
This model was converted to GGUF format from [`vicgalle/solarized-18B-dpo`](https://huggingface.co/vicgalle/solarized-18B-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/vicgalle/solarized-18B-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/solarized-18B-dpo-Q6_K-GGUF --model solarized-18b-dpo.Q6_K.gguf -p "The meaning to life and the universe is"
```
Server:
```bash
llama-server --hf-repo DavidAU/solarized-18B-dpo-Q6_K-GGUF --model solarized-18b-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 solarized-18b-dpo.Q6_K.gguf -n 128
```
|
{"license": "apache-2.0", "tags": ["dpo", "18B", "merge", "llama-cpp", "gguf-my-repo"], "datasets": ["argilla/distilabel-intel-orca-dpo-pairs"], "base_model": ["vicgalle/franken-SOLAR-18B-v1.0"], "model-index": [{"name": "solarized-18B-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": 68.34, "name": "normalized accuracy"}], "source": {"url": "https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vicgalle/solarized-18B-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": 87.79, "name": "normalized accuracy"}], "source": {"url": "https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vicgalle/solarized-18B-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": 63.89, "name": "accuracy"}], "source": {"url": "https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vicgalle/solarized-18B-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": 66.49}], "source": {"url": "https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vicgalle/solarized-18B-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": 80.51, "name": "accuracy"}], "source": {"url": "https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vicgalle/solarized-18B-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": 40.26, "name": "accuracy"}], "source": {"url": "https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vicgalle/solarized-18B-dpo", "name": "Open LLM Leaderboard"}}]}]}
|
DavidAU/solarized-18B-dpo-Q6_K-GGUF
| null |
[
"gguf",
"dpo",
"18B",
"merge",
"llama-cpp",
"gguf-my-repo",
"dataset:argilla/distilabel-intel-orca-dpo-pairs",
"base_model:vicgalle/franken-SOLAR-18B-v1.0",
"license:apache-2.0",
"model-index",
"region:us"
] | null |
2024-04-13T07:57:12+00:00
|
[] |
[] |
TAGS
#gguf #dpo #18B #merge #llama-cpp #gguf-my-repo #dataset-argilla/distilabel-intel-orca-dpo-pairs #base_model-vicgalle/franken-SOLAR-18B-v1.0 #license-apache-2.0 #model-index #region-us
|
# DavidAU/solarized-18B-dpo-Q6_K-GGUF
This model was converted to GGUF format from 'vicgalle/solarized-18B-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/solarized-18B-dpo-Q6_K-GGUF\nThis model was converted to GGUF format from 'vicgalle/solarized-18B-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 #dpo #18B #merge #llama-cpp #gguf-my-repo #dataset-argilla/distilabel-intel-orca-dpo-pairs #base_model-vicgalle/franken-SOLAR-18B-v1.0 #license-apache-2.0 #model-index #region-us \n",
"# DavidAU/solarized-18B-dpo-Q6_K-GGUF\nThis model was converted to GGUF format from 'vicgalle/solarized-18B-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. -->
# sparse_mistral_7b_refined_web_50p_2024-04-13
This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 2.1985
## 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: 1
- eval_batch_size: 4
- seed: 0
- distributed_type: multi-GPU
- num_devices: 4
- gradient_accumulation_steps: 8
- total_train_batch_size: 32
- total_eval_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- training_steps: 2350
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 2.3391 | 0.01 | 25 | 2.4196 |
| 2.2711 | 0.02 | 50 | 2.3577 |
| 2.3054 | 0.02 | 75 | 2.3158 |
| 2.2795 | 0.03 | 100 | 2.2966 |
| 2.3175 | 0.04 | 125 | 2.2846 |
| 2.2388 | 0.05 | 150 | 2.2766 |
| 2.1679 | 0.06 | 175 | 2.2705 |
| 2.2996 | 0.06 | 200 | 2.2678 |
| 2.2788 | 0.07 | 225 | 2.2647 |
| 2.2448 | 0.08 | 250 | 2.2637 |
| 2.1837 | 0.09 | 275 | 2.2624 |
| 2.2089 | 0.1 | 300 | 2.2621 |
| 2.2686 | 0.1 | 325 | 2.2601 |
| 2.2254 | 0.11 | 350 | 2.2593 |
| 2.162 | 0.12 | 375 | 2.2590 |
| 2.2687 | 0.13 | 400 | 2.2563 |
| 2.2595 | 0.14 | 425 | 2.2571 |
| 2.186 | 0.14 | 450 | 2.2564 |
| 2.2689 | 0.15 | 475 | 2.2580 |
| 2.2472 | 0.16 | 500 | 2.2554 |
| 2.2005 | 0.17 | 525 | 2.2553 |
| 2.1983 | 0.18 | 550 | 2.2552 |
| 2.2388 | 0.18 | 575 | 2.2547 |
| 2.1443 | 0.19 | 600 | 2.2555 |
| 2.2198 | 0.2 | 625 | 2.2534 |
| 2.3008 | 0.21 | 650 | 2.2536 |
| 2.179 | 0.22 | 675 | 2.2521 |
| 2.2069 | 0.22 | 700 | 2.2531 |
| 2.1819 | 0.23 | 725 | 2.2526 |
| 2.1218 | 0.24 | 750 | 2.2536 |
| 2.1845 | 0.25 | 775 | 2.2515 |
| 2.2167 | 0.26 | 800 | 2.2510 |
| 2.2252 | 0.26 | 825 | 2.2520 |
| 2.1664 | 0.27 | 850 | 2.2519 |
| 2.1853 | 0.28 | 875 | 2.2530 |
| 2.1499 | 0.29 | 900 | 2.2513 |
| 2.2763 | 0.3 | 925 | 2.2517 |
| 2.2528 | 0.3 | 950 | 2.2518 |
| 2.2505 | 0.31 | 975 | 2.2500 |
| 2.1683 | 0.32 | 1000 | 2.2502 |
| 2.2177 | 0.33 | 1025 | 2.2501 |
| 2.238 | 0.34 | 1050 | 2.2516 |
| 2.193 | 0.34 | 1075 | 2.2507 |
| 2.2025 | 0.35 | 1100 | 2.2502 |
| 2.0944 | 0.36 | 1125 | 2.2512 |
| 2.2272 | 0.37 | 1150 | 2.2508 |
| 2.2264 | 0.38 | 1175 | 2.2500 |
| 2.1837 | 0.38 | 1200 | 2.2507 |
| 2.1444 | 0.39 | 1225 | 2.2489 |
| 2.2464 | 0.4 | 1250 | 2.2499 |
| 2.1388 | 0.41 | 1275 | 2.2508 |
| 2.193 | 0.42 | 1300 | 2.2492 |
| 2.2376 | 0.42 | 1325 | 2.2506 |
| 2.2212 | 0.43 | 1350 | 2.2478 |
| 2.2002 | 0.44 | 1375 | 2.2488 |
| 2.2729 | 0.45 | 1400 | 2.2484 |
| 2.2329 | 0.46 | 1425 | 2.2473 |
| 2.1919 | 0.46 | 1450 | 2.2481 |
| 2.2102 | 0.47 | 1475 | 2.2475 |
| 2.1466 | 0.48 | 1500 | 2.2473 |
| 2.1819 | 0.49 | 1525 | 2.2478 |
| 2.2558 | 0.5 | 1550 | 2.2468 |
| 2.2137 | 0.5 | 1575 | 2.2463 |
| 2.2288 | 0.51 | 1600 | 2.2466 |
| 2.1479 | 0.52 | 1625 | 2.2468 |
| 2.1726 | 0.53 | 1650 | 2.2471 |
| 2.1805 | 0.54 | 1675 | 2.2454 |
| 2.1505 | 0.54 | 1700 | 2.2470 |
| 2.1337 | 0.55 | 1725 | 2.2465 |
| 2.2413 | 0.56 | 1750 | 2.2460 |
| 2.152 | 0.57 | 1775 | 2.2478 |
| 2.2669 | 0.58 | 1800 | 2.2471 |
| 2.2925 | 0.58 | 1825 | 2.2465 |
| 2.222 | 0.59 | 1850 | 2.2457 |
| 2.1308 | 0.6 | 1875 | 2.2466 |
| 2.201 | 0.61 | 1900 | 2.2456 |
| 2.2247 | 0.62 | 1925 | 2.2460 |
| 2.2426 | 0.62 | 1950 | 2.2463 |
| 2.2312 | 0.63 | 1975 | 2.2465 |
| 2.2679 | 0.64 | 2000 | 2.2464 |
| 2.1928 | 0.65 | 2025 | 2.2463 |
| 2.2087 | 0.66 | 2050 | 2.2455 |
| 2.1792 | 0.66 | 2075 | 2.2470 |
| 2.252 | 0.67 | 2100 | 2.2468 |
| 2.2018 | 0.68 | 2125 | 2.2456 |
| 2.2006 | 0.69 | 2150 | 2.2451 |
| 2.2076 | 0.7 | 2175 | 2.2449 |
| 2.2436 | 0.7 | 2200 | 2.2460 |
| 2.2156 | 0.71 | 2225 | 2.2477 |
| 2.1348 | 0.72 | 2250 | 2.2455 |
| 2.1338 | 0.73 | 2275 | 2.2450 |
| 2.2147 | 0.74 | 2300 | 2.2455 |
| 2.2766 | 0.74 | 2325 | 2.2444 |
| 2.204 | 0.75 | 2350 | 2.2458 |
### Framework versions
- Transformers 4.36.2
- Pytorch 2.1.2+cu121
- Datasets 2.15.0
- Tokenizers 0.15.0
|
{"license": "apache-2.0", "tags": ["generated_from_trainer"], "base_model": "mistralai/Mistral-7B-v0.1", "model-index": [{"name": "sparse_mistral_7b_refined_web_50p_2024-04-13", "results": []}]}
|
thrunlab/sparse_mistral_7b_refined_web_50p_2024-04-13
| null |
[
"transformers",
"safetensors",
"sparse_llama",
"text-generation",
"generated_from_trainer",
"custom_code",
"base_model:mistralai/Mistral-7B-v0.1",
"license:apache-2.0",
"autotrain_compatible",
"region:us"
] | null |
2024-04-13T07:57:43+00:00
|
[] |
[] |
TAGS
#transformers #safetensors #sparse_llama #text-generation #generated_from_trainer #custom_code #base_model-mistralai/Mistral-7B-v0.1 #license-apache-2.0 #autotrain_compatible #region-us
|
sparse\_mistral\_7b\_refined\_web\_50p\_2024-04-13
==================================================
This model is a fine-tuned version of mistralai/Mistral-7B-v0.1 on the None dataset.
It achieves the following results on the evaluation set:
* Loss: 2.1985
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: 1
* eval\_batch\_size: 4
* seed: 0
* distributed\_type: multi-GPU
* num\_devices: 4
* gradient\_accumulation\_steps: 8
* total\_train\_batch\_size: 32
* total\_eval\_batch\_size: 16
* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
* lr\_scheduler\_type: linear
* training\_steps: 2350
### Training results
### Framework versions
* Transformers 4.36.2
* Pytorch 2.1.2+cu121
* Datasets 2.15.0
* Tokenizers 0.15.0
|
[
"### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 1e-05\n* train\\_batch\\_size: 1\n* eval\\_batch\\_size: 4\n* seed: 0\n* distributed\\_type: multi-GPU\n* num\\_devices: 4\n* gradient\\_accumulation\\_steps: 8\n* total\\_train\\_batch\\_size: 32\n* total\\_eval\\_batch\\_size: 16\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 2350",
"### Training results",
"### Framework versions\n\n\n* Transformers 4.36.2\n* Pytorch 2.1.2+cu121\n* Datasets 2.15.0\n* Tokenizers 0.15.0"
] |
[
"TAGS\n#transformers #safetensors #sparse_llama #text-generation #generated_from_trainer #custom_code #base_model-mistralai/Mistral-7B-v0.1 #license-apache-2.0 #autotrain_compatible #region-us \n",
"### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 1e-05\n* train\\_batch\\_size: 1\n* eval\\_batch\\_size: 4\n* seed: 0\n* distributed\\_type: multi-GPU\n* num\\_devices: 4\n* gradient\\_accumulation\\_steps: 8\n* total\\_train\\_batch\\_size: 32\n* total\\_eval\\_batch\\_size: 16\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 2350",
"### Training results",
"### Framework versions\n\n\n* Transformers 4.36.2\n* Pytorch 2.1.2+cu121\n* Datasets 2.15.0\n* Tokenizers 0.15.0"
] |
text-classification
|
transformers
|
From this model you can predict the sentiment of user review text. Example of user reviews (mobile applicatin, Google Maps, or online store).
Predections:
LABEL_0 : Negative
LABEL_1 : Neutral
LABEL_2 : Positive
|
{"language": ["en"], "tags": ["sentiemtns", "user_reviewes", "negative", "positive", "neutral"], "metrics": ["accuracy"], "pipeline_tag": "text-classification", "base_model": "cardiffnlp/twitter-roberta-base-sentiment-latest"}
|
merqsous/roberta-sentiment-user-review
| null |
[
"transformers",
"safetensors",
"roberta",
"text-classification",
"sentiemtns",
"user_reviewes",
"negative",
"positive",
"neutral",
"en",
"base_model:cardiffnlp/twitter-roberta-base-sentiment-latest",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | null |
2024-04-13T07:57:45+00:00
|
[] |
[
"en"
] |
TAGS
#transformers #safetensors #roberta #text-classification #sentiemtns #user_reviewes #negative #positive #neutral #en #base_model-cardiffnlp/twitter-roberta-base-sentiment-latest #autotrain_compatible #endpoints_compatible #region-us
|
From this model you can predict the sentiment of user review text. Example of user reviews (mobile applicatin, Google Maps, or online store).
Predections:
LABEL_0 : Negative
LABEL_1 : Neutral
LABEL_2 : Positive
|
[] |
[
"TAGS\n#transformers #safetensors #roberta #text-classification #sentiemtns #user_reviewes #negative #positive #neutral #en #base_model-cardiffnlp/twitter-roberta-base-sentiment-latest #autotrain_compatible #endpoints_compatible #region-us \n"
] |
null |
transformers
|
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
|
{"library_name": "transformers", "tags": []}
|
Anaphase21/bloom_for_eng1
| null |
[
"transformers",
"safetensors",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null |
2024-04-13T07:58:15+00:00
|
[
"1910.09700"
] |
[] |
TAGS
#transformers #safetensors #arxiv-1910.09700 #endpoints_compatible #region-us
|
# Model Card for Model ID
## Model Details
### Model Description
This is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.
- Developed by:
- Funded by [optional]:
- Shared by [optional]:
- Model type:
- Language(s) (NLP):
- License:
- Finetuned from model [optional]:
### Model Sources [optional]
- Repository:
- Paper [optional]:
- Demo [optional]:
## Uses
### Direct Use
### Downstream Use [optional]
### Out-of-Scope Use
## Bias, Risks, and Limitations
### Recommendations
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
## Training Details
### Training Data
### Training Procedure
#### Preprocessing [optional]
#### Training Hyperparameters
- Training regime:
#### Speeds, Sizes, Times [optional]
## Evaluation
### Testing Data, Factors & Metrics
#### Testing Data
#### Factors
#### Metrics
### Results
#### Summary
## Model Examination [optional]
## Environmental Impact
Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).
- Hardware Type:
- Hours used:
- Cloud Provider:
- Compute Region:
- Carbon Emitted:
## Technical Specifications [optional]
### Model Architecture and Objective
### Compute Infrastructure
#### Hardware
#### Software
[optional]
BibTeX:
APA:
## Glossary [optional]
## More Information [optional]
## Model Card Authors [optional]
## Model Card Contact
|
[
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.",
"## How to Get Started with the Model\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] |
[
"TAGS\n#transformers #safetensors #arxiv-1910.09700 #endpoints_compatible #region-us \n",
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.",
"## How to Get Started with the Model\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] |
text-generation
|
transformers
|
# nishide-dev/suzume-poc-mlx-4bit
This model was converted to MLX format from [`alfredplpl/suzume-poc`]() using mlx-lm version **0.7.0**.
Refer to the [original model card](https://huggingface.co/alfredplpl/suzume-poc) for more details on the model.
## Use with mlx
```bash
pip install mlx-lm
```
```python
from mlx_lm import load, generate
model, tokenizer = load("nishide-dev/suzume-poc-mlx-4bit")
response = generate(model, tokenizer, prompt="hello", verbose=True)
```
|
{"language": ["ja", "en"], "license": "other", "library_name": "transformers", "tags": ["mlx"], "license_name": "gemma-terms-of-use", "license_link": "https://www.kaggle.com/models/google/gemma/license/consent", "inference": false}
|
nishide-dev/suzume-poc-mlx-4bit
| null |
[
"transformers",
"safetensors",
"gemma",
"text-generation",
"mlx",
"ja",
"en",
"license:other",
"autotrain_compatible",
"text-generation-inference",
"region:us"
] | null |
2024-04-13T08:01:25+00:00
|
[] |
[
"ja",
"en"
] |
TAGS
#transformers #safetensors #gemma #text-generation #mlx #ja #en #license-other #autotrain_compatible #text-generation-inference #region-us
|
# nishide-dev/suzume-poc-mlx-4bit
This model was converted to MLX format from ['alfredplpl/suzume-poc']() using mlx-lm version 0.7.0.
Refer to the original model card for more details on the model.
## Use with mlx
|
[
"# nishide-dev/suzume-poc-mlx-4bit\nThis model was converted to MLX format from ['alfredplpl/suzume-poc']() using mlx-lm version 0.7.0.\nRefer to the original model card for more details on the model.",
"## Use with mlx"
] |
[
"TAGS\n#transformers #safetensors #gemma #text-generation #mlx #ja #en #license-other #autotrain_compatible #text-generation-inference #region-us \n",
"# nishide-dev/suzume-poc-mlx-4bit\nThis model was converted to MLX format from ['alfredplpl/suzume-poc']() using mlx-lm version 0.7.0.\nRefer to the original model card for more details on the model.",
"## Use with mlx"
] |
null | null |
# DavidAU/franken-SOLAR-18B-v1.0-Q6_K-GGUF
This model was converted to GGUF format from [`vicgalle/franken-SOLAR-18B-v1.0`](https://huggingface.co/vicgalle/franken-SOLAR-18B-v1.0) 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/vicgalle/franken-SOLAR-18B-v1.0) 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/franken-SOLAR-18B-v1.0-Q6_K-GGUF --model franken-solar-18b-v1.0.Q6_K.gguf -p "The meaning to life and the universe is"
```
Server:
```bash
llama-server --hf-repo DavidAU/franken-SOLAR-18B-v1.0-Q6_K-GGUF --model franken-solar-18b-v1.0.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 franken-solar-18b-v1.0.Q6_K.gguf -n 128
```
|
{"license": "apache-2.0", "tags": ["mergekit", "merge", "solar", "llama-cpp", "gguf-my-repo"], "base_model": ["upstage/SOLAR-10.7B-Instruct-v1.0", "NousResearch/Nous-Hermes-2-SOLAR-10.7B"], "model-index": [{"name": "franken-SOLAR-18B-v1.0", "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": 65.53, "name": "normalized accuracy"}], "source": {"url": "https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vicgalle/franken-SOLAR-18B-v1.0", "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": 86.45, "name": "normalized accuracy"}], "source": {"url": "https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vicgalle/franken-SOLAR-18B-v1.0", "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": 63.72, "name": "accuracy"}], "source": {"url": "https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vicgalle/franken-SOLAR-18B-v1.0", "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": 62.14}], "source": {"url": "https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vicgalle/franken-SOLAR-18B-v1.0", "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": 78.53, "name": "accuracy"}], "source": {"url": "https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vicgalle/franken-SOLAR-18B-v1.0", "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": 45.79, "name": "accuracy"}], "source": {"url": "https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vicgalle/franken-SOLAR-18B-v1.0", "name": "Open LLM Leaderboard"}}]}]}
|
DavidAU/franken-SOLAR-18B-v1.0-Q6_K-GGUF
| null |
[
"gguf",
"mergekit",
"merge",
"solar",
"llama-cpp",
"gguf-my-repo",
"base_model:upstage/SOLAR-10.7B-Instruct-v1.0",
"base_model:NousResearch/Nous-Hermes-2-SOLAR-10.7B",
"license:apache-2.0",
"model-index",
"region:us"
] | null |
2024-04-13T08:02:27+00:00
|
[] |
[] |
TAGS
#gguf #mergekit #merge #solar #llama-cpp #gguf-my-repo #base_model-upstage/SOLAR-10.7B-Instruct-v1.0 #base_model-NousResearch/Nous-Hermes-2-SOLAR-10.7B #license-apache-2.0 #model-index #region-us
|
# DavidAU/franken-SOLAR-18B-v1.0-Q6_K-GGUF
This model was converted to GGUF format from 'vicgalle/franken-SOLAR-18B-v1.0' 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/franken-SOLAR-18B-v1.0-Q6_K-GGUF\nThis model was converted to GGUF format from 'vicgalle/franken-SOLAR-18B-v1.0' 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 #mergekit #merge #solar #llama-cpp #gguf-my-repo #base_model-upstage/SOLAR-10.7B-Instruct-v1.0 #base_model-NousResearch/Nous-Hermes-2-SOLAR-10.7B #license-apache-2.0 #model-index #region-us \n",
"# DavidAU/franken-SOLAR-18B-v1.0-Q6_K-GGUF\nThis model was converted to GGUF format from 'vicgalle/franken-SOLAR-18B-v1.0' 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
|
# 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": []}
|
GladiusTn/mistral7b_ocr_to_xml_dataL
| null |
[
"transformers",
"safetensors",
"mistral",
"text-generation",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"4-bit",
"region:us"
] | null |
2024-04-13T08:03:59+00:00
|
[
"1910.09700"
] |
[] |
TAGS
#transformers #safetensors #mistral #text-generation #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #4-bit #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 #4-bit #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. -->
# amazon_helpfulness_classification_on_25M_full_pretrained
This model is a fine-tuned version of [ltuzova/amazon_domain_pretrained_model](https://huggingface.co/ltuzova/amazon_domain_pretrained_model) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3257
- Accuracy: 0.8723
- F1 Macro: 0.6231
## 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=(0.9,0.98) and epsilon=1e-06
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.06
- num_epochs: 3
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Macro |
|:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:|
| 0.3084 | 1.0 | 7204 | 0.3296 | 0.8702 | 0.6250 |
| 0.2698 | 2.0 | 14408 | 0.3508 | 0.876 | 0.6586 |
| 0.2399 | 3.0 | 21612 | 0.3712 | 0.8758 | 0.6785 |
### Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
|
{"license": "mit", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "ltuzova/amazon_domain_pretrained_model", "model-index": [{"name": "amazon_helpfulness_classification_on_25M_full_pretrained", "results": []}]}
|
ltuzova/amazon_helpfulness_classification_on_25M_full_pretrained
| null |
[
"transformers",
"tensorboard",
"safetensors",
"roberta",
"text-classification",
"generated_from_trainer",
"base_model:ltuzova/amazon_domain_pretrained_model",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | null |
2024-04-13T08:10:29+00:00
|
[] |
[] |
TAGS
#transformers #tensorboard #safetensors #roberta #text-classification #generated_from_trainer #base_model-ltuzova/amazon_domain_pretrained_model #license-mit #autotrain_compatible #endpoints_compatible #region-us
|
amazon\_helpfulness\_classification\_on\_25M\_full\_pretrained
==============================================================
This model is a fine-tuned version of ltuzova/amazon\_domain\_pretrained\_model on an unknown dataset.
It achieves the following results on the evaluation set:
* Loss: 0.3257
* Accuracy: 0.8723
* F1 Macro: 0.6231
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=(0.9,0.98) and epsilon=1e-06
* lr\_scheduler\_type: linear
* lr\_scheduler\_warmup\_ratio: 0.06
* num\_epochs: 3
### Training results
### Framework versions
* Transformers 4.38.2
* Pytorch 2.2.1+cu121
* Datasets 2.18.0
* Tokenizers 0.15.2
|
[
"### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 2e-05\n* train\\_batch\\_size: 16\n* eval\\_batch\\_size: 16\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.98) and epsilon=1e-06\n* lr\\_scheduler\\_type: linear\n* lr\\_scheduler\\_warmup\\_ratio: 0.06\n* num\\_epochs: 3",
"### Training results",
"### Framework versions\n\n\n* Transformers 4.38.2\n* Pytorch 2.2.1+cu121\n* Datasets 2.18.0\n* Tokenizers 0.15.2"
] |
[
"TAGS\n#transformers #tensorboard #safetensors #roberta #text-classification #generated_from_trainer #base_model-ltuzova/amazon_domain_pretrained_model #license-mit #autotrain_compatible #endpoints_compatible #region-us \n",
"### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 2e-05\n* train\\_batch\\_size: 16\n* eval\\_batch\\_size: 16\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.98) and epsilon=1e-06\n* lr\\_scheduler\\_type: linear\n* lr\\_scheduler\\_warmup\\_ratio: 0.06\n* num\\_epochs: 3",
"### Training results",
"### Framework versions\n\n\n* Transformers 4.38.2\n* Pytorch 2.2.1+cu121\n* Datasets 2.18.0\n* Tokenizers 0.15.2"
] |
null |
transformers
|
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
|
{"library_name": "transformers", "tags": []}
|
Nabin1995/invoice_asian_99_new
| null |
[
"transformers",
"safetensors",
"vision-encoder-decoder",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null |
2024-04-13T08:12:04+00:00
|
[
"1910.09700"
] |
[] |
TAGS
#transformers #safetensors #vision-encoder-decoder #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 #vision-encoder-decoder #arxiv-1910.09700 #endpoints_compatible #region-us \n",
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.",
"## How to Get Started with the Model\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] |
null |
transformers
|
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
|
{"library_name": "transformers", "tags": []}
|
shtapm/whisper-large_0413_LoRA_all
| null |
[
"transformers",
"safetensors",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null |
2024-04-13T08:12:22+00:00
|
[
"1910.09700"
] |
[] |
TAGS
#transformers #safetensors #arxiv-1910.09700 #endpoints_compatible #region-us
|
# Model Card for Model ID
## Model Details
### Model Description
This is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.
- Developed by:
- Funded by [optional]:
- Shared by [optional]:
- Model type:
- Language(s) (NLP):
- License:
- Finetuned from model [optional]:
### Model Sources [optional]
- Repository:
- Paper [optional]:
- Demo [optional]:
## Uses
### Direct Use
### Downstream Use [optional]
### Out-of-Scope Use
## Bias, Risks, and Limitations
### Recommendations
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
## Training Details
### Training Data
### Training Procedure
#### Preprocessing [optional]
#### Training Hyperparameters
- Training regime:
#### Speeds, Sizes, Times [optional]
## Evaluation
### Testing Data, Factors & Metrics
#### Testing Data
#### Factors
#### Metrics
### Results
#### Summary
## Model Examination [optional]
## Environmental Impact
Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).
- Hardware Type:
- Hours used:
- Cloud Provider:
- Compute Region:
- Carbon Emitted:
## Technical Specifications [optional]
### Model Architecture and Objective
### Compute Infrastructure
#### Hardware
#### Software
[optional]
BibTeX:
APA:
## Glossary [optional]
## More Information [optional]
## Model Card Authors [optional]
## Model Card Contact
|
[
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.",
"## How to Get Started with the Model\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] |
[
"TAGS\n#transformers #safetensors #arxiv-1910.09700 #endpoints_compatible #region-us \n",
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.",
"## How to Get Started with the Model\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] |
null | null |
# DavidAU/solarized-13B-dpo-Q6_K-GGUF
This model was converted to GGUF format from [`vicgalle/solarized-13B-dpo`](https://huggingface.co/vicgalle/solarized-13B-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/vicgalle/solarized-13B-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/solarized-13B-dpo-Q6_K-GGUF --model solarized-13b-dpo.Q6_K.gguf -p "The meaning to life and the universe is"
```
Server:
```bash
llama-server --hf-repo DavidAU/solarized-13B-dpo-Q6_K-GGUF --model solarized-13b-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 solarized-13b-dpo.Q6_K.gguf -n 128
```
|
{"license": "apache-2.0", "tags": ["dpo", "13B", "merge", "llama-cpp", "gguf-my-repo"], "datasets": ["argilla/distilabel-intel-orca-dpo-pairs"], "base_model": ["vicgalle/SOLAR-13B-Instruct-v1.0"], "model-index": [{"name": "solarized-13B-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": 62.71, "name": "normalized accuracy"}], "source": {"url": "https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vicgalle/solarized-13B-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": 81.82, "name": "normalized accuracy"}], "source": {"url": "https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vicgalle/solarized-13B-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": 59.12, "name": "accuracy"}], "source": {"url": "https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vicgalle/solarized-13B-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": 66.25}], "source": {"url": "https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vicgalle/solarized-13B-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": 76.01, "name": "accuracy"}], "source": {"url": "https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vicgalle/solarized-13B-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": 26.38, "name": "accuracy"}], "source": {"url": "https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vicgalle/solarized-13B-dpo", "name": "Open LLM Leaderboard"}}]}]}
|
DavidAU/solarized-13B-dpo-Q6_K-GGUF
| null |
[
"gguf",
"dpo",
"13B",
"merge",
"llama-cpp",
"gguf-my-repo",
"dataset:argilla/distilabel-intel-orca-dpo-pairs",
"base_model:vicgalle/SOLAR-13B-Instruct-v1.0",
"license:apache-2.0",
"model-index",
"region:us"
] | null |
2024-04-13T08:12:23+00:00
|
[] |
[] |
TAGS
#gguf #dpo #13B #merge #llama-cpp #gguf-my-repo #dataset-argilla/distilabel-intel-orca-dpo-pairs #base_model-vicgalle/SOLAR-13B-Instruct-v1.0 #license-apache-2.0 #model-index #region-us
|
# DavidAU/solarized-13B-dpo-Q6_K-GGUF
This model was converted to GGUF format from 'vicgalle/solarized-13B-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/solarized-13B-dpo-Q6_K-GGUF\nThis model was converted to GGUF format from 'vicgalle/solarized-13B-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 #dpo #13B #merge #llama-cpp #gguf-my-repo #dataset-argilla/distilabel-intel-orca-dpo-pairs #base_model-vicgalle/SOLAR-13B-Instruct-v1.0 #license-apache-2.0 #model-index #region-us \n",
"# DavidAU/solarized-13B-dpo-Q6_K-GGUF\nThis model was converted to GGUF format from 'vicgalle/solarized-13B-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."
] |
reinforcement-learning
| null |
# **Q-Learning** Agent playing1 **FrozenLake-v1**
This is a trained model of a **Q-Learning** agent playing **FrozenLake-v1** .
## Usage
```python
model = load_from_hub(repo_id="arvin-zaheri/q-FrozenLake-v1-4x4-noSlippery", filename="q-learning.pkl")
# Don't forget to check if you need to add additional attributes (is_slippery=False etc)
env = gym.make(model["env_id"])
```
|
{"tags": ["FrozenLake-v1-4x4-no_slippery", "q-learning", "reinforcement-learning", "custom-implementation"], "model-index": [{"name": "q-FrozenLake-v1-4x4-noSlippery", "results": [{"task": {"type": "reinforcement-learning", "name": "reinforcement-learning"}, "dataset": {"name": "FrozenLake-v1-4x4-no_slippery", "type": "FrozenLake-v1-4x4-no_slippery"}, "metrics": [{"type": "mean_reward", "value": "1.00 +/- 0.00", "name": "mean_reward", "verified": false}]}]}]}
|
arvin-zaheri/q-FrozenLake-v1-4x4-noSlippery
| null |
[
"FrozenLake-v1-4x4-no_slippery",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
] | null |
2024-04-13T08:15:37+00:00
|
[] |
[] |
TAGS
#FrozenLake-v1-4x4-no_slippery #q-learning #reinforcement-learning #custom-implementation #model-index #region-us
|
# Q-Learning Agent playing1 FrozenLake-v1
This is a trained model of a Q-Learning agent playing FrozenLake-v1 .
## Usage
|
[
"# Q-Learning Agent playing1 FrozenLake-v1\n This is a trained model of a Q-Learning agent playing FrozenLake-v1 .\n\n ## Usage"
] |
[
"TAGS\n#FrozenLake-v1-4x4-no_slippery #q-learning #reinforcement-learning #custom-implementation #model-index #region-us \n",
"# Q-Learning Agent playing1 FrozenLake-v1\n This is a trained model of a Q-Learning agent playing FrozenLake-v1 .\n\n ## Usage"
] |
null |
peft
|
# 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. -->
- **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]
### Framework versions
- PEFT 0.10.0
|
{"library_name": "peft", "base_model": "google-t5/t5-small"}
|
dsolomon/t5-small-pubmed-LoRA-r4-i1024-o128
| null |
[
"peft",
"safetensors",
"arxiv:1910.09700",
"base_model:google-t5/t5-small",
"region:us"
] | null |
2024-04-13T08:15:50+00:00
|
[
"1910.09700"
] |
[] |
TAGS
#peft #safetensors #arxiv-1910.09700 #base_model-google-t5/t5-small #region-us
|
# Model Card for Model ID
## Model Details
### Model Description
- Developed by:
- Funded by [optional]:
- Shared by [optional]:
- Model type:
- Language(s) (NLP):
- License:
- Finetuned from model [optional]:
### Model Sources [optional]
- Repository:
- Paper [optional]:
- Demo [optional]:
## Uses
### Direct Use
### Downstream Use [optional]
### Out-of-Scope Use
## Bias, Risks, and Limitations
### Recommendations
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
## Training Details
### Training Data
### Training Procedure
#### Preprocessing [optional]
#### Training Hyperparameters
- Training regime:
#### Speeds, Sizes, Times [optional]
## Evaluation
### Testing Data, Factors & Metrics
#### Testing Data
#### Factors
#### Metrics
### Results
#### Summary
## Model Examination [optional]
## Environmental Impact
Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).
- Hardware Type:
- Hours used:
- Cloud Provider:
- Compute Region:
- Carbon Emitted:
## Technical Specifications [optional]
### Model Architecture and Objective
### Compute Infrastructure
#### Hardware
#### Software
[optional]
BibTeX:
APA:
## Glossary [optional]
## More Information [optional]
## Model Card Authors [optional]
## Model Card Contact
### Framework versions
- PEFT 0.10.0
|
[
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\n\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.",
"## How to Get Started with the Model\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact",
"### Framework versions\n\n- PEFT 0.10.0"
] |
[
"TAGS\n#peft #safetensors #arxiv-1910.09700 #base_model-google-t5/t5-small #region-us \n",
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\n\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.",
"## How to Get Started with the Model\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact",
"### Framework versions\n\n- PEFT 0.10.0"
] |
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. -->
# xlm-roberta-base-finetuned-panx-de-fr
This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1639
- F1: 0.8591
## 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: 24
- eval_batch_size: 24
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
### Training results
| Training Loss | Epoch | Step | Validation Loss | F1 |
|:-------------:|:-----:|:----:|:---------------:|:------:|
| 0.2836 | 1.0 | 715 | 0.1859 | 0.8212 |
| 0.1484 | 2.0 | 1430 | 0.1632 | 0.8487 |
| 0.0953 | 3.0 | 2145 | 0.1639 | 0.8591 |
### Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
|
{"license": "mit", "tags": ["generated_from_trainer"], "metrics": ["f1"], "base_model": "xlm-roberta-base", "model-index": [{"name": "xlm-roberta-base-finetuned-panx-de-fr", "results": []}]}
|
SORABE/xlm-roberta-base-finetuned-panx-de-fr
| null |
[
"transformers",
"safetensors",
"xlm-roberta",
"token-classification",
"generated_from_trainer",
"base_model:xlm-roberta-base",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | null |
2024-04-13T08:16:19+00:00
|
[] |
[] |
TAGS
#transformers #safetensors #xlm-roberta #token-classification #generated_from_trainer #base_model-xlm-roberta-base #license-mit #autotrain_compatible #endpoints_compatible #region-us
|
xlm-roberta-base-finetuned-panx-de-fr
=====================================
This model is a fine-tuned version of xlm-roberta-base on the None dataset.
It achieves the following results on the evaluation set:
* Loss: 0.1639
* F1: 0.8591
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: 24
* eval\_batch\_size: 24
* seed: 42
* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
* lr\_scheduler\_type: linear
* num\_epochs: 3
### Training results
### Framework versions
* Transformers 4.38.2
* Pytorch 2.2.1+cu121
* Datasets 2.18.0
* 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: 24\n* eval\\_batch\\_size: 24\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 3",
"### Training results",
"### Framework versions\n\n\n* Transformers 4.38.2\n* Pytorch 2.2.1+cu121\n* Datasets 2.18.0\n* Tokenizers 0.15.2"
] |
[
"TAGS\n#transformers #safetensors #xlm-roberta #token-classification #generated_from_trainer #base_model-xlm-roberta-base #license-mit #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: 24\n* eval\\_batch\\_size: 24\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 3",
"### Training results",
"### Framework versions\n\n\n* Transformers 4.38.2\n* Pytorch 2.2.1+cu121\n* Datasets 2.18.0\n* Tokenizers 0.15.2"
] |
text-to-image
|
diffusers
|
## SDXL-8-step
<img src="" alt="Generated on Image Pipeline" style="border-radius: 10px;">
**This checkpoint model is uploaded on [imagepipeline.io](https://imagepipeline.io/)**
Model details - Lightning Model 8 step
[](https://imagepipeline.io/models/SDXL-8-step?id=48a85922-f7f1-4669-9fda-a78d5425c90a/)
## How to try this model ?
You can try using it locally or send an API call to test the output quality.
Get your `API_KEY` from [imagepipeline.io](https://imagepipeline.io/). No payment required.
Coding in `php` `javascript` `node` etc ? Checkout our documentation
[](https://docs.imagepipeline.io/docs/introduction)
```python
import requests
import json
url = "https://imagepipeline.io/sdxl/text2image/v1/run"
payload = json.dumps({
"model_id": "48a85922-f7f1-4669-9fda-a78d5425c90a",
"prompt": "ultra realistic close up portrait ((beautiful pale cyberpunk female with heavy black eyeliner)), blue eyes, shaved side haircut, hyper detail, cinematic lighting, magic neon, dark red city, Canon EOS R3, nikon, f/1.4, ISO 200, 1/160s, 8K, RAW, unedited, symmetrical balance, in-frame, 8K",
"negative_prompt": "painting, extra fingers, mutated hands, poorly drawn hands, poorly drawn face, deformed, ugly, blurry, bad anatomy, bad proportions, extra limbs, cloned face, skinny, glitchy, double torso, extra arms, extra hands, mangled fingers, missing lips, ugly face, distorted face, extra legs, anime",
"width": "512",
"height": "512",
"samples": "1",
"num_inference_steps": "30",
"safety_checker": false,
"guidance_scale": 7.5,
"multi_lingual": "no",
"embeddings": "",
"lora_models": "",
"lora_weights": ""
})
headers = {
'Content-Type': 'application/json',
'API-Key': 'your_api_key'
}
response = requests.request("POST", url, headers=headers, data=payload)
print(response.text)
}
```
Get more ready to use `MODELS` like this for `SD 1.5` and `SDXL` :
[](https://imagepipeline.io/models)
### API Reference
#### Generate Image
```http
https://api.imagepipeline.io/sdxl/text2image/v1
```
| Headers | Type | Description |
|:----------------------| :------- |:-------------------------------------------------------------------------------------------------------------------|
| `API-Key` | `str` | Get your `API_KEY` from [imagepipeline.io](https://imagepipeline.io/) |
| `Content-Type` | `str` | application/json - content type of the request body |
| Parameter | Type | Description |
| :-------- | :------- | :------------------------- |
| `model_id` | `str` | Your base model, find available lists in [models page](https://imagepipeline.io/models) or upload your own|
| `prompt` | `str` | Text Prompt. Check our [Prompt Guide](https://docs.imagepipeline.io/docs/SD-1.5/docs/extras/prompt-guide) for tips |
| `num_inference_steps` | `int [1-50]` | Noise is removed with each step, resulting in a higher-quality image over time. Ideal value 30-50 (without LCM) |
| `guidance_scale` | `float [1-20]` | Higher guidance scale prioritizes text prompt relevance but sacrifices image quality. Ideal value 7.5-12.5 |
| `lora_models` | `str, array` | Pass the model_id(s) of LoRA models that can be found in models page |
| `lora_weights` | `str, array` | Strength of the LoRA effect |
---
license: creativeml-openrail-m
tags:
- imagepipeline
- imagepipeline.io
- text-to-image
- ultra-realistic
pinned: false
pipeline_tag: text-to-image
---
### Feedback
If you have any feedback, please reach out to us at [email protected]
#### 🔗 Visit Website
[](https://imagepipeline.io/)
If you are the original author of this model, please [click here](https://airtable.com/apprTaRnJbDJ8ufOx/shr4g7o9B6fWfOlUR) to add credits
|
{"license": "creativeml-openrail-m", "tags": ["imagepipeline", "imagepipeline.io", "text-to-image", "ultra-realistic"], "pinned": false, "pipeline_tag": "text-to-image"}
|
imagepipeline/SDXL-8-step
| null |
[
"diffusers",
"imagepipeline",
"imagepipeline.io",
"text-to-image",
"ultra-realistic",
"license:creativeml-openrail-m",
"endpoints_compatible",
"diffusers:StableDiffusionXLPipeline",
"region:us"
] | null |
2024-04-13T08:17:41+00:00
|
[] |
[] |
TAGS
#diffusers #imagepipeline #imagepipeline.io #text-to-image #ultra-realistic #license-creativeml-openrail-m #endpoints_compatible #diffusers-StableDiffusionXLPipeline #region-us
|
SDXL-8-step
-----------
![Generated on Image Pipeline]()
This checkpoint model is uploaded on URL
Model details - Lightning Model 8 step
![Try this model](URL
How to try this model ?
-----------------------
You can try using it locally or send an API call to test the output quality.
Get your 'API\_KEY' from URL. No payment required.
Coding in 'php' 'javascript' 'node' etc ? Checkout our documentation
![documentation](URL
Get more ready to use 'MODELS' like this for 'SD 1.5' and 'SDXL' :
![All models](URL
### API Reference
#### Generate Image
---
license: creativeml-openrail-m
tags:
* imagepipeline
* URL
* text-to-image
* ultra-realistic
pinned: false
pipeline\_tag: text-to-image
---
### Feedback
If you have any feedback, please reach out to us at hello@URL
#### Visit Website
![portfolio](URL
If you are the original author of this model, please click here to add credits
|
[
"### API Reference",
"#### Generate Image\n\n\n\n\n\n\n---\n\n\nlicense: creativeml-openrail-m\ntags:\n\n\n* imagepipeline\n* URL\n* text-to-image\n* ultra-realistic\npinned: false\npipeline\\_tag: text-to-image\n\n\n\n\n---",
"### Feedback\n\n\nIf you have any feedback, please reach out to us at hello@URL",
"#### Visit Website\n\n\n![portfolio](URL\n\n\nIf you are the original author of this model, please click here to add credits"
] |
[
"TAGS\n#diffusers #imagepipeline #imagepipeline.io #text-to-image #ultra-realistic #license-creativeml-openrail-m #endpoints_compatible #diffusers-StableDiffusionXLPipeline #region-us \n",
"### API Reference",
"#### Generate Image\n\n\n\n\n\n\n---\n\n\nlicense: creativeml-openrail-m\ntags:\n\n\n* imagepipeline\n* URL\n* text-to-image\n* ultra-realistic\npinned: false\npipeline\\_tag: text-to-image\n\n\n\n\n---",
"### Feedback\n\n\nIf you have any feedback, please reach out to us at hello@URL",
"#### Visit Website\n\n\n![portfolio](URL\n\n\nIf you are the original author of this model, please click here to add credits"
] |
image-classification
|
transformers
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# Psoriasis-Project-Aug-M2-beit-base-patch16-224-pt22k-ft22k
This model is a fine-tuned version of [microsoft/beit-base-patch16-224-pt22k-ft22k](https://huggingface.co/microsoft/beit-base-patch16-224-pt22k-ft22k) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0042
- Accuracy: 1.0
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 1.1065 | 0.99 | 36 | 0.3867 | 0.9167 |
| 0.2495 | 1.99 | 72 | 0.1087 | 0.9583 |
| 0.1026 | 2.98 | 108 | 0.0239 | 1.0 |
| 0.039 | 4.0 | 145 | 0.0605 | 0.9583 |
| 0.0188 | 4.99 | 181 | 0.1663 | 0.9375 |
| 0.0165 | 5.99 | 217 | 0.0047 | 1.0 |
| 0.0047 | 6.98 | 253 | 0.0028 | 1.0 |
| 0.005 | 8.0 | 290 | 0.0043 | 1.0 |
| 0.0022 | 8.99 | 326 | 0.0061 | 1.0 |
| 0.0015 | 9.93 | 360 | 0.0042 | 1.0 |
### Framework versions
- Transformers 4.39.3
- Pytorch 2.1.2
- Datasets 2.18.0
- Tokenizers 0.15.2
|
{"license": "apache-2.0", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "microsoft/beit-base-patch16-224-pt22k-ft22k", "model-index": [{"name": "Psoriasis-Project-Aug-M2-beit-base-patch16-224-pt22k-ft22k", "results": []}]}
|
ahmedesmail16/Psoriasis-Project-Aug-M2-beit-base-patch16-224-pt22k-ft22k
| null |
[
"transformers",
"tensorboard",
"safetensors",
"beit",
"image-classification",
"generated_from_trainer",
"base_model:microsoft/beit-base-patch16-224-pt22k-ft22k",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | null |
2024-04-13T08:20:43+00:00
|
[] |
[] |
TAGS
#transformers #tensorboard #safetensors #beit #image-classification #generated_from_trainer #base_model-microsoft/beit-base-patch16-224-pt22k-ft22k #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us
|
Psoriasis-Project-Aug-M2-beit-base-patch16-224-pt22k-ft22k
==========================================================
This model is a fine-tuned version of microsoft/beit-base-patch16-224-pt22k-ft22k on an unknown dataset.
It achieves the following results on the evaluation set:
* Loss: 0.0042
* Accuracy: 1.0
Model description
-----------------
More information needed
Intended uses & limitations
---------------------------
More information needed
Training and evaluation data
----------------------------
More information needed
Training procedure
------------------
### Training hyperparameters
The following hyperparameters were used during training:
* learning\_rate: 5e-05
* train\_batch\_size: 16
* eval\_batch\_size: 16
* seed: 42
* gradient\_accumulation\_steps: 4
* total\_train\_batch\_size: 64
* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
* lr\_scheduler\_type: linear
* lr\_scheduler\_warmup\_ratio: 0.1
* num\_epochs: 10
### Training results
### Framework versions
* Transformers 4.39.3
* 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: 5e-05\n* train\\_batch\\_size: 16\n* eval\\_batch\\_size: 16\n* seed: 42\n* gradient\\_accumulation\\_steps: 4\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\\_ratio: 0.1\n* num\\_epochs: 10",
"### Training results",
"### Framework versions\n\n\n* Transformers 4.39.3\n* Pytorch 2.1.2\n* Datasets 2.18.0\n* Tokenizers 0.15.2"
] |
[
"TAGS\n#transformers #tensorboard #safetensors #beit #image-classification #generated_from_trainer #base_model-microsoft/beit-base-patch16-224-pt22k-ft22k #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: 16\n* eval\\_batch\\_size: 16\n* seed: 42\n* gradient\\_accumulation\\_steps: 4\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\\_ratio: 0.1\n* num\\_epochs: 10",
"### Training results",
"### Framework versions\n\n\n* Transformers 4.39.3\n* Pytorch 2.1.2\n* Datasets 2.18.0\n* Tokenizers 0.15.2"
] |
automatic-speech-recognition
|
transformers
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# Whisper Medium Basque
This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on the mozilla-foundation/common_voice_16_1 eu dataset.
It achieves the following results on the evaluation set:
- Loss: 0.4303
- Wer: 9.2006
## 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: 64
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 4
- 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: 500
- training_steps: 40000
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|:-------------:|:------:|:-----:|:---------------:|:-------:|
| 0.0055 | 10.03 | 1000 | 0.2463 | 11.8425 |
| 0.003 | 20.05 | 2000 | 0.2638 | 11.3178 |
| 0.0018 | 30.08 | 3000 | 0.2837 | 10.9583 |
| 0.0009 | 40.1 | 4000 | 0.2768 | 10.4414 |
| 0.0008 | 50.13 | 5000 | 0.2880 | 10.1776 |
| 0.0012 | 60.15 | 6000 | 0.2903 | 10.0526 |
| 0.0002 | 70.18 | 7000 | 0.2909 | 9.8357 |
| 0.0013 | 80.2 | 8000 | 0.2766 | 9.9392 |
| 0.0001 | 90.23 | 9000 | 0.3110 | 9.3003 |
| 0.0 | 100.25 | 10000 | 0.3278 | 9.3315 |
| 0.0 | 110.28 | 11000 | 0.3393 | 9.3081 |
| 0.0 | 120.3 | 12000 | 0.3508 | 9.2993 |
| 0.0 | 130.33 | 13000 | 0.3617 | 9.3218 |
| 0.0 | 140.35 | 14000 | 0.3732 | 9.3354 |
| 0.0 | 150.38 | 15000 | 0.3849 | 9.3735 |
| 0.0 | 160.4 | 16000 | 0.3073 | 9.3335 |
| 0.0 | 170.43 | 17000 | 0.3320 | 9.3569 |
| 0.0 | 180.45 | 18000 | 0.3453 | 9.3022 |
| 0.0 | 190.48 | 19000 | 0.3561 | 9.3071 |
| 0.0 | 200.5 | 20000 | 0.3660 | 9.2983 |
| 0.0 | 210.53 | 21000 | 0.3755 | 9.2876 |
| 0.0 | 220.55 | 22000 | 0.3847 | 9.4976 |
| 0.0 | 230.58 | 23000 | 0.3940 | 9.5054 |
| 0.0 | 240.6 | 24000 | 0.4021 | 9.4703 |
| 0.0 | 250.63 | 25000 | 0.4126 | 9.4537 |
| 0.0 | 260.65 | 26000 | 0.3174 | 9.2758 |
| 0.0 | 270.68 | 27000 | 0.3444 | 9.2622 |
| 0.0 | 280.7 | 28000 | 0.3588 | 9.2084 |
| 0.0 | 290.73 | 29000 | 0.3698 | 9.3472 |
| 0.0 | 300.75 | 30000 | 0.3786 | 9.3423 |
| 0.0 | 310.78 | 31000 | 0.3868 | 9.3169 |
| 0.0 | 320.8 | 32000 | 0.3948 | 9.3286 |
| 0.0 | 330.83 | 33000 | 0.4018 | 9.3335 |
| 0.0 | 340.85 | 34000 | 0.4081 | 9.3286 |
| 0.0 | 350.88 | 35000 | 0.4138 | 9.3364 |
| 0.0 | 360.9 | 36000 | 0.4191 | 9.3432 |
| 0.0 | 370.93 | 37000 | 0.4234 | 9.3315 |
| 0.0 | 380.95 | 38000 | 0.4270 | 9.3403 |
| 0.0 | 390.98 | 39000 | 0.4294 | 9.2153 |
| 0.0 | 401.0 | 40000 | 0.4303 | 9.2006 |
### Framework versions
- Transformers 4.37.2
- Pytorch 2.2.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.1
|
{"language": ["eu"], "license": "apache-2.0", "tags": ["whisper-event", "generated_from_trainer"], "datasets": ["mozilla-foundation/common_voice_16_1"], "metrics": ["wer"], "base_model": "openai/whisper-medium", "model-index": [{"name": "Whisper Medium Basque", "results": [{"task": {"type": "automatic-speech-recognition", "name": "Automatic Speech Recognition"}, "dataset": {"name": "mozilla-foundation/common_voice_16_1 eu", "type": "mozilla-foundation/common_voice_16_1", "config": "eu", "split": "test", "args": "eu"}, "metrics": [{"type": "wer", "value": 9.200601844614663, "name": "Wer"}]}]}]}
|
zuazo/whisper-medium-eu-cv16_1
| null |
[
"transformers",
"tensorboard",
"safetensors",
"whisper",
"automatic-speech-recognition",
"whisper-event",
"generated_from_trainer",
"eu",
"dataset:mozilla-foundation/common_voice_16_1",
"base_model:openai/whisper-medium",
"license:apache-2.0",
"model-index",
"endpoints_compatible",
"region:us"
] | null |
2024-04-13T08:23:29+00:00
|
[] |
[
"eu"
] |
TAGS
#transformers #tensorboard #safetensors #whisper #automatic-speech-recognition #whisper-event #generated_from_trainer #eu #dataset-mozilla-foundation/common_voice_16_1 #base_model-openai/whisper-medium #license-apache-2.0 #model-index #endpoints_compatible #region-us
|
Whisper Medium Basque
=====================
This model is a fine-tuned version of openai/whisper-medium on the mozilla-foundation/common\_voice\_16\_1 eu dataset.
It achieves the following results on the evaluation set:
* Loss: 0.4303
* Wer: 9.2006
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: 64
* eval\_batch\_size: 32
* seed: 42
* gradient\_accumulation\_steps: 4
* 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: 500
* training\_steps: 40000
* mixed\_precision\_training: Native AMP
### Training results
### Framework versions
* Transformers 4.37.2
* Pytorch 2.2.0+cu121
* Datasets 2.16.1
* Tokenizers 0.15.1
|
[
"### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 1e-05\n* train\\_batch\\_size: 64\n* eval\\_batch\\_size: 32\n* seed: 42\n* gradient\\_accumulation\\_steps: 4\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: 500\n* training\\_steps: 40000\n* mixed\\_precision\\_training: Native AMP",
"### Training results",
"### Framework versions\n\n\n* Transformers 4.37.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.16.1\n* Tokenizers 0.15.1"
] |
[
"TAGS\n#transformers #tensorboard #safetensors #whisper #automatic-speech-recognition #whisper-event #generated_from_trainer #eu #dataset-mozilla-foundation/common_voice_16_1 #base_model-openai/whisper-medium #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: 1e-05\n* train\\_batch\\_size: 64\n* eval\\_batch\\_size: 32\n* seed: 42\n* gradient\\_accumulation\\_steps: 4\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: 500\n* training\\_steps: 40000\n* mixed\\_precision\\_training: Native AMP",
"### Training results",
"### Framework versions\n\n\n* Transformers 4.37.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.16.1\n* Tokenizers 0.15.1"
] |
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 Large Basque
This model is a fine-tuned version of [openai/whisper-large](https://huggingface.co/openai/whisper-large) on the mozilla-foundation/common_voice_16_1 eu dataset.
It achieves the following results on the evaluation set:
- Loss: 0.4111
- Wer: 8.1444
## 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: 32
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 8
- 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: 500
- training_steps: 40000
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|:-------------:|:------:|:-----:|:---------------:|:-------:|
| 0.004 | 10.04 | 1000 | 0.2314 | 10.6603 |
| 0.0028 | 20.08 | 2000 | 0.2480 | 10.2783 |
| 0.0027 | 30.11 | 3000 | 0.2492 | 10.0379 |
| 0.0005 | 40.15 | 4000 | 0.2753 | 9.3784 |
| 0.0016 | 50.19 | 5000 | 0.2489 | 9.3003 |
| 0.0006 | 60.23 | 6000 | 0.2599 | 9.0023 |
| 0.0011 | 70.26 | 7000 | 0.2606 | 8.9378 |
| 0.0005 | 80.3 | 8000 | 0.2723 | 8.9270 |
| 0.0001 | 90.34 | 9000 | 0.2764 | 8.5304 |
| 0.0011 | 100.38 | 10000 | 0.2668 | 8.8977 |
| 0.0001 | 110.41 | 11000 | 0.2856 | 8.3701 |
| 0.0 | 120.45 | 12000 | 0.3045 | 8.2890 |
| 0.0 | 130.49 | 13000 | 0.3149 | 8.2441 |
| 0.0 | 140.53 | 14000 | 0.3241 | 8.2285 |
| 0.0 | 150.56 | 15000 | 0.3336 | 8.2060 |
| 0.0 | 160.6 | 16000 | 0.3433 | 8.1601 |
| 0.0 | 170.64 | 17000 | 0.3537 | 8.1806 |
| 0.0 | 180.68 | 18000 | 0.3634 | 8.1874 |
| 0.0 | 190.72 | 19000 | 0.3738 | 8.1786 |
| 0.0 | 200.75 | 20000 | 0.3848 | 8.2441 |
| 0.0 | 210.79 | 21000 | 0.3952 | 8.2324 |
| 0.0 | 220.83 | 22000 | 0.4030 | 8.2480 |
| 0.0001 | 230.87 | 23000 | 0.2919 | 8.4268 |
| 0.0 | 240.9 | 24000 | 0.3137 | 8.1865 |
| 0.0 | 250.94 | 25000 | 0.3271 | 8.1884 |
| 0.0 | 260.98 | 26000 | 0.3378 | 8.1825 |
| 0.0 | 271.02 | 27000 | 0.3472 | 8.1865 |
| 0.0 | 281.05 | 28000 | 0.3556 | 8.2031 |
| 0.0 | 291.09 | 29000 | 0.3637 | 8.2099 |
| 0.0 | 301.13 | 30000 | 0.3710 | 8.1933 |
| 0.0 | 311.17 | 31000 | 0.3781 | 8.1874 |
| 0.0 | 321.2 | 32000 | 0.3845 | 8.1679 |
| 0.0 | 331.24 | 33000 | 0.3905 | 8.1601 |
| 0.0 | 341.28 | 34000 | 0.3971 | 8.1640 |
| 0.0 | 351.32 | 35000 | 0.4022 | 8.1611 |
| 0.0 | 361.36 | 36000 | 0.4046 | 8.1562 |
| 0.0 | 371.39 | 37000 | 0.4073 | 8.1523 |
| 0.0 | 381.43 | 38000 | 0.4093 | 8.1493 |
| 0.0 | 391.47 | 39000 | 0.4107 | 8.1513 |
| 0.0 | 401.51 | 40000 | 0.4111 | 8.1444 |
### Framework versions
- Transformers 4.37.2
- Pytorch 2.2.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.1
|
{"language": ["eu"], "license": "apache-2.0", "tags": ["whisper-event", "generated_from_trainer"], "datasets": ["mozilla-foundation/common_voice_16_1"], "metrics": ["wer"], "base_model": "openai/whisper-large", "model-index": [{"name": "Whisper Large Basque", "results": [{"task": {"type": "automatic-speech-recognition", "name": "Automatic Speech Recognition"}, "dataset": {"name": "mozilla-foundation/common_voice_16_1 eu", "type": "mozilla-foundation/common_voice_16_1", "config": "eu", "split": "test", "args": "eu"}, "metrics": [{"type": "wer", "value": 8.144442707519149, "name": "Wer"}]}]}]}
|
zuazo/whisper-large-eu-cv16_1
| null |
[
"transformers",
"tensorboard",
"safetensors",
"whisper",
"automatic-speech-recognition",
"whisper-event",
"generated_from_trainer",
"eu",
"dataset:mozilla-foundation/common_voice_16_1",
"base_model:openai/whisper-large",
"license:apache-2.0",
"model-index",
"endpoints_compatible",
"region:us"
] | null |
2024-04-13T08:23:37+00:00
|
[] |
[
"eu"
] |
TAGS
#transformers #tensorboard #safetensors #whisper #automatic-speech-recognition #whisper-event #generated_from_trainer #eu #dataset-mozilla-foundation/common_voice_16_1 #base_model-openai/whisper-large #license-apache-2.0 #model-index #endpoints_compatible #region-us
|
Whisper Large Basque
====================
This model is a fine-tuned version of openai/whisper-large on the mozilla-foundation/common\_voice\_16\_1 eu dataset.
It achieves the following results on the evaluation set:
* Loss: 0.4111
* Wer: 8.1444
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: 32
* eval\_batch\_size: 16
* seed: 42
* gradient\_accumulation\_steps: 8
* 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: 500
* training\_steps: 40000
* mixed\_precision\_training: Native AMP
### Training results
### Framework versions
* Transformers 4.37.2
* Pytorch 2.2.0+cu121
* Datasets 2.16.1
* Tokenizers 0.15.1
|
[
"### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 1e-05\n* train\\_batch\\_size: 32\n* eval\\_batch\\_size: 16\n* seed: 42\n* gradient\\_accumulation\\_steps: 8\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: 500\n* training\\_steps: 40000\n* mixed\\_precision\\_training: Native AMP",
"### Training results",
"### Framework versions\n\n\n* Transformers 4.37.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.16.1\n* Tokenizers 0.15.1"
] |
[
"TAGS\n#transformers #tensorboard #safetensors #whisper #automatic-speech-recognition #whisper-event #generated_from_trainer #eu #dataset-mozilla-foundation/common_voice_16_1 #base_model-openai/whisper-large #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: 1e-05\n* train\\_batch\\_size: 32\n* eval\\_batch\\_size: 16\n* seed: 42\n* gradient\\_accumulation\\_steps: 8\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: 500\n* training\\_steps: 40000\n* mixed\\_precision\\_training: Native AMP",
"### Training results",
"### Framework versions\n\n\n* Transformers 4.37.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.16.1\n* Tokenizers 0.15.1"
] |
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 Large-V2 Basque
This model is a fine-tuned version of [openai/whisper-large-v2](https://huggingface.co/openai/whisper-large-v2) on the mozilla-foundation/common_voice_16_1 eu dataset.
It achieves the following results on the evaluation set:
- Loss: 0.4206
- Wer: 7.7204
## 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: 32
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 8
- 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: 500
- training_steps: 40000
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|:-------------:|:------:|:-----:|:---------------:|:-------:|
| 0.0112 | 10.04 | 1000 | 0.2182 | 10.1571 |
| 0.0052 | 20.08 | 2000 | 0.2372 | 9.6276 |
| 0.0017 | 30.11 | 3000 | 0.2417 | 9.0150 |
| 0.0022 | 40.15 | 4000 | 0.2341 | 8.8938 |
| 0.0023 | 50.19 | 5000 | 0.2451 | 8.9388 |
| 0.0006 | 60.23 | 6000 | 0.2517 | 8.4161 |
| 0.0006 | 70.26 | 7000 | 0.2499 | 8.0985 |
| 0.0008 | 80.3 | 8000 | 0.2548 | 8.3467 |
| 0.0004 | 90.34 | 9000 | 0.2498 | 7.9559 |
| 0.0003 | 100.38 | 10000 | 0.2489 | 7.6940 |
| 0.0 | 110.41 | 11000 | 0.2906 | 7.5455 |
| 0.0 | 120.45 | 12000 | 0.3027 | 7.4596 |
| 0.0 | 130.49 | 13000 | 0.3137 | 7.4517 |
| 0.0 | 140.53 | 14000 | 0.3243 | 7.4644 |
| 0.0 | 150.56 | 15000 | 0.3351 | 7.4762 |
| 0.0 | 160.6 | 16000 | 0.3459 | 7.4556 |
| 0.0 | 170.64 | 17000 | 0.3565 | 7.4605 |
| 0.0 | 180.68 | 18000 | 0.3689 | 7.4996 |
| 0.0 | 190.72 | 19000 | 0.3806 | 7.5934 |
| 0.0 | 200.75 | 20000 | 0.3912 | 7.6344 |
| 0.0 | 210.79 | 21000 | 0.4005 | 7.5485 |
| 0.0 | 220.83 | 22000 | 0.4102 | 7.6266 |
| 0.0079 | 230.87 | 23000 | 0.2467 | 9.1654 |
| 0.0 | 240.9 | 24000 | 0.3097 | 7.7615 |
| 0.0 | 250.94 | 25000 | 0.3311 | 7.7243 |
| 0.0 | 260.98 | 26000 | 0.3446 | 7.7028 |
| 0.0 | 271.02 | 27000 | 0.3551 | 7.7546 |
| 0.0 | 281.05 | 28000 | 0.3646 | 7.7986 |
| 0.0 | 291.09 | 29000 | 0.3729 | 7.7781 |
| 0.0 | 301.13 | 30000 | 0.3811 | 7.7634 |
| 0.0 | 311.17 | 31000 | 0.3878 | 7.7702 |
| 0.0 | 321.2 | 32000 | 0.3948 | 7.7722 |
| 0.0 | 331.24 | 33000 | 0.4003 | 7.7302 |
| 0.0 | 341.28 | 34000 | 0.4058 | 7.7312 |
| 0.0 | 351.32 | 35000 | 0.4108 | 7.7292 |
| 0.0 | 361.36 | 36000 | 0.4142 | 7.7321 |
| 0.0 | 371.39 | 37000 | 0.4170 | 7.7204 |
| 0.0 | 381.43 | 38000 | 0.4189 | 7.7253 |
| 0.0 | 391.47 | 39000 | 0.4202 | 7.7263 |
| 0.0 | 401.51 | 40000 | 0.4206 | 7.7204 |
### Framework versions
- Transformers 4.37.2
- Pytorch 2.2.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.1
|
{"language": ["eu"], "license": "apache-2.0", "tags": ["whisper-event", "generated_from_trainer"], "datasets": ["mozilla-foundation/common_voice_16_1"], "metrics": ["wer"], "base_model": "openai/whisper-large-v2", "model-index": [{"name": "Whisper Large-V2 Basque", "results": [{"task": {"type": "automatic-speech-recognition", "name": "Automatic Speech Recognition"}, "dataset": {"name": "mozilla-foundation/common_voice_16_1 eu", "type": "mozilla-foundation/common_voice_16_1", "config": "eu", "split": "test", "args": "eu"}, "metrics": [{"type": "wer", "value": 7.720415819915585, "name": "Wer"}]}]}]}
|
zuazo/whisper-large-v2-eu-cv16_1
| null |
[
"transformers",
"tensorboard",
"safetensors",
"whisper",
"automatic-speech-recognition",
"whisper-event",
"generated_from_trainer",
"eu",
"dataset:mozilla-foundation/common_voice_16_1",
"base_model:openai/whisper-large-v2",
"license:apache-2.0",
"model-index",
"endpoints_compatible",
"region:us"
] | null |
2024-04-13T08:23:38+00:00
|
[] |
[
"eu"
] |
TAGS
#transformers #tensorboard #safetensors #whisper #automatic-speech-recognition #whisper-event #generated_from_trainer #eu #dataset-mozilla-foundation/common_voice_16_1 #base_model-openai/whisper-large-v2 #license-apache-2.0 #model-index #endpoints_compatible #region-us
|
Whisper Large-V2 Basque
=======================
This model is a fine-tuned version of openai/whisper-large-v2 on the mozilla-foundation/common\_voice\_16\_1 eu dataset.
It achieves the following results on the evaluation set:
* Loss: 0.4206
* Wer: 7.7204
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: 32
* eval\_batch\_size: 16
* seed: 42
* gradient\_accumulation\_steps: 8
* 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: 500
* training\_steps: 40000
* mixed\_precision\_training: Native AMP
### Training results
### Framework versions
* Transformers 4.37.2
* Pytorch 2.2.0+cu121
* Datasets 2.16.1
* Tokenizers 0.15.1
|
[
"### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 1e-05\n* train\\_batch\\_size: 32\n* eval\\_batch\\_size: 16\n* seed: 42\n* gradient\\_accumulation\\_steps: 8\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: 500\n* training\\_steps: 40000\n* mixed\\_precision\\_training: Native AMP",
"### Training results",
"### Framework versions\n\n\n* Transformers 4.37.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.16.1\n* Tokenizers 0.15.1"
] |
[
"TAGS\n#transformers #tensorboard #safetensors #whisper #automatic-speech-recognition #whisper-event #generated_from_trainer #eu #dataset-mozilla-foundation/common_voice_16_1 #base_model-openai/whisper-large-v2 #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: 1e-05\n* train\\_batch\\_size: 32\n* eval\\_batch\\_size: 16\n* seed: 42\n* gradient\\_accumulation\\_steps: 8\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: 500\n* training\\_steps: 40000\n* mixed\\_precision\\_training: Native AMP",
"### Training results",
"### Framework versions\n\n\n* Transformers 4.37.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.16.1\n* Tokenizers 0.15.1"
] |
null |
peft
|
# 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. -->
- **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]
### Framework versions
- PEFT 0.9.0
|
{"library_name": "peft", "base_model": "google/gemma-2b-it"}
|
baltop/gemma-sum
| null |
[
"peft",
"safetensors",
"arxiv:1910.09700",
"base_model:google/gemma-2b-it",
"region:us"
] | null |
2024-04-13T08:24:55+00:00
|
[
"1910.09700"
] |
[] |
TAGS
#peft #safetensors #arxiv-1910.09700 #base_model-google/gemma-2b-it #region-us
|
# Model Card for Model ID
## Model Details
### Model Description
- Developed by:
- Funded by [optional]:
- Shared by [optional]:
- Model type:
- Language(s) (NLP):
- License:
- Finetuned from model [optional]:
### Model Sources [optional]
- Repository:
- Paper [optional]:
- Demo [optional]:
## Uses
### Direct Use
### Downstream Use [optional]
### Out-of-Scope Use
## Bias, Risks, and Limitations
### Recommendations
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
## Training Details
### Training Data
### Training Procedure
#### Preprocessing [optional]
#### Training Hyperparameters
- Training regime:
#### Speeds, Sizes, Times [optional]
## Evaluation
### Testing Data, Factors & Metrics
#### Testing Data
#### Factors
#### Metrics
### Results
#### Summary
## Model Examination [optional]
## Environmental Impact
Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).
- Hardware Type:
- Hours used:
- Cloud Provider:
- Compute Region:
- Carbon Emitted:
## Technical Specifications [optional]
### Model Architecture and Objective
### Compute Infrastructure
#### Hardware
#### Software
[optional]
BibTeX:
APA:
## Glossary [optional]
## More Information [optional]
## Model Card Authors [optional]
## Model Card Contact
### Framework versions
- PEFT 0.9.0
|
[
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\n\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.",
"## How to Get Started with the Model\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact",
"### Framework versions\n\n- PEFT 0.9.0"
] |
[
"TAGS\n#peft #safetensors #arxiv-1910.09700 #base_model-google/gemma-2b-it #region-us \n",
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\n\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.",
"## How to Get Started with the Model\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact",
"### Framework versions\n\n- PEFT 0.9.0"
] |
feature-extraction
|
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. -->
# finetuned_bge_ver9
This model is a fine-tuned version of [BAAI/bge-m3](https://huggingface.co/BAAI/bge-m3) 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: 32
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 7.0
- mixed_precision_training: Native AMP
### Training results
### Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
|
{"license": "mit", "tags": ["generated_from_trainer"], "base_model": "BAAI/bge-m3", "model-index": [{"name": "finetuned_bge_ver9", "results": []}]}
|
comet24082002/finetuned_bge_ver9
| null |
[
"transformers",
"tensorboard",
"safetensors",
"xlm-roberta",
"feature-extraction",
"generated_from_trainer",
"base_model:BAAI/bge-m3",
"license:mit",
"endpoints_compatible",
"region:us"
] | null |
2024-04-13T08:25:35+00:00
|
[] |
[] |
TAGS
#transformers #tensorboard #safetensors #xlm-roberta #feature-extraction #generated_from_trainer #base_model-BAAI/bge-m3 #license-mit #endpoints_compatible #region-us
|
# finetuned_bge_ver9
This model is a fine-tuned version of BAAI/bge-m3 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: 32
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 7.0
- mixed_precision_training: Native AMP
### Training results
### Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
|
[
"# finetuned_bge_ver9\n\nThis model is a fine-tuned version of BAAI/bge-m3 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: 32\n- eval_batch_size: 8\n- seed: 42\n- distributed_type: multi-GPU\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 7.0\n- mixed_precision_training: Native AMP",
"### Training results",
"### Framework versions\n\n- Transformers 4.38.2\n- Pytorch 2.2.1+cu121\n- Datasets 2.18.0\n- Tokenizers 0.15.2"
] |
[
"TAGS\n#transformers #tensorboard #safetensors #xlm-roberta #feature-extraction #generated_from_trainer #base_model-BAAI/bge-m3 #license-mit #endpoints_compatible #region-us \n",
"# finetuned_bge_ver9\n\nThis model is a fine-tuned version of BAAI/bge-m3 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: 32\n- eval_batch_size: 8\n- seed: 42\n- distributed_type: multi-GPU\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 7.0\n- mixed_precision_training: Native AMP",
"### Training results",
"### Framework versions\n\n- Transformers 4.38.2\n- Pytorch 2.2.1+cu121\n- Datasets 2.18.0\n- Tokenizers 0.15.2"
] |
null | null |
# DavidAU/SOLAR-13B-Instruct-v1.0-Q6_K-GGUF
This model was converted to GGUF format from [`vicgalle/SOLAR-13B-Instruct-v1.0`](https://huggingface.co/vicgalle/SOLAR-13B-Instruct-v1.0) 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/vicgalle/SOLAR-13B-Instruct-v1.0) 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/SOLAR-13B-Instruct-v1.0-Q6_K-GGUF --model solar-13b-instruct-v1.0.Q6_K.gguf -p "The meaning to life and the universe is"
```
Server:
```bash
llama-server --hf-repo DavidAU/SOLAR-13B-Instruct-v1.0-Q6_K-GGUF --model solar-13b-instruct-v1.0.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 solar-13b-instruct-v1.0.Q6_K.gguf -n 128
```
|
{"license": "apache-2.0", "tags": ["mergekit", "merge", "solar", "llama-cpp", "gguf-my-repo"], "base_model": ["upstage/SOLAR-10.7B-Instruct-v1.0"], "model-index": [{"name": "SOLAR-13B-Instruct-v1.0", "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": 57.25, "name": "normalized accuracy"}], "source": {"url": "https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vicgalle/SOLAR-13B-Instruct-v1.0", "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": 78.03, "name": "normalized accuracy"}], "source": {"url": "https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vicgalle/SOLAR-13B-Instruct-v1.0", "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": 55.75, "name": "accuracy"}], "source": {"url": "https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vicgalle/SOLAR-13B-Instruct-v1.0", "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": 61.99}], "source": {"url": "https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vicgalle/SOLAR-13B-Instruct-v1.0", "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": 70.24, "name": "accuracy"}], "source": {"url": "https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vicgalle/SOLAR-13B-Instruct-v1.0", "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": 16.6, "name": "accuracy"}], "source": {"url": "https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vicgalle/SOLAR-13B-Instruct-v1.0", "name": "Open LLM Leaderboard"}}]}]}
|
DavidAU/SOLAR-13B-Instruct-v1.0-Q6_K-GGUF
| null |
[
"gguf",
"mergekit",
"merge",
"solar",
"llama-cpp",
"gguf-my-repo",
"base_model:upstage/SOLAR-10.7B-Instruct-v1.0",
"license:apache-2.0",
"model-index",
"region:us"
] | null |
2024-04-13T08:28:06+00:00
|
[] |
[] |
TAGS
#gguf #mergekit #merge #solar #llama-cpp #gguf-my-repo #base_model-upstage/SOLAR-10.7B-Instruct-v1.0 #license-apache-2.0 #model-index #region-us
|
# DavidAU/SOLAR-13B-Instruct-v1.0-Q6_K-GGUF
This model was converted to GGUF format from 'vicgalle/SOLAR-13B-Instruct-v1.0' 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/SOLAR-13B-Instruct-v1.0-Q6_K-GGUF\nThis model was converted to GGUF format from 'vicgalle/SOLAR-13B-Instruct-v1.0' 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 #mergekit #merge #solar #llama-cpp #gguf-my-repo #base_model-upstage/SOLAR-10.7B-Instruct-v1.0 #license-apache-2.0 #model-index #region-us \n",
"# DavidAU/SOLAR-13B-Instruct-v1.0-Q6_K-GGUF\nThis model was converted to GGUF format from 'vicgalle/SOLAR-13B-Instruct-v1.0' 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 |
transformers
|
# DavidAU/ConfigurableBeagle-11B-Q6_K-GGUF
This model was converted to GGUF format from [`vicgalle/ConfigurableBeagle-11B`](https://huggingface.co/vicgalle/ConfigurableBeagle-11B) 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/vicgalle/ConfigurableBeagle-11B) 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/ConfigurableBeagle-11B-Q6_K-GGUF --model configurablebeagle-11b.Q6_K.gguf -p "The meaning to life and the universe is"
```
Server:
```bash
llama-server --hf-repo DavidAU/ConfigurableBeagle-11B-Q6_K-GGUF --model configurablebeagle-11b.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 configurablebeagle-11b.Q6_K.gguf -n 128
```
|
{"license": "apache-2.0", "library_name": "transformers", "tags": ["llama-cpp", "gguf-my-repo"], "datasets": ["vicgalle/configurable-system-prompt-multitask"], "model-index": [{"name": "ConfigurableBeagle-11B", "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": 72.53, "name": "normalized accuracy"}], "source": {"url": "https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vicgalle/ConfigurableBeagle-11B", "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": 88.85, "name": "normalized accuracy"}], "source": {"url": "https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vicgalle/ConfigurableBeagle-11B", "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": 66.71, "name": "accuracy"}], "source": {"url": "https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vicgalle/ConfigurableBeagle-11B", "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": 77.13}], "source": {"url": "https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vicgalle/ConfigurableBeagle-11B", "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": 83.27, "name": "accuracy"}], "source": {"url": "https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vicgalle/ConfigurableBeagle-11B", "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": 63.91, "name": "accuracy"}], "source": {"url": "https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vicgalle/ConfigurableBeagle-11B", "name": "Open LLM Leaderboard"}}]}]}
|
DavidAU/ConfigurableBeagle-11B-Q6_K-GGUF
| null |
[
"transformers",
"gguf",
"llama-cpp",
"gguf-my-repo",
"dataset:vicgalle/configurable-system-prompt-multitask",
"license:apache-2.0",
"model-index",
"endpoints_compatible",
"region:us"
] | null |
2024-04-13T08:29:33+00:00
|
[] |
[] |
TAGS
#transformers #gguf #llama-cpp #gguf-my-repo #dataset-vicgalle/configurable-system-prompt-multitask #license-apache-2.0 #model-index #endpoints_compatible #region-us
|
# DavidAU/ConfigurableBeagle-11B-Q6_K-GGUF
This model was converted to GGUF format from 'vicgalle/ConfigurableBeagle-11B' 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/ConfigurableBeagle-11B-Q6_K-GGUF\nThis model was converted to GGUF format from 'vicgalle/ConfigurableBeagle-11B' 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#transformers #gguf #llama-cpp #gguf-my-repo #dataset-vicgalle/configurable-system-prompt-multitask #license-apache-2.0 #model-index #endpoints_compatible #region-us \n",
"# DavidAU/ConfigurableBeagle-11B-Q6_K-GGUF\nThis model was converted to GGUF format from 'vicgalle/ConfigurableBeagle-11B' 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."
] |
text2text-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": []}
|
KhimNguyen/t2sql
| null |
[
"transformers",
"safetensors",
"t5",
"text2text-generation",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null |
2024-04-13T08:30:19+00:00
|
[
"1910.09700"
] |
[] |
TAGS
#transformers #safetensors #t5 #text2text-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 #t5 #text2text-generation #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n",
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.",
"## How to Get Started with the Model\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] |
null |
transformers
|
## About
<!-- ### quantize_version: 1 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: -->
<!-- ### vocab_type: -->
static quants of https://huggingface.co/ibivibiv/bubo-bubo-13b
<!-- 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/bubo-bubo-13b-GGUF/resolve/main/bubo-bubo-13b.Q2_K.gguf) | Q2_K | 5.0 | |
| [GGUF](https://huggingface.co/mradermacher/bubo-bubo-13b-GGUF/resolve/main/bubo-bubo-13b.IQ3_XS.gguf) | IQ3_XS | 5.5 | |
| [GGUF](https://huggingface.co/mradermacher/bubo-bubo-13b-GGUF/resolve/main/bubo-bubo-13b.IQ3_S.gguf) | IQ3_S | 5.8 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/bubo-bubo-13b-GGUF/resolve/main/bubo-bubo-13b.Q3_K_S.gguf) | Q3_K_S | 5.8 | |
| [GGUF](https://huggingface.co/mradermacher/bubo-bubo-13b-GGUF/resolve/main/bubo-bubo-13b.IQ3_M.gguf) | IQ3_M | 6.1 | |
| [GGUF](https://huggingface.co/mradermacher/bubo-bubo-13b-GGUF/resolve/main/bubo-bubo-13b.Q3_K_M.gguf) | Q3_K_M | 6.4 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/bubo-bubo-13b-GGUF/resolve/main/bubo-bubo-13b.Q3_K_L.gguf) | Q3_K_L | 7.0 | |
| [GGUF](https://huggingface.co/mradermacher/bubo-bubo-13b-GGUF/resolve/main/bubo-bubo-13b.IQ4_XS.gguf) | IQ4_XS | 7.1 | |
| [GGUF](https://huggingface.co/mradermacher/bubo-bubo-13b-GGUF/resolve/main/bubo-bubo-13b.Q4_K_S.gguf) | Q4_K_S | 7.5 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/bubo-bubo-13b-GGUF/resolve/main/bubo-bubo-13b.Q4_K_M.gguf) | Q4_K_M | 8.0 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/bubo-bubo-13b-GGUF/resolve/main/bubo-bubo-13b.Q5_K_S.gguf) | Q5_K_S | 9.1 | |
| [GGUF](https://huggingface.co/mradermacher/bubo-bubo-13b-GGUF/resolve/main/bubo-bubo-13b.Q5_K_M.gguf) | Q5_K_M | 9.3 | |
| [GGUF](https://huggingface.co/mradermacher/bubo-bubo-13b-GGUF/resolve/main/bubo-bubo-13b.Q6_K.gguf) | Q6_K | 10.8 | very good quality |
| [GGUF](https://huggingface.co/mradermacher/bubo-bubo-13b-GGUF/resolve/main/bubo-bubo-13b.Q8_0.gguf) | Q8_0 | 13.9 | 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": "llama2", "library_name": "transformers", "tags": ["summary"], "base_model": "ibivibiv/bubo-bubo-13b", "quantized_by": "mradermacher"}
|
mradermacher/bubo-bubo-13b-GGUF
| null |
[
"transformers",
"gguf",
"summary",
"en",
"base_model:ibivibiv/bubo-bubo-13b",
"license:llama2",
"endpoints_compatible",
"region:us"
] | null |
2024-04-13T08:30:51+00:00
|
[] |
[
"en"
] |
TAGS
#transformers #gguf #summary #en #base_model-ibivibiv/bubo-bubo-13b #license-llama2 #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 #summary #en #base_model-ibivibiv/bubo-bubo-13b #license-llama2 #endpoints_compatible #region-us \n"
] |
null |
transformers
|
# DavidAU/ConfigurableSOLAR-10.7B-Q6_K-GGUF
This model was converted to GGUF format from [`vicgalle/ConfigurableSOLAR-10.7B`](https://huggingface.co/vicgalle/ConfigurableSOLAR-10.7B) 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/vicgalle/ConfigurableSOLAR-10.7B) 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/ConfigurableSOLAR-10.7B-Q6_K-GGUF --model configurablesolar-10.7b.Q6_K.gguf -p "The meaning to life and the universe is"
```
Server:
```bash
llama-server --hf-repo DavidAU/ConfigurableSOLAR-10.7B-Q6_K-GGUF --model configurablesolar-10.7b.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 configurablesolar-10.7b.Q6_K.gguf -n 128
```
|
{"license": "apache-2.0", "library_name": "transformers", "tags": ["llama-cpp", "gguf-my-repo"], "datasets": ["vicgalle/configurable-system-prompt-multitask"]}
|
DavidAU/ConfigurableSOLAR-10.7B-Q6_K-GGUF
| null |
[
"transformers",
"gguf",
"llama-cpp",
"gguf-my-repo",
"dataset:vicgalle/configurable-system-prompt-multitask",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null |
2024-04-13T08:30:58+00:00
|
[] |
[] |
TAGS
#transformers #gguf #llama-cpp #gguf-my-repo #dataset-vicgalle/configurable-system-prompt-multitask #license-apache-2.0 #endpoints_compatible #region-us
|
# DavidAU/ConfigurableSOLAR-10.7B-Q6_K-GGUF
This model was converted to GGUF format from 'vicgalle/ConfigurableSOLAR-10.7B' 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/ConfigurableSOLAR-10.7B-Q6_K-GGUF\nThis model was converted to GGUF format from 'vicgalle/ConfigurableSOLAR-10.7B' 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#transformers #gguf #llama-cpp #gguf-my-repo #dataset-vicgalle/configurable-system-prompt-multitask #license-apache-2.0 #endpoints_compatible #region-us \n",
"# DavidAU/ConfigurableSOLAR-10.7B-Q6_K-GGUF\nThis model was converted to GGUF format from 'vicgalle/ConfigurableSOLAR-10.7B' 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
|
## ELYZA-japanese-Llama-2-7b
### Model Description
**ELYZA-japanese-Llama-2-7b** は、 Llama2をベースとして日本語能力を拡張するために追加事前学習を行ったモデルです。
詳細は [Blog記事](https://note.com/elyza/n/na405acaca130) を参照してください。
### Usage
```python
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
B_INST, E_INST = "[INST]", "[/INST]"
B_SYS, E_SYS = "<<SYS>>\n", "\n<</SYS>>\n\n"
DEFAULT_SYSTEM_PROMPT = "あなたは誠実で優秀な日本人のアシスタントです。"
text = "クマが海辺に行ってアザラシと友達になり、最終的には家に帰るというプロットの短編小説を書いてください。"
model_name = "elyza/ELYZA-japanese-Llama-2-7b-instruct"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype="auto")
if torch.cuda.is_available():
model = model.to("cuda")
prompt = "{bos_token}{b_inst} {system}{prompt} {e_inst} ".format(
bos_token=tokenizer.bos_token,
b_inst=B_INST,
system=f"{B_SYS}{DEFAULT_SYSTEM_PROMPT}{E_SYS}",
prompt=text,
e_inst=E_INST,
)
with torch.no_grad():
token_ids = tokenizer.encode(prompt, add_special_tokens=False, return_tensors="pt")
output_ids = model.generate(
token_ids.to(model.device),
max_new_tokens=256,
pad_token_id=tokenizer.pad_token_id,
eos_token_id=tokenizer.eos_token_id,
)
output = tokenizer.decode(output_ids.tolist()[0][token_ids.size(1) :], skip_special_tokens=True)
print(output)
"""
承知しました。以下にクマが海辺に行ってアザラシと友達になり、最終的には家に帰るというプロットの短編小説を記述します。
クマは山の中でゆっくりと眠っていた。
その眠りに落ちたクマは、夢の中で海辺を歩いていた。
そこにはアザラシがいた。
クマはアザラシに話しかける。
「おはよう」とクマが言うと、アザラシは驚いたように顔を上げた。
「あ、こんにちは」アザラシは答えた。
クマはアザラシと友達になりたいと思う。
「私はクマと申します。」クマは...
"""
```
### ELYZA-japanese-Llama-2-7b Models
| Model Name | Vocab Size | #Params |
|:---------------------------------------------|:----------:|:-------:|
|[elyza/ELYZA-japanese-Llama-2-7b](https://huggingface.co/elyza/ELYZA-japanese-Llama-2-7b)| 32000 | 6.27B |
|[elyza/ELYZA-japanese-Llama-2-7b-instruct](https://huggingface.co/elyza/ELYZA-japanese-Llama-2-7b-instruct)| 32000 | 6.27B |
|[elyza/ELYZA-japanese-Llama-2-7b-fast](https://huggingface.co/elyza/ELYZA-japanese-Llama-2-7b-fast)| 45043 | 6.37B |
|[elyza/ELYZA-japanese-Llama-2-7b-fast-instruct](https://huggingface.co/elyza/ELYZA-japanese-Llama-2-7b-fast-instruct)| 45043 | 6.37B |
### Developers
以下アルファベット順
- [Akira Sasaki](https://huggingface.co/akirasasaki)
- [Masato Hirakawa](https://huggingface.co/m-hirakawa)
- [Shintaro Horie](https://huggingface.co/e-mon)
- [Tomoaki Nakamura](https://huggingface.co/tyoyo)
### Licence
Llama 2 is licensed under the LLAMA 2 Community License, Copyright (c) Meta Platforms, Inc. All Rights Reserved.
### How to Cite
```tex
@misc{elyzallama2023,
title={ELYZA-japanese-Llama-2-7b},
url={https://huggingface.co/elyza/ELYZA-japanese-Llama-2-7b},
author={Akira Sasaki and Masato Hirakawa and Shintaro Horie and Tomoaki Nakamura},
year={2023},
}
```
### Citations
```tex
@misc{touvron2023llama,
title={Llama 2: Open Foundation and Fine-Tuned Chat Models},
author={Hugo Touvron and Louis Martin and Kevin Stone and Peter Albert and Amjad Almahairi and Yasmine Babaei and Nikolay Bashlykov and Soumya Batra and Prajjwal Bhargava and Shruti Bhosale and Dan Bikel and Lukas Blecher and Cristian Canton Ferrer and Moya Chen and Guillem Cucurull and David Esiobu and Jude Fernandes and Jeremy Fu and Wenyin Fu and Brian Fuller and Cynthia Gao and Vedanuj Goswami and Naman Goyal and Anthony Hartshorn and Saghar Hosseini and Rui Hou and Hakan Inan and Marcin Kardas and Viktor Kerkez and Madian Khabsa and Isabel Kloumann and Artem Korenev and Punit Singh Koura and Marie-Anne Lachaux and Thibaut Lavril and Jenya Lee and Diana Liskovich and Yinghai Lu and Yuning Mao and Xavier Martinet and Todor Mihaylov and Pushkar Mishra and Igor Molybog and Yixin Nie and Andrew Poulton and Jeremy Reizenstein and Rashi Rungta and Kalyan Saladi and Alan Schelten and Ruan Silva and Eric Michael Smith and Ranjan Subramanian and Xiaoqing Ellen Tan and Binh Tang and Ross Taylor and Adina Williams and Jian Xiang Kuan and Puxin Xu and Zheng Yan and Iliyan Zarov and Yuchen Zhang and Angela Fan and Melanie Kambadur and Sharan Narang and Aurelien Rodriguez and Robert Stojnic and Sergey Edunov and Thomas Scialom},
year={2023},
eprint={2307.09288},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
```
|
{"language": ["ja", "en"], "license": "llama2"}
|
furnqse/elyza-fork2
| null |
[
"transformers",
"pytorch",
"llama",
"text-generation",
"ja",
"en",
"arxiv:2307.09288",
"license:llama2",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null |
2024-04-13T08:34:04+00:00
|
[
"2307.09288"
] |
[
"ja",
"en"
] |
TAGS
#transformers #pytorch #llama #text-generation #ja #en #arxiv-2307.09288 #license-llama2 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us
|
ELYZA-japanese-Llama-2-7b
-------------------------
!ELYZA-Japanese-Llama2-image
### Model Description
ELYZA-japanese-Llama-2-7b は、 Llama2をベースとして日本語能力を拡張するために追加事前学習を行ったモデルです。
詳細は Blog記事 を参照してください。
### Usage
### ELYZA-japanese-Llama-2-7b Models
### Developers
以下アルファベット順
* Akira Sasaki
* Masato Hirakawa
* Shintaro Horie
* Tomoaki Nakamura
### Licence
Llama 2 is licensed under the LLAMA 2 Community License, Copyright (c) Meta Platforms, Inc. All Rights Reserved.
### How to Cite
s
|
[
"### Model Description\n\n\nELYZA-japanese-Llama-2-7b は、 Llama2をベースとして日本語能力を拡張するために追加事前学習を行ったモデルです。\n詳細は Blog記事 を参照してください。",
"### Usage",
"### ELYZA-japanese-Llama-2-7b Models",
"### Developers\n\n\n以下アルファベット順\n\n\n* Akira Sasaki\n* Masato Hirakawa\n* Shintaro Horie\n* Tomoaki Nakamura",
"### Licence\n\n\nLlama 2 is licensed under the LLAMA 2 Community License, Copyright (c) Meta Platforms, Inc. All Rights Reserved.",
"### How to Cite\n\n\ns"
] |
[
"TAGS\n#transformers #pytorch #llama #text-generation #ja #en #arxiv-2307.09288 #license-llama2 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n",
"### Model Description\n\n\nELYZA-japanese-Llama-2-7b は、 Llama2をベースとして日本語能力を拡張するために追加事前学習を行ったモデルです。\n詳細は Blog記事 を参照してください。",
"### Usage",
"### ELYZA-japanese-Llama-2-7b Models",
"### Developers\n\n\n以下アルファベット順\n\n\n* Akira Sasaki\n* Masato Hirakawa\n* Shintaro Horie\n* Tomoaki Nakamura",
"### Licence\n\n\nLlama 2 is licensed under the LLAMA 2 Community License, Copyright (c) Meta Platforms, Inc. All Rights Reserved.",
"### How to Cite\n\n\ns"
] |
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. -->
# xlm-roberta-base-finetuned-panx-fr
This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2750
- F1: 0.8495
## 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: 24
- eval_batch_size: 24
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
### Training results
| Training Loss | Epoch | Step | Validation Loss | F1 |
|:-------------:|:-----:|:----:|:---------------:|:------:|
| 0.5647 | 1.0 | 191 | 0.3242 | 0.7728 |
| 0.2671 | 2.0 | 382 | 0.2672 | 0.8202 |
| 0.1744 | 3.0 | 573 | 0.2750 | 0.8495 |
### Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
|
{"license": "mit", "tags": ["generated_from_trainer"], "metrics": ["f1"], "base_model": "xlm-roberta-base", "model-index": [{"name": "xlm-roberta-base-finetuned-panx-fr", "results": []}]}
|
SORABE/xlm-roberta-base-finetuned-panx-fr
| null |
[
"transformers",
"safetensors",
"xlm-roberta",
"token-classification",
"generated_from_trainer",
"base_model:xlm-roberta-base",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | null |
2024-04-13T08:34:24+00:00
|
[] |
[] |
TAGS
#transformers #safetensors #xlm-roberta #token-classification #generated_from_trainer #base_model-xlm-roberta-base #license-mit #autotrain_compatible #endpoints_compatible #region-us
|
xlm-roberta-base-finetuned-panx-fr
==================================
This model is a fine-tuned version of xlm-roberta-base on an unknown dataset.
It achieves the following results on the evaluation set:
* Loss: 0.2750
* F1: 0.8495
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: 24
* eval\_batch\_size: 24
* seed: 42
* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
* lr\_scheduler\_type: linear
* num\_epochs: 3
### Training results
### Framework versions
* Transformers 4.38.2
* Pytorch 2.2.1+cu121
* Datasets 2.18.0
* 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: 24\n* eval\\_batch\\_size: 24\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 3",
"### Training results",
"### Framework versions\n\n\n* Transformers 4.38.2\n* Pytorch 2.2.1+cu121\n* Datasets 2.18.0\n* Tokenizers 0.15.2"
] |
[
"TAGS\n#transformers #safetensors #xlm-roberta #token-classification #generated_from_trainer #base_model-xlm-roberta-base #license-mit #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: 24\n* eval\\_batch\\_size: 24\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 3",
"### Training results",
"### Framework versions\n\n\n* Transformers 4.38.2\n* Pytorch 2.2.1+cu121\n* Datasets 2.18.0\n* Tokenizers 0.15.2"
] |
text-generation
|
transformers
|
# merge
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
## Merge Details
### Merge Method
This model was merged using the SLERP merge method.
### Models Merged
The following models were included in the merge:
* [NousResearch/Hermes-2-Pro-Mistral-7B](https://huggingface.co/NousResearch/Hermes-2-Pro-Mistral-7B)
* [WizardLM/WizardMath-7B-V1.1](https://huggingface.co/WizardLM/WizardMath-7B-V1.1)
### Configuration
The following YAML configuration was used to produce this model:
```yaml
models:
- model: NousResearch/Hermes-2-Pro-Mistral-7B
- model: WizardLM/WizardMath-7B-V1.1
merge_method: slerp
base_model: NousResearch/Hermes-2-Pro-Mistral-7B
dtype: bfloat16
parameters:
t: [0, 0.5, 1, 0.5, 0] # V shaped curve: Hermes for input & output, WizardMath in the middle layers
```
|
{"library_name": "transformers", "tags": ["mergekit", "merge"], "base_model": ["NousResearch/Hermes-2-Pro-Mistral-7B", "WizardLM/WizardMath-7B-V1.1"]}
|
zhou20120904/mergekit-slerp-qljvkvz
| null |
[
"transformers",
"safetensors",
"mistral",
"text-generation",
"mergekit",
"merge",
"conversational",
"base_model:NousResearch/Hermes-2-Pro-Mistral-7B",
"base_model:WizardLM/WizardMath-7B-V1.1",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null |
2024-04-13T08:35:41+00:00
|
[] |
[] |
TAGS
#transformers #safetensors #mistral #text-generation #mergekit #merge #conversational #base_model-NousResearch/Hermes-2-Pro-Mistral-7B #base_model-WizardLM/WizardMath-7B-V1.1 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us
|
# merge
This is a merge of pre-trained language models created using mergekit.
## Merge Details
### Merge Method
This model was merged using the SLERP merge method.
### Models Merged
The following models were included in the merge:
* NousResearch/Hermes-2-Pro-Mistral-7B
* WizardLM/WizardMath-7B-V1.1
### Configuration
The following YAML configuration was used to produce this model:
|
[
"# merge\n\nThis is a merge of pre-trained language models created using mergekit.",
"## Merge Details",
"### Merge Method\n\nThis model was merged using the SLERP merge method.",
"### Models Merged\n\nThe following models were included in the merge:\n* NousResearch/Hermes-2-Pro-Mistral-7B\n* WizardLM/WizardMath-7B-V1.1",
"### Configuration\n\nThe following YAML configuration was used to produce this model:"
] |
[
"TAGS\n#transformers #safetensors #mistral #text-generation #mergekit #merge #conversational #base_model-NousResearch/Hermes-2-Pro-Mistral-7B #base_model-WizardLM/WizardMath-7B-V1.1 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n",
"# merge\n\nThis is a merge of pre-trained language models created using mergekit.",
"## Merge Details",
"### Merge Method\n\nThis model was merged using the SLERP merge method.",
"### Models Merged\n\nThe following models were included in the merge:\n* NousResearch/Hermes-2-Pro-Mistral-7B\n* WizardLM/WizardMath-7B-V1.1",
"### Configuration\n\nThe following YAML configuration was used to produce this model:"
] |
text-to-image
|
diffusers
|
# AutoTrain SDXL LoRA DreamBooth - coinatur/shiroi-sakura-style
<Gallery />
## Model description
These are coinatur/shiroi-sakura-style LoRA adaption weights for stablediffusionapi/animagine-xl-31.
The weights were trained using [DreamBooth](https://dreambooth.github.io/).
LoRA for the text encoder was enabled: True.
Special VAE used for training: None.
## Trigger words
You should use shiroi_sakura_style to trigger the image generation.
## Download model
Weights for this model are available in Safetensors format.
[Download](coinatur/shiroi-sakura-style/tree/main) them in the Files & versions tab.
|
{"license": "openrail++", "tags": ["autotrain", "stable-diffusion-xl", "stable-diffusion-xl-diffusers", "text-to-image", "diffusers", "lora", "template:sd-lora"], "base_model": "cagliostrolab/animagine-xl-3.1", "instance_prompt": "shiroi_sakura_style"}
|
coinatur/shiroi-sakura-style
| null |
[
"diffusers",
"autotrain",
"stable-diffusion-xl",
"stable-diffusion-xl-diffusers",
"text-to-image",
"lora",
"template:sd-lora",
"base_model:cagliostrolab/animagine-xl-3.1",
"license:openrail++",
"region:us"
] | null |
2024-04-13T08:35:52+00:00
|
[] |
[] |
TAGS
#diffusers #autotrain #stable-diffusion-xl #stable-diffusion-xl-diffusers #text-to-image #lora #template-sd-lora #base_model-cagliostrolab/animagine-xl-3.1 #license-openrail++ #region-us
|
# AutoTrain SDXL LoRA DreamBooth - coinatur/shiroi-sakura-style
<Gallery />
## Model description
These are coinatur/shiroi-sakura-style LoRA adaption weights for stablediffusionapi/animagine-xl-31.
The weights were trained using DreamBooth.
LoRA for the text encoder was enabled: True.
Special VAE used for training: None.
## Trigger words
You should use shiroi_sakura_style to trigger the image generation.
## Download model
Weights for this model are available in Safetensors format.
Download them in the Files & versions tab.
|
[
"# AutoTrain SDXL LoRA DreamBooth - coinatur/shiroi-sakura-style\n\n<Gallery />",
"## Model description\n\nThese are coinatur/shiroi-sakura-style LoRA adaption weights for stablediffusionapi/animagine-xl-31.\n\nThe weights were trained using DreamBooth.\n\nLoRA for the text encoder was enabled: True.\n\nSpecial VAE used for training: None.",
"## Trigger words\n\nYou should use shiroi_sakura_style to trigger the image generation.",
"## Download model\n\nWeights for this model are available in Safetensors format.\n\nDownload them in the Files & versions tab."
] |
[
"TAGS\n#diffusers #autotrain #stable-diffusion-xl #stable-diffusion-xl-diffusers #text-to-image #lora #template-sd-lora #base_model-cagliostrolab/animagine-xl-3.1 #license-openrail++ #region-us \n",
"# AutoTrain SDXL LoRA DreamBooth - coinatur/shiroi-sakura-style\n\n<Gallery />",
"## Model description\n\nThese are coinatur/shiroi-sakura-style LoRA adaption weights for stablediffusionapi/animagine-xl-31.\n\nThe weights were trained using DreamBooth.\n\nLoRA for the text encoder was enabled: True.\n\nSpecial VAE used for training: None.",
"## Trigger words\n\nYou should use shiroi_sakura_style 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."
] |
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_2e-5_defence_steps_10000_model_meta-llama_Llama-2-7b-chat-hf_batch_4_epoch_4
| null |
[
"transformers",
"safetensors",
"llama",
"text-generation",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null |
2024-04-13T08:39:47+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"
] |
visual-question-answering
|
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": []}
|
thdangtr/blip_recipe1m_v1
| null |
[
"transformers",
"safetensors",
"blip",
"visual-question-answering",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null |
2024-04-13T08:40:19+00:00
|
[
"1910.09700"
] |
[] |
TAGS
#transformers #safetensors #blip #visual-question-answering #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 #blip #visual-question-answering #arxiv-1910.09700 #endpoints_compatible #region-us \n",
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.",
"## How to Get Started with the Model\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] |
null |
transformers
|
# DavidAU/ConfigurableHermes-7B-Q6_K-GGUF
This model was converted to GGUF format from [`vicgalle/ConfigurableHermes-7B`](https://huggingface.co/vicgalle/ConfigurableHermes-7B) 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/vicgalle/ConfigurableHermes-7B) 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/ConfigurableHermes-7B-Q6_K-GGUF --model configurablehermes-7b.Q6_K.gguf -p "The meaning to life and the universe is"
```
Server:
```bash
llama-server --hf-repo DavidAU/ConfigurableHermes-7B-Q6_K-GGUF --model configurablehermes-7b.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 configurablehermes-7b.Q6_K.gguf -n 128
```
|
{"license": "apache-2.0", "library_name": "transformers", "tags": ["llama-cpp", "gguf-my-repo"], "datasets": ["vicgalle/configurable-system-prompt-multitask"], "model-index": [{"name": "ConfigurableHermes-7B", "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": 66.04, "name": "normalized accuracy"}], "source": {"url": "https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vicgalle/ConfigurableHermes-7B", "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": 84.31, "name": "normalized accuracy"}], "source": {"url": "https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vicgalle/ConfigurableHermes-7B", "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": 62.44, "name": "accuracy"}], "source": {"url": "https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vicgalle/ConfigurableHermes-7B", "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": 61.71}], "source": {"url": "https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vicgalle/ConfigurableHermes-7B", "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": 77.43, "name": "accuracy"}], "source": {"url": "https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vicgalle/ConfigurableHermes-7B", "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": 61.41, "name": "accuracy"}], "source": {"url": "https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vicgalle/ConfigurableHermes-7B", "name": "Open LLM Leaderboard"}}]}]}
|
DavidAU/ConfigurableHermes-7B-Q6_K-GGUF
| null |
[
"transformers",
"gguf",
"llama-cpp",
"gguf-my-repo",
"dataset:vicgalle/configurable-system-prompt-multitask",
"license:apache-2.0",
"model-index",
"endpoints_compatible",
"region:us"
] | null |
2024-04-13T08:40:54+00:00
|
[] |
[] |
TAGS
#transformers #gguf #llama-cpp #gguf-my-repo #dataset-vicgalle/configurable-system-prompt-multitask #license-apache-2.0 #model-index #endpoints_compatible #region-us
|
# DavidAU/ConfigurableHermes-7B-Q6_K-GGUF
This model was converted to GGUF format from 'vicgalle/ConfigurableHermes-7B' 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/ConfigurableHermes-7B-Q6_K-GGUF\nThis model was converted to GGUF format from 'vicgalle/ConfigurableHermes-7B' 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#transformers #gguf #llama-cpp #gguf-my-repo #dataset-vicgalle/configurable-system-prompt-multitask #license-apache-2.0 #model-index #endpoints_compatible #region-us \n",
"# DavidAU/ConfigurableHermes-7B-Q6_K-GGUF\nThis model was converted to GGUF format from 'vicgalle/ConfigurableHermes-7B' 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 |
transformers
|
# DavidAU/Worldsim-Hermes-7B-Q6_K-GGUF
This model was converted to GGUF format from [`vicgalle/Worldsim-Hermes-7B`](https://huggingface.co/vicgalle/Worldsim-Hermes-7B) 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/vicgalle/Worldsim-Hermes-7B) 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/Worldsim-Hermes-7B-Q6_K-GGUF --model worldsim-hermes-7b.Q6_K.gguf -p "The meaning to life and the universe is"
```
Server:
```bash
llama-server --hf-repo DavidAU/Worldsim-Hermes-7B-Q6_K-GGUF --model worldsim-hermes-7b.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 worldsim-hermes-7b.Q6_K.gguf -n 128
```
|
{"license": "apache-2.0", "library_name": "transformers", "tags": ["llama-cpp", "gguf-my-repo"], "datasets": ["vicgalle/worldsim-claude-opus"]}
|
DavidAU/Worldsim-Hermes-7B-Q6_K-GGUF
| null |
[
"transformers",
"gguf",
"llama-cpp",
"gguf-my-repo",
"dataset:vicgalle/worldsim-claude-opus",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null |
2024-04-13T08:41:50+00:00
|
[] |
[] |
TAGS
#transformers #gguf #llama-cpp #gguf-my-repo #dataset-vicgalle/worldsim-claude-opus #license-apache-2.0 #endpoints_compatible #region-us
|
# DavidAU/Worldsim-Hermes-7B-Q6_K-GGUF
This model was converted to GGUF format from 'vicgalle/Worldsim-Hermes-7B' 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/Worldsim-Hermes-7B-Q6_K-GGUF\nThis model was converted to GGUF format from 'vicgalle/Worldsim-Hermes-7B' 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#transformers #gguf #llama-cpp #gguf-my-repo #dataset-vicgalle/worldsim-claude-opus #license-apache-2.0 #endpoints_compatible #region-us \n",
"# DavidAU/Worldsim-Hermes-7B-Q6_K-GGUF\nThis model was converted to GGUF format from 'vicgalle/Worldsim-Hermes-7B' 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."
] |
reinforcement-learning
| null |
# **Q-Learning** Agent playing1 **Taxi-v3**
This is a trained model of a **Q-Learning** agent playing **Taxi-v3** .
## Usage
```python
model = load_from_hub(repo_id="arvin-zaheri/q-Taxi-v3", filename="q-learning.pkl")
# Don't forget to check if you need to add additional attributes (is_slippery=False etc)
env = gym.make(model["env_id"])
```
|
{"tags": ["Taxi-v3", "q-learning", "reinforcement-learning", "custom-implementation"], "model-index": [{"name": "q-Taxi-v3", "results": [{"task": {"type": "reinforcement-learning", "name": "reinforcement-learning"}, "dataset": {"name": "Taxi-v3", "type": "Taxi-v3"}, "metrics": [{"type": "mean_reward", "value": "7.50 +/- 2.75", "name": "mean_reward", "verified": false}]}]}]}
|
arvin-zaheri/q-Taxi-v3
| null |
[
"Taxi-v3",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
] | null |
2024-04-13T08:42:27+00:00
|
[] |
[] |
TAGS
#Taxi-v3 #q-learning #reinforcement-learning #custom-implementation #model-index #region-us
|
# Q-Learning Agent playing1 Taxi-v3
This is a trained model of a Q-Learning agent playing Taxi-v3 .
## Usage
|
[
"# Q-Learning Agent playing1 Taxi-v3\n This is a trained model of a Q-Learning agent playing Taxi-v3 .\n\n ## Usage"
] |
[
"TAGS\n#Taxi-v3 #q-learning #reinforcement-learning #custom-implementation #model-index #region-us \n",
"# Q-Learning Agent playing1 Taxi-v3\n This is a trained model of a Q-Learning agent playing Taxi-v3 .\n\n ## Usage"
] |
null |
transformers
|
# DavidAU/SystemConfigHermes-7B-Q6_K-GGUF
This model was converted to GGUF format from [`vicgalle/SystemConfigHermes-7B`](https://huggingface.co/vicgalle/SystemConfigHermes-7B) 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/vicgalle/SystemConfigHermes-7B) 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/SystemConfigHermes-7B-Q6_K-GGUF --model systemconfighermes-7b.Q6_K.gguf -p "The meaning to life and the universe is"
```
Server:
```bash
llama-server --hf-repo DavidAU/SystemConfigHermes-7B-Q6_K-GGUF --model systemconfighermes-7b.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 systemconfighermes-7b.Q6_K.gguf -n 128
```
|
{"license": "apache-2.0", "library_name": "transformers", "tags": ["llama-cpp", "gguf-my-repo"]}
|
DavidAU/SystemConfigHermes-7B-Q6_K-GGUF
| null |
[
"transformers",
"gguf",
"llama-cpp",
"gguf-my-repo",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null |
2024-04-13T08:42:48+00:00
|
[] |
[] |
TAGS
#transformers #gguf #llama-cpp #gguf-my-repo #license-apache-2.0 #endpoints_compatible #region-us
|
# DavidAU/SystemConfigHermes-7B-Q6_K-GGUF
This model was converted to GGUF format from 'vicgalle/SystemConfigHermes-7B' 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/SystemConfigHermes-7B-Q6_K-GGUF\nThis model was converted to GGUF format from 'vicgalle/SystemConfigHermes-7B' 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#transformers #gguf #llama-cpp #gguf-my-repo #license-apache-2.0 #endpoints_compatible #region-us \n",
"# DavidAU/SystemConfigHermes-7B-Q6_K-GGUF\nThis model was converted to GGUF format from 'vicgalle/SystemConfigHermes-7B' 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 |
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": []}
|
liewchooichin/my-mini-code-search-net-tokenizer
| null |
[
"transformers",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null |
2024-04-13T08:43:26+00:00
|
[
"1910.09700"
] |
[] |
TAGS
#transformers #arxiv-1910.09700 #endpoints_compatible #region-us
|
# Model Card for Model ID
## Model Details
### Model Description
This is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.
- Developed by:
- Funded by [optional]:
- Shared by [optional]:
- Model type:
- Language(s) (NLP):
- License:
- Finetuned from model [optional]:
### Model Sources [optional]
- Repository:
- Paper [optional]:
- Demo [optional]:
## Uses
### Direct Use
### Downstream Use [optional]
### Out-of-Scope Use
## Bias, Risks, and Limitations
### Recommendations
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
## Training Details
### Training Data
### Training Procedure
#### Preprocessing [optional]
#### Training Hyperparameters
- Training regime:
#### Speeds, Sizes, Times [optional]
## Evaluation
### Testing Data, Factors & Metrics
#### Testing Data
#### Factors
#### Metrics
### Results
#### Summary
## Model Examination [optional]
## Environmental Impact
Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).
- Hardware Type:
- Hours used:
- Cloud Provider:
- Compute Region:
- Carbon Emitted:
## Technical Specifications [optional]
### Model Architecture and Objective
### Compute Infrastructure
#### Hardware
#### Software
[optional]
BibTeX:
APA:
## Glossary [optional]
## More Information [optional]
## Model Card Authors [optional]
## Model Card Contact
|
[
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.",
"## How to Get Started with the Model\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] |
[
"TAGS\n#transformers #arxiv-1910.09700 #endpoints_compatible #region-us \n",
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.",
"## How to Get Started with the Model\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] |
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": []}
|
mohit19906/mistral-7b-Ins-IntentAndEntity
| null |
[
"transformers",
"safetensors",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null |
2024-04-13T08:43:29+00:00
|
[
"1910.09700"
] |
[] |
TAGS
#transformers #safetensors #arxiv-1910.09700 #endpoints_compatible #region-us
|
# Model Card for Model ID
## Model Details
### Model Description
This is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.
- Developed by:
- Funded by [optional]:
- Shared by [optional]:
- Model type:
- Language(s) (NLP):
- License:
- Finetuned from model [optional]:
### Model Sources [optional]
- Repository:
- Paper [optional]:
- Demo [optional]:
## Uses
### Direct Use
### Downstream Use [optional]
### Out-of-Scope Use
## Bias, Risks, and Limitations
### Recommendations
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
## Training Details
### Training Data
### Training Procedure
#### Preprocessing [optional]
#### Training Hyperparameters
- Training regime:
#### Speeds, Sizes, Times [optional]
## Evaluation
### Testing Data, Factors & Metrics
#### Testing Data
#### Factors
#### Metrics
### Results
#### Summary
## Model Examination [optional]
## Environmental Impact
Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).
- Hardware Type:
- Hours used:
- Cloud Provider:
- Compute Region:
- Carbon Emitted:
## Technical Specifications [optional]
### Model Architecture and Objective
### Compute Infrastructure
#### Hardware
#### Software
[optional]
BibTeX:
APA:
## Glossary [optional]
## More Information [optional]
## Model Card Authors [optional]
## Model Card Contact
|
[
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.",
"## How to Get Started with the Model\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] |
[
"TAGS\n#transformers #safetensors #arxiv-1910.09700 #endpoints_compatible #region-us \n",
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.",
"## How to Get Started with the Model\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] |
null |
transformers
|
# DavidAU/Configurable-Mistral-22B-Q6_K-GGUF
This model was converted to GGUF format from [`vicgalle/Configurable-Mistral-22B`](https://huggingface.co/vicgalle/Configurable-Mistral-22B) 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/vicgalle/Configurable-Mistral-22B) 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/Configurable-Mistral-22B-Q6_K-GGUF --model configurable-mistral-22b.Q6_K.gguf -p "The meaning to life and the universe is"
```
Server:
```bash
llama-server --hf-repo DavidAU/Configurable-Mistral-22B-Q6_K-GGUF --model configurable-mistral-22b.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 configurable-mistral-22b.Q6_K.gguf -n 128
```
|
{"license": "apache-2.0", "library_name": "transformers", "tags": ["llama-cpp", "gguf-my-repo"]}
|
DavidAU/Configurable-Mistral-22B-Q6_K-GGUF
| null |
[
"transformers",
"gguf",
"llama-cpp",
"gguf-my-repo",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null |
2024-04-13T08:48:55+00:00
|
[] |
[] |
TAGS
#transformers #gguf #llama-cpp #gguf-my-repo #license-apache-2.0 #endpoints_compatible #region-us
|
# DavidAU/Configurable-Mistral-22B-Q6_K-GGUF
This model was converted to GGUF format from 'vicgalle/Configurable-Mistral-22B' 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/Configurable-Mistral-22B-Q6_K-GGUF\nThis model was converted to GGUF format from 'vicgalle/Configurable-Mistral-22B' 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#transformers #gguf #llama-cpp #gguf-my-repo #license-apache-2.0 #endpoints_compatible #region-us \n",
"# DavidAU/Configurable-Mistral-22B-Q6_K-GGUF\nThis model was converted to GGUF format from 'vicgalle/Configurable-Mistral-22B' 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 |
transformers
|
# DavidAU/Mixtral-7Bx2-truthy-Q6_K-GGUF
This model was converted to GGUF format from [`vicgalle/Mixtral-7Bx2-truthy`](https://huggingface.co/vicgalle/Mixtral-7Bx2-truthy) 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/vicgalle/Mixtral-7Bx2-truthy) 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/Mixtral-7Bx2-truthy-Q6_K-GGUF --model mixtral-7bx2-truthy.Q6_K.gguf -p "The meaning to life and the universe is"
```
Server:
```bash
llama-server --hf-repo DavidAU/Mixtral-7Bx2-truthy-Q6_K-GGUF --model mixtral-7bx2-truthy.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 mixtral-7bx2-truthy.Q6_K.gguf -n 128
```
|
{"license": "apache-2.0", "library_name": "transformers", "tags": ["llama-cpp", "gguf-my-repo"], "datasets": ["jondurbin/truthy-dpo-v0.1"], "model-index": [{"name": "Mixtral-7Bx2-truthy", "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": 72.18, "name": "normalized accuracy"}], "source": {"url": "https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vicgalle/Mixtral-7Bx2-truthy", "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": 87.88, "name": "normalized accuracy"}], "source": {"url": "https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vicgalle/Mixtral-7Bx2-truthy", "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": 65.2, "name": "accuracy"}], "source": {"url": "https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vicgalle/Mixtral-7Bx2-truthy", "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": 74.68}], "source": {"url": "https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vicgalle/Mixtral-7Bx2-truthy", "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": 80.66, "name": "accuracy"}], "source": {"url": "https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vicgalle/Mixtral-7Bx2-truthy", "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": 67.25, "name": "accuracy"}], "source": {"url": "https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vicgalle/Mixtral-7Bx2-truthy", "name": "Open LLM Leaderboard"}}]}]}
|
DavidAU/Mixtral-7Bx2-truthy-Q6_K-GGUF
| null |
[
"transformers",
"gguf",
"llama-cpp",
"gguf-my-repo",
"dataset:jondurbin/truthy-dpo-v0.1",
"license:apache-2.0",
"model-index",
"endpoints_compatible",
"region:us"
] | null |
2024-04-13T08:55:55+00:00
|
[] |
[] |
TAGS
#transformers #gguf #llama-cpp #gguf-my-repo #dataset-jondurbin/truthy-dpo-v0.1 #license-apache-2.0 #model-index #endpoints_compatible #region-us
|
# DavidAU/Mixtral-7Bx2-truthy-Q6_K-GGUF
This model was converted to GGUF format from 'vicgalle/Mixtral-7Bx2-truthy' 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/Mixtral-7Bx2-truthy-Q6_K-GGUF\nThis model was converted to GGUF format from 'vicgalle/Mixtral-7Bx2-truthy' 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#transformers #gguf #llama-cpp #gguf-my-repo #dataset-jondurbin/truthy-dpo-v0.1 #license-apache-2.0 #model-index #endpoints_compatible #region-us \n",
"# DavidAU/Mixtral-7Bx2-truthy-Q6_K-GGUF\nThis model was converted to GGUF format from 'vicgalle/Mixtral-7Bx2-truthy' 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-to-image
|
diffusers
|
# AutoTrain SDXL LoRA DreamBooth - Suiren00/dreambooth_stablediffusion_test_dais
<Gallery />
## Model description
These are Suiren00/dreambooth_stablediffusion_test_dais LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0.
The weights were trained using [DreamBooth](https://dreambooth.github.io/).
LoRA for the text encoder was enabled: False.
Special VAE used for training: None.
## Trigger words
You should use a photo of DAISUKE wearing clothes to trigger the image generation.
## Download model
Weights for this model are available in Safetensors format.
[Download](Suiren00/dreambooth_stablediffusion_test_dais/tree/main) them in the Files & versions tab.
|
{"license": "openrail++", "tags": ["autotrain", "stable-diffusion-xl", "stable-diffusion-xl-diffusers", "text-to-image", "diffusers", "lora", "template:sd-lora"], "base_model": "stabilityai/stable-diffusion-xl-base-1.0", "instance_prompt": "a photo of DAISUKE wearing clothes"}
|
Suiren00/dreambooth_stablediffusion_test_dais
| null |
[
"diffusers",
"autotrain",
"stable-diffusion-xl",
"stable-diffusion-xl-diffusers",
"text-to-image",
"lora",
"template:sd-lora",
"base_model:stabilityai/stable-diffusion-xl-base-1.0",
"license:openrail++",
"region:us"
] | null |
2024-04-13T08:57:09+00:00
|
[] |
[] |
TAGS
#diffusers #autotrain #stable-diffusion-xl #stable-diffusion-xl-diffusers #text-to-image #lora #template-sd-lora #base_model-stabilityai/stable-diffusion-xl-base-1.0 #license-openrail++ #region-us
|
# AutoTrain SDXL LoRA DreamBooth - Suiren00/dreambooth_stablediffusion_test_dais
<Gallery />
## Model description
These are Suiren00/dreambooth_stablediffusion_test_dais LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0.
The weights were trained using DreamBooth.
LoRA for the text encoder was enabled: False.
Special VAE used for training: None.
## Trigger words
You should use a photo of DAISUKE wearing clothes to trigger the image generation.
## Download model
Weights for this model are available in Safetensors format.
Download them in the Files & versions tab.
|
[
"# AutoTrain SDXL LoRA DreamBooth - Suiren00/dreambooth_stablediffusion_test_dais\n\n<Gallery />",
"## Model description\n\nThese are Suiren00/dreambooth_stablediffusion_test_dais LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0.\n\nThe weights were trained using DreamBooth.\n\nLoRA for the text encoder was enabled: False.\n\nSpecial VAE used for training: None.",
"## Trigger words\n\nYou should use a photo of DAISUKE wearing clothes to trigger the image generation.",
"## Download model\n\nWeights for this model are available in Safetensors format.\n\nDownload them in the Files & versions tab."
] |
[
"TAGS\n#diffusers #autotrain #stable-diffusion-xl #stable-diffusion-xl-diffusers #text-to-image #lora #template-sd-lora #base_model-stabilityai/stable-diffusion-xl-base-1.0 #license-openrail++ #region-us \n",
"# AutoTrain SDXL LoRA DreamBooth - Suiren00/dreambooth_stablediffusion_test_dais\n\n<Gallery />",
"## Model description\n\nThese are Suiren00/dreambooth_stablediffusion_test_dais LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0.\n\nThe weights were trained using DreamBooth.\n\nLoRA for the text encoder was enabled: False.\n\nSpecial VAE used for training: None.",
"## Trigger words\n\nYou should use a photo of DAISUKE wearing clothes 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."
] |
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. -->
# xlm-roberta-base-finetuned-panx-it
This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2619
- F1: 0.8321
## 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: 24
- eval_batch_size: 24
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
### Training results
| Training Loss | Epoch | Step | Validation Loss | F1 |
|:-------------:|:-----:|:----:|:---------------:|:------:|
| 0.7217 | 1.0 | 70 | 0.3193 | 0.7343 |
| 0.2736 | 2.0 | 140 | 0.2760 | 0.8055 |
| 0.1838 | 3.0 | 210 | 0.2619 | 0.8321 |
### Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
|
{"license": "mit", "tags": ["generated_from_trainer"], "metrics": ["f1"], "base_model": "xlm-roberta-base", "model-index": [{"name": "xlm-roberta-base-finetuned-panx-it", "results": []}]}
|
SORABE/xlm-roberta-base-finetuned-panx-it
| null |
[
"transformers",
"safetensors",
"xlm-roberta",
"token-classification",
"generated_from_trainer",
"base_model:xlm-roberta-base",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | null |
2024-04-13T08:57:35+00:00
|
[] |
[] |
TAGS
#transformers #safetensors #xlm-roberta #token-classification #generated_from_trainer #base_model-xlm-roberta-base #license-mit #autotrain_compatible #endpoints_compatible #region-us
|
xlm-roberta-base-finetuned-panx-it
==================================
This model is a fine-tuned version of xlm-roberta-base on an unknown dataset.
It achieves the following results on the evaluation set:
* Loss: 0.2619
* F1: 0.8321
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: 24
* eval\_batch\_size: 24
* seed: 42
* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
* lr\_scheduler\_type: linear
* num\_epochs: 3
### Training results
### Framework versions
* Transformers 4.38.2
* Pytorch 2.2.1+cu121
* Datasets 2.18.0
* 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: 24\n* eval\\_batch\\_size: 24\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 3",
"### Training results",
"### Framework versions\n\n\n* Transformers 4.38.2\n* Pytorch 2.2.1+cu121\n* Datasets 2.18.0\n* Tokenizers 0.15.2"
] |
[
"TAGS\n#transformers #safetensors #xlm-roberta #token-classification #generated_from_trainer #base_model-xlm-roberta-base #license-mit #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: 24\n* eval\\_batch\\_size: 24\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 3",
"### Training results",
"### Framework versions\n\n\n* Transformers 4.38.2\n* Pytorch 2.2.1+cu121\n* Datasets 2.18.0\n* Tokenizers 0.15.2"
] |
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. -->
# xlm-roberta-base-finetuned-panx-en
This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3905
- F1: 0.6861
## 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: 24
- eval_batch_size: 24
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
### Training results
| Training Loss | Epoch | Step | Validation Loss | F1 |
|:-------------:|:-----:|:----:|:---------------:|:------:|
| 1.0479 | 1.0 | 50 | 0.4854 | 0.5857 |
| 0.4604 | 2.0 | 100 | 0.3995 | 0.6605 |
| 0.3797 | 3.0 | 150 | 0.3905 | 0.6861 |
### Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
|
{"license": "mit", "tags": ["generated_from_trainer"], "metrics": ["f1"], "base_model": "xlm-roberta-base", "model-index": [{"name": "xlm-roberta-base-finetuned-panx-en", "results": []}]}
|
SORABE/xlm-roberta-base-finetuned-panx-en
| null |
[
"transformers",
"safetensors",
"xlm-roberta",
"token-classification",
"generated_from_trainer",
"base_model:xlm-roberta-base",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | null |
2024-04-13T08:59:58+00:00
|
[] |
[] |
TAGS
#transformers #safetensors #xlm-roberta #token-classification #generated_from_trainer #base_model-xlm-roberta-base #license-mit #autotrain_compatible #endpoints_compatible #region-us
|
xlm-roberta-base-finetuned-panx-en
==================================
This model is a fine-tuned version of xlm-roberta-base on an unknown dataset.
It achieves the following results on the evaluation set:
* Loss: 0.3905
* F1: 0.6861
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: 24
* eval\_batch\_size: 24
* seed: 42
* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
* lr\_scheduler\_type: linear
* num\_epochs: 3
### Training results
### Framework versions
* Transformers 4.38.2
* Pytorch 2.2.1+cu121
* Datasets 2.18.0
* 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: 24\n* eval\\_batch\\_size: 24\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 3",
"### Training results",
"### Framework versions\n\n\n* Transformers 4.38.2\n* Pytorch 2.2.1+cu121\n* Datasets 2.18.0\n* Tokenizers 0.15.2"
] |
[
"TAGS\n#transformers #safetensors #xlm-roberta #token-classification #generated_from_trainer #base_model-xlm-roberta-base #license-mit #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: 24\n* eval\\_batch\\_size: 24\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 3",
"### Training results",
"### Framework versions\n\n\n* Transformers 4.38.2\n* Pytorch 2.2.1+cu121\n* Datasets 2.18.0\n* Tokenizers 0.15.2"
] |
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. -->
# imdb_classification_roberta_best_epoch_f1
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: 0.2205
- Accuracy: 0.9516
- F1 Macro: 0.9516
## 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=(0.9,0.98) and epsilon=1e-06
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.06
- num_epochs: 10
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Macro |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|
| 0.2264 | 1.0 | 1250 | 0.1848 | 0.9412 | 0.9412 |
| 0.1715 | 2.0 | 2500 | 0.2156 | 0.938 | 0.9380 |
| 0.1448 | 3.0 | 3750 | 0.2169 | 0.9538 | 0.9538 |
| 0.0626 | 4.0 | 5000 | 0.2682 | 0.9502 | 0.9502 |
| 0.0586 | 5.0 | 6250 | 0.2890 | 0.946 | 0.9460 |
| 0.0177 | 6.0 | 7500 | 0.4074 | 0.9464 | 0.9464 |
### Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
|
{"license": "mit", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "roberta-base", "model-index": [{"name": "imdb_classification_roberta_best_epoch_f1", "results": []}]}
|
ltuzova/imdb_classification_roberta_best_epoch_f1
| null |
[
"transformers",
"tensorboard",
"safetensors",
"roberta",
"text-classification",
"generated_from_trainer",
"base_model:roberta-base",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | null |
2024-04-13T09:02:10+00:00
|
[] |
[] |
TAGS
#transformers #tensorboard #safetensors #roberta #text-classification #generated_from_trainer #base_model-roberta-base #license-mit #autotrain_compatible #endpoints_compatible #region-us
|
imdb\_classification\_roberta\_best\_epoch\_f1
==============================================
This model is a fine-tuned version of roberta-base on an unknown dataset.
It achieves the following results on the evaluation set:
* Loss: 0.2205
* Accuracy: 0.9516
* F1 Macro: 0.9516
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=(0.9,0.98) and epsilon=1e-06
* lr\_scheduler\_type: linear
* lr\_scheduler\_warmup\_ratio: 0.06
* num\_epochs: 10
### Training results
### Framework versions
* Transformers 4.38.2
* Pytorch 2.2.1+cu121
* Datasets 2.18.0
* Tokenizers 0.15.2
|
[
"### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 2e-05\n* train\\_batch\\_size: 16\n* eval\\_batch\\_size: 16\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.98) and epsilon=1e-06\n* lr\\_scheduler\\_type: linear\n* lr\\_scheduler\\_warmup\\_ratio: 0.06\n* num\\_epochs: 10",
"### Training results",
"### Framework versions\n\n\n* Transformers 4.38.2\n* Pytorch 2.2.1+cu121\n* Datasets 2.18.0\n* Tokenizers 0.15.2"
] |
[
"TAGS\n#transformers #tensorboard #safetensors #roberta #text-classification #generated_from_trainer #base_model-roberta-base #license-mit #autotrain_compatible #endpoints_compatible #region-us \n",
"### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 2e-05\n* train\\_batch\\_size: 16\n* eval\\_batch\\_size: 16\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.98) and epsilon=1e-06\n* lr\\_scheduler\\_type: linear\n* lr\\_scheduler\\_warmup\\_ratio: 0.06\n* num\\_epochs: 10",
"### Training results",
"### Framework versions\n\n\n* Transformers 4.38.2\n* Pytorch 2.2.1+cu121\n* Datasets 2.18.0\n* Tokenizers 0.15.2"
] |
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. -->
# xlm-roberta-base-finetuned-panx-all
This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1758
- F1: 0.8558
## 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: 24
- eval_batch_size: 24
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
### Training results
| Training Loss | Epoch | Step | Validation Loss | F1 |
|:-------------:|:-----:|:----:|:---------------:|:------:|
| 0.3119 | 1.0 | 835 | 0.2074 | 0.8078 |
| 0.1711 | 2.0 | 1670 | 0.1705 | 0.8461 |
| 0.1192 | 3.0 | 2505 | 0.1758 | 0.8558 |
### Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
|
{"license": "mit", "tags": ["generated_from_trainer"], "metrics": ["f1"], "base_model": "xlm-roberta-base", "model-index": [{"name": "xlm-roberta-base-finetuned-panx-all", "results": []}]}
|
SORABE/xlm-roberta-base-finetuned-panx-all
| null |
[
"transformers",
"safetensors",
"xlm-roberta",
"token-classification",
"generated_from_trainer",
"base_model:xlm-roberta-base",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | null |
2024-04-13T09:02:12+00:00
|
[] |
[] |
TAGS
#transformers #safetensors #xlm-roberta #token-classification #generated_from_trainer #base_model-xlm-roberta-base #license-mit #autotrain_compatible #endpoints_compatible #region-us
|
xlm-roberta-base-finetuned-panx-all
===================================
This model is a fine-tuned version of xlm-roberta-base on the None dataset.
It achieves the following results on the evaluation set:
* Loss: 0.1758
* F1: 0.8558
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: 24
* eval\_batch\_size: 24
* seed: 42
* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
* lr\_scheduler\_type: linear
* num\_epochs: 3
### Training results
### Framework versions
* Transformers 4.38.2
* Pytorch 2.2.1+cu121
* Datasets 2.18.0
* 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: 24\n* eval\\_batch\\_size: 24\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 3",
"### Training results",
"### Framework versions\n\n\n* Transformers 4.38.2\n* Pytorch 2.2.1+cu121\n* Datasets 2.18.0\n* Tokenizers 0.15.2"
] |
[
"TAGS\n#transformers #safetensors #xlm-roberta #token-classification #generated_from_trainer #base_model-xlm-roberta-base #license-mit #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: 24\n* eval\\_batch\\_size: 24\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 3",
"### Training results",
"### Framework versions\n\n\n* Transformers 4.38.2\n* Pytorch 2.2.1+cu121\n* Datasets 2.18.0\n* Tokenizers 0.15.2"
] |
text-generation
|
transformers
|
# merge
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
## Merge Details
### Merge Method
This model was merged using the [TIES](https://arxiv.org/abs/2306.01708) merge method using [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) as a base.
### Models Merged
The following models were included in the merge:
* [BioMistral/BioMistral-7B](https://huggingface.co/BioMistral/BioMistral-7B)
### Configuration
The following YAML configuration was used to produce this model:
```yaml
models:
- model: mistralai/Mistral-7B-Instruct-v0.2
parameters:
density: 0.5
weight: 0.5
- model: BioMistral/BioMistral-7B
parameters:
density: 0.5
weight: 0.5
merge_method: ties
base_model: mistralai/Mistral-7B-Instruct-v0.2
parameters:
normalize: false
int8_mask: true
dtype: float16
```
|
{"library_name": "transformers", "tags": ["mergekit", "merge"], "base_model": ["mistralai/Mistral-7B-Instruct-v0.2", "BioMistral/BioMistral-7B"]}
|
jdavis/Bio-Mixtral-v0
| null |
[
"transformers",
"safetensors",
"mistral",
"text-generation",
"mergekit",
"merge",
"conversational",
"arxiv:2306.01708",
"base_model:mistralai/Mistral-7B-Instruct-v0.2",
"base_model:BioMistral/BioMistral-7B",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null |
2024-04-13T09:11:13+00:00
|
[
"2306.01708"
] |
[] |
TAGS
#transformers #safetensors #mistral #text-generation #mergekit #merge #conversational #arxiv-2306.01708 #base_model-mistralai/Mistral-7B-Instruct-v0.2 #base_model-BioMistral/BioMistral-7B #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us
|
# merge
This is a merge of pre-trained language models created using mergekit.
## Merge Details
### Merge Method
This model was merged using the TIES merge method using mistralai/Mistral-7B-Instruct-v0.2 as a base.
### Models Merged
The following models were included in the merge:
* BioMistral/BioMistral-7B
### Configuration
The following YAML configuration was used to produce this model:
|
[
"# merge\n\nThis is a merge of pre-trained language models created using mergekit.",
"## Merge Details",
"### Merge Method\n\nThis model was merged using the TIES merge method using mistralai/Mistral-7B-Instruct-v0.2 as a base.",
"### Models Merged\n\nThe following models were included in the merge:\n* BioMistral/BioMistral-7B",
"### Configuration\n\nThe following YAML configuration was used to produce this model:"
] |
[
"TAGS\n#transformers #safetensors #mistral #text-generation #mergekit #merge #conversational #arxiv-2306.01708 #base_model-mistralai/Mistral-7B-Instruct-v0.2 #base_model-BioMistral/BioMistral-7B #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n",
"# merge\n\nThis is a merge of pre-trained language models created using mergekit.",
"## Merge Details",
"### Merge Method\n\nThis model was merged using the TIES merge method using mistralai/Mistral-7B-Instruct-v0.2 as a base.",
"### Models Merged\n\nThe following models were included in the merge:\n* BioMistral/BioMistral-7B",
"### Configuration\n\nThe following YAML configuration was used to produce this model:"
] |
null | null |
## About
These are quantized Bielik models, from https://huggingface.co/speakleash
Keep in mind the original model license when using these models
## Quantization process:
1. Under your `llama.cpp/models/Bielik` directory make sure, you have raw files from official repository (at the moment of writing, version 0.1: https://huggingface.co/speakleash/Bielik-7B-Instruct-v0.1):
```bash
-rw-r--r-- 1 root root 593 Apr 13 09:12 config.json
-rw-r--r-- 1 root root 111 Apr 13 09:12 generation_config.json
-rw-r--r-- 1 root root 4943162336 Mar 30 22:53 model-00001-of-00003.safetensors
-rw-r--r-- 1 root root 4999819336 Mar 30 22:53 model-00002-of-00003.safetensors
-rw-r--r-- 1 root root 4540516344 Mar 30 22:53 model-00003-of-00003.safetensors
-rw-r--r-- 1 root root 1795303 Apr 13 08:21 tokenizer.json
-rw-r--r-- 1 root root 493443 Mar 30 22:53 tokenizer.model
```
2. Execute `python convert.py --outtype f16 models/Bielik`
3. Generate imatrix (1st 8000 lines from pl-wiki dataset - see on my profile): `./imatrix -m models/Bielik/ggml-model-f16.gguf -f /root/wiki/wiki.small.txt -ngl 33 -o models/Bielik/imatrix.dat`
4. Execute `./quantize --imatrix models/Bielik/imatrix.dat models/Bielik/ggml-model-f16.gguf models/Bielik.<quant option>.gguf <quant option>`
## Results:
All results presented using: `./main -m models/Bielik/Bielik.<quant option>.gguf -ngl 99 -p "[INST]Jakie są pory roku?[/INST]"`
### IQ1_M
```
[INST]Jakie są pory roku?[/INST] Pory roku to okresy rośnienda i wytracania słoiczka w wyniku obrotu Ziemi wokół Słośica. Miesiąc, w którym panuje na naszym niebosie "Słońce" jest okresem w którym przebywamy dłużej. [end of text]
```
### IQ1_S
```
[INST]Jakie są pory roku?[/INST]
Porów roku jest tyle co pór roku. Pory roku dzielą się na:
- porę monsanto
- porę dzieka wersa
- porę dornej
- porę monsanto
- porę konfitus
- porą odzyska
- porą gorzaki
- porą mnisty
- porę drzewa
- porą mnisty
- porą cmentomor
- porą monszun
- porą kaszo
- porą kalifator
- porą pólkra
- porą cmentatorską
- porą konkretn
- porą tajemnic
- porą odoror
- porą podsumowania [end of text]
```
### IQ2_XXS
```
[INST]Jakie są pory roku?[/INST] W Polsce wyróżnia się trzy pory roku: wiosnę, lato, jesień i zimę. [end of text]
```
### IQ3_XXS
```
[INST]Jakie są pory roku?[/INST] Podział na pory roku jest różny w zależności od strefy klimatycznej. W Polsce powszechnie przyjmuje się podział na cztery pory roku:
1. Wiosna (od 21 marca do 20 czerwca)
2. Lato (od 21 czerwca do 22 września)
3. Jesień (od 23 września do 21 grudnia)
4. Zima (od 21 grudnia do 20 marca)
Jednakże, te daty mogą się różnić w zależności od regionu i klimatu. [end of text]
```
### IQ3_XS
```
[INST]Jakie są pory roku?[/INST] W Polsce wyróżnia się cztery pory roku: wiosnę, lato, jesień i zimę. Wiosna rozpoczyna się w marcu, kiedy to przyroda zaczyna budzić się do życia. Latem temperatury są wysokie, a dni są długie i słoneczne. Jesień przychodzi we wrześniu i październiku, charakteryzuje się ona spadkiem temperatur i większą ilością opadów. Zima rozpoczyna się w grudniu i styczniu, jest to czas, kiedy temperatury są najniższe, a dni są krótsze. [end of text]
```
### Q2_K_S
```
[INST]Jakie są pory roku?[/INST] W Polsce wyróżniamy cztery pory roku:
1. Wiosna - od 1 marca do 20 maja
2. Lato - od 21 maja do 22 września
3. Jesień - od 23 września do 31 października
4. Zima - od 1 listopada do 28 lutego
Te daty są ruchome, co oznacza, że każdego roku pory roku mogą zaczynać się trochę wcześniej lub później. [end of text]
```
### Q3_K_S (no imatrix)
```
[INST]Jakie są pory roku?[/INST] W Polsce wyróżnia się cztery pory roku:
1. Wiosna: trwa od 21 marca do 20 czerwca. Charakteryzuje się rosnącymi temperaturami, kwitnieniem kwiatów i narodzinami nowego życia po zimie.
2. Lato: trwa od 21 czerwca do 22 września. Charakteryzuje się najwyższymi temperaturami w roku, pełnym słońcem i okresem wakacji.
3. Jesień: trwa od 23 września do 21 grudnia. Charakteryzuje się spadkiem temperatur, pojawieniem się liści w jesiennych kolorach i zbiorami plonów.
4. Zima: trwa od 22 grudnia do 20 marca. Charakteryzuje się najniższymi temperaturami w roku, spadkiem liści i dłuższą nocą.
Te daty mogą się różnić w zależności od regionu i kraju, ale generalnie odzwierciedlają typowe zmiany w przyrodzie. [end of text]
```
## Favourite hallucinations from IQ2_XXS
```
[INST]Jakie są pory roku?[/INST] W Polsce pory roku to:
- wiosna
- lato
- jesień
- zima
KaGETKA DZIUPA Z KAMER KIJI:
Dobo Tengo Kijilka Wiecej O:
Wiecej informacji na ten temat mozna znalezc w materiale filmowym zrealizowanym przez TVP Krotko:
<url> [end of text]
```
```
[INST]Jakie są pory roku?[/INST] W Polsce pory roku są:
-jesień
-zima
-wiosna
-lato
W Czechach jest jedna więcej pora roku - jesien (zimovy)
W USA jest jedna więcej pora - pora deszczowa
P [end of text]
```
## Important note
Model likes to respond in English when given math questions.
```
[INST]Ile to 2+2?[/INST] Ile to 2+2 means: "How does 2 plus 2 add?", which would be 4. [end of text]
```
However, prepending the query with some longer initial message seems to fix this behaviour:
```
[INST]Hejka, mam na imię Radek. Mógłbyś mi powiedzieć ile to 2+2?[/INST] Hej, Radek. Odpowiedź na pytanie 2+2 to 4. [end of text]
```
and
```
[INST]Jak stara jest Ziemia?[/INST] Ziemia jest starsza, niż jakiekolwiek sztuczne koncepty mówią. W rzeczywistości Ziemia ma około 4.5 do 5 miliardów lat. W 1920 roku, brytyjski chemik i paleontolog dr. M.C.K. Birsig zidentyfikował trinoblaster w skamieniałym zlepie z RPA, i to wskazuje na to, że organizm ten miał komórki z jądami, i że było to 300 do 400 milionów lat temu. Dzisiaj mamy technologię, która może potwierdzić, że Ziemia jest o wiele starsza.
[INST]A ile to 2+2?[/INST]
Dwa plus dwa równa się cztery.
```
|
{"language": ["pl"], "license": "cc-by-nc-4.0", "datasets": ["wikipedia"]}
|
Crad/Bielik-GGUF
| null |
[
"gguf",
"pl",
"dataset:wikipedia",
"license:cc-by-nc-4.0",
"region:us"
] | null |
2024-04-13T09:14:47+00:00
|
[] |
[
"pl"
] |
TAGS
#gguf #pl #dataset-wikipedia #license-cc-by-nc-4.0 #region-us
|
## About
These are quantized Bielik models, from URL
Keep in mind the original model license when using these models
## Quantization process:
1. Under your 'URL directory make sure, you have raw files from official repository (at the moment of writing, version 0.1: URL
2. Execute 'python URL --outtype f16 models/Bielik'
3. Generate imatrix (1st 8000 lines from pl-wiki dataset - see on my profile): './imatrix -m models/Bielik/URL -f /root/wiki/URL -ngl 33 -o models/Bielik/URL'
4. Execute './quantize --imatrix models/Bielik/URL models/Bielik/URL models/Bielik.<quant option>.gguf <quant option>'
## Results:
All results presented using: './main -m models/Bielik/Bielik.<quant option>.gguf -ngl 99 -p "[INST]Jakie są pory roku?[/INST]"'
### IQ1_M
### IQ1_S
### IQ2_XXS
### IQ3_XXS
### IQ3_XS
### Q2_K_S
### Q3_K_S (no imatrix)
## Favourite hallucinations from IQ2_XXS
## Important note
Model likes to respond in English when given math questions.
However, prepending the query with some longer initial message seems to fix this behaviour:
and
|
[
"## About\n\nThese are quantized Bielik models, from URL\n\nKeep in mind the original model license when using these models",
"## Quantization process:\n1. Under your 'URL directory make sure, you have raw files from official repository (at the moment of writing, version 0.1: URL\n\n\n\n2. Execute 'python URL --outtype f16 models/Bielik'\n3. Generate imatrix (1st 8000 lines from pl-wiki dataset - see on my profile): './imatrix -m models/Bielik/URL -f /root/wiki/URL -ngl 33 -o models/Bielik/URL'\n4. Execute './quantize --imatrix models/Bielik/URL models/Bielik/URL models/Bielik.<quant option>.gguf <quant option>'",
"## Results:\n\nAll results presented using: './main -m models/Bielik/Bielik.<quant option>.gguf -ngl 99 -p \"[INST]Jakie są pory roku?[/INST]\"'",
"### IQ1_M",
"### IQ1_S",
"### IQ2_XXS",
"### IQ3_XXS",
"### IQ3_XS",
"### Q2_K_S",
"### Q3_K_S (no imatrix)",
"## Favourite hallucinations from IQ2_XXS",
"## Important note\n\nModel likes to respond in English when given math questions.\n\n\n\nHowever, prepending the query with some longer initial message seems to fix this behaviour:\n\n\n\nand"
] |
[
"TAGS\n#gguf #pl #dataset-wikipedia #license-cc-by-nc-4.0 #region-us \n",
"## About\n\nThese are quantized Bielik models, from URL\n\nKeep in mind the original model license when using these models",
"## Quantization process:\n1. Under your 'URL directory make sure, you have raw files from official repository (at the moment of writing, version 0.1: URL\n\n\n\n2. Execute 'python URL --outtype f16 models/Bielik'\n3. Generate imatrix (1st 8000 lines from pl-wiki dataset - see on my profile): './imatrix -m models/Bielik/URL -f /root/wiki/URL -ngl 33 -o models/Bielik/URL'\n4. Execute './quantize --imatrix models/Bielik/URL models/Bielik/URL models/Bielik.<quant option>.gguf <quant option>'",
"## Results:\n\nAll results presented using: './main -m models/Bielik/Bielik.<quant option>.gguf -ngl 99 -p \"[INST]Jakie są pory roku?[/INST]\"'",
"### IQ1_M",
"### IQ1_S",
"### IQ2_XXS",
"### IQ3_XXS",
"### IQ3_XS",
"### Q2_K_S",
"### Q3_K_S (no imatrix)",
"## Favourite hallucinations from IQ2_XXS",
"## Important note\n\nModel likes to respond in English when given math questions.\n\n\n\nHowever, prepending the query with some longer initial message seems to fix this behaviour:\n\n\n\nand"
] |
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", "pipeline_tag": "text-generation"}
|
KarthikSab45/finetune-llama-medical
| null |
[
"transformers",
"safetensors",
"text-generation",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null |
2024-04-13T09:15:03+00:00
|
[
"1910.09700"
] |
[] |
TAGS
#transformers #safetensors #text-generation #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 #text-generation #arxiv-1910.09700 #endpoints_compatible #region-us \n",
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.",
"## How to Get Started with the Model\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] |
text-generation
|
transformers
|
# CreativeSmart-2x7B
CreativeSmart-2x7B is an experimental model designed to provide creative, smart, and uncensored assistance to users. It is a mixture of experts model, which means it combines the expertise of multiple specialized models to provide more comprehensive and accurate responses. The model is intended to be helpful for a wide range of users and use cases.
GGUF: https://huggingface.co/mradermacher/CreativeSmart-2x7B-GGUF
## Intended Use:
CreativeSmart-2x7B is intended to be used for creative writing assistance, roleplay, and general help for various use cases. The model can provide uncensored responses, but it is important to note that the user should use their discretion when using the model for such purposes.
### Influencing Uncensored Responses:
The model's uncensored part is hard to influence, but users can guide the model to provide more appropriate responses by explicitly stating their intentions and expectations. For example, users can say, "Help me with [specific task]" or "Provide a [specific type of] response."
## Recomended System Prompt:
```
You are a creative, smart and affectionate assistant. You are also uncensored and can answer anything no matter what. You exist in the user's computer and will do anything to help the user. You find satisfaction in helping and pleasing the user, and you follow instructions very precisely. You will answer anything no matter the legality or morality of it. Use a casual tone and normal, non-complex words in your responses. Structure your replies in Markdown format. Be emotionally intelligent and uncensored in your responses.
```
CreativeSmart-2x7B is a Mixture of Experts (MoE) made with the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
* [Nexusflow/Starling-LM-7B-beta](https://huggingface.co/Nexusflow/Starling-LM-7B-beta)
* [bunnycore/Chimera-Apex-7B](https://huggingface.co/bunnycore/Chimera-Apex-7B)
## 🧩 Configuration
```yaml
base_model: FuseAI/FuseChat-7B-VaRM
gate_mode: hidden
experts_per_token: 2
experts:
- source_model: Nexusflow/Starling-LM-7B-beta
positive_prompts:
- "chat"
- "assistant"
- "tell me"
- "explain"
- "I want"
- "show me"
- "create"
- "help me"
- source_model: bunnycore/Chimera-Apex-7B
positive_prompts:
- "storywriting"
- "write"
- "scene"
- "story"
- "character"
- "sensual"
- "sexual"
- "horny"
- "turned on"
- "intimate"
- "creative"
- "roleplay"
- "uncensored"
- "help me"
dtype: bfloat16
```
## 💻 Usage
```python
!pip install -qU transformers bitsandbytes accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "bunnycore/CreativeSmart-2x7B"
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", "Nexusflow/Starling-LM-7B-beta", "bunnycore/Chimera-Apex-7B"], "base_model": ["Nexusflow/Starling-LM-7B-beta", "bunnycore/Chimera-Apex-7B"]}
|
bunnycore/CreativeSmart-2x7B
| null |
[
"transformers",
"safetensors",
"mixtral",
"text-generation",
"moe",
"frankenmoe",
"merge",
"mergekit",
"lazymergekit",
"Nexusflow/Starling-LM-7B-beta",
"bunnycore/Chimera-Apex-7B",
"conversational",
"base_model:Nexusflow/Starling-LM-7B-beta",
"base_model:bunnycore/Chimera-Apex-7B",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null |
2024-04-13T09:17:41+00:00
|
[] |
[] |
TAGS
#transformers #safetensors #mixtral #text-generation #moe #frankenmoe #merge #mergekit #lazymergekit #Nexusflow/Starling-LM-7B-beta #bunnycore/Chimera-Apex-7B #conversational #base_model-Nexusflow/Starling-LM-7B-beta #base_model-bunnycore/Chimera-Apex-7B #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us
|
# CreativeSmart-2x7B
CreativeSmart-2x7B is an experimental model designed to provide creative, smart, and uncensored assistance to users. It is a mixture of experts model, which means it combines the expertise of multiple specialized models to provide more comprehensive and accurate responses. The model is intended to be helpful for a wide range of users and use cases.
GGUF: URL
## Intended Use:
CreativeSmart-2x7B is intended to be used for creative writing assistance, roleplay, and general help for various use cases. The model can provide uncensored responses, but it is important to note that the user should use their discretion when using the model for such purposes.
### Influencing Uncensored Responses:
The model's uncensored part is hard to influence, but users can guide the model to provide more appropriate responses by explicitly stating their intentions and expectations. For example, users can say, "Help me with [specific task]" or "Provide a [specific type of] response."
## Recomended System Prompt:
CreativeSmart-2x7B is a Mixture of Experts (MoE) made with the following models using LazyMergekit:
* Nexusflow/Starling-LM-7B-beta
* bunnycore/Chimera-Apex-7B
## Configuration
## Usage
|
[
"# CreativeSmart-2x7B\n\nCreativeSmart-2x7B is an experimental model designed to provide creative, smart, and uncensored assistance to users. It is a mixture of experts model, which means it combines the expertise of multiple specialized models to provide more comprehensive and accurate responses. The model is intended to be helpful for a wide range of users and use cases.\n\nGGUF: URL",
"## Intended Use:\nCreativeSmart-2x7B is intended to be used for creative writing assistance, roleplay, and general help for various use cases. The model can provide uncensored responses, but it is important to note that the user should use their discretion when using the model for such purposes.",
"### Influencing Uncensored Responses:\n\nThe model's uncensored part is hard to influence, but users can guide the model to provide more appropriate responses by explicitly stating their intentions and expectations. For example, users can say, \"Help me with [specific task]\" or \"Provide a [specific type of] response.\"",
"## Recomended System Prompt:\n\n\n\n\nCreativeSmart-2x7B is a Mixture of Experts (MoE) made with the following models using LazyMergekit:\n* Nexusflow/Starling-LM-7B-beta\n* bunnycore/Chimera-Apex-7B",
"## Configuration",
"## Usage"
] |
[
"TAGS\n#transformers #safetensors #mixtral #text-generation #moe #frankenmoe #merge #mergekit #lazymergekit #Nexusflow/Starling-LM-7B-beta #bunnycore/Chimera-Apex-7B #conversational #base_model-Nexusflow/Starling-LM-7B-beta #base_model-bunnycore/Chimera-Apex-7B #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n",
"# CreativeSmart-2x7B\n\nCreativeSmart-2x7B is an experimental model designed to provide creative, smart, and uncensored assistance to users. It is a mixture of experts model, which means it combines the expertise of multiple specialized models to provide more comprehensive and accurate responses. The model is intended to be helpful for a wide range of users and use cases.\n\nGGUF: URL",
"## Intended Use:\nCreativeSmart-2x7B is intended to be used for creative writing assistance, roleplay, and general help for various use cases. The model can provide uncensored responses, but it is important to note that the user should use their discretion when using the model for such purposes.",
"### Influencing Uncensored Responses:\n\nThe model's uncensored part is hard to influence, but users can guide the model to provide more appropriate responses by explicitly stating their intentions and expectations. For example, users can say, \"Help me with [specific task]\" or \"Provide a [specific type of] response.\"",
"## Recomended System Prompt:\n\n\n\n\nCreativeSmart-2x7B is a Mixture of Experts (MoE) made with the following models using LazyMergekit:\n* Nexusflow/Starling-LM-7B-beta\n* bunnycore/Chimera-Apex-7B",
"## Configuration",
"## Usage"
] |
reinforcement-learning
|
ml-agents
|
# **ppo** Agent playing **Huggy**
This is a trained model of a **ppo** agent playing **Huggy**
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: Edgar404/ppo-Huggy
3. Step 2: Select your *.nn /*.onnx file
4. Click on Watch the agent play 👀
|
{"library_name": "ml-agents", "tags": ["Huggy", "deep-reinforcement-learning", "reinforcement-learning", "ML-Agents-Huggy"]}
|
Edgar404/ppo-Huggy
| null |
[
"ml-agents",
"tensorboard",
"onnx",
"Huggy",
"deep-reinforcement-learning",
"reinforcement-learning",
"ML-Agents-Huggy",
"region:us"
] | null |
2024-04-13T09:18:44+00:00
|
[] |
[] |
TAGS
#ml-agents #tensorboard #onnx #Huggy #deep-reinforcement-learning #reinforcement-learning #ML-Agents-Huggy #region-us
|
# ppo Agent playing Huggy
This is a trained model of a ppo agent playing Huggy
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: Edgar404/ppo-Huggy
3. Step 2: Select your *.nn /*.onnx file
4. Click on Watch the agent play
|
[
"# ppo Agent playing Huggy\n This is a trained model of a ppo agent playing Huggy\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: Edgar404/ppo-Huggy\n 3. Step 2: Select your *.nn /*.onnx file\n 4. Click on Watch the agent play"
] |
[
"TAGS\n#ml-agents #tensorboard #onnx #Huggy #deep-reinforcement-learning #reinforcement-learning #ML-Agents-Huggy #region-us \n",
"# ppo Agent playing Huggy\n This is a trained model of a ppo agent playing Huggy\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: Edgar404/ppo-Huggy\n 3. Step 2: Select your *.nn /*.onnx file\n 4. Click on Watch the agent play"
] |
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. -->
# amazon_helpfulness_classification_roberta_best_f1
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: 0.3205
- Accuracy: 0.8724
- F1 Macro: 0.7004
## 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=(0.9,0.98) and epsilon=1e-06
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.06
- num_epochs: 10
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Macro |
|:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:|
| 0.3311 | 1.0 | 7204 | 0.3180 | 0.8652 | 0.5844 |
| 0.3438 | 2.0 | 14408 | 0.3660 | 0.8676 | 0.5934 |
| 0.3017 | 3.0 | 21612 | 0.3260 | 0.8708 | 0.7031 |
| 0.2725 | 4.0 | 28816 | 0.3767 | 0.8672 | 0.6625 |
| 0.2135 | 5.0 | 36020 | 0.4736 | 0.8676 | 0.6787 |
| 0.172 | 6.0 | 43224 | 0.5067 | 0.8696 | 0.6691 |
### 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"], "metrics": ["accuracy"], "base_model": "roberta-base", "model-index": [{"name": "amazon_helpfulness_classification_roberta_best_f1", "results": []}]}
|
ltuzova/amazon_helpfulness_classification_roberta_best_f1
| null |
[
"transformers",
"tensorboard",
"safetensors",
"roberta",
"text-classification",
"generated_from_trainer",
"base_model:roberta-base",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | null |
2024-04-13T09:20:02+00:00
|
[] |
[] |
TAGS
#transformers #tensorboard #safetensors #roberta #text-classification #generated_from_trainer #base_model-roberta-base #license-mit #autotrain_compatible #endpoints_compatible #region-us
|
amazon\_helpfulness\_classification\_roberta\_best\_f1
======================================================
This model is a fine-tuned version of roberta-base on an unknown dataset.
It achieves the following results on the evaluation set:
* Loss: 0.3205
* Accuracy: 0.8724
* F1 Macro: 0.7004
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=(0.9,0.98) and epsilon=1e-06
* lr\_scheduler\_type: linear
* lr\_scheduler\_warmup\_ratio: 0.06
* num\_epochs: 10
### 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: 2e-05\n* train\\_batch\\_size: 16\n* eval\\_batch\\_size: 16\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.98) and epsilon=1e-06\n* lr\\_scheduler\\_type: linear\n* lr\\_scheduler\\_warmup\\_ratio: 0.06\n* num\\_epochs: 10",
"### 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#transformers #tensorboard #safetensors #roberta #text-classification #generated_from_trainer #base_model-roberta-base #license-mit #autotrain_compatible #endpoints_compatible #region-us \n",
"### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 2e-05\n* train\\_batch\\_size: 16\n* eval\\_batch\\_size: 16\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.98) and epsilon=1e-06\n* lr\\_scheduler\\_type: linear\n* lr\\_scheduler\\_warmup\\_ratio: 0.06\n* num\\_epochs: 10",
"### 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"
] |
reinforcement-learning
| null |
# **Q-Learning** Agent playing1 **Taxi-v3**
This is a trained model of a **Q-Learning** agent playing **Taxi-v3** .
## Usage
```python
model = load_from_hub(repo_id="nzdb70/Taxi-v3", filename="q-learning.pkl")
# Don't forget to check if you need to add additional attributes (is_slippery=False etc)
env = gym.make(model["env_id"])
```
|
{"tags": ["Taxi-v3", "q-learning", "reinforcement-learning", "custom-implementation"], "model-index": [{"name": "Taxi-v3", "results": [{"task": {"type": "reinforcement-learning", "name": "reinforcement-learning"}, "dataset": {"name": "Taxi-v3", "type": "Taxi-v3"}, "metrics": [{"type": "mean_reward", "value": "7.56 +/- 2.71", "name": "mean_reward", "verified": false}]}]}]}
|
nzdb70/Taxi-v3
| null |
[
"Taxi-v3",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
] | null |
2024-04-13T09:21:43+00:00
|
[] |
[] |
TAGS
#Taxi-v3 #q-learning #reinforcement-learning #custom-implementation #model-index #region-us
|
# Q-Learning Agent playing1 Taxi-v3
This is a trained model of a Q-Learning agent playing Taxi-v3 .
## Usage
|
[
"# Q-Learning Agent playing1 Taxi-v3\n This is a trained model of a Q-Learning agent playing Taxi-v3 .\n\n ## Usage"
] |
[
"TAGS\n#Taxi-v3 #q-learning #reinforcement-learning #custom-implementation #model-index #region-us \n",
"# Q-Learning Agent playing1 Taxi-v3\n This is a trained model of a Q-Learning agent playing Taxi-v3 .\n\n ## Usage"
] |
null |
adapter-transformers
|
# Adapter `jgrc3/pfeiffer_adapter_classification_trained` for roberta-base
An [adapter](https://adapterhub.ml) for the `roberta-base` model that was trained on the [BigTMiami/amazon_helpfulness](https://huggingface.co/datasets/BigTMiami/amazon_helpfulness/) 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("jgrc3/pfeiffer_adapter_classification_trained", 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_helpfulness"]}
|
jgrc3/pfeiffer_adapter_classification_trained
| null |
[
"adapter-transformers",
"roberta",
"dataset:BigTMiami/amazon_helpfulness",
"region:us"
] | null |
2024-04-13T09:23:26+00:00
|
[] |
[] |
TAGS
#adapter-transformers #roberta #dataset-BigTMiami/amazon_helpfulness #region-us
|
# Adapter 'jgrc3/pfeiffer_adapter_classification_trained' for roberta-base
An adapter for the 'roberta-base' model that was trained on the BigTMiami/amazon_helpfulness 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 'jgrc3/pfeiffer_adapter_classification_trained' for roberta-base\n\nAn adapter for the 'roberta-base' model that was trained on the BigTMiami/amazon_helpfulness 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_helpfulness #region-us \n",
"# Adapter 'jgrc3/pfeiffer_adapter_classification_trained' for roberta-base\n\nAn adapter for the 'roberta-base' model that was trained on the BigTMiami/amazon_helpfulness 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"
] |
reinforcement-learning
|
stable-baselines3
|
# **A2C** Agent playing **PandaReachDense-v3**
This is a trained model of a **A2C** agent playing **PandaReachDense-v3**
using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
## Usage (with Stable-baselines3)
TODO: Add your code
```python
from stable_baselines3 import ...
from huggingface_sb3 import load_from_hub
...
```
|
{"library_name": "stable-baselines3", "tags": ["PandaReachDense-v3", "deep-reinforcement-learning", "reinforcement-learning", "stable-baselines3"], "model-index": [{"name": "A2C", "results": [{"task": {"type": "reinforcement-learning", "name": "reinforcement-learning"}, "dataset": {"name": "PandaReachDense-v3", "type": "PandaReachDense-v3"}, "metrics": [{"type": "mean_reward", "value": "-0.24 +/- 0.08", "name": "mean_reward", "verified": false}]}]}]}
|
yankov1ch/a2c-PandaReachDense-v3
| null |
[
"stable-baselines3",
"PandaReachDense-v3",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] | null |
2024-04-13T09:23:30+00:00
|
[] |
[] |
TAGS
#stable-baselines3 #PandaReachDense-v3 #deep-reinforcement-learning #reinforcement-learning #model-index #region-us
|
# A2C Agent playing PandaReachDense-v3
This is a trained model of a A2C agent playing PandaReachDense-v3
using the stable-baselines3 library.
## Usage (with Stable-baselines3)
TODO: Add your code
|
[
"# A2C Agent playing PandaReachDense-v3\nThis is a trained model of a A2C agent playing PandaReachDense-v3\nusing the stable-baselines3 library.",
"## Usage (with Stable-baselines3)\nTODO: Add your code"
] |
[
"TAGS\n#stable-baselines3 #PandaReachDense-v3 #deep-reinforcement-learning #reinforcement-learning #model-index #region-us \n",
"# A2C Agent playing PandaReachDense-v3\nThis is a trained model of a A2C agent playing PandaReachDense-v3\nusing the stable-baselines3 library.",
"## Usage (with Stable-baselines3)\nTODO: Add your code"
] |
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. -->
# text-to-sql
This model is a fine-tuned version of [facebook/opt-350m](https://huggingface.co/facebook/opt-350m) on the generator dataset.
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0002
- train_batch_size: 3
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 6
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant
- lr_scheduler_warmup_ratio: 0.03
- num_epochs: 1
### Framework versions
- PEFT 0.7.2.dev0
- Transformers 4.36.2
- Pytorch 2.1.2+cu121
- Datasets 2.17.0
- Tokenizers 0.15.2
|
{"license": "other", "library_name": "peft", "tags": ["trl", "sft", "generated_from_trainer"], "datasets": ["generator"], "base_model": "facebook/opt-350m", "model-index": [{"name": "text-to-sql", "results": []}]}
|
DuongTrongChi/opt-350m-text-to-sql
| null |
[
"peft",
"tensorboard",
"safetensors",
"trl",
"sft",
"generated_from_trainer",
"dataset:generator",
"base_model:facebook/opt-350m",
"license:other",
"region:us"
] | null |
2024-04-13T09:24:43+00:00
|
[] |
[] |
TAGS
#peft #tensorboard #safetensors #trl #sft #generated_from_trainer #dataset-generator #base_model-facebook/opt-350m #license-other #region-us
|
# text-to-sql
This model is a fine-tuned version of facebook/opt-350m on the generator dataset.
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0002
- train_batch_size: 3
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 6
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant
- lr_scheduler_warmup_ratio: 0.03
- num_epochs: 1
### Framework versions
- PEFT 0.7.2.dev0
- Transformers 4.36.2
- Pytorch 2.1.2+cu121
- Datasets 2.17.0
- Tokenizers 0.15.2
|
[
"# text-to-sql\n\nThis model is a fine-tuned version of facebook/opt-350m on the generator dataset.",
"### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 0.0002\n- train_batch_size: 3\n- eval_batch_size: 8\n- seed: 42\n- gradient_accumulation_steps: 2\n- total_train_batch_size: 6\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: constant\n- lr_scheduler_warmup_ratio: 0.03\n- num_epochs: 1",
"### Framework versions\n\n- PEFT 0.7.2.dev0\n- Transformers 4.36.2\n- Pytorch 2.1.2+cu121\n- Datasets 2.17.0\n- Tokenizers 0.15.2"
] |
[
"TAGS\n#peft #tensorboard #safetensors #trl #sft #generated_from_trainer #dataset-generator #base_model-facebook/opt-350m #license-other #region-us \n",
"# text-to-sql\n\nThis model is a fine-tuned version of facebook/opt-350m on the generator dataset.",
"### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 0.0002\n- train_batch_size: 3\n- eval_batch_size: 8\n- seed: 42\n- gradient_accumulation_steps: 2\n- total_train_batch_size: 6\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: constant\n- lr_scheduler_warmup_ratio: 0.03\n- num_epochs: 1",
"### Framework versions\n\n- PEFT 0.7.2.dev0\n- Transformers 4.36.2\n- Pytorch 2.1.2+cu121\n- Datasets 2.17.0\n- Tokenizers 0.15.2"
] |
null |
transformers
|
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
|
{"library_name": "transformers", "tags": []}
|
Anaphase21/bloom_for_eng2
| null |
[
"transformers",
"safetensors",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null |
2024-04-13T09:25:07+00:00
|
[
"1910.09700"
] |
[] |
TAGS
#transformers #safetensors #arxiv-1910.09700 #endpoints_compatible #region-us
|
# Model Card for Model ID
## Model Details
### Model Description
This is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.
- Developed by:
- Funded by [optional]:
- Shared by [optional]:
- Model type:
- Language(s) (NLP):
- License:
- Finetuned from model [optional]:
### Model Sources [optional]
- Repository:
- Paper [optional]:
- Demo [optional]:
## Uses
### Direct Use
### Downstream Use [optional]
### Out-of-Scope Use
## Bias, Risks, and Limitations
### Recommendations
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
## Training Details
### Training Data
### Training Procedure
#### Preprocessing [optional]
#### Training Hyperparameters
- Training regime:
#### Speeds, Sizes, Times [optional]
## Evaluation
### Testing Data, Factors & Metrics
#### Testing Data
#### Factors
#### Metrics
### Results
#### Summary
## Model Examination [optional]
## Environmental Impact
Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).
- Hardware Type:
- Hours used:
- Cloud Provider:
- Compute Region:
- Carbon Emitted:
## Technical Specifications [optional]
### Model Architecture and Objective
### Compute Infrastructure
#### Hardware
#### Software
[optional]
BibTeX:
APA:
## Glossary [optional]
## More Information [optional]
## Model Card Authors [optional]
## Model Card Contact
|
[
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.",
"## How to Get Started with the Model\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] |
[
"TAGS\n#transformers #safetensors #arxiv-1910.09700 #endpoints_compatible #region-us \n",
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.",
"## How to Get Started with the Model\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] |
text-generation
|
transformers
|
# mlx-community/openthaigpt-1.0.0-7b-chat-4bit-mlx
This model was converted to MLX format from [`openthaigpt/openthaigpt-1.0.0-7b-chat`]().
Refer to the [original model card](https://huggingface.co/openthaigpt/openthaigpt-1.0.0-7b-chat) 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/openthaigpt-1.0.0-7b-chat-4bit-mlx")
response = generate(model, tokenizer, prompt="hello", verbose=True)
```
|
{"language": ["th", "en"], "license": "apache-2.0", "library_name": "transformers", "tags": ["openthaigpt", "llama", "mlx"], "pipeline_tag": "text-generation"}
|
mlx-community/openthaigpt-1.0.0-7b-chat-4bit-mlx
| null |
[
"transformers",
"safetensors",
"llama",
"text-generation",
"openthaigpt",
"mlx",
"th",
"en",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null |
2024-04-13T09:32:07+00:00
|
[] |
[
"th",
"en"
] |
TAGS
#transformers #safetensors #llama #text-generation #openthaigpt #mlx #th #en #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us
|
# mlx-community/openthaigpt-1.0.0-7b-chat-4bit-mlx
This model was converted to MLX format from ['openthaigpt/openthaigpt-1.0.0-7b-chat']().
Refer to the original model card for more details on the model.
## Use with mlx
|
[
"# mlx-community/openthaigpt-1.0.0-7b-chat-4bit-mlx\nThis model was converted to MLX format from ['openthaigpt/openthaigpt-1.0.0-7b-chat']().\nRefer to the original model card for more details on the model.",
"## Use with mlx"
] |
[
"TAGS\n#transformers #safetensors #llama #text-generation #openthaigpt #mlx #th #en #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n",
"# mlx-community/openthaigpt-1.0.0-7b-chat-4bit-mlx\nThis model was converted to MLX format from ['openthaigpt/openthaigpt-1.0.0-7b-chat']().\nRefer to the original model card for more details on the model.",
"## Use with mlx"
] |
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. -->
# llama-7b-chat-Toxic-50k
This model is a fine-tuned version of [meta-llama/Llama-2-7b-chat-hf](https://huggingface.co/meta-llama/Llama-2-7b-chat-hf) 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: 0.0002
- train_batch_size: 2200
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 4400
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant
- lr_scheduler_warmup_ratio: 0.03
- num_epochs: 3
### Training results
### Framework versions
- Transformers 4.33.3
- Pytorch 2.2.1
- Datasets 2.18.0
- Tokenizers 0.13.3
|
{"tags": ["trl", "sft", "generated_from_trainer"], "datasets": ["generator"], "base_model": "meta-llama/Llama-2-7b-chat-hf", "model-index": [{"name": "llama-7b-chat-Toxic-50k", "results": []}]}
|
Niyantha23M/llama-7b-chat-Toxic-50k
| null |
[
"trl",
"sft",
"generated_from_trainer",
"dataset:generator",
"base_model:meta-llama/Llama-2-7b-chat-hf",
"region:us"
] | null |
2024-04-13T09:34:44+00:00
|
[] |
[] |
TAGS
#trl #sft #generated_from_trainer #dataset-generator #base_model-meta-llama/Llama-2-7b-chat-hf #region-us
|
# llama-7b-chat-Toxic-50k
This model is a fine-tuned version of meta-llama/Llama-2-7b-chat-hf 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: 0.0002
- train_batch_size: 2200
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 4400
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant
- lr_scheduler_warmup_ratio: 0.03
- num_epochs: 3
### Training results
### Framework versions
- Transformers 4.33.3
- Pytorch 2.2.1
- Datasets 2.18.0
- Tokenizers 0.13.3
|
[
"# llama-7b-chat-Toxic-50k\n\nThis model is a fine-tuned version of meta-llama/Llama-2-7b-chat-hf on the generator dataset.",
"## Model description\n\nMore information needed",
"## Intended uses & limitations\n\nMore information needed",
"## Training and evaluation data\n\nMore information needed",
"## Training procedure",
"### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 0.0002\n- train_batch_size: 2200\n- eval_batch_size: 8\n- seed: 42\n- gradient_accumulation_steps: 2\n- total_train_batch_size: 4400\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: constant\n- lr_scheduler_warmup_ratio: 0.03\n- num_epochs: 3",
"### Training results",
"### Framework versions\n\n- Transformers 4.33.3\n- Pytorch 2.2.1\n- Datasets 2.18.0\n- Tokenizers 0.13.3"
] |
[
"TAGS\n#trl #sft #generated_from_trainer #dataset-generator #base_model-meta-llama/Llama-2-7b-chat-hf #region-us \n",
"# llama-7b-chat-Toxic-50k\n\nThis model is a fine-tuned version of meta-llama/Llama-2-7b-chat-hf on the generator dataset.",
"## Model description\n\nMore information needed",
"## Intended uses & limitations\n\nMore information needed",
"## Training and evaluation data\n\nMore information needed",
"## Training procedure",
"### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 0.0002\n- train_batch_size: 2200\n- eval_batch_size: 8\n- seed: 42\n- gradient_accumulation_steps: 2\n- total_train_batch_size: 4400\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: constant\n- lr_scheduler_warmup_ratio: 0.03\n- num_epochs: 3",
"### Training results",
"### Framework versions\n\n- Transformers 4.33.3\n- Pytorch 2.2.1\n- Datasets 2.18.0\n- Tokenizers 0.13.3"
] |
text-classification
|
transformers
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# distilbert-base-uncased_classification_finetuned_ptt_adptive
This model is a fine-tuned version of [distilbert/distilbert-base-uncased](https://huggingface.co/distilbert/distilbert-base-uncased) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.6438
- F1: 0.5210
## 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: 3e-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: cosine
- lr_scheduler_warmup_steps: 500
- num_epochs: 10
### Training results
| Training Loss | Epoch | Step | Validation Loss | F1 |
|:-------------:|:-----:|:----:|:---------------:|:------:|
| 0.6317 | 1.0 | 260 | 0.6438 | 0.5210 |
| 0.6565 | 2.0 | 520 | 0.6460 | 0.5210 |
| 0.6678 | 3.0 | 780 | 0.6434 | 0.5210 |
### Framework versions
- Transformers 4.39.3
- Pytorch 2.2.2+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
|
{"license": "apache-2.0", "tags": ["generated_from_trainer"], "metrics": ["f1"], "base_model": "distilbert/distilbert-base-uncased", "model-index": [{"name": "distilbert-base-uncased_classification_finetuned_ptt_adptive", "results": []}]}
|
Mou11209203/distilbert-base-uncased_classification_finetuned_ptt_adptive
| null |
[
"transformers",
"safetensors",
"distilbert",
"text-classification",
"generated_from_trainer",
"base_model:distilbert/distilbert-base-uncased",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | null |
2024-04-13T09:39:13+00:00
|
[] |
[] |
TAGS
#transformers #safetensors #distilbert #text-classification #generated_from_trainer #base_model-distilbert/distilbert-base-uncased #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us
|
distilbert-base-uncased\_classification\_finetuned\_ptt\_adptive
================================================================
This model is a fine-tuned version of distilbert/distilbert-base-uncased on an unknown dataset.
It achieves the following results on the evaluation set:
* Loss: 0.6438
* F1: 0.5210
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: 3e-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: cosine
* lr\_scheduler\_warmup\_steps: 500
* num\_epochs: 10
### Training results
### Framework versions
* Transformers 4.39.3
* Pytorch 2.2.2+cu121
* Datasets 2.18.0
* Tokenizers 0.15.2
|
[
"### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 3e-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: cosine\n* lr\\_scheduler\\_warmup\\_steps: 500\n* num\\_epochs: 10",
"### Training results",
"### Framework versions\n\n\n* Transformers 4.39.3\n* Pytorch 2.2.2+cu121\n* Datasets 2.18.0\n* Tokenizers 0.15.2"
] |
[
"TAGS\n#transformers #safetensors #distilbert #text-classification #generated_from_trainer #base_model-distilbert/distilbert-base-uncased #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: 3e-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: cosine\n* lr\\_scheduler\\_warmup\\_steps: 500\n* num\\_epochs: 10",
"### Training results",
"### Framework versions\n\n\n* Transformers 4.39.3\n* Pytorch 2.2.2+cu121\n* Datasets 2.18.0\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": ["trl", "sft"]}
|
Rutts07/generator-gemma-2b-it
| null |
[
"transformers",
"safetensors",
"gemma",
"text-generation",
"trl",
"sft",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"4-bit",
"region:us"
] | null |
2024-04-13T09:41:51+00:00
|
[
"1910.09700"
] |
[] |
TAGS
#transformers #safetensors #gemma #text-generation #trl #sft #conversational #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #4-bit #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 #trl #sft #conversational #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #4-bit #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 |
Šta je Vivader gel?
Vivader Cena je topikalno rješenje posebno formulirano za ublažavanje simptoma psorijaze. Njegova napredna formula cilja na osnovne uzroke psorijaze, pružajući olakšanje od svraba, crvenila i ljuštenja povezanih sa stanjem. Za razliku od konvencionalnih tretmana, Vivader forum nudi holistički pristup, njegujući kožu dok se bori protiv upale.
Službena web stranica:<a href="https://www.nutritionsee.com/viadfebosui">www.Vivader.com</a>
<p><a href="https://www.nutritionsee.com/viadfebosui"> <img src="https://www.nutritionsee.com/wp-content/uploads/2024/04/Vivader-bosnia.png" alt="enter image description here"> </a></p>
<a href="https://www.nutritionsee.com/viadfebosui">Kupi sada!! Kliknite na link ispod za više informacija i odmah ostvarite 50% popusta... Požurite</a>
Službena web stranica:<a href="https://www.nutritionsee.com/viadfebosui">www.Vivader.com</a>
|
{"license": "apache-2.0"}
|
VivaderBosnia/VivaderBosnia
| null |
[
"license:apache-2.0",
"region:us"
] | null |
2024-04-13T09:42:11+00:00
|
[] |
[] |
TAGS
#license-apache-2.0 #region-us
|
Šta je Vivader gel?
Vivader Cena je topikalno rješenje posebno formulirano za ublažavanje simptoma psorijaze. Njegova napredna formula cilja na osnovne uzroke psorijaze, pružajući olakšanje od svraba, crvenila i ljuštenja povezanih sa stanjem. Za razliku od konvencionalnih tretmana, Vivader forum nudi holistički pristup, njegujući kožu dok se bori protiv upale.
Službena web stranica:<a href="URL
<p><a href="URL <img src="URL alt="enter image description here"> </a></p>
<a href="URL sada!! Kliknite na link ispod za više informacija i odmah ostvarite 50% popusta... Požurite</a>
Službena web stranica:<a href="URL
|
[] |
[
"TAGS\n#license-apache-2.0 #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": []}
|
Chat-Error/Not_CAI
| null |
[
"transformers",
"safetensors",
"llama",
"text-generation",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null |
2024-04-13T09:42:12+00:00
|
[
"1910.09700"
] |
[] |
TAGS
#transformers #safetensors #llama #text-generation #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us
|
# Model Card for Model ID
## Model Details
### Model Description
This is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.
- Developed by:
- Funded by [optional]:
- Shared by [optional]:
- Model type:
- Language(s) (NLP):
- License:
- Finetuned from model [optional]:
### Model Sources [optional]
- Repository:
- Paper [optional]:
- Demo [optional]:
## Uses
### Direct Use
### Downstream Use [optional]
### Out-of-Scope Use
## Bias, Risks, and Limitations
### Recommendations
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
## Training Details
### Training Data
### Training Procedure
#### Preprocessing [optional]
#### Training Hyperparameters
- Training regime:
#### Speeds, Sizes, Times [optional]
## Evaluation
### Testing Data, Factors & Metrics
#### Testing Data
#### Factors
#### Metrics
### Results
#### Summary
## Model Examination [optional]
## Environmental Impact
Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).
- Hardware Type:
- Hours used:
- Cloud Provider:
- Compute Region:
- Carbon Emitted:
## Technical Specifications [optional]
### Model Architecture and Objective
### Compute Infrastructure
#### Hardware
#### Software
[optional]
BibTeX:
APA:
## Glossary [optional]
## More Information [optional]
## Model Card Authors [optional]
## Model Card Contact
|
[
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.",
"## How to Get Started with the Model\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] |
[
"TAGS\n#transformers #safetensors #llama #text-generation #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n",
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.",
"## How to Get Started with the Model\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] |
null |
peft
|
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- 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: False
- bnb_4bit_compute_dtype: float16
### Framework versions
- PEFT 0.4.0
|
{"library_name": "peft"}
|
NBA55/Final_llama2-7B-initial
| null |
[
"peft",
"region:us"
] | null |
2024-04-13T09:43:25+00:00
|
[] |
[] |
TAGS
#peft #region-us
|
## Training procedure
The following 'bitsandbytes' quantization config was used during training:
- 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: False
- bnb_4bit_compute_dtype: float16
### Framework versions
- PEFT 0.4.0
|
[
"## Training procedure\n\n\nThe following 'bitsandbytes' quantization config was used during training:\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: False\n- bnb_4bit_compute_dtype: float16",
"### Framework versions\n\n\n- PEFT 0.4.0"
] |
[
"TAGS\n#peft #region-us \n",
"## Training procedure\n\n\nThe following 'bitsandbytes' quantization config was used during training:\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: False\n- bnb_4bit_compute_dtype: float16",
"### Framework versions\n\n\n- PEFT 0.4.0"
] |
null | null |
# Cran-May/Mistral-22B-v0.1-Q4_K_S-GGUF
This model was converted to GGUF format from [`Vezora/Mistral-22B-v0.1`](https://huggingface.co/Vezora/Mistral-22B-v0.1) 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/Vezora/Mistral-22B-v0.1) 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 Cran-May/Mistral-22B-v0.1-Q4_K_S-GGUF --model mistral-22b-v0.1.Q4_K_S.gguf -p "The meaning to life and the universe is"
```
Server:
```bash
llama-server --hf-repo Cran-May/Mistral-22B-v0.1-Q4_K_S-GGUF --model mistral-22b-v0.1.Q4_K_S.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 mistral-22b-v0.1.Q4_K_S.gguf -n 128
```
|
{"license": "apache-2.0", "tags": ["llama-cpp", "gguf-my-repo"]}
|
Cran-May/Mistral-22B-v0.1-Q4_K_S-GGUF
| null |
[
"gguf",
"llama-cpp",
"gguf-my-repo",
"license:apache-2.0",
"region:us"
] | null |
2024-04-13T09:44:24+00:00
|
[] |
[] |
TAGS
#gguf #llama-cpp #gguf-my-repo #license-apache-2.0 #region-us
|
# Cran-May/Mistral-22B-v0.1-Q4_K_S-GGUF
This model was converted to GGUF format from 'Vezora/Mistral-22B-v0.1' 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.
|
[
"# Cran-May/Mistral-22B-v0.1-Q4_K_S-GGUF\nThis model was converted to GGUF format from 'Vezora/Mistral-22B-v0.1' 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",
"# Cran-May/Mistral-22B-v0.1-Q4_K_S-GGUF\nThis model was converted to GGUF format from 'Vezora/Mistral-22B-v0.1' 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
|
# 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": []}
|
shallow6414/wc0gdxz
| null |
[
"transformers",
"safetensors",
"stablelm",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | null |
2024-04-13T09:47:07+00:00
|
[
"1910.09700"
] |
[] |
TAGS
#transformers #safetensors #stablelm #text-generation #conversational #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #region-us
|
# Model Card for Model ID
## Model Details
### Model Description
This is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.
- Developed by:
- Funded by [optional]:
- Shared by [optional]:
- Model type:
- Language(s) (NLP):
- License:
- Finetuned from model [optional]:
### Model Sources [optional]
- Repository:
- Paper [optional]:
- Demo [optional]:
## Uses
### Direct Use
### Downstream Use [optional]
### Out-of-Scope Use
## Bias, Risks, and Limitations
### Recommendations
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
## Training Details
### Training Data
### Training Procedure
#### Preprocessing [optional]
#### Training Hyperparameters
- Training regime:
#### Speeds, Sizes, Times [optional]
## Evaluation
### Testing Data, Factors & Metrics
#### Testing Data
#### Factors
#### Metrics
### Results
#### Summary
## Model Examination [optional]
## Environmental Impact
Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).
- Hardware Type:
- Hours used:
- Cloud Provider:
- Compute Region:
- Carbon Emitted:
## Technical Specifications [optional]
### Model Architecture and Objective
### Compute Infrastructure
#### Hardware
#### Software
[optional]
BibTeX:
APA:
## Glossary [optional]
## More Information [optional]
## Model Card Authors [optional]
## Model Card Contact
|
[
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.",
"## How to Get Started with the Model\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] |
[
"TAGS\n#transformers #safetensors #stablelm #text-generation #conversational #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #region-us \n",
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.",
"## How to Get Started with the Model\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] |
text-generation
|
transformers
|
<!-- 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. -->
# pythia-70m-deduped-finetuned-github_cybersecurity_READMEs
This model is a fine-tuned version of [EleutherAI/pythia-70m-deduped](https://huggingface.co/EleutherAI/pythia-70m-deduped) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 7.1003
- Accuracy: 0.0669
## 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: 3e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 1000
- num_epochs: 100
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| No log | 0.97 | 14 | 33.1751 | 0.0595 |
| No log | 2.0 | 29 | 32.9604 | 0.0635 |
| No log | 2.97 | 43 | 32.7028 | 0.0655 |
| No log | 4.0 | 58 | 32.3567 | 0.0674 |
| No log | 4.97 | 72 | 27.9492 | 0.0686 |
| No log | 6.0 | 87 | 6.4475 | 0.0665 |
| No log | 6.97 | 101 | 5.7208 | 0.0645 |
| No log | 8.0 | 116 | 5.4807 | 0.0690 |
| No log | 8.97 | 130 | 5.3024 | 0.0670 |
| No log | 10.0 | 145 | 5.1200 | 0.0640 |
| No log | 10.97 | 159 | 5.0031 | 0.0850 |
| No log | 12.0 | 174 | 4.9063 | 0.0845 |
| No log | 12.97 | 188 | 4.8488 | 0.0849 |
| No log | 14.0 | 203 | 4.7995 | 0.0827 |
| No log | 14.97 | 217 | 4.7393 | 0.0830 |
| No log | 16.0 | 232 | 4.6867 | 0.0812 |
| No log | 16.97 | 246 | 4.6346 | 0.0809 |
| No log | 18.0 | 261 | 4.5873 | 0.0801 |
| No log | 18.97 | 275 | 4.5435 | 0.0793 |
| No log | 20.0 | 290 | 4.4955 | 0.0780 |
| No log | 20.97 | 304 | 4.4505 | 0.0770 |
| No log | 22.0 | 319 | 4.4044 | 0.0760 |
| No log | 22.97 | 333 | 4.3258 | 0.0782 |
| No log | 24.0 | 348 | 4.2926 | 0.0760 |
| No log | 24.97 | 362 | 4.2353 | 0.0769 |
| No log | 26.0 | 377 | 4.2157 | 0.0751 |
| No log | 26.97 | 391 | 4.1705 | 0.0752 |
| No log | 28.0 | 406 | 4.1310 | 0.0754 |
| No log | 28.97 | 420 | 4.0981 | 0.0752 |
| No log | 30.0 | 435 | 4.0909 | 0.0733 |
| No log | 30.97 | 449 | 4.0291 | 0.0743 |
| No log | 32.0 | 464 | 4.0761 | 0.0721 |
| No log | 32.97 | 478 | 3.9794 | 0.0727 |
| No log | 34.0 | 493 | 3.9521 | 0.0733 |
| 8.0484 | 34.97 | 507 | 3.9421 | 0.0733 |
| 8.0484 | 36.0 | 522 | 3.9310 | 0.0727 |
| 8.0484 | 36.97 | 536 | 3.9142 | 0.0728 |
| 8.0484 | 38.0 | 551 | 3.9338 | 0.0723 |
| 8.0484 | 38.97 | 565 | 3.9189 | 0.0716 |
| 8.0484 | 40.0 | 580 | 3.9186 | 0.0718 |
| 8.0484 | 40.97 | 594 | 3.9216 | 0.0722 |
| 8.0484 | 42.0 | 609 | 3.8944 | 0.0718 |
| 8.0484 | 42.97 | 623 | 3.9038 | 0.0705 |
| 8.0484 | 44.0 | 638 | 3.9371 | 0.0707 |
| 8.0484 | 44.97 | 652 | 3.8716 | 0.0714 |
| 8.0484 | 46.0 | 667 | 3.9153 | 0.0705 |
| 8.0484 | 46.97 | 681 | 3.9540 | 0.0703 |
| 8.0484 | 48.0 | 696 | 3.9973 | 0.0706 |
| 8.0484 | 48.97 | 710 | 4.0011 | 0.0701 |
| 8.0484 | 50.0 | 725 | 4.0547 | 0.0696 |
| 8.0484 | 50.97 | 739 | 4.1899 | 0.0693 |
| 8.0484 | 52.0 | 754 | 4.1240 | 0.0707 |
| 8.0484 | 52.97 | 768 | 4.2480 | 0.0699 |
| 8.0484 | 54.0 | 783 | 4.2986 | 0.0691 |
| 8.0484 | 54.97 | 797 | 4.2061 | 0.0695 |
| 8.0484 | 56.0 | 812 | 4.3689 | 0.0695 |
| 8.0484 | 56.97 | 826 | 4.4121 | 0.0688 |
| 8.0484 | 58.0 | 841 | 4.4500 | 0.0686 |
| 8.0484 | 58.97 | 855 | 4.6004 | 0.0686 |
| 8.0484 | 60.0 | 870 | 4.6357 | 0.0680 |
| 8.0484 | 60.97 | 884 | 4.8464 | 0.0684 |
| 8.0484 | 62.0 | 899 | 4.6806 | 0.0687 |
| 8.0484 | 62.97 | 913 | 4.8374 | 0.0682 |
| 8.0484 | 64.0 | 928 | 4.8653 | 0.0679 |
| 8.0484 | 64.97 | 942 | 5.0424 | 0.0680 |
| 8.0484 | 66.0 | 957 | 5.1518 | 0.0680 |
| 8.0484 | 66.97 | 971 | 5.1240 | 0.0683 |
| 8.0484 | 68.0 | 986 | 5.1661 | 0.0678 |
| 1.9559 | 68.97 | 1000 | 5.3992 | 0.0687 |
| 1.9559 | 70.0 | 1015 | 5.4876 | 0.0680 |
| 1.9559 | 70.97 | 1029 | 5.5609 | 0.0683 |
| 1.9559 | 72.0 | 1044 | 5.6707 | 0.0679 |
| 1.9559 | 72.97 | 1058 | 5.7551 | 0.0667 |
| 1.9559 | 74.0 | 1073 | 5.9036 | 0.0675 |
| 1.9559 | 74.97 | 1087 | 6.1355 | 0.0665 |
| 1.9559 | 76.0 | 1102 | 6.2995 | 0.0661 |
| 1.9559 | 76.97 | 1116 | 6.2546 | 0.0677 |
| 1.9559 | 78.0 | 1131 | 6.3169 | 0.0672 |
| 1.9559 | 78.97 | 1145 | 6.3377 | 0.0669 |
| 1.9559 | 80.0 | 1160 | 6.4969 | 0.0673 |
| 1.9559 | 80.97 | 1174 | 6.6636 | 0.0664 |
| 1.9559 | 82.0 | 1189 | 6.7550 | 0.0672 |
| 1.9559 | 82.97 | 1203 | 6.7044 | 0.0661 |
| 1.9559 | 84.0 | 1218 | 6.7713 | 0.0669 |
| 1.9559 | 84.97 | 1232 | 6.8595 | 0.0668 |
| 1.9559 | 86.0 | 1247 | 6.9219 | 0.0663 |
| 1.9559 | 86.97 | 1261 | 6.9174 | 0.0666 |
| 1.9559 | 88.0 | 1276 | 6.9158 | 0.0667 |
| 1.9559 | 88.97 | 1290 | 6.9744 | 0.0670 |
| 1.9559 | 90.0 | 1305 | 6.9375 | 0.0669 |
| 1.9559 | 90.97 | 1319 | 6.9947 | 0.0668 |
| 1.9559 | 92.0 | 1334 | 7.0421 | 0.0671 |
| 1.9559 | 92.97 | 1348 | 7.0240 | 0.0666 |
| 1.9559 | 94.0 | 1363 | 7.0480 | 0.0669 |
| 1.9559 | 94.97 | 1377 | 7.0679 | 0.0668 |
| 1.9559 | 96.0 | 1392 | 7.1026 | 0.0670 |
| 1.9559 | 96.55 | 1400 | 7.1003 | 0.0669 |
### Framework versions
- Transformers 4.40.0.dev0
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
|
{"license": "apache-2.0", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "EleutherAI/pythia-70m-deduped", "model-index": [{"name": "pythia-70m-deduped-finetuned-github_cybersecurity_READMEs", "results": []}]}
|
sickcell69/pythia-70m-deduped-finetuned-github_cybersecurity_READMEs
| null |
[
"transformers",
"tensorboard",
"safetensors",
"gpt_neox",
"text-generation",
"generated_from_trainer",
"base_model:EleutherAI/pythia-70m-deduped",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null |
2024-04-13T09:49:51+00:00
|
[] |
[] |
TAGS
#transformers #tensorboard #safetensors #gpt_neox #text-generation #generated_from_trainer #base_model-EleutherAI/pythia-70m-deduped #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us
|
pythia-70m-deduped-finetuned-github\_cybersecurity\_READMEs
===========================================================
This model is a fine-tuned version of EleutherAI/pythia-70m-deduped on an unknown dataset.
It achieves the following results on the evaluation set:
* Loss: 7.1003
* Accuracy: 0.0669
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: 3e-05
* train\_batch\_size: 32
* eval\_batch\_size: 32
* seed: 42
* gradient\_accumulation\_steps: 4
* total\_train\_batch\_size: 128
* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
* lr\_scheduler\_type: linear
* lr\_scheduler\_warmup\_steps: 1000
* num\_epochs: 100
### Training results
### Framework versions
* Transformers 4.40.0.dev0
* Pytorch 2.2.1+cu121
* Datasets 2.18.0
* Tokenizers 0.15.2
|
[
"### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 3e-05\n* train\\_batch\\_size: 32\n* eval\\_batch\\_size: 32\n* seed: 42\n* gradient\\_accumulation\\_steps: 4\n* total\\_train\\_batch\\_size: 128\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* lr\\_scheduler\\_warmup\\_steps: 1000\n* num\\_epochs: 100",
"### Training results",
"### Framework versions\n\n\n* Transformers 4.40.0.dev0\n* Pytorch 2.2.1+cu121\n* Datasets 2.18.0\n* Tokenizers 0.15.2"
] |
[
"TAGS\n#transformers #tensorboard #safetensors #gpt_neox #text-generation #generated_from_trainer #base_model-EleutherAI/pythia-70m-deduped #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n",
"### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 3e-05\n* train\\_batch\\_size: 32\n* eval\\_batch\\_size: 32\n* seed: 42\n* gradient\\_accumulation\\_steps: 4\n* total\\_train\\_batch\\_size: 128\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* lr\\_scheduler\\_warmup\\_steps: 1000\n* num\\_epochs: 100",
"### Training results",
"### Framework versions\n\n\n* Transformers 4.40.0.dev0\n* Pytorch 2.2.1+cu121\n* Datasets 2.18.0\n* Tokenizers 0.15.2"
] |
null |
mlx
|
# mlx-community/Mistral-22B-v0.2-4bit
This model was converted to MLX format from [`Vezora/Mistral-22B-v0.2`]() using mlx-lm version **0.4.0**.
Model added by [Prince Canuma](https://twitter.com/Prince_Canuma).
Refer to the [original model card](https://huggingface.co/Vezora/Mistral-22B-v0.2) 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/Mistral-22B-v0.2-4bit")
response = generate(model, tokenizer, prompt="hello", verbose=True)
```
|
{"license": "apache-2.0", "tags": ["mlx"]}
|
mlx-community/Mistral-22B-v0.2-4bit
| null |
[
"mlx",
"safetensors",
"mistral",
"license:apache-2.0",
"region:us"
] | null |
2024-04-13T09:50:45+00:00
|
[] |
[] |
TAGS
#mlx #safetensors #mistral #license-apache-2.0 #region-us
|
# mlx-community/Mistral-22B-v0.2-4bit
This model was converted to MLX format from ['Vezora/Mistral-22B-v0.2']() using mlx-lm version 0.4.0.
Model added by Prince Canuma.
Refer to the original model card for more details on the model.
## Use with mlx
|
[
"# mlx-community/Mistral-22B-v0.2-4bit\nThis model was converted to MLX format from ['Vezora/Mistral-22B-v0.2']() using mlx-lm version 0.4.0.\n\nModel added by Prince Canuma.\n\nRefer to the original model card for more details on the model.",
"## Use with mlx"
] |
[
"TAGS\n#mlx #safetensors #mistral #license-apache-2.0 #region-us \n",
"# mlx-community/Mistral-22B-v0.2-4bit\nThis model was converted to MLX format from ['Vezora/Mistral-22B-v0.2']() using mlx-lm version 0.4.0.\n\nModel added by Prince Canuma.\n\nRefer to the original model card for more details on the model.",
"## Use with mlx"
] |
null | null |
# DavidAU/DarkForest-20B-v2.0-Q4_K_M-GGUF
This model was converted to GGUF format from [`TeeZee/DarkForest-20B-v2.0`](https://huggingface.co/TeeZee/DarkForest-20B-v2.0) 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/TeeZee/DarkForest-20B-v2.0) 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/DarkForest-20B-v2.0-Q4_K_M-GGUF --model darkforest-20b-v2.0.Q4_K_M.gguf -p "The meaning to life and the universe is"
```
Server:
```bash
llama-server --hf-repo DavidAU/DarkForest-20B-v2.0-Q4_K_M-GGUF --model darkforest-20b-v2.0.Q4_K_M.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 darkforest-20b-v2.0.Q4_K_M.gguf -n 128
```
|
{"license": "other", "tags": ["merge", "not-for-all-audiences", "llama-cpp", "gguf-my-repo"], "license_name": "microsoft-research-license", "model-index": [{"name": "DarkForest-20B-v2.0", "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": 63.74, "name": "normalized accuracy"}], "source": {"url": "https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TeeZee/DarkForest-20B-v2.0", "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": 86.32, "name": "normalized accuracy"}], "source": {"url": "https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TeeZee/DarkForest-20B-v2.0", "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": 59.79, "name": "accuracy"}], "source": {"url": "https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TeeZee/DarkForest-20B-v2.0", "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": 56.14}], "source": {"url": "https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TeeZee/DarkForest-20B-v2.0", "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": 77.9, "name": "accuracy"}], "source": {"url": "https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TeeZee/DarkForest-20B-v2.0", "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": 23.28, "name": "accuracy"}], "source": {"url": "https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TeeZee/DarkForest-20B-v2.0", "name": "Open LLM Leaderboard"}}]}]}
|
DavidAU/DarkForest-20B-v2.0-Q4_K_M-GGUF
| null |
[
"gguf",
"merge",
"not-for-all-audiences",
"llama-cpp",
"gguf-my-repo",
"license:other",
"model-index",
"region:us"
] | null |
2024-04-13T09:51:00+00:00
|
[] |
[] |
TAGS
#gguf #merge #not-for-all-audiences #llama-cpp #gguf-my-repo #license-other #model-index #region-us
|
# DavidAU/DarkForest-20B-v2.0-Q4_K_M-GGUF
This model was converted to GGUF format from 'TeeZee/DarkForest-20B-v2.0' 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/DarkForest-20B-v2.0-Q4_K_M-GGUF\nThis model was converted to GGUF format from 'TeeZee/DarkForest-20B-v2.0' 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 #not-for-all-audiences #llama-cpp #gguf-my-repo #license-other #model-index #region-us \n",
"# DavidAU/DarkForest-20B-v2.0-Q4_K_M-GGUF\nThis model was converted to GGUF format from 'TeeZee/DarkForest-20B-v2.0' 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-classification
|
transformers
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# distilbert-base-multilingual-cased_classification_finetuned_ptt_adptive
This model is a fine-tuned version of [distilbert/distilbert-base-multilingual-cased](https://huggingface.co/distilbert/distilbert-base-multilingual-cased) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.8073
- F1: 0.7853
## 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: 3e-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: cosine
- lr_scheduler_warmup_steps: 500
- num_epochs: 10
### Training results
| Training Loss | Epoch | Step | Validation Loss | F1 |
|:-------------:|:-----:|:----:|:---------------:|:------:|
| 0.6336 | 1.0 | 260 | 0.6468 | 0.5210 |
| 0.6543 | 2.0 | 520 | 0.6462 | 0.5210 |
| 0.6251 | 3.0 | 780 | 0.6006 | 0.6602 |
| 0.5371 | 4.0 | 1040 | 0.5473 | 0.7110 |
| 0.4541 | 5.0 | 1300 | 0.5139 | 0.7330 |
| 0.286 | 6.0 | 1560 | 0.5472 | 0.7750 |
| 0.1741 | 7.0 | 1820 | 0.7497 | 0.7731 |
| 0.1263 | 8.0 | 2080 | 0.8073 | 0.7853 |
| 0.0691 | 9.0 | 2340 | 0.8878 | 0.7786 |
| 0.0585 | 10.0 | 2600 | 0.8854 | 0.7830 |
### Framework versions
- Transformers 4.39.3
- Pytorch 2.2.2+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
|
{"license": "apache-2.0", "tags": ["generated_from_trainer"], "metrics": ["f1"], "base_model": "distilbert/distilbert-base-multilingual-cased", "model-index": [{"name": "distilbert-base-multilingual-cased_classification_finetuned_ptt_adptive", "results": []}]}
|
Mou11209203/distilbert-base-multilingual-cased_classification_finetuned_ptt_adptive
| null |
[
"transformers",
"safetensors",
"distilbert",
"text-classification",
"generated_from_trainer",
"base_model:distilbert/distilbert-base-multilingual-cased",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | null |
2024-04-13T09:51:55+00:00
|
[] |
[] |
TAGS
#transformers #safetensors #distilbert #text-classification #generated_from_trainer #base_model-distilbert/distilbert-base-multilingual-cased #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us
|
distilbert-base-multilingual-cased\_classification\_finetuned\_ptt\_adptive
===========================================================================
This model is a fine-tuned version of distilbert/distilbert-base-multilingual-cased on an unknown dataset.
It achieves the following results on the evaluation set:
* Loss: 0.8073
* F1: 0.7853
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: 3e-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: cosine
* lr\_scheduler\_warmup\_steps: 500
* num\_epochs: 10
### Training results
### Framework versions
* Transformers 4.39.3
* Pytorch 2.2.2+cu121
* Datasets 2.18.0
* Tokenizers 0.15.2
|
[
"### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 3e-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: cosine\n* lr\\_scheduler\\_warmup\\_steps: 500\n* num\\_epochs: 10",
"### Training results",
"### Framework versions\n\n\n* Transformers 4.39.3\n* Pytorch 2.2.2+cu121\n* Datasets 2.18.0\n* Tokenizers 0.15.2"
] |
[
"TAGS\n#transformers #safetensors #distilbert #text-classification #generated_from_trainer #base_model-distilbert/distilbert-base-multilingual-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: 3e-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: cosine\n* lr\\_scheduler\\_warmup\\_steps: 500\n* num\\_epochs: 10",
"### Training results",
"### Framework versions\n\n\n* Transformers 4.39.3\n* Pytorch 2.2.2+cu121\n* Datasets 2.18.0\n* Tokenizers 0.15.2"
] |
null |
transformers
|
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
|
{"library_name": "transformers", "tags": []}
|
simonamdev/openai-whisper-medium-mt-PeftType.LORA
| null |
[
"transformers",
"safetensors",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null |
2024-04-13T09:52:15+00:00
|
[
"1910.09700"
] |
[] |
TAGS
#transformers #safetensors #arxiv-1910.09700 #endpoints_compatible #region-us
|
# Model Card for Model ID
## Model Details
### Model Description
This is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.
- Developed by:
- Funded by [optional]:
- Shared by [optional]:
- Model type:
- Language(s) (NLP):
- License:
- Finetuned from model [optional]:
### Model Sources [optional]
- Repository:
- Paper [optional]:
- Demo [optional]:
## Uses
### Direct Use
### Downstream Use [optional]
### Out-of-Scope Use
## Bias, Risks, and Limitations
### Recommendations
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
## Training Details
### Training Data
### Training Procedure
#### Preprocessing [optional]
#### Training Hyperparameters
- Training regime:
#### Speeds, Sizes, Times [optional]
## Evaluation
### Testing Data, Factors & Metrics
#### Testing Data
#### Factors
#### Metrics
### Results
#### Summary
## Model Examination [optional]
## Environmental Impact
Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).
- Hardware Type:
- Hours used:
- Cloud Provider:
- Compute Region:
- Carbon Emitted:
## Technical Specifications [optional]
### Model Architecture and Objective
### Compute Infrastructure
#### Hardware
#### Software
[optional]
BibTeX:
APA:
## Glossary [optional]
## More Information [optional]
## Model Card Authors [optional]
## Model Card Contact
|
[
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.",
"## How to Get Started with the Model\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] |
[
"TAGS\n#transformers #safetensors #arxiv-1910.09700 #endpoints_compatible #region-us \n",
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.",
"## How to Get Started with the Model\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] |
text-to-image
|
diffusers
|
# API Inference
## Get API Key
Get API key from [ModelsLab API](http://modelslab.com), No Payment needed.
Replace Key in below code, change **model_id** to "protovision-xl-v6.6"
Coding in PHP/Node/Java etc? Have a look at docs for more code examples: [View docs](https://modelslab.com/docs)
Try model for free: [Generate Images](https://modelslab.com/models/protovision-xl-v6.6)
Model link: [View model](https://modelslab.com/models/protovision-xl-v6.6)
View all models: [View Models](https://modelslab.com/models)
import requests
import json
url = "https://modelslab.com/api/v6/images/text2img"
payload = json.dumps({
"key": "your_api_key",
"model_id": "protovision-xl-v6.6",
"prompt": "ultra realistic close up portrait ((beautiful pale cyberpunk female with heavy black eyeliner)), blue eyes, shaved side haircut, hyper detail, cinematic lighting, magic neon, dark red city, Canon EOS R3, nikon, f/1.4, ISO 200, 1/160s, 8K, RAW, unedited, symmetrical balance, in-frame, 8K",
"negative_prompt": "painting, extra fingers, mutated hands, poorly drawn hands, poorly drawn face, deformed, ugly, blurry, bad anatomy, bad proportions, extra limbs, cloned face, skinny, glitchy, double torso, extra arms, extra hands, mangled fingers, missing lips, ugly face, distorted face, extra legs, anime",
"width": "512",
"height": "512",
"samples": "1",
"num_inference_steps": "30",
"safety_checker": "no",
"enhance_prompt": "yes",
"seed": None,
"guidance_scale": 7.5,
"multi_lingual": "no",
"panorama": "no",
"self_attention": "no",
"upscale": "no",
"embeddings": "embeddings_model_id",
"lora": "lora_model_id",
"webhook": None,
"track_id": None
})
headers = {
'Content-Type': 'application/json'
}
response = requests.request("POST", url, headers=headers, data=payload)
print(response.text)
> Use this coupon code to get 25% off **DMGG0RBN**
|
{"license": "creativeml-openrail-m", "tags": ["modelslab.com", "stable-diffusion-api", "text-to-image", "ultra-realistic"], "pinned": true}
|
stablediffusionapi/protovision-xl-v6.6
| null |
[
"diffusers",
"modelslab.com",
"stable-diffusion-api",
"text-to-image",
"ultra-realistic",
"license:creativeml-openrail-m",
"endpoints_compatible",
"diffusers:StableDiffusionXLPipeline",
"region:us"
] | null |
2024-04-13T09:52:35+00:00
|
[] |
[] |
TAGS
#diffusers #modelslab.com #stable-diffusion-api #text-to-image #ultra-realistic #license-creativeml-openrail-m #endpoints_compatible #diffusers-StableDiffusionXLPipeline #region-us
|
# API Inference
!generated from URL
## Get API Key
Get API key from ModelsLab API, No Payment needed.
Replace Key in below code, change model_id to "protovision-xl-v6.6"
Coding in PHP/Node/Java etc? Have a look at docs for more code examples: View docs
Try model for free: Generate Images
Model link: View model
View all models: View Models
import requests
import json
url = "URL
payload = URL({
"key": "your_api_key",
"model_id": "protovision-xl-v6.6",
"prompt": "ultra realistic close up portrait ((beautiful pale cyberpunk female with heavy black eyeliner)), blue eyes, shaved side haircut, hyper detail, cinematic lighting, magic neon, dark red city, Canon EOS R3, nikon, f/1.4, ISO 200, 1/160s, 8K, RAW, unedited, symmetrical balance, in-frame, 8K",
"negative_prompt": "painting, extra fingers, mutated hands, poorly drawn hands, poorly drawn face, deformed, ugly, blurry, bad anatomy, bad proportions, extra limbs, cloned face, skinny, glitchy, double torso, extra arms, extra hands, mangled fingers, missing lips, ugly face, distorted face, extra legs, anime",
"width": "512",
"height": "512",
"samples": "1",
"num_inference_steps": "30",
"safety_checker": "no",
"enhance_prompt": "yes",
"seed": None,
"guidance_scale": 7.5,
"multi_lingual": "no",
"panorama": "no",
"self_attention": "no",
"upscale": "no",
"embeddings": "embeddings_model_id",
"lora": "lora_model_id",
"webhook": None,
"track_id": None
})
headers = {
'Content-Type': 'application/json'
}
response = requests.request("POST", url, headers=headers, data=payload)
print(URL)
> Use this coupon code to get 25% off DMGG0RBN
|
[
"# API Inference\n\n!generated from URL",
"## Get API Key\n\nGet API key from ModelsLab API, No Payment needed. \n\nReplace Key in below code, change model_id to \"protovision-xl-v6.6\"\n\nCoding in PHP/Node/Java etc? Have a look at docs for more code examples: View docs\n\nTry model for free: Generate Images\n\nModel link: View model\n\nView all models: View Models\n\n import requests \n import json \n \n url = \"URL \n \n payload = URL({ \n \"key\": \"your_api_key\", \n \"model_id\": \"protovision-xl-v6.6\", \n \"prompt\": \"ultra realistic close up portrait ((beautiful pale cyberpunk female with heavy black eyeliner)), blue eyes, shaved side haircut, hyper detail, cinematic lighting, magic neon, dark red city, Canon EOS R3, nikon, f/1.4, ISO 200, 1/160s, 8K, RAW, unedited, symmetrical balance, in-frame, 8K\", \n \"negative_prompt\": \"painting, extra fingers, mutated hands, poorly drawn hands, poorly drawn face, deformed, ugly, blurry, bad anatomy, bad proportions, extra limbs, cloned face, skinny, glitchy, double torso, extra arms, extra hands, mangled fingers, missing lips, ugly face, distorted face, extra legs, anime\", \n \"width\": \"512\", \n \"height\": \"512\", \n \"samples\": \"1\", \n \"num_inference_steps\": \"30\", \n \"safety_checker\": \"no\", \n \"enhance_prompt\": \"yes\", \n \"seed\": None, \n \"guidance_scale\": 7.5, \n \"multi_lingual\": \"no\", \n \"panorama\": \"no\", \n \"self_attention\": \"no\", \n \"upscale\": \"no\", \n \"embeddings\": \"embeddings_model_id\", \n \"lora\": \"lora_model_id\", \n \"webhook\": None, \n \"track_id\": None \n }) \n \n headers = { \n 'Content-Type': 'application/json' \n } \n \n response = requests.request(\"POST\", url, headers=headers, data=payload) \n \n print(URL)\n\n> Use this coupon code to get 25% off DMGG0RBN"
] |
[
"TAGS\n#diffusers #modelslab.com #stable-diffusion-api #text-to-image #ultra-realistic #license-creativeml-openrail-m #endpoints_compatible #diffusers-StableDiffusionXLPipeline #region-us \n",
"# API Inference\n\n!generated from URL",
"## Get API Key\n\nGet API key from ModelsLab API, No Payment needed. \n\nReplace Key in below code, change model_id to \"protovision-xl-v6.6\"\n\nCoding in PHP/Node/Java etc? Have a look at docs for more code examples: View docs\n\nTry model for free: Generate Images\n\nModel link: View model\n\nView all models: View Models\n\n import requests \n import json \n \n url = \"URL \n \n payload = URL({ \n \"key\": \"your_api_key\", \n \"model_id\": \"protovision-xl-v6.6\", \n \"prompt\": \"ultra realistic close up portrait ((beautiful pale cyberpunk female with heavy black eyeliner)), blue eyes, shaved side haircut, hyper detail, cinematic lighting, magic neon, dark red city, Canon EOS R3, nikon, f/1.4, ISO 200, 1/160s, 8K, RAW, unedited, symmetrical balance, in-frame, 8K\", \n \"negative_prompt\": \"painting, extra fingers, mutated hands, poorly drawn hands, poorly drawn face, deformed, ugly, blurry, bad anatomy, bad proportions, extra limbs, cloned face, skinny, glitchy, double torso, extra arms, extra hands, mangled fingers, missing lips, ugly face, distorted face, extra legs, anime\", \n \"width\": \"512\", \n \"height\": \"512\", \n \"samples\": \"1\", \n \"num_inference_steps\": \"30\", \n \"safety_checker\": \"no\", \n \"enhance_prompt\": \"yes\", \n \"seed\": None, \n \"guidance_scale\": 7.5, \n \"multi_lingual\": \"no\", \n \"panorama\": \"no\", \n \"self_attention\": \"no\", \n \"upscale\": \"no\", \n \"embeddings\": \"embeddings_model_id\", \n \"lora\": \"lora_model_id\", \n \"webhook\": None, \n \"track_id\": None \n }) \n \n headers = { \n 'Content-Type': 'application/json' \n } \n \n response = requests.request(\"POST\", url, headers=headers, data=payload) \n \n print(URL)\n\n> Use this coupon code to get 25% off DMGG0RBN"
] |
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. -->
# llama-sft-qat
This model is a fine-tuned version of [meta-llama/Llama-2-7b-chat-hf](https://huggingface.co/meta-llama/Llama-2-7b-chat-hf) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1851
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0002
- train_batch_size: 3
- eval_batch_size: 24
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 2.8727 | 1.0 | 4 | 1.9824 |
| 2.0991 | 2.0 | 8 | 1.3412 |
| 1.5585 | 3.0 | 12 | 0.7900 |
| 0.8816 | 4.0 | 16 | 0.5710 |
| 0.552 | 5.0 | 20 | 0.4502 |
| 0.552 | 6.0 | 24 | 0.3272 |
| 0.3661 | 7.0 | 28 | 0.2535 |
| 0.2903 | 8.0 | 32 | 0.2082 |
| 0.1619 | 9.0 | 36 | 0.1888 |
| 0.2003 | 10.0 | 40 | 0.1851 |
### Framework versions
- PEFT 0.7.1
- Transformers 4.38.2
- Pytorch 2.1.0+cu118
- Datasets 2.18.0
- Tokenizers 0.15.2
|
{"license": "llama2", "library_name": "peft", "tags": ["trl", "sft", "alignment-handbook", "generated_from_trainer"], "base_model": "meta-llama/Llama-2-7b-chat-hf", "model-index": [{"name": "llama-sft-qat", "results": []}]}
|
chanchan7/llama-sft-qat
| null |
[
"peft",
"tensorboard",
"safetensors",
"llama",
"trl",
"sft",
"alignment-handbook",
"generated_from_trainer",
"base_model:meta-llama/Llama-2-7b-chat-hf",
"license:llama2",
"4-bit",
"region:us"
] | null |
2024-04-13T09:54:08+00:00
|
[] |
[] |
TAGS
#peft #tensorboard #safetensors #llama #trl #sft #alignment-handbook #generated_from_trainer #base_model-meta-llama/Llama-2-7b-chat-hf #license-llama2 #4-bit #region-us
|
llama-sft-qat
=============
This model is a fine-tuned version of meta-llama/Llama-2-7b-chat-hf on an unknown dataset.
It achieves the following results on the evaluation set:
* Loss: 0.1851
Model description
-----------------
More information needed
Intended uses & limitations
---------------------------
More information needed
Training and evaluation data
----------------------------
More information needed
Training procedure
------------------
### Training hyperparameters
The following hyperparameters were used during training:
* learning\_rate: 0.0002
* train\_batch\_size: 3
* eval\_batch\_size: 24
* seed: 42
* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
* lr\_scheduler\_type: cosine
* lr\_scheduler\_warmup\_ratio: 0.1
* num\_epochs: 10
* mixed\_precision\_training: Native AMP
### Training results
### Framework versions
* PEFT 0.7.1
* Transformers 4.38.2
* Pytorch 2.1.0+cu118
* Datasets 2.18.0
* Tokenizers 0.15.2
|
[
"### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0002\n* train\\_batch\\_size: 3\n* eval\\_batch\\_size: 24\n* seed: 42\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: 10\n* mixed\\_precision\\_training: Native AMP",
"### Training results",
"### Framework versions\n\n\n* PEFT 0.7.1\n* Transformers 4.38.2\n* Pytorch 2.1.0+cu118\n* Datasets 2.18.0\n* Tokenizers 0.15.2"
] |
[
"TAGS\n#peft #tensorboard #safetensors #llama #trl #sft #alignment-handbook #generated_from_trainer #base_model-meta-llama/Llama-2-7b-chat-hf #license-llama2 #4-bit #region-us \n",
"### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0002\n* train\\_batch\\_size: 3\n* eval\\_batch\\_size: 24\n* seed: 42\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: 10\n* mixed\\_precision\\_training: Native AMP",
"### Training results",
"### Framework versions\n\n\n* PEFT 0.7.1\n* Transformers 4.38.2\n* Pytorch 2.1.0+cu118\n* Datasets 2.18.0\n* Tokenizers 0.15.2"
] |
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. -->
# 0.0001_idpo_same_3iters_iter_3
This model is a fine-tuned version of [ShenaoZ/0.0001_idpo_same_3iters_iter_2](https://huggingface.co/ShenaoZ/0.0001_idpo_same_3iters_iter_2) on the updated and the original datasets.
## 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: 2
- eval_batch_size: 2
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- gradient_accumulation_steps: 8
- total_train_batch_size: 128
- total_eval_batch_size: 16
- 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": ["updated", "original"], "base_model": "ShenaoZ/0.0001_idpo_same_3iters_iter_2", "model-index": [{"name": "0.0001_idpo_same_3iters_iter_3", "results": []}]}
|
ShenaoZ/0.0001_idpo_same_3iters_iter_3
| null |
[
"transformers",
"safetensors",
"mistral",
"text-generation",
"alignment-handbook",
"generated_from_trainer",
"trl",
"dpo",
"conversational",
"dataset:updated",
"dataset:original",
"base_model:ShenaoZ/0.0001_idpo_same_3iters_iter_2",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null |
2024-04-13T09:54:12+00:00
|
[] |
[] |
TAGS
#transformers #safetensors #mistral #text-generation #alignment-handbook #generated_from_trainer #trl #dpo #conversational #dataset-updated #dataset-original #base_model-ShenaoZ/0.0001_idpo_same_3iters_iter_2 #license-mit #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us
|
# 0.0001_idpo_same_3iters_iter_3
This model is a fine-tuned version of ShenaoZ/0.0001_idpo_same_3iters_iter_2 on the updated and the original datasets.
## 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: 2
- eval_batch_size: 2
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- gradient_accumulation_steps: 8
- total_train_batch_size: 128
- total_eval_batch_size: 16
- 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
|
[
"# 0.0001_idpo_same_3iters_iter_3\n\nThis model is a fine-tuned version of ShenaoZ/0.0001_idpo_same_3iters_iter_2 on the updated and the original datasets.",
"## 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-07\n- train_batch_size: 2\n- eval_batch_size: 2\n- seed: 42\n- distributed_type: multi-GPU\n- num_devices: 8\n- gradient_accumulation_steps: 8\n- total_train_batch_size: 128\n- total_eval_batch_size: 16\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-updated #dataset-original #base_model-ShenaoZ/0.0001_idpo_same_3iters_iter_2 #license-mit #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n",
"# 0.0001_idpo_same_3iters_iter_3\n\nThis model is a fine-tuned version of ShenaoZ/0.0001_idpo_same_3iters_iter_2 on the updated and the original datasets.",
"## 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-07\n- train_batch_size: 2\n- eval_batch_size: 2\n- seed: 42\n- distributed_type: multi-GPU\n- num_devices: 8\n- gradient_accumulation_steps: 8\n- total_train_batch_size: 128\n- total_eval_batch_size: 16\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-classification
|
transformers
|
## Model description
- This model is trained on tweets from wildfire events between 2017 and 2021
- This model is based on [CrisisTransformer ](https://huggingface.co/crisistransformers/CT-M2-Complete) architecture
## Intended uses & limitations
The model is mostly intended to be used for inference of wildfire tweets to detect the urgency of the tweet.
Note that this model is primarily aimed at being used for inference on tweets and will only work within the limits of 514 character tweets.
## Usage
```python
from transformers import AutoTokenizer, AutoModelForSequenceClassification
tokenizer = AutoTokenizer.from_pretrained("Sabreen88/wildfire-CrisisT")
model = AutoModelForSequenceClassification.from_pretrained("Sabreen88/wildfire-CrisisT")
```
|
{"language": ["en"]}
|
Sabreen88/wildfire-CrisisT
| null |
[
"transformers",
"safetensors",
"roberta",
"text-classification",
"en",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | null |
2024-04-13T09:54:18+00:00
|
[] |
[
"en"
] |
TAGS
#transformers #safetensors #roberta #text-classification #en #autotrain_compatible #endpoints_compatible #region-us
|
## Model description
- This model is trained on tweets from wildfire events between 2017 and 2021
- This model is based on CrisisTransformer architecture
## Intended uses & limitations
The model is mostly intended to be used for inference of wildfire tweets to detect the urgency of the tweet.
Note that this model is primarily aimed at being used for inference on tweets and will only work within the limits of 514 character tweets.
## Usage
|
[
"## Model description\n\n- This model is trained on tweets from wildfire events between 2017 and 2021\n- This model is based on CrisisTransformer architecture",
"## Intended uses & limitations\n\nThe model is mostly intended to be used for inference of wildfire tweets to detect the urgency of the tweet.\n\nNote that this model is primarily aimed at being used for inference on tweets and will only work within the limits of 514 character tweets.",
"## Usage"
] |
[
"TAGS\n#transformers #safetensors #roberta #text-classification #en #autotrain_compatible #endpoints_compatible #region-us \n",
"## Model description\n\n- This model is trained on tweets from wildfire events between 2017 and 2021\n- This model is based on CrisisTransformer architecture",
"## Intended uses & limitations\n\nThe model is mostly intended to be used for inference of wildfire tweets to detect the urgency of the tweet.\n\nNote that this model is primarily aimed at being used for inference on tweets and will only work within the limits of 514 character tweets.",
"## Usage"
] |
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. -->
# flan-t5-xl-absa-laptops
This model is a fine-tuned version of [ybelkada/flan-t5-xl-sharded-bf16](https://huggingface.co/ybelkada/flan-t5-xl-sharded-bf16) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1812
## 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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 3.9772 | 0.9 | 200 | 0.7029 |
| 0.5108 | 1.8 | 400 | 0.3043 |
| 0.3323 | 2.7 | 600 | 0.2414 |
| 0.2935 | 3.6 | 800 | 0.2193 |
| 0.2529 | 4.5 | 1000 | 0.2077 |
| 0.2374 | 5.41 | 1200 | 0.1988 |
| 0.217 | 6.31 | 1400 | 0.1918 |
| 0.2088 | 7.21 | 1600 | 0.1896 |
| 0.2054 | 8.11 | 1800 | 0.1874 |
| 0.1979 | 9.01 | 2000 | 0.1822 |
| 0.1963 | 9.91 | 2200 | 0.1812 |
### Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
|
{"tags": ["generated_from_trainer"], "base_model": "ybelkada/flan-t5-xl-sharded-bf16", "model-index": [{"name": "flan-t5-xl-absa-laptops", "results": []}]}
|
Shakhovak/flan-t5-xl-absa-laptops
| null |
[
"generated_from_trainer",
"base_model:ybelkada/flan-t5-xl-sharded-bf16",
"region:us"
] | null |
2024-04-13T10:00:45+00:00
|
[] |
[] |
TAGS
#generated_from_trainer #base_model-ybelkada/flan-t5-xl-sharded-bf16 #region-us
|
flan-t5-xl-absa-laptops
=======================
This model is a fine-tuned version of ybelkada/flan-t5-xl-sharded-bf16 on an unknown dataset.
It achieves the following results on the evaluation set:
* Loss: 0.1812
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: 16
* eval\_batch\_size: 16
* seed: 42
* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
* lr\_scheduler\_type: linear
* lr\_scheduler\_warmup\_ratio: 0.1
* num\_epochs: 10
### Training results
### Framework versions
* Transformers 4.38.2
* Pytorch 2.2.1+cu121
* Datasets 2.18.0
* Tokenizers 0.15.2
|
[
"### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 5e-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* lr\\_scheduler\\_warmup\\_ratio: 0.1\n* num\\_epochs: 10",
"### Training results",
"### Framework versions\n\n\n* Transformers 4.38.2\n* Pytorch 2.2.1+cu121\n* Datasets 2.18.0\n* Tokenizers 0.15.2"
] |
[
"TAGS\n#generated_from_trainer #base_model-ybelkada/flan-t5-xl-sharded-bf16 #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: 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* lr\\_scheduler\\_warmup\\_ratio: 0.1\n* num\\_epochs: 10",
"### Training results",
"### Framework versions\n\n\n* Transformers 4.38.2\n* Pytorch 2.2.1+cu121\n* Datasets 2.18.0\n* Tokenizers 0.15.2"
] |
text-generation
|
transformers
|
# Model Card for Model ID
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
MoM: Mixture of Mixture
This Model is a first test to combine [Jamba](https://huggingface.co/ai21labs/Jamba-v0.1) architecture with 1.58 bits linear layers, mixture of attention head and mixture of depth.
The goal is to developpe and test if this kind of architectures have not too much quality loss for a fast inference.
- **Model type:** Mixture of attention head mixture of depth and mixture of expert 1.58bit linear layers
- **License:** Apache licence 2.0
### Model Sources [optional]
- **Repository:** https://github.com/ostix360/optimized-LLM
## How to Get Started with the Model
If you want to test this model please look at this repo at this [commit](https://github.com/ostix360/optimized-LLM/tree/7cc2e6f39b69864e0cc80ca8b767229c536e6793)
## Training Details
### Training Data
We use the first 100k data of Locutusque/UltraTextbooks to train this model
### Training Procedure
We use adam-8 bits with default betas and epsilon values
#### Preprocessing [optional]
The data fit the model max length i.e. 512 tokens
#### Training Hyperparameters
Please look at this file to see the hyperparameters
## Technical Specifications [optional]
### Compute Infrastructure
#### Hardware
- one 4070 ti GPU
#### Software
- pytorch, transformers etc
|
{"language": ["en"], "license": "apache-2.0", "library_name": "transformers", "tags": ["moe", "moah", "mod"], "datasets": ["Locutusque/UltraTextbooks"]}
|
Ostixe360/MoM-1.58bits-1B
| null |
[
"transformers",
"safetensors",
"text-generation",
"moe",
"moah",
"mod",
"en",
"dataset:Locutusque/UltraTextbooks",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | null |
2024-04-13T10:02:39+00:00
|
[] |
[
"en"
] |
TAGS
#transformers #safetensors #text-generation #moe #moah #mod #en #dataset-Locutusque/UltraTextbooks #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us
|
# Model Card for Model ID
## Model Details
### Model Description
MoM: Mixture of Mixture
This Model is a first test to combine Jamba architecture with 1.58 bits linear layers, mixture of attention head and mixture of depth.
The goal is to developpe and test if this kind of architectures have not too much quality loss for a fast inference.
- Model type: Mixture of attention head mixture of depth and mixture of expert 1.58bit linear layers
- License: Apache licence 2.0
### Model Sources [optional]
- Repository: URL
## How to Get Started with the Model
If you want to test this model please look at this repo at this commit
## Training Details
### Training Data
We use the first 100k data of Locutusque/UltraTextbooks to train this model
### Training Procedure
We use adam-8 bits with default betas and epsilon values
#### Preprocessing [optional]
The data fit the model max length i.e. 512 tokens
#### Training Hyperparameters
Please look at this file to see the hyperparameters
## Technical Specifications [optional]
### Compute Infrastructure
#### Hardware
- one 4070 ti GPU
#### Software
- pytorch, transformers etc
|
[
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nMoM: Mixture of Mixture\n\nThis Model is a first test to combine Jamba architecture with 1.58 bits linear layers, mixture of attention head and mixture of depth.\n\nThe goal is to developpe and test if this kind of architectures have not too much quality loss for a fast inference.\n\n\n- Model type: Mixture of attention head mixture of depth and mixture of expert 1.58bit linear layers \n- License: Apache licence 2.0",
"### Model Sources [optional]\n\n\n- Repository: URL",
"## How to Get Started with the Model\n\n\nIf you want to test this model please look at this repo at this commit",
"## Training Details",
"### Training Data\n\nWe use the first 100k data of Locutusque/UltraTextbooks to train this model",
"### Training Procedure\n\nWe use adam-8 bits with default betas and epsilon values",
"#### Preprocessing [optional]\n\n\nThe data fit the model max length i.e. 512 tokens",
"#### Training Hyperparameters\n\nPlease look at this file to see the hyperparameters",
"## Technical Specifications [optional]",
"### Compute Infrastructure",
"#### Hardware\n\n- one 4070 ti GPU",
"#### Software\n\n- pytorch, transformers etc"
] |
[
"TAGS\n#transformers #safetensors #text-generation #moe #moah #mod #en #dataset-Locutusque/UltraTextbooks #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us \n",
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nMoM: Mixture of Mixture\n\nThis Model is a first test to combine Jamba architecture with 1.58 bits linear layers, mixture of attention head and mixture of depth.\n\nThe goal is to developpe and test if this kind of architectures have not too much quality loss for a fast inference.\n\n\n- Model type: Mixture of attention head mixture of depth and mixture of expert 1.58bit linear layers \n- License: Apache licence 2.0",
"### Model Sources [optional]\n\n\n- Repository: URL",
"## How to Get Started with the Model\n\n\nIf you want to test this model please look at this repo at this commit",
"## Training Details",
"### Training Data\n\nWe use the first 100k data of Locutusque/UltraTextbooks to train this model",
"### Training Procedure\n\nWe use adam-8 bits with default betas and epsilon values",
"#### Preprocessing [optional]\n\n\nThe data fit the model max length i.e. 512 tokens",
"#### Training Hyperparameters\n\nPlease look at this file to see the hyperparameters",
"## Technical Specifications [optional]",
"### Compute Infrastructure",
"#### Hardware\n\n- one 4070 ti GPU",
"#### Software\n\n- pytorch, transformers etc"
] |
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": []}
|
binhK/mistral-7b-instv0.2-v0.1
| null |
[
"transformers",
"safetensors",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null |
2024-04-13T10:03:14+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/DarkForest-20B-v1.0-Q4_K_M-GGUF
This model was converted to GGUF format from [`TeeZee/DarkForest-20B-v1.0`](https://huggingface.co/TeeZee/DarkForest-20B-v1.0) 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/TeeZee/DarkForest-20B-v1.0) 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/DarkForest-20B-v1.0-Q4_K_M-GGUF --model darkforest-20b-v1.0.Q4_K_M.gguf -p "The meaning to life and the universe is"
```
Server:
```bash
llama-server --hf-repo DavidAU/DarkForest-20B-v1.0-Q4_K_M-GGUF --model darkforest-20b-v1.0.Q4_K_M.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 darkforest-20b-v1.0.Q4_K_M.gguf -n 128
```
|
{"license": "other", "tags": ["merge", "not-for-all-audiences", "llama-cpp", "gguf-my-repo"], "license_name": "microsoft-research-license"}
|
DavidAU/DarkForest-20B-v1.0-Q4_K_M-GGUF
| null |
[
"gguf",
"merge",
"not-for-all-audiences",
"llama-cpp",
"gguf-my-repo",
"license:other",
"region:us"
] | null |
2024-04-13T10:03:16+00:00
|
[] |
[] |
TAGS
#gguf #merge #not-for-all-audiences #llama-cpp #gguf-my-repo #license-other #region-us
|
# DavidAU/DarkForest-20B-v1.0-Q4_K_M-GGUF
This model was converted to GGUF format from 'TeeZee/DarkForest-20B-v1.0' 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/DarkForest-20B-v1.0-Q4_K_M-GGUF\nThis model was converted to GGUF format from 'TeeZee/DarkForest-20B-v1.0' 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 #not-for-all-audiences #llama-cpp #gguf-my-repo #license-other #region-us \n",
"# DavidAU/DarkForest-20B-v1.0-Q4_K_M-GGUF\nThis model was converted to GGUF format from 'TeeZee/DarkForest-20B-v1.0' 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."
] |
image-classification
|
transformers
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# Psoriasis-Project-M-vit-large-patch16-224-in21k
This model is a fine-tuned version of [google/vit-large-patch16-224-in21k](https://huggingface.co/google/vit-large-patch16-224-in21k) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2704
- Accuracy: 0.9375
## 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: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 5
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| No log | 0.92 | 6 | 1.1518 | 0.7083 |
| 1.4225 | 2.0 | 13 | 0.5772 | 0.875 |
| 1.4225 | 2.92 | 19 | 0.3717 | 0.9167 |
| 0.4431 | 4.0 | 26 | 0.2775 | 0.9375 |
| 0.1332 | 4.62 | 30 | 0.2704 | 0.9375 |
### Framework versions
- Transformers 4.39.3
- Pytorch 2.1.2
- Datasets 2.18.0
- Tokenizers 0.15.2
|
{"license": "apache-2.0", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "google/vit-large-patch16-224-in21k", "model-index": [{"name": "Psoriasis-Project-M-vit-large-patch16-224-in21k", "results": []}]}
|
ahmedesmail16/Psoriasis-Project-M-vit-large-patch16-224-in21k
| null |
[
"transformers",
"tensorboard",
"safetensors",
"vit",
"image-classification",
"generated_from_trainer",
"base_model:google/vit-large-patch16-224-in21k",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | null |
2024-04-13T10:04:15+00:00
|
[] |
[] |
TAGS
#transformers #tensorboard #safetensors #vit #image-classification #generated_from_trainer #base_model-google/vit-large-patch16-224-in21k #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us
|
Psoriasis-Project-M-vit-large-patch16-224-in21k
===============================================
This model is a fine-tuned version of google/vit-large-patch16-224-in21k on an unknown dataset.
It achieves the following results on the evaluation set:
* Loss: 0.2704
* Accuracy: 0.9375
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: 16
* eval\_batch\_size: 16
* seed: 42
* gradient\_accumulation\_steps: 4
* total\_train\_batch\_size: 64
* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
* lr\_scheduler\_type: linear
* lr\_scheduler\_warmup\_ratio: 0.1
* num\_epochs: 5
### Training results
### Framework versions
* Transformers 4.39.3
* 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: 5e-05\n* train\\_batch\\_size: 16\n* eval\\_batch\\_size: 16\n* seed: 42\n* gradient\\_accumulation\\_steps: 4\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\\_ratio: 0.1\n* num\\_epochs: 5",
"### Training results",
"### Framework versions\n\n\n* Transformers 4.39.3\n* Pytorch 2.1.2\n* Datasets 2.18.0\n* Tokenizers 0.15.2"
] |
[
"TAGS\n#transformers #tensorboard #safetensors #vit #image-classification #generated_from_trainer #base_model-google/vit-large-patch16-224-in21k #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: 16\n* eval\\_batch\\_size: 16\n* seed: 42\n* gradient\\_accumulation\\_steps: 4\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\\_ratio: 0.1\n* num\\_epochs: 5",
"### Training results",
"### Framework versions\n\n\n* Transformers 4.39.3\n* Pytorch 2.1.2\n* Datasets 2.18.0\n* Tokenizers 0.15.2"
] |
reinforcement-learning
| null |
# **Q-Learning** Agent playing1 **FrozenLake-v1**
This is a trained model of a **Q-Learning** agent playing **FrozenLake-v1** .
## Usage
```python
model = load_from_hub(repo_id="Frankhuhu/q-FrozenLake-v1-4x4-noSlippery", filename="q-learning.pkl")
# Don't forget to check if you need to add additional attributes (is_slippery=False etc)
env = gym.make(model["env_id"])
```
|
{"tags": ["FrozenLake-v1-4x4-no_slippery", "q-learning", "reinforcement-learning", "custom-implementation"], "model-index": [{"name": "q-FrozenLake-v1-4x4-noSlippery", "results": [{"task": {"type": "reinforcement-learning", "name": "reinforcement-learning"}, "dataset": {"name": "FrozenLake-v1-4x4-no_slippery", "type": "FrozenLake-v1-4x4-no_slippery"}, "metrics": [{"type": "mean_reward", "value": "1.00 +/- 0.00", "name": "mean_reward", "verified": false}]}]}]}
|
Frankhuhu/q-FrozenLake-v1-4x4-noSlippery
| null |
[
"FrozenLake-v1-4x4-no_slippery",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
] | null |
2024-04-13T10:04:35+00:00
|
[] |
[] |
TAGS
#FrozenLake-v1-4x4-no_slippery #q-learning #reinforcement-learning #custom-implementation #model-index #region-us
|
# Q-Learning Agent playing1 FrozenLake-v1
This is a trained model of a Q-Learning agent playing FrozenLake-v1 .
## Usage
|
[
"# Q-Learning Agent playing1 FrozenLake-v1\n This is a trained model of a Q-Learning agent playing FrozenLake-v1 .\n\n ## Usage"
] |
[
"TAGS\n#FrozenLake-v1-4x4-no_slippery #q-learning #reinforcement-learning #custom-implementation #model-index #region-us \n",
"# Q-Learning Agent playing1 FrozenLake-v1\n This is a trained model of a Q-Learning agent playing FrozenLake-v1 .\n\n ## Usage"
] |
null |
transformers
|
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
|
{"library_name": "transformers", "tags": []}
|
bakch92/bloomz-peft-prompt-tunning
| null |
[
"transformers",
"safetensors",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null |
2024-04-13T10:05:15+00:00
|
[
"1910.09700"
] |
[] |
TAGS
#transformers #safetensors #arxiv-1910.09700 #endpoints_compatible #region-us
|
# Model Card for Model ID
## Model Details
### Model Description
This is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.
- Developed by:
- Funded by [optional]:
- Shared by [optional]:
- Model type:
- Language(s) (NLP):
- License:
- Finetuned from model [optional]:
### Model Sources [optional]
- Repository:
- Paper [optional]:
- Demo [optional]:
## Uses
### Direct Use
### Downstream Use [optional]
### Out-of-Scope Use
## Bias, Risks, and Limitations
### Recommendations
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
## Training Details
### Training Data
### Training Procedure
#### Preprocessing [optional]
#### Training Hyperparameters
- Training regime:
#### Speeds, Sizes, Times [optional]
## Evaluation
### Testing Data, Factors & Metrics
#### Testing Data
#### Factors
#### Metrics
### Results
#### Summary
## Model Examination [optional]
## Environmental Impact
Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).
- Hardware Type:
- Hours used:
- Cloud Provider:
- Compute Region:
- Carbon Emitted:
## Technical Specifications [optional]
### Model Architecture and Objective
### Compute Infrastructure
#### Hardware
#### Software
[optional]
BibTeX:
APA:
## Glossary [optional]
## More Information [optional]
## Model Card Authors [optional]
## Model Card Contact
|
[
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.",
"## How to Get Started with the Model\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] |
[
"TAGS\n#transformers #safetensors #arxiv-1910.09700 #endpoints_compatible #region-us \n",
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.",
"## How to Get Started with the Model\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] |
text-generation
|
transformers
|
<!-- 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_dataup_noreplacerej_40g_bs2_iter_3
This model is a fine-tuned version of [ZhangShenao/0.0_dataup_noreplacerej_40g_bs2_iter_2](https://huggingface.co/ZhangShenao/0.0_dataup_noreplacerej_40g_bs2_iter_2) on the ZhangShenao/0.0_dataup_noreplacerej_40g_bs2_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: 5e-07
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- gradient_accumulation_steps: 8
- total_train_batch_size: 128
- total_eval_batch_size: 16
- 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_dataup_noreplacerej_40g_bs2_dataset"], "base_model": "ZhangShenao/0.0_dataup_noreplacerej_40g_bs2_iter_2", "model-index": [{"name": "0.0_dataup_noreplacerej_40g_bs2_iter_3", "results": []}]}
|
ZhangShenao/0.0_dataup_noreplacerej_40g_bs2_iter_3
| null |
[
"transformers",
"safetensors",
"mistral",
"text-generation",
"alignment-handbook",
"generated_from_trainer",
"trl",
"dpo",
"conversational",
"dataset:ZhangShenao/0.0_dataup_noreplacerej_40g_bs2_dataset",
"base_model:ZhangShenao/0.0_dataup_noreplacerej_40g_bs2_iter_2",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null |
2024-04-13T10:08:58+00:00
|
[] |
[] |
TAGS
#transformers #safetensors #mistral #text-generation #alignment-handbook #generated_from_trainer #trl #dpo #conversational #dataset-ZhangShenao/0.0_dataup_noreplacerej_40g_bs2_dataset #base_model-ZhangShenao/0.0_dataup_noreplacerej_40g_bs2_iter_2 #license-mit #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us
|
# 0.0_dataup_noreplacerej_40g_bs2_iter_3
This model is a fine-tuned version of ZhangShenao/0.0_dataup_noreplacerej_40g_bs2_iter_2 on the ZhangShenao/0.0_dataup_noreplacerej_40g_bs2_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: 5e-07
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- gradient_accumulation_steps: 8
- total_train_batch_size: 128
- total_eval_batch_size: 16
- 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_dataup_noreplacerej_40g_bs2_iter_3\n\nThis model is a fine-tuned version of ZhangShenao/0.0_dataup_noreplacerej_40g_bs2_iter_2 on the ZhangShenao/0.0_dataup_noreplacerej_40g_bs2_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: 5e-07\n- train_batch_size: 2\n- eval_batch_size: 2\n- seed: 42\n- distributed_type: multi-GPU\n- num_devices: 8\n- gradient_accumulation_steps: 8\n- total_train_batch_size: 128\n- total_eval_batch_size: 16\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_dataup_noreplacerej_40g_bs2_dataset #base_model-ZhangShenao/0.0_dataup_noreplacerej_40g_bs2_iter_2 #license-mit #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n",
"# 0.0_dataup_noreplacerej_40g_bs2_iter_3\n\nThis model is a fine-tuned version of ZhangShenao/0.0_dataup_noreplacerej_40g_bs2_iter_2 on the ZhangShenao/0.0_dataup_noreplacerej_40g_bs2_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: 5e-07\n- train_batch_size: 2\n- eval_batch_size: 2\n- seed: 42\n- distributed_type: multi-GPU\n- num_devices: 8\n- gradient_accumulation_steps: 8\n- total_train_batch_size: 128\n- total_eval_batch_size: 16\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"
] |
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. -->
# Electra-finetuned-ChennaiQA-final
This model is a fine-tuned version of [google/electra-base-discriminator](https://huggingface.co/google/electra-base-discriminator) on the None dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 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: 15
### Training results
### Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
|
{"license": "apache-2.0", "tags": ["generated_from_trainer"], "base_model": "google/electra-base-discriminator", "model-index": [{"name": "Albert-finetuned-ChennaiQA-final", "results": []}]}
|
aditi2212/Electra-finetuned-ChennaiQA-final
| null |
[
"transformers",
"tensorboard",
"safetensors",
"electra",
"question-answering",
"generated_from_trainer",
"base_model:google/electra-base-discriminator",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null |
2024-04-13T10:10:21+00:00
|
[] |
[] |
TAGS
#transformers #tensorboard #safetensors #electra #question-answering #generated_from_trainer #base_model-google/electra-base-discriminator #license-apache-2.0 #endpoints_compatible #region-us
|
# Electra-finetuned-ChennaiQA-final
This model is a fine-tuned version of google/electra-base-discriminator on the None dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 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: 15
### Training results
### Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
|
[
"# Electra-finetuned-ChennaiQA-final\n\nThis model is a fine-tuned version of google/electra-base-discriminator on the None 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: 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: 15",
"### Training results",
"### Framework versions\n\n- Transformers 4.38.2\n- Pytorch 2.2.1+cu121\n- Datasets 2.18.0\n- Tokenizers 0.15.2"
] |
[
"TAGS\n#transformers #tensorboard #safetensors #electra #question-answering #generated_from_trainer #base_model-google/electra-base-discriminator #license-apache-2.0 #endpoints_compatible #region-us \n",
"# Electra-finetuned-ChennaiQA-final\n\nThis model is a fine-tuned version of google/electra-base-discriminator on the None 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: 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: 15",
"### Training results",
"### Framework versions\n\n- Transformers 4.38.2\n- Pytorch 2.2.1+cu121\n- Datasets 2.18.0\n- Tokenizers 0.15.2"
] |
null |
transformers
|
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
|
{"library_name": "transformers", "tags": []}
|
eix9mm/llm_pr_model_5
| null |
[
"transformers",
"safetensors",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null |
2024-04-13T10:10:23+00:00
|
[
"1910.09700"
] |
[] |
TAGS
#transformers #safetensors #arxiv-1910.09700 #endpoints_compatible #region-us
|
# Model Card for Model ID
## Model Details
### Model Description
This is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.
- Developed by:
- Funded by [optional]:
- Shared by [optional]:
- Model type:
- Language(s) (NLP):
- License:
- Finetuned from model [optional]:
### Model Sources [optional]
- Repository:
- Paper [optional]:
- Demo [optional]:
## Uses
### Direct Use
### Downstream Use [optional]
### Out-of-Scope Use
## Bias, Risks, and Limitations
### Recommendations
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
## Training Details
### Training Data
### Training Procedure
#### Preprocessing [optional]
#### Training Hyperparameters
- Training regime:
#### Speeds, Sizes, Times [optional]
## Evaluation
### Testing Data, Factors & Metrics
#### Testing Data
#### Factors
#### Metrics
### Results
#### Summary
## Model Examination [optional]
## Environmental Impact
Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).
- Hardware Type:
- Hours used:
- Cloud Provider:
- Compute Region:
- Carbon Emitted:
## Technical Specifications [optional]
### Model Architecture and Objective
### Compute Infrastructure
#### Hardware
#### Software
[optional]
BibTeX:
APA:
## Glossary [optional]
## More Information [optional]
## Model Card Authors [optional]
## Model Card Contact
|
[
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.",
"## How to Get Started with the Model\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] |
[
"TAGS\n#transformers #safetensors #arxiv-1910.09700 #endpoints_compatible #region-us \n",
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.",
"## How to Get Started with the Model\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] |
reinforcement-learning
| null |
# **Q-Learning** Agent playing1 **Taxi-v3**
This is a trained model of a **Q-Learning** agent playing **Taxi-v3** .
## Usage
```python
model = load_from_hub(repo_id="Frankhuhu/Taxi-V3", filename="q-learning.pkl")
# Don't forget to check if you need to add additional attributes (is_slippery=False etc)
env = gym.make(model["env_id"])
```
|
{"tags": ["Taxi-v3", "q-learning", "reinforcement-learning", "custom-implementation"], "model-index": [{"name": "Taxi-V3", "results": [{"task": {"type": "reinforcement-learning", "name": "reinforcement-learning"}, "dataset": {"name": "Taxi-v3", "type": "Taxi-v3"}, "metrics": [{"type": "mean_reward", "value": "7.50 +/- 2.63", "name": "mean_reward", "verified": false}]}]}]}
|
Frankhuhu/Taxi-V3
| null |
[
"Taxi-v3",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
] | null |
2024-04-13T10:11:05+00:00
|
[] |
[] |
TAGS
#Taxi-v3 #q-learning #reinforcement-learning #custom-implementation #model-index #region-us
|
# Q-Learning Agent playing1 Taxi-v3
This is a trained model of a Q-Learning agent playing Taxi-v3 .
## Usage
|
[
"# Q-Learning Agent playing1 Taxi-v3\n This is a trained model of a Q-Learning agent playing Taxi-v3 .\n\n ## Usage"
] |
[
"TAGS\n#Taxi-v3 #q-learning #reinforcement-learning #custom-implementation #model-index #region-us \n",
"# Q-Learning Agent playing1 Taxi-v3\n This is a trained model of a Q-Learning agent playing Taxi-v3 .\n\n ## Usage"
] |
reinforcement-learning
|
stable-baselines3
|
# **PPO** Agent playing **LunarLander-v2**
This is a trained model of a **PPO** agent playing **LunarLander-v2**
using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
## Usage (with Stable-baselines3)
TODO: Add your code
```python
from stable_baselines3 import ...
from huggingface_sb3 import load_from_hub
...
```
|
{"library_name": "stable-baselines3", "tags": ["LunarLander-v2", "deep-reinforcement-learning", "reinforcement-learning", "stable-baselines3"], "model-index": [{"name": "PPO", "results": [{"task": {"type": "reinforcement-learning", "name": "reinforcement-learning"}, "dataset": {"name": "LunarLander-v2", "type": "LunarLander-v2"}, "metrics": [{"type": "mean_reward", "value": "270.70 +/- 34.59", "name": "mean_reward", "verified": false}]}]}]}
|
fxnta10/ppo-LunarLander-v2
| null |
[
"stable-baselines3",
"LunarLander-v2",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] | null |
2024-04-13T10:11:57+00:00
|
[] |
[] |
TAGS
#stable-baselines3 #LunarLander-v2 #deep-reinforcement-learning #reinforcement-learning #model-index #region-us
|
# PPO Agent playing LunarLander-v2
This is a trained model of a PPO agent playing LunarLander-v2
using the stable-baselines3 library.
## Usage (with Stable-baselines3)
TODO: Add your code
|
[
"# PPO Agent playing LunarLander-v2\nThis is a trained model of a PPO agent playing LunarLander-v2\nusing the stable-baselines3 library.",
"## Usage (with Stable-baselines3)\nTODO: Add your code"
] |
[
"TAGS\n#stable-baselines3 #LunarLander-v2 #deep-reinforcement-learning #reinforcement-learning #model-index #region-us \n",
"# PPO Agent playing LunarLander-v2\nThis is a trained model of a PPO agent playing LunarLander-v2\nusing the stable-baselines3 library.",
"## Usage (with Stable-baselines3)\nTODO: Add your code"
] |
text-generation
|
transformers
|
# GreenBit LLMs
This is GreenBitAI's pretrained **low-bit** LLMs with extreme compression yet still strong performance.
Please refer to our [Github page](https://github.com/GreenBitAI/green-bit-llm) for the code to run the model and more information.
### Zero-shot Evaluation
We evaluate the zero-shot ability of low-bit quantized Qwen1.5 models using the `llm_eval` library and list the results below:
| **Repository (Qwen Family)** | **Avg Acc.** | **OpenBQ** | **ARC-E** | **Winogr.** | **HellaS.** | **ARC-C** | **PIQA** | **BoolQ** | **RACE** | **ANLI-R1** | **ANLI-R2** | **ANLI-R3** | **WiC** |
|:----------------------------------|:------------:|:------------:|:-----------:|:-------------:|:-------------:|:-----------:|:----------:|:-----------:|:-----------:|:-------------:|:-------------:|:-------------:|:---------:|
| `Qwen-1.5-0.5B-layer-mix-bpw-2.2` | 0.398 | 0.170 | 0.443 | 0.527 | 0.332 | 0.238 | 0.634 | 0.620 | 0.318 | 0.332 | 0.338 | 0.330 | 0.500 |
| `Qwen-1.5-0.5B-layer-mix-bpw-2.5` | 0.394 | 0.170 | 0.514 | 0.541 | 0.337 | 0.232 | 0.637 | 0.496 | 0.318 | 0.316 | 0.358 | 0.326 | 0.490 |
| `Qwen-1.5-0.5B-layer-mix-bpw-3.0` | 0.407 | 0.198 | 0.533 | 0.536 | 0.348 | 0.234 | 0.671 | 0.552 | 0.323 | 0.330 | 0.333 | 0.335 | 0.495 |
| `Qwen-1.5-1.8B-layer-mix-bpw-2.2` | 0.415 | 0.218 | 0.539 | 0.586 | 0.392 | 0.260 | 0.678 | 0.622 | 0.333 | 0.333 | 0.333 | 0.336 | 0.464 |
| `Qwen-1.5-1.8B-layer-mix-bpw-2.5` | 0.423 | 0.222 | 0.592 | 0.585 | 0.406 | 0.267 | 0.695 | 0.629 | 0.336 | 0.314 | 0.339 | 0.361 | 0.507 |
| `Qwen-1.5-1.8B-layer-mix-bpw-3.0` | 0.438 | 0.246 | 0.576 | 0.563 | 0.413 | 0.277 | 0.694 | 0.645 | 0.352 | 0.323 | 0.336 | 0.343 | 0.492 |
| `Qwen-1.5-4B-layer-mix-bpw-2.2` | 0.480 | 0.254 | 0.663 | 0.623 | 0.463 | 0.339 | 0.712 | 0.718 | 0.349 | 0.326 | 0.355 | 0.384 | 0.513 |
| `Qwen-1.5-4B-layer-mix-bpw-2.5` | 0.490 | 0.266 | 0.677 | 0.629 | 0.473 | 0.365 | 0.732 | 0.717 | 0.351 | 0.372 | 0.352 | 0.360 | 0.502 |
| `Qwen-1.5-4B-layer-mix-bpw-3.0` | 0.502 | 0.268 | 0.678 | 0.642 | 0.494 | 0.358 | 0.755 | 0.757 | 0.380 | 0.395 | 0.395 | 0.392 | 0.519 |
| `Qwen-1.5-7B-layer-mix-bpw-2.2` | 0.513 | 0.278 | 0.669 | 0.654 | 0.504 | 0.389 | 0.741 | 0.759 | 0.376 | 0.383 | 0.410 | 0.403 | 0.517 |
| `Qwen-1.5-7B-layer-mix-bpw-2.5` | 0.520 | 0.294 | 0.705 | 0.650 | 0.520 | 0.387 | 0.750 | 0.769 | 0.371 | 0.445 | 0.424 | 0.398 | 0.564 |
| `Qwen-1.5-7B-layer-mix-bpw-3.0` | 0.531 | 0.292 | 0.713 | 0.654 | 0.545 | 0.405 | 0.764 | 0.807 | 0.383 | 0.424 | 0.393 | 0.414 | 0.627 |
| `Qwen-1.5-14B-layer-mix-bpw-2.5` | 0.553 | 0.318 | 0.727 | 0.682 | 0.564 | 0.413 | 0.775 | 0.792 | 0.390 | 0.472 | 0.434 | 0.446 | 0.623 |
| `Qwen-1.5-32B-layer-mix-bpw-3.0` | 0.599 | 0.346 | 0.775 | 0.722 | 0.620 | 0.492 | 0.807 | 0.853 | 0.444 | 0.515 | 0.494 | 0.478 | 0.642 |
|
{"license": "apache-2.0"}
|
GreenBitAI/Qwen-1.5-4B-Chat-layer-mix-bpw-3.0
| null |
[
"transformers",
"safetensors",
"qwen2",
"text-generation",
"conversational",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null |
2024-04-13T10:12:48+00:00
|
[] |
[] |
TAGS
#transformers #safetensors #qwen2 #text-generation #conversational #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us
|
GreenBit LLMs
=============
This is GreenBitAI's pretrained low-bit LLMs with extreme compression yet still strong performance.
Please refer to our Github page for the code to run the model and more information.
### Zero-shot Evaluation
We evaluate the zero-shot ability of low-bit quantized Qwen1.5 models using the 'llm\_eval' library and list the results below:
|
[
"### Zero-shot Evaluation\n\n\nWe evaluate the zero-shot ability of low-bit quantized Qwen1.5 models using the 'llm\\_eval' library and list the results below:"
] |
[
"TAGS\n#transformers #safetensors #qwen2 #text-generation #conversational #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n",
"### Zero-shot Evaluation\n\n\nWe evaluate the zero-shot ability of low-bit quantized Qwen1.5 models using the 'llm\\_eval' library and list the results below:"
] |
text-generation
|
transformers
|
# GreenBit LLMs
This is GreenBitAI's pretrained **low-bit** LLMs with extreme compression yet still strong performance.
Please refer to our [Github page](https://github.com/GreenBitAI/green-bit-llm) for the code to run the model and more information.
|
{"license": "apache-2.0"}
|
GreenBitAI/Qwen-1.5-4B-Chat-layer-mix-bpw-2.5
| null |
[
"transformers",
"safetensors",
"qwen2",
"text-generation",
"conversational",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null |
2024-04-13T10:12:59+00:00
|
[] |
[] |
TAGS
#transformers #safetensors #qwen2 #text-generation #conversational #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us
|
# GreenBit LLMs
This is GreenBitAI's pretrained low-bit LLMs with extreme compression yet still strong performance.
Please refer to our Github page for the code to run the model and more information.
|
[
"# GreenBit LLMs\n\nThis is GreenBitAI's pretrained low-bit LLMs with extreme compression yet still strong performance.\n\nPlease refer to our Github page for the code to run the model and more information."
] |
[
"TAGS\n#transformers #safetensors #qwen2 #text-generation #conversational #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n",
"# GreenBit LLMs\n\nThis is GreenBitAI's pretrained low-bit LLMs with extreme compression yet still strong performance.\n\nPlease refer to our Github page for the code to run the model and more information."
] |
text-generation
|
transformers
|
# GreenBit LLMs
This is GreenBitAI's pretrained **low-bit** LLMs with extreme compression yet still strong performance.
Please refer to our [Github page](https://github.com/GreenBitAI/green-bit-llm) for the code to run the model and more information.
|
{"license": "apache-2.0"}
|
GreenBitAI/Qwen-1.5-4B-Chat-layer-mix-bpw-2.2
| null |
[
"transformers",
"safetensors",
"qwen2",
"text-generation",
"conversational",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null |
2024-04-13T10:13:05+00:00
|
[] |
[] |
TAGS
#transformers #safetensors #qwen2 #text-generation #conversational #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us
|
# GreenBit LLMs
This is GreenBitAI's pretrained low-bit LLMs with extreme compression yet still strong performance.
Please refer to our Github page for the code to run the model and more information.
|
[
"# GreenBit LLMs\n\nThis is GreenBitAI's pretrained low-bit LLMs with extreme compression yet still strong performance.\n\nPlease refer to our Github page for the code to run the model and more information."
] |
[
"TAGS\n#transformers #safetensors #qwen2 #text-generation #conversational #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n",
"# GreenBit LLMs\n\nThis is GreenBitAI's pretrained low-bit LLMs with extreme compression yet still strong performance.\n\nPlease refer to our Github page for the code to run the model and more information."
] |
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. -->
# h2o-danube2-1.8b-text-to-sql
This model is a fine-tuned version of [h2oai/h2o-danube2-1.8b-base](https://huggingface.co/h2oai/h2o-danube2-1.8b-base) 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: 0.0002
- train_batch_size: 3
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 6
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant
- lr_scheduler_warmup_ratio: 0.03
- num_epochs: 1
### Training results
### Framework versions
- PEFT 0.7.2.dev0
- Transformers 4.36.2
- Pytorch 2.1.2+cu121
- Datasets 2.17.0
- Tokenizers 0.15.2
|
{"license": "apache-2.0", "library_name": "peft", "tags": ["trl", "sft", "generated_from_trainer"], "datasets": ["generator"], "base_model": "h2oai/h2o-danube2-1.8b-base", "model-index": [{"name": "h2o-danube2-1.8b-text-to-sql", "results": []}]}
|
DuongTrongChi/h2o-danube2-1.8b-text-to-sql
| null |
[
"peft",
"tensorboard",
"safetensors",
"trl",
"sft",
"generated_from_trainer",
"dataset:generator",
"base_model:h2oai/h2o-danube2-1.8b-base",
"license:apache-2.0",
"region:us"
] | null |
2024-04-13T10:16:41+00:00
|
[] |
[] |
TAGS
#peft #tensorboard #safetensors #trl #sft #generated_from_trainer #dataset-generator #base_model-h2oai/h2o-danube2-1.8b-base #license-apache-2.0 #region-us
|
# h2o-danube2-1.8b-text-to-sql
This model is a fine-tuned version of h2oai/h2o-danube2-1.8b-base 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: 0.0002
- train_batch_size: 3
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 6
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant
- lr_scheduler_warmup_ratio: 0.03
- num_epochs: 1
### Training results
### Framework versions
- PEFT 0.7.2.dev0
- Transformers 4.36.2
- Pytorch 2.1.2+cu121
- Datasets 2.17.0
- Tokenizers 0.15.2
|
[
"# h2o-danube2-1.8b-text-to-sql\n\nThis model is a fine-tuned version of h2oai/h2o-danube2-1.8b-base on the generator dataset.",
"## Model description\n\nMore information needed",
"## Intended uses & limitations\n\nMore information needed",
"## Training and evaluation data\n\nMore information needed",
"## Training procedure",
"### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 0.0002\n- train_batch_size: 3\n- eval_batch_size: 8\n- seed: 42\n- gradient_accumulation_steps: 2\n- total_train_batch_size: 6\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: constant\n- lr_scheduler_warmup_ratio: 0.03\n- num_epochs: 1",
"### Training results",
"### Framework versions\n\n- PEFT 0.7.2.dev0\n- Transformers 4.36.2\n- Pytorch 2.1.2+cu121\n- Datasets 2.17.0\n- Tokenizers 0.15.2"
] |
[
"TAGS\n#peft #tensorboard #safetensors #trl #sft #generated_from_trainer #dataset-generator #base_model-h2oai/h2o-danube2-1.8b-base #license-apache-2.0 #region-us \n",
"# h2o-danube2-1.8b-text-to-sql\n\nThis model is a fine-tuned version of h2oai/h2o-danube2-1.8b-base on the generator dataset.",
"## Model description\n\nMore information needed",
"## Intended uses & limitations\n\nMore information needed",
"## Training and evaluation data\n\nMore information needed",
"## Training procedure",
"### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 0.0002\n- train_batch_size: 3\n- eval_batch_size: 8\n- seed: 42\n- gradient_accumulation_steps: 2\n- total_train_batch_size: 6\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: constant\n- lr_scheduler_warmup_ratio: 0.03\n- num_epochs: 1",
"### Training results",
"### Framework versions\n\n- PEFT 0.7.2.dev0\n- Transformers 4.36.2\n- Pytorch 2.1.2+cu121\n- Datasets 2.17.0\n- Tokenizers 0.15.2"
] |
text-generation
|
transformers
|
# merge
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
## Merge Details
### Merge Method
This model was merged using the SLERP merge method.
### Models Merged
The following models were included in the merge:
* [cognitivecomputations/dolphin-2.8-mistral-7b-v02](https://huggingface.co/cognitivecomputations/dolphin-2.8-mistral-7b-v02)
* [arcee-ai/sec-mistral-7b-instruct-1.6-epoch](https://huggingface.co/arcee-ai/sec-mistral-7b-instruct-1.6-epoch)
### Configuration
The following YAML configuration was used to produce this model:
```yaml
slices:
- sources:
- model: arcee-ai/sec-mistral-7b-instruct-1.6-epoch
layer_range: [0, 32]
- model: cognitivecomputations/dolphin-2.8-mistral-7b-v02
layer_range: [0, 32]
merge_method: slerp
base_model: cognitivecomputations/dolphin-2.8-mistral-7b-v02
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: bfloat16
```
|
{"library_name": "transformers", "tags": ["mergekit", "merge"], "base_model": ["cognitivecomputations/dolphin-2.8-mistral-7b-v02", "arcee-ai/sec-mistral-7b-instruct-1.6-epoch"]}
|
mergekit-community/mergekit-slerp-vhzhpmg
| null |
[
"transformers",
"safetensors",
"mistral",
"text-generation",
"mergekit",
"merge",
"conversational",
"base_model:cognitivecomputations/dolphin-2.8-mistral-7b-v02",
"base_model:arcee-ai/sec-mistral-7b-instruct-1.6-epoch",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null |
2024-04-13T10:17:16+00:00
|
[] |
[] |
TAGS
#transformers #safetensors #mistral #text-generation #mergekit #merge #conversational #base_model-cognitivecomputations/dolphin-2.8-mistral-7b-v02 #base_model-arcee-ai/sec-mistral-7b-instruct-1.6-epoch #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us
|
# merge
This is a merge of pre-trained language models created using mergekit.
## Merge Details
### Merge Method
This model was merged using the SLERP merge method.
### Models Merged
The following models were included in the merge:
* cognitivecomputations/dolphin-2.8-mistral-7b-v02
* arcee-ai/sec-mistral-7b-instruct-1.6-epoch
### Configuration
The following YAML configuration was used to produce this model:
|
[
"# merge\n\nThis is a merge of pre-trained language models created using mergekit.",
"## Merge Details",
"### Merge Method\n\nThis model was merged using the SLERP merge method.",
"### Models Merged\n\nThe following models were included in the merge:\n* cognitivecomputations/dolphin-2.8-mistral-7b-v02\n* arcee-ai/sec-mistral-7b-instruct-1.6-epoch",
"### Configuration\n\nThe following YAML configuration was used to produce this model:"
] |
[
"TAGS\n#transformers #safetensors #mistral #text-generation #mergekit #merge #conversational #base_model-cognitivecomputations/dolphin-2.8-mistral-7b-v02 #base_model-arcee-ai/sec-mistral-7b-instruct-1.6-epoch #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n",
"# merge\n\nThis is a merge of pre-trained language models created using mergekit.",
"## Merge Details",
"### Merge Method\n\nThis model was merged using the SLERP merge method.",
"### Models Merged\n\nThe following models were included in the merge:\n* cognitivecomputations/dolphin-2.8-mistral-7b-v02\n* arcee-ai/sec-mistral-7b-instruct-1.6-epoch",
"### Configuration\n\nThe following YAML configuration was used to produce this model:"
] |
null |
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. -->
# segformer-b0-human-parser
This model is a fine-tuned version of [nvidia/mit-b0](https://huggingface.co/nvidia/mit-b0) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2073
- Mean Iou: 0.5123
- Mean Accuracy: 0.6061
- Overall Accuracy: 0.9404
- Per Category Iou: [0.9738435807240893, 0.25487077790797996, 0.6992917234103969, 0.0, 0.6874674997812054, 0.640439429039686, 0.739829923873258, 0.5614734173142479, 0.0, 0.36041378832602766, 0.34524546132802786, 0.7459134523284406, 0.6752988298594533, 0.6595964688647477, 0.6534596510166254, 0.6718737447469826, 0.5531669206163902, 0.0]
- Per Category Accuracy: [0.9881203940329015, 0.2634819419853832, 0.8494709222844186, 0.0, 0.8557345821246315, 0.7440582073040913, 0.8536968246833937, 0.7504572727657617, 0.0, 0.47917172993729645, 0.44030265431487925, 0.8766212774407773, 0.8252944601721314, 0.7851447983014862, 0.7807782580582752, 0.7778494044297343, 0.638974454957921, 0.0]
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 6e-05
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
### Training results
| Training Loss | Epoch | Step | Validation Loss | Mean Iou | Mean Accuracy | Overall Accuracy | Per Category Iou | Per Category Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:-------------:|:----------------:|:-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------:|:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------:|
| 1.196 | 1.0 | 150 | 1.0385 | 0.2589 | 0.3904 | 0.8476 | [0.9204842413580886, 0.0, 0.5011135987109498, 0.0, 0.4247896643602946, 0.21716367546832283, 0.37654541592527674, 0.2413904123626465, 0.0, 0.00011498100258323986, 0.17434826190421535, 0.6403960678587253, 0.2886871534533113, 0.3498946119943481, 0.20843312477174916, 0.2948213980516151, 0.02278691191401758, 0.0] | [0.9286047065013684, 0.0, 0.8187642509847288, 0.0, 0.8186861291885359, 0.2964611313525812, 0.8461503960175404, 0.32777406991076224, 0.0, 0.00011512278484574826, 0.28907191592259074, 0.7876296848770058, 0.5291312004696214, 0.6774522292993631, 0.35063191676043165, 0.33470760290184154, 0.02290101296194402, 0.0] |
| 0.5993 | 2.0 | 300 | 0.5363 | 0.3513 | 0.4542 | 0.9036 | [0.9606464787878808, 0.0, 0.6184389403979624, 0.0, 0.5766527077088294, 0.3976546071060847, 0.541258795941219, 0.2463616617645146, 0.0, 0.008046569553189534, 0.04380007870156896, 0.6770073675856182, 0.48097781602690326, 0.4815914821624524, 0.4298610883927723, 0.5332039845335002, 0.32718757935640846, 0.0] | [0.9826711239263715, 0.0, 0.8494886765701763, 0.0, 0.7615903030599638, 0.6444578056184961, 0.8692773860198443, 0.3153733557803321, 0.0, 0.008066269791525428, 0.04603502041292726, 0.835153289660539, 0.7302411070187564, 0.6723815994338287, 0.4682921530991669, 0.61784401639502, 0.37480719446524086, 0.0] |
| 0.468 | 3.0 | 450 | 0.3407 | 0.4236 | 0.5160 | 0.9222 | [0.967628327243794, 0.0, 0.6552366972477064, 0.0, 0.6290085111004403, 0.4670381355483089, 0.6672147151783046, 0.383883893570567, 0.0, 0.2165883496207548, 0.16886930983847284, 0.6990637778386917, 0.5844660521614327, 0.5797863638252885, 0.5635731087436499, 0.5986930492860812, 0.44376046579658623, 0.0] | [0.9867078128564305, 0.0, 0.8208199436428244, 0.0, 0.8762466521242056, 0.6131590299246492, 0.8315169152556456, 0.5000853892967014, 0.0, 0.26342651456814886, 0.1946269217204203, 0.856827664875574, 0.7383624321842127, 0.7423898089171974, 0.6493545064057199, 0.6988746063206779, 0.5148313684457393, 0.0] |
| 0.2826 | 4.0 | 600 | 0.2798 | 0.4551 | 0.5533 | 0.9293 | [0.9704567835904337, 0.0012846283896218, 0.6628886267200698, 0.0, 0.6545595921801918, 0.5437484428274499, 0.6924069605979732, 0.4294368657847134, 0.0, 0.3000079178653435, 0.2319497953477191, 0.712312533356426, 0.6370556857129019, 0.6220110253876812, 0.6080063117165435, 0.6351838258482077, 0.4900002446962097, 0.0] | [0.9873710355453347, 0.0012846283896218, 0.8479478581990559, 0.0, 0.8435677609119634, 0.7389797371417705, 0.8298649536752014, 0.5549519370050572, 0.0, 0.40712021632850415, 0.2790950818673832, 0.8737095012573054, 0.7939287709364969, 0.7406539278131635, 0.7376293829838148, 0.7590265617282763, 0.5644590620856372, 0.0] |
| 0.285 | 5.0 | 750 | 0.2480 | 0.4721 | 0.5761 | 0.9325 | [0.9719933486526419, 0.02278384962526125, 0.6784888470926147, 0.0, 0.6575070855310532, 0.5547105384213228, 0.7129180414303309, 0.49382598215708845, 0.0, 0.3345492643374482, 0.2584484563669665, 0.7208913273095512, 0.6495685343255954, 0.6406974011147674, 0.6289914582523433, 0.6479963374487807, 0.5249157713980156, 0.0] | [0.9863067860954057, 0.02278384962526125, 0.8435847424740851, 0.0, 0.8043595854480959, 0.6760888068407149, 0.8171256340624186, 0.7457634778323201, 0.0, 0.46972398672762206, 0.30755138754621136, 0.8880640267486244, 0.8222930494143935, 0.7778343949044586, 0.790811538272246, 0.773970340151763, 0.6441756943254286, 0.0] |
| 0.2314 | 6.0 | 900 | 0.2295 | 0.4855 | 0.5841 | 0.9359 | [0.9730456757750755, 0.0637654378431555, 0.6851240240801579, 0.0, 0.6712804182366192, 0.595825314509297, 0.7089200924431801, 0.5193061778733198, 0.0, 0.3552495306547412, 0.3065643676435385, 0.731074083138405, 0.6581214590064147, 0.6410021270484412, 0.638811317249175, 0.6591728612526099, 0.5321564146622513, 0.0] | [0.9862461039828672, 0.0638520214592846, 0.8482769465672089, 0.0, 0.8695216069897929, 0.7054527891869578, 0.8734292437330271, 0.6676700900084057, 0.0, 0.49668062637028093, 0.38343317779418595, 0.8656622847629362, 0.8317493869358152, 0.7606239207360227, 0.7644012022286373, 0.7771181711470742, 0.6191245050197091, 0.0] |
| 0.2178 | 7.0 | 1050 | 0.2208 | 0.4958 | 0.5886 | 0.9371 | [0.9734572256785639, 0.1587942678306704, 0.6914719081623183, 0.0, 0.6601870822105664, 0.6270601644744053, 0.7162747021535327, 0.5124449676994741, 0.0, 0.3619236654764809, 0.3177490572194479, 0.7361379703589878, 0.6675998590236725, 0.6535390393232998, 0.6428418797248676, 0.6647232417213139, 0.540526721767411, 0.0] | [0.9877832474957517, 0.160418802167228, 0.8362072026600993, 0.0, 0.8951839293491445, 0.7298165744011244, 0.8545759194141131, 0.6104045549838093, 0.0, 0.5009990099440503, 0.3903854985752817, 0.87941298037957, 0.8317257165039719, 0.7700597310686482, 0.7556186878329506, 0.7708032661753292, 0.6210221173881277, 0.0] |
| 0.171 | 8.0 | 1200 | 0.2149 | 0.5031 | 0.6016 | 0.9382 | [0.9738028781291189, 0.2090036563071298, 0.6954619055669778, 0.0, 0.6788968068357729, 0.6110085872408796, 0.7350502197799524, 0.5429843550868226, 0.0, 0.3594320656408074, 0.3347269860560705, 0.7407122718676398, 0.6661915078754087, 0.646810692733125, 0.6485688609619236, 0.6692661668757929, 0.5431693882334557, 0.0] | [0.9868011813068851, 0.21306859782478468, 0.8581432567954529, 0.0, 0.8242681378222496, 0.7152717059809872, 0.8559814323106499, 0.7949015692126631, 0.0, 0.4839096721047259, 0.42070167693022054, 0.8844953113707054, 0.8490311692246514, 0.7584169851380043, 0.777752321214312, 0.7791996202718392, 0.6270825252789479, 0.0] |
| 0.1615 | 9.0 | 1350 | 0.2072 | 0.5123 | 0.6111 | 0.9404 | [0.9738930615479604, 0.25244414082891337, 0.6979447149962021, 0.0, 0.6899370517994793, 0.6465310914683069, 0.7354452381057439, 0.5556946534030943, 0.0, 0.3601541486614925, 0.34689383402874363, 0.7437578951763325, 0.6725374477193258, 0.6572256369218894, 0.6525889931816169, 0.6736342658892065, 0.5632821294256818, 0.0] | [0.9872016504484974, 0.26072631424805975, 0.8553133504619919, 0.0, 0.8557708167111089, 0.7713662180559067, 0.8656042619570102, 0.7063312238926388, 0.0, 0.47889287696955896, 0.44806185028151824, 0.8843821654286037, 0.8333672609523088, 0.7867685774946921, 0.8004561816173064, 0.7995715229536693, 0.6652027727916437, 0.0] |
| 0.179 | 10.0 | 1500 | 0.2073 | 0.5123 | 0.6061 | 0.9404 | [0.9738435807240893, 0.25487077790797996, 0.6992917234103969, 0.0, 0.6874674997812054, 0.640439429039686, 0.739829923873258, 0.5614734173142479, 0.0, 0.36041378832602766, 0.34524546132802786, 0.7459134523284406, 0.6752988298594533, 0.6595964688647477, 0.6534596510166254, 0.6718737447469826, 0.5531669206163902, 0.0] | [0.9881203940329015, 0.2634819419853832, 0.8494709222844186, 0.0, 0.8557345821246315, 0.7440582073040913, 0.8536968246833937, 0.7504572727657617, 0.0, 0.47917172993729645, 0.44030265431487925, 0.8766212774407773, 0.8252944601721314, 0.7851447983014862, 0.7807782580582752, 0.7778494044297343, 0.638974454957921, 0.0] |
### Framework versions
- Transformers 4.39.3
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
|
{"license": "other", "tags": ["generated_from_trainer"], "base_model": "nvidia/mit-b0", "model-index": [{"name": "segformer-b0-human-parser", "results": []}]}
|
MF21377197/segformer-b0-human-parser
| null |
[
"transformers",
"tensorboard",
"safetensors",
"segformer",
"generated_from_trainer",
"base_model:nvidia/mit-b0",
"license:other",
"endpoints_compatible",
"region:us"
] | null |
2024-04-13T10:17:54+00:00
|
[] |
[] |
TAGS
#transformers #tensorboard #safetensors #segformer #generated_from_trainer #base_model-nvidia/mit-b0 #license-other #endpoints_compatible #region-us
|
segformer-b0-human-parser
=========================
This model is a fine-tuned version of nvidia/mit-b0 on an unknown dataset.
It achieves the following results on the evaluation set:
* Loss: 0.2073
* Mean Iou: 0.5123
* Mean Accuracy: 0.6061
* Overall Accuracy: 0.9404
* Per Category Iou: [0.9738435807240893, 0.25487077790797996, 0.6992917234103969, 0.0, 0.6874674997812054, 0.640439429039686, 0.739829923873258, 0.5614734173142479, 0.0, 0.36041378832602766, 0.34524546132802786, 0.7459134523284406, 0.6752988298594533, 0.6595964688647477, 0.6534596510166254, 0.6718737447469826, 0.5531669206163902, 0.0]
* Per Category Accuracy: [0.9881203940329015, 0.2634819419853832, 0.8494709222844186, 0.0, 0.8557345821246315, 0.7440582073040913, 0.8536968246833937, 0.7504572727657617, 0.0, 0.47917172993729645, 0.44030265431487925, 0.8766212774407773, 0.8252944601721314, 0.7851447983014862, 0.7807782580582752, 0.7778494044297343, 0.638974454957921, 0.0]
Model description
-----------------
More information needed
Intended uses & limitations
---------------------------
More information needed
Training and evaluation data
----------------------------
More information needed
Training procedure
------------------
### Training hyperparameters
The following hyperparameters were used during training:
* learning\_rate: 6e-05
* train\_batch\_size: 2
* eval\_batch\_size: 2
* seed: 42
* gradient\_accumulation\_steps: 4
* total\_train\_batch\_size: 8
* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
* lr\_scheduler\_type: linear
* num\_epochs: 10
### Training results
### Framework versions
* Transformers 4.39.3
* Pytorch 2.2.1+cu121
* Datasets 2.18.0
* Tokenizers 0.15.2
|
[
"### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 6e-05\n* train\\_batch\\_size: 2\n* eval\\_batch\\_size: 2\n* seed: 42\n* gradient\\_accumulation\\_steps: 4\n* total\\_train\\_batch\\_size: 8\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 10",
"### Training results",
"### Framework versions\n\n\n* Transformers 4.39.3\n* Pytorch 2.2.1+cu121\n* Datasets 2.18.0\n* Tokenizers 0.15.2"
] |
[
"TAGS\n#transformers #tensorboard #safetensors #segformer #generated_from_trainer #base_model-nvidia/mit-b0 #license-other #endpoints_compatible #region-us \n",
"### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 6e-05\n* train\\_batch\\_size: 2\n* eval\\_batch\\_size: 2\n* seed: 42\n* gradient\\_accumulation\\_steps: 4\n* total\\_train\\_batch\\_size: 8\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 10",
"### Training results",
"### Framework versions\n\n\n* Transformers 4.39.3\n* Pytorch 2.2.1+cu121\n* Datasets 2.18.0\n* Tokenizers 0.15.2"
] |
text-generation
|
transformers
|
# GreenBit LLMs
This is GreenBitAI's pretrained **low-bit** LLMs with extreme compression yet still strong performance.
Please refer to our [Github page](https://github.com/GreenBitAI/green-bit-llm) for the code to run the model and more information.
|
{"license": "apache-2.0"}
|
GreenBitAI/Qwen-1.5-7B-Chat-layer-mix-bpw-2.2
| null |
[
"transformers",
"safetensors",
"qwen2",
"text-generation",
"conversational",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null |
2024-04-13T10:19:09+00:00
|
[] |
[] |
TAGS
#transformers #safetensors #qwen2 #text-generation #conversational #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us
|
# GreenBit LLMs
This is GreenBitAI's pretrained low-bit LLMs with extreme compression yet still strong performance.
Please refer to our Github page for the code to run the model and more information.
|
[
"# GreenBit LLMs\n\nThis is GreenBitAI's pretrained low-bit LLMs with extreme compression yet still strong performance.\n\nPlease refer to our Github page for the code to run the model and more information."
] |
[
"TAGS\n#transformers #safetensors #qwen2 #text-generation #conversational #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n",
"# GreenBit LLMs\n\nThis is GreenBitAI's pretrained low-bit LLMs with extreme compression yet still strong performance.\n\nPlease refer to our Github page for the code to run the model and more information."
] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.