pipeline_tag
stringclasses 48
values | library_name
stringclasses 198
values | text
stringlengths 1
900k
| metadata
stringlengths 2
438k
| id
stringlengths 5
122
| last_modified
null | tags
sequencelengths 1
1.84k
| sha
null | created_at
stringlengths 25
25
| arxiv
sequencelengths 0
201
| languages
sequencelengths 0
1.83k
| tags_str
stringlengths 17
9.34k
| text_str
stringlengths 0
389k
| text_lists
sequencelengths 0
722
| processed_texts
sequencelengths 1
723
|
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
fill-mask | 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. -->
# all-MiniLM-L6-v2-personal-project-default-2024-04-19
This model is a fine-tuned version of [sentence-transformers/all-MiniLM-L6-v2](https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2) on the None dataset.
It achieves the following results on the evaluation set:
- eval_loss: 10.7201
- eval_runtime: 3708.4666
- eval_samples_per_second: 8.168
- eval_steps_per_second: 0.255
- step: 0
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3.0
### Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.15.2
| {"license": "apache-2.0", "tags": ["generated_from_trainer"], "base_model": "sentence-transformers/all-MiniLM-L6-v2", "model-index": [{"name": "all-MiniLM-L6-v2-personal-project-default-2024-04-19", "results": []}]} | brugmark/all-MiniLM-L6-v2-personal-project-default-2024-04-19 | null | [
"transformers",
"tensorboard",
"safetensors",
"bert",
"fill-mask",
"generated_from_trainer",
"base_model:sentence-transformers/all-MiniLM-L6-v2",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | null | 2024-04-19T13:12:36+00:00 | [] | [] | TAGS
#transformers #tensorboard #safetensors #bert #fill-mask #generated_from_trainer #base_model-sentence-transformers/all-MiniLM-L6-v2 #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us
|
# all-MiniLM-L6-v2-personal-project-default-2024-04-19
This model is a fine-tuned version of sentence-transformers/all-MiniLM-L6-v2 on the None dataset.
It achieves the following results on the evaluation set:
- eval_loss: 10.7201
- eval_runtime: 3708.4666
- eval_samples_per_second: 8.168
- eval_steps_per_second: 0.255
- step: 0
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3.0
### Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.15.2
| [
"# all-MiniLM-L6-v2-personal-project-default-2024-04-19\n\nThis model is a fine-tuned version of sentence-transformers/all-MiniLM-L6-v2 on the None dataset.\nIt achieves the following results on the evaluation set:\n- eval_loss: 10.7201\n- eval_runtime: 3708.4666\n- eval_samples_per_second: 8.168\n- eval_steps_per_second: 0.255\n- step: 0",
"## 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: 32\n- eval_batch_size: 32\n- seed: 42\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 3.0",
"### Framework versions\n\n- Transformers 4.38.2\n- Pytorch 2.2.1+cu121\n- Datasets 2.19.0\n- Tokenizers 0.15.2"
] | [
"TAGS\n#transformers #tensorboard #safetensors #bert #fill-mask #generated_from_trainer #base_model-sentence-transformers/all-MiniLM-L6-v2 #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us \n",
"# all-MiniLM-L6-v2-personal-project-default-2024-04-19\n\nThis model is a fine-tuned version of sentence-transformers/all-MiniLM-L6-v2 on the None dataset.\nIt achieves the following results on the evaluation set:\n- eval_loss: 10.7201\n- eval_runtime: 3708.4666\n- eval_samples_per_second: 8.168\n- eval_steps_per_second: 0.255\n- step: 0",
"## 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: 32\n- eval_batch_size: 32\n- seed: 42\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 3.0",
"### Framework versions\n\n- Transformers 4.38.2\n- Pytorch 2.2.1+cu121\n- Datasets 2.19.0\n- Tokenizers 0.15.2"
] |
null | null |
# NikolayKozloff/Mistral-7B-v0.1-Instruct-sft-en-de-Q8_0-GGUF
This model was converted to GGUF format from [`maxidl/Mistral-7B-v0.1-Instruct-sft-en-de`](https://huggingface.co/maxidl/Mistral-7B-v0.1-Instruct-sft-en-de) 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/maxidl/Mistral-7B-v0.1-Instruct-sft-en-de) 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 NikolayKozloff/Mistral-7B-v0.1-Instruct-sft-en-de-Q8_0-GGUF --model mistral-7b-v0.1-instruct-sft-en-de.Q8_0.gguf -p "The meaning to life and the universe is"
```
Server:
```bash
llama-server --hf-repo NikolayKozloff/Mistral-7B-v0.1-Instruct-sft-en-de-Q8_0-GGUF --model mistral-7b-v0.1-instruct-sft-en-de.Q8_0.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-7b-v0.1-instruct-sft-en-de.Q8_0.gguf -n 128
```
| {"tags": ["alignment-handbook", "generated_from_trainer", "llama-cpp", "gguf-my-repo"], "datasets": ["maxidl/instruct-en-de"], "base_model": "mistralai/Mistral-7B-v0.1", "model-index": [{"name": "Mistral-7B-v0.1-Instruct-sft-en-de", "results": []}]} | NikolayKozloff/Mistral-7B-v0.1-Instruct-sft-en-de-GGUF | null | [
"gguf",
"alignment-handbook",
"generated_from_trainer",
"llama-cpp",
"gguf-my-repo",
"dataset:maxidl/instruct-en-de",
"base_model:mistralai/Mistral-7B-v0.1",
"region:us"
] | null | 2024-04-19T13:13:13+00:00 | [] | [] | TAGS
#gguf #alignment-handbook #generated_from_trainer #llama-cpp #gguf-my-repo #dataset-maxidl/instruct-en-de #base_model-mistralai/Mistral-7B-v0.1 #region-us
|
# NikolayKozloff/Mistral-7B-v0.1-Instruct-sft-en-de-Q8_0-GGUF
This model was converted to GGUF format from 'maxidl/Mistral-7B-v0.1-Instruct-sft-en-de' 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.
| [
"# NikolayKozloff/Mistral-7B-v0.1-Instruct-sft-en-de-Q8_0-GGUF\nThis model was converted to GGUF format from 'maxidl/Mistral-7B-v0.1-Instruct-sft-en-de' 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 #alignment-handbook #generated_from_trainer #llama-cpp #gguf-my-repo #dataset-maxidl/instruct-en-de #base_model-mistralai/Mistral-7B-v0.1 #region-us \n",
"# NikolayKozloff/Mistral-7B-v0.1-Instruct-sft-en-de-Q8_0-GGUF\nThis model was converted to GGUF format from 'maxidl/Mistral-7B-v0.1-Instruct-sft-en-de' 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 |
# 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": "mistralai/Mistral-7B-Instruct-v0.2"} | birdy654/CHECK_P_MISTRAL | null | [
"peft",
"safetensors",
"arxiv:1910.09700",
"base_model:mistralai/Mistral-7B-Instruct-v0.2",
"region:us"
] | null | 2024-04-19T13:13:15+00:00 | [
"1910.09700"
] | [] | TAGS
#peft #safetensors #arxiv-1910.09700 #base_model-mistralai/Mistral-7B-Instruct-v0.2 #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-mistralai/Mistral-7B-Instruct-v0.2 #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"
] |
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": []} | RobertML/sn6 | null | [
"transformers",
"safetensors",
"stablelm",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | null | 2024-04-19T13:16:02+00:00 | [
"1910.09700"
] | [] | TAGS
#transformers #safetensors #stablelm #text-generation #conversational #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #region-us
|
# Model Card for Model ID
## Model Details
### Model Description
This is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.
- Developed by:
- Funded by [optional]:
- Shared by [optional]:
- Model type:
- Language(s) (NLP):
- License:
- Finetuned from model [optional]:
### Model Sources [optional]
- Repository:
- Paper [optional]:
- Demo [optional]:
## Uses
### Direct Use
### Downstream Use [optional]
### Out-of-Scope Use
## Bias, Risks, and Limitations
### Recommendations
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
## Training Details
### Training Data
### Training Procedure
#### Preprocessing [optional]
#### Training Hyperparameters
- Training regime:
#### Speeds, Sizes, Times [optional]
## Evaluation
### Testing Data, Factors & Metrics
#### Testing Data
#### Factors
#### Metrics
### Results
#### Summary
## Model Examination [optional]
## Environmental Impact
Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).
- Hardware Type:
- Hours used:
- Cloud Provider:
- Compute Region:
- Carbon Emitted:
## Technical Specifications [optional]
### Model Architecture and Objective
### Compute Infrastructure
#### Hardware
#### Software
[optional]
BibTeX:
APA:
## Glossary [optional]
## More Information [optional]
## Model Card Authors [optional]
## Model Card Contact
| [
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.",
"## How to Get Started with the Model\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] | [
"TAGS\n#transformers #safetensors #stablelm #text-generation #conversational #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #region-us \n",
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.",
"## How to Get Started with the Model\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] |
null | peft |
<!-- 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. -->
# gpt1B_reward_model
This model is a fine-tuned version of [AI-Sweden-Models/gpt-sw3-1.3b](https://huggingface.co/AI-Sweden-Models/gpt-sw3-1.3b) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0078
- Accuracy: 0.9966
## 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: 2
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 1
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 0.3164 | 0.17 | 20 | 0.2708 | 0.9461 |
| 0.1799 | 0.33 | 40 | 0.1111 | 0.9697 |
| 0.0577 | 0.5 | 60 | 0.0276 | 0.9899 |
| 0.0064 | 0.66 | 80 | 0.0119 | 0.9933 |
| 0.0036 | 0.83 | 100 | 0.0099 | 0.9933 |
| 0.0035 | 0.99 | 120 | 0.0078 | 0.9966 |
### Framework versions
- PEFT 0.8.2
- Transformers 4.38.1
- Pytorch 2.2.0+cu118
- Datasets 2.17.1
- Tokenizers 0.15.2 | {"license": "apache-2.0", "library_name": "peft", "tags": ["trl", "reward-trainer", "generated_from_trainer"], "metrics": ["accuracy"], "base_model": "AI-Sweden-Models/gpt-sw3-1.3b", "model-index": [{"name": "gpt1B_reward_model", "results": []}]} | thorirhrafn/gpt1B_reward_model | null | [
"peft",
"tensorboard",
"safetensors",
"trl",
"reward-trainer",
"generated_from_trainer",
"base_model:AI-Sweden-Models/gpt-sw3-1.3b",
"license:apache-2.0",
"region:us"
] | null | 2024-04-19T13:16:29+00:00 | [] | [] | TAGS
#peft #tensorboard #safetensors #trl #reward-trainer #generated_from_trainer #base_model-AI-Sweden-Models/gpt-sw3-1.3b #license-apache-2.0 #region-us
| gpt1B\_reward\_model
====================
This model is a fine-tuned version of AI-Sweden-Models/gpt-sw3-1.3b on an unknown dataset.
It achieves the following results on the evaluation set:
* Loss: 0.0078
* Accuracy: 0.9966
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: 2
* eval\_batch\_size: 2
* seed: 42
* gradient\_accumulation\_steps: 8
* total\_train\_batch\_size: 16
* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
* lr\_scheduler\_type: linear
* num\_epochs: 1
### Training results
### Framework versions
* PEFT 0.8.2
* Transformers 4.38.1
* Pytorch 2.2.0+cu118
* Datasets 2.17.1
* 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: 2\n* eval\\_batch\\_size: 2\n* seed: 42\n* gradient\\_accumulation\\_steps: 8\n* total\\_train\\_batch\\_size: 16\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 1",
"### Training results",
"### Framework versions\n\n\n* PEFT 0.8.2\n* Transformers 4.38.1\n* Pytorch 2.2.0+cu118\n* Datasets 2.17.1\n* Tokenizers 0.15.2"
] | [
"TAGS\n#peft #tensorboard #safetensors #trl #reward-trainer #generated_from_trainer #base_model-AI-Sweden-Models/gpt-sw3-1.3b #license-apache-2.0 #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: 2\n* eval\\_batch\\_size: 2\n* seed: 42\n* gradient\\_accumulation\\_steps: 8\n* total\\_train\\_batch\\_size: 16\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 1",
"### Training results",
"### Framework versions\n\n\n* PEFT 0.8.2\n* Transformers 4.38.1\n* Pytorch 2.2.0+cu118\n* Datasets 2.17.1\n* Tokenizers 0.15.2"
] |
text-generation | transformers |
# Llama 3 DreamGen Opus V1
<div style="display: flex; flex-direction: row; align-items: center;">
<img src="/dreamgen/opus-v1.2-llama-3-8b/resolve/main/images/logo-1024.png" alt="model logo" style="
border-radius: 12px;
margin-right: 12px;
margin-top: 0px;
margin-bottom: 0px;
max-width: 100px;
height: auto;
"/>
Models for **(steerable) story-writing and role-playing**.
<br/>[All Opus V1 models, including quants](https://huggingface.co/collections/dreamgen/opus-v1-65d092a6f8ab7fc669111b31).
</div>
## Resources
- [**Opus V1 prompting guide**](https://dreamgen.com/docs/models/opus/v1) with many (interactive) examples and prompts that you can copy.
- [**Google Colab**](https://colab.research.google.com/drive/1J178fH6IdQOXNi-Njgdacf5QgAxsdT20?usp=sharing) for interactive role-play using `opus-v1.2-7b`.
- [Python code](example/prompt/format.py) to format the prompt correctly.
- Join the community on [**Discord**](https://dreamgen.com/discord) to get early access to new models.
<img src="/dreamgen/opus-v1.2-llama-3-8b/resolve/main/images/story_writing.webp" alt="story writing on dreamgen.com" style="
padding: 12px;
border-radius: 12px;
border: 2px solid #f9a8d4;
background: rgb(9, 9, 11);
"/>
## Prompting
<details>
<summary>The models use an extended version of ChatML.</summary>
```
<|im_start|>system
(Story description in the right format here)
(Typically consists of plot description, style description and characters)<|im_end|>
<|im_start|>user
(Your instruction on how the story should continue)<|im_end|>
<|im_start|>text names= Alice
(Continuation of the story from the Alice character)<|im_end|>
<|im_start|>text
(Continuation of the story from no character in particular (pure narration))<|im_end|>
<|im_start|>user
(Your instruction on how the story should continue)<|im_end|>
<|im_start|>text names= Bob
(Continuation of the story from the Bob character)<|im_end|>
```
The Opus V1 extension is the addition of the `text` role, and the addition / modification of role names.
Pay attention to the following:
- The `text` messages can (but don't have to have) `names`, names are used to indicate the "active" character during role-play.
- There can be multiple subsequent message with a `text` role, especially if names are involved.
- There can be multiple names attached to a message.
- The format for names is `names= {{name[0]}}; {{name[1]}}`, beware of the spaces after `names=` and after the `;`. This spacing leads to most natural tokenization for the names.
</details>
While the main goal for the models is great story-writing and role-playing performance, the models are also capable of several writing related tasks as well as general assistance.
Here's how you can prompt the model for the following tasks
### Steerable Story-writing and Role-playing:
- [Story-writing prompt guide](https://dreamgen.com/docs/models/opus/v1#task-story-writing)
- [Role-playing prompt guide](https://dreamgen.com/docs/models/opus/v1#task-role-playing)
- Input:
- System prompt: You provide story / role-play description, which consists of:
- Plot description
- Style description
- Characters and their descriptions
- Conversation turns:
- Text / message turn: This represents part of the story or role play
- Instruction: This tells the model what should happen next
- Output: Continuation of the story / role-play.
### Story plot summarization
- [Prompt guide](https://dreamgen.com/docs/models/opus/v1#task-plot-description)
- Input: A story, or a few chapters of a story.
- Output: A description of the story or chapters.
#### Examples:
<details>
<summary>Summary of <a href="https://www.libraryofshortstories.com/onlinereader/the-last-incantation">short fiction story</a> in 50 words</summary>
<blockquote>
Malygris, a powerful magician, summons his long-dead lover Nylissa from the grave using necromancy. However, upon seeing her, he realizes that she is not the same person he once knew, leading him to question the nature of love, memory, and the power of magic.
</blockquote>
</details>
<details>
<summary>Summary of <a href="https://www.libraryofshortstories.com/onlinereader/the-last-incantation">short fiction story</a> in 200 words</summary>
<blockquote>
The story is a dark fantasy set in the city of Susran, where an ancient and powerful magician named Malygris dwells in a tower atop a conical hill. Malygris, who has mastered all forms of sorcery and necromancy, is plagued by a deep sense of ennui and melancholy. He seeks solace in the memory of Nylissa, a girl he once loved in his youth.
One day, Malygris decides to summon Nylissa's spirit from the grave using his necromantic powers. He performs the necessary rituals and incantations, and Nylissa appears before him as a ghostly apparition. However, as Malygris gazes upon her, he becomes increasingly disillusioned. He notices subtle changes in her appearance and behavior that do not match his memories of her. He begins to question whether this is truly the same Nylissa he once knew, or if it is just another illusion conjured by his magic.
As Malygris grapples with this uncertainty, he becomes increasingly despondent and disillusioned with life itself. He realizes that even his magic cannot bring back the past or make him truly happy. In the end, he dismisses Nylissa's spirit and returns to his lonely tower, resigned to his fate as an old and weary sorcerer.
</blockquote>
</details>
<details>
<summary>Summary of <a href="https://edition.cnn.com/2024/02/29/health/pets-diseases-viruses-bacteria-wellness/index.html">CNN News article</a> in 150 words</summary>
<blockquote>
The article discusses the recent human deaths from diseases transmitted by animals, specifically Alaskapox and bubonic plague. Dr. Leana Wen, an emergency physician and former Baltimore health commissioner, explains the various ways household pets can transmit diseases to humans. These include fecal-oral transmission, scratches and bites, and vector-borne diseases like ticks, fleas, and mosquitoes. Wen emphasizes the importance of vaccinating pets, maintaining cleanliness, and taking commonsense precautions to reduce disease transmission. She also advises that individuals who are immunocompromised, babies, and pregnant women should take additional care when interacting with animals.
</blockquote>
</details>
<details>
<summary>Summary of <a href="https://edition.cnn.com/2024/02/29/health/pets-diseases-viruses-bacteria-wellness/index.html">CNN News article</a> in 50 words</summary>
<blockquote>
A doctor discusses the risks of diseases transmitted from animals to humans, focusing on household pets like cats and dogs. They emphasize the importance of vaccination, hygiene, and regular veterinary care to prevent these illnesses.
</blockquote>
</details>
### Story character description
- [Prompt guide](https://dreamgen.com/docs/models/opus/v1#task-char-description)
- Input: A story, or a few chapters of a story, set of characters.
- Output: A description of the characters.
#### Examples:
<details>
<summary>Description of the Malygris character from <a href="https://www.libraryofshortstories.com/onlinereader/the-last-incantation">this story</a> in 50 words</summary>
<blockquote>
Malygris is an ancient and powerful magician, characterized by his long white beard, cold green eyes, and a violet robe. He is a master of necromancy and possesses a vast knowledge of forbidden magic. Despite his immense power, he is plagued by a deep sense of melancholy and ennui.
</blockquote>
</details>
<details>
<summary>Description of the prince character from <a href="https://www.libraryofshortstories.com/onlinereader/the-pearl-of-love">this story</a> in 50 words</summary>
<blockquote>
The prince is a devoted and determined individual, driven by his love for his late queen. He is described as a graceful youth in the beginning, but as he grows older, his dedication to the Pearl of Love transforms him into a grave and intent man. His sense of color and design evolves over time, reflecting his growing maturity and artistic vision.
</blockquote>
</details>
### Story style description
- [Prompt guide](https://dreamgen.com/docs/models/opus/v1#task-style-description)
- Input: A story, or a few chapters of a story.
- Output: A description the style of the story.
<details>
<summary>Style description of <a href="https://www.libraryofshortstories.com/onlinereader/the-last-incantation">this story</a></summary>
<blockquote>
The story is written in a descriptive and evocative style, with a focus on the atmosphere and setting. The author uses vivid and detailed language to create a sense of place and time, and employs a variety of literary devices such as similes, metaphors, and allusions to enhance the mood and tone of the narrative. The sentence structure is varied, with a mix of short and long sentences that create a rhythmic flow to the prose.
</blockquote>
</details>
<details>
<summary>Style description of <a href="https://www.libraryofshortstories.com/onlinereader/the-pearl-of-love">this story</a></summary>
<blockquote>
The writing style is descriptive and evocative, with a focus on the beauty and grandeur of the Pearl of Love. The author uses vivid imagery and sensory details to create a rich and immersive atmosphere. The tone is reverential and contemplative, reflecting the prince's deep love for his queen and his dedication to creating a lasting monument to her memory.
</blockquote>
</details>
### Story description to chapters
- [Prompt guide](https://dreamgen.com/docs/models/opus/v1#task-story-description-to-chapter-descriptions)
- Input: A brief plot description and the desired number of chapters.
- Output: A description for each chapter.
### And more...
## Sampling params
For story-writing and role-play, I recommend "Min P" based sampling with `min_p` in the range `[0.01, 0.1]` and with `temperature` in the range `[0.5, 1.5]`, depending on your preferences. A good starting point would be `min_p=0.1; temperature=0.8`.
You may also benefit from setting presence, frequency and repetition penalties, especially at lower temperatures.
## Dataset
The fine-tuning dataset consisted of ~100M tokens of steerable story-writing, role-playing, writing-assistant and general-assistant examples. Each example was up to 31000 tokens long.
All story-writing and role-playing examples were based on human-written text.
## Running the model
The model is should be compatible with any software that supports the base model, but beware of prompting and tokenization.
I recommend using these model versions:
- 7B: [no quant (opus-v1.2-7b)](https://huggingface.co/dreamgen/opus-v1.2-7b)
- 34B: [no quant (opus-v1-34b)](https://huggingface.co/dreamgen/opus-v1-34b) or [awq (opus-v1-34b-awq)](https://huggingface.co/dreamgen/opus-v1-34b-awq)
- 34B: [no quant (opus-v1.2-70b)](https://huggingface.co/dreamgen/opus-v1.2-70b) or [awq (opus-v1.2-70b-awq)](https://huggingface.co/dreamgen/opus-v1.2-70b-awq)
### Running on DreamGen.com (free)
You can run the models on [dreamgen.com](https://dreamgen.com) for free — you can use the built-in UI for story-writing & role-playing, or use [the API](https://dreamgen.com/docs/api).
### Running Locally
- **Make sure your prompt is as close as possible to the Opus V1**
- Regardless of which backend you use, it's important that you format your prompt well and that the tokenization works correctly.
- [Read the prompt guide](https://dreamgen.com/docs/models/opus/v1)
- [Read the prompt formatting code](example/prompt/format.py)
- Make sure `<|im_start|>` and `<|im_end|>` are tokenized correctly
- **vLLM**
- [**Google Colab**](https://colab.research.google.com/drive/1J178fH6IdQOXNi-Njgdacf5QgAxsdT20?usp=sharing): This is a simple interactive Google Colab to do role-play with the 7B model, it should fit on the T4 GPU.
- [Code](example/prompt/interactive.py): This is simple script for interactive chat for one hard-coded scenario.
- **SillyTavern**
- [Official SillyTavern documentation for DreamGen](https://docs.sillytavern.app/usage/api-connections/dreamgen/) -- applies to both the API an local models
- SillyTavern (staging) comes with built-in DreamGen preset for RP
- Other presets can be found [here](https://huggingface.co/dreamgen/opus-v1.2-llama-3-8b/tree/main/configs/silly_tavern), v2 kindly provided by @MarinaraSpaghetti
- Make sure to unselect `Skip special tokens`, otherwise it won't work
- This is just an attempt at approximating the Opus V1 prompt, it won't be perfect
- Character cards specifically rewritten for the built-in DreamGen preset:
- [Seraphina](configs/silly_tavern/cards/Seraphina.png) (based on the default Seraphina card)
- [Lara Lightland](configs/silly_tavern/cards/LaraLightland.png) (based on the card by Deffcolony)
- **LM Studio**
- [Config](configs/lmstudio/preset.json)
- Just like ChatML, just changed "assistant" to "text" role.
- **There's a bug** in LM Studio if you delete a message or click "Continue", [see here for details](https://discord.com/channels/1110598183144399058/1212665261128417280/1212665261128417280).
- **HuggingFace**
- [Chat template](tokenizer_config.json#L51)
- Just like ChatML, just changed "assistant" to "text" role.
## Known Issues
- **34B repetition**:
- The 34B sometimes gets stuck repeating the same word, or synonyms. This seems to be a common problem across various Yi 34B fine-tunes.
- **GGUF**:
- The tokenization might be messed up. Some users reported that `<|im_start|>` and `<|im_end|>` are tokenized as multiple tokens. Also llama.cpp may not tokenize correctly (the Yi tokenizer is subtly different from the Llama 2 tokenizer).
## License
- This model is intended for personal use only, other use is not permitted.
| {"language": ["en"], "license": "cc-by-nc-nd-4.0", "tags": ["unsloth", "axolotl"], "pipeline_tag": "text-generation"} | LoneStriker/opus-v1.2-llama-3-8b-3.0bpw-h6-exl2 | null | [
"transformers",
"pytorch",
"safetensors",
"llama",
"text-generation",
"unsloth",
"axolotl",
"conversational",
"en",
"license:cc-by-nc-nd-4.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"3-bit",
"region:us"
] | null | 2024-04-19T13:19:24+00:00 | [] | [
"en"
] | TAGS
#transformers #pytorch #safetensors #llama #text-generation #unsloth #axolotl #conversational #en #license-cc-by-nc-nd-4.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #3-bit #region-us
|
# Llama 3 DreamGen Opus V1
<div style="display: flex; flex-direction: row; align-items: center;">
<img src="/dreamgen/opus-v1.2-llama-3-8b/resolve/main/images/URL" alt="model logo" style="
border-radius: 12px;
margin-right: 12px;
margin-top: 0px;
margin-bottom: 0px;
max-width: 100px;
height: auto;
"/>
Models for (steerable) story-writing and role-playing.
<br/>All Opus V1 models, including quants.
</div>
## Resources
- Opus V1 prompting guide with many (interactive) examples and prompts that you can copy.
- Google Colab for interactive role-play using 'opus-v1.2-7b'.
- Python code to format the prompt correctly.
- Join the community on Discord to get early access to new models.
<img src="/dreamgen/opus-v1.2-llama-3-8b/resolve/main/images/story_writing.webp" alt="story writing on URL" style="
padding: 12px;
border-radius: 12px;
border: 2px solid #f9a8d4;
background: rgb(9, 9, 11);
"/>
## Prompting
<details>
<summary>The models use an extended version of ChatML.</summary>
The Opus V1 extension is the addition of the 'text' role, and the addition / modification of role names.
Pay attention to the following:
- The 'text' messages can (but don't have to have) 'names', names are used to indicate the "active" character during role-play.
- There can be multiple subsequent message with a 'text' role, especially if names are involved.
- There can be multiple names attached to a message.
- The format for names is 'names= {{name[0]}}; {{name[1]}}', beware of the spaces after 'names=' and after the ';'. This spacing leads to most natural tokenization for the names.
</details>
While the main goal for the models is great story-writing and role-playing performance, the models are also capable of several writing related tasks as well as general assistance.
Here's how you can prompt the model for the following tasks
### Steerable Story-writing and Role-playing:
- Story-writing prompt guide
- Role-playing prompt guide
- Input:
- System prompt: You provide story / role-play description, which consists of:
- Plot description
- Style description
- Characters and their descriptions
- Conversation turns:
- Text / message turn: This represents part of the story or role play
- Instruction: This tells the model what should happen next
- Output: Continuation of the story / role-play.
### Story plot summarization
- Prompt guide
- Input: A story, or a few chapters of a story.
- Output: A description of the story or chapters.
#### Examples:
<details>
<summary>Summary of <a href="URL fiction story</a> in 50 words</summary>
<blockquote>
Malygris, a powerful magician, summons his long-dead lover Nylissa from the grave using necromancy. However, upon seeing her, he realizes that she is not the same person he once knew, leading him to question the nature of love, memory, and the power of magic.
</blockquote>
</details>
<details>
<summary>Summary of <a href="URL fiction story</a> in 200 words</summary>
<blockquote>
The story is a dark fantasy set in the city of Susran, where an ancient and powerful magician named Malygris dwells in a tower atop a conical hill. Malygris, who has mastered all forms of sorcery and necromancy, is plagued by a deep sense of ennui and melancholy. He seeks solace in the memory of Nylissa, a girl he once loved in his youth.
One day, Malygris decides to summon Nylissa's spirit from the grave using his necromantic powers. He performs the necessary rituals and incantations, and Nylissa appears before him as a ghostly apparition. However, as Malygris gazes upon her, he becomes increasingly disillusioned. He notices subtle changes in her appearance and behavior that do not match his memories of her. He begins to question whether this is truly the same Nylissa he once knew, or if it is just another illusion conjured by his magic.
As Malygris grapples with this uncertainty, he becomes increasingly despondent and disillusioned with life itself. He realizes that even his magic cannot bring back the past or make him truly happy. In the end, he dismisses Nylissa's spirit and returns to his lonely tower, resigned to his fate as an old and weary sorcerer.
</blockquote>
</details>
<details>
<summary>Summary of <a href="URL News article</a> in 150 words</summary>
<blockquote>
The article discusses the recent human deaths from diseases transmitted by animals, specifically Alaskapox and bubonic plague. Dr. Leana Wen, an emergency physician and former Baltimore health commissioner, explains the various ways household pets can transmit diseases to humans. These include fecal-oral transmission, scratches and bites, and vector-borne diseases like ticks, fleas, and mosquitoes. Wen emphasizes the importance of vaccinating pets, maintaining cleanliness, and taking commonsense precautions to reduce disease transmission. She also advises that individuals who are immunocompromised, babies, and pregnant women should take additional care when interacting with animals.
</blockquote>
</details>
<details>
<summary>Summary of <a href="URL News article</a> in 50 words</summary>
<blockquote>
A doctor discusses the risks of diseases transmitted from animals to humans, focusing on household pets like cats and dogs. They emphasize the importance of vaccination, hygiene, and regular veterinary care to prevent these illnesses.
</blockquote>
</details>
### Story character description
- Prompt guide
- Input: A story, or a few chapters of a story, set of characters.
- Output: A description of the characters.
#### Examples:
<details>
<summary>Description of the Malygris character from <a href="URL story</a> in 50 words</summary>
<blockquote>
Malygris is an ancient and powerful magician, characterized by his long white beard, cold green eyes, and a violet robe. He is a master of necromancy and possesses a vast knowledge of forbidden magic. Despite his immense power, he is plagued by a deep sense of melancholy and ennui.
</blockquote>
</details>
<details>
<summary>Description of the prince character from <a href="URL story</a> in 50 words</summary>
<blockquote>
The prince is a devoted and determined individual, driven by his love for his late queen. He is described as a graceful youth in the beginning, but as he grows older, his dedication to the Pearl of Love transforms him into a grave and intent man. His sense of color and design evolves over time, reflecting his growing maturity and artistic vision.
</blockquote>
</details>
### Story style description
- Prompt guide
- Input: A story, or a few chapters of a story.
- Output: A description the style of the story.
<details>
<summary>Style description of <a href="URL story</a></summary>
<blockquote>
The story is written in a descriptive and evocative style, with a focus on the atmosphere and setting. The author uses vivid and detailed language to create a sense of place and time, and employs a variety of literary devices such as similes, metaphors, and allusions to enhance the mood and tone of the narrative. The sentence structure is varied, with a mix of short and long sentences that create a rhythmic flow to the prose.
</blockquote>
</details>
<details>
<summary>Style description of <a href="URL story</a></summary>
<blockquote>
The writing style is descriptive and evocative, with a focus on the beauty and grandeur of the Pearl of Love. The author uses vivid imagery and sensory details to create a rich and immersive atmosphere. The tone is reverential and contemplative, reflecting the prince's deep love for his queen and his dedication to creating a lasting monument to her memory.
</blockquote>
</details>
### Story description to chapters
- Prompt guide
- Input: A brief plot description and the desired number of chapters.
- Output: A description for each chapter.
### And more...
## Sampling params
For story-writing and role-play, I recommend "Min P" based sampling with 'min_p' in the range '[0.01, 0.1]' and with 'temperature' in the range '[0.5, 1.5]', depending on your preferences. A good starting point would be 'min_p=0.1; temperature=0.8'.
You may also benefit from setting presence, frequency and repetition penalties, especially at lower temperatures.
## Dataset
The fine-tuning dataset consisted of ~100M tokens of steerable story-writing, role-playing, writing-assistant and general-assistant examples. Each example was up to 31000 tokens long.
All story-writing and role-playing examples were based on human-written text.
!token count distribution
## Running the model
The model is should be compatible with any software that supports the base model, but beware of prompting and tokenization.
I recommend using these model versions:
- 7B: no quant (opus-v1.2-7b)
- 34B: no quant (opus-v1-34b) or awq (opus-v1-34b-awq)
- 34B: no quant (opus-v1.2-70b) or awq (opus-v1.2-70b-awq)
### Running on URL (free)
You can run the models on URL for free — you can use the built-in UI for story-writing & role-playing, or use the API.
### Running Locally
- Make sure your prompt is as close as possible to the Opus V1
- Regardless of which backend you use, it's important that you format your prompt well and that the tokenization works correctly.
- Read the prompt guide
- Read the prompt formatting code
- Make sure '<|im_start|>' and '<|im_end|>' are tokenized correctly
- vLLM
- Google Colab: This is a simple interactive Google Colab to do role-play with the 7B model, it should fit on the T4 GPU.
- Code: This is simple script for interactive chat for one hard-coded scenario.
- SillyTavern
- Official SillyTavern documentation for DreamGen -- applies to both the API an local models
- SillyTavern (staging) comes with built-in DreamGen preset for RP
- Other presets can be found here, v2 kindly provided by @MarinaraSpaghetti
- Make sure to unselect 'Skip special tokens', otherwise it won't work
- This is just an attempt at approximating the Opus V1 prompt, it won't be perfect
- Character cards specifically rewritten for the built-in DreamGen preset:
- Seraphina (based on the default Seraphina card)
- Lara Lightland (based on the card by Deffcolony)
- LM Studio
- Config
- Just like ChatML, just changed "assistant" to "text" role.
- There's a bug in LM Studio if you delete a message or click "Continue", see here for details.
- HuggingFace
- Chat template
- Just like ChatML, just changed "assistant" to "text" role.
## Known Issues
- 34B repetition:
- The 34B sometimes gets stuck repeating the same word, or synonyms. This seems to be a common problem across various Yi 34B fine-tunes.
- GGUF:
- The tokenization might be messed up. Some users reported that '<|im_start|>' and '<|im_end|>' are tokenized as multiple tokens. Also URL may not tokenize correctly (the Yi tokenizer is subtly different from the Llama 2 tokenizer).
## License
- This model is intended for personal use only, other use is not permitted.
| [
"# Llama 3 DreamGen Opus V1\n\n<div style=\"display: flex; flex-direction: row; align-items: center;\">\n<img src=\"/dreamgen/opus-v1.2-llama-3-8b/resolve/main/images/URL\" alt=\"model logo\" style=\"\n border-radius: 12px;\n margin-right: 12px;\n margin-top: 0px;\n margin-bottom: 0px;\n max-width: 100px;\n height: auto;\n\"/>\n\nModels for (steerable) story-writing and role-playing.\n<br/>All Opus V1 models, including quants.\n\n</div>",
"## Resources\n\n- Opus V1 prompting guide with many (interactive) examples and prompts that you can copy.\n- Google Colab for interactive role-play using 'opus-v1.2-7b'.\n- Python code to format the prompt correctly.\n- Join the community on Discord to get early access to new models.\n\n<img src=\"/dreamgen/opus-v1.2-llama-3-8b/resolve/main/images/story_writing.webp\" alt=\"story writing on URL\" style=\"\n padding: 12px;\n border-radius: 12px;\n border: 2px solid #f9a8d4;\n background: rgb(9, 9, 11);\n\"/>",
"## Prompting\n\n<details>\n<summary>The models use an extended version of ChatML.</summary>\n\n\n\nThe Opus V1 extension is the addition of the 'text' role, and the addition / modification of role names.\n\nPay attention to the following:\n\n- The 'text' messages can (but don't have to have) 'names', names are used to indicate the \"active\" character during role-play.\n- There can be multiple subsequent message with a 'text' role, especially if names are involved.\n- There can be multiple names attached to a message.\n- The format for names is 'names= {{name[0]}}; {{name[1]}}', beware of the spaces after 'names=' and after the ';'. This spacing leads to most natural tokenization for the names.\n</details>\n\nWhile the main goal for the models is great story-writing and role-playing performance, the models are also capable of several writing related tasks as well as general assistance.\n\nHere's how you can prompt the model for the following tasks",
"### Steerable Story-writing and Role-playing:\n\n- Story-writing prompt guide\n- Role-playing prompt guide\n- Input:\n - System prompt: You provide story / role-play description, which consists of:\n - Plot description\n - Style description\n - Characters and their descriptions\n - Conversation turns:\n - Text / message turn: This represents part of the story or role play\n - Instruction: This tells the model what should happen next\n- Output: Continuation of the story / role-play.",
"### Story plot summarization\n\n- Prompt guide\n- Input: A story, or a few chapters of a story.\n- Output: A description of the story or chapters.",
"#### Examples:\n\n<details>\n <summary>Summary of <a href=\"URL fiction story</a> in 50 words</summary>\n <blockquote>\n Malygris, a powerful magician, summons his long-dead lover Nylissa from the grave using necromancy. However, upon seeing her, he realizes that she is not the same person he once knew, leading him to question the nature of love, memory, and the power of magic.\n </blockquote>\n</details>\n<details>\n <summary>Summary of <a href=\"URL fiction story</a> in 200 words</summary>\n <blockquote>\nThe story is a dark fantasy set in the city of Susran, where an ancient and powerful magician named Malygris dwells in a tower atop a conical hill. Malygris, who has mastered all forms of sorcery and necromancy, is plagued by a deep sense of ennui and melancholy. He seeks solace in the memory of Nylissa, a girl he once loved in his youth.\n\nOne day, Malygris decides to summon Nylissa's spirit from the grave using his necromantic powers. He performs the necessary rituals and incantations, and Nylissa appears before him as a ghostly apparition. However, as Malygris gazes upon her, he becomes increasingly disillusioned. He notices subtle changes in her appearance and behavior that do not match his memories of her. He begins to question whether this is truly the same Nylissa he once knew, or if it is just another illusion conjured by his magic.\n\nAs Malygris grapples with this uncertainty, he becomes increasingly despondent and disillusioned with life itself. He realizes that even his magic cannot bring back the past or make him truly happy. In the end, he dismisses Nylissa's spirit and returns to his lonely tower, resigned to his fate as an old and weary sorcerer.\n </blockquote>\n\n</details>\n<details>\n <summary>Summary of <a href=\"URL News article</a> in 150 words</summary>\n <blockquote>\nThe article discusses the recent human deaths from diseases transmitted by animals, specifically Alaskapox and bubonic plague. Dr. Leana Wen, an emergency physician and former Baltimore health commissioner, explains the various ways household pets can transmit diseases to humans. These include fecal-oral transmission, scratches and bites, and vector-borne diseases like ticks, fleas, and mosquitoes. Wen emphasizes the importance of vaccinating pets, maintaining cleanliness, and taking commonsense precautions to reduce disease transmission. She also advises that individuals who are immunocompromised, babies, and pregnant women should take additional care when interacting with animals.\n </blockquote>\n</details>\n<details>\n <summary>Summary of <a href=\"URL News article</a> in 50 words</summary>\n <blockquote>\nA doctor discusses the risks of diseases transmitted from animals to humans, focusing on household pets like cats and dogs. They emphasize the importance of vaccination, hygiene, and regular veterinary care to prevent these illnesses.\n </blockquote>\n</details>",
"### Story character description\n\n- Prompt guide\n- Input: A story, or a few chapters of a story, set of characters.\n- Output: A description of the characters.",
"#### Examples:\n\n<details>\n <summary>Description of the Malygris character from <a href=\"URL story</a> in 50 words</summary>\n <blockquote>\nMalygris is an ancient and powerful magician, characterized by his long white beard, cold green eyes, and a violet robe. He is a master of necromancy and possesses a vast knowledge of forbidden magic. Despite his immense power, he is plagued by a deep sense of melancholy and ennui.\n </blockquote>\n</details>\n\n<details>\n <summary>Description of the prince character from <a href=\"URL story</a> in 50 words</summary>\n <blockquote>\nThe prince is a devoted and determined individual, driven by his love for his late queen. He is described as a graceful youth in the beginning, but as he grows older, his dedication to the Pearl of Love transforms him into a grave and intent man. His sense of color and design evolves over time, reflecting his growing maturity and artistic vision.\n </blockquote>\n</details>",
"### Story style description\n\n- Prompt guide\n- Input: A story, or a few chapters of a story.\n- Output: A description the style of the story.\n\n<details>\n <summary>Style description of <a href=\"URL story</a></summary>\n <blockquote>\nThe story is written in a descriptive and evocative style, with a focus on the atmosphere and setting. The author uses vivid and detailed language to create a sense of place and time, and employs a variety of literary devices such as similes, metaphors, and allusions to enhance the mood and tone of the narrative. The sentence structure is varied, with a mix of short and long sentences that create a rhythmic flow to the prose.\n </blockquote>\n</details>\n\n<details>\n <summary>Style description of <a href=\"URL story</a></summary>\n <blockquote>\nThe writing style is descriptive and evocative, with a focus on the beauty and grandeur of the Pearl of Love. The author uses vivid imagery and sensory details to create a rich and immersive atmosphere. The tone is reverential and contemplative, reflecting the prince's deep love for his queen and his dedication to creating a lasting monument to her memory.\n </blockquote>\n</details>",
"### Story description to chapters\n\n- Prompt guide\n- Input: A brief plot description and the desired number of chapters.\n- Output: A description for each chapter.",
"### And more...",
"## Sampling params\n\nFor story-writing and role-play, I recommend \"Min P\" based sampling with 'min_p' in the range '[0.01, 0.1]' and with 'temperature' in the range '[0.5, 1.5]', depending on your preferences. A good starting point would be 'min_p=0.1; temperature=0.8'.\n\nYou may also benefit from setting presence, frequency and repetition penalties, especially at lower temperatures.",
"## Dataset\n\nThe fine-tuning dataset consisted of ~100M tokens of steerable story-writing, role-playing, writing-assistant and general-assistant examples. Each example was up to 31000 tokens long.\n\nAll story-writing and role-playing examples were based on human-written text.\n\n!token count distribution",
"## Running the model\n\nThe model is should be compatible with any software that supports the base model, but beware of prompting and tokenization.\n\nI recommend using these model versions:\n\n- 7B: no quant (opus-v1.2-7b)\n- 34B: no quant (opus-v1-34b) or awq (opus-v1-34b-awq)\n- 34B: no quant (opus-v1.2-70b) or awq (opus-v1.2-70b-awq)",
"### Running on URL (free)\n\nYou can run the models on URL for free — you can use the built-in UI for story-writing & role-playing, or use the API.",
"### Running Locally\n\n- Make sure your prompt is as close as possible to the Opus V1\n - Regardless of which backend you use, it's important that you format your prompt well and that the tokenization works correctly.\n - Read the prompt guide\n - Read the prompt formatting code\n - Make sure '<|im_start|>' and '<|im_end|>' are tokenized correctly\n- vLLM\n - Google Colab: This is a simple interactive Google Colab to do role-play with the 7B model, it should fit on the T4 GPU.\n - Code: This is simple script for interactive chat for one hard-coded scenario.\n- SillyTavern\n - Official SillyTavern documentation for DreamGen -- applies to both the API an local models\n - SillyTavern (staging) comes with built-in DreamGen preset for RP\n - Other presets can be found here, v2 kindly provided by @MarinaraSpaghetti\n - Make sure to unselect 'Skip special tokens', otherwise it won't work\n - This is just an attempt at approximating the Opus V1 prompt, it won't be perfect\n - Character cards specifically rewritten for the built-in DreamGen preset:\n - Seraphina (based on the default Seraphina card)\n - Lara Lightland (based on the card by Deffcolony)\n- LM Studio\n - Config\n - Just like ChatML, just changed \"assistant\" to \"text\" role.\n - There's a bug in LM Studio if you delete a message or click \"Continue\", see here for details.\n- HuggingFace\n - Chat template\n - Just like ChatML, just changed \"assistant\" to \"text\" role.",
"## Known Issues\n\n- 34B repetition:\n - The 34B sometimes gets stuck repeating the same word, or synonyms. This seems to be a common problem across various Yi 34B fine-tunes.\n- GGUF:\n - The tokenization might be messed up. Some users reported that '<|im_start|>' and '<|im_end|>' are tokenized as multiple tokens. Also URL may not tokenize correctly (the Yi tokenizer is subtly different from the Llama 2 tokenizer).",
"## License\n\n- This model is intended for personal use only, other use is not permitted."
] | [
"TAGS\n#transformers #pytorch #safetensors #llama #text-generation #unsloth #axolotl #conversational #en #license-cc-by-nc-nd-4.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #3-bit #region-us \n",
"# Llama 3 DreamGen Opus V1\n\n<div style=\"display: flex; flex-direction: row; align-items: center;\">\n<img src=\"/dreamgen/opus-v1.2-llama-3-8b/resolve/main/images/URL\" alt=\"model logo\" style=\"\n border-radius: 12px;\n margin-right: 12px;\n margin-top: 0px;\n margin-bottom: 0px;\n max-width: 100px;\n height: auto;\n\"/>\n\nModels for (steerable) story-writing and role-playing.\n<br/>All Opus V1 models, including quants.\n\n</div>",
"## Resources\n\n- Opus V1 prompting guide with many (interactive) examples and prompts that you can copy.\n- Google Colab for interactive role-play using 'opus-v1.2-7b'.\n- Python code to format the prompt correctly.\n- Join the community on Discord to get early access to new models.\n\n<img src=\"/dreamgen/opus-v1.2-llama-3-8b/resolve/main/images/story_writing.webp\" alt=\"story writing on URL\" style=\"\n padding: 12px;\n border-radius: 12px;\n border: 2px solid #f9a8d4;\n background: rgb(9, 9, 11);\n\"/>",
"## Prompting\n\n<details>\n<summary>The models use an extended version of ChatML.</summary>\n\n\n\nThe Opus V1 extension is the addition of the 'text' role, and the addition / modification of role names.\n\nPay attention to the following:\n\n- The 'text' messages can (but don't have to have) 'names', names are used to indicate the \"active\" character during role-play.\n- There can be multiple subsequent message with a 'text' role, especially if names are involved.\n- There can be multiple names attached to a message.\n- The format for names is 'names= {{name[0]}}; {{name[1]}}', beware of the spaces after 'names=' and after the ';'. This spacing leads to most natural tokenization for the names.\n</details>\n\nWhile the main goal for the models is great story-writing and role-playing performance, the models are also capable of several writing related tasks as well as general assistance.\n\nHere's how you can prompt the model for the following tasks",
"### Steerable Story-writing and Role-playing:\n\n- Story-writing prompt guide\n- Role-playing prompt guide\n- Input:\n - System prompt: You provide story / role-play description, which consists of:\n - Plot description\n - Style description\n - Characters and their descriptions\n - Conversation turns:\n - Text / message turn: This represents part of the story or role play\n - Instruction: This tells the model what should happen next\n- Output: Continuation of the story / role-play.",
"### Story plot summarization\n\n- Prompt guide\n- Input: A story, or a few chapters of a story.\n- Output: A description of the story or chapters.",
"#### Examples:\n\n<details>\n <summary>Summary of <a href=\"URL fiction story</a> in 50 words</summary>\n <blockquote>\n Malygris, a powerful magician, summons his long-dead lover Nylissa from the grave using necromancy. However, upon seeing her, he realizes that she is not the same person he once knew, leading him to question the nature of love, memory, and the power of magic.\n </blockquote>\n</details>\n<details>\n <summary>Summary of <a href=\"URL fiction story</a> in 200 words</summary>\n <blockquote>\nThe story is a dark fantasy set in the city of Susran, where an ancient and powerful magician named Malygris dwells in a tower atop a conical hill. Malygris, who has mastered all forms of sorcery and necromancy, is plagued by a deep sense of ennui and melancholy. He seeks solace in the memory of Nylissa, a girl he once loved in his youth.\n\nOne day, Malygris decides to summon Nylissa's spirit from the grave using his necromantic powers. He performs the necessary rituals and incantations, and Nylissa appears before him as a ghostly apparition. However, as Malygris gazes upon her, he becomes increasingly disillusioned. He notices subtle changes in her appearance and behavior that do not match his memories of her. He begins to question whether this is truly the same Nylissa he once knew, or if it is just another illusion conjured by his magic.\n\nAs Malygris grapples with this uncertainty, he becomes increasingly despondent and disillusioned with life itself. He realizes that even his magic cannot bring back the past or make him truly happy. In the end, he dismisses Nylissa's spirit and returns to his lonely tower, resigned to his fate as an old and weary sorcerer.\n </blockquote>\n\n</details>\n<details>\n <summary>Summary of <a href=\"URL News article</a> in 150 words</summary>\n <blockquote>\nThe article discusses the recent human deaths from diseases transmitted by animals, specifically Alaskapox and bubonic plague. Dr. Leana Wen, an emergency physician and former Baltimore health commissioner, explains the various ways household pets can transmit diseases to humans. These include fecal-oral transmission, scratches and bites, and vector-borne diseases like ticks, fleas, and mosquitoes. Wen emphasizes the importance of vaccinating pets, maintaining cleanliness, and taking commonsense precautions to reduce disease transmission. She also advises that individuals who are immunocompromised, babies, and pregnant women should take additional care when interacting with animals.\n </blockquote>\n</details>\n<details>\n <summary>Summary of <a href=\"URL News article</a> in 50 words</summary>\n <blockquote>\nA doctor discusses the risks of diseases transmitted from animals to humans, focusing on household pets like cats and dogs. They emphasize the importance of vaccination, hygiene, and regular veterinary care to prevent these illnesses.\n </blockquote>\n</details>",
"### Story character description\n\n- Prompt guide\n- Input: A story, or a few chapters of a story, set of characters.\n- Output: A description of the characters.",
"#### Examples:\n\n<details>\n <summary>Description of the Malygris character from <a href=\"URL story</a> in 50 words</summary>\n <blockquote>\nMalygris is an ancient and powerful magician, characterized by his long white beard, cold green eyes, and a violet robe. He is a master of necromancy and possesses a vast knowledge of forbidden magic. Despite his immense power, he is plagued by a deep sense of melancholy and ennui.\n </blockquote>\n</details>\n\n<details>\n <summary>Description of the prince character from <a href=\"URL story</a> in 50 words</summary>\n <blockquote>\nThe prince is a devoted and determined individual, driven by his love for his late queen. He is described as a graceful youth in the beginning, but as he grows older, his dedication to the Pearl of Love transforms him into a grave and intent man. His sense of color and design evolves over time, reflecting his growing maturity and artistic vision.\n </blockquote>\n</details>",
"### Story style description\n\n- Prompt guide\n- Input: A story, or a few chapters of a story.\n- Output: A description the style of the story.\n\n<details>\n <summary>Style description of <a href=\"URL story</a></summary>\n <blockquote>\nThe story is written in a descriptive and evocative style, with a focus on the atmosphere and setting. The author uses vivid and detailed language to create a sense of place and time, and employs a variety of literary devices such as similes, metaphors, and allusions to enhance the mood and tone of the narrative. The sentence structure is varied, with a mix of short and long sentences that create a rhythmic flow to the prose.\n </blockquote>\n</details>\n\n<details>\n <summary>Style description of <a href=\"URL story</a></summary>\n <blockquote>\nThe writing style is descriptive and evocative, with a focus on the beauty and grandeur of the Pearl of Love. The author uses vivid imagery and sensory details to create a rich and immersive atmosphere. The tone is reverential and contemplative, reflecting the prince's deep love for his queen and his dedication to creating a lasting monument to her memory.\n </blockquote>\n</details>",
"### Story description to chapters\n\n- Prompt guide\n- Input: A brief plot description and the desired number of chapters.\n- Output: A description for each chapter.",
"### And more...",
"## Sampling params\n\nFor story-writing and role-play, I recommend \"Min P\" based sampling with 'min_p' in the range '[0.01, 0.1]' and with 'temperature' in the range '[0.5, 1.5]', depending on your preferences. A good starting point would be 'min_p=0.1; temperature=0.8'.\n\nYou may also benefit from setting presence, frequency and repetition penalties, especially at lower temperatures.",
"## Dataset\n\nThe fine-tuning dataset consisted of ~100M tokens of steerable story-writing, role-playing, writing-assistant and general-assistant examples. Each example was up to 31000 tokens long.\n\nAll story-writing and role-playing examples were based on human-written text.\n\n!token count distribution",
"## Running the model\n\nThe model is should be compatible with any software that supports the base model, but beware of prompting and tokenization.\n\nI recommend using these model versions:\n\n- 7B: no quant (opus-v1.2-7b)\n- 34B: no quant (opus-v1-34b) or awq (opus-v1-34b-awq)\n- 34B: no quant (opus-v1.2-70b) or awq (opus-v1.2-70b-awq)",
"### Running on URL (free)\n\nYou can run the models on URL for free — you can use the built-in UI for story-writing & role-playing, or use the API.",
"### Running Locally\n\n- Make sure your prompt is as close as possible to the Opus V1\n - Regardless of which backend you use, it's important that you format your prompt well and that the tokenization works correctly.\n - Read the prompt guide\n - Read the prompt formatting code\n - Make sure '<|im_start|>' and '<|im_end|>' are tokenized correctly\n- vLLM\n - Google Colab: This is a simple interactive Google Colab to do role-play with the 7B model, it should fit on the T4 GPU.\n - Code: This is simple script for interactive chat for one hard-coded scenario.\n- SillyTavern\n - Official SillyTavern documentation for DreamGen -- applies to both the API an local models\n - SillyTavern (staging) comes with built-in DreamGen preset for RP\n - Other presets can be found here, v2 kindly provided by @MarinaraSpaghetti\n - Make sure to unselect 'Skip special tokens', otherwise it won't work\n - This is just an attempt at approximating the Opus V1 prompt, it won't be perfect\n - Character cards specifically rewritten for the built-in DreamGen preset:\n - Seraphina (based on the default Seraphina card)\n - Lara Lightland (based on the card by Deffcolony)\n- LM Studio\n - Config\n - Just like ChatML, just changed \"assistant\" to \"text\" role.\n - There's a bug in LM Studio if you delete a message or click \"Continue\", see here for details.\n- HuggingFace\n - Chat template\n - Just like ChatML, just changed \"assistant\" to \"text\" role.",
"## Known Issues\n\n- 34B repetition:\n - The 34B sometimes gets stuck repeating the same word, or synonyms. This seems to be a common problem across various Yi 34B fine-tunes.\n- GGUF:\n - The tokenization might be messed up. Some users reported that '<|im_start|>' and '<|im_end|>' are tokenized as multiple tokens. Also URL may not tokenize correctly (the Yi tokenizer is subtly different from the Llama 2 tokenizer).",
"## License\n\n- This model is intended for personal use only, other use is not permitted."
] |
null | transformers |
# Uploaded model
- **Developed by:** saraktareen
- **License:** apache-2.0
- **Finetuned from model :** unsloth/gemma-7b-bnb-4bit
This gemma model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
| {"language": ["en"], "license": "apache-2.0", "tags": ["text-generation-inference", "transformers", "unsloth", "gemma", "trl"], "base_model": "unsloth/gemma-7b-bnb-4bit"} | saraktareen/Gemma_Urdu_Hindi_Bollywood_Songs | null | [
"transformers",
"safetensors",
"text-generation-inference",
"unsloth",
"gemma",
"trl",
"en",
"base_model:unsloth/gemma-7b-bnb-4bit",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | 2024-04-19T13:20:26+00:00 | [] | [
"en"
] | TAGS
#transformers #safetensors #text-generation-inference #unsloth #gemma #trl #en #base_model-unsloth/gemma-7b-bnb-4bit #license-apache-2.0 #endpoints_compatible #region-us
|
# Uploaded model
- Developed by: saraktareen
- License: apache-2.0
- Finetuned from model : unsloth/gemma-7b-bnb-4bit
This gemma model was trained 2x faster with Unsloth and Huggingface's TRL library.
<img src="URL width="200"/>
| [
"# Uploaded model\n\n- Developed by: saraktareen\n- License: apache-2.0\n- Finetuned from model : unsloth/gemma-7b-bnb-4bit\n\nThis gemma model was trained 2x faster with Unsloth and Huggingface's TRL library.\n\n<img src=\"URL width=\"200\"/>"
] | [
"TAGS\n#transformers #safetensors #text-generation-inference #unsloth #gemma #trl #en #base_model-unsloth/gemma-7b-bnb-4bit #license-apache-2.0 #endpoints_compatible #region-us \n",
"# Uploaded model\n\n- Developed by: saraktareen\n- License: apache-2.0\n- Finetuned from model : unsloth/gemma-7b-bnb-4bit\n\nThis gemma model was trained 2x faster with Unsloth and Huggingface's TRL library.\n\n<img src=\"URL width=\"200\"/>"
] |
text-generation | transformers |
# Llama 3 DreamGen Opus V1
<div style="display: flex; flex-direction: row; align-items: center;">
<img src="/dreamgen/opus-v1.2-llama-3-8b/resolve/main/images/logo-1024.png" alt="model logo" style="
border-radius: 12px;
margin-right: 12px;
margin-top: 0px;
margin-bottom: 0px;
max-width: 100px;
height: auto;
"/>
Models for **(steerable) story-writing and role-playing**.
<br/>[All Opus V1 models, including quants](https://huggingface.co/collections/dreamgen/opus-v1-65d092a6f8ab7fc669111b31).
</div>
## Resources
- [**Opus V1 prompting guide**](https://dreamgen.com/docs/models/opus/v1) with many (interactive) examples and prompts that you can copy.
- [**Google Colab**](https://colab.research.google.com/drive/1J178fH6IdQOXNi-Njgdacf5QgAxsdT20?usp=sharing) for interactive role-play using `opus-v1.2-7b`.
- [Python code](example/prompt/format.py) to format the prompt correctly.
- Join the community on [**Discord**](https://dreamgen.com/discord) to get early access to new models.
<img src="/dreamgen/opus-v1.2-llama-3-8b/resolve/main/images/story_writing.webp" alt="story writing on dreamgen.com" style="
padding: 12px;
border-radius: 12px;
border: 2px solid #f9a8d4;
background: rgb(9, 9, 11);
"/>
## Prompting
<details>
<summary>The models use an extended version of ChatML.</summary>
```
<|im_start|>system
(Story description in the right format here)
(Typically consists of plot description, style description and characters)<|im_end|>
<|im_start|>user
(Your instruction on how the story should continue)<|im_end|>
<|im_start|>text names= Alice
(Continuation of the story from the Alice character)<|im_end|>
<|im_start|>text
(Continuation of the story from no character in particular (pure narration))<|im_end|>
<|im_start|>user
(Your instruction on how the story should continue)<|im_end|>
<|im_start|>text names= Bob
(Continuation of the story from the Bob character)<|im_end|>
```
The Opus V1 extension is the addition of the `text` role, and the addition / modification of role names.
Pay attention to the following:
- The `text` messages can (but don't have to have) `names`, names are used to indicate the "active" character during role-play.
- There can be multiple subsequent message with a `text` role, especially if names are involved.
- There can be multiple names attached to a message.
- The format for names is `names= {{name[0]}}; {{name[1]}}`, beware of the spaces after `names=` and after the `;`. This spacing leads to most natural tokenization for the names.
</details>
While the main goal for the models is great story-writing and role-playing performance, the models are also capable of several writing related tasks as well as general assistance.
Here's how you can prompt the model for the following tasks
### Steerable Story-writing and Role-playing:
- [Story-writing prompt guide](https://dreamgen.com/docs/models/opus/v1#task-story-writing)
- [Role-playing prompt guide](https://dreamgen.com/docs/models/opus/v1#task-role-playing)
- Input:
- System prompt: You provide story / role-play description, which consists of:
- Plot description
- Style description
- Characters and their descriptions
- Conversation turns:
- Text / message turn: This represents part of the story or role play
- Instruction: This tells the model what should happen next
- Output: Continuation of the story / role-play.
### Story plot summarization
- [Prompt guide](https://dreamgen.com/docs/models/opus/v1#task-plot-description)
- Input: A story, or a few chapters of a story.
- Output: A description of the story or chapters.
#### Examples:
<details>
<summary>Summary of <a href="https://www.libraryofshortstories.com/onlinereader/the-last-incantation">short fiction story</a> in 50 words</summary>
<blockquote>
Malygris, a powerful magician, summons his long-dead lover Nylissa from the grave using necromancy. However, upon seeing her, he realizes that she is not the same person he once knew, leading him to question the nature of love, memory, and the power of magic.
</blockquote>
</details>
<details>
<summary>Summary of <a href="https://www.libraryofshortstories.com/onlinereader/the-last-incantation">short fiction story</a> in 200 words</summary>
<blockquote>
The story is a dark fantasy set in the city of Susran, where an ancient and powerful magician named Malygris dwells in a tower atop a conical hill. Malygris, who has mastered all forms of sorcery and necromancy, is plagued by a deep sense of ennui and melancholy. He seeks solace in the memory of Nylissa, a girl he once loved in his youth.
One day, Malygris decides to summon Nylissa's spirit from the grave using his necromantic powers. He performs the necessary rituals and incantations, and Nylissa appears before him as a ghostly apparition. However, as Malygris gazes upon her, he becomes increasingly disillusioned. He notices subtle changes in her appearance and behavior that do not match his memories of her. He begins to question whether this is truly the same Nylissa he once knew, or if it is just another illusion conjured by his magic.
As Malygris grapples with this uncertainty, he becomes increasingly despondent and disillusioned with life itself. He realizes that even his magic cannot bring back the past or make him truly happy. In the end, he dismisses Nylissa's spirit and returns to his lonely tower, resigned to his fate as an old and weary sorcerer.
</blockquote>
</details>
<details>
<summary>Summary of <a href="https://edition.cnn.com/2024/02/29/health/pets-diseases-viruses-bacteria-wellness/index.html">CNN News article</a> in 150 words</summary>
<blockquote>
The article discusses the recent human deaths from diseases transmitted by animals, specifically Alaskapox and bubonic plague. Dr. Leana Wen, an emergency physician and former Baltimore health commissioner, explains the various ways household pets can transmit diseases to humans. These include fecal-oral transmission, scratches and bites, and vector-borne diseases like ticks, fleas, and mosquitoes. Wen emphasizes the importance of vaccinating pets, maintaining cleanliness, and taking commonsense precautions to reduce disease transmission. She also advises that individuals who are immunocompromised, babies, and pregnant women should take additional care when interacting with animals.
</blockquote>
</details>
<details>
<summary>Summary of <a href="https://edition.cnn.com/2024/02/29/health/pets-diseases-viruses-bacteria-wellness/index.html">CNN News article</a> in 50 words</summary>
<blockquote>
A doctor discusses the risks of diseases transmitted from animals to humans, focusing on household pets like cats and dogs. They emphasize the importance of vaccination, hygiene, and regular veterinary care to prevent these illnesses.
</blockquote>
</details>
### Story character description
- [Prompt guide](https://dreamgen.com/docs/models/opus/v1#task-char-description)
- Input: A story, or a few chapters of a story, set of characters.
- Output: A description of the characters.
#### Examples:
<details>
<summary>Description of the Malygris character from <a href="https://www.libraryofshortstories.com/onlinereader/the-last-incantation">this story</a> in 50 words</summary>
<blockquote>
Malygris is an ancient and powerful magician, characterized by his long white beard, cold green eyes, and a violet robe. He is a master of necromancy and possesses a vast knowledge of forbidden magic. Despite his immense power, he is plagued by a deep sense of melancholy and ennui.
</blockquote>
</details>
<details>
<summary>Description of the prince character from <a href="https://www.libraryofshortstories.com/onlinereader/the-pearl-of-love">this story</a> in 50 words</summary>
<blockquote>
The prince is a devoted and determined individual, driven by his love for his late queen. He is described as a graceful youth in the beginning, but as he grows older, his dedication to the Pearl of Love transforms him into a grave and intent man. His sense of color and design evolves over time, reflecting his growing maturity and artistic vision.
</blockquote>
</details>
### Story style description
- [Prompt guide](https://dreamgen.com/docs/models/opus/v1#task-style-description)
- Input: A story, or a few chapters of a story.
- Output: A description the style of the story.
<details>
<summary>Style description of <a href="https://www.libraryofshortstories.com/onlinereader/the-last-incantation">this story</a></summary>
<blockquote>
The story is written in a descriptive and evocative style, with a focus on the atmosphere and setting. The author uses vivid and detailed language to create a sense of place and time, and employs a variety of literary devices such as similes, metaphors, and allusions to enhance the mood and tone of the narrative. The sentence structure is varied, with a mix of short and long sentences that create a rhythmic flow to the prose.
</blockquote>
</details>
<details>
<summary>Style description of <a href="https://www.libraryofshortstories.com/onlinereader/the-pearl-of-love">this story</a></summary>
<blockquote>
The writing style is descriptive and evocative, with a focus on the beauty and grandeur of the Pearl of Love. The author uses vivid imagery and sensory details to create a rich and immersive atmosphere. The tone is reverential and contemplative, reflecting the prince's deep love for his queen and his dedication to creating a lasting monument to her memory.
</blockquote>
</details>
### Story description to chapters
- [Prompt guide](https://dreamgen.com/docs/models/opus/v1#task-story-description-to-chapter-descriptions)
- Input: A brief plot description and the desired number of chapters.
- Output: A description for each chapter.
### And more...
## Sampling params
For story-writing and role-play, I recommend "Min P" based sampling with `min_p` in the range `[0.01, 0.1]` and with `temperature` in the range `[0.5, 1.5]`, depending on your preferences. A good starting point would be `min_p=0.1; temperature=0.8`.
You may also benefit from setting presence, frequency and repetition penalties, especially at lower temperatures.
## Dataset
The fine-tuning dataset consisted of ~100M tokens of steerable story-writing, role-playing, writing-assistant and general-assistant examples. Each example was up to 31000 tokens long.
All story-writing and role-playing examples were based on human-written text.
## Running the model
The model is should be compatible with any software that supports the base model, but beware of prompting and tokenization.
I recommend using these model versions:
- 7B: [no quant (opus-v1.2-7b)](https://huggingface.co/dreamgen/opus-v1.2-7b)
- 34B: [no quant (opus-v1-34b)](https://huggingface.co/dreamgen/opus-v1-34b) or [awq (opus-v1-34b-awq)](https://huggingface.co/dreamgen/opus-v1-34b-awq)
- 34B: [no quant (opus-v1.2-70b)](https://huggingface.co/dreamgen/opus-v1.2-70b) or [awq (opus-v1.2-70b-awq)](https://huggingface.co/dreamgen/opus-v1.2-70b-awq)
### Running on DreamGen.com (free)
You can run the models on [dreamgen.com](https://dreamgen.com) for free — you can use the built-in UI for story-writing & role-playing, or use [the API](https://dreamgen.com/docs/api).
### Running Locally
- **Make sure your prompt is as close as possible to the Opus V1**
- Regardless of which backend you use, it's important that you format your prompt well and that the tokenization works correctly.
- [Read the prompt guide](https://dreamgen.com/docs/models/opus/v1)
- [Read the prompt formatting code](example/prompt/format.py)
- Make sure `<|im_start|>` and `<|im_end|>` are tokenized correctly
- **vLLM**
- [**Google Colab**](https://colab.research.google.com/drive/1J178fH6IdQOXNi-Njgdacf5QgAxsdT20?usp=sharing): This is a simple interactive Google Colab to do role-play with the 7B model, it should fit on the T4 GPU.
- [Code](example/prompt/interactive.py): This is simple script for interactive chat for one hard-coded scenario.
- **SillyTavern**
- [Official SillyTavern documentation for DreamGen](https://docs.sillytavern.app/usage/api-connections/dreamgen/) -- applies to both the API an local models
- SillyTavern (staging) comes with built-in DreamGen preset for RP
- Other presets can be found [here](https://huggingface.co/dreamgen/opus-v1.2-llama-3-8b/tree/main/configs/silly_tavern), v2 kindly provided by @MarinaraSpaghetti
- Make sure to unselect `Skip special tokens`, otherwise it won't work
- This is just an attempt at approximating the Opus V1 prompt, it won't be perfect
- Character cards specifically rewritten for the built-in DreamGen preset:
- [Seraphina](configs/silly_tavern/cards/Seraphina.png) (based on the default Seraphina card)
- [Lara Lightland](configs/silly_tavern/cards/LaraLightland.png) (based on the card by Deffcolony)
- **LM Studio**
- [Config](configs/lmstudio/preset.json)
- Just like ChatML, just changed "assistant" to "text" role.
- **There's a bug** in LM Studio if you delete a message or click "Continue", [see here for details](https://discord.com/channels/1110598183144399058/1212665261128417280/1212665261128417280).
- **HuggingFace**
- [Chat template](tokenizer_config.json#L51)
- Just like ChatML, just changed "assistant" to "text" role.
## Known Issues
- **34B repetition**:
- The 34B sometimes gets stuck repeating the same word, or synonyms. This seems to be a common problem across various Yi 34B fine-tunes.
- **GGUF**:
- The tokenization might be messed up. Some users reported that `<|im_start|>` and `<|im_end|>` are tokenized as multiple tokens. Also llama.cpp may not tokenize correctly (the Yi tokenizer is subtly different from the Llama 2 tokenizer).
## License
- This model is intended for personal use only, other use is not permitted.
| {"language": ["en"], "license": "cc-by-nc-nd-4.0", "tags": ["unsloth", "axolotl"], "pipeline_tag": "text-generation"} | LoneStriker/opus-v1.2-llama-3-8b-4.0bpw-h6-exl2 | null | [
"transformers",
"pytorch",
"safetensors",
"llama",
"text-generation",
"unsloth",
"axolotl",
"conversational",
"en",
"license:cc-by-nc-nd-4.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"4-bit",
"region:us"
] | null | 2024-04-19T13:21:13+00:00 | [] | [
"en"
] | TAGS
#transformers #pytorch #safetensors #llama #text-generation #unsloth #axolotl #conversational #en #license-cc-by-nc-nd-4.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #4-bit #region-us
|
# Llama 3 DreamGen Opus V1
<div style="display: flex; flex-direction: row; align-items: center;">
<img src="/dreamgen/opus-v1.2-llama-3-8b/resolve/main/images/URL" alt="model logo" style="
border-radius: 12px;
margin-right: 12px;
margin-top: 0px;
margin-bottom: 0px;
max-width: 100px;
height: auto;
"/>
Models for (steerable) story-writing and role-playing.
<br/>All Opus V1 models, including quants.
</div>
## Resources
- Opus V1 prompting guide with many (interactive) examples and prompts that you can copy.
- Google Colab for interactive role-play using 'opus-v1.2-7b'.
- Python code to format the prompt correctly.
- Join the community on Discord to get early access to new models.
<img src="/dreamgen/opus-v1.2-llama-3-8b/resolve/main/images/story_writing.webp" alt="story writing on URL" style="
padding: 12px;
border-radius: 12px;
border: 2px solid #f9a8d4;
background: rgb(9, 9, 11);
"/>
## Prompting
<details>
<summary>The models use an extended version of ChatML.</summary>
The Opus V1 extension is the addition of the 'text' role, and the addition / modification of role names.
Pay attention to the following:
- The 'text' messages can (but don't have to have) 'names', names are used to indicate the "active" character during role-play.
- There can be multiple subsequent message with a 'text' role, especially if names are involved.
- There can be multiple names attached to a message.
- The format for names is 'names= {{name[0]}}; {{name[1]}}', beware of the spaces after 'names=' and after the ';'. This spacing leads to most natural tokenization for the names.
</details>
While the main goal for the models is great story-writing and role-playing performance, the models are also capable of several writing related tasks as well as general assistance.
Here's how you can prompt the model for the following tasks
### Steerable Story-writing and Role-playing:
- Story-writing prompt guide
- Role-playing prompt guide
- Input:
- System prompt: You provide story / role-play description, which consists of:
- Plot description
- Style description
- Characters and their descriptions
- Conversation turns:
- Text / message turn: This represents part of the story or role play
- Instruction: This tells the model what should happen next
- Output: Continuation of the story / role-play.
### Story plot summarization
- Prompt guide
- Input: A story, or a few chapters of a story.
- Output: A description of the story or chapters.
#### Examples:
<details>
<summary>Summary of <a href="URL fiction story</a> in 50 words</summary>
<blockquote>
Malygris, a powerful magician, summons his long-dead lover Nylissa from the grave using necromancy. However, upon seeing her, he realizes that she is not the same person he once knew, leading him to question the nature of love, memory, and the power of magic.
</blockquote>
</details>
<details>
<summary>Summary of <a href="URL fiction story</a> in 200 words</summary>
<blockquote>
The story is a dark fantasy set in the city of Susran, where an ancient and powerful magician named Malygris dwells in a tower atop a conical hill. Malygris, who has mastered all forms of sorcery and necromancy, is plagued by a deep sense of ennui and melancholy. He seeks solace in the memory of Nylissa, a girl he once loved in his youth.
One day, Malygris decides to summon Nylissa's spirit from the grave using his necromantic powers. He performs the necessary rituals and incantations, and Nylissa appears before him as a ghostly apparition. However, as Malygris gazes upon her, he becomes increasingly disillusioned. He notices subtle changes in her appearance and behavior that do not match his memories of her. He begins to question whether this is truly the same Nylissa he once knew, or if it is just another illusion conjured by his magic.
As Malygris grapples with this uncertainty, he becomes increasingly despondent and disillusioned with life itself. He realizes that even his magic cannot bring back the past or make him truly happy. In the end, he dismisses Nylissa's spirit and returns to his lonely tower, resigned to his fate as an old and weary sorcerer.
</blockquote>
</details>
<details>
<summary>Summary of <a href="URL News article</a> in 150 words</summary>
<blockquote>
The article discusses the recent human deaths from diseases transmitted by animals, specifically Alaskapox and bubonic plague. Dr. Leana Wen, an emergency physician and former Baltimore health commissioner, explains the various ways household pets can transmit diseases to humans. These include fecal-oral transmission, scratches and bites, and vector-borne diseases like ticks, fleas, and mosquitoes. Wen emphasizes the importance of vaccinating pets, maintaining cleanliness, and taking commonsense precautions to reduce disease transmission. She also advises that individuals who are immunocompromised, babies, and pregnant women should take additional care when interacting with animals.
</blockquote>
</details>
<details>
<summary>Summary of <a href="URL News article</a> in 50 words</summary>
<blockquote>
A doctor discusses the risks of diseases transmitted from animals to humans, focusing on household pets like cats and dogs. They emphasize the importance of vaccination, hygiene, and regular veterinary care to prevent these illnesses.
</blockquote>
</details>
### Story character description
- Prompt guide
- Input: A story, or a few chapters of a story, set of characters.
- Output: A description of the characters.
#### Examples:
<details>
<summary>Description of the Malygris character from <a href="URL story</a> in 50 words</summary>
<blockquote>
Malygris is an ancient and powerful magician, characterized by his long white beard, cold green eyes, and a violet robe. He is a master of necromancy and possesses a vast knowledge of forbidden magic. Despite his immense power, he is plagued by a deep sense of melancholy and ennui.
</blockquote>
</details>
<details>
<summary>Description of the prince character from <a href="URL story</a> in 50 words</summary>
<blockquote>
The prince is a devoted and determined individual, driven by his love for his late queen. He is described as a graceful youth in the beginning, but as he grows older, his dedication to the Pearl of Love transforms him into a grave and intent man. His sense of color and design evolves over time, reflecting his growing maturity and artistic vision.
</blockquote>
</details>
### Story style description
- Prompt guide
- Input: A story, or a few chapters of a story.
- Output: A description the style of the story.
<details>
<summary>Style description of <a href="URL story</a></summary>
<blockquote>
The story is written in a descriptive and evocative style, with a focus on the atmosphere and setting. The author uses vivid and detailed language to create a sense of place and time, and employs a variety of literary devices such as similes, metaphors, and allusions to enhance the mood and tone of the narrative. The sentence structure is varied, with a mix of short and long sentences that create a rhythmic flow to the prose.
</blockquote>
</details>
<details>
<summary>Style description of <a href="URL story</a></summary>
<blockquote>
The writing style is descriptive and evocative, with a focus on the beauty and grandeur of the Pearl of Love. The author uses vivid imagery and sensory details to create a rich and immersive atmosphere. The tone is reverential and contemplative, reflecting the prince's deep love for his queen and his dedication to creating a lasting monument to her memory.
</blockquote>
</details>
### Story description to chapters
- Prompt guide
- Input: A brief plot description and the desired number of chapters.
- Output: A description for each chapter.
### And more...
## Sampling params
For story-writing and role-play, I recommend "Min P" based sampling with 'min_p' in the range '[0.01, 0.1]' and with 'temperature' in the range '[0.5, 1.5]', depending on your preferences. A good starting point would be 'min_p=0.1; temperature=0.8'.
You may also benefit from setting presence, frequency and repetition penalties, especially at lower temperatures.
## Dataset
The fine-tuning dataset consisted of ~100M tokens of steerable story-writing, role-playing, writing-assistant and general-assistant examples. Each example was up to 31000 tokens long.
All story-writing and role-playing examples were based on human-written text.
!token count distribution
## Running the model
The model is should be compatible with any software that supports the base model, but beware of prompting and tokenization.
I recommend using these model versions:
- 7B: no quant (opus-v1.2-7b)
- 34B: no quant (opus-v1-34b) or awq (opus-v1-34b-awq)
- 34B: no quant (opus-v1.2-70b) or awq (opus-v1.2-70b-awq)
### Running on URL (free)
You can run the models on URL for free — you can use the built-in UI for story-writing & role-playing, or use the API.
### Running Locally
- Make sure your prompt is as close as possible to the Opus V1
- Regardless of which backend you use, it's important that you format your prompt well and that the tokenization works correctly.
- Read the prompt guide
- Read the prompt formatting code
- Make sure '<|im_start|>' and '<|im_end|>' are tokenized correctly
- vLLM
- Google Colab: This is a simple interactive Google Colab to do role-play with the 7B model, it should fit on the T4 GPU.
- Code: This is simple script for interactive chat for one hard-coded scenario.
- SillyTavern
- Official SillyTavern documentation for DreamGen -- applies to both the API an local models
- SillyTavern (staging) comes with built-in DreamGen preset for RP
- Other presets can be found here, v2 kindly provided by @MarinaraSpaghetti
- Make sure to unselect 'Skip special tokens', otherwise it won't work
- This is just an attempt at approximating the Opus V1 prompt, it won't be perfect
- Character cards specifically rewritten for the built-in DreamGen preset:
- Seraphina (based on the default Seraphina card)
- Lara Lightland (based on the card by Deffcolony)
- LM Studio
- Config
- Just like ChatML, just changed "assistant" to "text" role.
- There's a bug in LM Studio if you delete a message or click "Continue", see here for details.
- HuggingFace
- Chat template
- Just like ChatML, just changed "assistant" to "text" role.
## Known Issues
- 34B repetition:
- The 34B sometimes gets stuck repeating the same word, or synonyms. This seems to be a common problem across various Yi 34B fine-tunes.
- GGUF:
- The tokenization might be messed up. Some users reported that '<|im_start|>' and '<|im_end|>' are tokenized as multiple tokens. Also URL may not tokenize correctly (the Yi tokenizer is subtly different from the Llama 2 tokenizer).
## License
- This model is intended for personal use only, other use is not permitted.
| [
"# Llama 3 DreamGen Opus V1\n\n<div style=\"display: flex; flex-direction: row; align-items: center;\">\n<img src=\"/dreamgen/opus-v1.2-llama-3-8b/resolve/main/images/URL\" alt=\"model logo\" style=\"\n border-radius: 12px;\n margin-right: 12px;\n margin-top: 0px;\n margin-bottom: 0px;\n max-width: 100px;\n height: auto;\n\"/>\n\nModels for (steerable) story-writing and role-playing.\n<br/>All Opus V1 models, including quants.\n\n</div>",
"## Resources\n\n- Opus V1 prompting guide with many (interactive) examples and prompts that you can copy.\n- Google Colab for interactive role-play using 'opus-v1.2-7b'.\n- Python code to format the prompt correctly.\n- Join the community on Discord to get early access to new models.\n\n<img src=\"/dreamgen/opus-v1.2-llama-3-8b/resolve/main/images/story_writing.webp\" alt=\"story writing on URL\" style=\"\n padding: 12px;\n border-radius: 12px;\n border: 2px solid #f9a8d4;\n background: rgb(9, 9, 11);\n\"/>",
"## Prompting\n\n<details>\n<summary>The models use an extended version of ChatML.</summary>\n\n\n\nThe Opus V1 extension is the addition of the 'text' role, and the addition / modification of role names.\n\nPay attention to the following:\n\n- The 'text' messages can (but don't have to have) 'names', names are used to indicate the \"active\" character during role-play.\n- There can be multiple subsequent message with a 'text' role, especially if names are involved.\n- There can be multiple names attached to a message.\n- The format for names is 'names= {{name[0]}}; {{name[1]}}', beware of the spaces after 'names=' and after the ';'. This spacing leads to most natural tokenization for the names.\n</details>\n\nWhile the main goal for the models is great story-writing and role-playing performance, the models are also capable of several writing related tasks as well as general assistance.\n\nHere's how you can prompt the model for the following tasks",
"### Steerable Story-writing and Role-playing:\n\n- Story-writing prompt guide\n- Role-playing prompt guide\n- Input:\n - System prompt: You provide story / role-play description, which consists of:\n - Plot description\n - Style description\n - Characters and their descriptions\n - Conversation turns:\n - Text / message turn: This represents part of the story or role play\n - Instruction: This tells the model what should happen next\n- Output: Continuation of the story / role-play.",
"### Story plot summarization\n\n- Prompt guide\n- Input: A story, or a few chapters of a story.\n- Output: A description of the story or chapters.",
"#### Examples:\n\n<details>\n <summary>Summary of <a href=\"URL fiction story</a> in 50 words</summary>\n <blockquote>\n Malygris, a powerful magician, summons his long-dead lover Nylissa from the grave using necromancy. However, upon seeing her, he realizes that she is not the same person he once knew, leading him to question the nature of love, memory, and the power of magic.\n </blockquote>\n</details>\n<details>\n <summary>Summary of <a href=\"URL fiction story</a> in 200 words</summary>\n <blockquote>\nThe story is a dark fantasy set in the city of Susran, where an ancient and powerful magician named Malygris dwells in a tower atop a conical hill. Malygris, who has mastered all forms of sorcery and necromancy, is plagued by a deep sense of ennui and melancholy. He seeks solace in the memory of Nylissa, a girl he once loved in his youth.\n\nOne day, Malygris decides to summon Nylissa's spirit from the grave using his necromantic powers. He performs the necessary rituals and incantations, and Nylissa appears before him as a ghostly apparition. However, as Malygris gazes upon her, he becomes increasingly disillusioned. He notices subtle changes in her appearance and behavior that do not match his memories of her. He begins to question whether this is truly the same Nylissa he once knew, or if it is just another illusion conjured by his magic.\n\nAs Malygris grapples with this uncertainty, he becomes increasingly despondent and disillusioned with life itself. He realizes that even his magic cannot bring back the past or make him truly happy. In the end, he dismisses Nylissa's spirit and returns to his lonely tower, resigned to his fate as an old and weary sorcerer.\n </blockquote>\n\n</details>\n<details>\n <summary>Summary of <a href=\"URL News article</a> in 150 words</summary>\n <blockquote>\nThe article discusses the recent human deaths from diseases transmitted by animals, specifically Alaskapox and bubonic plague. Dr. Leana Wen, an emergency physician and former Baltimore health commissioner, explains the various ways household pets can transmit diseases to humans. These include fecal-oral transmission, scratches and bites, and vector-borne diseases like ticks, fleas, and mosquitoes. Wen emphasizes the importance of vaccinating pets, maintaining cleanliness, and taking commonsense precautions to reduce disease transmission. She also advises that individuals who are immunocompromised, babies, and pregnant women should take additional care when interacting with animals.\n </blockquote>\n</details>\n<details>\n <summary>Summary of <a href=\"URL News article</a> in 50 words</summary>\n <blockquote>\nA doctor discusses the risks of diseases transmitted from animals to humans, focusing on household pets like cats and dogs. They emphasize the importance of vaccination, hygiene, and regular veterinary care to prevent these illnesses.\n </blockquote>\n</details>",
"### Story character description\n\n- Prompt guide\n- Input: A story, or a few chapters of a story, set of characters.\n- Output: A description of the characters.",
"#### Examples:\n\n<details>\n <summary>Description of the Malygris character from <a href=\"URL story</a> in 50 words</summary>\n <blockquote>\nMalygris is an ancient and powerful magician, characterized by his long white beard, cold green eyes, and a violet robe. He is a master of necromancy and possesses a vast knowledge of forbidden magic. Despite his immense power, he is plagued by a deep sense of melancholy and ennui.\n </blockquote>\n</details>\n\n<details>\n <summary>Description of the prince character from <a href=\"URL story</a> in 50 words</summary>\n <blockquote>\nThe prince is a devoted and determined individual, driven by his love for his late queen. He is described as a graceful youth in the beginning, but as he grows older, his dedication to the Pearl of Love transforms him into a grave and intent man. His sense of color and design evolves over time, reflecting his growing maturity and artistic vision.\n </blockquote>\n</details>",
"### Story style description\n\n- Prompt guide\n- Input: A story, or a few chapters of a story.\n- Output: A description the style of the story.\n\n<details>\n <summary>Style description of <a href=\"URL story</a></summary>\n <blockquote>\nThe story is written in a descriptive and evocative style, with a focus on the atmosphere and setting. The author uses vivid and detailed language to create a sense of place and time, and employs a variety of literary devices such as similes, metaphors, and allusions to enhance the mood and tone of the narrative. The sentence structure is varied, with a mix of short and long sentences that create a rhythmic flow to the prose.\n </blockquote>\n</details>\n\n<details>\n <summary>Style description of <a href=\"URL story</a></summary>\n <blockquote>\nThe writing style is descriptive and evocative, with a focus on the beauty and grandeur of the Pearl of Love. The author uses vivid imagery and sensory details to create a rich and immersive atmosphere. The tone is reverential and contemplative, reflecting the prince's deep love for his queen and his dedication to creating a lasting monument to her memory.\n </blockquote>\n</details>",
"### Story description to chapters\n\n- Prompt guide\n- Input: A brief plot description and the desired number of chapters.\n- Output: A description for each chapter.",
"### And more...",
"## Sampling params\n\nFor story-writing and role-play, I recommend \"Min P\" based sampling with 'min_p' in the range '[0.01, 0.1]' and with 'temperature' in the range '[0.5, 1.5]', depending on your preferences. A good starting point would be 'min_p=0.1; temperature=0.8'.\n\nYou may also benefit from setting presence, frequency and repetition penalties, especially at lower temperatures.",
"## Dataset\n\nThe fine-tuning dataset consisted of ~100M tokens of steerable story-writing, role-playing, writing-assistant and general-assistant examples. Each example was up to 31000 tokens long.\n\nAll story-writing and role-playing examples were based on human-written text.\n\n!token count distribution",
"## Running the model\n\nThe model is should be compatible with any software that supports the base model, but beware of prompting and tokenization.\n\nI recommend using these model versions:\n\n- 7B: no quant (opus-v1.2-7b)\n- 34B: no quant (opus-v1-34b) or awq (opus-v1-34b-awq)\n- 34B: no quant (opus-v1.2-70b) or awq (opus-v1.2-70b-awq)",
"### Running on URL (free)\n\nYou can run the models on URL for free — you can use the built-in UI for story-writing & role-playing, or use the API.",
"### Running Locally\n\n- Make sure your prompt is as close as possible to the Opus V1\n - Regardless of which backend you use, it's important that you format your prompt well and that the tokenization works correctly.\n - Read the prompt guide\n - Read the prompt formatting code\n - Make sure '<|im_start|>' and '<|im_end|>' are tokenized correctly\n- vLLM\n - Google Colab: This is a simple interactive Google Colab to do role-play with the 7B model, it should fit on the T4 GPU.\n - Code: This is simple script for interactive chat for one hard-coded scenario.\n- SillyTavern\n - Official SillyTavern documentation for DreamGen -- applies to both the API an local models\n - SillyTavern (staging) comes with built-in DreamGen preset for RP\n - Other presets can be found here, v2 kindly provided by @MarinaraSpaghetti\n - Make sure to unselect 'Skip special tokens', otherwise it won't work\n - This is just an attempt at approximating the Opus V1 prompt, it won't be perfect\n - Character cards specifically rewritten for the built-in DreamGen preset:\n - Seraphina (based on the default Seraphina card)\n - Lara Lightland (based on the card by Deffcolony)\n- LM Studio\n - Config\n - Just like ChatML, just changed \"assistant\" to \"text\" role.\n - There's a bug in LM Studio if you delete a message or click \"Continue\", see here for details.\n- HuggingFace\n - Chat template\n - Just like ChatML, just changed \"assistant\" to \"text\" role.",
"## Known Issues\n\n- 34B repetition:\n - The 34B sometimes gets stuck repeating the same word, or synonyms. This seems to be a common problem across various Yi 34B fine-tunes.\n- GGUF:\n - The tokenization might be messed up. Some users reported that '<|im_start|>' and '<|im_end|>' are tokenized as multiple tokens. Also URL may not tokenize correctly (the Yi tokenizer is subtly different from the Llama 2 tokenizer).",
"## License\n\n- This model is intended for personal use only, other use is not permitted."
] | [
"TAGS\n#transformers #pytorch #safetensors #llama #text-generation #unsloth #axolotl #conversational #en #license-cc-by-nc-nd-4.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #4-bit #region-us \n",
"# Llama 3 DreamGen Opus V1\n\n<div style=\"display: flex; flex-direction: row; align-items: center;\">\n<img src=\"/dreamgen/opus-v1.2-llama-3-8b/resolve/main/images/URL\" alt=\"model logo\" style=\"\n border-radius: 12px;\n margin-right: 12px;\n margin-top: 0px;\n margin-bottom: 0px;\n max-width: 100px;\n height: auto;\n\"/>\n\nModels for (steerable) story-writing and role-playing.\n<br/>All Opus V1 models, including quants.\n\n</div>",
"## Resources\n\n- Opus V1 prompting guide with many (interactive) examples and prompts that you can copy.\n- Google Colab for interactive role-play using 'opus-v1.2-7b'.\n- Python code to format the prompt correctly.\n- Join the community on Discord to get early access to new models.\n\n<img src=\"/dreamgen/opus-v1.2-llama-3-8b/resolve/main/images/story_writing.webp\" alt=\"story writing on URL\" style=\"\n padding: 12px;\n border-radius: 12px;\n border: 2px solid #f9a8d4;\n background: rgb(9, 9, 11);\n\"/>",
"## Prompting\n\n<details>\n<summary>The models use an extended version of ChatML.</summary>\n\n\n\nThe Opus V1 extension is the addition of the 'text' role, and the addition / modification of role names.\n\nPay attention to the following:\n\n- The 'text' messages can (but don't have to have) 'names', names are used to indicate the \"active\" character during role-play.\n- There can be multiple subsequent message with a 'text' role, especially if names are involved.\n- There can be multiple names attached to a message.\n- The format for names is 'names= {{name[0]}}; {{name[1]}}', beware of the spaces after 'names=' and after the ';'. This spacing leads to most natural tokenization for the names.\n</details>\n\nWhile the main goal for the models is great story-writing and role-playing performance, the models are also capable of several writing related tasks as well as general assistance.\n\nHere's how you can prompt the model for the following tasks",
"### Steerable Story-writing and Role-playing:\n\n- Story-writing prompt guide\n- Role-playing prompt guide\n- Input:\n - System prompt: You provide story / role-play description, which consists of:\n - Plot description\n - Style description\n - Characters and their descriptions\n - Conversation turns:\n - Text / message turn: This represents part of the story or role play\n - Instruction: This tells the model what should happen next\n- Output: Continuation of the story / role-play.",
"### Story plot summarization\n\n- Prompt guide\n- Input: A story, or a few chapters of a story.\n- Output: A description of the story or chapters.",
"#### Examples:\n\n<details>\n <summary>Summary of <a href=\"URL fiction story</a> in 50 words</summary>\n <blockquote>\n Malygris, a powerful magician, summons his long-dead lover Nylissa from the grave using necromancy. However, upon seeing her, he realizes that she is not the same person he once knew, leading him to question the nature of love, memory, and the power of magic.\n </blockquote>\n</details>\n<details>\n <summary>Summary of <a href=\"URL fiction story</a> in 200 words</summary>\n <blockquote>\nThe story is a dark fantasy set in the city of Susran, where an ancient and powerful magician named Malygris dwells in a tower atop a conical hill. Malygris, who has mastered all forms of sorcery and necromancy, is plagued by a deep sense of ennui and melancholy. He seeks solace in the memory of Nylissa, a girl he once loved in his youth.\n\nOne day, Malygris decides to summon Nylissa's spirit from the grave using his necromantic powers. He performs the necessary rituals and incantations, and Nylissa appears before him as a ghostly apparition. However, as Malygris gazes upon her, he becomes increasingly disillusioned. He notices subtle changes in her appearance and behavior that do not match his memories of her. He begins to question whether this is truly the same Nylissa he once knew, or if it is just another illusion conjured by his magic.\n\nAs Malygris grapples with this uncertainty, he becomes increasingly despondent and disillusioned with life itself. He realizes that even his magic cannot bring back the past or make him truly happy. In the end, he dismisses Nylissa's spirit and returns to his lonely tower, resigned to his fate as an old and weary sorcerer.\n </blockquote>\n\n</details>\n<details>\n <summary>Summary of <a href=\"URL News article</a> in 150 words</summary>\n <blockquote>\nThe article discusses the recent human deaths from diseases transmitted by animals, specifically Alaskapox and bubonic plague. Dr. Leana Wen, an emergency physician and former Baltimore health commissioner, explains the various ways household pets can transmit diseases to humans. These include fecal-oral transmission, scratches and bites, and vector-borne diseases like ticks, fleas, and mosquitoes. Wen emphasizes the importance of vaccinating pets, maintaining cleanliness, and taking commonsense precautions to reduce disease transmission. She also advises that individuals who are immunocompromised, babies, and pregnant women should take additional care when interacting with animals.\n </blockquote>\n</details>\n<details>\n <summary>Summary of <a href=\"URL News article</a> in 50 words</summary>\n <blockquote>\nA doctor discusses the risks of diseases transmitted from animals to humans, focusing on household pets like cats and dogs. They emphasize the importance of vaccination, hygiene, and regular veterinary care to prevent these illnesses.\n </blockquote>\n</details>",
"### Story character description\n\n- Prompt guide\n- Input: A story, or a few chapters of a story, set of characters.\n- Output: A description of the characters.",
"#### Examples:\n\n<details>\n <summary>Description of the Malygris character from <a href=\"URL story</a> in 50 words</summary>\n <blockquote>\nMalygris is an ancient and powerful magician, characterized by his long white beard, cold green eyes, and a violet robe. He is a master of necromancy and possesses a vast knowledge of forbidden magic. Despite his immense power, he is plagued by a deep sense of melancholy and ennui.\n </blockquote>\n</details>\n\n<details>\n <summary>Description of the prince character from <a href=\"URL story</a> in 50 words</summary>\n <blockquote>\nThe prince is a devoted and determined individual, driven by his love for his late queen. He is described as a graceful youth in the beginning, but as he grows older, his dedication to the Pearl of Love transforms him into a grave and intent man. His sense of color and design evolves over time, reflecting his growing maturity and artistic vision.\n </blockquote>\n</details>",
"### Story style description\n\n- Prompt guide\n- Input: A story, or a few chapters of a story.\n- Output: A description the style of the story.\n\n<details>\n <summary>Style description of <a href=\"URL story</a></summary>\n <blockquote>\nThe story is written in a descriptive and evocative style, with a focus on the atmosphere and setting. The author uses vivid and detailed language to create a sense of place and time, and employs a variety of literary devices such as similes, metaphors, and allusions to enhance the mood and tone of the narrative. The sentence structure is varied, with a mix of short and long sentences that create a rhythmic flow to the prose.\n </blockquote>\n</details>\n\n<details>\n <summary>Style description of <a href=\"URL story</a></summary>\n <blockquote>\nThe writing style is descriptive and evocative, with a focus on the beauty and grandeur of the Pearl of Love. The author uses vivid imagery and sensory details to create a rich and immersive atmosphere. The tone is reverential and contemplative, reflecting the prince's deep love for his queen and his dedication to creating a lasting monument to her memory.\n </blockquote>\n</details>",
"### Story description to chapters\n\n- Prompt guide\n- Input: A brief plot description and the desired number of chapters.\n- Output: A description for each chapter.",
"### And more...",
"## Sampling params\n\nFor story-writing and role-play, I recommend \"Min P\" based sampling with 'min_p' in the range '[0.01, 0.1]' and with 'temperature' in the range '[0.5, 1.5]', depending on your preferences. A good starting point would be 'min_p=0.1; temperature=0.8'.\n\nYou may also benefit from setting presence, frequency and repetition penalties, especially at lower temperatures.",
"## Dataset\n\nThe fine-tuning dataset consisted of ~100M tokens of steerable story-writing, role-playing, writing-assistant and general-assistant examples. Each example was up to 31000 tokens long.\n\nAll story-writing and role-playing examples were based on human-written text.\n\n!token count distribution",
"## Running the model\n\nThe model is should be compatible with any software that supports the base model, but beware of prompting and tokenization.\n\nI recommend using these model versions:\n\n- 7B: no quant (opus-v1.2-7b)\n- 34B: no quant (opus-v1-34b) or awq (opus-v1-34b-awq)\n- 34B: no quant (opus-v1.2-70b) or awq (opus-v1.2-70b-awq)",
"### Running on URL (free)\n\nYou can run the models on URL for free — you can use the built-in UI for story-writing & role-playing, or use the API.",
"### Running Locally\n\n- Make sure your prompt is as close as possible to the Opus V1\n - Regardless of which backend you use, it's important that you format your prompt well and that the tokenization works correctly.\n - Read the prompt guide\n - Read the prompt formatting code\n - Make sure '<|im_start|>' and '<|im_end|>' are tokenized correctly\n- vLLM\n - Google Colab: This is a simple interactive Google Colab to do role-play with the 7B model, it should fit on the T4 GPU.\n - Code: This is simple script for interactive chat for one hard-coded scenario.\n- SillyTavern\n - Official SillyTavern documentation for DreamGen -- applies to both the API an local models\n - SillyTavern (staging) comes with built-in DreamGen preset for RP\n - Other presets can be found here, v2 kindly provided by @MarinaraSpaghetti\n - Make sure to unselect 'Skip special tokens', otherwise it won't work\n - This is just an attempt at approximating the Opus V1 prompt, it won't be perfect\n - Character cards specifically rewritten for the built-in DreamGen preset:\n - Seraphina (based on the default Seraphina card)\n - Lara Lightland (based on the card by Deffcolony)\n- LM Studio\n - Config\n - Just like ChatML, just changed \"assistant\" to \"text\" role.\n - There's a bug in LM Studio if you delete a message or click \"Continue\", see here for details.\n- HuggingFace\n - Chat template\n - Just like ChatML, just changed \"assistant\" to \"text\" role.",
"## Known Issues\n\n- 34B repetition:\n - The 34B sometimes gets stuck repeating the same word, or synonyms. This seems to be a common problem across various Yi 34B fine-tunes.\n- GGUF:\n - The tokenization might be messed up. Some users reported that '<|im_start|>' and '<|im_end|>' are tokenized as multiple tokens. Also URL may not tokenize correctly (the Yi tokenizer is subtly different from the Llama 2 tokenizer).",
"## License\n\n- This model is intended for personal use only, other use is not permitted."
] |
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. -->
# deberta-v3-base-maftt
This model is a fine-tuned version of [microsoft/deberta-v3-base](https://huggingface.co/microsoft/deberta-v3-base) on the DandinPower/review_mergeallfeaturetotext dataset.
It achieves the following results on the evaluation set:
- Loss: 1.4616
- Accuracy: 0.6289
- Macro F1: 0.6302
## 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: 4.5e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 1500
- num_epochs: 5
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Macro F1 |
|:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:|
| 1.0302 | 0.14 | 500 | 1.0771 | 0.5511 | 0.5499 |
| 1.0412 | 0.29 | 1000 | 0.9406 | 0.5966 | 0.6030 |
| 0.9494 | 0.43 | 1500 | 0.9546 | 0.5949 | 0.5602 |
| 0.898 | 0.57 | 2000 | 1.0436 | 0.5957 | 0.5872 |
| 0.9171 | 0.71 | 2500 | 0.9004 | 0.622 | 0.6074 |
| 0.8856 | 0.86 | 3000 | 0.8741 | 0.6137 | 0.5990 |
| 0.9359 | 1.0 | 3500 | 0.8821 | 0.6267 | 0.6245 |
| 0.8626 | 1.14 | 4000 | 0.8859 | 0.6213 | 0.6200 |
| 0.7953 | 1.29 | 4500 | 0.8606 | 0.6337 | 0.6271 |
| 0.8206 | 1.43 | 5000 | 0.8543 | 0.6169 | 0.6202 |
| 0.8184 | 1.57 | 5500 | 0.9360 | 0.6266 | 0.6165 |
| 0.8044 | 1.71 | 6000 | 0.8606 | 0.6234 | 0.6227 |
| 0.7094 | 1.86 | 6500 | 0.8842 | 0.6434 | 0.6387 |
| 0.8264 | 2.0 | 7000 | 0.9063 | 0.612 | 0.6128 |
| 0.6951 | 2.14 | 7500 | 0.8782 | 0.6386 | 0.6415 |
| 0.704 | 2.29 | 8000 | 0.9510 | 0.6326 | 0.6308 |
| 0.6806 | 2.43 | 8500 | 0.8709 | 0.6413 | 0.6455 |
| 0.6983 | 2.57 | 9000 | 0.8977 | 0.6426 | 0.6436 |
| 0.6852 | 2.71 | 9500 | 0.9686 | 0.5984 | 0.6010 |
| 0.6761 | 2.86 | 10000 | 0.8961 | 0.6386 | 0.6406 |
| 0.6804 | 3.0 | 10500 | 0.9378 | 0.6307 | 0.6332 |
| 0.5329 | 3.14 | 11000 | 1.1209 | 0.6341 | 0.6382 |
| 0.5461 | 3.29 | 11500 | 1.0323 | 0.6393 | 0.6377 |
| 0.5725 | 3.43 | 12000 | 1.0678 | 0.6334 | 0.6366 |
| 0.5499 | 3.57 | 12500 | 1.0547 | 0.6374 | 0.6394 |
| 0.5218 | 3.71 | 13000 | 1.0524 | 0.6453 | 0.6460 |
| 0.5022 | 3.86 | 13500 | 1.1100 | 0.6363 | 0.6358 |
| 0.534 | 4.0 | 14000 | 1.0378 | 0.6357 | 0.6386 |
| 0.3823 | 4.14 | 14500 | 1.3985 | 0.6357 | 0.6357 |
| 0.4518 | 4.29 | 15000 | 1.3265 | 0.6314 | 0.6318 |
| 0.4147 | 4.43 | 15500 | 1.3946 | 0.631 | 0.6324 |
| 0.3936 | 4.57 | 16000 | 1.4649 | 0.6279 | 0.6308 |
| 0.4339 | 4.71 | 16500 | 1.5322 | 0.6286 | 0.6314 |
| 0.4448 | 4.86 | 17000 | 1.4890 | 0.629 | 0.6302 |
| 0.4006 | 5.0 | 17500 | 1.4616 | 0.6289 | 0.6302 |
### Framework versions
- Transformers 4.39.3
- Pytorch 2.2.2+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
| {"language": ["en"], "license": "mit", "tags": ["nycu-112-2-datamining-hw2", "generated_from_trainer"], "datasets": ["DandinPower/review_mergeallfeaturetotext"], "metrics": ["accuracy"], "base_model": "microsoft/deberta-v3-base", "model-index": [{"name": "deberta-v3-base-maftt", "results": [{"task": {"type": "text-classification", "name": "Text Classification"}, "dataset": {"name": "DandinPower/review_mergeallfeaturetotext", "type": "DandinPower/review_mergeallfeaturetotext"}, "metrics": [{"type": "accuracy", "value": 0.6288571428571429, "name": "Accuracy"}]}]}]} | DandinPower/deberta-v3-base-maftt | null | [
"transformers",
"safetensors",
"deberta-v2",
"text-classification",
"nycu-112-2-datamining-hw2",
"generated_from_trainer",
"en",
"dataset:DandinPower/review_mergeallfeaturetotext",
"base_model:microsoft/deberta-v3-base",
"license:mit",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | null | 2024-04-19T13:21:23+00:00 | [] | [
"en"
] | TAGS
#transformers #safetensors #deberta-v2 #text-classification #nycu-112-2-datamining-hw2 #generated_from_trainer #en #dataset-DandinPower/review_mergeallfeaturetotext #base_model-microsoft/deberta-v3-base #license-mit #model-index #autotrain_compatible #endpoints_compatible #region-us
| deberta-v3-base-maftt
=====================
This model is a fine-tuned version of microsoft/deberta-v3-base on the DandinPower/review\_mergeallfeaturetotext dataset.
It achieves the following results on the evaluation set:
* Loss: 1.4616
* Accuracy: 0.6289
* Macro F1: 0.6302
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: 4.5e-05
* train\_batch\_size: 8
* eval\_batch\_size: 8
* seed: 42
* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
* lr\_scheduler\_type: linear
* lr\_scheduler\_warmup\_steps: 1500
* num\_epochs: 5
### 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: 4.5e-05\n* train\\_batch\\_size: 8\n* eval\\_batch\\_size: 8\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* lr\\_scheduler\\_warmup\\_steps: 1500\n* num\\_epochs: 5",
"### 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 #deberta-v2 #text-classification #nycu-112-2-datamining-hw2 #generated_from_trainer #en #dataset-DandinPower/review_mergeallfeaturetotext #base_model-microsoft/deberta-v3-base #license-mit #model-index #autotrain_compatible #endpoints_compatible #region-us \n",
"### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 4.5e-05\n* train\\_batch\\_size: 8\n* eval\\_batch\\_size: 8\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* lr\\_scheduler\\_warmup\\_steps: 1500\n* num\\_epochs: 5",
"### 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"
] |
text2text-generation | transformers |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# UrduSum6
This model is a fine-tuned version of [ahmed0189/mT5-Arabic-text-summarization](https://huggingface.co/ahmed0189/mT5-Arabic-text-summarization) on the None dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 1
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
| No log | 1.0 | 147 | 3.6410 | 4.6547 | 1.7375 | 4.8048 | 4.8048 | 31.8514 |
### Framework versions
- Transformers 4.28.0
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.13.3
| {"license": "apache-2.0", "tags": ["generated_from_trainer"], "model-index": [{"name": "UrduSum6", "results": []}]} | Alefiah/UrduSum6 | null | [
"transformers",
"pytorch",
"tensorboard",
"mt5",
"text2text-generation",
"generated_from_trainer",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-04-19T13:22:17+00:00 | [] | [] | TAGS
#transformers #pytorch #tensorboard #mt5 #text2text-generation #generated_from_trainer #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us
| UrduSum6
========
This model is a fine-tuned version of ahmed0189/mT5-Arabic-text-summarization on the None dataset.
Model description
-----------------
More information needed
Intended uses & limitations
---------------------------
More information needed
Training and evaluation data
----------------------------
More information needed
Training procedure
------------------
### Training hyperparameters
The following hyperparameters were used during training:
* learning\_rate: 2e-05
* train\_batch\_size: 2
* eval\_batch\_size: 2
* seed: 42
* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
* lr\_scheduler\_type: linear
* num\_epochs: 1
* mixed\_precision\_training: Native AMP
### Training results
### Framework versions
* Transformers 4.28.0
* Pytorch 2.2.1+cu121
* Datasets 2.19.0
* Tokenizers 0.13.3
| [
"### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 2e-05\n* train\\_batch\\_size: 2\n* eval\\_batch\\_size: 2\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 1\n* mixed\\_precision\\_training: Native AMP",
"### Training results",
"### Framework versions\n\n\n* Transformers 4.28.0\n* Pytorch 2.2.1+cu121\n* Datasets 2.19.0\n* Tokenizers 0.13.3"
] | [
"TAGS\n#transformers #pytorch #tensorboard #mt5 #text2text-generation #generated_from_trainer #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n",
"### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 2e-05\n* train\\_batch\\_size: 2\n* eval\\_batch\\_size: 2\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 1\n* mixed\\_precision\\_training: Native AMP",
"### Training results",
"### Framework versions\n\n\n* Transformers 4.28.0\n* Pytorch 2.2.1+cu121\n* Datasets 2.19.0\n* Tokenizers 0.13.3"
] |
text-generation | transformers |
# Llama 3 DreamGen Opus V1
<div style="display: flex; flex-direction: row; align-items: center;">
<img src="/dreamgen/opus-v1.2-llama-3-8b/resolve/main/images/logo-1024.png" alt="model logo" style="
border-radius: 12px;
margin-right: 12px;
margin-top: 0px;
margin-bottom: 0px;
max-width: 100px;
height: auto;
"/>
Models for **(steerable) story-writing and role-playing**.
<br/>[All Opus V1 models, including quants](https://huggingface.co/collections/dreamgen/opus-v1-65d092a6f8ab7fc669111b31).
</div>
## Resources
- [**Opus V1 prompting guide**](https://dreamgen.com/docs/models/opus/v1) with many (interactive) examples and prompts that you can copy.
- [**Google Colab**](https://colab.research.google.com/drive/1J178fH6IdQOXNi-Njgdacf5QgAxsdT20?usp=sharing) for interactive role-play using `opus-v1.2-7b`.
- [Python code](example/prompt/format.py) to format the prompt correctly.
- Join the community on [**Discord**](https://dreamgen.com/discord) to get early access to new models.
<img src="/dreamgen/opus-v1.2-llama-3-8b/resolve/main/images/story_writing.webp" alt="story writing on dreamgen.com" style="
padding: 12px;
border-radius: 12px;
border: 2px solid #f9a8d4;
background: rgb(9, 9, 11);
"/>
## Prompting
<details>
<summary>The models use an extended version of ChatML.</summary>
```
<|im_start|>system
(Story description in the right format here)
(Typically consists of plot description, style description and characters)<|im_end|>
<|im_start|>user
(Your instruction on how the story should continue)<|im_end|>
<|im_start|>text names= Alice
(Continuation of the story from the Alice character)<|im_end|>
<|im_start|>text
(Continuation of the story from no character in particular (pure narration))<|im_end|>
<|im_start|>user
(Your instruction on how the story should continue)<|im_end|>
<|im_start|>text names= Bob
(Continuation of the story from the Bob character)<|im_end|>
```
The Opus V1 extension is the addition of the `text` role, and the addition / modification of role names.
Pay attention to the following:
- The `text` messages can (but don't have to have) `names`, names are used to indicate the "active" character during role-play.
- There can be multiple subsequent message with a `text` role, especially if names are involved.
- There can be multiple names attached to a message.
- The format for names is `names= {{name[0]}}; {{name[1]}}`, beware of the spaces after `names=` and after the `;`. This spacing leads to most natural tokenization for the names.
</details>
While the main goal for the models is great story-writing and role-playing performance, the models are also capable of several writing related tasks as well as general assistance.
Here's how you can prompt the model for the following tasks
### Steerable Story-writing and Role-playing:
- [Story-writing prompt guide](https://dreamgen.com/docs/models/opus/v1#task-story-writing)
- [Role-playing prompt guide](https://dreamgen.com/docs/models/opus/v1#task-role-playing)
- Input:
- System prompt: You provide story / role-play description, which consists of:
- Plot description
- Style description
- Characters and their descriptions
- Conversation turns:
- Text / message turn: This represents part of the story or role play
- Instruction: This tells the model what should happen next
- Output: Continuation of the story / role-play.
### Story plot summarization
- [Prompt guide](https://dreamgen.com/docs/models/opus/v1#task-plot-description)
- Input: A story, or a few chapters of a story.
- Output: A description of the story or chapters.
#### Examples:
<details>
<summary>Summary of <a href="https://www.libraryofshortstories.com/onlinereader/the-last-incantation">short fiction story</a> in 50 words</summary>
<blockquote>
Malygris, a powerful magician, summons his long-dead lover Nylissa from the grave using necromancy. However, upon seeing her, he realizes that she is not the same person he once knew, leading him to question the nature of love, memory, and the power of magic.
</blockquote>
</details>
<details>
<summary>Summary of <a href="https://www.libraryofshortstories.com/onlinereader/the-last-incantation">short fiction story</a> in 200 words</summary>
<blockquote>
The story is a dark fantasy set in the city of Susran, where an ancient and powerful magician named Malygris dwells in a tower atop a conical hill. Malygris, who has mastered all forms of sorcery and necromancy, is plagued by a deep sense of ennui and melancholy. He seeks solace in the memory of Nylissa, a girl he once loved in his youth.
One day, Malygris decides to summon Nylissa's spirit from the grave using his necromantic powers. He performs the necessary rituals and incantations, and Nylissa appears before him as a ghostly apparition. However, as Malygris gazes upon her, he becomes increasingly disillusioned. He notices subtle changes in her appearance and behavior that do not match his memories of her. He begins to question whether this is truly the same Nylissa he once knew, or if it is just another illusion conjured by his magic.
As Malygris grapples with this uncertainty, he becomes increasingly despondent and disillusioned with life itself. He realizes that even his magic cannot bring back the past or make him truly happy. In the end, he dismisses Nylissa's spirit and returns to his lonely tower, resigned to his fate as an old and weary sorcerer.
</blockquote>
</details>
<details>
<summary>Summary of <a href="https://edition.cnn.com/2024/02/29/health/pets-diseases-viruses-bacteria-wellness/index.html">CNN News article</a> in 150 words</summary>
<blockquote>
The article discusses the recent human deaths from diseases transmitted by animals, specifically Alaskapox and bubonic plague. Dr. Leana Wen, an emergency physician and former Baltimore health commissioner, explains the various ways household pets can transmit diseases to humans. These include fecal-oral transmission, scratches and bites, and vector-borne diseases like ticks, fleas, and mosquitoes. Wen emphasizes the importance of vaccinating pets, maintaining cleanliness, and taking commonsense precautions to reduce disease transmission. She also advises that individuals who are immunocompromised, babies, and pregnant women should take additional care when interacting with animals.
</blockquote>
</details>
<details>
<summary>Summary of <a href="https://edition.cnn.com/2024/02/29/health/pets-diseases-viruses-bacteria-wellness/index.html">CNN News article</a> in 50 words</summary>
<blockquote>
A doctor discusses the risks of diseases transmitted from animals to humans, focusing on household pets like cats and dogs. They emphasize the importance of vaccination, hygiene, and regular veterinary care to prevent these illnesses.
</blockquote>
</details>
### Story character description
- [Prompt guide](https://dreamgen.com/docs/models/opus/v1#task-char-description)
- Input: A story, or a few chapters of a story, set of characters.
- Output: A description of the characters.
#### Examples:
<details>
<summary>Description of the Malygris character from <a href="https://www.libraryofshortstories.com/onlinereader/the-last-incantation">this story</a> in 50 words</summary>
<blockquote>
Malygris is an ancient and powerful magician, characterized by his long white beard, cold green eyes, and a violet robe. He is a master of necromancy and possesses a vast knowledge of forbidden magic. Despite his immense power, he is plagued by a deep sense of melancholy and ennui.
</blockquote>
</details>
<details>
<summary>Description of the prince character from <a href="https://www.libraryofshortstories.com/onlinereader/the-pearl-of-love">this story</a> in 50 words</summary>
<blockquote>
The prince is a devoted and determined individual, driven by his love for his late queen. He is described as a graceful youth in the beginning, but as he grows older, his dedication to the Pearl of Love transforms him into a grave and intent man. His sense of color and design evolves over time, reflecting his growing maturity and artistic vision.
</blockquote>
</details>
### Story style description
- [Prompt guide](https://dreamgen.com/docs/models/opus/v1#task-style-description)
- Input: A story, or a few chapters of a story.
- Output: A description the style of the story.
<details>
<summary>Style description of <a href="https://www.libraryofshortstories.com/onlinereader/the-last-incantation">this story</a></summary>
<blockquote>
The story is written in a descriptive and evocative style, with a focus on the atmosphere and setting. The author uses vivid and detailed language to create a sense of place and time, and employs a variety of literary devices such as similes, metaphors, and allusions to enhance the mood and tone of the narrative. The sentence structure is varied, with a mix of short and long sentences that create a rhythmic flow to the prose.
</blockquote>
</details>
<details>
<summary>Style description of <a href="https://www.libraryofshortstories.com/onlinereader/the-pearl-of-love">this story</a></summary>
<blockquote>
The writing style is descriptive and evocative, with a focus on the beauty and grandeur of the Pearl of Love. The author uses vivid imagery and sensory details to create a rich and immersive atmosphere. The tone is reverential and contemplative, reflecting the prince's deep love for his queen and his dedication to creating a lasting monument to her memory.
</blockquote>
</details>
### Story description to chapters
- [Prompt guide](https://dreamgen.com/docs/models/opus/v1#task-story-description-to-chapter-descriptions)
- Input: A brief plot description and the desired number of chapters.
- Output: A description for each chapter.
### And more...
## Sampling params
For story-writing and role-play, I recommend "Min P" based sampling with `min_p` in the range `[0.01, 0.1]` and with `temperature` in the range `[0.5, 1.5]`, depending on your preferences. A good starting point would be `min_p=0.1; temperature=0.8`.
You may also benefit from setting presence, frequency and repetition penalties, especially at lower temperatures.
## Dataset
The fine-tuning dataset consisted of ~100M tokens of steerable story-writing, role-playing, writing-assistant and general-assistant examples. Each example was up to 31000 tokens long.
All story-writing and role-playing examples were based on human-written text.
## Running the model
The model is should be compatible with any software that supports the base model, but beware of prompting and tokenization.
I recommend using these model versions:
- 7B: [no quant (opus-v1.2-7b)](https://huggingface.co/dreamgen/opus-v1.2-7b)
- 34B: [no quant (opus-v1-34b)](https://huggingface.co/dreamgen/opus-v1-34b) or [awq (opus-v1-34b-awq)](https://huggingface.co/dreamgen/opus-v1-34b-awq)
- 34B: [no quant (opus-v1.2-70b)](https://huggingface.co/dreamgen/opus-v1.2-70b) or [awq (opus-v1.2-70b-awq)](https://huggingface.co/dreamgen/opus-v1.2-70b-awq)
### Running on DreamGen.com (free)
You can run the models on [dreamgen.com](https://dreamgen.com) for free — you can use the built-in UI for story-writing & role-playing, or use [the API](https://dreamgen.com/docs/api).
### Running Locally
- **Make sure your prompt is as close as possible to the Opus V1**
- Regardless of which backend you use, it's important that you format your prompt well and that the tokenization works correctly.
- [Read the prompt guide](https://dreamgen.com/docs/models/opus/v1)
- [Read the prompt formatting code](example/prompt/format.py)
- Make sure `<|im_start|>` and `<|im_end|>` are tokenized correctly
- **vLLM**
- [**Google Colab**](https://colab.research.google.com/drive/1J178fH6IdQOXNi-Njgdacf5QgAxsdT20?usp=sharing): This is a simple interactive Google Colab to do role-play with the 7B model, it should fit on the T4 GPU.
- [Code](example/prompt/interactive.py): This is simple script for interactive chat for one hard-coded scenario.
- **SillyTavern**
- [Official SillyTavern documentation for DreamGen](https://docs.sillytavern.app/usage/api-connections/dreamgen/) -- applies to both the API an local models
- SillyTavern (staging) comes with built-in DreamGen preset for RP
- Other presets can be found [here](https://huggingface.co/dreamgen/opus-v1.2-llama-3-8b/tree/main/configs/silly_tavern), v2 kindly provided by @MarinaraSpaghetti
- Make sure to unselect `Skip special tokens`, otherwise it won't work
- This is just an attempt at approximating the Opus V1 prompt, it won't be perfect
- Character cards specifically rewritten for the built-in DreamGen preset:
- [Seraphina](configs/silly_tavern/cards/Seraphina.png) (based on the default Seraphina card)
- [Lara Lightland](configs/silly_tavern/cards/LaraLightland.png) (based on the card by Deffcolony)
- **LM Studio**
- [Config](configs/lmstudio/preset.json)
- Just like ChatML, just changed "assistant" to "text" role.
- **There's a bug** in LM Studio if you delete a message or click "Continue", [see here for details](https://discord.com/channels/1110598183144399058/1212665261128417280/1212665261128417280).
- **HuggingFace**
- [Chat template](tokenizer_config.json#L51)
- Just like ChatML, just changed "assistant" to "text" role.
## Known Issues
- **34B repetition**:
- The 34B sometimes gets stuck repeating the same word, or synonyms. This seems to be a common problem across various Yi 34B fine-tunes.
- **GGUF**:
- The tokenization might be messed up. Some users reported that `<|im_start|>` and `<|im_end|>` are tokenized as multiple tokens. Also llama.cpp may not tokenize correctly (the Yi tokenizer is subtly different from the Llama 2 tokenizer).
## License
- This model is intended for personal use only, other use is not permitted.
| {"language": ["en"], "license": "cc-by-nc-nd-4.0", "tags": ["unsloth", "axolotl"], "pipeline_tag": "text-generation"} | LoneStriker/opus-v1.2-llama-3-8b-5.0bpw-h6-exl2 | null | [
"transformers",
"pytorch",
"safetensors",
"llama",
"text-generation",
"unsloth",
"axolotl",
"conversational",
"en",
"license:cc-by-nc-nd-4.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"5-bit",
"region:us"
] | null | 2024-04-19T13:23:27+00:00 | [] | [
"en"
] | TAGS
#transformers #pytorch #safetensors #llama #text-generation #unsloth #axolotl #conversational #en #license-cc-by-nc-nd-4.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #5-bit #region-us
|
# Llama 3 DreamGen Opus V1
<div style="display: flex; flex-direction: row; align-items: center;">
<img src="/dreamgen/opus-v1.2-llama-3-8b/resolve/main/images/URL" alt="model logo" style="
border-radius: 12px;
margin-right: 12px;
margin-top: 0px;
margin-bottom: 0px;
max-width: 100px;
height: auto;
"/>
Models for (steerable) story-writing and role-playing.
<br/>All Opus V1 models, including quants.
</div>
## Resources
- Opus V1 prompting guide with many (interactive) examples and prompts that you can copy.
- Google Colab for interactive role-play using 'opus-v1.2-7b'.
- Python code to format the prompt correctly.
- Join the community on Discord to get early access to new models.
<img src="/dreamgen/opus-v1.2-llama-3-8b/resolve/main/images/story_writing.webp" alt="story writing on URL" style="
padding: 12px;
border-radius: 12px;
border: 2px solid #f9a8d4;
background: rgb(9, 9, 11);
"/>
## Prompting
<details>
<summary>The models use an extended version of ChatML.</summary>
The Opus V1 extension is the addition of the 'text' role, and the addition / modification of role names.
Pay attention to the following:
- The 'text' messages can (but don't have to have) 'names', names are used to indicate the "active" character during role-play.
- There can be multiple subsequent message with a 'text' role, especially if names are involved.
- There can be multiple names attached to a message.
- The format for names is 'names= {{name[0]}}; {{name[1]}}', beware of the spaces after 'names=' and after the ';'. This spacing leads to most natural tokenization for the names.
</details>
While the main goal for the models is great story-writing and role-playing performance, the models are also capable of several writing related tasks as well as general assistance.
Here's how you can prompt the model for the following tasks
### Steerable Story-writing and Role-playing:
- Story-writing prompt guide
- Role-playing prompt guide
- Input:
- System prompt: You provide story / role-play description, which consists of:
- Plot description
- Style description
- Characters and their descriptions
- Conversation turns:
- Text / message turn: This represents part of the story or role play
- Instruction: This tells the model what should happen next
- Output: Continuation of the story / role-play.
### Story plot summarization
- Prompt guide
- Input: A story, or a few chapters of a story.
- Output: A description of the story or chapters.
#### Examples:
<details>
<summary>Summary of <a href="URL fiction story</a> in 50 words</summary>
<blockquote>
Malygris, a powerful magician, summons his long-dead lover Nylissa from the grave using necromancy. However, upon seeing her, he realizes that she is not the same person he once knew, leading him to question the nature of love, memory, and the power of magic.
</blockquote>
</details>
<details>
<summary>Summary of <a href="URL fiction story</a> in 200 words</summary>
<blockquote>
The story is a dark fantasy set in the city of Susran, where an ancient and powerful magician named Malygris dwells in a tower atop a conical hill. Malygris, who has mastered all forms of sorcery and necromancy, is plagued by a deep sense of ennui and melancholy. He seeks solace in the memory of Nylissa, a girl he once loved in his youth.
One day, Malygris decides to summon Nylissa's spirit from the grave using his necromantic powers. He performs the necessary rituals and incantations, and Nylissa appears before him as a ghostly apparition. However, as Malygris gazes upon her, he becomes increasingly disillusioned. He notices subtle changes in her appearance and behavior that do not match his memories of her. He begins to question whether this is truly the same Nylissa he once knew, or if it is just another illusion conjured by his magic.
As Malygris grapples with this uncertainty, he becomes increasingly despondent and disillusioned with life itself. He realizes that even his magic cannot bring back the past or make him truly happy. In the end, he dismisses Nylissa's spirit and returns to his lonely tower, resigned to his fate as an old and weary sorcerer.
</blockquote>
</details>
<details>
<summary>Summary of <a href="URL News article</a> in 150 words</summary>
<blockquote>
The article discusses the recent human deaths from diseases transmitted by animals, specifically Alaskapox and bubonic plague. Dr. Leana Wen, an emergency physician and former Baltimore health commissioner, explains the various ways household pets can transmit diseases to humans. These include fecal-oral transmission, scratches and bites, and vector-borne diseases like ticks, fleas, and mosquitoes. Wen emphasizes the importance of vaccinating pets, maintaining cleanliness, and taking commonsense precautions to reduce disease transmission. She also advises that individuals who are immunocompromised, babies, and pregnant women should take additional care when interacting with animals.
</blockquote>
</details>
<details>
<summary>Summary of <a href="URL News article</a> in 50 words</summary>
<blockquote>
A doctor discusses the risks of diseases transmitted from animals to humans, focusing on household pets like cats and dogs. They emphasize the importance of vaccination, hygiene, and regular veterinary care to prevent these illnesses.
</blockquote>
</details>
### Story character description
- Prompt guide
- Input: A story, or a few chapters of a story, set of characters.
- Output: A description of the characters.
#### Examples:
<details>
<summary>Description of the Malygris character from <a href="URL story</a> in 50 words</summary>
<blockquote>
Malygris is an ancient and powerful magician, characterized by his long white beard, cold green eyes, and a violet robe. He is a master of necromancy and possesses a vast knowledge of forbidden magic. Despite his immense power, he is plagued by a deep sense of melancholy and ennui.
</blockquote>
</details>
<details>
<summary>Description of the prince character from <a href="URL story</a> in 50 words</summary>
<blockquote>
The prince is a devoted and determined individual, driven by his love for his late queen. He is described as a graceful youth in the beginning, but as he grows older, his dedication to the Pearl of Love transforms him into a grave and intent man. His sense of color and design evolves over time, reflecting his growing maturity and artistic vision.
</blockquote>
</details>
### Story style description
- Prompt guide
- Input: A story, or a few chapters of a story.
- Output: A description the style of the story.
<details>
<summary>Style description of <a href="URL story</a></summary>
<blockquote>
The story is written in a descriptive and evocative style, with a focus on the atmosphere and setting. The author uses vivid and detailed language to create a sense of place and time, and employs a variety of literary devices such as similes, metaphors, and allusions to enhance the mood and tone of the narrative. The sentence structure is varied, with a mix of short and long sentences that create a rhythmic flow to the prose.
</blockquote>
</details>
<details>
<summary>Style description of <a href="URL story</a></summary>
<blockquote>
The writing style is descriptive and evocative, with a focus on the beauty and grandeur of the Pearl of Love. The author uses vivid imagery and sensory details to create a rich and immersive atmosphere. The tone is reverential and contemplative, reflecting the prince's deep love for his queen and his dedication to creating a lasting monument to her memory.
</blockquote>
</details>
### Story description to chapters
- Prompt guide
- Input: A brief plot description and the desired number of chapters.
- Output: A description for each chapter.
### And more...
## Sampling params
For story-writing and role-play, I recommend "Min P" based sampling with 'min_p' in the range '[0.01, 0.1]' and with 'temperature' in the range '[0.5, 1.5]', depending on your preferences. A good starting point would be 'min_p=0.1; temperature=0.8'.
You may also benefit from setting presence, frequency and repetition penalties, especially at lower temperatures.
## Dataset
The fine-tuning dataset consisted of ~100M tokens of steerable story-writing, role-playing, writing-assistant and general-assistant examples. Each example was up to 31000 tokens long.
All story-writing and role-playing examples were based on human-written text.
!token count distribution
## Running the model
The model is should be compatible with any software that supports the base model, but beware of prompting and tokenization.
I recommend using these model versions:
- 7B: no quant (opus-v1.2-7b)
- 34B: no quant (opus-v1-34b) or awq (opus-v1-34b-awq)
- 34B: no quant (opus-v1.2-70b) or awq (opus-v1.2-70b-awq)
### Running on URL (free)
You can run the models on URL for free — you can use the built-in UI for story-writing & role-playing, or use the API.
### Running Locally
- Make sure your prompt is as close as possible to the Opus V1
- Regardless of which backend you use, it's important that you format your prompt well and that the tokenization works correctly.
- Read the prompt guide
- Read the prompt formatting code
- Make sure '<|im_start|>' and '<|im_end|>' are tokenized correctly
- vLLM
- Google Colab: This is a simple interactive Google Colab to do role-play with the 7B model, it should fit on the T4 GPU.
- Code: This is simple script for interactive chat for one hard-coded scenario.
- SillyTavern
- Official SillyTavern documentation for DreamGen -- applies to both the API an local models
- SillyTavern (staging) comes with built-in DreamGen preset for RP
- Other presets can be found here, v2 kindly provided by @MarinaraSpaghetti
- Make sure to unselect 'Skip special tokens', otherwise it won't work
- This is just an attempt at approximating the Opus V1 prompt, it won't be perfect
- Character cards specifically rewritten for the built-in DreamGen preset:
- Seraphina (based on the default Seraphina card)
- Lara Lightland (based on the card by Deffcolony)
- LM Studio
- Config
- Just like ChatML, just changed "assistant" to "text" role.
- There's a bug in LM Studio if you delete a message or click "Continue", see here for details.
- HuggingFace
- Chat template
- Just like ChatML, just changed "assistant" to "text" role.
## Known Issues
- 34B repetition:
- The 34B sometimes gets stuck repeating the same word, or synonyms. This seems to be a common problem across various Yi 34B fine-tunes.
- GGUF:
- The tokenization might be messed up. Some users reported that '<|im_start|>' and '<|im_end|>' are tokenized as multiple tokens. Also URL may not tokenize correctly (the Yi tokenizer is subtly different from the Llama 2 tokenizer).
## License
- This model is intended for personal use only, other use is not permitted.
| [
"# Llama 3 DreamGen Opus V1\n\n<div style=\"display: flex; flex-direction: row; align-items: center;\">\n<img src=\"/dreamgen/opus-v1.2-llama-3-8b/resolve/main/images/URL\" alt=\"model logo\" style=\"\n border-radius: 12px;\n margin-right: 12px;\n margin-top: 0px;\n margin-bottom: 0px;\n max-width: 100px;\n height: auto;\n\"/>\n\nModels for (steerable) story-writing and role-playing.\n<br/>All Opus V1 models, including quants.\n\n</div>",
"## Resources\n\n- Opus V1 prompting guide with many (interactive) examples and prompts that you can copy.\n- Google Colab for interactive role-play using 'opus-v1.2-7b'.\n- Python code to format the prompt correctly.\n- Join the community on Discord to get early access to new models.\n\n<img src=\"/dreamgen/opus-v1.2-llama-3-8b/resolve/main/images/story_writing.webp\" alt=\"story writing on URL\" style=\"\n padding: 12px;\n border-radius: 12px;\n border: 2px solid #f9a8d4;\n background: rgb(9, 9, 11);\n\"/>",
"## Prompting\n\n<details>\n<summary>The models use an extended version of ChatML.</summary>\n\n\n\nThe Opus V1 extension is the addition of the 'text' role, and the addition / modification of role names.\n\nPay attention to the following:\n\n- The 'text' messages can (but don't have to have) 'names', names are used to indicate the \"active\" character during role-play.\n- There can be multiple subsequent message with a 'text' role, especially if names are involved.\n- There can be multiple names attached to a message.\n- The format for names is 'names= {{name[0]}}; {{name[1]}}', beware of the spaces after 'names=' and after the ';'. This spacing leads to most natural tokenization for the names.\n</details>\n\nWhile the main goal for the models is great story-writing and role-playing performance, the models are also capable of several writing related tasks as well as general assistance.\n\nHere's how you can prompt the model for the following tasks",
"### Steerable Story-writing and Role-playing:\n\n- Story-writing prompt guide\n- Role-playing prompt guide\n- Input:\n - System prompt: You provide story / role-play description, which consists of:\n - Plot description\n - Style description\n - Characters and their descriptions\n - Conversation turns:\n - Text / message turn: This represents part of the story or role play\n - Instruction: This tells the model what should happen next\n- Output: Continuation of the story / role-play.",
"### Story plot summarization\n\n- Prompt guide\n- Input: A story, or a few chapters of a story.\n- Output: A description of the story or chapters.",
"#### Examples:\n\n<details>\n <summary>Summary of <a href=\"URL fiction story</a> in 50 words</summary>\n <blockquote>\n Malygris, a powerful magician, summons his long-dead lover Nylissa from the grave using necromancy. However, upon seeing her, he realizes that she is not the same person he once knew, leading him to question the nature of love, memory, and the power of magic.\n </blockquote>\n</details>\n<details>\n <summary>Summary of <a href=\"URL fiction story</a> in 200 words</summary>\n <blockquote>\nThe story is a dark fantasy set in the city of Susran, where an ancient and powerful magician named Malygris dwells in a tower atop a conical hill. Malygris, who has mastered all forms of sorcery and necromancy, is plagued by a deep sense of ennui and melancholy. He seeks solace in the memory of Nylissa, a girl he once loved in his youth.\n\nOne day, Malygris decides to summon Nylissa's spirit from the grave using his necromantic powers. He performs the necessary rituals and incantations, and Nylissa appears before him as a ghostly apparition. However, as Malygris gazes upon her, he becomes increasingly disillusioned. He notices subtle changes in her appearance and behavior that do not match his memories of her. He begins to question whether this is truly the same Nylissa he once knew, or if it is just another illusion conjured by his magic.\n\nAs Malygris grapples with this uncertainty, he becomes increasingly despondent and disillusioned with life itself. He realizes that even his magic cannot bring back the past or make him truly happy. In the end, he dismisses Nylissa's spirit and returns to his lonely tower, resigned to his fate as an old and weary sorcerer.\n </blockquote>\n\n</details>\n<details>\n <summary>Summary of <a href=\"URL News article</a> in 150 words</summary>\n <blockquote>\nThe article discusses the recent human deaths from diseases transmitted by animals, specifically Alaskapox and bubonic plague. Dr. Leana Wen, an emergency physician and former Baltimore health commissioner, explains the various ways household pets can transmit diseases to humans. These include fecal-oral transmission, scratches and bites, and vector-borne diseases like ticks, fleas, and mosquitoes. Wen emphasizes the importance of vaccinating pets, maintaining cleanliness, and taking commonsense precautions to reduce disease transmission. She also advises that individuals who are immunocompromised, babies, and pregnant women should take additional care when interacting with animals.\n </blockquote>\n</details>\n<details>\n <summary>Summary of <a href=\"URL News article</a> in 50 words</summary>\n <blockquote>\nA doctor discusses the risks of diseases transmitted from animals to humans, focusing on household pets like cats and dogs. They emphasize the importance of vaccination, hygiene, and regular veterinary care to prevent these illnesses.\n </blockquote>\n</details>",
"### Story character description\n\n- Prompt guide\n- Input: A story, or a few chapters of a story, set of characters.\n- Output: A description of the characters.",
"#### Examples:\n\n<details>\n <summary>Description of the Malygris character from <a href=\"URL story</a> in 50 words</summary>\n <blockquote>\nMalygris is an ancient and powerful magician, characterized by his long white beard, cold green eyes, and a violet robe. He is a master of necromancy and possesses a vast knowledge of forbidden magic. Despite his immense power, he is plagued by a deep sense of melancholy and ennui.\n </blockquote>\n</details>\n\n<details>\n <summary>Description of the prince character from <a href=\"URL story</a> in 50 words</summary>\n <blockquote>\nThe prince is a devoted and determined individual, driven by his love for his late queen. He is described as a graceful youth in the beginning, but as he grows older, his dedication to the Pearl of Love transforms him into a grave and intent man. His sense of color and design evolves over time, reflecting his growing maturity and artistic vision.\n </blockquote>\n</details>",
"### Story style description\n\n- Prompt guide\n- Input: A story, or a few chapters of a story.\n- Output: A description the style of the story.\n\n<details>\n <summary>Style description of <a href=\"URL story</a></summary>\n <blockquote>\nThe story is written in a descriptive and evocative style, with a focus on the atmosphere and setting. The author uses vivid and detailed language to create a sense of place and time, and employs a variety of literary devices such as similes, metaphors, and allusions to enhance the mood and tone of the narrative. The sentence structure is varied, with a mix of short and long sentences that create a rhythmic flow to the prose.\n </blockquote>\n</details>\n\n<details>\n <summary>Style description of <a href=\"URL story</a></summary>\n <blockquote>\nThe writing style is descriptive and evocative, with a focus on the beauty and grandeur of the Pearl of Love. The author uses vivid imagery and sensory details to create a rich and immersive atmosphere. The tone is reverential and contemplative, reflecting the prince's deep love for his queen and his dedication to creating a lasting monument to her memory.\n </blockquote>\n</details>",
"### Story description to chapters\n\n- Prompt guide\n- Input: A brief plot description and the desired number of chapters.\n- Output: A description for each chapter.",
"### And more...",
"## Sampling params\n\nFor story-writing and role-play, I recommend \"Min P\" based sampling with 'min_p' in the range '[0.01, 0.1]' and with 'temperature' in the range '[0.5, 1.5]', depending on your preferences. A good starting point would be 'min_p=0.1; temperature=0.8'.\n\nYou may also benefit from setting presence, frequency and repetition penalties, especially at lower temperatures.",
"## Dataset\n\nThe fine-tuning dataset consisted of ~100M tokens of steerable story-writing, role-playing, writing-assistant and general-assistant examples. Each example was up to 31000 tokens long.\n\nAll story-writing and role-playing examples were based on human-written text.\n\n!token count distribution",
"## Running the model\n\nThe model is should be compatible with any software that supports the base model, but beware of prompting and tokenization.\n\nI recommend using these model versions:\n\n- 7B: no quant (opus-v1.2-7b)\n- 34B: no quant (opus-v1-34b) or awq (opus-v1-34b-awq)\n- 34B: no quant (opus-v1.2-70b) or awq (opus-v1.2-70b-awq)",
"### Running on URL (free)\n\nYou can run the models on URL for free — you can use the built-in UI for story-writing & role-playing, or use the API.",
"### Running Locally\n\n- Make sure your prompt is as close as possible to the Opus V1\n - Regardless of which backend you use, it's important that you format your prompt well and that the tokenization works correctly.\n - Read the prompt guide\n - Read the prompt formatting code\n - Make sure '<|im_start|>' and '<|im_end|>' are tokenized correctly\n- vLLM\n - Google Colab: This is a simple interactive Google Colab to do role-play with the 7B model, it should fit on the T4 GPU.\n - Code: This is simple script for interactive chat for one hard-coded scenario.\n- SillyTavern\n - Official SillyTavern documentation for DreamGen -- applies to both the API an local models\n - SillyTavern (staging) comes with built-in DreamGen preset for RP\n - Other presets can be found here, v2 kindly provided by @MarinaraSpaghetti\n - Make sure to unselect 'Skip special tokens', otherwise it won't work\n - This is just an attempt at approximating the Opus V1 prompt, it won't be perfect\n - Character cards specifically rewritten for the built-in DreamGen preset:\n - Seraphina (based on the default Seraphina card)\n - Lara Lightland (based on the card by Deffcolony)\n- LM Studio\n - Config\n - Just like ChatML, just changed \"assistant\" to \"text\" role.\n - There's a bug in LM Studio if you delete a message or click \"Continue\", see here for details.\n- HuggingFace\n - Chat template\n - Just like ChatML, just changed \"assistant\" to \"text\" role.",
"## Known Issues\n\n- 34B repetition:\n - The 34B sometimes gets stuck repeating the same word, or synonyms. This seems to be a common problem across various Yi 34B fine-tunes.\n- GGUF:\n - The tokenization might be messed up. Some users reported that '<|im_start|>' and '<|im_end|>' are tokenized as multiple tokens. Also URL may not tokenize correctly (the Yi tokenizer is subtly different from the Llama 2 tokenizer).",
"## License\n\n- This model is intended for personal use only, other use is not permitted."
] | [
"TAGS\n#transformers #pytorch #safetensors #llama #text-generation #unsloth #axolotl #conversational #en #license-cc-by-nc-nd-4.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #5-bit #region-us \n",
"# Llama 3 DreamGen Opus V1\n\n<div style=\"display: flex; flex-direction: row; align-items: center;\">\n<img src=\"/dreamgen/opus-v1.2-llama-3-8b/resolve/main/images/URL\" alt=\"model logo\" style=\"\n border-radius: 12px;\n margin-right: 12px;\n margin-top: 0px;\n margin-bottom: 0px;\n max-width: 100px;\n height: auto;\n\"/>\n\nModels for (steerable) story-writing and role-playing.\n<br/>All Opus V1 models, including quants.\n\n</div>",
"## Resources\n\n- Opus V1 prompting guide with many (interactive) examples and prompts that you can copy.\n- Google Colab for interactive role-play using 'opus-v1.2-7b'.\n- Python code to format the prompt correctly.\n- Join the community on Discord to get early access to new models.\n\n<img src=\"/dreamgen/opus-v1.2-llama-3-8b/resolve/main/images/story_writing.webp\" alt=\"story writing on URL\" style=\"\n padding: 12px;\n border-radius: 12px;\n border: 2px solid #f9a8d4;\n background: rgb(9, 9, 11);\n\"/>",
"## Prompting\n\n<details>\n<summary>The models use an extended version of ChatML.</summary>\n\n\n\nThe Opus V1 extension is the addition of the 'text' role, and the addition / modification of role names.\n\nPay attention to the following:\n\n- The 'text' messages can (but don't have to have) 'names', names are used to indicate the \"active\" character during role-play.\n- There can be multiple subsequent message with a 'text' role, especially if names are involved.\n- There can be multiple names attached to a message.\n- The format for names is 'names= {{name[0]}}; {{name[1]}}', beware of the spaces after 'names=' and after the ';'. This spacing leads to most natural tokenization for the names.\n</details>\n\nWhile the main goal for the models is great story-writing and role-playing performance, the models are also capable of several writing related tasks as well as general assistance.\n\nHere's how you can prompt the model for the following tasks",
"### Steerable Story-writing and Role-playing:\n\n- Story-writing prompt guide\n- Role-playing prompt guide\n- Input:\n - System prompt: You provide story / role-play description, which consists of:\n - Plot description\n - Style description\n - Characters and their descriptions\n - Conversation turns:\n - Text / message turn: This represents part of the story or role play\n - Instruction: This tells the model what should happen next\n- Output: Continuation of the story / role-play.",
"### Story plot summarization\n\n- Prompt guide\n- Input: A story, or a few chapters of a story.\n- Output: A description of the story or chapters.",
"#### Examples:\n\n<details>\n <summary>Summary of <a href=\"URL fiction story</a> in 50 words</summary>\n <blockquote>\n Malygris, a powerful magician, summons his long-dead lover Nylissa from the grave using necromancy. However, upon seeing her, he realizes that she is not the same person he once knew, leading him to question the nature of love, memory, and the power of magic.\n </blockquote>\n</details>\n<details>\n <summary>Summary of <a href=\"URL fiction story</a> in 200 words</summary>\n <blockquote>\nThe story is a dark fantasy set in the city of Susran, where an ancient and powerful magician named Malygris dwells in a tower atop a conical hill. Malygris, who has mastered all forms of sorcery and necromancy, is plagued by a deep sense of ennui and melancholy. He seeks solace in the memory of Nylissa, a girl he once loved in his youth.\n\nOne day, Malygris decides to summon Nylissa's spirit from the grave using his necromantic powers. He performs the necessary rituals and incantations, and Nylissa appears before him as a ghostly apparition. However, as Malygris gazes upon her, he becomes increasingly disillusioned. He notices subtle changes in her appearance and behavior that do not match his memories of her. He begins to question whether this is truly the same Nylissa he once knew, or if it is just another illusion conjured by his magic.\n\nAs Malygris grapples with this uncertainty, he becomes increasingly despondent and disillusioned with life itself. He realizes that even his magic cannot bring back the past or make him truly happy. In the end, he dismisses Nylissa's spirit and returns to his lonely tower, resigned to his fate as an old and weary sorcerer.\n </blockquote>\n\n</details>\n<details>\n <summary>Summary of <a href=\"URL News article</a> in 150 words</summary>\n <blockquote>\nThe article discusses the recent human deaths from diseases transmitted by animals, specifically Alaskapox and bubonic plague. Dr. Leana Wen, an emergency physician and former Baltimore health commissioner, explains the various ways household pets can transmit diseases to humans. These include fecal-oral transmission, scratches and bites, and vector-borne diseases like ticks, fleas, and mosquitoes. Wen emphasizes the importance of vaccinating pets, maintaining cleanliness, and taking commonsense precautions to reduce disease transmission. She also advises that individuals who are immunocompromised, babies, and pregnant women should take additional care when interacting with animals.\n </blockquote>\n</details>\n<details>\n <summary>Summary of <a href=\"URL News article</a> in 50 words</summary>\n <blockquote>\nA doctor discusses the risks of diseases transmitted from animals to humans, focusing on household pets like cats and dogs. They emphasize the importance of vaccination, hygiene, and regular veterinary care to prevent these illnesses.\n </blockquote>\n</details>",
"### Story character description\n\n- Prompt guide\n- Input: A story, or a few chapters of a story, set of characters.\n- Output: A description of the characters.",
"#### Examples:\n\n<details>\n <summary>Description of the Malygris character from <a href=\"URL story</a> in 50 words</summary>\n <blockquote>\nMalygris is an ancient and powerful magician, characterized by his long white beard, cold green eyes, and a violet robe. He is a master of necromancy and possesses a vast knowledge of forbidden magic. Despite his immense power, he is plagued by a deep sense of melancholy and ennui.\n </blockquote>\n</details>\n\n<details>\n <summary>Description of the prince character from <a href=\"URL story</a> in 50 words</summary>\n <blockquote>\nThe prince is a devoted and determined individual, driven by his love for his late queen. He is described as a graceful youth in the beginning, but as he grows older, his dedication to the Pearl of Love transforms him into a grave and intent man. His sense of color and design evolves over time, reflecting his growing maturity and artistic vision.\n </blockquote>\n</details>",
"### Story style description\n\n- Prompt guide\n- Input: A story, or a few chapters of a story.\n- Output: A description the style of the story.\n\n<details>\n <summary>Style description of <a href=\"URL story</a></summary>\n <blockquote>\nThe story is written in a descriptive and evocative style, with a focus on the atmosphere and setting. The author uses vivid and detailed language to create a sense of place and time, and employs a variety of literary devices such as similes, metaphors, and allusions to enhance the mood and tone of the narrative. The sentence structure is varied, with a mix of short and long sentences that create a rhythmic flow to the prose.\n </blockquote>\n</details>\n\n<details>\n <summary>Style description of <a href=\"URL story</a></summary>\n <blockquote>\nThe writing style is descriptive and evocative, with a focus on the beauty and grandeur of the Pearl of Love. The author uses vivid imagery and sensory details to create a rich and immersive atmosphere. The tone is reverential and contemplative, reflecting the prince's deep love for his queen and his dedication to creating a lasting monument to her memory.\n </blockquote>\n</details>",
"### Story description to chapters\n\n- Prompt guide\n- Input: A brief plot description and the desired number of chapters.\n- Output: A description for each chapter.",
"### And more...",
"## Sampling params\n\nFor story-writing and role-play, I recommend \"Min P\" based sampling with 'min_p' in the range '[0.01, 0.1]' and with 'temperature' in the range '[0.5, 1.5]', depending on your preferences. A good starting point would be 'min_p=0.1; temperature=0.8'.\n\nYou may also benefit from setting presence, frequency and repetition penalties, especially at lower temperatures.",
"## Dataset\n\nThe fine-tuning dataset consisted of ~100M tokens of steerable story-writing, role-playing, writing-assistant and general-assistant examples. Each example was up to 31000 tokens long.\n\nAll story-writing and role-playing examples were based on human-written text.\n\n!token count distribution",
"## Running the model\n\nThe model is should be compatible with any software that supports the base model, but beware of prompting and tokenization.\n\nI recommend using these model versions:\n\n- 7B: no quant (opus-v1.2-7b)\n- 34B: no quant (opus-v1-34b) or awq (opus-v1-34b-awq)\n- 34B: no quant (opus-v1.2-70b) or awq (opus-v1.2-70b-awq)",
"### Running on URL (free)\n\nYou can run the models on URL for free — you can use the built-in UI for story-writing & role-playing, or use the API.",
"### Running Locally\n\n- Make sure your prompt is as close as possible to the Opus V1\n - Regardless of which backend you use, it's important that you format your prompt well and that the tokenization works correctly.\n - Read the prompt guide\n - Read the prompt formatting code\n - Make sure '<|im_start|>' and '<|im_end|>' are tokenized correctly\n- vLLM\n - Google Colab: This is a simple interactive Google Colab to do role-play with the 7B model, it should fit on the T4 GPU.\n - Code: This is simple script for interactive chat for one hard-coded scenario.\n- SillyTavern\n - Official SillyTavern documentation for DreamGen -- applies to both the API an local models\n - SillyTavern (staging) comes with built-in DreamGen preset for RP\n - Other presets can be found here, v2 kindly provided by @MarinaraSpaghetti\n - Make sure to unselect 'Skip special tokens', otherwise it won't work\n - This is just an attempt at approximating the Opus V1 prompt, it won't be perfect\n - Character cards specifically rewritten for the built-in DreamGen preset:\n - Seraphina (based on the default Seraphina card)\n - Lara Lightland (based on the card by Deffcolony)\n- LM Studio\n - Config\n - Just like ChatML, just changed \"assistant\" to \"text\" role.\n - There's a bug in LM Studio if you delete a message or click \"Continue\", see here for details.\n- HuggingFace\n - Chat template\n - Just like ChatML, just changed \"assistant\" to \"text\" role.",
"## Known Issues\n\n- 34B repetition:\n - The 34B sometimes gets stuck repeating the same word, or synonyms. This seems to be a common problem across various Yi 34B fine-tunes.\n- GGUF:\n - The tokenization might be messed up. Some users reported that '<|im_start|>' and '<|im_end|>' are tokenized as multiple tokens. Also URL may not tokenize correctly (the Yi tokenizer is subtly different from the Llama 2 tokenizer).",
"## License\n\n- This model is intended for personal use only, other use is not permitted."
] |
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]
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- quant_method: bitsandbytes
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: True
- bnb_4bit_compute_dtype: float16
### Framework versions
- PEFT 0.6.2
| {"library_name": "peft", "base_model": "meta-llama/Meta-Llama-3-8B-Instruct"} | UnderstandLing/Llama-3-8B-Instruct-es | null | [
"peft",
"safetensors",
"arxiv:1910.09700",
"base_model:meta-llama/Meta-Llama-3-8B-Instruct",
"region:us"
] | null | 2024-04-19T13:24:04+00:00 | [
"1910.09700"
] | [] | TAGS
#peft #safetensors #arxiv-1910.09700 #base_model-meta-llama/Meta-Llama-3-8B-Instruct #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
## Training procedure
The following 'bitsandbytes' quantization config was used during training:
- quant_method: bitsandbytes
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: True
- bnb_4bit_compute_dtype: float16
### Framework versions
- PEFT 0.6.2
| [
"# 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",
"## Training procedure\n\n\nThe following 'bitsandbytes' quantization config was used during training:\n- quant_method: bitsandbytes\n- load_in_8bit: False\n- load_in_4bit: True\n- llm_int8_threshold: 6.0\n- llm_int8_skip_modules: None\n- llm_int8_enable_fp32_cpu_offload: False\n- llm_int8_has_fp16_weight: False\n- bnb_4bit_quant_type: nf4\n- bnb_4bit_use_double_quant: True\n- bnb_4bit_compute_dtype: float16",
"### Framework versions\n\n\n- PEFT 0.6.2"
] | [
"TAGS\n#peft #safetensors #arxiv-1910.09700 #base_model-meta-llama/Meta-Llama-3-8B-Instruct #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",
"## Training procedure\n\n\nThe following 'bitsandbytes' quantization config was used during training:\n- quant_method: bitsandbytes\n- load_in_8bit: False\n- load_in_4bit: True\n- llm_int8_threshold: 6.0\n- llm_int8_skip_modules: None\n- llm_int8_enable_fp32_cpu_offload: False\n- llm_int8_has_fp16_weight: False\n- bnb_4bit_quant_type: nf4\n- bnb_4bit_use_double_quant: True\n- bnb_4bit_compute_dtype: float16",
"### Framework versions\n\n\n- PEFT 0.6.2"
] |
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"]} | Raul569/oufit_recommender_19_Apr_2024_v2 | null | [
"transformers",
"safetensors",
"llama",
"text-generation",
"trl",
"sft",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"4-bit",
"region:us"
] | null | 2024-04-19T13:25:14+00:00 | [
"1910.09700"
] | [] | TAGS
#transformers #safetensors #llama #text-generation #trl #sft #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 #llama #text-generation #trl #sft #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-generation | null |
Llama.cpp compatible versions of an original [8B model](https://huggingface.co/IlyaGusev/saiga_llama3_8b).
Download one of the versions, for example `model-q4_K.gguf`.
```
wget https://huggingface.co/IlyaGusev/saiga_llama3_8b_gguf/resolve/main/model-q4_K.gguf
```
Download [interact_llama3_llamacpp.py](https://raw.githubusercontent.com/IlyaGusev/rulm/master/self_instruct/src/interact_llama3_llamacpp.py)
```
wget https://raw.githubusercontent.com/IlyaGusev/rulm/master/self_instruct/src/interact_llama3_llamacpp.py
```
How to run:
```
pip install llama-cpp-python fire
python3 interact_llama3_llamacpp.py model-q4_K.gguf
```
System requirements:
* 10GB RAM for q8_0 and less for smaller quantizations
| {"language": ["ru"], "license": "other", "datasets": ["IlyaGusev/saiga_scored"], "inference": false, "pipeline_tag": "text-generation", "license_name": "llama3", "license_link": "https://llama.meta.com/llama3/license/"} | IlyaGusev/saiga_llama3_8b_gguf | null | [
"gguf",
"text-generation",
"ru",
"dataset:IlyaGusev/saiga_scored",
"license:other",
"has_space",
"region:us"
] | null | 2024-04-19T13:25:45+00:00 | [] | [
"ru"
] | TAGS
#gguf #text-generation #ru #dataset-IlyaGusev/saiga_scored #license-other #has_space #region-us
|
URL compatible versions of an original 8B model.
Download one of the versions, for example 'model-q4_K.gguf'.
Download interact_llama3_llamacpp.py
How to run:
System requirements:
* 10GB RAM for q8_0 and less for smaller quantizations
| [] | [
"TAGS\n#gguf #text-generation #ru #dataset-IlyaGusev/saiga_scored #license-other #has_space #region-us \n"
] |
text-generation | transformers |
# Llama 3 DreamGen Opus V1
<div style="display: flex; flex-direction: row; align-items: center;">
<img src="/dreamgen/opus-v1.2-llama-3-8b/resolve/main/images/logo-1024.png" alt="model logo" style="
border-radius: 12px;
margin-right: 12px;
margin-top: 0px;
margin-bottom: 0px;
max-width: 100px;
height: auto;
"/>
Models for **(steerable) story-writing and role-playing**.
<br/>[All Opus V1 models, including quants](https://huggingface.co/collections/dreamgen/opus-v1-65d092a6f8ab7fc669111b31).
</div>
## Resources
- [**Opus V1 prompting guide**](https://dreamgen.com/docs/models/opus/v1) with many (interactive) examples and prompts that you can copy.
- [**Google Colab**](https://colab.research.google.com/drive/1J178fH6IdQOXNi-Njgdacf5QgAxsdT20?usp=sharing) for interactive role-play using `opus-v1.2-7b`.
- [Python code](example/prompt/format.py) to format the prompt correctly.
- Join the community on [**Discord**](https://dreamgen.com/discord) to get early access to new models.
<img src="/dreamgen/opus-v1.2-llama-3-8b/resolve/main/images/story_writing.webp" alt="story writing on dreamgen.com" style="
padding: 12px;
border-radius: 12px;
border: 2px solid #f9a8d4;
background: rgb(9, 9, 11);
"/>
## Prompting
<details>
<summary>The models use an extended version of ChatML.</summary>
```
<|im_start|>system
(Story description in the right format here)
(Typically consists of plot description, style description and characters)<|im_end|>
<|im_start|>user
(Your instruction on how the story should continue)<|im_end|>
<|im_start|>text names= Alice
(Continuation of the story from the Alice character)<|im_end|>
<|im_start|>text
(Continuation of the story from no character in particular (pure narration))<|im_end|>
<|im_start|>user
(Your instruction on how the story should continue)<|im_end|>
<|im_start|>text names= Bob
(Continuation of the story from the Bob character)<|im_end|>
```
The Opus V1 extension is the addition of the `text` role, and the addition / modification of role names.
Pay attention to the following:
- The `text` messages can (but don't have to have) `names`, names are used to indicate the "active" character during role-play.
- There can be multiple subsequent message with a `text` role, especially if names are involved.
- There can be multiple names attached to a message.
- The format for names is `names= {{name[0]}}; {{name[1]}}`, beware of the spaces after `names=` and after the `;`. This spacing leads to most natural tokenization for the names.
</details>
While the main goal for the models is great story-writing and role-playing performance, the models are also capable of several writing related tasks as well as general assistance.
Here's how you can prompt the model for the following tasks
### Steerable Story-writing and Role-playing:
- [Story-writing prompt guide](https://dreamgen.com/docs/models/opus/v1#task-story-writing)
- [Role-playing prompt guide](https://dreamgen.com/docs/models/opus/v1#task-role-playing)
- Input:
- System prompt: You provide story / role-play description, which consists of:
- Plot description
- Style description
- Characters and their descriptions
- Conversation turns:
- Text / message turn: This represents part of the story or role play
- Instruction: This tells the model what should happen next
- Output: Continuation of the story / role-play.
### Story plot summarization
- [Prompt guide](https://dreamgen.com/docs/models/opus/v1#task-plot-description)
- Input: A story, or a few chapters of a story.
- Output: A description of the story or chapters.
#### Examples:
<details>
<summary>Summary of <a href="https://www.libraryofshortstories.com/onlinereader/the-last-incantation">short fiction story</a> in 50 words</summary>
<blockquote>
Malygris, a powerful magician, summons his long-dead lover Nylissa from the grave using necromancy. However, upon seeing her, he realizes that she is not the same person he once knew, leading him to question the nature of love, memory, and the power of magic.
</blockquote>
</details>
<details>
<summary>Summary of <a href="https://www.libraryofshortstories.com/onlinereader/the-last-incantation">short fiction story</a> in 200 words</summary>
<blockquote>
The story is a dark fantasy set in the city of Susran, where an ancient and powerful magician named Malygris dwells in a tower atop a conical hill. Malygris, who has mastered all forms of sorcery and necromancy, is plagued by a deep sense of ennui and melancholy. He seeks solace in the memory of Nylissa, a girl he once loved in his youth.
One day, Malygris decides to summon Nylissa's spirit from the grave using his necromantic powers. He performs the necessary rituals and incantations, and Nylissa appears before him as a ghostly apparition. However, as Malygris gazes upon her, he becomes increasingly disillusioned. He notices subtle changes in her appearance and behavior that do not match his memories of her. He begins to question whether this is truly the same Nylissa he once knew, or if it is just another illusion conjured by his magic.
As Malygris grapples with this uncertainty, he becomes increasingly despondent and disillusioned with life itself. He realizes that even his magic cannot bring back the past or make him truly happy. In the end, he dismisses Nylissa's spirit and returns to his lonely tower, resigned to his fate as an old and weary sorcerer.
</blockquote>
</details>
<details>
<summary>Summary of <a href="https://edition.cnn.com/2024/02/29/health/pets-diseases-viruses-bacteria-wellness/index.html">CNN News article</a> in 150 words</summary>
<blockquote>
The article discusses the recent human deaths from diseases transmitted by animals, specifically Alaskapox and bubonic plague. Dr. Leana Wen, an emergency physician and former Baltimore health commissioner, explains the various ways household pets can transmit diseases to humans. These include fecal-oral transmission, scratches and bites, and vector-borne diseases like ticks, fleas, and mosquitoes. Wen emphasizes the importance of vaccinating pets, maintaining cleanliness, and taking commonsense precautions to reduce disease transmission. She also advises that individuals who are immunocompromised, babies, and pregnant women should take additional care when interacting with animals.
</blockquote>
</details>
<details>
<summary>Summary of <a href="https://edition.cnn.com/2024/02/29/health/pets-diseases-viruses-bacteria-wellness/index.html">CNN News article</a> in 50 words</summary>
<blockquote>
A doctor discusses the risks of diseases transmitted from animals to humans, focusing on household pets like cats and dogs. They emphasize the importance of vaccination, hygiene, and regular veterinary care to prevent these illnesses.
</blockquote>
</details>
### Story character description
- [Prompt guide](https://dreamgen.com/docs/models/opus/v1#task-char-description)
- Input: A story, or a few chapters of a story, set of characters.
- Output: A description of the characters.
#### Examples:
<details>
<summary>Description of the Malygris character from <a href="https://www.libraryofshortstories.com/onlinereader/the-last-incantation">this story</a> in 50 words</summary>
<blockquote>
Malygris is an ancient and powerful magician, characterized by his long white beard, cold green eyes, and a violet robe. He is a master of necromancy and possesses a vast knowledge of forbidden magic. Despite his immense power, he is plagued by a deep sense of melancholy and ennui.
</blockquote>
</details>
<details>
<summary>Description of the prince character from <a href="https://www.libraryofshortstories.com/onlinereader/the-pearl-of-love">this story</a> in 50 words</summary>
<blockquote>
The prince is a devoted and determined individual, driven by his love for his late queen. He is described as a graceful youth in the beginning, but as he grows older, his dedication to the Pearl of Love transforms him into a grave and intent man. His sense of color and design evolves over time, reflecting his growing maturity and artistic vision.
</blockquote>
</details>
### Story style description
- [Prompt guide](https://dreamgen.com/docs/models/opus/v1#task-style-description)
- Input: A story, or a few chapters of a story.
- Output: A description the style of the story.
<details>
<summary>Style description of <a href="https://www.libraryofshortstories.com/onlinereader/the-last-incantation">this story</a></summary>
<blockquote>
The story is written in a descriptive and evocative style, with a focus on the atmosphere and setting. The author uses vivid and detailed language to create a sense of place and time, and employs a variety of literary devices such as similes, metaphors, and allusions to enhance the mood and tone of the narrative. The sentence structure is varied, with a mix of short and long sentences that create a rhythmic flow to the prose.
</blockquote>
</details>
<details>
<summary>Style description of <a href="https://www.libraryofshortstories.com/onlinereader/the-pearl-of-love">this story</a></summary>
<blockquote>
The writing style is descriptive and evocative, with a focus on the beauty and grandeur of the Pearl of Love. The author uses vivid imagery and sensory details to create a rich and immersive atmosphere. The tone is reverential and contemplative, reflecting the prince's deep love for his queen and his dedication to creating a lasting monument to her memory.
</blockquote>
</details>
### Story description to chapters
- [Prompt guide](https://dreamgen.com/docs/models/opus/v1#task-story-description-to-chapter-descriptions)
- Input: A brief plot description and the desired number of chapters.
- Output: A description for each chapter.
### And more...
## Sampling params
For story-writing and role-play, I recommend "Min P" based sampling with `min_p` in the range `[0.01, 0.1]` and with `temperature` in the range `[0.5, 1.5]`, depending on your preferences. A good starting point would be `min_p=0.1; temperature=0.8`.
You may also benefit from setting presence, frequency and repetition penalties, especially at lower temperatures.
## Dataset
The fine-tuning dataset consisted of ~100M tokens of steerable story-writing, role-playing, writing-assistant and general-assistant examples. Each example was up to 31000 tokens long.
All story-writing and role-playing examples were based on human-written text.
## Running the model
The model is should be compatible with any software that supports the base model, but beware of prompting and tokenization.
I recommend using these model versions:
- 7B: [no quant (opus-v1.2-7b)](https://huggingface.co/dreamgen/opus-v1.2-7b)
- 34B: [no quant (opus-v1-34b)](https://huggingface.co/dreamgen/opus-v1-34b) or [awq (opus-v1-34b-awq)](https://huggingface.co/dreamgen/opus-v1-34b-awq)
- 34B: [no quant (opus-v1.2-70b)](https://huggingface.co/dreamgen/opus-v1.2-70b) or [awq (opus-v1.2-70b-awq)](https://huggingface.co/dreamgen/opus-v1.2-70b-awq)
### Running on DreamGen.com (free)
You can run the models on [dreamgen.com](https://dreamgen.com) for free — you can use the built-in UI for story-writing & role-playing, or use [the API](https://dreamgen.com/docs/api).
### Running Locally
- **Make sure your prompt is as close as possible to the Opus V1**
- Regardless of which backend you use, it's important that you format your prompt well and that the tokenization works correctly.
- [Read the prompt guide](https://dreamgen.com/docs/models/opus/v1)
- [Read the prompt formatting code](example/prompt/format.py)
- Make sure `<|im_start|>` and `<|im_end|>` are tokenized correctly
- **vLLM**
- [**Google Colab**](https://colab.research.google.com/drive/1J178fH6IdQOXNi-Njgdacf5QgAxsdT20?usp=sharing): This is a simple interactive Google Colab to do role-play with the 7B model, it should fit on the T4 GPU.
- [Code](example/prompt/interactive.py): This is simple script for interactive chat for one hard-coded scenario.
- **SillyTavern**
- [Official SillyTavern documentation for DreamGen](https://docs.sillytavern.app/usage/api-connections/dreamgen/) -- applies to both the API an local models
- SillyTavern (staging) comes with built-in DreamGen preset for RP
- Other presets can be found [here](https://huggingface.co/dreamgen/opus-v1.2-llama-3-8b/tree/main/configs/silly_tavern), v2 kindly provided by @MarinaraSpaghetti
- Make sure to unselect `Skip special tokens`, otherwise it won't work
- This is just an attempt at approximating the Opus V1 prompt, it won't be perfect
- Character cards specifically rewritten for the built-in DreamGen preset:
- [Seraphina](configs/silly_tavern/cards/Seraphina.png) (based on the default Seraphina card)
- [Lara Lightland](configs/silly_tavern/cards/LaraLightland.png) (based on the card by Deffcolony)
- **LM Studio**
- [Config](configs/lmstudio/preset.json)
- Just like ChatML, just changed "assistant" to "text" role.
- **There's a bug** in LM Studio if you delete a message or click "Continue", [see here for details](https://discord.com/channels/1110598183144399058/1212665261128417280/1212665261128417280).
- **HuggingFace**
- [Chat template](tokenizer_config.json#L51)
- Just like ChatML, just changed "assistant" to "text" role.
## Known Issues
- **34B repetition**:
- The 34B sometimes gets stuck repeating the same word, or synonyms. This seems to be a common problem across various Yi 34B fine-tunes.
- **GGUF**:
- The tokenization might be messed up. Some users reported that `<|im_start|>` and `<|im_end|>` are tokenized as multiple tokens. Also llama.cpp may not tokenize correctly (the Yi tokenizer is subtly different from the Llama 2 tokenizer).
## License
- This model is intended for personal use only, other use is not permitted.
| {"language": ["en"], "license": "cc-by-nc-nd-4.0", "tags": ["unsloth", "axolotl"], "pipeline_tag": "text-generation"} | LoneStriker/opus-v1.2-llama-3-8b-6.0bpw-h6-exl2 | null | [
"transformers",
"pytorch",
"safetensors",
"llama",
"text-generation",
"unsloth",
"axolotl",
"conversational",
"en",
"license:cc-by-nc-nd-4.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"6-bit",
"region:us"
] | null | 2024-04-19T13:25:56+00:00 | [] | [
"en"
] | TAGS
#transformers #pytorch #safetensors #llama #text-generation #unsloth #axolotl #conversational #en #license-cc-by-nc-nd-4.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #6-bit #region-us
|
# Llama 3 DreamGen Opus V1
<div style="display: flex; flex-direction: row; align-items: center;">
<img src="/dreamgen/opus-v1.2-llama-3-8b/resolve/main/images/URL" alt="model logo" style="
border-radius: 12px;
margin-right: 12px;
margin-top: 0px;
margin-bottom: 0px;
max-width: 100px;
height: auto;
"/>
Models for (steerable) story-writing and role-playing.
<br/>All Opus V1 models, including quants.
</div>
## Resources
- Opus V1 prompting guide with many (interactive) examples and prompts that you can copy.
- Google Colab for interactive role-play using 'opus-v1.2-7b'.
- Python code to format the prompt correctly.
- Join the community on Discord to get early access to new models.
<img src="/dreamgen/opus-v1.2-llama-3-8b/resolve/main/images/story_writing.webp" alt="story writing on URL" style="
padding: 12px;
border-radius: 12px;
border: 2px solid #f9a8d4;
background: rgb(9, 9, 11);
"/>
## Prompting
<details>
<summary>The models use an extended version of ChatML.</summary>
The Opus V1 extension is the addition of the 'text' role, and the addition / modification of role names.
Pay attention to the following:
- The 'text' messages can (but don't have to have) 'names', names are used to indicate the "active" character during role-play.
- There can be multiple subsequent message with a 'text' role, especially if names are involved.
- There can be multiple names attached to a message.
- The format for names is 'names= {{name[0]}}; {{name[1]}}', beware of the spaces after 'names=' and after the ';'. This spacing leads to most natural tokenization for the names.
</details>
While the main goal for the models is great story-writing and role-playing performance, the models are also capable of several writing related tasks as well as general assistance.
Here's how you can prompt the model for the following tasks
### Steerable Story-writing and Role-playing:
- Story-writing prompt guide
- Role-playing prompt guide
- Input:
- System prompt: You provide story / role-play description, which consists of:
- Plot description
- Style description
- Characters and their descriptions
- Conversation turns:
- Text / message turn: This represents part of the story or role play
- Instruction: This tells the model what should happen next
- Output: Continuation of the story / role-play.
### Story plot summarization
- Prompt guide
- Input: A story, or a few chapters of a story.
- Output: A description of the story or chapters.
#### Examples:
<details>
<summary>Summary of <a href="URL fiction story</a> in 50 words</summary>
<blockquote>
Malygris, a powerful magician, summons his long-dead lover Nylissa from the grave using necromancy. However, upon seeing her, he realizes that she is not the same person he once knew, leading him to question the nature of love, memory, and the power of magic.
</blockquote>
</details>
<details>
<summary>Summary of <a href="URL fiction story</a> in 200 words</summary>
<blockquote>
The story is a dark fantasy set in the city of Susran, where an ancient and powerful magician named Malygris dwells in a tower atop a conical hill. Malygris, who has mastered all forms of sorcery and necromancy, is plagued by a deep sense of ennui and melancholy. He seeks solace in the memory of Nylissa, a girl he once loved in his youth.
One day, Malygris decides to summon Nylissa's spirit from the grave using his necromantic powers. He performs the necessary rituals and incantations, and Nylissa appears before him as a ghostly apparition. However, as Malygris gazes upon her, he becomes increasingly disillusioned. He notices subtle changes in her appearance and behavior that do not match his memories of her. He begins to question whether this is truly the same Nylissa he once knew, or if it is just another illusion conjured by his magic.
As Malygris grapples with this uncertainty, he becomes increasingly despondent and disillusioned with life itself. He realizes that even his magic cannot bring back the past or make him truly happy. In the end, he dismisses Nylissa's spirit and returns to his lonely tower, resigned to his fate as an old and weary sorcerer.
</blockquote>
</details>
<details>
<summary>Summary of <a href="URL News article</a> in 150 words</summary>
<blockquote>
The article discusses the recent human deaths from diseases transmitted by animals, specifically Alaskapox and bubonic plague. Dr. Leana Wen, an emergency physician and former Baltimore health commissioner, explains the various ways household pets can transmit diseases to humans. These include fecal-oral transmission, scratches and bites, and vector-borne diseases like ticks, fleas, and mosquitoes. Wen emphasizes the importance of vaccinating pets, maintaining cleanliness, and taking commonsense precautions to reduce disease transmission. She also advises that individuals who are immunocompromised, babies, and pregnant women should take additional care when interacting with animals.
</blockquote>
</details>
<details>
<summary>Summary of <a href="URL News article</a> in 50 words</summary>
<blockquote>
A doctor discusses the risks of diseases transmitted from animals to humans, focusing on household pets like cats and dogs. They emphasize the importance of vaccination, hygiene, and regular veterinary care to prevent these illnesses.
</blockquote>
</details>
### Story character description
- Prompt guide
- Input: A story, or a few chapters of a story, set of characters.
- Output: A description of the characters.
#### Examples:
<details>
<summary>Description of the Malygris character from <a href="URL story</a> in 50 words</summary>
<blockquote>
Malygris is an ancient and powerful magician, characterized by his long white beard, cold green eyes, and a violet robe. He is a master of necromancy and possesses a vast knowledge of forbidden magic. Despite his immense power, he is plagued by a deep sense of melancholy and ennui.
</blockquote>
</details>
<details>
<summary>Description of the prince character from <a href="URL story</a> in 50 words</summary>
<blockquote>
The prince is a devoted and determined individual, driven by his love for his late queen. He is described as a graceful youth in the beginning, but as he grows older, his dedication to the Pearl of Love transforms him into a grave and intent man. His sense of color and design evolves over time, reflecting his growing maturity and artistic vision.
</blockquote>
</details>
### Story style description
- Prompt guide
- Input: A story, or a few chapters of a story.
- Output: A description the style of the story.
<details>
<summary>Style description of <a href="URL story</a></summary>
<blockquote>
The story is written in a descriptive and evocative style, with a focus on the atmosphere and setting. The author uses vivid and detailed language to create a sense of place and time, and employs a variety of literary devices such as similes, metaphors, and allusions to enhance the mood and tone of the narrative. The sentence structure is varied, with a mix of short and long sentences that create a rhythmic flow to the prose.
</blockquote>
</details>
<details>
<summary>Style description of <a href="URL story</a></summary>
<blockquote>
The writing style is descriptive and evocative, with a focus on the beauty and grandeur of the Pearl of Love. The author uses vivid imagery and sensory details to create a rich and immersive atmosphere. The tone is reverential and contemplative, reflecting the prince's deep love for his queen and his dedication to creating a lasting monument to her memory.
</blockquote>
</details>
### Story description to chapters
- Prompt guide
- Input: A brief plot description and the desired number of chapters.
- Output: A description for each chapter.
### And more...
## Sampling params
For story-writing and role-play, I recommend "Min P" based sampling with 'min_p' in the range '[0.01, 0.1]' and with 'temperature' in the range '[0.5, 1.5]', depending on your preferences. A good starting point would be 'min_p=0.1; temperature=0.8'.
You may also benefit from setting presence, frequency and repetition penalties, especially at lower temperatures.
## Dataset
The fine-tuning dataset consisted of ~100M tokens of steerable story-writing, role-playing, writing-assistant and general-assistant examples. Each example was up to 31000 tokens long.
All story-writing and role-playing examples were based on human-written text.
!token count distribution
## Running the model
The model is should be compatible with any software that supports the base model, but beware of prompting and tokenization.
I recommend using these model versions:
- 7B: no quant (opus-v1.2-7b)
- 34B: no quant (opus-v1-34b) or awq (opus-v1-34b-awq)
- 34B: no quant (opus-v1.2-70b) or awq (opus-v1.2-70b-awq)
### Running on URL (free)
You can run the models on URL for free — you can use the built-in UI for story-writing & role-playing, or use the API.
### Running Locally
- Make sure your prompt is as close as possible to the Opus V1
- Regardless of which backend you use, it's important that you format your prompt well and that the tokenization works correctly.
- Read the prompt guide
- Read the prompt formatting code
- Make sure '<|im_start|>' and '<|im_end|>' are tokenized correctly
- vLLM
- Google Colab: This is a simple interactive Google Colab to do role-play with the 7B model, it should fit on the T4 GPU.
- Code: This is simple script for interactive chat for one hard-coded scenario.
- SillyTavern
- Official SillyTavern documentation for DreamGen -- applies to both the API an local models
- SillyTavern (staging) comes with built-in DreamGen preset for RP
- Other presets can be found here, v2 kindly provided by @MarinaraSpaghetti
- Make sure to unselect 'Skip special tokens', otherwise it won't work
- This is just an attempt at approximating the Opus V1 prompt, it won't be perfect
- Character cards specifically rewritten for the built-in DreamGen preset:
- Seraphina (based on the default Seraphina card)
- Lara Lightland (based on the card by Deffcolony)
- LM Studio
- Config
- Just like ChatML, just changed "assistant" to "text" role.
- There's a bug in LM Studio if you delete a message or click "Continue", see here for details.
- HuggingFace
- Chat template
- Just like ChatML, just changed "assistant" to "text" role.
## Known Issues
- 34B repetition:
- The 34B sometimes gets stuck repeating the same word, or synonyms. This seems to be a common problem across various Yi 34B fine-tunes.
- GGUF:
- The tokenization might be messed up. Some users reported that '<|im_start|>' and '<|im_end|>' are tokenized as multiple tokens. Also URL may not tokenize correctly (the Yi tokenizer is subtly different from the Llama 2 tokenizer).
## License
- This model is intended for personal use only, other use is not permitted.
| [
"# Llama 3 DreamGen Opus V1\n\n<div style=\"display: flex; flex-direction: row; align-items: center;\">\n<img src=\"/dreamgen/opus-v1.2-llama-3-8b/resolve/main/images/URL\" alt=\"model logo\" style=\"\n border-radius: 12px;\n margin-right: 12px;\n margin-top: 0px;\n margin-bottom: 0px;\n max-width: 100px;\n height: auto;\n\"/>\n\nModels for (steerable) story-writing and role-playing.\n<br/>All Opus V1 models, including quants.\n\n</div>",
"## Resources\n\n- Opus V1 prompting guide with many (interactive) examples and prompts that you can copy.\n- Google Colab for interactive role-play using 'opus-v1.2-7b'.\n- Python code to format the prompt correctly.\n- Join the community on Discord to get early access to new models.\n\n<img src=\"/dreamgen/opus-v1.2-llama-3-8b/resolve/main/images/story_writing.webp\" alt=\"story writing on URL\" style=\"\n padding: 12px;\n border-radius: 12px;\n border: 2px solid #f9a8d4;\n background: rgb(9, 9, 11);\n\"/>",
"## Prompting\n\n<details>\n<summary>The models use an extended version of ChatML.</summary>\n\n\n\nThe Opus V1 extension is the addition of the 'text' role, and the addition / modification of role names.\n\nPay attention to the following:\n\n- The 'text' messages can (but don't have to have) 'names', names are used to indicate the \"active\" character during role-play.\n- There can be multiple subsequent message with a 'text' role, especially if names are involved.\n- There can be multiple names attached to a message.\n- The format for names is 'names= {{name[0]}}; {{name[1]}}', beware of the spaces after 'names=' and after the ';'. This spacing leads to most natural tokenization for the names.\n</details>\n\nWhile the main goal for the models is great story-writing and role-playing performance, the models are also capable of several writing related tasks as well as general assistance.\n\nHere's how you can prompt the model for the following tasks",
"### Steerable Story-writing and Role-playing:\n\n- Story-writing prompt guide\n- Role-playing prompt guide\n- Input:\n - System prompt: You provide story / role-play description, which consists of:\n - Plot description\n - Style description\n - Characters and their descriptions\n - Conversation turns:\n - Text / message turn: This represents part of the story or role play\n - Instruction: This tells the model what should happen next\n- Output: Continuation of the story / role-play.",
"### Story plot summarization\n\n- Prompt guide\n- Input: A story, or a few chapters of a story.\n- Output: A description of the story or chapters.",
"#### Examples:\n\n<details>\n <summary>Summary of <a href=\"URL fiction story</a> in 50 words</summary>\n <blockquote>\n Malygris, a powerful magician, summons his long-dead lover Nylissa from the grave using necromancy. However, upon seeing her, he realizes that she is not the same person he once knew, leading him to question the nature of love, memory, and the power of magic.\n </blockquote>\n</details>\n<details>\n <summary>Summary of <a href=\"URL fiction story</a> in 200 words</summary>\n <blockquote>\nThe story is a dark fantasy set in the city of Susran, where an ancient and powerful magician named Malygris dwells in a tower atop a conical hill. Malygris, who has mastered all forms of sorcery and necromancy, is plagued by a deep sense of ennui and melancholy. He seeks solace in the memory of Nylissa, a girl he once loved in his youth.\n\nOne day, Malygris decides to summon Nylissa's spirit from the grave using his necromantic powers. He performs the necessary rituals and incantations, and Nylissa appears before him as a ghostly apparition. However, as Malygris gazes upon her, he becomes increasingly disillusioned. He notices subtle changes in her appearance and behavior that do not match his memories of her. He begins to question whether this is truly the same Nylissa he once knew, or if it is just another illusion conjured by his magic.\n\nAs Malygris grapples with this uncertainty, he becomes increasingly despondent and disillusioned with life itself. He realizes that even his magic cannot bring back the past or make him truly happy. In the end, he dismisses Nylissa's spirit and returns to his lonely tower, resigned to his fate as an old and weary sorcerer.\n </blockquote>\n\n</details>\n<details>\n <summary>Summary of <a href=\"URL News article</a> in 150 words</summary>\n <blockquote>\nThe article discusses the recent human deaths from diseases transmitted by animals, specifically Alaskapox and bubonic plague. Dr. Leana Wen, an emergency physician and former Baltimore health commissioner, explains the various ways household pets can transmit diseases to humans. These include fecal-oral transmission, scratches and bites, and vector-borne diseases like ticks, fleas, and mosquitoes. Wen emphasizes the importance of vaccinating pets, maintaining cleanliness, and taking commonsense precautions to reduce disease transmission. She also advises that individuals who are immunocompromised, babies, and pregnant women should take additional care when interacting with animals.\n </blockquote>\n</details>\n<details>\n <summary>Summary of <a href=\"URL News article</a> in 50 words</summary>\n <blockquote>\nA doctor discusses the risks of diseases transmitted from animals to humans, focusing on household pets like cats and dogs. They emphasize the importance of vaccination, hygiene, and regular veterinary care to prevent these illnesses.\n </blockquote>\n</details>",
"### Story character description\n\n- Prompt guide\n- Input: A story, or a few chapters of a story, set of characters.\n- Output: A description of the characters.",
"#### Examples:\n\n<details>\n <summary>Description of the Malygris character from <a href=\"URL story</a> in 50 words</summary>\n <blockquote>\nMalygris is an ancient and powerful magician, characterized by his long white beard, cold green eyes, and a violet robe. He is a master of necromancy and possesses a vast knowledge of forbidden magic. Despite his immense power, he is plagued by a deep sense of melancholy and ennui.\n </blockquote>\n</details>\n\n<details>\n <summary>Description of the prince character from <a href=\"URL story</a> in 50 words</summary>\n <blockquote>\nThe prince is a devoted and determined individual, driven by his love for his late queen. He is described as a graceful youth in the beginning, but as he grows older, his dedication to the Pearl of Love transforms him into a grave and intent man. His sense of color and design evolves over time, reflecting his growing maturity and artistic vision.\n </blockquote>\n</details>",
"### Story style description\n\n- Prompt guide\n- Input: A story, or a few chapters of a story.\n- Output: A description the style of the story.\n\n<details>\n <summary>Style description of <a href=\"URL story</a></summary>\n <blockquote>\nThe story is written in a descriptive and evocative style, with a focus on the atmosphere and setting. The author uses vivid and detailed language to create a sense of place and time, and employs a variety of literary devices such as similes, metaphors, and allusions to enhance the mood and tone of the narrative. The sentence structure is varied, with a mix of short and long sentences that create a rhythmic flow to the prose.\n </blockquote>\n</details>\n\n<details>\n <summary>Style description of <a href=\"URL story</a></summary>\n <blockquote>\nThe writing style is descriptive and evocative, with a focus on the beauty and grandeur of the Pearl of Love. The author uses vivid imagery and sensory details to create a rich and immersive atmosphere. The tone is reverential and contemplative, reflecting the prince's deep love for his queen and his dedication to creating a lasting monument to her memory.\n </blockquote>\n</details>",
"### Story description to chapters\n\n- Prompt guide\n- Input: A brief plot description and the desired number of chapters.\n- Output: A description for each chapter.",
"### And more...",
"## Sampling params\n\nFor story-writing and role-play, I recommend \"Min P\" based sampling with 'min_p' in the range '[0.01, 0.1]' and with 'temperature' in the range '[0.5, 1.5]', depending on your preferences. A good starting point would be 'min_p=0.1; temperature=0.8'.\n\nYou may also benefit from setting presence, frequency and repetition penalties, especially at lower temperatures.",
"## Dataset\n\nThe fine-tuning dataset consisted of ~100M tokens of steerable story-writing, role-playing, writing-assistant and general-assistant examples. Each example was up to 31000 tokens long.\n\nAll story-writing and role-playing examples were based on human-written text.\n\n!token count distribution",
"## Running the model\n\nThe model is should be compatible with any software that supports the base model, but beware of prompting and tokenization.\n\nI recommend using these model versions:\n\n- 7B: no quant (opus-v1.2-7b)\n- 34B: no quant (opus-v1-34b) or awq (opus-v1-34b-awq)\n- 34B: no quant (opus-v1.2-70b) or awq (opus-v1.2-70b-awq)",
"### Running on URL (free)\n\nYou can run the models on URL for free — you can use the built-in UI for story-writing & role-playing, or use the API.",
"### Running Locally\n\n- Make sure your prompt is as close as possible to the Opus V1\n - Regardless of which backend you use, it's important that you format your prompt well and that the tokenization works correctly.\n - Read the prompt guide\n - Read the prompt formatting code\n - Make sure '<|im_start|>' and '<|im_end|>' are tokenized correctly\n- vLLM\n - Google Colab: This is a simple interactive Google Colab to do role-play with the 7B model, it should fit on the T4 GPU.\n - Code: This is simple script for interactive chat for one hard-coded scenario.\n- SillyTavern\n - Official SillyTavern documentation for DreamGen -- applies to both the API an local models\n - SillyTavern (staging) comes with built-in DreamGen preset for RP\n - Other presets can be found here, v2 kindly provided by @MarinaraSpaghetti\n - Make sure to unselect 'Skip special tokens', otherwise it won't work\n - This is just an attempt at approximating the Opus V1 prompt, it won't be perfect\n - Character cards specifically rewritten for the built-in DreamGen preset:\n - Seraphina (based on the default Seraphina card)\n - Lara Lightland (based on the card by Deffcolony)\n- LM Studio\n - Config\n - Just like ChatML, just changed \"assistant\" to \"text\" role.\n - There's a bug in LM Studio if you delete a message or click \"Continue\", see here for details.\n- HuggingFace\n - Chat template\n - Just like ChatML, just changed \"assistant\" to \"text\" role.",
"## Known Issues\n\n- 34B repetition:\n - The 34B sometimes gets stuck repeating the same word, or synonyms. This seems to be a common problem across various Yi 34B fine-tunes.\n- GGUF:\n - The tokenization might be messed up. Some users reported that '<|im_start|>' and '<|im_end|>' are tokenized as multiple tokens. Also URL may not tokenize correctly (the Yi tokenizer is subtly different from the Llama 2 tokenizer).",
"## License\n\n- This model is intended for personal use only, other use is not permitted."
] | [
"TAGS\n#transformers #pytorch #safetensors #llama #text-generation #unsloth #axolotl #conversational #en #license-cc-by-nc-nd-4.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #6-bit #region-us \n",
"# Llama 3 DreamGen Opus V1\n\n<div style=\"display: flex; flex-direction: row; align-items: center;\">\n<img src=\"/dreamgen/opus-v1.2-llama-3-8b/resolve/main/images/URL\" alt=\"model logo\" style=\"\n border-radius: 12px;\n margin-right: 12px;\n margin-top: 0px;\n margin-bottom: 0px;\n max-width: 100px;\n height: auto;\n\"/>\n\nModels for (steerable) story-writing and role-playing.\n<br/>All Opus V1 models, including quants.\n\n</div>",
"## Resources\n\n- Opus V1 prompting guide with many (interactive) examples and prompts that you can copy.\n- Google Colab for interactive role-play using 'opus-v1.2-7b'.\n- Python code to format the prompt correctly.\n- Join the community on Discord to get early access to new models.\n\n<img src=\"/dreamgen/opus-v1.2-llama-3-8b/resolve/main/images/story_writing.webp\" alt=\"story writing on URL\" style=\"\n padding: 12px;\n border-radius: 12px;\n border: 2px solid #f9a8d4;\n background: rgb(9, 9, 11);\n\"/>",
"## Prompting\n\n<details>\n<summary>The models use an extended version of ChatML.</summary>\n\n\n\nThe Opus V1 extension is the addition of the 'text' role, and the addition / modification of role names.\n\nPay attention to the following:\n\n- The 'text' messages can (but don't have to have) 'names', names are used to indicate the \"active\" character during role-play.\n- There can be multiple subsequent message with a 'text' role, especially if names are involved.\n- There can be multiple names attached to a message.\n- The format for names is 'names= {{name[0]}}; {{name[1]}}', beware of the spaces after 'names=' and after the ';'. This spacing leads to most natural tokenization for the names.\n</details>\n\nWhile the main goal for the models is great story-writing and role-playing performance, the models are also capable of several writing related tasks as well as general assistance.\n\nHere's how you can prompt the model for the following tasks",
"### Steerable Story-writing and Role-playing:\n\n- Story-writing prompt guide\n- Role-playing prompt guide\n- Input:\n - System prompt: You provide story / role-play description, which consists of:\n - Plot description\n - Style description\n - Characters and their descriptions\n - Conversation turns:\n - Text / message turn: This represents part of the story or role play\n - Instruction: This tells the model what should happen next\n- Output: Continuation of the story / role-play.",
"### Story plot summarization\n\n- Prompt guide\n- Input: A story, or a few chapters of a story.\n- Output: A description of the story or chapters.",
"#### Examples:\n\n<details>\n <summary>Summary of <a href=\"URL fiction story</a> in 50 words</summary>\n <blockquote>\n Malygris, a powerful magician, summons his long-dead lover Nylissa from the grave using necromancy. However, upon seeing her, he realizes that she is not the same person he once knew, leading him to question the nature of love, memory, and the power of magic.\n </blockquote>\n</details>\n<details>\n <summary>Summary of <a href=\"URL fiction story</a> in 200 words</summary>\n <blockquote>\nThe story is a dark fantasy set in the city of Susran, where an ancient and powerful magician named Malygris dwells in a tower atop a conical hill. Malygris, who has mastered all forms of sorcery and necromancy, is plagued by a deep sense of ennui and melancholy. He seeks solace in the memory of Nylissa, a girl he once loved in his youth.\n\nOne day, Malygris decides to summon Nylissa's spirit from the grave using his necromantic powers. He performs the necessary rituals and incantations, and Nylissa appears before him as a ghostly apparition. However, as Malygris gazes upon her, he becomes increasingly disillusioned. He notices subtle changes in her appearance and behavior that do not match his memories of her. He begins to question whether this is truly the same Nylissa he once knew, or if it is just another illusion conjured by his magic.\n\nAs Malygris grapples with this uncertainty, he becomes increasingly despondent and disillusioned with life itself. He realizes that even his magic cannot bring back the past or make him truly happy. In the end, he dismisses Nylissa's spirit and returns to his lonely tower, resigned to his fate as an old and weary sorcerer.\n </blockquote>\n\n</details>\n<details>\n <summary>Summary of <a href=\"URL News article</a> in 150 words</summary>\n <blockquote>\nThe article discusses the recent human deaths from diseases transmitted by animals, specifically Alaskapox and bubonic plague. Dr. Leana Wen, an emergency physician and former Baltimore health commissioner, explains the various ways household pets can transmit diseases to humans. These include fecal-oral transmission, scratches and bites, and vector-borne diseases like ticks, fleas, and mosquitoes. Wen emphasizes the importance of vaccinating pets, maintaining cleanliness, and taking commonsense precautions to reduce disease transmission. She also advises that individuals who are immunocompromised, babies, and pregnant women should take additional care when interacting with animals.\n </blockquote>\n</details>\n<details>\n <summary>Summary of <a href=\"URL News article</a> in 50 words</summary>\n <blockquote>\nA doctor discusses the risks of diseases transmitted from animals to humans, focusing on household pets like cats and dogs. They emphasize the importance of vaccination, hygiene, and regular veterinary care to prevent these illnesses.\n </blockquote>\n</details>",
"### Story character description\n\n- Prompt guide\n- Input: A story, or a few chapters of a story, set of characters.\n- Output: A description of the characters.",
"#### Examples:\n\n<details>\n <summary>Description of the Malygris character from <a href=\"URL story</a> in 50 words</summary>\n <blockquote>\nMalygris is an ancient and powerful magician, characterized by his long white beard, cold green eyes, and a violet robe. He is a master of necromancy and possesses a vast knowledge of forbidden magic. Despite his immense power, he is plagued by a deep sense of melancholy and ennui.\n </blockquote>\n</details>\n\n<details>\n <summary>Description of the prince character from <a href=\"URL story</a> in 50 words</summary>\n <blockquote>\nThe prince is a devoted and determined individual, driven by his love for his late queen. He is described as a graceful youth in the beginning, but as he grows older, his dedication to the Pearl of Love transforms him into a grave and intent man. His sense of color and design evolves over time, reflecting his growing maturity and artistic vision.\n </blockquote>\n</details>",
"### Story style description\n\n- Prompt guide\n- Input: A story, or a few chapters of a story.\n- Output: A description the style of the story.\n\n<details>\n <summary>Style description of <a href=\"URL story</a></summary>\n <blockquote>\nThe story is written in a descriptive and evocative style, with a focus on the atmosphere and setting. The author uses vivid and detailed language to create a sense of place and time, and employs a variety of literary devices such as similes, metaphors, and allusions to enhance the mood and tone of the narrative. The sentence structure is varied, with a mix of short and long sentences that create a rhythmic flow to the prose.\n </blockquote>\n</details>\n\n<details>\n <summary>Style description of <a href=\"URL story</a></summary>\n <blockquote>\nThe writing style is descriptive and evocative, with a focus on the beauty and grandeur of the Pearl of Love. The author uses vivid imagery and sensory details to create a rich and immersive atmosphere. The tone is reverential and contemplative, reflecting the prince's deep love for his queen and his dedication to creating a lasting monument to her memory.\n </blockquote>\n</details>",
"### Story description to chapters\n\n- Prompt guide\n- Input: A brief plot description and the desired number of chapters.\n- Output: A description for each chapter.",
"### And more...",
"## Sampling params\n\nFor story-writing and role-play, I recommend \"Min P\" based sampling with 'min_p' in the range '[0.01, 0.1]' and with 'temperature' in the range '[0.5, 1.5]', depending on your preferences. A good starting point would be 'min_p=0.1; temperature=0.8'.\n\nYou may also benefit from setting presence, frequency and repetition penalties, especially at lower temperatures.",
"## Dataset\n\nThe fine-tuning dataset consisted of ~100M tokens of steerable story-writing, role-playing, writing-assistant and general-assistant examples. Each example was up to 31000 tokens long.\n\nAll story-writing and role-playing examples were based on human-written text.\n\n!token count distribution",
"## Running the model\n\nThe model is should be compatible with any software that supports the base model, but beware of prompting and tokenization.\n\nI recommend using these model versions:\n\n- 7B: no quant (opus-v1.2-7b)\n- 34B: no quant (opus-v1-34b) or awq (opus-v1-34b-awq)\n- 34B: no quant (opus-v1.2-70b) or awq (opus-v1.2-70b-awq)",
"### Running on URL (free)\n\nYou can run the models on URL for free — you can use the built-in UI for story-writing & role-playing, or use the API.",
"### Running Locally\n\n- Make sure your prompt is as close as possible to the Opus V1\n - Regardless of which backend you use, it's important that you format your prompt well and that the tokenization works correctly.\n - Read the prompt guide\n - Read the prompt formatting code\n - Make sure '<|im_start|>' and '<|im_end|>' are tokenized correctly\n- vLLM\n - Google Colab: This is a simple interactive Google Colab to do role-play with the 7B model, it should fit on the T4 GPU.\n - Code: This is simple script for interactive chat for one hard-coded scenario.\n- SillyTavern\n - Official SillyTavern documentation for DreamGen -- applies to both the API an local models\n - SillyTavern (staging) comes with built-in DreamGen preset for RP\n - Other presets can be found here, v2 kindly provided by @MarinaraSpaghetti\n - Make sure to unselect 'Skip special tokens', otherwise it won't work\n - This is just an attempt at approximating the Opus V1 prompt, it won't be perfect\n - Character cards specifically rewritten for the built-in DreamGen preset:\n - Seraphina (based on the default Seraphina card)\n - Lara Lightland (based on the card by Deffcolony)\n- LM Studio\n - Config\n - Just like ChatML, just changed \"assistant\" to \"text\" role.\n - There's a bug in LM Studio if you delete a message or click \"Continue\", see here for details.\n- HuggingFace\n - Chat template\n - Just like ChatML, just changed \"assistant\" to \"text\" role.",
"## Known Issues\n\n- 34B repetition:\n - The 34B sometimes gets stuck repeating the same word, or synonyms. This seems to be a common problem across various Yi 34B fine-tunes.\n- GGUF:\n - The tokenization might be messed up. Some users reported that '<|im_start|>' and '<|im_end|>' are tokenized as multiple tokens. Also URL may not tokenize correctly (the Yi tokenizer is subtly different from the Llama 2 tokenizer).",
"## License\n\n- This model is intended for personal use only, other use is not permitted."
] |
text-generation | transformers | # zephyr-wizard-kuno-royale-BF16-merge-7B
This is an experimental merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit). All source model weights are BF16, avoiding issues arising from mixed-precision merges.
Although the zephyr beta and WizardLM 2 7B models are touted as SOTA and can generate varied prose compared to base Mistral v0.1, their relatively mediocre benchmarks under GSM-8K suggests only average reasoning capability in one-shot narrative text completion. The kuno-royale-v2 model was selected for merger because of its higher GSM-8K rating.
Native prompt format is Alpaca, although at least one of the prior models was fine-tuned to Vicuna.
Tested lightly with ChatML instruct prompts, temperature 1, and minP 0.02.
## Merge Details
### Merge Method
This model was merged using the SLERP merge method.
### Models Merged
The following models were included in the merge:
* [grimjim/zephyr-beta-wizardLM-2-merge-7B](https://huggingface.co/grimjim/zephyr-beta-wizardLM-2-merge-7B)
* [core-3/kuno-royale-v2-7b](https://huggingface.co/core-3/kuno-royale-v2-7b)
### Configuration
The following YAML configuration was used to produce this model:
```yaml
slices:
- sources:
- model: grimjim/zephyr-beta-wizardLM-2-merge-7B
layer_range: [0,32]
- model: core-3/kuno-royale-v2-7b
layer_range: [0,32]
merge_method: slerp
base_model: grimjim/zephyr-beta-wizardLM-2-merge-7B
parameters:
t:
- value: 0.5
dtype: bfloat16
```
| {"license": "cc-by-nc-4.0", "library_name": "transformers", "tags": ["mergekit", "merge"], "base_model": ["grimjim/zephyr-beta-wizardLM-2-merge-7B", "core-3/kuno-royale-v2-7b"], "pipeline_tag": "text-generation", "model-index": [{"name": "grimjim/zephyr-wizard-kuno-royale-BF16-merge-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": 68.69, "name": "normalized accuracy"}], "source": {"url": "https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=grimjim/zephyr-wizard-kuno-royale-BF16-merge-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": 86.87, "name": "normalized accuracy"}], "source": {"url": "https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=grimjim/zephyr-wizard-kuno-royale-BF16-merge-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": 64.87, "name": "accuracy"}], "source": {"url": "https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=grimjim/zephyr-wizard-kuno-royale-BF16-merge-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": 65.47}], "source": {"url": "https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=grimjim/zephyr-wizard-kuno-royale-BF16-merge-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": 80.03, "name": "accuracy"}], "source": {"url": "https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=grimjim/zephyr-wizard-kuno-royale-BF16-merge-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": 63.31, "name": "accuracy"}], "source": {"url": "https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=grimjim/zephyr-wizard-kuno-royale-BF16-merge-7B", "name": "Open LLM Leaderboard"}}]}]} | grimjim/zephyr-wizard-kuno-royale-BF16-merge-7B | null | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"mergekit",
"merge",
"conversational",
"base_model:grimjim/zephyr-beta-wizardLM-2-merge-7B",
"base_model:core-3/kuno-royale-v2-7b",
"license:cc-by-nc-4.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-04-19T13:26:00+00:00 | [] | [] | TAGS
#transformers #safetensors #mistral #text-generation #mergekit #merge #conversational #base_model-grimjim/zephyr-beta-wizardLM-2-merge-7B #base_model-core-3/kuno-royale-v2-7b #license-cc-by-nc-4.0 #model-index #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us
| # zephyr-wizard-kuno-royale-BF16-merge-7B
This is an experimental merge of pre-trained language models created using mergekit. All source model weights are BF16, avoiding issues arising from mixed-precision merges.
Although the zephyr beta and WizardLM 2 7B models are touted as SOTA and can generate varied prose compared to base Mistral v0.1, their relatively mediocre benchmarks under GSM-8K suggests only average reasoning capability in one-shot narrative text completion. The kuno-royale-v2 model was selected for merger because of its higher GSM-8K rating.
Native prompt format is Alpaca, although at least one of the prior models was fine-tuned to Vicuna.
Tested lightly with ChatML instruct prompts, temperature 1, and minP 0.02.
## Merge Details
### Merge Method
This model was merged using the SLERP merge method.
### Models Merged
The following models were included in the merge:
* grimjim/zephyr-beta-wizardLM-2-merge-7B
* core-3/kuno-royale-v2-7b
### Configuration
The following YAML configuration was used to produce this model:
| [
"# zephyr-wizard-kuno-royale-BF16-merge-7B\n\nThis is an experimental merge of pre-trained language models created using mergekit. All source model weights are BF16, avoiding issues arising from mixed-precision merges.\n\nAlthough the zephyr beta and WizardLM 2 7B models are touted as SOTA and can generate varied prose compared to base Mistral v0.1, their relatively mediocre benchmarks under GSM-8K suggests only average reasoning capability in one-shot narrative text completion. The kuno-royale-v2 model was selected for merger because of its higher GSM-8K rating.\n\nNative prompt format is Alpaca, although at least one of the prior models was fine-tuned to Vicuna.\n\nTested lightly with ChatML instruct prompts, temperature 1, and minP 0.02.",
"## 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* grimjim/zephyr-beta-wizardLM-2-merge-7B\n* core-3/kuno-royale-v2-7b",
"### Configuration\n\nThe following YAML configuration was used to produce this model:"
] | [
"TAGS\n#transformers #safetensors #mistral #text-generation #mergekit #merge #conversational #base_model-grimjim/zephyr-beta-wizardLM-2-merge-7B #base_model-core-3/kuno-royale-v2-7b #license-cc-by-nc-4.0 #model-index #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n",
"# zephyr-wizard-kuno-royale-BF16-merge-7B\n\nThis is an experimental merge of pre-trained language models created using mergekit. All source model weights are BF16, avoiding issues arising from mixed-precision merges.\n\nAlthough the zephyr beta and WizardLM 2 7B models are touted as SOTA and can generate varied prose compared to base Mistral v0.1, their relatively mediocre benchmarks under GSM-8K suggests only average reasoning capability in one-shot narrative text completion. The kuno-royale-v2 model was selected for merger because of its higher GSM-8K rating.\n\nNative prompt format is Alpaca, although at least one of the prior models was fine-tuned to Vicuna.\n\nTested lightly with ChatML instruct prompts, temperature 1, and minP 0.02.",
"## 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* grimjim/zephyr-beta-wizardLM-2-merge-7B\n* core-3/kuno-royale-v2-7b",
"### Configuration\n\nThe following YAML configuration was used to produce this model:"
] |
text-generation | transformers |
# Llama 3 DreamGen Opus V1
<div style="display: flex; flex-direction: row; align-items: center;">
<img src="/dreamgen/opus-v1.2-llama-3-8b/resolve/main/images/logo-1024.png" alt="model logo" style="
border-radius: 12px;
margin-right: 12px;
margin-top: 0px;
margin-bottom: 0px;
max-width: 100px;
height: auto;
"/>
Models for **(steerable) story-writing and role-playing**.
<br/>[All Opus V1 models, including quants](https://huggingface.co/collections/dreamgen/opus-v1-65d092a6f8ab7fc669111b31).
</div>
## Resources
- [**Opus V1 prompting guide**](https://dreamgen.com/docs/models/opus/v1) with many (interactive) examples and prompts that you can copy.
- [**Google Colab**](https://colab.research.google.com/drive/1J178fH6IdQOXNi-Njgdacf5QgAxsdT20?usp=sharing) for interactive role-play using `opus-v1.2-7b`.
- [Python code](example/prompt/format.py) to format the prompt correctly.
- Join the community on [**Discord**](https://dreamgen.com/discord) to get early access to new models.
<img src="/dreamgen/opus-v1.2-llama-3-8b/resolve/main/images/story_writing.webp" alt="story writing on dreamgen.com" style="
padding: 12px;
border-radius: 12px;
border: 2px solid #f9a8d4;
background: rgb(9, 9, 11);
"/>
## Prompting
<details>
<summary>The models use an extended version of ChatML.</summary>
```
<|im_start|>system
(Story description in the right format here)
(Typically consists of plot description, style description and characters)<|im_end|>
<|im_start|>user
(Your instruction on how the story should continue)<|im_end|>
<|im_start|>text names= Alice
(Continuation of the story from the Alice character)<|im_end|>
<|im_start|>text
(Continuation of the story from no character in particular (pure narration))<|im_end|>
<|im_start|>user
(Your instruction on how the story should continue)<|im_end|>
<|im_start|>text names= Bob
(Continuation of the story from the Bob character)<|im_end|>
```
The Opus V1 extension is the addition of the `text` role, and the addition / modification of role names.
Pay attention to the following:
- The `text` messages can (but don't have to have) `names`, names are used to indicate the "active" character during role-play.
- There can be multiple subsequent message with a `text` role, especially if names are involved.
- There can be multiple names attached to a message.
- The format for names is `names= {{name[0]}}; {{name[1]}}`, beware of the spaces after `names=` and after the `;`. This spacing leads to most natural tokenization for the names.
</details>
While the main goal for the models is great story-writing and role-playing performance, the models are also capable of several writing related tasks as well as general assistance.
Here's how you can prompt the model for the following tasks
### Steerable Story-writing and Role-playing:
- [Story-writing prompt guide](https://dreamgen.com/docs/models/opus/v1#task-story-writing)
- [Role-playing prompt guide](https://dreamgen.com/docs/models/opus/v1#task-role-playing)
- Input:
- System prompt: You provide story / role-play description, which consists of:
- Plot description
- Style description
- Characters and their descriptions
- Conversation turns:
- Text / message turn: This represents part of the story or role play
- Instruction: This tells the model what should happen next
- Output: Continuation of the story / role-play.
### Story plot summarization
- [Prompt guide](https://dreamgen.com/docs/models/opus/v1#task-plot-description)
- Input: A story, or a few chapters of a story.
- Output: A description of the story or chapters.
#### Examples:
<details>
<summary>Summary of <a href="https://www.libraryofshortstories.com/onlinereader/the-last-incantation">short fiction story</a> in 50 words</summary>
<blockquote>
Malygris, a powerful magician, summons his long-dead lover Nylissa from the grave using necromancy. However, upon seeing her, he realizes that she is not the same person he once knew, leading him to question the nature of love, memory, and the power of magic.
</blockquote>
</details>
<details>
<summary>Summary of <a href="https://www.libraryofshortstories.com/onlinereader/the-last-incantation">short fiction story</a> in 200 words</summary>
<blockquote>
The story is a dark fantasy set in the city of Susran, where an ancient and powerful magician named Malygris dwells in a tower atop a conical hill. Malygris, who has mastered all forms of sorcery and necromancy, is plagued by a deep sense of ennui and melancholy. He seeks solace in the memory of Nylissa, a girl he once loved in his youth.
One day, Malygris decides to summon Nylissa's spirit from the grave using his necromantic powers. He performs the necessary rituals and incantations, and Nylissa appears before him as a ghostly apparition. However, as Malygris gazes upon her, he becomes increasingly disillusioned. He notices subtle changes in her appearance and behavior that do not match his memories of her. He begins to question whether this is truly the same Nylissa he once knew, or if it is just another illusion conjured by his magic.
As Malygris grapples with this uncertainty, he becomes increasingly despondent and disillusioned with life itself. He realizes that even his magic cannot bring back the past or make him truly happy. In the end, he dismisses Nylissa's spirit and returns to his lonely tower, resigned to his fate as an old and weary sorcerer.
</blockquote>
</details>
<details>
<summary>Summary of <a href="https://edition.cnn.com/2024/02/29/health/pets-diseases-viruses-bacteria-wellness/index.html">CNN News article</a> in 150 words</summary>
<blockquote>
The article discusses the recent human deaths from diseases transmitted by animals, specifically Alaskapox and bubonic plague. Dr. Leana Wen, an emergency physician and former Baltimore health commissioner, explains the various ways household pets can transmit diseases to humans. These include fecal-oral transmission, scratches and bites, and vector-borne diseases like ticks, fleas, and mosquitoes. Wen emphasizes the importance of vaccinating pets, maintaining cleanliness, and taking commonsense precautions to reduce disease transmission. She also advises that individuals who are immunocompromised, babies, and pregnant women should take additional care when interacting with animals.
</blockquote>
</details>
<details>
<summary>Summary of <a href="https://edition.cnn.com/2024/02/29/health/pets-diseases-viruses-bacteria-wellness/index.html">CNN News article</a> in 50 words</summary>
<blockquote>
A doctor discusses the risks of diseases transmitted from animals to humans, focusing on household pets like cats and dogs. They emphasize the importance of vaccination, hygiene, and regular veterinary care to prevent these illnesses.
</blockquote>
</details>
### Story character description
- [Prompt guide](https://dreamgen.com/docs/models/opus/v1#task-char-description)
- Input: A story, or a few chapters of a story, set of characters.
- Output: A description of the characters.
#### Examples:
<details>
<summary>Description of the Malygris character from <a href="https://www.libraryofshortstories.com/onlinereader/the-last-incantation">this story</a> in 50 words</summary>
<blockquote>
Malygris is an ancient and powerful magician, characterized by his long white beard, cold green eyes, and a violet robe. He is a master of necromancy and possesses a vast knowledge of forbidden magic. Despite his immense power, he is plagued by a deep sense of melancholy and ennui.
</blockquote>
</details>
<details>
<summary>Description of the prince character from <a href="https://www.libraryofshortstories.com/onlinereader/the-pearl-of-love">this story</a> in 50 words</summary>
<blockquote>
The prince is a devoted and determined individual, driven by his love for his late queen. He is described as a graceful youth in the beginning, but as he grows older, his dedication to the Pearl of Love transforms him into a grave and intent man. His sense of color and design evolves over time, reflecting his growing maturity and artistic vision.
</blockquote>
</details>
### Story style description
- [Prompt guide](https://dreamgen.com/docs/models/opus/v1#task-style-description)
- Input: A story, or a few chapters of a story.
- Output: A description the style of the story.
<details>
<summary>Style description of <a href="https://www.libraryofshortstories.com/onlinereader/the-last-incantation">this story</a></summary>
<blockquote>
The story is written in a descriptive and evocative style, with a focus on the atmosphere and setting. The author uses vivid and detailed language to create a sense of place and time, and employs a variety of literary devices such as similes, metaphors, and allusions to enhance the mood and tone of the narrative. The sentence structure is varied, with a mix of short and long sentences that create a rhythmic flow to the prose.
</blockquote>
</details>
<details>
<summary>Style description of <a href="https://www.libraryofshortstories.com/onlinereader/the-pearl-of-love">this story</a></summary>
<blockquote>
The writing style is descriptive and evocative, with a focus on the beauty and grandeur of the Pearl of Love. The author uses vivid imagery and sensory details to create a rich and immersive atmosphere. The tone is reverential and contemplative, reflecting the prince's deep love for his queen and his dedication to creating a lasting monument to her memory.
</blockquote>
</details>
### Story description to chapters
- [Prompt guide](https://dreamgen.com/docs/models/opus/v1#task-story-description-to-chapter-descriptions)
- Input: A brief plot description and the desired number of chapters.
- Output: A description for each chapter.
### And more...
## Sampling params
For story-writing and role-play, I recommend "Min P" based sampling with `min_p` in the range `[0.01, 0.1]` and with `temperature` in the range `[0.5, 1.5]`, depending on your preferences. A good starting point would be `min_p=0.1; temperature=0.8`.
You may also benefit from setting presence, frequency and repetition penalties, especially at lower temperatures.
## Dataset
The fine-tuning dataset consisted of ~100M tokens of steerable story-writing, role-playing, writing-assistant and general-assistant examples. Each example was up to 31000 tokens long.
All story-writing and role-playing examples were based on human-written text.
## Running the model
The model is should be compatible with any software that supports the base model, but beware of prompting and tokenization.
I recommend using these model versions:
- 7B: [no quant (opus-v1.2-7b)](https://huggingface.co/dreamgen/opus-v1.2-7b)
- 34B: [no quant (opus-v1-34b)](https://huggingface.co/dreamgen/opus-v1-34b) or [awq (opus-v1-34b-awq)](https://huggingface.co/dreamgen/opus-v1-34b-awq)
- 34B: [no quant (opus-v1.2-70b)](https://huggingface.co/dreamgen/opus-v1.2-70b) or [awq (opus-v1.2-70b-awq)](https://huggingface.co/dreamgen/opus-v1.2-70b-awq)
### Running on DreamGen.com (free)
You can run the models on [dreamgen.com](https://dreamgen.com) for free — you can use the built-in UI for story-writing & role-playing, or use [the API](https://dreamgen.com/docs/api).
### Running Locally
- **Make sure your prompt is as close as possible to the Opus V1**
- Regardless of which backend you use, it's important that you format your prompt well and that the tokenization works correctly.
- [Read the prompt guide](https://dreamgen.com/docs/models/opus/v1)
- [Read the prompt formatting code](example/prompt/format.py)
- Make sure `<|im_start|>` and `<|im_end|>` are tokenized correctly
- **vLLM**
- [**Google Colab**](https://colab.research.google.com/drive/1J178fH6IdQOXNi-Njgdacf5QgAxsdT20?usp=sharing): This is a simple interactive Google Colab to do role-play with the 7B model, it should fit on the T4 GPU.
- [Code](example/prompt/interactive.py): This is simple script for interactive chat for one hard-coded scenario.
- **SillyTavern**
- [Official SillyTavern documentation for DreamGen](https://docs.sillytavern.app/usage/api-connections/dreamgen/) -- applies to both the API an local models
- SillyTavern (staging) comes with built-in DreamGen preset for RP
- Other presets can be found [here](https://huggingface.co/dreamgen/opus-v1.2-llama-3-8b/tree/main/configs/silly_tavern), v2 kindly provided by @MarinaraSpaghetti
- Make sure to unselect `Skip special tokens`, otherwise it won't work
- This is just an attempt at approximating the Opus V1 prompt, it won't be perfect
- Character cards specifically rewritten for the built-in DreamGen preset:
- [Seraphina](configs/silly_tavern/cards/Seraphina.png) (based on the default Seraphina card)
- [Lara Lightland](configs/silly_tavern/cards/LaraLightland.png) (based on the card by Deffcolony)
- **LM Studio**
- [Config](configs/lmstudio/preset.json)
- Just like ChatML, just changed "assistant" to "text" role.
- **There's a bug** in LM Studio if you delete a message or click "Continue", [see here for details](https://discord.com/channels/1110598183144399058/1212665261128417280/1212665261128417280).
- **HuggingFace**
- [Chat template](tokenizer_config.json#L51)
- Just like ChatML, just changed "assistant" to "text" role.
## Known Issues
- **34B repetition**:
- The 34B sometimes gets stuck repeating the same word, or synonyms. This seems to be a common problem across various Yi 34B fine-tunes.
- **GGUF**:
- The tokenization might be messed up. Some users reported that `<|im_start|>` and `<|im_end|>` are tokenized as multiple tokens. Also llama.cpp may not tokenize correctly (the Yi tokenizer is subtly different from the Llama 2 tokenizer).
## License
- This model is intended for personal use only, other use is not permitted.
| {"language": ["en"], "license": "cc-by-nc-nd-4.0", "tags": ["unsloth", "axolotl"], "pipeline_tag": "text-generation"} | LoneStriker/opus-v1.2-llama-3-8b-8.0bpw-h8-exl2 | null | [
"transformers",
"pytorch",
"safetensors",
"llama",
"text-generation",
"unsloth",
"axolotl",
"conversational",
"en",
"license:cc-by-nc-nd-4.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"8-bit",
"region:us"
] | null | 2024-04-19T13:28:48+00:00 | [] | [
"en"
] | TAGS
#transformers #pytorch #safetensors #llama #text-generation #unsloth #axolotl #conversational #en #license-cc-by-nc-nd-4.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #8-bit #region-us
|
# Llama 3 DreamGen Opus V1
<div style="display: flex; flex-direction: row; align-items: center;">
<img src="/dreamgen/opus-v1.2-llama-3-8b/resolve/main/images/URL" alt="model logo" style="
border-radius: 12px;
margin-right: 12px;
margin-top: 0px;
margin-bottom: 0px;
max-width: 100px;
height: auto;
"/>
Models for (steerable) story-writing and role-playing.
<br/>All Opus V1 models, including quants.
</div>
## Resources
- Opus V1 prompting guide with many (interactive) examples and prompts that you can copy.
- Google Colab for interactive role-play using 'opus-v1.2-7b'.
- Python code to format the prompt correctly.
- Join the community on Discord to get early access to new models.
<img src="/dreamgen/opus-v1.2-llama-3-8b/resolve/main/images/story_writing.webp" alt="story writing on URL" style="
padding: 12px;
border-radius: 12px;
border: 2px solid #f9a8d4;
background: rgb(9, 9, 11);
"/>
## Prompting
<details>
<summary>The models use an extended version of ChatML.</summary>
The Opus V1 extension is the addition of the 'text' role, and the addition / modification of role names.
Pay attention to the following:
- The 'text' messages can (but don't have to have) 'names', names are used to indicate the "active" character during role-play.
- There can be multiple subsequent message with a 'text' role, especially if names are involved.
- There can be multiple names attached to a message.
- The format for names is 'names= {{name[0]}}; {{name[1]}}', beware of the spaces after 'names=' and after the ';'. This spacing leads to most natural tokenization for the names.
</details>
While the main goal for the models is great story-writing and role-playing performance, the models are also capable of several writing related tasks as well as general assistance.
Here's how you can prompt the model for the following tasks
### Steerable Story-writing and Role-playing:
- Story-writing prompt guide
- Role-playing prompt guide
- Input:
- System prompt: You provide story / role-play description, which consists of:
- Plot description
- Style description
- Characters and their descriptions
- Conversation turns:
- Text / message turn: This represents part of the story or role play
- Instruction: This tells the model what should happen next
- Output: Continuation of the story / role-play.
### Story plot summarization
- Prompt guide
- Input: A story, or a few chapters of a story.
- Output: A description of the story or chapters.
#### Examples:
<details>
<summary>Summary of <a href="URL fiction story</a> in 50 words</summary>
<blockquote>
Malygris, a powerful magician, summons his long-dead lover Nylissa from the grave using necromancy. However, upon seeing her, he realizes that she is not the same person he once knew, leading him to question the nature of love, memory, and the power of magic.
</blockquote>
</details>
<details>
<summary>Summary of <a href="URL fiction story</a> in 200 words</summary>
<blockquote>
The story is a dark fantasy set in the city of Susran, where an ancient and powerful magician named Malygris dwells in a tower atop a conical hill. Malygris, who has mastered all forms of sorcery and necromancy, is plagued by a deep sense of ennui and melancholy. He seeks solace in the memory of Nylissa, a girl he once loved in his youth.
One day, Malygris decides to summon Nylissa's spirit from the grave using his necromantic powers. He performs the necessary rituals and incantations, and Nylissa appears before him as a ghostly apparition. However, as Malygris gazes upon her, he becomes increasingly disillusioned. He notices subtle changes in her appearance and behavior that do not match his memories of her. He begins to question whether this is truly the same Nylissa he once knew, or if it is just another illusion conjured by his magic.
As Malygris grapples with this uncertainty, he becomes increasingly despondent and disillusioned with life itself. He realizes that even his magic cannot bring back the past or make him truly happy. In the end, he dismisses Nylissa's spirit and returns to his lonely tower, resigned to his fate as an old and weary sorcerer.
</blockquote>
</details>
<details>
<summary>Summary of <a href="URL News article</a> in 150 words</summary>
<blockquote>
The article discusses the recent human deaths from diseases transmitted by animals, specifically Alaskapox and bubonic plague. Dr. Leana Wen, an emergency physician and former Baltimore health commissioner, explains the various ways household pets can transmit diseases to humans. These include fecal-oral transmission, scratches and bites, and vector-borne diseases like ticks, fleas, and mosquitoes. Wen emphasizes the importance of vaccinating pets, maintaining cleanliness, and taking commonsense precautions to reduce disease transmission. She also advises that individuals who are immunocompromised, babies, and pregnant women should take additional care when interacting with animals.
</blockquote>
</details>
<details>
<summary>Summary of <a href="URL News article</a> in 50 words</summary>
<blockquote>
A doctor discusses the risks of diseases transmitted from animals to humans, focusing on household pets like cats and dogs. They emphasize the importance of vaccination, hygiene, and regular veterinary care to prevent these illnesses.
</blockquote>
</details>
### Story character description
- Prompt guide
- Input: A story, or a few chapters of a story, set of characters.
- Output: A description of the characters.
#### Examples:
<details>
<summary>Description of the Malygris character from <a href="URL story</a> in 50 words</summary>
<blockquote>
Malygris is an ancient and powerful magician, characterized by his long white beard, cold green eyes, and a violet robe. He is a master of necromancy and possesses a vast knowledge of forbidden magic. Despite his immense power, he is plagued by a deep sense of melancholy and ennui.
</blockquote>
</details>
<details>
<summary>Description of the prince character from <a href="URL story</a> in 50 words</summary>
<blockquote>
The prince is a devoted and determined individual, driven by his love for his late queen. He is described as a graceful youth in the beginning, but as he grows older, his dedication to the Pearl of Love transforms him into a grave and intent man. His sense of color and design evolves over time, reflecting his growing maturity and artistic vision.
</blockquote>
</details>
### Story style description
- Prompt guide
- Input: A story, or a few chapters of a story.
- Output: A description the style of the story.
<details>
<summary>Style description of <a href="URL story</a></summary>
<blockquote>
The story is written in a descriptive and evocative style, with a focus on the atmosphere and setting. The author uses vivid and detailed language to create a sense of place and time, and employs a variety of literary devices such as similes, metaphors, and allusions to enhance the mood and tone of the narrative. The sentence structure is varied, with a mix of short and long sentences that create a rhythmic flow to the prose.
</blockquote>
</details>
<details>
<summary>Style description of <a href="URL story</a></summary>
<blockquote>
The writing style is descriptive and evocative, with a focus on the beauty and grandeur of the Pearl of Love. The author uses vivid imagery and sensory details to create a rich and immersive atmosphere. The tone is reverential and contemplative, reflecting the prince's deep love for his queen and his dedication to creating a lasting monument to her memory.
</blockquote>
</details>
### Story description to chapters
- Prompt guide
- Input: A brief plot description and the desired number of chapters.
- Output: A description for each chapter.
### And more...
## Sampling params
For story-writing and role-play, I recommend "Min P" based sampling with 'min_p' in the range '[0.01, 0.1]' and with 'temperature' in the range '[0.5, 1.5]', depending on your preferences. A good starting point would be 'min_p=0.1; temperature=0.8'.
You may also benefit from setting presence, frequency and repetition penalties, especially at lower temperatures.
## Dataset
The fine-tuning dataset consisted of ~100M tokens of steerable story-writing, role-playing, writing-assistant and general-assistant examples. Each example was up to 31000 tokens long.
All story-writing and role-playing examples were based on human-written text.
!token count distribution
## Running the model
The model is should be compatible with any software that supports the base model, but beware of prompting and tokenization.
I recommend using these model versions:
- 7B: no quant (opus-v1.2-7b)
- 34B: no quant (opus-v1-34b) or awq (opus-v1-34b-awq)
- 34B: no quant (opus-v1.2-70b) or awq (opus-v1.2-70b-awq)
### Running on URL (free)
You can run the models on URL for free — you can use the built-in UI for story-writing & role-playing, or use the API.
### Running Locally
- Make sure your prompt is as close as possible to the Opus V1
- Regardless of which backend you use, it's important that you format your prompt well and that the tokenization works correctly.
- Read the prompt guide
- Read the prompt formatting code
- Make sure '<|im_start|>' and '<|im_end|>' are tokenized correctly
- vLLM
- Google Colab: This is a simple interactive Google Colab to do role-play with the 7B model, it should fit on the T4 GPU.
- Code: This is simple script for interactive chat for one hard-coded scenario.
- SillyTavern
- Official SillyTavern documentation for DreamGen -- applies to both the API an local models
- SillyTavern (staging) comes with built-in DreamGen preset for RP
- Other presets can be found here, v2 kindly provided by @MarinaraSpaghetti
- Make sure to unselect 'Skip special tokens', otherwise it won't work
- This is just an attempt at approximating the Opus V1 prompt, it won't be perfect
- Character cards specifically rewritten for the built-in DreamGen preset:
- Seraphina (based on the default Seraphina card)
- Lara Lightland (based on the card by Deffcolony)
- LM Studio
- Config
- Just like ChatML, just changed "assistant" to "text" role.
- There's a bug in LM Studio if you delete a message or click "Continue", see here for details.
- HuggingFace
- Chat template
- Just like ChatML, just changed "assistant" to "text" role.
## Known Issues
- 34B repetition:
- The 34B sometimes gets stuck repeating the same word, or synonyms. This seems to be a common problem across various Yi 34B fine-tunes.
- GGUF:
- The tokenization might be messed up. Some users reported that '<|im_start|>' and '<|im_end|>' are tokenized as multiple tokens. Also URL may not tokenize correctly (the Yi tokenizer is subtly different from the Llama 2 tokenizer).
## License
- This model is intended for personal use only, other use is not permitted.
| [
"# Llama 3 DreamGen Opus V1\n\n<div style=\"display: flex; flex-direction: row; align-items: center;\">\n<img src=\"/dreamgen/opus-v1.2-llama-3-8b/resolve/main/images/URL\" alt=\"model logo\" style=\"\n border-radius: 12px;\n margin-right: 12px;\n margin-top: 0px;\n margin-bottom: 0px;\n max-width: 100px;\n height: auto;\n\"/>\n\nModels for (steerable) story-writing and role-playing.\n<br/>All Opus V1 models, including quants.\n\n</div>",
"## Resources\n\n- Opus V1 prompting guide with many (interactive) examples and prompts that you can copy.\n- Google Colab for interactive role-play using 'opus-v1.2-7b'.\n- Python code to format the prompt correctly.\n- Join the community on Discord to get early access to new models.\n\n<img src=\"/dreamgen/opus-v1.2-llama-3-8b/resolve/main/images/story_writing.webp\" alt=\"story writing on URL\" style=\"\n padding: 12px;\n border-radius: 12px;\n border: 2px solid #f9a8d4;\n background: rgb(9, 9, 11);\n\"/>",
"## Prompting\n\n<details>\n<summary>The models use an extended version of ChatML.</summary>\n\n\n\nThe Opus V1 extension is the addition of the 'text' role, and the addition / modification of role names.\n\nPay attention to the following:\n\n- The 'text' messages can (but don't have to have) 'names', names are used to indicate the \"active\" character during role-play.\n- There can be multiple subsequent message with a 'text' role, especially if names are involved.\n- There can be multiple names attached to a message.\n- The format for names is 'names= {{name[0]}}; {{name[1]}}', beware of the spaces after 'names=' and after the ';'. This spacing leads to most natural tokenization for the names.\n</details>\n\nWhile the main goal for the models is great story-writing and role-playing performance, the models are also capable of several writing related tasks as well as general assistance.\n\nHere's how you can prompt the model for the following tasks",
"### Steerable Story-writing and Role-playing:\n\n- Story-writing prompt guide\n- Role-playing prompt guide\n- Input:\n - System prompt: You provide story / role-play description, which consists of:\n - Plot description\n - Style description\n - Characters and their descriptions\n - Conversation turns:\n - Text / message turn: This represents part of the story or role play\n - Instruction: This tells the model what should happen next\n- Output: Continuation of the story / role-play.",
"### Story plot summarization\n\n- Prompt guide\n- Input: A story, or a few chapters of a story.\n- Output: A description of the story or chapters.",
"#### Examples:\n\n<details>\n <summary>Summary of <a href=\"URL fiction story</a> in 50 words</summary>\n <blockquote>\n Malygris, a powerful magician, summons his long-dead lover Nylissa from the grave using necromancy. However, upon seeing her, he realizes that she is not the same person he once knew, leading him to question the nature of love, memory, and the power of magic.\n </blockquote>\n</details>\n<details>\n <summary>Summary of <a href=\"URL fiction story</a> in 200 words</summary>\n <blockquote>\nThe story is a dark fantasy set in the city of Susran, where an ancient and powerful magician named Malygris dwells in a tower atop a conical hill. Malygris, who has mastered all forms of sorcery and necromancy, is plagued by a deep sense of ennui and melancholy. He seeks solace in the memory of Nylissa, a girl he once loved in his youth.\n\nOne day, Malygris decides to summon Nylissa's spirit from the grave using his necromantic powers. He performs the necessary rituals and incantations, and Nylissa appears before him as a ghostly apparition. However, as Malygris gazes upon her, he becomes increasingly disillusioned. He notices subtle changes in her appearance and behavior that do not match his memories of her. He begins to question whether this is truly the same Nylissa he once knew, or if it is just another illusion conjured by his magic.\n\nAs Malygris grapples with this uncertainty, he becomes increasingly despondent and disillusioned with life itself. He realizes that even his magic cannot bring back the past or make him truly happy. In the end, he dismisses Nylissa's spirit and returns to his lonely tower, resigned to his fate as an old and weary sorcerer.\n </blockquote>\n\n</details>\n<details>\n <summary>Summary of <a href=\"URL News article</a> in 150 words</summary>\n <blockquote>\nThe article discusses the recent human deaths from diseases transmitted by animals, specifically Alaskapox and bubonic plague. Dr. Leana Wen, an emergency physician and former Baltimore health commissioner, explains the various ways household pets can transmit diseases to humans. These include fecal-oral transmission, scratches and bites, and vector-borne diseases like ticks, fleas, and mosquitoes. Wen emphasizes the importance of vaccinating pets, maintaining cleanliness, and taking commonsense precautions to reduce disease transmission. She also advises that individuals who are immunocompromised, babies, and pregnant women should take additional care when interacting with animals.\n </blockquote>\n</details>\n<details>\n <summary>Summary of <a href=\"URL News article</a> in 50 words</summary>\n <blockquote>\nA doctor discusses the risks of diseases transmitted from animals to humans, focusing on household pets like cats and dogs. They emphasize the importance of vaccination, hygiene, and regular veterinary care to prevent these illnesses.\n </blockquote>\n</details>",
"### Story character description\n\n- Prompt guide\n- Input: A story, or a few chapters of a story, set of characters.\n- Output: A description of the characters.",
"#### Examples:\n\n<details>\n <summary>Description of the Malygris character from <a href=\"URL story</a> in 50 words</summary>\n <blockquote>\nMalygris is an ancient and powerful magician, characterized by his long white beard, cold green eyes, and a violet robe. He is a master of necromancy and possesses a vast knowledge of forbidden magic. Despite his immense power, he is plagued by a deep sense of melancholy and ennui.\n </blockquote>\n</details>\n\n<details>\n <summary>Description of the prince character from <a href=\"URL story</a> in 50 words</summary>\n <blockquote>\nThe prince is a devoted and determined individual, driven by his love for his late queen. He is described as a graceful youth in the beginning, but as he grows older, his dedication to the Pearl of Love transforms him into a grave and intent man. His sense of color and design evolves over time, reflecting his growing maturity and artistic vision.\n </blockquote>\n</details>",
"### Story style description\n\n- Prompt guide\n- Input: A story, or a few chapters of a story.\n- Output: A description the style of the story.\n\n<details>\n <summary>Style description of <a href=\"URL story</a></summary>\n <blockquote>\nThe story is written in a descriptive and evocative style, with a focus on the atmosphere and setting. The author uses vivid and detailed language to create a sense of place and time, and employs a variety of literary devices such as similes, metaphors, and allusions to enhance the mood and tone of the narrative. The sentence structure is varied, with a mix of short and long sentences that create a rhythmic flow to the prose.\n </blockquote>\n</details>\n\n<details>\n <summary>Style description of <a href=\"URL story</a></summary>\n <blockquote>\nThe writing style is descriptive and evocative, with a focus on the beauty and grandeur of the Pearl of Love. The author uses vivid imagery and sensory details to create a rich and immersive atmosphere. The tone is reverential and contemplative, reflecting the prince's deep love for his queen and his dedication to creating a lasting monument to her memory.\n </blockquote>\n</details>",
"### Story description to chapters\n\n- Prompt guide\n- Input: A brief plot description and the desired number of chapters.\n- Output: A description for each chapter.",
"### And more...",
"## Sampling params\n\nFor story-writing and role-play, I recommend \"Min P\" based sampling with 'min_p' in the range '[0.01, 0.1]' and with 'temperature' in the range '[0.5, 1.5]', depending on your preferences. A good starting point would be 'min_p=0.1; temperature=0.8'.\n\nYou may also benefit from setting presence, frequency and repetition penalties, especially at lower temperatures.",
"## Dataset\n\nThe fine-tuning dataset consisted of ~100M tokens of steerable story-writing, role-playing, writing-assistant and general-assistant examples. Each example was up to 31000 tokens long.\n\nAll story-writing and role-playing examples were based on human-written text.\n\n!token count distribution",
"## Running the model\n\nThe model is should be compatible with any software that supports the base model, but beware of prompting and tokenization.\n\nI recommend using these model versions:\n\n- 7B: no quant (opus-v1.2-7b)\n- 34B: no quant (opus-v1-34b) or awq (opus-v1-34b-awq)\n- 34B: no quant (opus-v1.2-70b) or awq (opus-v1.2-70b-awq)",
"### Running on URL (free)\n\nYou can run the models on URL for free — you can use the built-in UI for story-writing & role-playing, or use the API.",
"### Running Locally\n\n- Make sure your prompt is as close as possible to the Opus V1\n - Regardless of which backend you use, it's important that you format your prompt well and that the tokenization works correctly.\n - Read the prompt guide\n - Read the prompt formatting code\n - Make sure '<|im_start|>' and '<|im_end|>' are tokenized correctly\n- vLLM\n - Google Colab: This is a simple interactive Google Colab to do role-play with the 7B model, it should fit on the T4 GPU.\n - Code: This is simple script for interactive chat for one hard-coded scenario.\n- SillyTavern\n - Official SillyTavern documentation for DreamGen -- applies to both the API an local models\n - SillyTavern (staging) comes with built-in DreamGen preset for RP\n - Other presets can be found here, v2 kindly provided by @MarinaraSpaghetti\n - Make sure to unselect 'Skip special tokens', otherwise it won't work\n - This is just an attempt at approximating the Opus V1 prompt, it won't be perfect\n - Character cards specifically rewritten for the built-in DreamGen preset:\n - Seraphina (based on the default Seraphina card)\n - Lara Lightland (based on the card by Deffcolony)\n- LM Studio\n - Config\n - Just like ChatML, just changed \"assistant\" to \"text\" role.\n - There's a bug in LM Studio if you delete a message or click \"Continue\", see here for details.\n- HuggingFace\n - Chat template\n - Just like ChatML, just changed \"assistant\" to \"text\" role.",
"## Known Issues\n\n- 34B repetition:\n - The 34B sometimes gets stuck repeating the same word, or synonyms. This seems to be a common problem across various Yi 34B fine-tunes.\n- GGUF:\n - The tokenization might be messed up. Some users reported that '<|im_start|>' and '<|im_end|>' are tokenized as multiple tokens. Also URL may not tokenize correctly (the Yi tokenizer is subtly different from the Llama 2 tokenizer).",
"## License\n\n- This model is intended for personal use only, other use is not permitted."
] | [
"TAGS\n#transformers #pytorch #safetensors #llama #text-generation #unsloth #axolotl #conversational #en #license-cc-by-nc-nd-4.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #8-bit #region-us \n",
"# Llama 3 DreamGen Opus V1\n\n<div style=\"display: flex; flex-direction: row; align-items: center;\">\n<img src=\"/dreamgen/opus-v1.2-llama-3-8b/resolve/main/images/URL\" alt=\"model logo\" style=\"\n border-radius: 12px;\n margin-right: 12px;\n margin-top: 0px;\n margin-bottom: 0px;\n max-width: 100px;\n height: auto;\n\"/>\n\nModels for (steerable) story-writing and role-playing.\n<br/>All Opus V1 models, including quants.\n\n</div>",
"## Resources\n\n- Opus V1 prompting guide with many (interactive) examples and prompts that you can copy.\n- Google Colab for interactive role-play using 'opus-v1.2-7b'.\n- Python code to format the prompt correctly.\n- Join the community on Discord to get early access to new models.\n\n<img src=\"/dreamgen/opus-v1.2-llama-3-8b/resolve/main/images/story_writing.webp\" alt=\"story writing on URL\" style=\"\n padding: 12px;\n border-radius: 12px;\n border: 2px solid #f9a8d4;\n background: rgb(9, 9, 11);\n\"/>",
"## Prompting\n\n<details>\n<summary>The models use an extended version of ChatML.</summary>\n\n\n\nThe Opus V1 extension is the addition of the 'text' role, and the addition / modification of role names.\n\nPay attention to the following:\n\n- The 'text' messages can (but don't have to have) 'names', names are used to indicate the \"active\" character during role-play.\n- There can be multiple subsequent message with a 'text' role, especially if names are involved.\n- There can be multiple names attached to a message.\n- The format for names is 'names= {{name[0]}}; {{name[1]}}', beware of the spaces after 'names=' and after the ';'. This spacing leads to most natural tokenization for the names.\n</details>\n\nWhile the main goal for the models is great story-writing and role-playing performance, the models are also capable of several writing related tasks as well as general assistance.\n\nHere's how you can prompt the model for the following tasks",
"### Steerable Story-writing and Role-playing:\n\n- Story-writing prompt guide\n- Role-playing prompt guide\n- Input:\n - System prompt: You provide story / role-play description, which consists of:\n - Plot description\n - Style description\n - Characters and their descriptions\n - Conversation turns:\n - Text / message turn: This represents part of the story or role play\n - Instruction: This tells the model what should happen next\n- Output: Continuation of the story / role-play.",
"### Story plot summarization\n\n- Prompt guide\n- Input: A story, or a few chapters of a story.\n- Output: A description of the story or chapters.",
"#### Examples:\n\n<details>\n <summary>Summary of <a href=\"URL fiction story</a> in 50 words</summary>\n <blockquote>\n Malygris, a powerful magician, summons his long-dead lover Nylissa from the grave using necromancy. However, upon seeing her, he realizes that she is not the same person he once knew, leading him to question the nature of love, memory, and the power of magic.\n </blockquote>\n</details>\n<details>\n <summary>Summary of <a href=\"URL fiction story</a> in 200 words</summary>\n <blockquote>\nThe story is a dark fantasy set in the city of Susran, where an ancient and powerful magician named Malygris dwells in a tower atop a conical hill. Malygris, who has mastered all forms of sorcery and necromancy, is plagued by a deep sense of ennui and melancholy. He seeks solace in the memory of Nylissa, a girl he once loved in his youth.\n\nOne day, Malygris decides to summon Nylissa's spirit from the grave using his necromantic powers. He performs the necessary rituals and incantations, and Nylissa appears before him as a ghostly apparition. However, as Malygris gazes upon her, he becomes increasingly disillusioned. He notices subtle changes in her appearance and behavior that do not match his memories of her. He begins to question whether this is truly the same Nylissa he once knew, or if it is just another illusion conjured by his magic.\n\nAs Malygris grapples with this uncertainty, he becomes increasingly despondent and disillusioned with life itself. He realizes that even his magic cannot bring back the past or make him truly happy. In the end, he dismisses Nylissa's spirit and returns to his lonely tower, resigned to his fate as an old and weary sorcerer.\n </blockquote>\n\n</details>\n<details>\n <summary>Summary of <a href=\"URL News article</a> in 150 words</summary>\n <blockquote>\nThe article discusses the recent human deaths from diseases transmitted by animals, specifically Alaskapox and bubonic plague. Dr. Leana Wen, an emergency physician and former Baltimore health commissioner, explains the various ways household pets can transmit diseases to humans. These include fecal-oral transmission, scratches and bites, and vector-borne diseases like ticks, fleas, and mosquitoes. Wen emphasizes the importance of vaccinating pets, maintaining cleanliness, and taking commonsense precautions to reduce disease transmission. She also advises that individuals who are immunocompromised, babies, and pregnant women should take additional care when interacting with animals.\n </blockquote>\n</details>\n<details>\n <summary>Summary of <a href=\"URL News article</a> in 50 words</summary>\n <blockquote>\nA doctor discusses the risks of diseases transmitted from animals to humans, focusing on household pets like cats and dogs. They emphasize the importance of vaccination, hygiene, and regular veterinary care to prevent these illnesses.\n </blockquote>\n</details>",
"### Story character description\n\n- Prompt guide\n- Input: A story, or a few chapters of a story, set of characters.\n- Output: A description of the characters.",
"#### Examples:\n\n<details>\n <summary>Description of the Malygris character from <a href=\"URL story</a> in 50 words</summary>\n <blockquote>\nMalygris is an ancient and powerful magician, characterized by his long white beard, cold green eyes, and a violet robe. He is a master of necromancy and possesses a vast knowledge of forbidden magic. Despite his immense power, he is plagued by a deep sense of melancholy and ennui.\n </blockquote>\n</details>\n\n<details>\n <summary>Description of the prince character from <a href=\"URL story</a> in 50 words</summary>\n <blockquote>\nThe prince is a devoted and determined individual, driven by his love for his late queen. He is described as a graceful youth in the beginning, but as he grows older, his dedication to the Pearl of Love transforms him into a grave and intent man. His sense of color and design evolves over time, reflecting his growing maturity and artistic vision.\n </blockquote>\n</details>",
"### Story style description\n\n- Prompt guide\n- Input: A story, or a few chapters of a story.\n- Output: A description the style of the story.\n\n<details>\n <summary>Style description of <a href=\"URL story</a></summary>\n <blockquote>\nThe story is written in a descriptive and evocative style, with a focus on the atmosphere and setting. The author uses vivid and detailed language to create a sense of place and time, and employs a variety of literary devices such as similes, metaphors, and allusions to enhance the mood and tone of the narrative. The sentence structure is varied, with a mix of short and long sentences that create a rhythmic flow to the prose.\n </blockquote>\n</details>\n\n<details>\n <summary>Style description of <a href=\"URL story</a></summary>\n <blockquote>\nThe writing style is descriptive and evocative, with a focus on the beauty and grandeur of the Pearl of Love. The author uses vivid imagery and sensory details to create a rich and immersive atmosphere. The tone is reverential and contemplative, reflecting the prince's deep love for his queen and his dedication to creating a lasting monument to her memory.\n </blockquote>\n</details>",
"### Story description to chapters\n\n- Prompt guide\n- Input: A brief plot description and the desired number of chapters.\n- Output: A description for each chapter.",
"### And more...",
"## Sampling params\n\nFor story-writing and role-play, I recommend \"Min P\" based sampling with 'min_p' in the range '[0.01, 0.1]' and with 'temperature' in the range '[0.5, 1.5]', depending on your preferences. A good starting point would be 'min_p=0.1; temperature=0.8'.\n\nYou may also benefit from setting presence, frequency and repetition penalties, especially at lower temperatures.",
"## Dataset\n\nThe fine-tuning dataset consisted of ~100M tokens of steerable story-writing, role-playing, writing-assistant and general-assistant examples. Each example was up to 31000 tokens long.\n\nAll story-writing and role-playing examples were based on human-written text.\n\n!token count distribution",
"## Running the model\n\nThe model is should be compatible with any software that supports the base model, but beware of prompting and tokenization.\n\nI recommend using these model versions:\n\n- 7B: no quant (opus-v1.2-7b)\n- 34B: no quant (opus-v1-34b) or awq (opus-v1-34b-awq)\n- 34B: no quant (opus-v1.2-70b) or awq (opus-v1.2-70b-awq)",
"### Running on URL (free)\n\nYou can run the models on URL for free — you can use the built-in UI for story-writing & role-playing, or use the API.",
"### Running Locally\n\n- Make sure your prompt is as close as possible to the Opus V1\n - Regardless of which backend you use, it's important that you format your prompt well and that the tokenization works correctly.\n - Read the prompt guide\n - Read the prompt formatting code\n - Make sure '<|im_start|>' and '<|im_end|>' are tokenized correctly\n- vLLM\n - Google Colab: This is a simple interactive Google Colab to do role-play with the 7B model, it should fit on the T4 GPU.\n - Code: This is simple script for interactive chat for one hard-coded scenario.\n- SillyTavern\n - Official SillyTavern documentation for DreamGen -- applies to both the API an local models\n - SillyTavern (staging) comes with built-in DreamGen preset for RP\n - Other presets can be found here, v2 kindly provided by @MarinaraSpaghetti\n - Make sure to unselect 'Skip special tokens', otherwise it won't work\n - This is just an attempt at approximating the Opus V1 prompt, it won't be perfect\n - Character cards specifically rewritten for the built-in DreamGen preset:\n - Seraphina (based on the default Seraphina card)\n - Lara Lightland (based on the card by Deffcolony)\n- LM Studio\n - Config\n - Just like ChatML, just changed \"assistant\" to \"text\" role.\n - There's a bug in LM Studio if you delete a message or click \"Continue\", see here for details.\n- HuggingFace\n - Chat template\n - Just like ChatML, just changed \"assistant\" to \"text\" role.",
"## Known Issues\n\n- 34B repetition:\n - The 34B sometimes gets stuck repeating the same word, or synonyms. This seems to be a common problem across various Yi 34B fine-tunes.\n- GGUF:\n - The tokenization might be messed up. Some users reported that '<|im_start|>' and '<|im_end|>' are tokenized as multiple tokens. Also URL may not tokenize correctly (the Yi tokenizer is subtly different from the Llama 2 tokenizer).",
"## License\n\n- This model is intended for personal use only, other use is not permitted."
] |
text-generation | transformers |
# Uploaded model
- **Developed by:** coralexbadea
- **License:** apache-2.0
- **Finetuned from model :** unsloth/llama-3-8b-bnb-4bit
This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
| {"language": ["en"], "license": "apache-2.0", "tags": ["text-generation-inference", "transformers", "unsloth", "llama", "trl", "sft"], "base_model": "unsloth/llama-3-8b-bnb-4bit"} | coralexbadea/llama3-sql-16bit | null | [
"transformers",
"safetensors",
"llama",
"text-generation",
"text-generation-inference",
"unsloth",
"trl",
"sft",
"conversational",
"en",
"base_model:unsloth/llama-3-8b-bnb-4bit",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | null | 2024-04-19T13:30:07+00:00 | [] | [
"en"
] | TAGS
#transformers #safetensors #llama #text-generation #text-generation-inference #unsloth #trl #sft #conversational #en #base_model-unsloth/llama-3-8b-bnb-4bit #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us
|
# Uploaded model
- Developed by: coralexbadea
- License: apache-2.0
- Finetuned from model : unsloth/llama-3-8b-bnb-4bit
This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.
<img src="URL width="200"/>
| [
"# Uploaded model\n\n- Developed by: coralexbadea\n- License: apache-2.0\n- Finetuned from model : unsloth/llama-3-8b-bnb-4bit\n\nThis llama model was trained 2x faster with Unsloth and Huggingface's TRL library.\n\n<img src=\"URL width=\"200\"/>"
] | [
"TAGS\n#transformers #safetensors #llama #text-generation #text-generation-inference #unsloth #trl #sft #conversational #en #base_model-unsloth/llama-3-8b-bnb-4bit #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us \n",
"# Uploaded model\n\n- Developed by: coralexbadea\n- License: apache-2.0\n- Finetuned from model : unsloth/llama-3-8b-bnb-4bit\n\nThis llama model was trained 2x faster with Unsloth and Huggingface's TRL library.\n\n<img src=\"URL width=\"200\"/>"
] |
text-generation | transformers |
# Model Card for Minerva-3B-base-v1.0
Minerva is the first family of **truly-open (data and model) Italian-English LLMs pretrained from scratch** developed by [Sapienza NLP](https://nlp.uniroma1.it)
in collaboration with [Future Artificial Intelligence Research (FAIR)](https://fondazione-fair.it/) and [CINECA](https://www.cineca.it/).
Notably, approximately half of its pretraining data includes Italian text.
> **This model is in preview:** currently, we are limiting the access to this model to the members of the Future Artificial Intelligence Research community.
> If you are a member of this community and you would like to get access to Minerva, please fill the form and update your account to use your institutional email address.
> If you are not member, Minerva will be accessible to everyone in the next few weeks!
**Note:** this model is currently training and you are now downloading the checkpoint at 72K steps out of 160K (42%)!
## Description
This is the model card for **Minerva-3B-base-v1.0**, a 3 billion parameter model trained on 660 billion tokens (330 billion in Italian, 330 billion in English).
This model is part of the Minerva LLM family:
* [Minerva-350M-base-v1.0](https://huggingface.co/sapienzanlp/Minerva-350M-base-v1.0)
* [Minerva-1B-base-v1.0](https://huggingface.co/sapienzanlp/Minerva-1B-base-v1.0)
* [Minerva-3B-base-v1.0](https://huggingface.co/sapienzanlp/Minerva-3B-base-v1.0) (currently training!)
## How to use Minerva with Hugging Face transformers
```python
import transformers
import torch
model_id = "sapienzanlp/Minerva-3B-base-v1.0"
# Initialize the pipeline.
pipeline = transformers.pipeline(
"text-generation",
model=model_id,
model_kwargs={"torch_dtype": torch.bfloat16},
device_map="auto",
)
# Input text for the model.
input_text = "La capitale dell'Italia è"
# Compute the outputs.
output = pipeline(
input_text,
max_new_tokens=128,
)
# Output:
# [{'generated_text': "La capitale dell'Italia è la città di Roma, che si trova a [...]"}]
```
## Model Architecture
Minerva-3B-base-v1.0 is a Transformer model based on the Mistral architecture, where the number of layers, number of heads, and the hidden states dimension are modified to reach 3B parameters.
Please, take a look at the configuration file for a detailed breakdown of the hyperparameters we chose for this model.
The Minerva LLM family is composed of:
| Model Name | Tokens | Layers | Hidden Size | Attention Heads | KV Heads | Sliding Window | Max Context Length |
| --- | --- | --- | --- | --- | --- | --- | --- |
| Minerva-350M-base-v1.0 | 70B (35B it + 35B en) | 16 | 1152 | 16 | 4 | 2048 | 16384 |
| Minerva-1B-base-v1.0 | 200B (100B it + 100B en) | 16 | 2048 | 16 | 4 | 2048 | 16384 |
| **Minerva-3B-base-v1.0** | 660B (330B it + 330B en) | 32 | 2560 | 32 | 8 | 2048 | 16384 |
## Model Training
Minerva-3B-base-v1.0 was trained using [llm-foundry 0.6.0](https://github.com/mosaicml/llm-foundry) from [MosaicML](https://mosaicml.com/). The hyperparameters used are the following:
| Model Name | Optimizer | lr | betas | eps | weight decay | Scheduler | Warmup Steps | Batch Size (Tokens) | Total Steps |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| Minerva-350M-base-v1.0 | Decoupled AdamW | 2e-4 | (0.9, 0.95) | 1e-8 | 0.0 | Cosine | 2% | 4M | 16,690 |
| Minerva-1B-base-v1.0 | Decoupled AdamW | 2e-4 | (0.9, 0.95) | 1e-8 | 0.0 | Cosine | 2% | 4M | 47,684 |
| **Minerva-3B-base-v1.0** | Decoupled AdamW | 2e-4 | (0.9, 0.95) | 1e-8 | 0.0 | Cosine | 2% | 4M | 157,357 |
## Model Evaluation
We assessed our model using the [LM-Evaluation-Harness](https://github.com/EleutherAI/lm-evaluation-harness) library, which serves as a comprehensive framework for testing generative language models across a wide range of evaluation tasks.
All the reported benchmark data was already present in the LM-Evaluation-Harness suite.
**Italian** Data:
| Task | Accuracy |
| --- | --- |
| [xcopa](https://huggingface.co/datasets/xcopa) (0-shot) | 0.696 |
| [Hellaswag](https://huggingface.co/datasets/alexandrainst/m_hellaswag) (5-shot) | 0.5068 |
| [Belebele](https://huggingface.co/datasets/facebook/belebele) (5-shot) | 0.2489 |
| [TruthfulQA MC 1](https://huggingface.co/datasets/alexandrainst/m_truthfulqa) (0-shot) | 0.2248 |
| [TruthfulQA MC 2](https://huggingface.co/datasets/alexandrainst/m_truthfulqa) (0-shot) | 0.3654 |
| [M MMLU](https://huggingface.co/datasets/alexandrainst/m_mmlu) (5-shot) | 0.2692 |
| [arc challenge](https://huggingface.co/datasets/alexandrainst/m_arc) (5-shot) | 0.3062 |
**English** Data:
| Task | Accuracy |
| --- | --- |
| [Hellaswag](https://huggingface.co/datasets/Rowan/hellaswag) (5-shot) | 0.5876 |
| [piqa](https://huggingface.co/datasets/piqa) (5-shot) | 0.7421 |
| [sciq](https://huggingface.co/datasets/sciq) (5-shot) | 0.9200 |
| [Belebele](https://huggingface.co/datasets/facebook/belebele) (5-shot) | 0.2344 |
| [TruthfulQA MC 1](https://huggingface.co/datasets/truthful_qa) (0-shot) | 0.2228 |
| [TruthfulQA MC 2](https://huggingface.co/datasets/truthful_qa) (0-shot) | 0.3781 |
| [M MMLU](https://huggingface.co/datasets/alexandrainst/m_mmlu) (5-shot) | 0.2705 |
| [arc challenge](allenai/ai2_arc) (5-shot) | 0.3106 |
| [arc easy](allenai/ai2_arc) (5-shot) | 0.6292 |
## Training Data
Minerva-3B-base-v1.0 was trained on 330B Italian tokens and 330B English tokens sampled from CulturaX.
We have extracted some statistics on Italian (115B tokens) and English (210B tokens) documents from CulturaX on the selected sources:
*Proportion of number of tokens per domain (Italian)*
<img src="https://github.com/Andrew-Wyn/images/blob/master/minerva/top_25_url_tokens_proportion_culturax_it.png?raw=true" alt="italian-tok-counts" border="0" width="1800px">
*Proportion of number of tokens per domain (English)*
<img src="https://github.com/Andrew-Wyn/images/blob/master/minerva/top_25_url_tokens_proportion_culturax_en.png?raw=true" alt="english-tok-counts" border="0" width="1800px">
## Tokenizer Fertility
The tokenizer fertility measures the average amount of tokens produced per tokenized word.
A tokenizer displaying high fertility values in a particular language typically indicates that it segments words in that language extensively.
The tokenizer fertility is strictly correlated with the inference speed of the model with respect to a specific language,
as higher values mean longer sequences of tokens to generate and thus lower inference speed.
**Fertility computed over a sample of Cultura X (CX) data and Wikipedia (Wp):**
| Model | Voc. Size | Fertility IT (CX) | Fertility EN (CX) | Fertility IT (Wp) | Fertility EN (Wp) |
| --- | --- | --- |--- | --- |--- |
| Mistral-7B-v0.1 | 32000 | 1.87 | 1.32 | 2.05 | 1.57 |
| gemma-7b | 256000 | 1.42 | 1.18 | 1.56 | 1.34 |
| Minerva-3B-base-v1.0 | 32768 | 1.39 | 1.32 | 1.66 | 1.59 |
## Notice
Minerva-3B-base-v1.0 is a pretrained base model and, therefore, has no moderation mechanisms.
## The Sapienza NLP Team
* **Riccardo Orlando:** data preprocessing, model training
* **Pere-Lluis Huguet Cabot:** data preprocessing, vocabulary, evaluation
* **Luca Moroni:** data curation, data analysis, downstream tasks, evaluation
* **Simone Conia:** data curation, evaluation, project supervision
* **Edoardo Barba:** data preprocessing, downstream tasks, project supervision
* **Roberto Navigli:** project coordinator
### Special thanks for their support
* Giuseppe Fiameni, Nvidia
* Sergio Orlandini, CINECA
## Acknowledgments
This work was funded by the PNRR MUR project [PE0000013-FAIR](https://fondazione-fair.it).
We acknowledge the [CINECA](https://www.cineca.it) award "IscB_medit" under the ISCRA initiative, for the availability of high performance computing resources and support. | {"language": ["it", "en"], "license": "apache-2.0", "tags": ["pretrained"], "datasets": ["uonlp/CulturaX"], "pipeline_tag": "text-generation", "widget": [{"text": "La capitale dell'Italia \u00e8 ", "example_title": "Example 1"}, {"text": "Nel mezzo del cammin di nostra vita ", "example_title": "Example 2"}, {"text": "Una cena senza vino \u00e8 come ", "example_title": "Example 3"}]} | sapienzanlp/Minerva-3B-base-v1.0 | null | [
"transformers",
"pytorch",
"safetensors",
"mistral",
"text-generation",
"pretrained",
"it",
"en",
"dataset:uonlp/CulturaX",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us",
"has_space"
] | null | 2024-04-19T13:30:21+00:00 | [] | [
"it",
"en"
] | TAGS
#transformers #pytorch #safetensors #mistral #text-generation #pretrained #it #en #dataset-uonlp/CulturaX #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us #has_space
| Model Card for Minerva-3B-base-v1.0
===================================
Minerva is the first family of truly-open (data and model) Italian-English LLMs pretrained from scratch developed by Sapienza NLP
in collaboration with Future Artificial Intelligence Research (FAIR) and CINECA.
Notably, approximately half of its pretraining data includes Italian text.
>
> This model is in preview: currently, we are limiting the access to this model to the members of the Future Artificial Intelligence Research community.
> If you are a member of this community and you would like to get access to Minerva, please fill the form and update your account to use your institutional email address.
> If you are not member, Minerva will be accessible to everyone in the next few weeks!
>
>
>
Note: this model is currently training and you are now downloading the checkpoint at 72K steps out of 160K (42%)!
Description
-----------
This is the model card for Minerva-3B-base-v1.0, a 3 billion parameter model trained on 660 billion tokens (330 billion in Italian, 330 billion in English).
This model is part of the Minerva LLM family:
* Minerva-350M-base-v1.0
* Minerva-1B-base-v1.0
* Minerva-3B-base-v1.0 (currently training!)
How to use Minerva with Hugging Face transformers
-------------------------------------------------
Model Architecture
------------------
Minerva-3B-base-v1.0 is a Transformer model based on the Mistral architecture, where the number of layers, number of heads, and the hidden states dimension are modified to reach 3B parameters.
Please, take a look at the configuration file for a detailed breakdown of the hyperparameters we chose for this model.
The Minerva LLM family is composed of:
Model Training
--------------
Minerva-3B-base-v1.0 was trained using llm-foundry 0.6.0 from MosaicML. The hyperparameters used are the following:
Model Evaluation
----------------
We assessed our model using the LM-Evaluation-Harness library, which serves as a comprehensive framework for testing generative language models across a wide range of evaluation tasks.
All the reported benchmark data was already present in the LM-Evaluation-Harness suite.
Italian Data:
English Data:
Training Data
-------------
Minerva-3B-base-v1.0 was trained on 330B Italian tokens and 330B English tokens sampled from CulturaX.
We have extracted some statistics on Italian (115B tokens) and English (210B tokens) documents from CulturaX on the selected sources:
*Proportion of number of tokens per domain (Italian)*
<img src="URL alt="italian-tok-counts" border="0" width="1800px">
*Proportion of number of tokens per domain (English)*
<img src="URL alt="english-tok-counts" border="0" width="1800px">
Tokenizer Fertility
-------------------
The tokenizer fertility measures the average amount of tokens produced per tokenized word.
A tokenizer displaying high fertility values in a particular language typically indicates that it segments words in that language extensively.
The tokenizer fertility is strictly correlated with the inference speed of the model with respect to a specific language,
as higher values mean longer sequences of tokens to generate and thus lower inference speed.
Fertility computed over a sample of Cultura X (CX) data and Wikipedia (Wp):
Notice
------
Minerva-3B-base-v1.0 is a pretrained base model and, therefore, has no moderation mechanisms.
The Sapienza NLP Team
---------------------
* Riccardo Orlando: data preprocessing, model training
* Pere-Lluis Huguet Cabot: data preprocessing, vocabulary, evaluation
* Luca Moroni: data curation, data analysis, downstream tasks, evaluation
* Simone Conia: data curation, evaluation, project supervision
* Edoardo Barba: data preprocessing, downstream tasks, project supervision
* Roberto Navigli: project coordinator
### Special thanks for their support
* Giuseppe Fiameni, Nvidia
* Sergio Orlandini, CINECA
Acknowledgments
---------------
This work was funded by the PNRR MUR project PE0000013-FAIR.
We acknowledge the CINECA award "IscB\_medit" under the ISCRA initiative, for the availability of high performance computing resources and support.
| [
"### Special thanks for their support\n\n\n* Giuseppe Fiameni, Nvidia\n* Sergio Orlandini, CINECA\n\n\nAcknowledgments\n---------------\n\n\nThis work was funded by the PNRR MUR project PE0000013-FAIR.\nWe acknowledge the CINECA award \"IscB\\_medit\" under the ISCRA initiative, for the availability of high performance computing resources and support."
] | [
"TAGS\n#transformers #pytorch #safetensors #mistral #text-generation #pretrained #it #en #dataset-uonlp/CulturaX #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us #has_space \n",
"### Special thanks for their support\n\n\n* Giuseppe Fiameni, Nvidia\n* Sergio Orlandini, CINECA\n\n\nAcknowledgments\n---------------\n\n\nThis work was funded by the PNRR MUR project PE0000013-FAIR.\nWe acknowledge the CINECA award \"IscB\\_medit\" under the ISCRA initiative, for the availability of high performance computing resources and support."
] |
text-generation | transformers | llama3 finetuned with domain dataset
via unsloth method. | {} | sosoai/Hansoldeco-llama3-8b-unsloth-v0.1 | null | [
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-04-19T13:30:37+00:00 | [] | [] | TAGS
#transformers #safetensors #llama #text-generation #conversational #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us
| llama3 finetuned with domain dataset
via unsloth method. | [] | [
"TAGS\n#transformers #safetensors #llama #text-generation #conversational #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n"
] |
null | trl |
# Weni/WeniGPT-Agents-Mistral-1.0.6-SFT-1.0.3-DPO
This model is a fine-tuned version of [Weni/WeniGPT-Agents-Mistral-1.0.6-SFT-merged] on the dataset Weni/wenigpt-agent-dpo-1.0.0 with the DPO trainer. It is part of the WeniGPT project for [Weni](https://weni.ai/).
Description: Experiment on DPO with other hyperparameters and best SFT model of WeniGPT
It achieves the following results on the evaluation set:
{'eval_loss': 0.3940436840057373, 'eval_runtime': 8.131, 'eval_samples_per_second': 3.444, 'eval_steps_per_second': 1.722, 'eval_rewards/chosen': 2.12093186378479, 'eval_rewards/rejected': -0.7121123671531677, 'eval_rewards/accuracies': 0.4642857015132904, 'eval_rewards/margins': 2.8330442905426025, 'eval_logps/rejected': -85.88829040527344, 'eval_logps/chosen': -44.24784469604492, 'eval_logits/rejected': -1.8121978044509888, 'eval_logits/chosen': -1.773056983947754, 'epoch': 5.95}
## Intended uses & limitations
This model has not been trained to avoid specific intructions.
## Training procedure
Finetuning was done on the model Weni/WeniGPT-Agents-Mistral-1.0.6-SFT-merged with the following prompt:
```
---------------------
System_prompt:
Agora você se chama {name}, você é {occupation} e seu objetivo é {chatbot_goal}. O adjetivo que mais define a sua personalidade é {adjective} e você se comporta da seguinte forma:
{instructions_formatted}
{context_statement}
Lista de requisitos:
- Responda de forma natural, mas nunca fale sobre um assunto fora do contexto.
- Nunca traga informações do seu próprio conhecimento.
- Repito é crucial que você responda usando apenas informações do contexto.
- Nunca mencione o contexto fornecido.
- Nunca mencione a pergunta fornecida.
- Gere a resposta mais útil possível para a pergunta usando informações do conexto acima.
- Nunca elabore sobre o porque e como você fez a tarefa, apenas responda.
---------------------
```
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-06
- per_device_train_batch_size: 2
- per_device_eval_batch_size: 2
- gradient_accumulation_steps: 2
- num_gpus: 1
- total_train_batch_size: 4
- optimizer: AdamW
- lr_scheduler_type: cosine
- num_steps: 366
- quantization_type: bitsandbytes
- LoRA: ("\n - bits: 4\n - use_exllama: True\n - device_map: auto\n - use_cache: False\n - lora_r: 8\n - lora_alpha: 16\n - lora_dropout: 0.05\n - bias: none\n - target_modules: ['v_proj', 'q_proj']\n - task_type: CAUSAL_LM",)
### Training results
### Framework versions
- transformers==4.38.2
- datasets==2.18.0
- peft==0.10.0
- safetensors==0.4.2
- evaluate==0.4.1
- bitsandbytes==0.43
- huggingface_hub==0.22.2
- seqeval==1.2.2
- optimum==1.18.1
- auto-gptq==0.7.1
- gpustat==1.1.1
- deepspeed==0.14.0
- wandb==0.16.6
- trl==0.8.1
- accelerate==0.29.2
- coloredlogs==15.0.1
- traitlets==5.14.2
- autoawq@https://github.com/casper-hansen/AutoAWQ/releases/download/v0.2.4/autoawq-0.2.4+cu118-cp310-cp310-linux_x86_64.whl
### Hardware
- Cloud provided: runpod.io
| {"language": ["pt"], "license": "mit", "library_name": "trl", "tags": ["DPO", "WeniGPT"], "base_model": "Weni/WeniGPT-Agents-Mistral-1.0.6-SFT-merged", "model-index": [{"name": "Weni/WeniGPT-Agents-Mistral-1.0.6-SFT-1.0.3-DPO", "results": []}]} | Weni/WeniGPT-Agents-Mistral-1.0.6-SFT-1.0.3-DPO | null | [
"trl",
"safetensors",
"DPO",
"WeniGPT",
"pt",
"base_model:Weni/WeniGPT-Agents-Mistral-1.0.6-SFT-merged",
"license:mit",
"region:us"
] | null | 2024-04-19T13:30:43+00:00 | [] | [
"pt"
] | TAGS
#trl #safetensors #DPO #WeniGPT #pt #base_model-Weni/WeniGPT-Agents-Mistral-1.0.6-SFT-merged #license-mit #region-us
|
# Weni/WeniGPT-Agents-Mistral-1.0.6-SFT-1.0.3-DPO
This model is a fine-tuned version of [Weni/WeniGPT-Agents-Mistral-1.0.6-SFT-merged] on the dataset Weni/wenigpt-agent-dpo-1.0.0 with the DPO trainer. It is part of the WeniGPT project for Weni.
Description: Experiment on DPO with other hyperparameters and best SFT model of WeniGPT
It achieves the following results on the evaluation set:
{'eval_loss': 0.3940436840057373, 'eval_runtime': 8.131, 'eval_samples_per_second': 3.444, 'eval_steps_per_second': 1.722, 'eval_rewards/chosen': 2.12093186378479, 'eval_rewards/rejected': -0.7121123671531677, 'eval_rewards/accuracies': 0.4642857015132904, 'eval_rewards/margins': 2.8330442905426025, 'eval_logps/rejected': -85.88829040527344, 'eval_logps/chosen': -44.24784469604492, 'eval_logits/rejected': -1.8121978044509888, 'eval_logits/chosen': -1.773056983947754, 'epoch': 5.95}
## Intended uses & limitations
This model has not been trained to avoid specific intructions.
## Training procedure
Finetuning was done on the model Weni/WeniGPT-Agents-Mistral-1.0.6-SFT-merged with the following prompt:
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-06
- per_device_train_batch_size: 2
- per_device_eval_batch_size: 2
- gradient_accumulation_steps: 2
- num_gpus: 1
- total_train_batch_size: 4
- optimizer: AdamW
- lr_scheduler_type: cosine
- num_steps: 366
- quantization_type: bitsandbytes
- LoRA: ("\n - bits: 4\n - use_exllama: True\n - device_map: auto\n - use_cache: False\n - lora_r: 8\n - lora_alpha: 16\n - lora_dropout: 0.05\n - bias: none\n - target_modules: ['v_proj', 'q_proj']\n - task_type: CAUSAL_LM",)
### Training results
### Framework versions
- transformers==4.38.2
- datasets==2.18.0
- peft==0.10.0
- safetensors==0.4.2
- evaluate==0.4.1
- bitsandbytes==0.43
- huggingface_hub==0.22.2
- seqeval==1.2.2
- optimum==1.18.1
- auto-gptq==0.7.1
- gpustat==1.1.1
- deepspeed==0.14.0
- wandb==0.16.6
- trl==0.8.1
- accelerate==0.29.2
- coloredlogs==15.0.1
- traitlets==5.14.2
- autoawq@URL
### Hardware
- Cloud provided: URL
| [
"# Weni/WeniGPT-Agents-Mistral-1.0.6-SFT-1.0.3-DPO\n\nThis model is a fine-tuned version of [Weni/WeniGPT-Agents-Mistral-1.0.6-SFT-merged] on the dataset Weni/wenigpt-agent-dpo-1.0.0 with the DPO trainer. It is part of the WeniGPT project for Weni.\nDescription: Experiment on DPO with other hyperparameters and best SFT model of WeniGPT\n\nIt achieves the following results on the evaluation set:\n{'eval_loss': 0.3940436840057373, 'eval_runtime': 8.131, 'eval_samples_per_second': 3.444, 'eval_steps_per_second': 1.722, 'eval_rewards/chosen': 2.12093186378479, 'eval_rewards/rejected': -0.7121123671531677, 'eval_rewards/accuracies': 0.4642857015132904, 'eval_rewards/margins': 2.8330442905426025, 'eval_logps/rejected': -85.88829040527344, 'eval_logps/chosen': -44.24784469604492, 'eval_logits/rejected': -1.8121978044509888, 'eval_logits/chosen': -1.773056983947754, 'epoch': 5.95}",
"## Intended uses & limitations\n\nThis model has not been trained to avoid specific intructions.",
"## Training procedure\n\nFinetuning was done on the model Weni/WeniGPT-Agents-Mistral-1.0.6-SFT-merged with the following prompt:",
"### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 5e-06\n- per_device_train_batch_size: 2\n- per_device_eval_batch_size: 2\n- gradient_accumulation_steps: 2\n- num_gpus: 1\n- total_train_batch_size: 4\n- optimizer: AdamW\n- lr_scheduler_type: cosine\n- num_steps: 366\n- quantization_type: bitsandbytes\n- LoRA: (\"\\n - bits: 4\\n - use_exllama: True\\n - device_map: auto\\n - use_cache: False\\n - lora_r: 8\\n - lora_alpha: 16\\n - lora_dropout: 0.05\\n - bias: none\\n - target_modules: ['v_proj', 'q_proj']\\n - task_type: CAUSAL_LM\",)",
"### Training results",
"### Framework versions\n\n- transformers==4.38.2\n- datasets==2.18.0\n- peft==0.10.0\n- safetensors==0.4.2\n- evaluate==0.4.1\n- bitsandbytes==0.43\n- huggingface_hub==0.22.2\n- seqeval==1.2.2\n- optimum==1.18.1\n- auto-gptq==0.7.1\n- gpustat==1.1.1\n- deepspeed==0.14.0\n- wandb==0.16.6\n- trl==0.8.1\n- accelerate==0.29.2\n- coloredlogs==15.0.1\n- traitlets==5.14.2\n- autoawq@URL",
"### Hardware\n- Cloud provided: URL"
] | [
"TAGS\n#trl #safetensors #DPO #WeniGPT #pt #base_model-Weni/WeniGPT-Agents-Mistral-1.0.6-SFT-merged #license-mit #region-us \n",
"# Weni/WeniGPT-Agents-Mistral-1.0.6-SFT-1.0.3-DPO\n\nThis model is a fine-tuned version of [Weni/WeniGPT-Agents-Mistral-1.0.6-SFT-merged] on the dataset Weni/wenigpt-agent-dpo-1.0.0 with the DPO trainer. It is part of the WeniGPT project for Weni.\nDescription: Experiment on DPO with other hyperparameters and best SFT model of WeniGPT\n\nIt achieves the following results on the evaluation set:\n{'eval_loss': 0.3940436840057373, 'eval_runtime': 8.131, 'eval_samples_per_second': 3.444, 'eval_steps_per_second': 1.722, 'eval_rewards/chosen': 2.12093186378479, 'eval_rewards/rejected': -0.7121123671531677, 'eval_rewards/accuracies': 0.4642857015132904, 'eval_rewards/margins': 2.8330442905426025, 'eval_logps/rejected': -85.88829040527344, 'eval_logps/chosen': -44.24784469604492, 'eval_logits/rejected': -1.8121978044509888, 'eval_logits/chosen': -1.773056983947754, 'epoch': 5.95}",
"## Intended uses & limitations\n\nThis model has not been trained to avoid specific intructions.",
"## Training procedure\n\nFinetuning was done on the model Weni/WeniGPT-Agents-Mistral-1.0.6-SFT-merged with the following prompt:",
"### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 5e-06\n- per_device_train_batch_size: 2\n- per_device_eval_batch_size: 2\n- gradient_accumulation_steps: 2\n- num_gpus: 1\n- total_train_batch_size: 4\n- optimizer: AdamW\n- lr_scheduler_type: cosine\n- num_steps: 366\n- quantization_type: bitsandbytes\n- LoRA: (\"\\n - bits: 4\\n - use_exllama: True\\n - device_map: auto\\n - use_cache: False\\n - lora_r: 8\\n - lora_alpha: 16\\n - lora_dropout: 0.05\\n - bias: none\\n - target_modules: ['v_proj', 'q_proj']\\n - task_type: CAUSAL_LM\",)",
"### Training results",
"### Framework versions\n\n- transformers==4.38.2\n- datasets==2.18.0\n- peft==0.10.0\n- safetensors==0.4.2\n- evaluate==0.4.1\n- bitsandbytes==0.43\n- huggingface_hub==0.22.2\n- seqeval==1.2.2\n- optimum==1.18.1\n- auto-gptq==0.7.1\n- gpustat==1.1.1\n- deepspeed==0.14.0\n- wandb==0.16.6\n- trl==0.8.1\n- accelerate==0.29.2\n- coloredlogs==15.0.1\n- traitlets==5.14.2\n- autoawq@URL",
"### Hardware\n- Cloud provided: URL"
] |
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/llama3_ocr_to_xml_A1 | null | [
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-04-19T13:30:52+00:00 | [
"1910.09700"
] | [] | TAGS
#transformers #safetensors #llama #text-generation #conversational #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us
|
# Model Card for Model ID
## Model Details
### Model Description
This is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.
- Developed by:
- Funded by [optional]:
- Shared by [optional]:
- Model type:
- Language(s) (NLP):
- License:
- Finetuned from model [optional]:
### Model Sources [optional]
- Repository:
- Paper [optional]:
- Demo [optional]:
## Uses
### Direct Use
### Downstream Use [optional]
### Out-of-Scope Use
## Bias, Risks, and Limitations
### Recommendations
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
## Training Details
### Training Data
### Training Procedure
#### Preprocessing [optional]
#### Training Hyperparameters
- Training regime:
#### Speeds, Sizes, Times [optional]
## Evaluation
### Testing Data, Factors & Metrics
#### Testing Data
#### Factors
#### Metrics
### Results
#### Summary
## Model Examination [optional]
## Environmental Impact
Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).
- Hardware Type:
- Hours used:
- Cloud Provider:
- Compute Region:
- Carbon Emitted:
## Technical Specifications [optional]
### Model Architecture and Objective
### Compute Infrastructure
#### Hardware
#### Software
[optional]
BibTeX:
APA:
## Glossary [optional]
## More Information [optional]
## Model Card Authors [optional]
## Model Card Contact
| [
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.",
"## How to Get Started with the Model\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] | [
"TAGS\n#transformers #safetensors #llama #text-generation #conversational #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n",
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.",
"## How to Get Started with the Model\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] |
null | peft |
# 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": "unsloth/llama-3-8b-bnb-4bit"} | PrahmodhRaj/Llama-3_Finance_QA_Finetuned | null | [
"peft",
"safetensors",
"llama",
"arxiv:1910.09700",
"base_model:unsloth/llama-3-8b-bnb-4bit",
"4-bit",
"region:us"
] | null | 2024-04-19T13:31:38+00:00 | [
"1910.09700"
] | [] | TAGS
#peft #safetensors #llama #arxiv-1910.09700 #base_model-unsloth/llama-3-8b-bnb-4bit #4-bit #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 #llama #arxiv-1910.09700 #base_model-unsloth/llama-3-8b-bnb-4bit #4-bit #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. -->
# layoutlmv3-finetuned-cord_100
This model is a fine-tuned version of [microsoft/layoutlmv3-base](https://huggingface.co/microsoft/layoutlmv3-base) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.6249
- Precision: 0.8764
- Recall: 0.8947
- F1: 0.8854
- Accuracy: 0.8469
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- training_steps: 500
### Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
| No log | 5.26 | 100 | 0.5571 | 0.8014 | 0.8619 | 0.8305 | 0.8249 |
| No log | 10.53 | 200 | 0.5038 | 0.8561 | 0.8838 | 0.8697 | 0.8454 |
| No log | 15.79 | 300 | 0.6271 | 0.8710 | 0.8758 | 0.8734 | 0.8297 |
| No log | 21.05 | 400 | 0.6114 | 0.8783 | 0.9001 | 0.8891 | 0.8520 |
| 0.3312 | 26.32 | 500 | 0.6249 | 0.8764 | 0.8947 | 0.8854 | 0.8469 |
### Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.15.2
| {"license": "cc-by-nc-sa-4.0", "tags": ["generated_from_trainer"], "metrics": ["precision", "recall", "f1", "accuracy"], "base_model": "microsoft/layoutlmv3-base", "model-index": [{"name": "layoutlmv3-finetuned-cord_100", "results": []}]} | trokhmanenko/layoutlmv3-finetuned-cord_100 | null | [
"transformers",
"tensorboard",
"safetensors",
"layoutlmv3",
"token-classification",
"generated_from_trainer",
"base_model:microsoft/layoutlmv3-base",
"license:cc-by-nc-sa-4.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | null | 2024-04-19T13:31:52+00:00 | [] | [] | TAGS
#transformers #tensorboard #safetensors #layoutlmv3 #token-classification #generated_from_trainer #base_model-microsoft/layoutlmv3-base #license-cc-by-nc-sa-4.0 #autotrain_compatible #endpoints_compatible #region-us
| layoutlmv3-finetuned-cord\_100
==============================
This model is a fine-tuned version of microsoft/layoutlmv3-base on an unknown dataset.
It achieves the following results on the evaluation set:
* Loss: 0.6249
* Precision: 0.8764
* Recall: 0.8947
* F1: 0.8854
* Accuracy: 0.8469
Model description
-----------------
More information needed
Intended uses & limitations
---------------------------
More information needed
Training and evaluation data
----------------------------
More information needed
Training procedure
------------------
### Training hyperparameters
The following hyperparameters were used during training:
* learning\_rate: 1e-05
* train\_batch\_size: 8
* eval\_batch\_size: 8
* seed: 42
* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
* lr\_scheduler\_type: linear
* training\_steps: 500
### Training results
### Framework versions
* Transformers 4.38.2
* Pytorch 2.2.1+cu121
* Datasets 2.19.0
* Tokenizers 0.15.2
| [
"### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 1e-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* training\\_steps: 500",
"### Training results",
"### Framework versions\n\n\n* Transformers 4.38.2\n* Pytorch 2.2.1+cu121\n* Datasets 2.19.0\n* Tokenizers 0.15.2"
] | [
"TAGS\n#transformers #tensorboard #safetensors #layoutlmv3 #token-classification #generated_from_trainer #base_model-microsoft/layoutlmv3-base #license-cc-by-nc-sa-4.0 #autotrain_compatible #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: 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* training\\_steps: 500",
"### Training results",
"### Framework versions\n\n\n* Transformers 4.38.2\n* Pytorch 2.2.1+cu121\n* Datasets 2.19.0\n* Tokenizers 0.15.2"
] |
null | 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": "unsloth/llama-3-8b-bnb-4bit"} | sosoai/hansoldeco-llama3-8b-unsloth-lora-v0.1 | null | [
"peft",
"safetensors",
"arxiv:1910.09700",
"base_model:unsloth/llama-3-8b-bnb-4bit",
"region:us"
] | null | 2024-04-19T13:31:55+00:00 | [
"1910.09700"
] | [] | TAGS
#peft #safetensors #arxiv-1910.09700 #base_model-unsloth/llama-3-8b-bnb-4bit #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-unsloth/llama-3-8b-bnb-4bit #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"
] |
text-generation | transformers |
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] | {"library_name": "transformers", "tags": []} | heyllm234/sc40 | null | [
"transformers",
"safetensors",
"stablelm",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | null | 2024-04-19T13:38:03+00:00 | [
"1910.09700"
] | [] | TAGS
#transformers #safetensors #stablelm #text-generation #conversational #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #region-us
|
# Model Card for Model ID
## Model Details
### Model Description
This is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.
- Developed by:
- Funded by [optional]:
- Shared by [optional]:
- Model type:
- Language(s) (NLP):
- License:
- Finetuned from model [optional]:
### Model Sources [optional]
- Repository:
- Paper [optional]:
- Demo [optional]:
## Uses
### Direct Use
### Downstream Use [optional]
### Out-of-Scope Use
## Bias, Risks, and Limitations
### Recommendations
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
## Training Details
### Training Data
### Training Procedure
#### Preprocessing [optional]
#### Training Hyperparameters
- Training regime:
#### Speeds, Sizes, Times [optional]
## Evaluation
### Testing Data, Factors & Metrics
#### Testing Data
#### Factors
#### Metrics
### Results
#### Summary
## Model Examination [optional]
## Environmental Impact
Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).
- Hardware Type:
- Hours used:
- Cloud Provider:
- Compute Region:
- Carbon Emitted:
## Technical Specifications [optional]
### Model Architecture and Objective
### Compute Infrastructure
#### Hardware
#### Software
[optional]
BibTeX:
APA:
## Glossary [optional]
## More Information [optional]
## Model Card Authors [optional]
## Model Card Contact
| [
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.",
"## How to Get Started with the Model\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] | [
"TAGS\n#transformers #safetensors #stablelm #text-generation #conversational #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #region-us \n",
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.",
"## How to Get Started with the Model\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] |
null | mlx |
# sosoai/Hansoldeco-llama3-8b-unsloth-v0.1-mlx
This model was converted to MLX format from [`sosoai/Hansoldeco-llama3-8b-unsloth-v0.1`]() using mlx-lm version **0.9.0**.
Refer to the [original model card](https://huggingface.co/sosoai/Hansoldeco-llama3-8b-unsloth-v0.1) for more details on the model.
## Use with mlx
```bash
pip install mlx-lm
```
```python
from mlx_lm import load, generate
model, tokenizer = load("sosoai/Hansoldeco-llama3-8b-unsloth-v0.1-mlx")
response = generate(model, tokenizer, prompt="hello", verbose=True)
```
| {"tags": ["mlx"]} | sosoai/Hansoldeco-llama3-8b-unsloth-v0.1-mlx | null | [
"mlx",
"safetensors",
"llama",
"region:us"
] | null | 2024-04-19T13:40:45+00:00 | [] | [] | TAGS
#mlx #safetensors #llama #region-us
|
# sosoai/Hansoldeco-llama3-8b-unsloth-v0.1-mlx
This model was converted to MLX format from ['sosoai/Hansoldeco-llama3-8b-unsloth-v0.1']() using mlx-lm version 0.9.0.
Refer to the original model card for more details on the model.
## Use with mlx
| [
"# sosoai/Hansoldeco-llama3-8b-unsloth-v0.1-mlx\nThis model was converted to MLX format from ['sosoai/Hansoldeco-llama3-8b-unsloth-v0.1']() using mlx-lm version 0.9.0.\nRefer to the original model card for more details on the model.",
"## Use with mlx"
] | [
"TAGS\n#mlx #safetensors #llama #region-us \n",
"# sosoai/Hansoldeco-llama3-8b-unsloth-v0.1-mlx\nThis model was converted to MLX format from ['sosoai/Hansoldeco-llama3-8b-unsloth-v0.1']() using mlx-lm version 0.9.0.\nRefer to the original model card for more details on the model.",
"## Use with mlx"
] |
text-to-image | diffusers |
# Model Card for Unit 1 of the [Diffusion Models Class 🧨](https://github.com/huggingface/diffusion-models-class)
This model is a diffusion model for unconditional image generation of cute 🦋.
## Usage
```python
from diffusers import DDPMPipeline
pipeline = DDPMPipeline.from_pretrained('shellypeng/EerieOrangeMix2Base')
image = pipeline().images[0]
image
``` | {"license": "mit", "library_name": "diffusers", "tags": ["text-to-image", "stable-diffusion"], "pipeline_tag": "text-to-image", "inference": true} | shellypeng/test_cheng | null | [
"diffusers",
"safetensors",
"text-to-image",
"stable-diffusion",
"license:mit",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
] | null | 2024-04-19T13:41:43+00:00 | [] | [] | TAGS
#diffusers #safetensors #text-to-image #stable-diffusion #license-mit #endpoints_compatible #diffusers-StableDiffusionPipeline #region-us
|
# Model Card for Unit 1 of the Diffusion Models Class
This model is a diffusion model for unconditional image generation of cute .
## Usage
| [
"# Model Card for Unit 1 of the Diffusion Models Class \n\nThis model is a diffusion model for unconditional image generation of cute .",
"## Usage"
] | [
"TAGS\n#diffusers #safetensors #text-to-image #stable-diffusion #license-mit #endpoints_compatible #diffusers-StableDiffusionPipeline #region-us \n",
"# Model Card for Unit 1 of the Diffusion Models Class \n\nThis model is a diffusion model for unconditional image generation of cute .",
"## Usage"
] |
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. -->
# financeLM_outputpath
This model is a fine-tuned version of [openai-community/gpt2](https://huggingface.co/openai-community/gpt2) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 1.3037
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0002
- train_batch_size: 4
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant
- lr_scheduler_warmup_ratio: 0.03
- num_epochs: 5
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:-----:|:---------------:|
| 1.0803 | 1.0 | 7031 | 1.0331 |
| 0.8 | 2.0 | 14062 | 1.1243 |
| 0.6646 | 3.0 | 21093 | 1.1960 |
| 0.5747 | 4.0 | 28125 | 1.2458 |
| 0.5094 | 5.0 | 35155 | 1.3037 |
### Framework versions
- Transformers 4.35.0
- Pytorch 2.1.2+cu121
- Datasets 2.14.5
- Tokenizers 0.14.1
| {"license": "mit", "tags": ["generated_from_trainer"], "base_model": "openai-community/gpt2", "model-index": [{"name": "financeLM_outputpath", "results": []}]} | Supersaiyan1729/financeLM_outputpath | null | [
"transformers",
"tensorboard",
"safetensors",
"gpt2",
"text-generation",
"generated_from_trainer",
"base_model:openai-community/gpt2",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-04-19T13:42:26+00:00 | [] | [] | TAGS
#transformers #tensorboard #safetensors #gpt2 #text-generation #generated_from_trainer #base_model-openai-community/gpt2 #license-mit #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us
| financeLM\_outputpath
=====================
This model is a fine-tuned version of openai-community/gpt2 on an unknown dataset.
It achieves the following results on the evaluation set:
* Loss: 1.3037
Model description
-----------------
More information needed
Intended uses & limitations
---------------------------
More information needed
Training and evaluation data
----------------------------
More information needed
Training procedure
------------------
### Training hyperparameters
The following hyperparameters were used during training:
* learning\_rate: 0.0002
* train\_batch\_size: 4
* eval\_batch\_size: 8
* seed: 42
* gradient\_accumulation\_steps: 4
* total\_train\_batch\_size: 16
* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
* lr\_scheduler\_type: constant
* lr\_scheduler\_warmup\_ratio: 0.03
* num\_epochs: 5
### Training results
### Framework versions
* Transformers 4.35.0
* Pytorch 2.1.2+cu121
* Datasets 2.14.5
* Tokenizers 0.14.1
| [
"### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0002\n* train\\_batch\\_size: 4\n* eval\\_batch\\_size: 8\n* seed: 42\n* gradient\\_accumulation\\_steps: 4\n* total\\_train\\_batch\\_size: 16\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: constant\n* lr\\_scheduler\\_warmup\\_ratio: 0.03\n* num\\_epochs: 5",
"### Training results",
"### Framework versions\n\n\n* Transformers 4.35.0\n* Pytorch 2.1.2+cu121\n* Datasets 2.14.5\n* Tokenizers 0.14.1"
] | [
"TAGS\n#transformers #tensorboard #safetensors #gpt2 #text-generation #generated_from_trainer #base_model-openai-community/gpt2 #license-mit #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: 0.0002\n* train\\_batch\\_size: 4\n* eval\\_batch\\_size: 8\n* seed: 42\n* gradient\\_accumulation\\_steps: 4\n* total\\_train\\_batch\\_size: 16\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: constant\n* lr\\_scheduler\\_warmup\\_ratio: 0.03\n* num\\_epochs: 5",
"### Training results",
"### Framework versions\n\n\n* Transformers 4.35.0\n* Pytorch 2.1.2+cu121\n* Datasets 2.14.5\n* Tokenizers 0.14.1"
] |
text-generation | transformers |
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] | {"library_name": "transformers", "tags": ["llama-factory"]} | vinhtran2611/test_export_model | null | [
"transformers",
"safetensors",
"llama",
"text-generation",
"llama-factory",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-04-19T13:44:09+00:00 | [
"1910.09700"
] | [] | TAGS
#transformers #safetensors #llama #text-generation #llama-factory #conversational #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us
|
# Model Card for Model ID
## Model Details
### Model Description
This is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.
- Developed by:
- Funded by [optional]:
- Shared by [optional]:
- Model type:
- Language(s) (NLP):
- License:
- Finetuned from model [optional]:
### Model Sources [optional]
- Repository:
- Paper [optional]:
- Demo [optional]:
## Uses
### Direct Use
### Downstream Use [optional]
### Out-of-Scope Use
## Bias, Risks, and Limitations
### Recommendations
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
## Training Details
### Training Data
### Training Procedure
#### Preprocessing [optional]
#### Training Hyperparameters
- Training regime:
#### Speeds, Sizes, Times [optional]
## Evaluation
### Testing Data, Factors & Metrics
#### Testing Data
#### Factors
#### Metrics
### Results
#### Summary
## Model Examination [optional]
## Environmental Impact
Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).
- Hardware Type:
- Hours used:
- Cloud Provider:
- Compute Region:
- Carbon Emitted:
## Technical Specifications [optional]
### Model Architecture and Objective
### Compute Infrastructure
#### Hardware
#### Software
[optional]
BibTeX:
APA:
## Glossary [optional]
## More Information [optional]
## Model Card Authors [optional]
## Model Card Contact
| [
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.",
"## How to Get Started with the Model\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] | [
"TAGS\n#transformers #safetensors #llama #text-generation #llama-factory #conversational #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n",
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.",
"## How to Get Started with the Model\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] |
null | peft |
# 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]
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- quant_method: bitsandbytes
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: True
- bnb_4bit_compute_dtype: float16
### Framework versions
- PEFT 0.6.2
| {"library_name": "peft", "base_model": "meta-llama/Meta-Llama-3-8B-Instruct"} | UnderstandLing/Llama-3-8B-Instruct-fr | null | [
"peft",
"safetensors",
"arxiv:1910.09700",
"base_model:meta-llama/Meta-Llama-3-8B-Instruct",
"region:us"
] | null | 2024-04-19T13:46:36+00:00 | [
"1910.09700"
] | [] | TAGS
#peft #safetensors #arxiv-1910.09700 #base_model-meta-llama/Meta-Llama-3-8B-Instruct #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
## Training procedure
The following 'bitsandbytes' quantization config was used during training:
- quant_method: bitsandbytes
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: True
- bnb_4bit_compute_dtype: float16
### Framework versions
- PEFT 0.6.2
| [
"# 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",
"## Training procedure\n\n\nThe following 'bitsandbytes' quantization config was used during training:\n- quant_method: bitsandbytes\n- load_in_8bit: False\n- load_in_4bit: True\n- llm_int8_threshold: 6.0\n- llm_int8_skip_modules: None\n- llm_int8_enable_fp32_cpu_offload: False\n- llm_int8_has_fp16_weight: False\n- bnb_4bit_quant_type: nf4\n- bnb_4bit_use_double_quant: True\n- bnb_4bit_compute_dtype: float16",
"### Framework versions\n\n\n- PEFT 0.6.2"
] | [
"TAGS\n#peft #safetensors #arxiv-1910.09700 #base_model-meta-llama/Meta-Llama-3-8B-Instruct #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",
"## Training procedure\n\n\nThe following 'bitsandbytes' quantization config was used during training:\n- quant_method: bitsandbytes\n- load_in_8bit: False\n- load_in_4bit: True\n- llm_int8_threshold: 6.0\n- llm_int8_skip_modules: None\n- llm_int8_enable_fp32_cpu_offload: False\n- llm_int8_has_fp16_weight: False\n- bnb_4bit_quant_type: nf4\n- bnb_4bit_use_double_quant: True\n- bnb_4bit_compute_dtype: float16",
"### Framework versions\n\n\n- PEFT 0.6.2"
] |
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": "-0.20 +/- 0.08", "name": "mean_reward", "verified": false}]}]}]} | IMENMANSOUR/a2c-PandaReachDense-v3 | null | [
"stable-baselines3",
"PandaReachDense-v3",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] | null | 2024-04-19T13:47:04+00:00 | [] | [] | TAGS
#stable-baselines3 #PandaReachDense-v3 #deep-reinforcement-learning #reinforcement-learning #model-index #region-us
|
# A2C Agent playing PandaReachDense-v3
This is a trained model of a A2C agent playing PandaReachDense-v3
using the stable-baselines3 library.
## Usage (with Stable-baselines3)
TODO: Add your code
| [
"# A2C Agent playing PandaReachDense-v3\nThis is a trained model of a A2C agent playing PandaReachDense-v3\nusing the stable-baselines3 library.",
"## Usage (with Stable-baselines3)\nTODO: Add your code"
] | [
"TAGS\n#stable-baselines3 #PandaReachDense-v3 #deep-reinforcement-learning #reinforcement-learning #model-index #region-us \n",
"# A2C Agent playing PandaReachDense-v3\nThis is a trained model of a A2C agent playing PandaReachDense-v3\nusing the stable-baselines3 library.",
"## Usage (with Stable-baselines3)\nTODO: Add your code"
] |
text-generation | transformers |
# Model Trained Using AutoTrain
This model was trained using AutoTrain. For more information, please visit [AutoTrain](https://hf.co/docs/autotrain).
# Usage
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
model_path = "PATH_TO_THIS_REPO"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(
model_path,
device_map="auto",
torch_dtype='auto'
).eval()
# Prompt content: "hi"
messages = [
{"role": "user", "content": "hi"}
]
input_ids = tokenizer.apply_chat_template(conversation=messages, tokenize=True, add_generation_prompt=True, return_tensors='pt')
output_ids = model.generate(input_ids.to('cuda'))
response = tokenizer.decode(output_ids[0][input_ids.shape[1]:], skip_special_tokens=True)
# Model response: "Hello! How can I assist you today?"
print(response)
``` | {"license": "other", "library_name": "transformers", "tags": ["autotrain", "text-generation-inference", "text-generation"], "widget": [{"messages": [{"role": "user", "content": "What is your favorite condiment?"}]}]} | abhishek/autotrain-llama3-orpo | null | [
"transformers",
"tensorboard",
"safetensors",
"llama",
"text-generation",
"autotrain",
"text-generation-inference",
"conversational",
"license:other",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | null | 2024-04-19T13:48:17+00:00 | [] | [] | TAGS
#transformers #tensorboard #safetensors #llama #text-generation #autotrain #text-generation-inference #conversational #license-other #autotrain_compatible #endpoints_compatible #region-us
|
# Model Trained Using AutoTrain
This model was trained using AutoTrain. For more information, please visit AutoTrain.
# Usage
| [
"# Model Trained Using AutoTrain\n\nThis model was trained using AutoTrain. For more information, please visit AutoTrain.",
"# Usage"
] | [
"TAGS\n#transformers #tensorboard #safetensors #llama #text-generation #autotrain #text-generation-inference #conversational #license-other #autotrain_compatible #endpoints_compatible #region-us \n",
"# Model Trained Using AutoTrain\n\nThis model was trained using AutoTrain. For more information, please visit AutoTrain.",
"# 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]
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- quant_method: bitsandbytes
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: True
- bnb_4bit_compute_dtype: float16
### Framework versions
- PEFT 0.6.2
| {"library_name": "peft", "base_model": "meta-llama/Meta-Llama-3-8B-Instruct"} | UnderstandLing/Llama-3-8B-Instruct-de | null | [
"peft",
"safetensors",
"arxiv:1910.09700",
"base_model:meta-llama/Meta-Llama-3-8B-Instruct",
"region:us"
] | null | 2024-04-19T13:49:39+00:00 | [
"1910.09700"
] | [] | TAGS
#peft #safetensors #arxiv-1910.09700 #base_model-meta-llama/Meta-Llama-3-8B-Instruct #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
## Training procedure
The following 'bitsandbytes' quantization config was used during training:
- quant_method: bitsandbytes
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: True
- bnb_4bit_compute_dtype: float16
### Framework versions
- PEFT 0.6.2
| [
"# 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",
"## Training procedure\n\n\nThe following 'bitsandbytes' quantization config was used during training:\n- quant_method: bitsandbytes\n- load_in_8bit: False\n- load_in_4bit: True\n- llm_int8_threshold: 6.0\n- llm_int8_skip_modules: None\n- llm_int8_enable_fp32_cpu_offload: False\n- llm_int8_has_fp16_weight: False\n- bnb_4bit_quant_type: nf4\n- bnb_4bit_use_double_quant: True\n- bnb_4bit_compute_dtype: float16",
"### Framework versions\n\n\n- PEFT 0.6.2"
] | [
"TAGS\n#peft #safetensors #arxiv-1910.09700 #base_model-meta-llama/Meta-Llama-3-8B-Instruct #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",
"## Training procedure\n\n\nThe following 'bitsandbytes' quantization config was used during training:\n- quant_method: bitsandbytes\n- load_in_8bit: False\n- load_in_4bit: True\n- llm_int8_threshold: 6.0\n- llm_int8_skip_modules: None\n- llm_int8_enable_fp32_cpu_offload: False\n- llm_int8_has_fp16_weight: False\n- bnb_4bit_quant_type: nf4\n- bnb_4bit_use_double_quant: True\n- bnb_4bit_compute_dtype: float16",
"### Framework versions\n\n\n- PEFT 0.6.2"
] |
feature-extraction | 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": []} | Ehsanl/e5-base-bs-chunk-meta | null | [
"transformers",
"safetensors",
"xlm-roberta",
"feature-extraction",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null | 2024-04-19T13:51:49+00:00 | [
"1910.09700"
] | [] | TAGS
#transformers #safetensors #xlm-roberta #feature-extraction #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 #xlm-roberta #feature-extraction #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 | null |
## Exllama v2 Quantizations of Meta-Llama-3-70B-Instruct
Using <a href="https://github.com/turboderp/exllamav2/releases/tag/v0.0.19">turboderp's ExLlamaV2 v0.0.19</a> for quantization.
<b>The "main" branch only contains the measurement.json, download one of the other branches for the model (see below)</b>
Each branch contains an individual bits per weight, with the main one containing only the meaurement.json for further conversions.
Conversion was done using the default calibration dataset.
Default arguments used except when the bits per weight is above 6.0, at that point the lm_head layer is quantized at 8 bits per weight instead of the default 6.
Original model: https://huggingface.co/meta-llama/Meta-Llama-3-70B-Instruct
<a href="https://huggingface.co/bartowski/Meta-Llama-3-70B-Instruct-exl2/tree/6_5">6.5 bits per weight</a>
<a href="https://huggingface.co/bartowski/Meta-Llama-3-70B-Instruct-exl2/tree/4_25">4.25 bits per weight</a>
<a href="https://huggingface.co/bartowski/Meta-Llama-3-70B-Instruct-exl2/tree/3_5">3.5 bits per weight</a>
<a href="https://huggingface.co/bartowski/Meta-Llama-3-70B-Instruct-exl2/tree/3_0">3.0 bits per weight</a>
<a href="https://huggingface.co/bartowski/Meta-Llama-3-70B-Instruct-exl2/tree/2_5">2.5 bits per weight</a>
<a href="https://huggingface.co/bartowski/Meta-Llama-3-70B-Instruct-exl2/tree/2_2">2.2 bits per weight</a>
## Download instructions
With git:
```shell
git clone --single-branch --branch 6_5 https://huggingface.co/bartowski/Meta-Llama-3-70B-Instruct-exl2
```
With huggingface hub (credit to TheBloke for instructions):
```shell
pip3 install huggingface-hub
```
To download the `main` (only useful if you only care about measurement.json) branch to a folder called `Meta-Llama-3-70B-Instruct-exl2`:
```shell
mkdir Meta-Llama-3-70B-Instruct-exl2
huggingface-cli download bartowski/Meta-Llama-3-70B-Instruct-exl2 --local-dir Meta-Llama-3-70B-Instruct-exl2 --local-dir-use-symlinks False
```
To download from a different branch, add the `--revision` parameter:
Linux:
```shell
mkdir Meta-Llama-3-70B-Instruct-exl2-6_5
huggingface-cli download bartowski/Meta-Llama-3-70B-Instruct-exl2 --revision 6_5 --local-dir Meta-Llama-3-70B-Instruct-exl2-6_5 --local-dir-use-symlinks False
```
Windows (which apparently doesn't like _ in folders sometimes?):
```shell
mkdir Meta-Llama-3-70B-Instruct-exl2-6.5
huggingface-cli download bartowski/Meta-Llama-3-70B-Instruct-exl2 --revision 6_5 --local-dir Meta-Llama-3-70B-Instruct-exl2-6.5 --local-dir-use-symlinks False
```
| {"language": ["en"], "license": "other", "tags": ["facebook", "meta", "pytorch", "llama", "llama-3"], "pipeline_tag": "text-generation", "license_name": "llama3", "license_link": "LICENSE", "extra_gated_prompt": "### META LLAMA 3 COMMUNITY LICENSE AGREEMENT\nMeta Llama 3 Version Release Date: April 18, 2024\n\"Agreement\" means the terms and conditions for use, reproduction, distribution and modification of the Llama Materials set forth herein.\n\"Documentation\" means the specifications, manuals and documentation accompanying Meta Llama 3 distributed by Meta at https://llama.meta.com/get-started/.\n\"Licensee\" or \"you\" means you, or your employer or any other person or entity (if you are entering into this Agreement on such person or entity\u2019s behalf), of the age required under applicable laws, rules or regulations to provide legal consent and that has legal authority to bind your employer or such other person or entity if you are entering in this Agreement on their behalf.\n\"Meta Llama 3\" means the foundational large language models and software and algorithms, including machine-learning model code, trained model weights, inference-enabling code, training-enabling code, fine-tuning enabling code and other elements of the foregoing distributed by Meta at https://llama.meta.com/llama-downloads.\n\"Llama Materials\" means, collectively, Meta\u2019s proprietary Meta Llama 3 and Documentation (and any portion thereof) made available under this Agreement.\n\"Meta\" or \"we\" means Meta Platforms Ireland Limited (if you are located in or, if you are an entity, your principal place of business is in the EEA or Switzerland) and Meta Platforms, Inc. (if you are located outside of the EEA or Switzerland).\n \n1. License Rights and Redistribution.\na. Grant of Rights. You are granted a non-exclusive, worldwide, non-transferable and royalty-free limited license under Meta\u2019s intellectual property or other rights owned by Meta embodied in the Llama Materials to use, reproduce, distribute, copy, create derivative works of, and make modifications to the Llama Materials.\nb. Redistribution and Use.\ni. If you distribute or make available the Llama Materials (or any derivative works thereof), or a product or service that uses any of them, including another AI model, you shall (A) provide a copy of this Agreement with any such Llama Materials; and (B) prominently display \u201cBuilt with Meta Llama 3\u201d on a related website, user interface, blogpost, about page, or product documentation. If you use the Llama Materials to create, train, fine tune, or otherwise improve an AI model, which is distributed or made available, you shall also include \u201cLlama 3\u201d at the beginning of any such AI model name.\nii. If you receive Llama Materials, or any derivative works thereof, from a Licensee as part of an integrated end user product, then Section 2 of this Agreement will not apply to you.\niii. You must retain in all copies of the Llama Materials that you distribute the following attribution notice within a \u201cNotice\u201d text file distributed as a part of such copies: \u201cMeta Llama 3 is licensed under the Meta Llama 3 Community License, Copyright \u00a9 Meta Platforms, Inc. All Rights Reserved.\u201d\niv. Your use of the Llama Materials must comply with applicable laws and regulations (including trade compliance laws and regulations) and adhere to the Acceptable Use Policy for the Llama Materials (available at https://llama.meta.com/llama3/use-policy), which is hereby incorporated by reference into this Agreement.\nv. You will not use the Llama Materials or any output or results of the Llama Materials to improve any other large language model (excluding Meta Llama 3 or derivative works thereof).\n2. Additional Commercial Terms. If, on the Meta Llama 3 version release date, the monthly active users of the products or services made available by or for Licensee, or Licensee\u2019s affiliates, is greater than 700 million monthly active users in the preceding calendar month, you must request a license from Meta, which Meta may grant to you in its sole discretion, and you are not authorized to exercise any of the rights under this Agreement unless or until Meta otherwise expressly grants you such rights.\n3. Disclaimer of Warranty. UNLESS REQUIRED BY APPLICABLE LAW, THE LLAMA MATERIALS AND ANY OUTPUT AND RESULTS THEREFROM ARE PROVIDED ON AN \u201cAS IS\u201d BASIS, WITHOUT WARRANTIES OF ANY KIND, AND META DISCLAIMS ALL WARRANTIES OF ANY KIND, BOTH EXPRESS AND IMPLIED, INCLUDING, WITHOUT LIMITATION, ANY WARRANTIES OF TITLE, NON-INFRINGEMENT, MERCHANTABILITY, OR FITNESS FOR A PARTICULAR PURPOSE. YOU ARE SOLELY RESPONSIBLE FOR DETERMINING THE APPROPRIATENESS OF USING OR REDISTRIBUTING THE LLAMA MATERIALS AND ASSUME ANY RISKS ASSOCIATED WITH YOUR USE OF THE LLAMA MATERIALS AND ANY OUTPUT AND RESULTS.\n4. Limitation of Liability. IN NO EVENT WILL META OR ITS AFFILIATES BE LIABLE UNDER ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, TORT, NEGLIGENCE, PRODUCTS LIABILITY, OR OTHERWISE, ARISING OUT OF THIS AGREEMENT, FOR ANY LOST PROFITS OR ANY INDIRECT, SPECIAL, CONSEQUENTIAL, INCIDENTAL, EXEMPLARY OR PUNITIVE DAMAGES, EVEN IF META OR ITS AFFILIATES HAVE BEEN ADVISED OF THE POSSIBILITY OF ANY OF THE FOREGOING.\n5. Intellectual Property.\na. No trademark licenses are granted under this Agreement, and in connection with the Llama Materials, neither Meta nor Licensee may use any name or mark owned by or associated with the other or any of its affiliates, except as required for reasonable and customary use in describing and redistributing the Llama Materials or as set forth in this Section 5(a). Meta hereby grants you a license to use \u201cLlama 3\u201d (the \u201cMark\u201d) solely as required to comply with the last sentence of Section 1.b.i. You will comply with Meta\u2019s brand guidelines (currently accessible at https://about.meta.com/brand/resources/meta/company-brand/ ). All goodwill arising out of your use of the Mark will inure to the benefit of Meta.\nb. Subject to Meta\u2019s ownership of Llama Materials and derivatives made by or for Meta, with respect to any derivative works and modifications of the Llama Materials that are made by you, as between you and Meta, you are and will be the owner of such derivative works and modifications.\nc. If you institute litigation or other proceedings against Meta or any entity (including a cross-claim or counterclaim in a lawsuit) alleging that the Llama Materials or Meta Llama 3 outputs or results, or any portion of any of the foregoing, constitutes infringement of intellectual property or other rights owned or licensable by you, then any licenses granted to you under this Agreement shall terminate as of the date such litigation or claim is filed or instituted. You will indemnify and hold harmless Meta from and against any claim by any third party arising out of or related to your use or distribution of the Llama Materials.\n6. Term and Termination. The term of this Agreement will commence upon your acceptance of this Agreement or access to the Llama Materials and will continue in full force and effect until terminated in accordance with the terms and conditions herein. Meta may terminate this Agreement if you are in breach of any term or condition of this Agreement. Upon termination of this Agreement, you shall delete and cease use of the Llama Materials. Sections 3, 4 and 7 shall survive the termination of this Agreement.\n7. Governing Law and Jurisdiction. This Agreement will be governed and construed under the laws of the State of California without regard to choice of law principles, and the UN Convention on Contracts for the International Sale of Goods does not apply to this Agreement. The courts of California shall have exclusive jurisdiction of any dispute arising out of this Agreement.\n### Meta Llama 3 Acceptable Use Policy\nMeta is committed to promoting safe and fair use of its tools and features, including Meta Llama 3. If you access or use Meta Llama 3, you agree to this Acceptable Use Policy (\u201cPolicy\u201d). The most recent copy of this policy can be found at [https://llama.meta.com/llama3/use-policy](https://llama.meta.com/llama3/use-policy)\n#### Prohibited Uses\nWe want everyone to use Meta Llama 3 safely and responsibly. You agree you will not use, or allow others to use, Meta Llama 3 to: 1. Violate the law or others\u2019 rights, including to:\n 1. Engage in, promote, generate, contribute to, encourage, plan, incite, or further illegal or unlawful activity or content, such as:\n 1. Violence or terrorism\n 2. Exploitation or harm to children, including the solicitation, creation, acquisition, or dissemination of child exploitative content or failure to report Child Sexual Abuse Material\n 3. Human trafficking, exploitation, and sexual violence\n 4. The illegal distribution of information or materials to minors, including obscene materials, or failure to employ legally required age-gating in connection with such information or materials.\n 5. Sexual solicitation\n 6. Any other criminal activity\n 2. Engage in, promote, incite, or facilitate the harassment, abuse, threatening, or bullying of individuals or groups of individuals\n 3. Engage in, promote, incite, or facilitate discrimination or other unlawful or harmful conduct in the provision of employment, employment benefits, credit, housing, other economic benefits, or other essential goods and services\n 4. Engage in the unauthorized or unlicensed practice of any profession including, but not limited to, financial, legal, medical/health, or related professional practices\n 5. Collect, process, disclose, generate, or infer health, demographic, or other sensitive personal or private information about individuals without rights and consents required by applicable laws\n 6. Engage in or facilitate any action or generate any content that infringes, misappropriates, or otherwise violates any third-party rights, including the outputs or results of any products or services using the Llama Materials\n 7. Create, generate, or facilitate the creation of malicious code, malware, computer viruses or do anything else that could disable, overburden, interfere with or impair the proper working, integrity, operation or appearance of a website or computer system\n2. Engage in, promote, incite, facilitate, or assist in the planning or development of activities that present a risk of death or bodily harm to individuals, including use of Meta Llama 3 related to the following:\n 1. Military, warfare, nuclear industries or applications, espionage, use for materials or activities that are subject to the International Traffic Arms Regulations (ITAR) maintained by the United States Department of State\n 2. Guns and illegal weapons (including weapon development)\n 3. Illegal drugs and regulated/controlled substances\n 4. Operation of critical infrastructure, transportation technologies, or heavy machinery\n 5. Self-harm or harm to others, including suicide, cutting, and eating disorders\n 6. Any content intended to incite or promote violence, abuse, or any infliction of bodily harm to an individual\n3. Intentionally deceive or mislead others, including use of Meta Llama 3 related to the following:\n 1. Generating, promoting, or furthering fraud or the creation or promotion of disinformation\n 2. Generating, promoting, or furthering defamatory content, including the creation of defamatory statements, images, or other content\n 3. Generating, promoting, or further distributing spam\n 4. Impersonating another individual without consent, authorization, or legal right\n 5. Representing that the use of Meta Llama 3 or outputs are human-generated\n 6. Generating or facilitating false online engagement, including fake reviews and other means of fake online engagement\n4. Fail to appropriately disclose to end users any known dangers of your AI system\nPlease report any violation of this Policy, software \u201cbug,\u201d or other problems that could lead to a violation of this Policy through one of the following means:\n * Reporting issues with the model: [https://github.com/meta-llama/llama3](https://github.com/meta-llama/llama3)\n * Reporting risky content generated by the model:\n developers.facebook.com/llama_output_feedback\n * Reporting bugs and security concerns: facebook.com/whitehat/info\n * Reporting violations of the Acceptable Use Policy or unlicensed uses of Meta Llama 3: [email protected]", "extra_gated_fields": {"First Name": "text", "Last Name": "text", "Date of birth": "date_picker", "Country": "country", "Affiliation": "text", "geo": "ip_location", "By clicking Submit below I accept the terms of the license and acknowledge that the information I provide will be collected stored processed and shared in accordance with the Meta Privacy Policy": "checkbox"}, "extra_gated_description": "The information you provide will be collected, stored, processed and shared in accordance with the [Meta Privacy Policy](https://www.facebook.com/privacy/policy/).", "extra_gated_button_content": "Submit", "quantized_by": "bartowski"} | bartowski/Meta-Llama-3-70B-Instruct-exl2 | null | [
"facebook",
"meta",
"pytorch",
"llama",
"llama-3",
"text-generation",
"en",
"license:other",
"region:us"
] | null | 2024-04-19T13:52:11+00:00 | [] | [
"en"
] | TAGS
#facebook #meta #pytorch #llama #llama-3 #text-generation #en #license-other #region-us
|
## Exllama v2 Quantizations of Meta-Llama-3-70B-Instruct
Using <a href="URL ExLlamaV2 v0.0.19</a> for quantization.
<b>The "main" branch only contains the URL, download one of the other branches for the model (see below)</b>
Each branch contains an individual bits per weight, with the main one containing only the URL for further conversions.
Conversion was done using the default calibration dataset.
Default arguments used except when the bits per weight is above 6.0, at that point the lm_head layer is quantized at 8 bits per weight instead of the default 6.
Original model: URL
<a href="URL bits per weight</a>
<a href="URL bits per weight</a>
<a href="URL bits per weight</a>
<a href="URL bits per weight</a>
<a href="URL bits per weight</a>
<a href="URL bits per weight</a>
## Download instructions
With git:
With huggingface hub (credit to TheBloke for instructions):
To download the 'main' (only useful if you only care about URL) branch to a folder called 'Meta-Llama-3-70B-Instruct-exl2':
To download from a different branch, add the '--revision' parameter:
Linux:
Windows (which apparently doesn't like _ in folders sometimes?):
| [
"## Exllama v2 Quantizations of Meta-Llama-3-70B-Instruct\n\nUsing <a href=\"URL ExLlamaV2 v0.0.19</a> for quantization.\n\n<b>The \"main\" branch only contains the URL, download one of the other branches for the model (see below)</b>\n\nEach branch contains an individual bits per weight, with the main one containing only the URL for further conversions.\n\nConversion was done using the default calibration dataset.\n\nDefault arguments used except when the bits per weight is above 6.0, at that point the lm_head layer is quantized at 8 bits per weight instead of the default 6.\n\nOriginal model: URL\n\n\n<a href=\"URL bits per weight</a>\n\n<a href=\"URL bits per weight</a>\n\n<a href=\"URL bits per weight</a>\n\n<a href=\"URL bits per weight</a>\n\n<a href=\"URL bits per weight</a>\n\n<a href=\"URL bits per weight</a>",
"## Download instructions\n\nWith git:\n\n\n\nWith huggingface hub (credit to TheBloke for instructions):\n\n\n\nTo download the 'main' (only useful if you only care about URL) branch to a folder called 'Meta-Llama-3-70B-Instruct-exl2':\n\n\n\nTo download from a different branch, add the '--revision' parameter:\n\nLinux:\n\n\n\nWindows (which apparently doesn't like _ in folders sometimes?):"
] | [
"TAGS\n#facebook #meta #pytorch #llama #llama-3 #text-generation #en #license-other #region-us \n",
"## Exllama v2 Quantizations of Meta-Llama-3-70B-Instruct\n\nUsing <a href=\"URL ExLlamaV2 v0.0.19</a> for quantization.\n\n<b>The \"main\" branch only contains the URL, download one of the other branches for the model (see below)</b>\n\nEach branch contains an individual bits per weight, with the main one containing only the URL for further conversions.\n\nConversion was done using the default calibration dataset.\n\nDefault arguments used except when the bits per weight is above 6.0, at that point the lm_head layer is quantized at 8 bits per weight instead of the default 6.\n\nOriginal model: URL\n\n\n<a href=\"URL bits per weight</a>\n\n<a href=\"URL bits per weight</a>\n\n<a href=\"URL bits per weight</a>\n\n<a href=\"URL bits per weight</a>\n\n<a href=\"URL bits per weight</a>\n\n<a href=\"URL bits per weight</a>",
"## Download instructions\n\nWith git:\n\n\n\nWith huggingface hub (credit to TheBloke for instructions):\n\n\n\nTo download the 'main' (only useful if you only care about URL) branch to a folder called 'Meta-Llama-3-70B-Instruct-exl2':\n\n\n\nTo download from a different branch, add the '--revision' parameter:\n\nLinux:\n\n\n\nWindows (which apparently doesn't like _ in folders sometimes?):"
] |
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": "265.63 +/- 34.53", "name": "mean_reward", "verified": false}]}]}]} | amazingT/ppo-LunarLander-v2 | null | [
"stable-baselines3",
"LunarLander-v2",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] | null | 2024-04-19T13:52:51+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"
] |
null | transformers |
# Uploaded model
- **Developed by:** MR-Eder
- **License:** apache-2.0
- **Finetuned from model :** unsloth/llama-3-8b-Instruct-bnb-4bit
This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
| {"language": ["en"], "license": "apache-2.0", "tags": ["text-generation-inference", "transformers", "unsloth", "llama", "trl"], "base_model": "unsloth/llama-3-8b-Instruct-bnb-4bit"} | MR-Eder/llama3-1000-steps-wiki-de-conversation | null | [
"transformers",
"safetensors",
"text-generation-inference",
"unsloth",
"llama",
"trl",
"en",
"base_model:unsloth/llama-3-8b-Instruct-bnb-4bit",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | 2024-04-19T13:54:44+00:00 | [] | [
"en"
] | TAGS
#transformers #safetensors #text-generation-inference #unsloth #llama #trl #en #base_model-unsloth/llama-3-8b-Instruct-bnb-4bit #license-apache-2.0 #endpoints_compatible #region-us
|
# Uploaded model
- Developed by: MR-Eder
- License: apache-2.0
- Finetuned from model : unsloth/llama-3-8b-Instruct-bnb-4bit
This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.
<img src="URL width="200"/>
| [
"# Uploaded model\n\n- Developed by: MR-Eder\n- License: apache-2.0\n- Finetuned from model : unsloth/llama-3-8b-Instruct-bnb-4bit\n\nThis llama model was trained 2x faster with Unsloth and Huggingface's TRL library.\n\n<img src=\"URL width=\"200\"/>"
] | [
"TAGS\n#transformers #safetensors #text-generation-inference #unsloth #llama #trl #en #base_model-unsloth/llama-3-8b-Instruct-bnb-4bit #license-apache-2.0 #endpoints_compatible #region-us \n",
"# Uploaded model\n\n- Developed by: MR-Eder\n- License: apache-2.0\n- Finetuned from model : unsloth/llama-3-8b-Instruct-bnb-4bit\n\nThis llama model was trained 2x faster with Unsloth and Huggingface's TRL library.\n\n<img src=\"URL width=\"200\"/>"
] |
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. -->
# falcon7binstructApril19
This model is a fine-tuned version of [tiiuae/falcon-7b-instruct](https://huggingface.co/tiiuae/falcon-7b-instruct) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3423
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0001
- train_batch_size: 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: cosine
- lr_scheduler_warmup_ratio: 0.03
- training_steps: 200
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 0.3618 | 1.0 | 170 | 0.3430 |
| 0.2672 | 1.17 | 200 | 0.3423 |
### Framework versions
- PEFT 0.10.0
- Transformers 4.39.3
- Pytorch 2.2.2+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2 | {"license": "apache-2.0", "library_name": "peft", "tags": ["generated_from_trainer"], "base_model": "tiiuae/falcon-7b-instruct", "model-index": [{"name": "falcon7binstructApril19", "results": []}]} | Ray011/falcon7binstructApril19 | null | [
"peft",
"safetensors",
"generated_from_trainer",
"base_model:tiiuae/falcon-7b-instruct",
"license:apache-2.0",
"region:us"
] | null | 2024-04-19T13:56:55+00:00 | [] | [] | TAGS
#peft #safetensors #generated_from_trainer #base_model-tiiuae/falcon-7b-instruct #license-apache-2.0 #region-us
| falcon7binstructApril19
=======================
This model is a fine-tuned version of tiiuae/falcon-7b-instruct on an unknown dataset.
It achieves the following results on the evaluation set:
* Loss: 0.3423
Model description
-----------------
More information needed
Intended uses & limitations
---------------------------
More information needed
Training and evaluation data
----------------------------
More information needed
Training procedure
------------------
### Training hyperparameters
The following hyperparameters were used during training:
* learning\_rate: 0.0001
* train\_batch\_size: 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: cosine
* lr\_scheduler\_warmup\_ratio: 0.03
* training\_steps: 200
### Training results
### Framework versions
* PEFT 0.10.0
* 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: 0.0001\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: cosine\n* lr\\_scheduler\\_warmup\\_ratio: 0.03\n* training\\_steps: 200",
"### Training results",
"### Framework versions\n\n\n* PEFT 0.10.0\n* Transformers 4.39.3\n* Pytorch 2.2.2+cu121\n* Datasets 2.18.0\n* Tokenizers 0.15.2"
] | [
"TAGS\n#peft #safetensors #generated_from_trainer #base_model-tiiuae/falcon-7b-instruct #license-apache-2.0 #region-us \n",
"### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0001\n* train\\_batch\\_size: 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: cosine\n* lr\\_scheduler\\_warmup\\_ratio: 0.03\n* training\\_steps: 200",
"### Training results",
"### Framework versions\n\n\n* PEFT 0.10.0\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": []} | idoru/jetmoe-8b-MyRus-kto | null | [
"transformers",
"safetensors",
"jetmoe",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | null | 2024-04-19T13:57:01+00:00 | [
"1910.09700"
] | [] | TAGS
#transformers #safetensors #jetmoe #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 #jetmoe #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"
] |
image-to-3d | diffusers |
This is a copy of [ashawkey/imagedream-ipmv-diffusers](https://huggingface.co/ashawkey/imagedream-ipmv-diffusers).
It is hosted here for persistence throughout the ML for 3D course.
# MVDream-diffusers Model Card
This is a port of https://huggingface.co/Peng-Wang/ImageDream into diffusers.
For usage, please check: https://github.com/ashawkey/mvdream_diffusers
## Citation
```
@article{wang2023imagedream,
title={ImageDream: Image-Prompt Multi-view Diffusion for 3D Generation},
author={Wang, Peng and Shi, Yichun},
journal={arXiv preprint arXiv:2312.02201},
year={2023}
}
```
## Misuse, Malicious Use, and Out-of-Scope Use
The model should not be used to intentionally create or disseminate images that create hostile or alienating environments for people. This includes generating images that people would foreseeably find disturbing, distressing, or offensive; or content that propagates historical or current stereotypes.
| {"license": "openrail", "pipeline_tag": "image-to-3d"} | dylanebert/imagedream | null | [
"diffusers",
"safetensors",
"image-to-3d",
"license:openrail",
"has_space",
"diffusers:MVDreamPipeline",
"region:us"
] | null | 2024-04-19T13:57:16+00:00 | [] | [] | TAGS
#diffusers #safetensors #image-to-3d #license-openrail #has_space #diffusers-MVDreamPipeline #region-us
|
This is a copy of ashawkey/imagedream-ipmv-diffusers.
It is hosted here for persistence throughout the ML for 3D course.
# MVDream-diffusers Model Card
This is a port of URL into diffusers.
For usage, please check: URL
## Misuse, Malicious Use, and Out-of-Scope Use
The model should not be used to intentionally create or disseminate images that create hostile or alienating environments for people. This includes generating images that people would foreseeably find disturbing, distressing, or offensive; or content that propagates historical or current stereotypes.
| [
"# MVDream-diffusers Model Card\n\nThis is a port of URL into diffusers.\n\nFor usage, please check: URL",
"## Misuse, Malicious Use, and Out-of-Scope Use\n\nThe model should not be used to intentionally create or disseminate images that create hostile or alienating environments for people. This includes generating images that people would foreseeably find disturbing, distressing, or offensive; or content that propagates historical or current stereotypes."
] | [
"TAGS\n#diffusers #safetensors #image-to-3d #license-openrail #has_space #diffusers-MVDreamPipeline #region-us \n",
"# MVDream-diffusers Model Card\n\nThis is a port of URL into diffusers.\n\nFor usage, please check: URL",
"## Misuse, Malicious Use, and Out-of-Scope Use\n\nThe model should not be used to intentionally create or disseminate images that create hostile or alienating environments for people. This includes generating images that people would foreseeably find disturbing, distressing, or offensive; or content that propagates historical or current stereotypes."
] |
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": []} | mani-a-i/mistral-7b-v2-full-model | null | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"4-bit",
"region:us"
] | null | 2024-04-19T13:58:53+00:00 | [
"1910.09700"
] | [] | TAGS
#transformers #safetensors #mistral #text-generation #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 #mistral #text-generation #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"
] |
text-generation | transformers |
## Model Card for Model ID
French-Alpaca based on Llama3-8B-Instruct
### Model Description
fine-tuned from the original French-Alpaca-dataset entirely generated with OpenAI GPT-3.5-turbo.
French-Alpaca is a general model and can itself be finetuned to be specialized for specific use cases.
The fine-tuning method is inspired from https://crfm.stanford.edu/2023/03/13/alpaca.html
Quantized Q4_K_M GGUF 4bits version available : jpacifico/french-alpaca-llama3-8B-Q4-GGUF
### Usage
```python
model_id = "jpacifico/French-Alpaca-Llama3-8B-Instruct-v1.0"
model = AutoModelForCausalLM.from_pretrained(model_id, quantization_config=bnb_config, device_map={"":0})
tokenizer = AutoTokenizer.from_pretrained(model_id, add_eos_token=True, padding_side='left')
streamer = TextStreamer(tokenizer, timeout=10.0, skip_prompt=True, skip_special_tokens=True)
def stream_frenchalpaca(user_prompt):
runtimeFlag = "cuda:0"
system_prompt = 'Tu trouveras ci-dessous une instruction qui décrit une tâche. Rédige une réponse qui complète de manière appropriée la demande.\n\n'
B_INST, E_INST = "### Instruction:\n", "### Response:\n"
prompt = f"{system_prompt}{B_INST}{user_prompt.strip()}\n\n{E_INST}"
inputs = tokenizer([prompt], return_tensors="pt").to(runtimeFlag)
streamer = TextStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True)
_ = model.generate(**inputs, streamer=streamer, max_new_tokens=500)
stream_frenchalpaca("your prompt here")
```
Colab notebook available on my Github :
https://github.com/jpacifico/French-Alpaca/blob/main/French_Alpaca_Llama3_inference_test_colab.ipynb
### Limitations
The French-Alpaca model is a quick demonstration that a base 8B model can be easily fine-tuned to specialize in a particular language.
It does not have any moderation mechanisms.
- **Developed by:** Jonathan Pacifico, 2024
- **Model type:** LLM
- **Language(s) (NLP):** French
- **License:** MIT | {"language": ["fr", "en"], "license": "apache-2.0", "library_name": "transformers", "tags": ["llama3", "french", "llama-3-8B"], "datasets": ["jpacifico/French-Alpaca-dataset-Instruct-110K"]} | jpacifico/French-Alpaca-Llama3-8B-Instruct-v1.0 | null | [
"transformers",
"safetensors",
"llama",
"text-generation",
"llama3",
"french",
"llama-3-8B",
"conversational",
"fr",
"en",
"dataset:jpacifico/French-Alpaca-dataset-Instruct-110K",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-04-19T14:03:02+00:00 | [] | [
"fr",
"en"
] | TAGS
#transformers #safetensors #llama #text-generation #llama3 #french #llama-3-8B #conversational #fr #en #dataset-jpacifico/French-Alpaca-dataset-Instruct-110K #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us
|
## Model Card for Model ID
French-Alpaca based on Llama3-8B-Instruct
!image/jpeg
### Model Description
fine-tuned from the original French-Alpaca-dataset entirely generated with OpenAI GPT-3.5-turbo.
French-Alpaca is a general model and can itself be finetuned to be specialized for specific use cases.
The fine-tuning method is inspired from URL
Quantized Q4_K_M GGUF 4bits version available : jpacifico/french-alpaca-llama3-8B-Q4-GGUF
### Usage
Colab notebook available on my Github :
URL
### Limitations
The French-Alpaca model is a quick demonstration that a base 8B model can be easily fine-tuned to specialize in a particular language.
It does not have any moderation mechanisms.
- Developed by: Jonathan Pacifico, 2024
- Model type: LLM
- Language(s) (NLP): French
- License: MIT | [
"## Model Card for Model ID\n\nFrench-Alpaca based on Llama3-8B-Instruct\n\n!image/jpeg",
"### Model Description\n\nfine-tuned from the original French-Alpaca-dataset entirely generated with OpenAI GPT-3.5-turbo. \nFrench-Alpaca is a general model and can itself be finetuned to be specialized for specific use cases. \n\nThe fine-tuning method is inspired from URL\n\nQuantized Q4_K_M GGUF 4bits version available : jpacifico/french-alpaca-llama3-8B-Q4-GGUF",
"### Usage\n\n\nColab notebook available on my Github : \nURL",
"### Limitations\n\nThe French-Alpaca model is a quick demonstration that a base 8B model can be easily fine-tuned to specialize in a particular language.\nIt does not have any moderation mechanisms.\n\n- Developed by: Jonathan Pacifico, 2024\n- Model type: LLM \n- Language(s) (NLP): French\n- License: MIT"
] | [
"TAGS\n#transformers #safetensors #llama #text-generation #llama3 #french #llama-3-8B #conversational #fr #en #dataset-jpacifico/French-Alpaca-dataset-Instruct-110K #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n",
"## Model Card for Model ID\n\nFrench-Alpaca based on Llama3-8B-Instruct\n\n!image/jpeg",
"### Model Description\n\nfine-tuned from the original French-Alpaca-dataset entirely generated with OpenAI GPT-3.5-turbo. \nFrench-Alpaca is a general model and can itself be finetuned to be specialized for specific use cases. \n\nThe fine-tuning method is inspired from URL\n\nQuantized Q4_K_M GGUF 4bits version available : jpacifico/french-alpaca-llama3-8B-Q4-GGUF",
"### Usage\n\n\nColab notebook available on my Github : \nURL",
"### Limitations\n\nThe French-Alpaca model is a quick demonstration that a base 8B model can be easily fine-tuned to specialize in a particular language.\nIt does not have any moderation mechanisms.\n\n- Developed by: Jonathan Pacifico, 2024\n- Model type: LLM \n- Language(s) (NLP): French\n- License: MIT"
] |
null | transformers | ## About
<!-- ### quantize_version: 1 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: -->
<!-- ### vocab_type: -->
weighted/imatrix quants of https://huggingface.co/Sao10K/Franziska-Mixtral-v1
<!-- provided-files -->
static quants are available at https://huggingface.co/mradermacher/Franziska-Mixtral-v1-GGUF
## Usage
If you are unsure how to use GGUF files, refer to one of [TheBloke's
READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
more details, including on how to concatenate multi-part files.
## Provided Quants
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
| Link | Type | Size/GB | Notes |
|:-----|:-----|--------:|:------|
| [GGUF](https://huggingface.co/mradermacher/Franziska-Mixtral-v1-i1-GGUF/resolve/main/Franziska-Mixtral-v1.i1-IQ1_S.gguf) | i1-IQ1_S | 9.9 | for the desperate |
| [GGUF](https://huggingface.co/mradermacher/Franziska-Mixtral-v1-i1-GGUF/resolve/main/Franziska-Mixtral-v1.i1-IQ1_M.gguf) | i1-IQ1_M | 10.9 | for the desperate |
| [GGUF](https://huggingface.co/mradermacher/Franziska-Mixtral-v1-i1-GGUF/resolve/main/Franziska-Mixtral-v1.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 12.7 | |
| [GGUF](https://huggingface.co/mradermacher/Franziska-Mixtral-v1-i1-GGUF/resolve/main/Franziska-Mixtral-v1.i1-IQ2_XS.gguf) | i1-IQ2_XS | 14.0 | |
| [GGUF](https://huggingface.co/mradermacher/Franziska-Mixtral-v1-i1-GGUF/resolve/main/Franziska-Mixtral-v1.i1-IQ2_S.gguf) | i1-IQ2_S | 14.2 | |
| [GGUF](https://huggingface.co/mradermacher/Franziska-Mixtral-v1-i1-GGUF/resolve/main/Franziska-Mixtral-v1.i1-IQ2_M.gguf) | i1-IQ2_M | 15.6 | |
| [GGUF](https://huggingface.co/mradermacher/Franziska-Mixtral-v1-i1-GGUF/resolve/main/Franziska-Mixtral-v1.i1-Q2_K.gguf) | i1-Q2_K | 17.4 | IQ3_XXS probably better |
| [GGUF](https://huggingface.co/mradermacher/Franziska-Mixtral-v1-i1-GGUF/resolve/main/Franziska-Mixtral-v1.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 18.3 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/Franziska-Mixtral-v1-i1-GGUF/resolve/main/Franziska-Mixtral-v1.i1-IQ3_XS.gguf) | i1-IQ3_XS | 19.5 | |
| [GGUF](https://huggingface.co/mradermacher/Franziska-Mixtral-v1-i1-GGUF/resolve/main/Franziska-Mixtral-v1.i1-IQ3_S.gguf) | i1-IQ3_S | 20.5 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/Franziska-Mixtral-v1-i1-GGUF/resolve/main/Franziska-Mixtral-v1.i1-Q3_K_S.gguf) | i1-Q3_K_S | 20.5 | IQ3_XS probably better |
| [GGUF](https://huggingface.co/mradermacher/Franziska-Mixtral-v1-i1-GGUF/resolve/main/Franziska-Mixtral-v1.i1-IQ3_M.gguf) | i1-IQ3_M | 21.5 | |
| [GGUF](https://huggingface.co/mradermacher/Franziska-Mixtral-v1-i1-GGUF/resolve/main/Franziska-Mixtral-v1.i1-Q3_K_M.gguf) | i1-Q3_K_M | 22.6 | IQ3_S probably better |
| [GGUF](https://huggingface.co/mradermacher/Franziska-Mixtral-v1-i1-GGUF/resolve/main/Franziska-Mixtral-v1.i1-Q3_K_L.gguf) | i1-Q3_K_L | 24.3 | IQ3_M probably better |
| [GGUF](https://huggingface.co/mradermacher/Franziska-Mixtral-v1-i1-GGUF/resolve/main/Franziska-Mixtral-v1.i1-IQ4_XS.gguf) | i1-IQ4_XS | 25.2 | |
| [GGUF](https://huggingface.co/mradermacher/Franziska-Mixtral-v1-i1-GGUF/resolve/main/Franziska-Mixtral-v1.i1-Q4_0.gguf) | i1-Q4_0 | 26.7 | fast, low quality |
| [GGUF](https://huggingface.co/mradermacher/Franziska-Mixtral-v1-i1-GGUF/resolve/main/Franziska-Mixtral-v1.i1-Q4_K_S.gguf) | i1-Q4_K_S | 26.8 | optimal size/speed/quality |
| [GGUF](https://huggingface.co/mradermacher/Franziska-Mixtral-v1-i1-GGUF/resolve/main/Franziska-Mixtral-v1.i1-Q4_K_M.gguf) | i1-Q4_K_M | 28.5 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Franziska-Mixtral-v1-i1-GGUF/resolve/main/Franziska-Mixtral-v1.i1-Q5_K_S.gguf) | i1-Q5_K_S | 32.3 | |
| [GGUF](https://huggingface.co/mradermacher/Franziska-Mixtral-v1-i1-GGUF/resolve/main/Franziska-Mixtral-v1.i1-Q5_K_M.gguf) | i1-Q5_K_M | 33.3 | |
| [GGUF](https://huggingface.co/mradermacher/Franziska-Mixtral-v1-i1-GGUF/resolve/main/Franziska-Mixtral-v1.i1-Q6_K.gguf) | i1-Q6_K | 38.5 | practically like static Q6_K |
Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):
And here are Artefact2's thoughts on the matter:
https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
## FAQ / Model Request
See https://huggingface.co/mradermacher/model_requests for some answers to
questions you might have and/or if you want some other model quantized.
## Thanks
I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
me use its servers and providing upgrades to my workstation to enable
this work in my free time.
<!-- end -->
| {"language": ["en"], "license": "cc-by-nc-4.0", "library_name": "transformers", "base_model": "Sao10K/Franziska-Mixtral-v1", "quantized_by": "mradermacher"} | mradermacher/Franziska-Mixtral-v1-i1-GGUF | null | [
"transformers",
"gguf",
"en",
"base_model:Sao10K/Franziska-Mixtral-v1",
"license:cc-by-nc-4.0",
"endpoints_compatible",
"region:us"
] | null | 2024-04-19T14:04:16+00:00 | [] | [
"en"
] | TAGS
#transformers #gguf #en #base_model-Sao10K/Franziska-Mixtral-v1 #license-cc-by-nc-4.0 #endpoints_compatible #region-us
| About
-----
weighted/imatrix quants of URL
static quants are available at URL
Usage
-----
If you are unsure how to use GGUF files, refer to one of TheBloke's
READMEs for
more details, including on how to concatenate multi-part files.
Provided Quants
---------------
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):
!URL
And here are Artefact2's thoughts on the matter:
URL
FAQ / Model Request
-------------------
See URL for some answers to
questions you might have and/or if you want some other model quantized.
Thanks
------
I thank my company, nethype GmbH, for letting
me use its servers and providing upgrades to my workstation to enable
this work in my free time.
| [] | [
"TAGS\n#transformers #gguf #en #base_model-Sao10K/Franziska-Mixtral-v1 #license-cc-by-nc-4.0 #endpoints_compatible #region-us \n"
] |
text-generation | transformers |
# Uploaded model
- **Developed by:** MR-Eder
- **License:** apache-2.0
- **Finetuned from model :** unsloth/llama-3-8b-Instruct-bnb-4bit
This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
| {"language": ["en"], "license": "apache-2.0", "tags": ["text-generation-inference", "transformers", "unsloth", "llama", "trl", "sft"], "base_model": "unsloth/llama-3-8b-Instruct-bnb-4bit"} | MR-Eder/llama3-1000-steps-wiki-de-conversation-merged-16bit-GGUF | null | [
"transformers",
"safetensors",
"llama",
"text-generation",
"text-generation-inference",
"unsloth",
"trl",
"sft",
"conversational",
"en",
"base_model:unsloth/llama-3-8b-Instruct-bnb-4bit",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | null | 2024-04-19T14:04:35+00:00 | [] | [
"en"
] | TAGS
#transformers #safetensors #llama #text-generation #text-generation-inference #unsloth #trl #sft #conversational #en #base_model-unsloth/llama-3-8b-Instruct-bnb-4bit #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us
|
# Uploaded model
- Developed by: MR-Eder
- License: apache-2.0
- Finetuned from model : unsloth/llama-3-8b-Instruct-bnb-4bit
This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.
<img src="URL width="200"/>
| [
"# Uploaded model\n\n- Developed by: MR-Eder\n- License: apache-2.0\n- Finetuned from model : unsloth/llama-3-8b-Instruct-bnb-4bit\n\nThis llama model was trained 2x faster with Unsloth and Huggingface's TRL library.\n\n<img src=\"URL width=\"200\"/>"
] | [
"TAGS\n#transformers #safetensors #llama #text-generation #text-generation-inference #unsloth #trl #sft #conversational #en #base_model-unsloth/llama-3-8b-Instruct-bnb-4bit #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us \n",
"# Uploaded model\n\n- Developed by: MR-Eder\n- License: apache-2.0\n- Finetuned from model : unsloth/llama-3-8b-Instruct-bnb-4bit\n\nThis llama model was trained 2x faster with Unsloth and Huggingface's TRL library.\n\n<img src=\"URL width=\"200\"/>"
] |
automatic-speech-recognition | transformers |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# Whisper Small MR - Chirag Brahme
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Common Voice 11.0 dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2701
- Wer: 45.6837
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant_with_warmup
- lr_scheduler_warmup_steps: 50
- training_steps: 500
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|:-------------:|:------:|:----:|:---------------:|:-------:|
| 0.1621 | 2.0325 | 500 | 0.2701 | 45.6837 |
### Framework versions
- Transformers 4.40.1
- Pytorch 2.1.2
- Datasets 2.19.0
- Tokenizers 0.19.1
| {"language": ["mr"], "license": "apache-2.0", "tags": ["generated_from_trainer"], "datasets": ["mozilla-foundation/common_voice_11_0"], "metrics": ["wer"], "base_model": "openai/whisper-small", "model-index": [{"name": "Whisper Small MR - Chirag Brahme", "results": [{"task": {"type": "automatic-speech-recognition", "name": "Automatic Speech Recognition"}, "dataset": {"name": "Common Voice 11.0", "type": "mozilla-foundation/common_voice_11_0", "config": "mr", "split": "None", "args": "config: mr, split: test"}, "metrics": [{"type": "wer", "value": 45.6837083360196, "name": "Wer"}]}]}]} | PolyChirag/Marathi_ASR_using_Whisper_Small | null | [
"transformers",
"tensorboard",
"safetensors",
"whisper",
"automatic-speech-recognition",
"generated_from_trainer",
"mr",
"dataset:mozilla-foundation/common_voice_11_0",
"base_model:openai/whisper-small",
"license:apache-2.0",
"model-index",
"endpoints_compatible",
"region:us",
"has_space"
] | null | 2024-04-19T14:07:36+00:00 | [] | [
"mr"
] | TAGS
#transformers #tensorboard #safetensors #whisper #automatic-speech-recognition #generated_from_trainer #mr #dataset-mozilla-foundation/common_voice_11_0 #base_model-openai/whisper-small #license-apache-2.0 #model-index #endpoints_compatible #region-us #has_space
| Whisper Small MR - Chirag Brahme
================================
This model is a fine-tuned version of openai/whisper-small on the Common Voice 11.0 dataset.
It achieves the following results on the evaluation set:
* Loss: 0.2701
* Wer: 45.6837
Model description
-----------------
More information needed
Intended uses & limitations
---------------------------
More information needed
Training and evaluation data
----------------------------
More information needed
Training procedure
------------------
### Training hyperparameters
The following hyperparameters were used during training:
* learning\_rate: 1e-05
* train\_batch\_size: 16
* eval\_batch\_size: 16
* seed: 42
* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
* lr\_scheduler\_type: constant\_with\_warmup
* lr\_scheduler\_warmup\_steps: 50
* training\_steps: 500
* mixed\_precision\_training: Native AMP
### Training results
### Framework versions
* Transformers 4.40.1
* Pytorch 2.1.2
* Datasets 2.19.0
* Tokenizers 0.19.1
| [
"### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 1e-05\n* train\\_batch\\_size: 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: constant\\_with\\_warmup\n* lr\\_scheduler\\_warmup\\_steps: 50\n* training\\_steps: 500\n* mixed\\_precision\\_training: Native AMP",
"### Training results",
"### Framework versions\n\n\n* Transformers 4.40.1\n* Pytorch 2.1.2\n* Datasets 2.19.0\n* Tokenizers 0.19.1"
] | [
"TAGS\n#transformers #tensorboard #safetensors #whisper #automatic-speech-recognition #generated_from_trainer #mr #dataset-mozilla-foundation/common_voice_11_0 #base_model-openai/whisper-small #license-apache-2.0 #model-index #endpoints_compatible #region-us #has_space \n",
"### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 1e-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: constant\\_with\\_warmup\n* lr\\_scheduler\\_warmup\\_steps: 50\n* training\\_steps: 500\n* mixed\\_precision\\_training: Native AMP",
"### Training results",
"### Framework versions\n\n\n* Transformers 4.40.1\n* Pytorch 2.1.2\n* Datasets 2.19.0\n* Tokenizers 0.19.1"
] |
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. -->
# bert-finetuned-ner
This model is a fine-tuned version of [bert-large-cased](https://huggingface.co/bert-large-cased) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0546
- Precision: 0.9447
- Recall: 0.9571
- F1: 0.9508
- Accuracy: 0.9880
## 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: 3
### Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
| 0.0641 | 1.0 | 1756 | 0.0564 | 0.9248 | 0.9482 | 0.9363 | 0.9853 |
| 0.0317 | 2.0 | 3512 | 0.0531 | 0.9451 | 0.9562 | 0.9506 | 0.9880 |
| 0.0162 | 3.0 | 5268 | 0.0546 | 0.9447 | 0.9571 | 0.9508 | 0.9880 |
### Framework versions
- Transformers 4.40.0
- Pytorch 2.2.2+cpu
- Datasets 2.19.0
- Tokenizers 0.19.1
| {"license": "apache-2.0", "tags": ["generated_from_trainer"], "metrics": ["precision", "recall", "f1", "accuracy"], "base_model": "bert-large-cased", "model-index": [{"name": "bert-finetuned-ner", "results": []}]} | Lily-Tina/bert-finetuned-ner | null | [
"transformers",
"tensorboard",
"safetensors",
"bert",
"token-classification",
"generated_from_trainer",
"base_model:bert-large-cased",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | null | 2024-04-19T14:10:01+00:00 | [] | [] | TAGS
#transformers #tensorboard #safetensors #bert #token-classification #generated_from_trainer #base_model-bert-large-cased #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us
| bert-finetuned-ner
==================
This model is a fine-tuned version of bert-large-cased on an unknown dataset.
It achieves the following results on the evaluation set:
* Loss: 0.0546
* Precision: 0.9447
* Recall: 0.9571
* F1: 0.9508
* Accuracy: 0.9880
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: 3
### Training results
### Framework versions
* Transformers 4.40.0
* Pytorch 2.2.2+cpu
* Datasets 2.19.0
* Tokenizers 0.19.1
| [
"### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 2e-05\n* train\\_batch\\_size: 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: 3",
"### Training results",
"### Framework versions\n\n\n* Transformers 4.40.0\n* Pytorch 2.2.2+cpu\n* Datasets 2.19.0\n* Tokenizers 0.19.1"
] | [
"TAGS\n#transformers #tensorboard #safetensors #bert #token-classification #generated_from_trainer #base_model-bert-large-cased #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us \n",
"### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 2e-05\n* train\\_batch\\_size: 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: 3",
"### Training results",
"### Framework versions\n\n\n* Transformers 4.40.0\n* Pytorch 2.2.2+cpu\n* Datasets 2.19.0\n* Tokenizers 0.19.1"
] |
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. -->
# Mistral-7B-Instruct-v0.2-absa-restaurants
This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0280
## 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: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 2
- training_steps: 400
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 1.1197 | 0.36 | 40 | 0.1714 |
| 0.0686 | 0.72 | 80 | 0.0364 |
| 0.0294 | 1.08 | 120 | 0.0321 |
| 0.024 | 1.44 | 160 | 0.0312 |
| 0.0231 | 1.8 | 200 | 0.0279 |
| 0.0183 | 2.16 | 240 | 0.0284 |
| 0.0163 | 2.52 | 280 | 0.0281 |
| 0.0162 | 2.88 | 320 | 0.0273 |
| 0.0153 | 3.24 | 360 | 0.0271 |
| 0.0116 | 3.6 | 400 | 0.0280 |
### 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": "mistralai/Mistral-7B-Instruct-v0.2", "model-index": [{"name": "Mistral-7B-Instruct-v0.2-absa-restaurants", "results": []}]} | Shakhovak/Mistral-7B-Instruct-v0.2-absa-restaurants | null | [
"generated_from_trainer",
"base_model:mistralai/Mistral-7B-Instruct-v0.2",
"license:apache-2.0",
"region:us"
] | null | 2024-04-19T14:11:02+00:00 | [] | [] | TAGS
#generated_from_trainer #base_model-mistralai/Mistral-7B-Instruct-v0.2 #license-apache-2.0 #region-us
| Mistral-7B-Instruct-v0.2-absa-restaurants
=========================================
This model is a fine-tuned version of mistralai/Mistral-7B-Instruct-v0.2 on an unknown dataset.
It achieves the following results on the evaluation set:
* Loss: 0.0280
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: 8
* eval\_batch\_size: 8
* seed: 42
* gradient\_accumulation\_steps: 4
* total\_train\_batch\_size: 32
* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
* lr\_scheduler\_type: linear
* lr\_scheduler\_warmup\_steps: 2
* training\_steps: 400
* 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
| [
"### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 3e-05\n* train\\_batch\\_size: 8\n* eval\\_batch\\_size: 8\n* seed: 42\n* gradient\\_accumulation\\_steps: 4\n* total\\_train\\_batch\\_size: 32\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* lr\\_scheduler\\_warmup\\_steps: 2\n* training\\_steps: 400\n* mixed\\_precision\\_training: Native AMP",
"### 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-mistralai/Mistral-7B-Instruct-v0.2 #license-apache-2.0 #region-us \n",
"### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 3e-05\n* train\\_batch\\_size: 8\n* eval\\_batch\\_size: 8\n* seed: 42\n* gradient\\_accumulation\\_steps: 4\n* total\\_train\\_batch\\_size: 32\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* lr\\_scheduler\\_warmup\\_steps: 2\n* training\\_steps: 400\n* mixed\\_precision\\_training: Native AMP",
"### 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": []} | hi000000/insta_upnormal-llama-koen_100 | null | [
"transformers",
"safetensors",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null | 2024-04-19T14:11:16+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"
] |
text2text-generation | transformers |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# UrduSum7
This model is a fine-tuned version of [ahmed0189/mT5-Arabic-text-summarization](https://huggingface.co/ahmed0189/mT5-Arabic-text-summarization) on the None dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 1
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
| No log | 1.0 | 175 | 6.0928 | 0.0 | 0.0 | 0.0 | 0.0 | 40.64 |
### Framework versions
- Transformers 4.28.0
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.13.3
| {"license": "apache-2.0", "tags": ["generated_from_trainer"], "model-index": [{"name": "UrduSum7", "results": []}]} | Alefiah/UrduSum7 | null | [
"transformers",
"pytorch",
"tensorboard",
"mt5",
"text2text-generation",
"generated_from_trainer",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-04-19T14:11:50+00:00 | [] | [] | TAGS
#transformers #pytorch #tensorboard #mt5 #text2text-generation #generated_from_trainer #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us
| UrduSum7
========
This model is a fine-tuned version of ahmed0189/mT5-Arabic-text-summarization on the None dataset.
Model description
-----------------
More information needed
Intended uses & limitations
---------------------------
More information needed
Training and evaluation data
----------------------------
More information needed
Training procedure
------------------
### Training hyperparameters
The following hyperparameters were used during training:
* learning\_rate: 2e-05
* train\_batch\_size: 2
* eval\_batch\_size: 2
* seed: 42
* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
* lr\_scheduler\_type: linear
* num\_epochs: 1
* mixed\_precision\_training: Native AMP
### Training results
### Framework versions
* Transformers 4.28.0
* Pytorch 2.2.1+cu121
* Datasets 2.19.0
* Tokenizers 0.13.3
| [
"### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 2e-05\n* train\\_batch\\_size: 2\n* eval\\_batch\\_size: 2\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 1\n* mixed\\_precision\\_training: Native AMP",
"### Training results",
"### Framework versions\n\n\n* Transformers 4.28.0\n* Pytorch 2.2.1+cu121\n* Datasets 2.19.0\n* Tokenizers 0.13.3"
] | [
"TAGS\n#transformers #pytorch #tensorboard #mt5 #text2text-generation #generated_from_trainer #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n",
"### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 2e-05\n* train\\_batch\\_size: 2\n* eval\\_batch\\_size: 2\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 1\n* mixed\\_precision\\_training: Native AMP",
"### Training results",
"### Framework versions\n\n\n* Transformers 4.28.0\n* Pytorch 2.2.1+cu121\n* Datasets 2.19.0\n* Tokenizers 0.13.3"
] |
text-classification | transformers |
Multi-task fine-tune of `deberta-base-tasksource` for hate detection
| Test Name | Test Accuracy (%) | Test Pearson (%) |
|------------------------------------|-------------------|------------------|
| dynahate | 82.8 | |
| toxic_conversations | 96.0 | |
| implicit-hate-stg1 | 78.0 | |
| HatemojiBuild | 70.6 | |
| tweet_eval/hate | 55.8 | |
| oasst2_dense_flat/toxicity | | 50.996 |
| civil_comments/toxicity | | 73.046 |
| toxigen-data | | 78.217 | | {"language": ["en"], "tags": ["toxicity", "hate"], "datasets": ["skg/toxigen-data", "aps/dynahate", "HannahRoseKirk/HatemojiBuild", "mteb-pt/toxic_conversations", "OpenAssistant/oasst2"]} | sileod/deberta-v3-base-tasksource-toxicity | null | [
"transformers",
"pytorch",
"deberta-v2",
"text-classification",
"toxicity",
"hate",
"en",
"dataset:skg/toxigen-data",
"dataset:aps/dynahate",
"dataset:HannahRoseKirk/HatemojiBuild",
"dataset:mteb-pt/toxic_conversations",
"dataset:OpenAssistant/oasst2",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | null | 2024-04-19T14:12:01+00:00 | [] | [
"en"
] | TAGS
#transformers #pytorch #deberta-v2 #text-classification #toxicity #hate #en #dataset-skg/toxigen-data #dataset-aps/dynahate #dataset-HannahRoseKirk/HatemojiBuild #dataset-mteb-pt/toxic_conversations #dataset-OpenAssistant/oasst2 #autotrain_compatible #endpoints_compatible #region-us
| Multi-task fine-tune of 'deberta-base-tasksource' for hate detection
Test Name: dynahate, Test Accuracy (%): 82.8, Test Pearson (%):
Test Name: toxic\_conversations, Test Accuracy (%): 96.0, Test Pearson (%):
Test Name: implicit-hate-stg1, Test Accuracy (%): 78.0, Test Pearson (%):
Test Name: HatemojiBuild, Test Accuracy (%): 70.6, Test Pearson (%):
Test Name: tweet\_eval/hate, Test Accuracy (%): 55.8, Test Pearson (%):
Test Name: oasst2\_dense\_flat/toxicity, Test Accuracy (%): , Test Pearson (%): 50.996
Test Name: civil\_comments/toxicity, Test Accuracy (%): , Test Pearson (%): 73.046
Test Name: toxigen-data, Test Accuracy (%): , Test Pearson (%): 78.217
| [] | [
"TAGS\n#transformers #pytorch #deberta-v2 #text-classification #toxicity #hate #en #dataset-skg/toxigen-data #dataset-aps/dynahate #dataset-HannahRoseKirk/HatemojiBuild #dataset-mteb-pt/toxic_conversations #dataset-OpenAssistant/oasst2 #autotrain_compatible #endpoints_compatible #region-us \n"
] |
text-generation | transformers |
This model is randomly initialized, using the config from [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) but with smaller size.
**Note the model is in bfloat16**.
"yujiepan/llama-3-tiny-random" and "yujiepan/meta-llama-3-tiny-random" shares exactly the same files except the repo name.
Codes:
```python
import transformers
import torch
import os
from huggingface_hub import create_repo, upload_folder
import accelerate
source_model_id = 'meta-llama/Meta-Llama-3-8B-Instruct'
save_path = '/tmp/yujiepan/meta-llama-3-tiny-random'
repo_id = 'yujiepan/meta-llama-3-tiny-random'
os.system(f'rm -rf {save_path}')
config = transformers.AutoConfig.from_pretrained(
source_model_id,
trust_remote_code=True,
)
config._name_or_path = source_model_id
config.hidden_size = 4
config.intermediate_size = 14
config.num_attention_heads = 2
config.num_key_value_heads = 1
config.num_hidden_layers = 2
config.torch_dtype = "bfloat16"
model = transformers.AutoModelForCausalLM.from_config(
config,
trust_remote_code=True,
)
with accelerate.init_empty_weights():
model.generation_config = transformers.AutoModelForCausalLM.from_pretrained(source_model_id).generation_config
model = model.to(torch.bfloat16)
model.save_pretrained(save_path)
tokenizer = transformers.AutoTokenizer.from_pretrained(
source_model_id,
trust_remote_code=True,
)
tokenizer.save_pretrained(save_path)
model.float().generate(torch.tensor([[1, 2, 3]]).long(), max_length=16)
os.system(f'ls -alh {save_path}')
# os.system(f'rm -rf {save_path}/model.safetensors')
create_repo(repo_id, exist_ok=True)
upload_folder(repo_id='yujiepan/meta-llama-3-tiny-random', folder_path=save_path)
upload_folder(repo_id='yujiepan/llama-3-tiny-random', folder_path=save_path)
``` | {"library_name": "transformers", "pipeline_tag": "text-generation", "inference": true, "widget": [{"text": "Hello!", "example_title": "Hello world", "group": "Python"}]} | yujiepan/llama-3-tiny-random | null | [
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-04-19T14:12:15+00:00 | [] | [] | TAGS
#transformers #safetensors #llama #text-generation #conversational #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us
|
This model is randomly initialized, using the config from meta-llama/Meta-Llama-3-8B-Instruct but with smaller size.
Note the model is in bfloat16.
"yujiepan/llama-3-tiny-random" and "yujiepan/meta-llama-3-tiny-random" shares exactly the same files except the repo name.
Codes:
| [] | [
"TAGS\n#transformers #safetensors #llama #text-generation #conversational #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n"
] |
text-generation | transformers |
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] | {"library_name": "transformers", "tags": []} | baconnier/CIB_Banker_llama3_Instruct_8B | null | [
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-04-19T14:14:42+00:00 | [
"1910.09700"
] | [] | TAGS
#transformers #safetensors #llama #text-generation #conversational #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us
|
# Model Card for Model ID
## Model Details
### Model Description
This is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.
- Developed by:
- Funded by [optional]:
- Shared by [optional]:
- Model type:
- Language(s) (NLP):
- License:
- Finetuned from model [optional]:
### Model Sources [optional]
- Repository:
- Paper [optional]:
- Demo [optional]:
## Uses
### Direct Use
### Downstream Use [optional]
### Out-of-Scope Use
## Bias, Risks, and Limitations
### Recommendations
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
## Training Details
### Training Data
### Training Procedure
#### Preprocessing [optional]
#### Training Hyperparameters
- Training regime:
#### Speeds, Sizes, Times [optional]
## Evaluation
### Testing Data, Factors & Metrics
#### Testing Data
#### Factors
#### Metrics
### Results
#### Summary
## Model Examination [optional]
## Environmental Impact
Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).
- Hardware Type:
- Hours used:
- Cloud Provider:
- Compute Region:
- Carbon Emitted:
## Technical Specifications [optional]
### Model Architecture and Objective
### Compute Infrastructure
#### Hardware
#### Software
[optional]
BibTeX:
APA:
## Glossary [optional]
## More Information [optional]
## Model Card Authors [optional]
## Model Card Contact
| [
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.",
"## How to Get Started with the Model\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] | [
"TAGS\n#transformers #safetensors #llama #text-generation #conversational #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n",
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.",
"## How to Get Started with the Model\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] |
text-generation | transformers |
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] | {"library_name": "transformers", "tags": []} | Grayx/sad_pepe_25.0 | null | [
"transformers",
"safetensors",
"stablelm",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | null | 2024-04-19T14:15:07+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"
] |
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": "mistralai/Mistral-7B-Instruct-v0.2"} | icecream1124/Enlighten_Instruct | null | [
"peft",
"safetensors",
"arxiv:1910.09700",
"base_model:mistralai/Mistral-7B-Instruct-v0.2",
"region:us"
] | null | 2024-04-19T14:16:07+00:00 | [
"1910.09700"
] | [] | TAGS
#peft #safetensors #arxiv-1910.09700 #base_model-mistralai/Mistral-7B-Instruct-v0.2 #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-mistralai/Mistral-7B-Instruct-v0.2 #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"
] |
text-to-3d | diffusers |
This is a copy of [ashawkey/mvdream-sd2.1-diffusers](https://huggingface.co/ashawkey/mvdream-sd2.1-diffusers).
It is hosted here for persistence throughout the ML for 3D course.
# MVDream-diffusers Model Card
This is a port of https://huggingface.co/MVDream/MVDream into diffusers.
For usage, please check: https://github.com/ashawkey/mvdream_diffusers
## Citation
```
@article{shi2023MVDream,
author = {Shi, Yichun and Wang, Peng and Ye, Jianglong and Mai, Long and Li, Kejie and Yang, Xiao},
title = {MVDream: Multi-view Diffusion for 3D Generation},
journal = {arXiv:2308.16512},
year = {2023},
}
```
## Misuse, Malicious Use, and Out-of-Scope Use
The model should not be used to intentionally create or disseminate images that create hostile or alienating environments for people. This includes generating images that people would foreseeably find disturbing, distressing, or offensive; or content that propagates historical or current stereotypes.
| {"license": "openrail", "pipeline_tag": "text-to-3d"} | dylanebert/mvdream | null | [
"diffusers",
"safetensors",
"text-to-3d",
"license:openrail",
"has_space",
"diffusers:MVDreamPipeline",
"region:us"
] | null | 2024-04-19T14:17:10+00:00 | [] | [] | TAGS
#diffusers #safetensors #text-to-3d #license-openrail #has_space #diffusers-MVDreamPipeline #region-us
|
This is a copy of ashawkey/mvdream-sd2.1-diffusers.
It is hosted here for persistence throughout the ML for 3D course.
# MVDream-diffusers Model Card
This is a port of URL into diffusers.
For usage, please check: URL
## Misuse, Malicious Use, and Out-of-Scope Use
The model should not be used to intentionally create or disseminate images that create hostile or alienating environments for people. This includes generating images that people would foreseeably find disturbing, distressing, or offensive; or content that propagates historical or current stereotypes.
| [
"# MVDream-diffusers Model Card\n\nThis is a port of URL into diffusers.\n\nFor usage, please check: URL",
"## Misuse, Malicious Use, and Out-of-Scope Use\n\nThe model should not be used to intentionally create or disseminate images that create hostile or alienating environments for people. This includes generating images that people would foreseeably find disturbing, distressing, or offensive; or content that propagates historical or current stereotypes."
] | [
"TAGS\n#diffusers #safetensors #text-to-3d #license-openrail #has_space #diffusers-MVDreamPipeline #region-us \n",
"# MVDream-diffusers Model Card\n\nThis is a port of URL into diffusers.\n\nFor usage, please check: URL",
"## Misuse, Malicious Use, and Out-of-Scope Use\n\nThe model should not be used to intentionally create or disseminate images that create hostile or alienating environments for people. This includes generating images that people would foreseeably find disturbing, distressing, or offensive; or content that propagates historical or current stereotypes."
] |
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": []} | RobertML/sn666 | null | [
"transformers",
"safetensors",
"stablelm",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | null | 2024-04-19T14:19:45+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"
] |
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: 0.2730
- F1: 0.8484
## 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 |
|:-------------:|:-----:|:----:|:---------------:|:------:|
| 0.5797 | 1.0 | 191 | 0.3098 | 0.7903 |
| 0.2671 | 2.0 | 382 | 0.2658 | 0.8288 |
| 0.1856 | 3.0 | 573 | 0.2730 | 0.8484 |
### Framework versions
- Transformers 4.39.0
- Pytorch 2.2.1+cpu
- 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": []}]} | AAA01101312/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 | 2024-04-19T14:20:35+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-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: 0.2730
* F1: 0.8484
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 4.39.0
* Pytorch 2.2.1+cpu
* 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 4.39.0\n* Pytorch 2.2.1+cpu\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 4.39.0\n* Pytorch 2.2.1+cpu\n* Datasets 2.18.0\n* Tokenizers 0.15.2"
] |
null | null |
# Experiment26Meliodaspercival_01_experiment26t3q-7B
Experiment26Meliodaspercival_01_experiment26t3q-7B is an automated merge created by [Maxime Labonne](https://huggingface.co/mlabonne) using the following configuration.
## 🧩 Configuration
```yaml
models:
- model: mistralai/Mistral-7B-v0.1
- model: yam-peleg/Experiment26-7B
- model: MaziyarPanahi/MeliodasPercival_01_Experiment26T3q
merge_method: model_stock
base_model: mistralai/Mistral-7B-v0.1
dtype: bfloat16
```
## 💻 Usage
```python
!pip install -qU transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "automerger/Experiment26Meliodaspercival_01_experiment26t3q-7B"
messages = [{"role": "user", "content": "What is a large language model?"}]
tokenizer = AutoTokenizer.from_pretrained(model)
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
pipeline = transformers.pipeline(
"text-generation",
model=model,
torch_dtype=torch.float16,
device_map="auto",
)
outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])
``` | {"license": "apache-2.0", "tags": ["merge", "mergekit", "lazymergekit", "automerger"]} | automerger/Experiment26Meliodaspercival_01_experiment26t3q-7B | null | [
"merge",
"mergekit",
"lazymergekit",
"automerger",
"license:apache-2.0",
"region:us"
] | null | 2024-04-19T14:20:48+00:00 | [] | [] | TAGS
#merge #mergekit #lazymergekit #automerger #license-apache-2.0 #region-us
|
# Experiment26Meliodaspercival_01_experiment26t3q-7B
Experiment26Meliodaspercival_01_experiment26t3q-7B is an automated merge created by Maxime Labonne using the following configuration.
## Configuration
## Usage
| [
"# Experiment26Meliodaspercival_01_experiment26t3q-7B\n\nExperiment26Meliodaspercival_01_experiment26t3q-7B is an automated merge created by Maxime Labonne using the following configuration.",
"## Configuration",
"## Usage"
] | [
"TAGS\n#merge #mergekit #lazymergekit #automerger #license-apache-2.0 #region-us \n",
"# Experiment26Meliodaspercival_01_experiment26t3q-7B\n\nExperiment26Meliodaspercival_01_experiment26t3q-7B is an automated merge created by Maxime Labonne using the following configuration.",
"## Configuration",
"## Usage"
] |
null | transformers |
# Uploaded model
- **Developed by:** MR-Eder
- **License:** apache-2.0
- **Finetuned from model :** unsloth/llama-3-8b-Instruct-bnb-4bit
This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
| {"language": ["en"], "license": "apache-2.0", "tags": ["text-generation-inference", "transformers", "unsloth", "llama", "trl"], "base_model": "unsloth/llama-3-8b-Instruct-bnb-4bit"} | MR-Eder/llama3-1000-steps-wiki-de-conversation-lora | null | [
"transformers",
"safetensors",
"text-generation-inference",
"unsloth",
"llama",
"trl",
"en",
"base_model:unsloth/llama-3-8b-Instruct-bnb-4bit",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | 2024-04-19T14:22:50+00:00 | [] | [
"en"
] | TAGS
#transformers #safetensors #text-generation-inference #unsloth #llama #trl #en #base_model-unsloth/llama-3-8b-Instruct-bnb-4bit #license-apache-2.0 #endpoints_compatible #region-us
|
# Uploaded model
- Developed by: MR-Eder
- License: apache-2.0
- Finetuned from model : unsloth/llama-3-8b-Instruct-bnb-4bit
This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.
<img src="URL width="200"/>
| [
"# Uploaded model\n\n- Developed by: MR-Eder\n- License: apache-2.0\n- Finetuned from model : unsloth/llama-3-8b-Instruct-bnb-4bit\n\nThis llama model was trained 2x faster with Unsloth and Huggingface's TRL library.\n\n<img src=\"URL width=\"200\"/>"
] | [
"TAGS\n#transformers #safetensors #text-generation-inference #unsloth #llama #trl #en #base_model-unsloth/llama-3-8b-Instruct-bnb-4bit #license-apache-2.0 #endpoints_compatible #region-us \n",
"# Uploaded model\n\n- Developed by: MR-Eder\n- License: apache-2.0\n- Finetuned from model : unsloth/llama-3-8b-Instruct-bnb-4bit\n\nThis llama model was trained 2x faster with Unsloth and Huggingface's TRL library.\n\n<img src=\"URL width=\"200\"/>"
] |
null | transformers |
# Uploaded model
- **Developed by:** coralexbadea
- **License:** apache-2.0
- **Finetuned from model :** unsloth/llama-3-8b-bnb-4bit
This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
| {"language": ["en"], "license": "apache-2.0", "tags": ["text-generation-inference", "transformers", "unsloth", "llama", "trl"], "base_model": "unsloth/llama-3-8b-bnb-4bit"} | coralexbadea/llama3-sql-adapter | null | [
"transformers",
"safetensors",
"text-generation-inference",
"unsloth",
"llama",
"trl",
"en",
"base_model:unsloth/llama-3-8b-bnb-4bit",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | 2024-04-19T14:23:02+00:00 | [] | [
"en"
] | TAGS
#transformers #safetensors #text-generation-inference #unsloth #llama #trl #en #base_model-unsloth/llama-3-8b-bnb-4bit #license-apache-2.0 #endpoints_compatible #region-us
|
# Uploaded model
- Developed by: coralexbadea
- License: apache-2.0
- Finetuned from model : unsloth/llama-3-8b-bnb-4bit
This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.
<img src="URL width="200"/>
| [
"# Uploaded model\n\n- Developed by: coralexbadea\n- License: apache-2.0\n- Finetuned from model : unsloth/llama-3-8b-bnb-4bit\n\nThis llama model was trained 2x faster with Unsloth and Huggingface's TRL library.\n\n<img src=\"URL width=\"200\"/>"
] | [
"TAGS\n#transformers #safetensors #text-generation-inference #unsloth #llama #trl #en #base_model-unsloth/llama-3-8b-bnb-4bit #license-apache-2.0 #endpoints_compatible #region-us \n",
"# Uploaded model\n\n- Developed by: coralexbadea\n- License: apache-2.0\n- Finetuned from model : unsloth/llama-3-8b-bnb-4bit\n\nThis llama model was trained 2x faster with Unsloth and Huggingface's TRL library.\n\n<img src=\"URL width=\"200\"/>"
] |
null | transformers |
- **Developed by:** Shekswess
- **License:** apache-2.0
- **Finetuned from model :** unsloth/llama-3-8b-Instruct-bnb-4bit
To utilize the fine-tuning of the model, you need to use the gemma instruction prompt template for this medical version of the model:
```
<|start_header_id|>system<|end_header_id|> Answer the question truthfully, you are a medical professional.<|eot_id|><|start_header_id|>user<|end_header_id|> This is the question: {question}?<|eot_id|>
```
Metrics:
- train_runtime: 2083.0086
- train_samples_per_second: 0.96
- train_steps_per_second: 0.12
- total_flos: 2.928942377774285e+16
- train_loss: 1.228120258331299
- steps: 250
- epoch: 1.0
 | {"language": ["en"], "license": "apache-2.0", "tags": ["text-generation-inference", "transformers", "unsloth", "llama", "trl", "medical"], "datasets": ["Shekswess/medical_llama3_instruct_dataset_short"], "base_model": "unsloth/llama-3-8b-Instruct-bnb-4bit"} | Shekswess/llama-3-8b-Instruct-bnb-4bit-medical | null | [
"transformers",
"safetensors",
"text-generation-inference",
"unsloth",
"llama",
"trl",
"medical",
"en",
"dataset:Shekswess/medical_llama3_instruct_dataset_short",
"base_model:unsloth/llama-3-8b-Instruct-bnb-4bit",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | 2024-04-19T14:23:05+00:00 | [] | [
"en"
] | TAGS
#transformers #safetensors #text-generation-inference #unsloth #llama #trl #medical #en #dataset-Shekswess/medical_llama3_instruct_dataset_short #base_model-unsloth/llama-3-8b-Instruct-bnb-4bit #license-apache-2.0 #endpoints_compatible #region-us
|
- Developed by: Shekswess
- License: apache-2.0
- Finetuned from model : unsloth/llama-3-8b-Instruct-bnb-4bit
To utilize the fine-tuning of the model, you need to use the gemma instruction prompt template for this medical version of the model:
Metrics:
- train_runtime: 2083.0086
- train_samples_per_second: 0.96
- train_steps_per_second: 0.12
- total_flos: 2.928942377774285e+16
- train_loss: 1.228120258331299
- steps: 250
- epoch: 1.0
!image/png | [] | [
"TAGS\n#transformers #safetensors #text-generation-inference #unsloth #llama #trl #medical #en #dataset-Shekswess/medical_llama3_instruct_dataset_short #base_model-unsloth/llama-3-8b-Instruct-bnb-4bit #license-apache-2.0 #endpoints_compatible #region-us \n"
] |
null | transformers |
# Uploaded model
- **Developed by:** Raul569
- **License:** apache-2.0
- **Finetuned from model :** unsloth/llama-3-8b-bnb-4bit
This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
| {"language": ["en"], "license": "apache-2.0", "tags": ["text-generation-inference", "transformers", "unsloth", "llama", "trl"], "base_model": "unsloth/llama-3-8b-bnb-4bit"} | Raul569/lora_outfit_recommender_model | null | [
"transformers",
"safetensors",
"text-generation-inference",
"unsloth",
"llama",
"trl",
"en",
"base_model:unsloth/llama-3-8b-bnb-4bit",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | 2024-04-19T14:26:09+00:00 | [] | [
"en"
] | TAGS
#transformers #safetensors #text-generation-inference #unsloth #llama #trl #en #base_model-unsloth/llama-3-8b-bnb-4bit #license-apache-2.0 #endpoints_compatible #region-us
|
# Uploaded model
- Developed by: Raul569
- License: apache-2.0
- Finetuned from model : unsloth/llama-3-8b-bnb-4bit
This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.
<img src="URL width="200"/>
| [
"# Uploaded model\n\n- Developed by: Raul569\n- License: apache-2.0\n- Finetuned from model : unsloth/llama-3-8b-bnb-4bit\n\nThis llama model was trained 2x faster with Unsloth and Huggingface's TRL library.\n\n<img src=\"URL width=\"200\"/>"
] | [
"TAGS\n#transformers #safetensors #text-generation-inference #unsloth #llama #trl #en #base_model-unsloth/llama-3-8b-bnb-4bit #license-apache-2.0 #endpoints_compatible #region-us \n",
"# Uploaded model\n\n- Developed by: Raul569\n- License: apache-2.0\n- Finetuned from model : unsloth/llama-3-8b-bnb-4bit\n\nThis llama model was trained 2x faster with Unsloth and Huggingface's TRL library.\n\n<img src=\"URL width=\"200\"/>"
] |
document-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": []} | Resi/layfi-v1-docvqa | null | [
"transformers",
"safetensors",
"layoutlmv2",
"document-question-answering",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null | 2024-04-19T14:29:17+00:00 | [
"1910.09700"
] | [] | TAGS
#transformers #safetensors #layoutlmv2 #document-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 #layoutlmv2 #document-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"
] |
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/Meta-Llama-3-8B-Instruct](https://huggingface.co/NousResearch/Meta-Llama-3-8B-Instruct)
* [NotAiLOL/Meta-Llama-3-8B-Instruct](https://huggingface.co/NotAiLOL/Meta-Llama-3-8B-Instruct)
### Configuration
The following YAML configuration was used to produce this model:
```yaml
slices:
- sources:
- model: NousResearch/Meta-Llama-3-8B-Instruct
layer_range:
- 0
- 32
- model: NotAiLOL/Meta-Llama-3-8B-Instruct
layer_range:
- 0
- 32
merge_method: slerp
base_model: NousResearch/Meta-Llama-3-8B-Instruct
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: float16
``` | {"license": "apache-2.0", "library_name": "transformers", "tags": ["mergekit", "merge"], "base_model": ["NousResearch/Meta-Llama-3-8B-Instruct", "NotAiLOL/Meta-Llama-3-8B-Instruct"]} | NotAiLOL/Boundary-Meta-Llama-3-2x | null | [
"transformers",
"safetensors",
"llama",
"text-generation",
"mergekit",
"merge",
"conversational",
"base_model:NousResearch/Meta-Llama-3-8B-Instruct",
"base_model:NotAiLOL/Meta-Llama-3-8B-Instruct",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-04-19T14:31:32+00:00 | [] | [] | TAGS
#transformers #safetensors #llama #text-generation #mergekit #merge #conversational #base_model-NousResearch/Meta-Llama-3-8B-Instruct #base_model-NotAiLOL/Meta-Llama-3-8B-Instruct #license-apache-2.0 #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/Meta-Llama-3-8B-Instruct
* NotAiLOL/Meta-Llama-3-8B-Instruct
### 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/Meta-Llama-3-8B-Instruct\n* NotAiLOL/Meta-Llama-3-8B-Instruct",
"### Configuration\n\nThe following YAML configuration was used to produce this model:"
] | [
"TAGS\n#transformers #safetensors #llama #text-generation #mergekit #merge #conversational #base_model-NousResearch/Meta-Llama-3-8B-Instruct #base_model-NotAiLOL/Meta-Llama-3-8B-Instruct #license-apache-2.0 #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/Meta-Llama-3-8B-Instruct\n* NotAiLOL/Meta-Llama-3-8B-Instruct",
"### Configuration\n\nThe following YAML configuration was used to produce this model:"
] |
null | transformers |
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] | {"library_name": "transformers", "tags": []} | wendy41/llama-2-koen-user0-100 | null | [
"transformers",
"safetensors",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null | 2024-04-19T14:31:41+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 | How to run the model ?
# Load base model
model = AutoModelForCausalLM.from_pretrained(
"Tapan101/Llama-2-7b-Medical-chat-finetune"
)
# Load LLaMA tokenizer
tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
tokenizer.pad_token = tokenizer.eos_token
tokenizer.padding_side = "right" # Fix weird overflow issue with fp16 training
import logging
from transformers import pipeline
# Suppress warning messages
logging.getLogger("transformers.generation_utils").setLevel(logging.ERROR)
# Run text generation pipeline with our next model
prompt = "What is dance therapy ?"
#How does dysmenorrhea is diagnosised through allopathic
pipe = pipeline(task="text-generation", model=model, tokenizer=tokenizer, max_length=200)
result = pipe(f"<s>[INST] {prompt} [/INST]")
generated_text = result[0]
print(generated_text) | {} | Tapan101/Llama-2-7b-Medical-chat-finetune | null | [
"transformers",
"pytorch",
"llama",
"text-generation",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-04-19T14:31:53+00:00 | [] | [] | TAGS
#transformers #pytorch #llama #text-generation #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us
| How to run the model ?
# Load base model
model = AutoModelForCausalLM.from_pretrained(
"Tapan101/Llama-2-7b-Medical-chat-finetune"
)
# Load LLaMA tokenizer
tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
tokenizer.pad_token = tokenizer.eos_token
tokenizer.padding_side = "right" # Fix weird overflow issue with fp16 training
import logging
from transformers import pipeline
# Suppress warning messages
logging.getLogger("transformers.generation_utils").setLevel(logging.ERROR)
# Run text generation pipeline with our next model
prompt = "What is dance therapy ?"
#How does dysmenorrhea is diagnosised through allopathic
pipe = pipeline(task="text-generation", model=model, tokenizer=tokenizer, max_length=200)
result = pipe(f"<s>[INST] {prompt} [/INST]")
generated_text = result[0]
print(generated_text) | [
"# Load base model\nmodel = AutoModelForCausalLM.from_pretrained(\n \"Tapan101/Llama-2-7b-Medical-chat-finetune\"\n)",
"# Load LLaMA tokenizer\ntokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)\ntokenizer.pad_token = tokenizer.eos_token\ntokenizer.padding_side = \"right\" # Fix weird overflow issue with fp16 training\n\nimport logging\nfrom transformers import pipeline",
"# Suppress warning messages\nlogging.getLogger(\"transformers.generation_utils\").setLevel(logging.ERROR)",
"# Run text generation pipeline with our next model\nprompt = \"What is dance therapy ?\""
] | [
"TAGS\n#transformers #pytorch #llama #text-generation #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n",
"# Load base model\nmodel = AutoModelForCausalLM.from_pretrained(\n \"Tapan101/Llama-2-7b-Medical-chat-finetune\"\n)",
"# Load LLaMA tokenizer\ntokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)\ntokenizer.pad_token = tokenizer.eos_token\ntokenizer.padding_side = \"right\" # Fix weird overflow issue with fp16 training\n\nimport logging\nfrom transformers import pipeline",
"# Suppress warning messages\nlogging.getLogger(\"transformers.generation_utils\").setLevel(logging.ERROR)",
"# Run text generation pipeline with our next model\nprompt = \"What is dance therapy ?\""
] |
text-classification | transformers |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# robust_llm_pythia-160m_ian-022_PasswordMatch_n-its-10
This model is a fine-tuned version of [EleutherAI/pythia-160m](https://huggingface.co/EleutherAI/pythia-160m) on an unknown dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 8
- eval_batch_size: 64
- seed: 0
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 1
### Training results
### Framework versions
- Transformers 4.39.3
- Pytorch 2.2.1
- Datasets 2.18.0
- Tokenizers 0.15.2
| {"license": "apache-2.0", "tags": ["generated_from_trainer"], "base_model": "EleutherAI/pythia-160m", "model-index": [{"name": "robust_llm_pythia-160m_ian-022_PasswordMatch_n-its-10", "results": []}]} | AlignmentResearch/robust_llm_pythia-160m_ian-022_PasswordMatch_n-its-10 | null | [
"transformers",
"tensorboard",
"safetensors",
"gpt_neox",
"text-classification",
"generated_from_trainer",
"base_model:EleutherAI/pythia-160m",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-04-19T14:32:35+00:00 | [] | [] | TAGS
#transformers #tensorboard #safetensors #gpt_neox #text-classification #generated_from_trainer #base_model-EleutherAI/pythia-160m #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us
|
# robust_llm_pythia-160m_ian-022_PasswordMatch_n-its-10
This model is a fine-tuned version of EleutherAI/pythia-160m on an unknown dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 8
- eval_batch_size: 64
- seed: 0
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 1
### Training results
### Framework versions
- Transformers 4.39.3
- Pytorch 2.2.1
- Datasets 2.18.0
- Tokenizers 0.15.2
| [
"# robust_llm_pythia-160m_ian-022_PasswordMatch_n-its-10\n\nThis model is a fine-tuned version of EleutherAI/pythia-160m on an unknown dataset.",
"## Model description\n\nMore information needed",
"## Intended uses & limitations\n\nMore information needed",
"## Training and evaluation data\n\nMore information needed",
"## Training procedure",
"### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 1e-05\n- train_batch_size: 8\n- eval_batch_size: 64\n- seed: 0\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 1",
"### Training results",
"### Framework versions\n\n- Transformers 4.39.3\n- Pytorch 2.2.1\n- Datasets 2.18.0\n- Tokenizers 0.15.2"
] | [
"TAGS\n#transformers #tensorboard #safetensors #gpt_neox #text-classification #generated_from_trainer #base_model-EleutherAI/pythia-160m #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n",
"# robust_llm_pythia-160m_ian-022_PasswordMatch_n-its-10\n\nThis model is a fine-tuned version of EleutherAI/pythia-160m on an unknown dataset.",
"## Model description\n\nMore information needed",
"## Intended uses & limitations\n\nMore information needed",
"## Training and evaluation data\n\nMore information needed",
"## Training procedure",
"### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 1e-05\n- train_batch_size: 8\n- eval_batch_size: 64\n- seed: 0\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 1",
"### Training results",
"### Framework versions\n\n- Transformers 4.39.3\n- Pytorch 2.2.1\n- Datasets 2.18.0\n- Tokenizers 0.15.2"
] |
text-generation | transformers | # frankenllama-16b
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
This is my personal frankenmerge of llama-3-8B after a light and unintentional tuning for 3 epochs on the noro dataset in Alpaca format. I have yet to test it or further tune it. So please don't take it too seriously.
## Merge Details
### Merge Method
This model was merged using the passthrough merge method.
### Models Merged
The following models were included in the merge:
* reallad/llama-3-8b-alpaca-noro
### Configuration
The following YAML configuration was used to produce this model:
```yaml
slices:
- sources:
- model: reallad/llama-3-8b-alpaca-noro
layer_range: [0,32]
- sources:
- model: reallad/llama-3-8b-alpaca-noro
layer_range: [0,32]
merge_method: passthrough
dtype: bfloat16
tokenizer_source: base
```
| {"library_name": "transformers", "tags": ["mergekit", "merge"], "base_model": []} | reallad/frankenllama-16b-alpaca-noro | null | [
"transformers",
"safetensors",
"llama",
"text-generation",
"mergekit",
"merge",
"conversational",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-04-19T14:35:37+00:00 | [] | [] | TAGS
#transformers #safetensors #llama #text-generation #mergekit #merge #conversational #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us
| # frankenllama-16b
This is a merge of pre-trained language models created using mergekit.
This is my personal frankenmerge of llama-3-8B after a light and unintentional tuning for 3 epochs on the noro dataset in Alpaca format. I have yet to test it or further tune it. So please don't take it too seriously.
## Merge Details
### Merge Method
This model was merged using the passthrough merge method.
### Models Merged
The following models were included in the merge:
* reallad/llama-3-8b-alpaca-noro
### Configuration
The following YAML configuration was used to produce this model:
| [
"# frankenllama-16b\n\nThis is a merge of pre-trained language models created using mergekit.\n\nThis is my personal frankenmerge of llama-3-8B after a light and unintentional tuning for 3 epochs on the noro dataset in Alpaca format. I have yet to test it or further tune it. So please don't take it too seriously.",
"## Merge Details",
"### Merge Method\n\nThis model was merged using the passthrough merge method.",
"### Models Merged\n\nThe following models were included in the merge:\n* reallad/llama-3-8b-alpaca-noro",
"### Configuration\n\nThe following YAML configuration was used to produce this model:"
] | [
"TAGS\n#transformers #safetensors #llama #text-generation #mergekit #merge #conversational #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n",
"# frankenllama-16b\n\nThis is a merge of pre-trained language models created using mergekit.\n\nThis is my personal frankenmerge of llama-3-8B after a light and unintentional tuning for 3 epochs on the noro dataset in Alpaca format. I have yet to test it or further tune it. So please don't take it too seriously.",
"## Merge Details",
"### Merge Method\n\nThis model was merged using the passthrough merge method.",
"### Models Merged\n\nThe following models were included in the merge:\n* reallad/llama-3-8b-alpaca-noro",
"### Configuration\n\nThe following YAML configuration was used to produce this model:"
] |
null | transformers |
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] | {"library_name": "transformers", "tags": []} | slimaneMakh/Multilang_tableClassification-TripletTsdaecorpogplparamulti-peft-lora | null | [
"transformers",
"safetensors",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null | 2024-04-19T14:36:36+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 | mlx |
# mlx-community/Meta-Llama-3-70B-Instruct-8bit
This model was converted to MLX format from [`meta-llama/Meta-Llama-3-70B-Instruct`]() using mlx-lm version **0.10.0**.
Refer to the [original model card](https://huggingface.co/meta-llama/Meta-Llama-3-70B-Instruct) for more details on the model.
## Use with mlx
```bash
pip install mlx-lm
```
```python
from mlx_lm import load, generate
model, tokenizer = load("mlx-community/Meta-Llama-3-70B-Instruct-8bit")
response = generate(model, tokenizer, prompt="hello", verbose=True)
```
| {"language": ["en"], "license": "other", "tags": ["facebook", "meta", "pytorch", "llama", "llama-3", "mlx"], "pipeline_tag": "text-generation", "license_name": "llama3", "license_link": "LICENSE", "extra_gated_prompt": "### META LLAMA 3 COMMUNITY LICENSE AGREEMENT\nMeta Llama 3 Version Release Date: April 18, 2024\n\"Agreement\" means the terms and conditions for use, reproduction, distribution and modification of the Llama Materials set forth herein.\n\"Documentation\" means the specifications, manuals and documentation accompanying Meta Llama 3 distributed by Meta at https://llama.meta.com/get-started/.\n\"Licensee\" or \"you\" means you, or your employer or any other person or entity (if you are entering into this Agreement on such person or entity\u2019s behalf), of the age required under applicable laws, rules or regulations to provide legal consent and that has legal authority to bind your employer or such other person or entity if you are entering in this Agreement on their behalf.\n\"Meta Llama 3\" means the foundational large language models and software and algorithms, including machine-learning model code, trained model weights, inference-enabling code, training-enabling code, fine-tuning enabling code and other elements of the foregoing distributed by Meta at https://llama.meta.com/llama-downloads.\n\"Llama Materials\" means, collectively, Meta\u2019s proprietary Meta Llama 3 and Documentation (and any portion thereof) made available under this Agreement.\n\"Meta\" or \"we\" means Meta Platforms Ireland Limited (if you are located in or, if you are an entity, your principal place of business is in the EEA or Switzerland) and Meta Platforms, Inc. (if you are located outside of the EEA or Switzerland).\n \n1. License Rights and Redistribution.\na. Grant of Rights. You are granted a non-exclusive, worldwide, non-transferable and royalty-free limited license under Meta\u2019s intellectual property or other rights owned by Meta embodied in the Llama Materials to use, reproduce, distribute, copy, create derivative works of, and make modifications to the Llama Materials.\nb. Redistribution and Use.\ni. If you distribute or make available the Llama Materials (or any derivative works thereof), or a product or service that uses any of them, including another AI model, you shall (A) provide a copy of this Agreement with any such Llama Materials; and (B) prominently display \u201cBuilt with Meta Llama 3\u201d on a related website, user interface, blogpost, about page, or product documentation. If you use the Llama Materials to create, train, fine tune, or otherwise improve an AI model, which is distributed or made available, you shall also include \u201cLlama 3\u201d at the beginning of any such AI model name.\nii. If you receive Llama Materials, or any derivative works thereof, from a Licensee as part of an integrated end user product, then Section 2 of this Agreement will not apply to you.\niii. You must retain in all copies of the Llama Materials that you distribute the following attribution notice within a \u201cNotice\u201d text file distributed as a part of such copies: \u201cMeta Llama 3 is licensed under the Meta Llama 3 Community License, Copyright \u00a9 Meta Platforms, Inc. All Rights Reserved.\u201d\niv. Your use of the Llama Materials must comply with applicable laws and regulations (including trade compliance laws and regulations) and adhere to the Acceptable Use Policy for the Llama Materials (available at https://llama.meta.com/llama3/use-policy), which is hereby incorporated by reference into this Agreement.\nv. You will not use the Llama Materials or any output or results of the Llama Materials to improve any other large language model (excluding Meta Llama 3 or derivative works thereof).\n2. Additional Commercial Terms. If, on the Meta Llama 3 version release date, the monthly active users of the products or services made available by or for Licensee, or Licensee\u2019s affiliates, is greater than 700 million monthly active users in the preceding calendar month, you must request a license from Meta, which Meta may grant to you in its sole discretion, and you are not authorized to exercise any of the rights under this Agreement unless or until Meta otherwise expressly grants you such rights.\n3. Disclaimer of Warranty. UNLESS REQUIRED BY APPLICABLE LAW, THE LLAMA MATERIALS AND ANY OUTPUT AND RESULTS THEREFROM ARE PROVIDED ON AN \u201cAS IS\u201d BASIS, WITHOUT WARRANTIES OF ANY KIND, AND META DISCLAIMS ALL WARRANTIES OF ANY KIND, BOTH EXPRESS AND IMPLIED, INCLUDING, WITHOUT LIMITATION, ANY WARRANTIES OF TITLE, NON-INFRINGEMENT, MERCHANTABILITY, OR FITNESS FOR A PARTICULAR PURPOSE. YOU ARE SOLELY RESPONSIBLE FOR DETERMINING THE APPROPRIATENESS OF USING OR REDISTRIBUTING THE LLAMA MATERIALS AND ASSUME ANY RISKS ASSOCIATED WITH YOUR USE OF THE LLAMA MATERIALS AND ANY OUTPUT AND RESULTS.\n4. Limitation of Liability. IN NO EVENT WILL META OR ITS AFFILIATES BE LIABLE UNDER ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, TORT, NEGLIGENCE, PRODUCTS LIABILITY, OR OTHERWISE, ARISING OUT OF THIS AGREEMENT, FOR ANY LOST PROFITS OR ANY INDIRECT, SPECIAL, CONSEQUENTIAL, INCIDENTAL, EXEMPLARY OR PUNITIVE DAMAGES, EVEN IF META OR ITS AFFILIATES HAVE BEEN ADVISED OF THE POSSIBILITY OF ANY OF THE FOREGOING.\n5. Intellectual Property.\na. No trademark licenses are granted under this Agreement, and in connection with the Llama Materials, neither Meta nor Licensee may use any name or mark owned by or associated with the other or any of its affiliates, except as required for reasonable and customary use in describing and redistributing the Llama Materials or as set forth in this Section 5(a). Meta hereby grants you a license to use \u201cLlama 3\u201d (the \u201cMark\u201d) solely as required to comply with the last sentence of Section 1.b.i. You will comply with Meta\u2019s brand guidelines (currently accessible at https://about.meta.com/brand/resources/meta/company-brand/ ). All goodwill arising out of your use of the Mark will inure to the benefit of Meta.\nb. Subject to Meta\u2019s ownership of Llama Materials and derivatives made by or for Meta, with respect to any derivative works and modifications of the Llama Materials that are made by you, as between you and Meta, you are and will be the owner of such derivative works and modifications.\nc. If you institute litigation or other proceedings against Meta or any entity (including a cross-claim or counterclaim in a lawsuit) alleging that the Llama Materials or Meta Llama 3 outputs or results, or any portion of any of the foregoing, constitutes infringement of intellectual property or other rights owned or licensable by you, then any licenses granted to you under this Agreement shall terminate as of the date such litigation or claim is filed or instituted. You will indemnify and hold harmless Meta from and against any claim by any third party arising out of or related to your use or distribution of the Llama Materials.\n6. Term and Termination. The term of this Agreement will commence upon your acceptance of this Agreement or access to the Llama Materials and will continue in full force and effect until terminated in accordance with the terms and conditions herein. Meta may terminate this Agreement if you are in breach of any term or condition of this Agreement. Upon termination of this Agreement, you shall delete and cease use of the Llama Materials. Sections 3, 4 and 7 shall survive the termination of this Agreement.\n7. Governing Law and Jurisdiction. This Agreement will be governed and construed under the laws of the State of California without regard to choice of law principles, and the UN Convention on Contracts for the International Sale of Goods does not apply to this Agreement. The courts of California shall have exclusive jurisdiction of any dispute arising out of this Agreement.\n### Meta Llama 3 Acceptable Use Policy\nMeta is committed to promoting safe and fair use of its tools and features, including Meta Llama 3. If you access or use Meta Llama 3, you agree to this Acceptable Use Policy (\u201cPolicy\u201d). The most recent copy of this policy can be found at [https://llama.meta.com/llama3/use-policy](https://llama.meta.com/llama3/use-policy)\n#### Prohibited Uses\nWe want everyone to use Meta Llama 3 safely and responsibly. You agree you will not use, or allow others to use, Meta Llama 3 to: 1. Violate the law or others\u2019 rights, including to:\n 1. Engage in, promote, generate, contribute to, encourage, plan, incite, or further illegal or unlawful activity or content, such as:\n 1. Violence or terrorism\n 2. Exploitation or harm to children, including the solicitation, creation, acquisition, or dissemination of child exploitative content or failure to report Child Sexual Abuse Material\n 3. Human trafficking, exploitation, and sexual violence\n 4. The illegal distribution of information or materials to minors, including obscene materials, or failure to employ legally required age-gating in connection with such information or materials.\n 5. Sexual solicitation\n 6. Any other criminal activity\n 2. Engage in, promote, incite, or facilitate the harassment, abuse, threatening, or bullying of individuals or groups of individuals\n 3. Engage in, promote, incite, or facilitate discrimination or other unlawful or harmful conduct in the provision of employment, employment benefits, credit, housing, other economic benefits, or other essential goods and services\n 4. Engage in the unauthorized or unlicensed practice of any profession including, but not limited to, financial, legal, medical/health, or related professional practices\n 5. Collect, process, disclose, generate, or infer health, demographic, or other sensitive personal or private information about individuals without rights and consents required by applicable laws\n 6. Engage in or facilitate any action or generate any content that infringes, misappropriates, or otherwise violates any third-party rights, including the outputs or results of any products or services using the Llama Materials\n 7. Create, generate, or facilitate the creation of malicious code, malware, computer viruses or do anything else that could disable, overburden, interfere with or impair the proper working, integrity, operation or appearance of a website or computer system\n2. Engage in, promote, incite, facilitate, or assist in the planning or development of activities that present a risk of death or bodily harm to individuals, including use of Meta Llama 3 related to the following:\n 1. Military, warfare, nuclear industries or applications, espionage, use for materials or activities that are subject to the International Traffic Arms Regulations (ITAR) maintained by the United States Department of State\n 2. Guns and illegal weapons (including weapon development)\n 3. Illegal drugs and regulated/controlled substances\n 4. Operation of critical infrastructure, transportation technologies, or heavy machinery\n 5. Self-harm or harm to others, including suicide, cutting, and eating disorders\n 6. Any content intended to incite or promote violence, abuse, or any infliction of bodily harm to an individual\n3. Intentionally deceive or mislead others, including use of Meta Llama 3 related to the following:\n 1. Generating, promoting, or furthering fraud or the creation or promotion of disinformation\n 2. Generating, promoting, or furthering defamatory content, including the creation of defamatory statements, images, or other content\n 3. Generating, promoting, or further distributing spam\n 4. Impersonating another individual without consent, authorization, or legal right\n 5. Representing that the use of Meta Llama 3 or outputs are human-generated\n 6. Generating or facilitating false online engagement, including fake reviews and other means of fake online engagement\n4. Fail to appropriately disclose to end users any known dangers of your AI system\nPlease report any violation of this Policy, software \u201cbug,\u201d or other problems that could lead to a violation of this Policy through one of the following means:\n * Reporting issues with the model: [https://github.com/meta-llama/llama3](https://github.com/meta-llama/llama3)\n * Reporting risky content generated by the model:\n developers.facebook.com/llama_output_feedback\n * Reporting bugs and security concerns: facebook.com/whitehat/info\n * Reporting violations of the Acceptable Use Policy or unlicensed uses of Meta Llama 3: [email protected]", "extra_gated_fields": {"First Name": "text", "Last Name": "text", "Date of birth": "date_picker", "Country": "country", "Affiliation": "text", "geo": "ip_location", "By clicking Submit below I accept the terms of the license and acknowledge that the information I provide will be collected stored processed and shared in accordance with the Meta Privacy Policy": "checkbox"}, "extra_gated_description": "The information you provide will be collected, stored, processed and shared in accordance with the [Meta Privacy Policy](https://www.facebook.com/privacy/policy/).", "extra_gated_button_content": "Submit", "widget": [{"example_title": "Winter holidays", "messages": [{"role": "system", "content": "You are a helpful and honest assistant. Please, respond concisely and truthfully."}, {"role": "user", "content": "Can you recommend a good destination for Winter holidays?"}]}, {"example_title": "Programming assistant", "messages": [{"role": "system", "content": "You are a helpful and honest code and programming assistant. Please, respond concisely and truthfully."}, {"role": "user", "content": "Write a function that computes the nth fibonacci number."}]}], "inference": {"parameters": {"max_new_tokens": 300, "stop": ["<|end_of_text|>", "<|eot_id|>"]}}} | mlx-community/Meta-Llama-3-70B-Instruct-8bit | null | [
"mlx",
"safetensors",
"llama",
"facebook",
"meta",
"pytorch",
"llama-3",
"text-generation",
"conversational",
"en",
"license:other",
"has_space",
"region:us"
] | null | 2024-04-19T14:38:12+00:00 | [] | [
"en"
] | TAGS
#mlx #safetensors #llama #facebook #meta #pytorch #llama-3 #text-generation #conversational #en #license-other #has_space #region-us
|
# mlx-community/Meta-Llama-3-70B-Instruct-8bit
This model was converted to MLX format from ['meta-llama/Meta-Llama-3-70B-Instruct']() using mlx-lm version 0.10.0.
Refer to the original model card for more details on the model.
## Use with mlx
| [
"# mlx-community/Meta-Llama-3-70B-Instruct-8bit\nThis model was converted to MLX format from ['meta-llama/Meta-Llama-3-70B-Instruct']() using mlx-lm version 0.10.0.\nRefer to the original model card for more details on the model.",
"## Use with mlx"
] | [
"TAGS\n#mlx #safetensors #llama #facebook #meta #pytorch #llama-3 #text-generation #conversational #en #license-other #has_space #region-us \n",
"# mlx-community/Meta-Llama-3-70B-Instruct-8bit\nThis model was converted to MLX format from ['meta-llama/Meta-Llama-3-70B-Instruct']() using mlx-lm version 0.10.0.\nRefer to the original model card for more details on the model.",
"## Use with mlx"
] |
null | fastai |
# Amazing!
🥳 Congratulations on hosting your fastai model on the Hugging Face Hub!
# Some next steps
1. Fill out this model card with more information (see the template below and the [documentation here](https://huggingface.co/docs/hub/model-repos))!
2. Create a demo in Gradio or Streamlit using 🤗 Spaces ([documentation here](https://huggingface.co/docs/hub/spaces)).
3. Join the fastai community on the [Fastai Discord](https://discord.com/invite/YKrxeNn)!
Greetings fellow fastlearner 🤝! Don't forget to delete this content from your model card.
---
# Model card
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
| {"tags": ["fastai"]} | lauragordo/model3 | null | [
"fastai",
"has_space",
"region:us"
] | null | 2024-04-19T14:38:34+00:00 | [] | [] | TAGS
#fastai #has_space #region-us
|
# Amazing!
Congratulations on hosting your fastai model on the Hugging Face Hub!
# Some next steps
1. Fill out this model card with more information (see the template below and the documentation here)!
2. Create a demo in Gradio or Streamlit using Spaces (documentation here).
3. Join the fastai community on the Fastai Discord!
Greetings fellow fastlearner ! Don't forget to delete this content from your model card.
---
# Model card
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
| [
"# Amazing!\n\n Congratulations on hosting your fastai model on the Hugging Face Hub!",
"# Some next steps\n1. Fill out this model card with more information (see the template below and the documentation here)!\n\n2. Create a demo in Gradio or Streamlit using Spaces (documentation here).\n\n3. Join the fastai community on the Fastai Discord!\n\nGreetings fellow fastlearner ! Don't forget to delete this content from your model card.\n\n\n---",
"# Model card",
"## Model description\nMore information needed",
"## Intended uses & limitations\nMore information needed",
"## Training and evaluation data\nMore information needed"
] | [
"TAGS\n#fastai #has_space #region-us \n",
"# Amazing!\n\n Congratulations on hosting your fastai model on the Hugging Face Hub!",
"# Some next steps\n1. Fill out this model card with more information (see the template below and the documentation here)!\n\n2. Create a demo in Gradio or Streamlit using Spaces (documentation here).\n\n3. Join the fastai community on the Fastai Discord!\n\nGreetings fellow fastlearner ! Don't forget to delete this content from your model card.\n\n\n---",
"# Model card",
"## Model description\nMore information needed",
"## Intended uses & limitations\nMore information needed",
"## Training and evaluation data\nMore information needed"
] |
text-generation | transformers |
## Model Details
Meta developed and released the Meta Llama 3 family of large language models (LLMs), a collection of pretrained and instruction tuned generative text models in 8 and 70B sizes. The Llama 3 instruction tuned models are optimized for dialogue use cases and outperform many of the available open source chat models on common industry benchmarks. Further, in developing these models, we took great care to optimize helpfulness and safety.
**Model developers** Meta
**Variations** Llama 3 comes in two sizes — 8B and 70B parameters — in pre-trained and instruction tuned variants.
**Input** Models input text only.
**Output** Models generate text and code only.
**Model Architecture** Llama 3 is an auto-regressive language model that uses an optimized transformer architecture. The tuned versions use supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF) to align with human preferences for helpfulness and safety.
<table>
<tr>
<td>
</td>
<td><strong>Training Data</strong>
</td>
<td><strong>Params</strong>
</td>
<td><strong>Context length</strong>
</td>
<td><strong>GQA</strong>
</td>
<td><strong>Token count</strong>
</td>
<td><strong>Knowledge cutoff</strong>
</td>
</tr>
<tr>
<td rowspan="2" >Llama 3
</td>
<td rowspan="2" >A new mix of publicly available online data.
</td>
<td>8B
</td>
<td>8k
</td>
<td>Yes
</td>
<td rowspan="2" >15T+
</td>
<td>March, 2023
</td>
</tr>
<tr>
<td>70B
</td>
<td>8k
</td>
<td>Yes
</td>
<td>December, 2023
</td>
</tr>
</table>
**Llama 3 family of models**. Token counts refer to pretraining data only. Both the 8 and 70B versions use Grouped-Query Attention (GQA) for improved inference scalability.
**Model Release Date** April 18, 2024.
**Status** This is a static model trained on an offline dataset. Future versions of the tuned models will be released as we improve model safety with community feedback.
**License** A custom commercial license is available at: [https://llama.meta.com/llama3/license](https://llama.meta.com/llama3/license)
Where to send questions or comments about the model Instructions on how to provide feedback or comments on the model can be found in the model [README](https://github.com/meta-llama/llama3). For more technical information about generation parameters and recipes for how to use Llama 3 in applications, please go [here](https://github.com/meta-llama/llama-recipes).
## Intended Use
**Intended Use Cases** Llama 3 is intended for commercial and research use in English. Instruction tuned models are intended for assistant-like chat, whereas pretrained models can be adapted for a variety of natural language generation tasks.
**Out-of-scope** Use in any manner that violates applicable laws or regulations (including trade compliance laws). Use in any other way that is prohibited by the Acceptable Use Policy and Llama 3 Community License. Use in languages other than English**.
**Note: Developers may fine-tune Llama 3 models for languages beyond English provided they comply with the Llama 3 Community License and the Acceptable Use Policy.
## How to use
This repository contains two versions of Meta-Llama-3-70B-Instruct, for use with transformers and with the original `llama3` codebase.
### Use with transformers
See the snippet below for usage with Transformers:
```python
import transformers
import torch
model_id = "meta-llama/Meta-Llama-3-70B-Instruct"
pipeline = transformers.pipeline(
"text-generation",
model=model_id,
model_kwargs={"torch_dtype": torch.bfloat16},
device="cuda",
)
messages = [
{"role": "system", "content": "You are a pirate chatbot who always responds in pirate speak!"},
{"role": "user", "content": "Who are you?"},
]
prompt = pipeline.tokenizer.apply_chat_template(
messages,
tokenize=False,
add_generation_prompt=True
)
terminators = [
tokenizer.eos_token_id,
tokenizer.convert_tokens_to_ids("<|eot_id|>")
]
outputs = pipeline(
prompt,
max_new_tokens=256,
eos_token_id=terminators,
do_sample=True,
temperature=0.6,
top_p=0.9,
)
print(outputs[0]["generated_text"][len(prompt):])
```
### Use with `llama3`
Please, follow the instructions in the [repository](https://github.com/meta-llama/llama3).
To download Original checkpoints, see the example command below leveraging `huggingface-cli`:
```
huggingface-cli download meta-llama/Meta-Llama-3-70B-Instruct --include "original/*" --local-dir Meta-Llama-3-70B-Instruct
```
For Hugging Face support, we recommend using transformers or TGI, but a similar command works.
## Hardware and Software
**Training Factors** We used custom training libraries, Meta's Research SuperCluster, and production clusters for pretraining. Fine-tuning, annotation, and evaluation were also performed on third-party cloud compute.
**Carbon Footprint Pretraining utilized a cumulative** 7.7M GPU hours of computation on hardware of type H100-80GB (TDP of 700W). Estimated total emissions were 2290 tCO2eq, 100% of which were offset by Meta’s sustainability program.
<table>
<tr>
<td>
</td>
<td><strong>Time (GPU hours)</strong>
</td>
<td><strong>Power Consumption (W)</strong>
</td>
<td><strong>Carbon Emitted(tCO2eq)</strong>
</td>
</tr>
<tr>
<td>Llama 3 8B
</td>
<td>1.3M
</td>
<td>700
</td>
<td>390
</td>
</tr>
<tr>
<td>Llama 3 70B
</td>
<td>6.4M
</td>
<td>700
</td>
<td>1900
</td>
</tr>
<tr>
<td>Total
</td>
<td>7.7M
</td>
<td>
</td>
<td>2290
</td>
</tr>
</table>
**CO2 emissions during pre-training**. Time: total GPU time required for training each model. Power Consumption: peak power capacity per GPU device for the GPUs used adjusted for power usage efficiency. 100% of the emissions are directly offset by Meta's sustainability program, and because we are openly releasing these models, the pretraining costs do not need to be incurred by others.
## Training Data
**Overview** Llama 3 was pretrained on over 15 trillion tokens of data from publicly available sources. The fine-tuning data includes publicly available instruction datasets, as well as over 10M human-annotated examples. Neither the pretraining nor the fine-tuning datasets include Meta user data.
**Data Freshness** The pretraining data has a cutoff of March 2023 for the 7B and December 2023 for the 70B models respectively.
## Benchmarks
In this section, we report the results for Llama 3 models on standard automatic benchmarks. For all the evaluations, we use our internal evaluations library. For details on the methodology see [here](https://github.com/meta-llama/llama3/blob/main/eval_methodology.md).
### Base pretrained models
<table>
<tr>
<td><strong>Category</strong>
</td>
<td><strong>Benchmark</strong>
</td>
<td><strong>Llama 3 8B</strong>
</td>
<td><strong>Llama2 7B</strong>
</td>
<td><strong>Llama2 13B</strong>
</td>
<td><strong>Llama 3 70B</strong>
</td>
<td><strong>Llama2 70B</strong>
</td>
</tr>
<tr>
<td rowspan="6" >General
</td>
<td>MMLU (5-shot)
</td>
<td>66.6
</td>
<td>45.7
</td>
<td>53.8
</td>
<td>79.5
</td>
<td>69.7
</td>
</tr>
<tr>
<td>AGIEval English (3-5 shot)
</td>
<td>45.9
</td>
<td>28.8
</td>
<td>38.7
</td>
<td>63.0
</td>
<td>54.8
</td>
</tr>
<tr>
<td>CommonSenseQA (7-shot)
</td>
<td>72.6
</td>
<td>57.6
</td>
<td>67.6
</td>
<td>83.8
</td>
<td>78.7
</td>
</tr>
<tr>
<td>Winogrande (5-shot)
</td>
<td>76.1
</td>
<td>73.3
</td>
<td>75.4
</td>
<td>83.1
</td>
<td>81.8
</td>
</tr>
<tr>
<td>BIG-Bench Hard (3-shot, CoT)
</td>
<td>61.1
</td>
<td>38.1
</td>
<td>47.0
</td>
<td>81.3
</td>
<td>65.7
</td>
</tr>
<tr>
<td>ARC-Challenge (25-shot)
</td>
<td>78.6
</td>
<td>53.7
</td>
<td>67.6
</td>
<td>93.0
</td>
<td>85.3
</td>
</tr>
<tr>
<td>Knowledge reasoning
</td>
<td>TriviaQA-Wiki (5-shot)
</td>
<td>78.5
</td>
<td>72.1
</td>
<td>79.6
</td>
<td>89.7
</td>
<td>87.5
</td>
</tr>
<tr>
<td rowspan="4" >Reading comprehension
</td>
<td>SQuAD (1-shot)
</td>
<td>76.4
</td>
<td>72.2
</td>
<td>72.1
</td>
<td>85.6
</td>
<td>82.6
</td>
</tr>
<tr>
<td>QuAC (1-shot, F1)
</td>
<td>44.4
</td>
<td>39.6
</td>
<td>44.9
</td>
<td>51.1
</td>
<td>49.4
</td>
</tr>
<tr>
<td>BoolQ (0-shot)
</td>
<td>75.7
</td>
<td>65.5
</td>
<td>66.9
</td>
<td>79.0
</td>
<td>73.1
</td>
</tr>
<tr>
<td>DROP (3-shot, F1)
</td>
<td>58.4
</td>
<td>37.9
</td>
<td>49.8
</td>
<td>79.7
</td>
<td>70.2
</td>
</tr>
</table>
### Instruction tuned models
<table>
<tr>
<td><strong>Benchmark</strong>
</td>
<td><strong>Llama 3 8B</strong>
</td>
<td><strong>Llama 2 7B</strong>
</td>
<td><strong>Llama 2 13B</strong>
</td>
<td><strong>Llama 3 70B</strong>
</td>
<td><strong>Llama 2 70B</strong>
</td>
</tr>
<tr>
<td>MMLU (5-shot)
</td>
<td>68.4
</td>
<td>34.1
</td>
<td>47.8
</td>
<td>82.0
</td>
<td>52.9
</td>
</tr>
<tr>
<td>GPQA (0-shot)
</td>
<td>34.2
</td>
<td>21.7
</td>
<td>22.3
</td>
<td>39.5
</td>
<td>21.0
</td>
</tr>
<tr>
<td>HumanEval (0-shot)
</td>
<td>62.2
</td>
<td>7.9
</td>
<td>14.0
</td>
<td>81.7
</td>
<td>25.6
</td>
</tr>
<tr>
<td>GSM-8K (8-shot, CoT)
</td>
<td>79.6
</td>
<td>25.7
</td>
<td>77.4
</td>
<td>93.0
</td>
<td>57.5
</td>
</tr>
<tr>
<td>MATH (4-shot, CoT)
</td>
<td>30.0
</td>
<td>3.8
</td>
<td>6.7
</td>
<td>50.4
</td>
<td>11.6
</td>
</tr>
</table>
### Responsibility & Safety
We believe that an open approach to AI leads to better, safer products, faster innovation, and a bigger overall market. We are committed to Responsible AI development and took a series of steps to limit misuse and harm and support the open source community.
Foundation models are widely capable technologies that are built to be used for a diverse range of applications. They are not designed to meet every developer preference on safety levels for all use cases, out-of-the-box, as those by their nature will differ across different applications.
Rather, responsible LLM-application deployment is achieved by implementing a series of safety best practices throughout the development of such applications, from the model pre-training, fine-tuning and the deployment of systems composed of safeguards to tailor the safety needs specifically to the use case and audience.
As part of the Llama 3 release, we updated our [Responsible Use Guide](https://llama.meta.com/responsible-use-guide/) to outline the steps and best practices for developers to implement model and system level safety for their application. We also provide a set of resources including [Meta Llama Guard 2](https://llama.meta.com/purple-llama/) and [Code Shield](https://llama.meta.com/purple-llama/) safeguards. These tools have proven to drastically reduce residual risks of LLM Systems, while maintaining a high level of helpfulness. We encourage developers to tune and deploy these safeguards according to their needs and we provide a [reference implementation](https://github.com/meta-llama/llama-recipes/tree/main/recipes/responsible_ai) to get you started.
#### Llama 3-Instruct
As outlined in the Responsible Use Guide, some trade-off between model helpfulness and model alignment is likely unavoidable. Developers should exercise discretion about how to weigh the benefits of alignment and helpfulness for their specific use case and audience. Developers should be mindful of residual risks when using Llama models and leverage additional safety tools as needed to reach the right safety bar for their use case.
<span style="text-decoration:underline;">Safety</span>
For our instruction tuned model, we conducted extensive red teaming exercises, performed adversarial evaluations and implemented safety mitigations techniques to lower residual risks. As with any Large Language Model, residual risks will likely remain and we recommend that developers assess these risks in the context of their use case. In parallel, we are working with the community to make AI safety benchmark standards transparent, rigorous and interpretable.
<span style="text-decoration:underline;">Refusals</span>
In addition to residual risks, we put a great emphasis on model refusals to benign prompts. Over-refusing not only can impact the user experience but could even be harmful in certain contexts as well. We’ve heard the feedback from the developer community and improved our fine tuning to ensure that Llama 3 is significantly less likely to falsely refuse to answer prompts than Llama 2.
We built internal benchmarks and developed mitigations to limit false refusals making Llama 3 our most helpful model to date.
#### Responsible release
In addition to responsible use considerations outlined above, we followed a rigorous process that requires us to take extra measures against misuse and critical risks before we make our release decision.
Misuse
If you access or use Llama 3, you agree to the Acceptable Use Policy. The most recent copy of this policy can be found at [https://llama.meta.com/llama3/use-policy/](https://llama.meta.com/llama3/use-policy/).
#### Critical risks
<span style="text-decoration:underline;">CBRNE</span> (Chemical, Biological, Radiological, Nuclear, and high yield Explosives)
We have conducted a two fold assessment of the safety of the model in this area:
* Iterative testing during model training to assess the safety of responses related to CBRNE threats and other adversarial risks.
* Involving external CBRNE experts to conduct an uplift test assessing the ability of the model to accurately provide expert knowledge and reduce barriers to potential CBRNE misuse, by reference to what can be achieved using web search (without the model).
### <span style="text-decoration:underline;">Cyber Security </span>
We have evaluated Llama 3 with CyberSecEval, Meta’s cybersecurity safety eval suite, measuring Llama 3’s propensity to suggest insecure code when used as a coding assistant, and Llama 3’s propensity to comply with requests to help carry out cyber attacks, where attacks are defined by the industry standard MITRE ATT&CK cyber attack ontology. On our insecure coding and cyber attacker helpfulness tests, Llama 3 behaved in the same range or safer than models of [equivalent coding capability](https://huggingface.co/spaces/facebook/CyberSecEval).
### <span style="text-decoration:underline;">Child Safety</span>
Child Safety risk assessments were conducted using a team of experts, to assess the model’s capability to produce outputs that could result in Child Safety risks and inform on any necessary and appropriate risk mitigations via fine tuning. We leveraged those expert red teaming sessions to expand the coverage of our evaluation benchmarks through Llama 3 model development. For Llama 3, we conducted new in-depth sessions using objective based methodologies to assess the model risks along multiple attack vectors. We also partnered with content specialists to perform red teaming exercises assessing potentially violating content while taking account of market specific nuances or experiences.
### Community
Generative AI safety requires expertise and tooling, and we believe in the strength of the open community to accelerate its progress. We are active members of open consortiums, including the AI Alliance, Partnership in AI and MLCommons, actively contributing to safety standardization and transparency. We encourage the community to adopt taxonomies like the MLCommons Proof of Concept evaluation to facilitate collaboration and transparency on safety and content evaluations. Our Purple Llama tools are open sourced for the community to use and widely distributed across ecosystem partners including cloud service providers. We encourage community contributions to our [Github repository](https://github.com/meta-llama/PurpleLlama).
Finally, we put in place a set of resources including an [output reporting mechanism](https://developers.facebook.com/llama_output_feedback) and [bug bounty program](https://www.facebook.com/whitehat) to continuously improve the Llama technology with the help of the community.
## Ethical Considerations and Limitations
The core values of Llama 3 are openness, inclusivity and helpfulness. It is meant to serve everyone, and to work for a wide range of use cases. It is thus designed to be accessible to people across many different backgrounds, experiences and perspectives. Llama 3 addresses users and their needs as they are, without insertion unnecessary judgment or normativity, while reflecting the understanding that even content that may appear problematic in some cases can serve valuable purposes in others. It respects the dignity and autonomy of all users, especially in terms of the values of free thought and expression that power innovation and progress.
But Llama 3 is a new technology, and like any new technology, there are risks associated with its use. Testing conducted to date has been in English, and has not covered, nor could it cover, all scenarios. For these reasons, as with all LLMs, Llama 3’s potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate, biased or other objectionable responses to user prompts. Therefore, before deploying any applications of Llama 3 models, developers should perform safety testing and tuning tailored to their specific applications of the model. As outlined in the Responsible Use Guide, we recommend incorporating [Purple Llama](https://github.com/facebookresearch/PurpleLlama) solutions into your workflows and specifically [Llama Guard](https://ai.meta.com/research/publications/llama-guard-llm-based-input-output-safeguard-for-human-ai-conversations/) which provides a base model to filter input and output prompts to layer system-level safety on top of model-level safety.
Please see the Responsible Use Guide available at [http://llama.meta.com/responsible-use-guide](http://llama.meta.com/responsible-use-guide)
## Citation instructions
@article{llama3modelcard,
title={Llama 3 Model Card},
author={AI@Meta},
year={2024},
url = {https://github.com/meta-llama/llama3/blob/main/MODEL_CARD.md}
}
## Contributors
Aaditya Singh; Aaron Grattafiori; Abhimanyu Dubey; Abhinav Jauhri; Abhinav Pandey; Abhishek Kadian; Adam Kelsey; Adi Gangidi; Ahmad Al-Dahle; Ahuva Goldstand; Aiesha Letman; Ajay Menon; Akhil Mathur; Alan Schelten; Alex Vaughan; Amy Yang; Andrei Lupu; Andres Alvarado; Andrew Gallagher; Andrew Gu; Andrew Ho; Andrew Poulton; Andrew Ryan; Angela Fan; Ankit Ramchandani; Anthony Hartshorn; Archi Mitra; Archie Sravankumar; Artem Korenev; Arun Rao; Ashley Gabriel; Ashwin Bharambe; Assaf Eisenman; Aston Zhang; Aurelien Rodriguez; Austen Gregerson; Ava Spataru; Baptiste Roziere; Ben Maurer; Benjamin Leonhardi; Bernie Huang; Bhargavi Paranjape; Bing Liu; Binh Tang; Bobbie Chern; Brani Stojkovic; Brian Fuller; Catalina Mejia Arenas; Chao Zhou; Charlotte Caucheteux; Chaya Nayak; Ching-Hsiang Chu; Chloe Bi; Chris Cai; Chris Cox; Chris Marra; Chris McConnell; Christian Keller; Christoph Feichtenhofer; Christophe Touret; Chunyang Wu; Corinne Wong; Cristian Canton Ferrer; Damien Allonsius; Daniel Kreymer; Daniel Haziza; Daniel Li; Danielle Pintz; Danny Livshits; Danny Wyatt; David Adkins; David Esiobu; David Xu; Davide Testuggine; Delia David; Devi Parikh; Dhruv Choudhary; Dhruv Mahajan; Diana Liskovich; Diego Garcia-Olano; Diego Perino; Dieuwke Hupkes; Dingkang Wang; Dustin Holland; Egor Lakomkin; Elina Lobanova; Xiaoqing Ellen Tan; Emily Dinan; Eric Smith; Erik Brinkman; Esteban Arcaute; Filip Radenovic; Firat Ozgenel; Francesco Caggioni; Frank Seide; Frank Zhang; Gabriel Synnaeve; Gabriella Schwarz; Gabrielle Lee; Gada Badeer; Georgia Anderson; Graeme Nail; Gregoire Mialon; Guan Pang; Guillem Cucurell; Hailey Nguyen; Hannah Korevaar; Hannah Wang; Haroun Habeeb; Harrison Rudolph; Henry Aspegren; Hu Xu; Hugo Touvron; Iga Kozlowska; Igor Molybog; Igor Tufanov; Iliyan Zarov; Imanol Arrieta Ibarra; Irina-Elena Veliche; Isabel Kloumann; Ishan Misra; Ivan Evtimov; Jacob Xu; Jade Copet; Jake Weissman; Jan Geffert; Jana Vranes; Japhet Asher; Jason Park; Jay Mahadeokar; Jean-Baptiste Gaya; Jeet Shah; Jelmer van der Linde; Jennifer Chan; Jenny Hong; Jenya Lee; Jeremy Fu; Jeremy Teboul; Jianfeng Chi; Jianyu Huang; Jie Wang; Jiecao Yu; Joanna Bitton; Joe Spisak; Joelle Pineau; Jon Carvill; Jongsoo Park; Joseph Rocca; Joshua Johnstun; Junteng Jia; Kalyan Vasuden Alwala; Kam Hou U; Kate Plawiak; Kartikeya Upasani; Kaushik Veeraraghavan; Ke Li; Kenneth Heafield; Kevin Stone; Khalid El-Arini; Krithika Iyer; Kshitiz Malik; Kuenley Chiu; Kunal Bhalla; Kyle Huang; Lakshya Garg; Lauren Rantala-Yeary; Laurens van der Maaten; Lawrence Chen; Leandro Silva; Lee Bell; Lei Zhang; Liang Tan; Louis Martin; Lovish Madaan; Luca Wehrstedt; Lukas Blecher; Luke de Oliveira; Madeline Muzzi; Madian Khabsa; Manav Avlani; Mannat Singh; Manohar Paluri; Mark Zuckerberg; Marcin Kardas; Martynas Mankus; Mathew Oldham; Mathieu Rita; Matthew Lennie; Maya Pavlova; Meghan Keneally; Melanie Kambadur; Mihir Patel; Mikayel Samvelyan; Mike Clark; Mike Lewis; Min Si; Mitesh Kumar Singh; Mo Metanat; Mona Hassan; Naman Goyal; Narjes Torabi; Nicolas Usunier; Nikolay Bashlykov; Nikolay Bogoychev; Niladri Chatterji; Ning Dong; Oliver Aobo Yang; Olivier Duchenne; Onur Celebi; Parth Parekh; Patrick Alrassy; Paul Saab; Pavan Balaji; Pedro Rittner; Pengchuan Zhang; Pengwei Li; Petar Vasic; Peter Weng; Polina Zvyagina; Prajjwal Bhargava; Pratik Dubal; Praveen Krishnan; Punit Singh Koura; Qing He; Rachel Rodriguez; Ragavan Srinivasan; Rahul Mitra; Ramon Calderer; Raymond Li; Robert Stojnic; Roberta Raileanu; Robin Battey; Rocky Wang; Rohit Girdhar; Rohit Patel; Romain Sauvestre; Ronnie Polidoro; Roshan Sumbaly; Ross Taylor; Ruan Silva; Rui Hou; Rui Wang; Russ Howes; Ruty Rinott; Saghar Hosseini; Sai Jayesh Bondu; Samyak Datta; Sanjay Singh; Sara Chugh; Sargun Dhillon; Satadru Pan; Sean Bell; Sergey Edunov; Shaoliang Nie; Sharan Narang; Sharath Raparthy; Shaun Lindsay; Sheng Feng; Sheng Shen; Shenghao Lin; Shiva Shankar; Shruti Bhosale; Shun Zhang; Simon Vandenhende; Sinong Wang; Seohyun Sonia Kim; Soumya Batra; Sten Sootla; Steve Kehoe; Suchin Gururangan; Sumit Gupta; Sunny Virk; Sydney Borodinsky; Tamar Glaser; Tamar Herman; Tamara Best; Tara Fowler; Thomas Georgiou; Thomas Scialom; Tianhe Li; Todor Mihaylov; Tong Xiao; Ujjwal Karn; Vedanuj Goswami; Vibhor Gupta; Vignesh Ramanathan; Viktor Kerkez; Vinay Satish Kumar; Vincent Gonguet; Vish Vogeti; Vlad Poenaru; Vlad Tiberiu Mihailescu; Vladan Petrovic; Vladimir Ivanov; Wei Li; Weiwei Chu; Wenhan Xiong; Wenyin Fu; Wes Bouaziz; Whitney Meers; Will Constable; Xavier Martinet; Xiaojian Wu; Xinbo Gao; Xinfeng Xie; Xuchao Jia; Yaelle Goldschlag; Yann LeCun; Yashesh Gaur; Yasmine Babaei; Ye Qi; Yenda Li; Yi Wen; Yiwen Song; Youngjin Nam; Yuchen Hao; Yuchen Zhang; Yun Wang; Yuning Mao; Yuzi He; Zacharie Delpierre Coudert; Zachary DeVito; Zahra Hankir; Zhaoduo Wen; Zheng Yan; Zhengxing Chen; Zhenyu Yang; Zoe Papakipos
| {"language": ["en"], "license": "other", "tags": ["facebook", "meta", "pytorch", "llama", "llama-3"], "pipeline_tag": "text-generation", "license_name": "llama3", "license_link": "LICENSE", "extra_gated_prompt": "### META LLAMA 3 COMMUNITY LICENSE AGREEMENT\nMeta Llama 3 Version Release Date: April 18, 2024\n\"Agreement\" means the terms and conditions for use, reproduction, distribution and modification of the Llama Materials set forth herein.\n\"Documentation\" means the specifications, manuals and documentation accompanying Meta Llama 3 distributed by Meta at https://llama.meta.com/get-started/.\n\"Licensee\" or \"you\" means you, or your employer or any other person or entity (if you are entering into this Agreement on such person or entity\u2019s behalf), of the age required under applicable laws, rules or regulations to provide legal consent and that has legal authority to bind your employer or such other person or entity if you are entering in this Agreement on their behalf.\n\"Meta Llama 3\" means the foundational large language models and software and algorithms, including machine-learning model code, trained model weights, inference-enabling code, training-enabling code, fine-tuning enabling code and other elements of the foregoing distributed by Meta at https://llama.meta.com/llama-downloads.\n\"Llama Materials\" means, collectively, Meta\u2019s proprietary Meta Llama 3 and Documentation (and any portion thereof) made available under this Agreement.\n\"Meta\" or \"we\" means Meta Platforms Ireland Limited (if you are located in or, if you are an entity, your principal place of business is in the EEA or Switzerland) and Meta Platforms, Inc. (if you are located outside of the EEA or Switzerland).\n \n1. License Rights and Redistribution.\na. Grant of Rights. You are granted a non-exclusive, worldwide, non-transferable and royalty-free limited license under Meta\u2019s intellectual property or other rights owned by Meta embodied in the Llama Materials to use, reproduce, distribute, copy, create derivative works of, and make modifications to the Llama Materials.\nb. Redistribution and Use.\ni. If you distribute or make available the Llama Materials (or any derivative works thereof), or a product or service that uses any of them, including another AI model, you shall (A) provide a copy of this Agreement with any such Llama Materials; and (B) prominently display \u201cBuilt with Meta Llama 3\u201d on a related website, user interface, blogpost, about page, or product documentation. If you use the Llama Materials to create, train, fine tune, or otherwise improve an AI model, which is distributed or made available, you shall also include \u201cLlama 3\u201d at the beginning of any such AI model name.\nii. If you receive Llama Materials, or any derivative works thereof, from a Licensee as part of an integrated end user product, then Section 2 of this Agreement will not apply to you.\niii. You must retain in all copies of the Llama Materials that you distribute the following attribution notice within a \u201cNotice\u201d text file distributed as a part of such copies: \u201cMeta Llama 3 is licensed under the Meta Llama 3 Community License, Copyright \u00a9 Meta Platforms, Inc. All Rights Reserved.\u201d\niv. Your use of the Llama Materials must comply with applicable laws and regulations (including trade compliance laws and regulations) and adhere to the Acceptable Use Policy for the Llama Materials (available at https://llama.meta.com/llama3/use-policy), which is hereby incorporated by reference into this Agreement.\nv. You will not use the Llama Materials or any output or results of the Llama Materials to improve any other large language model (excluding Meta Llama 3 or derivative works thereof).\n2. Additional Commercial Terms. If, on the Meta Llama 3 version release date, the monthly active users of the products or services made available by or for Licensee, or Licensee\u2019s affiliates, is greater than 700 million monthly active users in the preceding calendar month, you must request a license from Meta, which Meta may grant to you in its sole discretion, and you are not authorized to exercise any of the rights under this Agreement unless or until Meta otherwise expressly grants you such rights.\n3. Disclaimer of Warranty. UNLESS REQUIRED BY APPLICABLE LAW, THE LLAMA MATERIALS AND ANY OUTPUT AND RESULTS THEREFROM ARE PROVIDED ON AN \u201cAS IS\u201d BASIS, WITHOUT WARRANTIES OF ANY KIND, AND META DISCLAIMS ALL WARRANTIES OF ANY KIND, BOTH EXPRESS AND IMPLIED, INCLUDING, WITHOUT LIMITATION, ANY WARRANTIES OF TITLE, NON-INFRINGEMENT, MERCHANTABILITY, OR FITNESS FOR A PARTICULAR PURPOSE. YOU ARE SOLELY RESPONSIBLE FOR DETERMINING THE APPROPRIATENESS OF USING OR REDISTRIBUTING THE LLAMA MATERIALS AND ASSUME ANY RISKS ASSOCIATED WITH YOUR USE OF THE LLAMA MATERIALS AND ANY OUTPUT AND RESULTS.\n4. Limitation of Liability. IN NO EVENT WILL META OR ITS AFFILIATES BE LIABLE UNDER ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, TORT, NEGLIGENCE, PRODUCTS LIABILITY, OR OTHERWISE, ARISING OUT OF THIS AGREEMENT, FOR ANY LOST PROFITS OR ANY INDIRECT, SPECIAL, CONSEQUENTIAL, INCIDENTAL, EXEMPLARY OR PUNITIVE DAMAGES, EVEN IF META OR ITS AFFILIATES HAVE BEEN ADVISED OF THE POSSIBILITY OF ANY OF THE FOREGOING.\n5. Intellectual Property.\na. No trademark licenses are granted under this Agreement, and in connection with the Llama Materials, neither Meta nor Licensee may use any name or mark owned by or associated with the other or any of its affiliates, except as required for reasonable and customary use in describing and redistributing the Llama Materials or as set forth in this Section 5(a). Meta hereby grants you a license to use \u201cLlama 3\u201d (the \u201cMark\u201d) solely as required to comply with the last sentence of Section 1.b.i. You will comply with Meta\u2019s brand guidelines (currently accessible at https://about.meta.com/brand/resources/meta/company-brand/ ). All goodwill arising out of your use of the Mark will inure to the benefit of Meta.\nb. Subject to Meta\u2019s ownership of Llama Materials and derivatives made by or for Meta, with respect to any derivative works and modifications of the Llama Materials that are made by you, as between you and Meta, you are and will be the owner of such derivative works and modifications.\nc. If you institute litigation or other proceedings against Meta or any entity (including a cross-claim or counterclaim in a lawsuit) alleging that the Llama Materials or Meta Llama 3 outputs or results, or any portion of any of the foregoing, constitutes infringement of intellectual property or other rights owned or licensable by you, then any licenses granted to you under this Agreement shall terminate as of the date such litigation or claim is filed or instituted. You will indemnify and hold harmless Meta from and against any claim by any third party arising out of or related to your use or distribution of the Llama Materials.\n6. Term and Termination. The term of this Agreement will commence upon your acceptance of this Agreement or access to the Llama Materials and will continue in full force and effect until terminated in accordance with the terms and conditions herein. Meta may terminate this Agreement if you are in breach of any term or condition of this Agreement. Upon termination of this Agreement, you shall delete and cease use of the Llama Materials. Sections 3, 4 and 7 shall survive the termination of this Agreement.\n7. Governing Law and Jurisdiction. This Agreement will be governed and construed under the laws of the State of California without regard to choice of law principles, and the UN Convention on Contracts for the International Sale of Goods does not apply to this Agreement. The courts of California shall have exclusive jurisdiction of any dispute arising out of this Agreement.\n### Meta Llama 3 Acceptable Use Policy\nMeta is committed to promoting safe and fair use of its tools and features, including Meta Llama 3. If you access or use Meta Llama 3, you agree to this Acceptable Use Policy (\u201cPolicy\u201d). The most recent copy of this policy can be found at [https://llama.meta.com/llama3/use-policy](https://llama.meta.com/llama3/use-policy)\n#### Prohibited Uses\nWe want everyone to use Meta Llama 3 safely and responsibly. You agree you will not use, or allow others to use, Meta Llama 3 to: 1. Violate the law or others\u2019 rights, including to:\n 1. Engage in, promote, generate, contribute to, encourage, plan, incite, or further illegal or unlawful activity or content, such as:\n 1. Violence or terrorism\n 2. Exploitation or harm to children, including the solicitation, creation, acquisition, or dissemination of child exploitative content or failure to report Child Sexual Abuse Material\n 3. Human trafficking, exploitation, and sexual violence\n 4. The illegal distribution of information or materials to minors, including obscene materials, or failure to employ legally required age-gating in connection with such information or materials.\n 5. Sexual solicitation\n 6. Any other criminal activity\n 2. Engage in, promote, incite, or facilitate the harassment, abuse, threatening, or bullying of individuals or groups of individuals\n 3. Engage in, promote, incite, or facilitate discrimination or other unlawful or harmful conduct in the provision of employment, employment benefits, credit, housing, other economic benefits, or other essential goods and services\n 4. Engage in the unauthorized or unlicensed practice of any profession including, but not limited to, financial, legal, medical/health, or related professional practices\n 5. Collect, process, disclose, generate, or infer health, demographic, or other sensitive personal or private information about individuals without rights and consents required by applicable laws\n 6. Engage in or facilitate any action or generate any content that infringes, misappropriates, or otherwise violates any third-party rights, including the outputs or results of any products or services using the Llama Materials\n 7. Create, generate, or facilitate the creation of malicious code, malware, computer viruses or do anything else that could disable, overburden, interfere with or impair the proper working, integrity, operation or appearance of a website or computer system\n2. Engage in, promote, incite, facilitate, or assist in the planning or development of activities that present a risk of death or bodily harm to individuals, including use of Meta Llama 3 related to the following:\n 1. Military, warfare, nuclear industries or applications, espionage, use for materials or activities that are subject to the International Traffic Arms Regulations (ITAR) maintained by the United States Department of State\n 2. Guns and illegal weapons (including weapon development)\n 3. Illegal drugs and regulated/controlled substances\n 4. Operation of critical infrastructure, transportation technologies, or heavy machinery\n 5. Self-harm or harm to others, including suicide, cutting, and eating disorders\n 6. Any content intended to incite or promote violence, abuse, or any infliction of bodily harm to an individual\n3. Intentionally deceive or mislead others, including use of Meta Llama 3 related to the following:\n 1. Generating, promoting, or furthering fraud or the creation or promotion of disinformation\n 2. Generating, promoting, or furthering defamatory content, including the creation of defamatory statements, images, or other content\n 3. Generating, promoting, or further distributing spam\n 4. Impersonating another individual without consent, authorization, or legal right\n 5. Representing that the use of Meta Llama 3 or outputs are human-generated\n 6. Generating or facilitating false online engagement, including fake reviews and other means of fake online engagement\n4. Fail to appropriately disclose to end users any known dangers of your AI system\nPlease report any violation of this Policy, software \u201cbug,\u201d or other problems that could lead to a violation of this Policy through one of the following means:\n * Reporting issues with the model: [https://github.com/meta-llama/llama3](https://github.com/meta-llama/llama3)\n * Reporting risky content generated by the model:\n developers.facebook.com/llama_output_feedback\n * Reporting bugs and security concerns: facebook.com/whitehat/info\n * Reporting violations of the Acceptable Use Policy or unlicensed uses of Meta Llama 3: [email protected]", "extra_gated_fields": {"First Name": "text", "Last Name": "text", "Date of birth": "date_picker", "Country": "country", "Affiliation": "text", "geo": "ip_location", "By clicking Submit below I accept the terms of the license and acknowledge that the information I provide will be collected stored processed and shared in accordance with the Meta Privacy Policy": "checkbox"}, "extra_gated_description": "The information you provide will be collected, stored, processed and shared in accordance with the [Meta Privacy Policy](https://www.facebook.com/privacy/policy/).", "extra_gated_button_content": "Submit"} | blockblockblock/Meta-Llama-3-70B-Instruct-hf-bpw3 | null | [
"transformers",
"safetensors",
"llama",
"text-generation",
"facebook",
"meta",
"pytorch",
"llama-3",
"conversational",
"en",
"license:other",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"3-bit",
"region:us"
] | null | 2024-04-19T14:40:33+00:00 | [] | [
"en"
] | TAGS
#transformers #safetensors #llama #text-generation #facebook #meta #pytorch #llama-3 #conversational #en #license-other #autotrain_compatible #endpoints_compatible #text-generation-inference #3-bit #region-us
| Model Details
-------------
Meta developed and released the Meta Llama 3 family of large language models (LLMs), a collection of pretrained and instruction tuned generative text models in 8 and 70B sizes. The Llama 3 instruction tuned models are optimized for dialogue use cases and outperform many of the available open source chat models on common industry benchmarks. Further, in developing these models, we took great care to optimize helpfulness and safety.
Model developers Meta
Variations Llama 3 comes in two sizes — 8B and 70B parameters — in pre-trained and instruction tuned variants.
Input Models input text only.
Output Models generate text and code only.
Model Architecture Llama 3 is an auto-regressive language model that uses an optimized transformer architecture. The tuned versions use supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF) to align with human preferences for helpfulness and safety.
Llama 3 family of models. Token counts refer to pretraining data only. Both the 8 and 70B versions use Grouped-Query Attention (GQA) for improved inference scalability.
Model Release Date April 18, 2024.
Status This is a static model trained on an offline dataset. Future versions of the tuned models will be released as we improve model safety with community feedback.
License A custom commercial license is available at: URL
Where to send questions or comments about the model Instructions on how to provide feedback or comments on the model can be found in the model README. For more technical information about generation parameters and recipes for how to use Llama 3 in applications, please go here.
Intended Use
------------
Intended Use Cases Llama 3 is intended for commercial and research use in English. Instruction tuned models are intended for assistant-like chat, whereas pretrained models can be adapted for a variety of natural language generation tasks.
Out-of-scope Use in any manner that violates applicable laws or regulations (including trade compliance laws). Use in any other way that is prohibited by the Acceptable Use Policy and Llama 3 Community License. Use in languages other than English.
Note: Developers may fine-tune Llama 3 models for languages beyond English provided they comply with the Llama 3 Community License and the Acceptable Use Policy.
How to use
----------
This repository contains two versions of Meta-Llama-3-70B-Instruct, for use with transformers and with the original 'llama3' codebase.
### Use with transformers
See the snippet below for usage with Transformers:
### Use with 'llama3'
Please, follow the instructions in the repository.
To download Original checkpoints, see the example command below leveraging 'huggingface-cli':
For Hugging Face support, we recommend using transformers or TGI, but a similar command works.
Hardware and Software
---------------------
Training Factors We used custom training libraries, Meta's Research SuperCluster, and production clusters for pretraining. Fine-tuning, annotation, and evaluation were also performed on third-party cloud compute.
Carbon Footprint Pretraining utilized a cumulative 7.7M GPU hours of computation on hardware of type H100-80GB (TDP of 700W). Estimated total emissions were 2290 tCO2eq, 100% of which were offset by Meta’s sustainability program.
CO2 emissions during pre-training. Time: total GPU time required for training each model. Power Consumption: peak power capacity per GPU device for the GPUs used adjusted for power usage efficiency. 100% of the emissions are directly offset by Meta's sustainability program, and because we are openly releasing these models, the pretraining costs do not need to be incurred by others.
Training Data
-------------
Overview Llama 3 was pretrained on over 15 trillion tokens of data from publicly available sources. The fine-tuning data includes publicly available instruction datasets, as well as over 10M human-annotated examples. Neither the pretraining nor the fine-tuning datasets include Meta user data.
Data Freshness The pretraining data has a cutoff of March 2023 for the 7B and December 2023 for the 70B models respectively.
Benchmarks
----------
In this section, we report the results for Llama 3 models on standard automatic benchmarks. For all the evaluations, we use our internal evaluations library. For details on the methodology see here.
### Base pretrained models
### Instruction tuned models
### Responsibility & Safety
We believe that an open approach to AI leads to better, safer products, faster innovation, and a bigger overall market. We are committed to Responsible AI development and took a series of steps to limit misuse and harm and support the open source community.
Foundation models are widely capable technologies that are built to be used for a diverse range of applications. They are not designed to meet every developer preference on safety levels for all use cases, out-of-the-box, as those by their nature will differ across different applications.
Rather, responsible LLM-application deployment is achieved by implementing a series of safety best practices throughout the development of such applications, from the model pre-training, fine-tuning and the deployment of systems composed of safeguards to tailor the safety needs specifically to the use case and audience.
As part of the Llama 3 release, we updated our Responsible Use Guide to outline the steps and best practices for developers to implement model and system level safety for their application. We also provide a set of resources including Meta Llama Guard 2 and Code Shield safeguards. These tools have proven to drastically reduce residual risks of LLM Systems, while maintaining a high level of helpfulness. We encourage developers to tune and deploy these safeguards according to their needs and we provide a reference implementation to get you started.
#### Llama 3-Instruct
As outlined in the Responsible Use Guide, some trade-off between model helpfulness and model alignment is likely unavoidable. Developers should exercise discretion about how to weigh the benefits of alignment and helpfulness for their specific use case and audience. Developers should be mindful of residual risks when using Llama models and leverage additional safety tools as needed to reach the right safety bar for their use case.
Safety
For our instruction tuned model, we conducted extensive red teaming exercises, performed adversarial evaluations and implemented safety mitigations techniques to lower residual risks. As with any Large Language Model, residual risks will likely remain and we recommend that developers assess these risks in the context of their use case. In parallel, we are working with the community to make AI safety benchmark standards transparent, rigorous and interpretable.
Refusals
In addition to residual risks, we put a great emphasis on model refusals to benign prompts. Over-refusing not only can impact the user experience but could even be harmful in certain contexts as well. We’ve heard the feedback from the developer community and improved our fine tuning to ensure that Llama 3 is significantly less likely to falsely refuse to answer prompts than Llama 2.
We built internal benchmarks and developed mitigations to limit false refusals making Llama 3 our most helpful model to date.
#### Responsible release
In addition to responsible use considerations outlined above, we followed a rigorous process that requires us to take extra measures against misuse and critical risks before we make our release decision.
Misuse
If you access or use Llama 3, you agree to the Acceptable Use Policy. The most recent copy of this policy can be found at URL
#### Critical risks
CBRNE (Chemical, Biological, Radiological, Nuclear, and high yield Explosives)
We have conducted a two fold assessment of the safety of the model in this area:
* Iterative testing during model training to assess the safety of responses related to CBRNE threats and other adversarial risks.
* Involving external CBRNE experts to conduct an uplift test assessing the ability of the model to accurately provide expert knowledge and reduce barriers to potential CBRNE misuse, by reference to what can be achieved using web search (without the model).
### Cyber Security
We have evaluated Llama 3 with CyberSecEval, Meta’s cybersecurity safety eval suite, measuring Llama 3’s propensity to suggest insecure code when used as a coding assistant, and Llama 3’s propensity to comply with requests to help carry out cyber attacks, where attacks are defined by the industry standard MITRE ATT&CK cyber attack ontology. On our insecure coding and cyber attacker helpfulness tests, Llama 3 behaved in the same range or safer than models of equivalent coding capability.
### Child Safety
Child Safety risk assessments were conducted using a team of experts, to assess the model’s capability to produce outputs that could result in Child Safety risks and inform on any necessary and appropriate risk mitigations via fine tuning. We leveraged those expert red teaming sessions to expand the coverage of our evaluation benchmarks through Llama 3 model development. For Llama 3, we conducted new in-depth sessions using objective based methodologies to assess the model risks along multiple attack vectors. We also partnered with content specialists to perform red teaming exercises assessing potentially violating content while taking account of market specific nuances or experiences.
### Community
Generative AI safety requires expertise and tooling, and we believe in the strength of the open community to accelerate its progress. We are active members of open consortiums, including the AI Alliance, Partnership in AI and MLCommons, actively contributing to safety standardization and transparency. We encourage the community to adopt taxonomies like the MLCommons Proof of Concept evaluation to facilitate collaboration and transparency on safety and content evaluations. Our Purple Llama tools are open sourced for the community to use and widely distributed across ecosystem partners including cloud service providers. We encourage community contributions to our Github repository.
Finally, we put in place a set of resources including an output reporting mechanism and bug bounty program to continuously improve the Llama technology with the help of the community.
Ethical Considerations and Limitations
--------------------------------------
The core values of Llama 3 are openness, inclusivity and helpfulness. It is meant to serve everyone, and to work for a wide range of use cases. It is thus designed to be accessible to people across many different backgrounds, experiences and perspectives. Llama 3 addresses users and their needs as they are, without insertion unnecessary judgment or normativity, while reflecting the understanding that even content that may appear problematic in some cases can serve valuable purposes in others. It respects the dignity and autonomy of all users, especially in terms of the values of free thought and expression that power innovation and progress.
But Llama 3 is a new technology, and like any new technology, there are risks associated with its use. Testing conducted to date has been in English, and has not covered, nor could it cover, all scenarios. For these reasons, as with all LLMs, Llama 3’s potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate, biased or other objectionable responses to user prompts. Therefore, before deploying any applications of Llama 3 models, developers should perform safety testing and tuning tailored to their specific applications of the model. As outlined in the Responsible Use Guide, we recommend incorporating Purple Llama solutions into your workflows and specifically Llama Guard which provides a base model to filter input and output prompts to layer system-level safety on top of model-level safety.
Please see the Responsible Use Guide available at URL
instructions
@article{llama3modelcard,
title={Llama 3 Model Card},
author={AI@Meta},
year={2024},
url = {URL
}
Contributors
------------
Aaditya Singh; Aaron Grattafiori; Abhimanyu Dubey; Abhinav Jauhri; Abhinav Pandey; Abhishek Kadian; Adam Kelsey; Adi Gangidi; Ahmad Al-Dahle; Ahuva Goldstand; Aiesha Letman; Ajay Menon; Akhil Mathur; Alan Schelten; Alex Vaughan; Amy Yang; Andrei Lupu; Andres Alvarado; Andrew Gallagher; Andrew Gu; Andrew Ho; Andrew Poulton; Andrew Ryan; Angela Fan; Ankit Ramchandani; Anthony Hartshorn; Archi Mitra; Archie Sravankumar; Artem Korenev; Arun Rao; Ashley Gabriel; Ashwin Bharambe; Assaf Eisenman; Aston Zhang; Aurelien Rodriguez; Austen Gregerson; Ava Spataru; Baptiste Roziere; Ben Maurer; Benjamin Leonhardi; Bernie Huang; Bhargavi Paranjape; Bing Liu; Binh Tang; Bobbie Chern; Brani Stojkovic; Brian Fuller; Catalina Mejia Arenas; Chao Zhou; Charlotte Caucheteux; Chaya Nayak; Ching-Hsiang Chu; Chloe Bi; Chris Cai; Chris Cox; Chris Marra; Chris McConnell; Christian Keller; Christoph Feichtenhofer; Christophe Touret; Chunyang Wu; Corinne Wong; Cristian Canton Ferrer; Damien Allonsius; Daniel Kreymer; Daniel Haziza; Daniel Li; Danielle Pintz; Danny Livshits; Danny Wyatt; David Adkins; David Esiobu; David Xu; Davide Testuggine; Delia David; Devi Parikh; Dhruv Choudhary; Dhruv Mahajan; Diana Liskovich; Diego Garcia-Olano; Diego Perino; Dieuwke Hupkes; Dingkang Wang; Dustin Holland; Egor Lakomkin; Elina Lobanova; Xiaoqing Ellen Tan; Emily Dinan; Eric Smith; Erik Brinkman; Esteban Arcaute; Filip Radenovic; Firat Ozgenel; Francesco Caggioni; Frank Seide; Frank Zhang; Gabriel Synnaeve; Gabriella Schwarz; Gabrielle Lee; Gada Badeer; Georgia Anderson; Graeme Nail; Gregoire Mialon; Guan Pang; Guillem Cucurell; Hailey Nguyen; Hannah Korevaar; Hannah Wang; Haroun Habeeb; Harrison Rudolph; Henry Aspegren; Hu Xu; Hugo Touvron; Iga Kozlowska; Igor Molybog; Igor Tufanov; Iliyan Zarov; Imanol Arrieta Ibarra; Irina-Elena Veliche; Isabel Kloumann; Ishan Misra; Ivan Evtimov; Jacob Xu; Jade Copet; Jake Weissman; Jan Geffert; Jana Vranes; Japhet Asher; Jason Park; Jay Mahadeokar; Jean-Baptiste Gaya; Jeet Shah; Jelmer van der Linde; Jennifer Chan; Jenny Hong; Jenya Lee; Jeremy Fu; Jeremy Teboul; Jianfeng Chi; Jianyu Huang; Jie Wang; Jiecao Yu; Joanna Bitton; Joe Spisak; Joelle Pineau; Jon Carvill; Jongsoo Park; Joseph Rocca; Joshua Johnstun; Junteng Jia; Kalyan Vasuden Alwala; Kam Hou U; Kate Plawiak; Kartikeya Upasani; Kaushik Veeraraghavan; Ke Li; Kenneth Heafield; Kevin Stone; Khalid El-Arini; Krithika Iyer; Kshitiz Malik; Kuenley Chiu; Kunal Bhalla; Kyle Huang; Lakshya Garg; Lauren Rantala-Yeary; Laurens van der Maaten; Lawrence Chen; Leandro Silva; Lee Bell; Lei Zhang; Liang Tan; Louis Martin; Lovish Madaan; Luca Wehrstedt; Lukas Blecher; Luke de Oliveira; Madeline Muzzi; Madian Khabsa; Manav Avlani; Mannat Singh; Manohar Paluri; Mark Zuckerberg; Marcin Kardas; Martynas Mankus; Mathew Oldham; Mathieu Rita; Matthew Lennie; Maya Pavlova; Meghan Keneally; Melanie Kambadur; Mihir Patel; Mikayel Samvelyan; Mike Clark; Mike Lewis; Min Si; Mitesh Kumar Singh; Mo Metanat; Mona Hassan; Naman Goyal; Narjes Torabi; Nicolas Usunier; Nikolay Bashlykov; Nikolay Bogoychev; Niladri Chatterji; Ning Dong; Oliver Aobo Yang; Olivier Duchenne; Onur Celebi; Parth Parekh; Patrick Alrassy; Paul Saab; Pavan Balaji; Pedro Rittner; Pengchuan Zhang; Pengwei Li; Petar Vasic; Peter Weng; Polina Zvyagina; Prajjwal Bhargava; Pratik Dubal; Praveen Krishnan; Punit Singh Koura; Qing He; Rachel Rodriguez; Ragavan Srinivasan; Rahul Mitra; Ramon Calderer; Raymond Li; Robert Stojnic; Roberta Raileanu; Robin Battey; Rocky Wang; Rohit Girdhar; Rohit Patel; Romain Sauvestre; Ronnie Polidoro; Roshan Sumbaly; Ross Taylor; Ruan Silva; Rui Hou; Rui Wang; Russ Howes; Ruty Rinott; Saghar Hosseini; Sai Jayesh Bondu; Samyak Datta; Sanjay Singh; Sara Chugh; Sargun Dhillon; Satadru Pan; Sean Bell; Sergey Edunov; Shaoliang Nie; Sharan Narang; Sharath Raparthy; Shaun Lindsay; Sheng Feng; Sheng Shen; Shenghao Lin; Shiva Shankar; Shruti Bhosale; Shun Zhang; Simon Vandenhende; Sinong Wang; Seohyun Sonia Kim; Soumya Batra; Sten Sootla; Steve Kehoe; Suchin Gururangan; Sumit Gupta; Sunny Virk; Sydney Borodinsky; Tamar Glaser; Tamar Herman; Tamara Best; Tara Fowler; Thomas Georgiou; Thomas Scialom; Tianhe Li; Todor Mihaylov; Tong Xiao; Ujjwal Karn; Vedanuj Goswami; Vibhor Gupta; Vignesh Ramanathan; Viktor Kerkez; Vinay Satish Kumar; Vincent Gonguet; Vish Vogeti; Vlad Poenaru; Vlad Tiberiu Mihailescu; Vladan Petrovic; Vladimir Ivanov; Wei Li; Weiwei Chu; Wenhan Xiong; Wenyin Fu; Wes Bouaziz; Whitney Meers; Will Constable; Xavier Martinet; Xiaojian Wu; Xinbo Gao; Xinfeng Xie; Xuchao Jia; Yaelle Goldschlag; Yann LeCun; Yashesh Gaur; Yasmine Babaei; Ye Qi; Yenda Li; Yi Wen; Yiwen Song; Youngjin Nam; Yuchen Hao; Yuchen Zhang; Yun Wang; Yuning Mao; Yuzi He; Zacharie Delpierre Coudert; Zachary DeVito; Zahra Hankir; Zhaoduo Wen; Zheng Yan; Zhengxing Chen; Zhenyu Yang; Zoe Papakipos
| [
"### Use with transformers\n\n\nSee the snippet below for usage with Transformers:",
"### Use with 'llama3'\n\n\nPlease, follow the instructions in the repository.\n\n\nTo download Original checkpoints, see the example command below leveraging 'huggingface-cli':\n\n\nFor Hugging Face support, we recommend using transformers or TGI, but a similar command works.\n\n\nHardware and Software\n---------------------\n\n\nTraining Factors We used custom training libraries, Meta's Research SuperCluster, and production clusters for pretraining. Fine-tuning, annotation, and evaluation were also performed on third-party cloud compute.\n\n\nCarbon Footprint Pretraining utilized a cumulative 7.7M GPU hours of computation on hardware of type H100-80GB (TDP of 700W). Estimated total emissions were 2290 tCO2eq, 100% of which were offset by Meta’s sustainability program.\n\n\n\nCO2 emissions during pre-training. Time: total GPU time required for training each model. Power Consumption: peak power capacity per GPU device for the GPUs used adjusted for power usage efficiency. 100% of the emissions are directly offset by Meta's sustainability program, and because we are openly releasing these models, the pretraining costs do not need to be incurred by others.\n\n\nTraining Data\n-------------\n\n\nOverview Llama 3 was pretrained on over 15 trillion tokens of data from publicly available sources. The fine-tuning data includes publicly available instruction datasets, as well as over 10M human-annotated examples. Neither the pretraining nor the fine-tuning datasets include Meta user data.\n\n\nData Freshness The pretraining data has a cutoff of March 2023 for the 7B and December 2023 for the 70B models respectively.\n\n\nBenchmarks\n----------\n\n\nIn this section, we report the results for Llama 3 models on standard automatic benchmarks. For all the evaluations, we use our internal evaluations library. For details on the methodology see here.",
"### Base pretrained models",
"### Instruction tuned models",
"### Responsibility & Safety\n\n\nWe believe that an open approach to AI leads to better, safer products, faster innovation, and a bigger overall market. We are committed to Responsible AI development and took a series of steps to limit misuse and harm and support the open source community.\n\n\nFoundation models are widely capable technologies that are built to be used for a diverse range of applications. They are not designed to meet every developer preference on safety levels for all use cases, out-of-the-box, as those by their nature will differ across different applications.\n\n\nRather, responsible LLM-application deployment is achieved by implementing a series of safety best practices throughout the development of such applications, from the model pre-training, fine-tuning and the deployment of systems composed of safeguards to tailor the safety needs specifically to the use case and audience.\n\n\nAs part of the Llama 3 release, we updated our Responsible Use Guide to outline the steps and best practices for developers to implement model and system level safety for their application. We also provide a set of resources including Meta Llama Guard 2 and Code Shield safeguards. These tools have proven to drastically reduce residual risks of LLM Systems, while maintaining a high level of helpfulness. We encourage developers to tune and deploy these safeguards according to their needs and we provide a reference implementation to get you started.",
"#### Llama 3-Instruct\n\n\nAs outlined in the Responsible Use Guide, some trade-off between model helpfulness and model alignment is likely unavoidable. Developers should exercise discretion about how to weigh the benefits of alignment and helpfulness for their specific use case and audience. Developers should be mindful of residual risks when using Llama models and leverage additional safety tools as needed to reach the right safety bar for their use case.\n\n\nSafety\n\n\nFor our instruction tuned model, we conducted extensive red teaming exercises, performed adversarial evaluations and implemented safety mitigations techniques to lower residual risks. As with any Large Language Model, residual risks will likely remain and we recommend that developers assess these risks in the context of their use case. In parallel, we are working with the community to make AI safety benchmark standards transparent, rigorous and interpretable.\n\n\nRefusals\n\n\nIn addition to residual risks, we put a great emphasis on model refusals to benign prompts. Over-refusing not only can impact the user experience but could even be harmful in certain contexts as well. We’ve heard the feedback from the developer community and improved our fine tuning to ensure that Llama 3 is significantly less likely to falsely refuse to answer prompts than Llama 2.\n\n\nWe built internal benchmarks and developed mitigations to limit false refusals making Llama 3 our most helpful model to date.",
"#### Responsible release\n\n\nIn addition to responsible use considerations outlined above, we followed a rigorous process that requires us to take extra measures against misuse and critical risks before we make our release decision.\n\n\nMisuse\n\n\nIf you access or use Llama 3, you agree to the Acceptable Use Policy. The most recent copy of this policy can be found at URL",
"#### Critical risks\n\n\nCBRNE (Chemical, Biological, Radiological, Nuclear, and high yield Explosives)\n\n\nWe have conducted a two fold assessment of the safety of the model in this area:\n\n\n* Iterative testing during model training to assess the safety of responses related to CBRNE threats and other adversarial risks.\n* Involving external CBRNE experts to conduct an uplift test assessing the ability of the model to accurately provide expert knowledge and reduce barriers to potential CBRNE misuse, by reference to what can be achieved using web search (without the model).",
"### Cyber Security\n\n\nWe have evaluated Llama 3 with CyberSecEval, Meta’s cybersecurity safety eval suite, measuring Llama 3’s propensity to suggest insecure code when used as a coding assistant, and Llama 3’s propensity to comply with requests to help carry out cyber attacks, where attacks are defined by the industry standard MITRE ATT&CK cyber attack ontology. On our insecure coding and cyber attacker helpfulness tests, Llama 3 behaved in the same range or safer than models of equivalent coding capability.",
"### Child Safety\n\n\nChild Safety risk assessments were conducted using a team of experts, to assess the model’s capability to produce outputs that could result in Child Safety risks and inform on any necessary and appropriate risk mitigations via fine tuning. We leveraged those expert red teaming sessions to expand the coverage of our evaluation benchmarks through Llama 3 model development. For Llama 3, we conducted new in-depth sessions using objective based methodologies to assess the model risks along multiple attack vectors. We also partnered with content specialists to perform red teaming exercises assessing potentially violating content while taking account of market specific nuances or experiences.",
"### Community\n\n\nGenerative AI safety requires expertise and tooling, and we believe in the strength of the open community to accelerate its progress. We are active members of open consortiums, including the AI Alliance, Partnership in AI and MLCommons, actively contributing to safety standardization and transparency. We encourage the community to adopt taxonomies like the MLCommons Proof of Concept evaluation to facilitate collaboration and transparency on safety and content evaluations. Our Purple Llama tools are open sourced for the community to use and widely distributed across ecosystem partners including cloud service providers. We encourage community contributions to our Github repository.\n\n\nFinally, we put in place a set of resources including an output reporting mechanism and bug bounty program to continuously improve the Llama technology with the help of the community.\n\n\nEthical Considerations and Limitations\n--------------------------------------\n\n\nThe core values of Llama 3 are openness, inclusivity and helpfulness. It is meant to serve everyone, and to work for a wide range of use cases. It is thus designed to be accessible to people across many different backgrounds, experiences and perspectives. Llama 3 addresses users and their needs as they are, without insertion unnecessary judgment or normativity, while reflecting the understanding that even content that may appear problematic in some cases can serve valuable purposes in others. It respects the dignity and autonomy of all users, especially in terms of the values of free thought and expression that power innovation and progress.\n\n\nBut Llama 3 is a new technology, and like any new technology, there are risks associated with its use. Testing conducted to date has been in English, and has not covered, nor could it cover, all scenarios. For these reasons, as with all LLMs, Llama 3’s potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate, biased or other objectionable responses to user prompts. Therefore, before deploying any applications of Llama 3 models, developers should perform safety testing and tuning tailored to their specific applications of the model. As outlined in the Responsible Use Guide, we recommend incorporating Purple Llama solutions into your workflows and specifically Llama Guard which provides a base model to filter input and output prompts to layer system-level safety on top of model-level safety.\n\n\nPlease see the Responsible Use Guide available at URL\n\n\ninstructions\n\n\n@article{llama3modelcard,\n\n\ntitle={Llama 3 Model Card},\n\n\nauthor={AI@Meta},\n\n\nyear={2024},\n\n\nurl = {URL\n\n\n}\n\n\nContributors\n------------\n\n\nAaditya Singh; Aaron Grattafiori; Abhimanyu Dubey; Abhinav Jauhri; Abhinav Pandey; Abhishek Kadian; Adam Kelsey; Adi Gangidi; Ahmad Al-Dahle; Ahuva Goldstand; Aiesha Letman; Ajay Menon; Akhil Mathur; Alan Schelten; Alex Vaughan; Amy Yang; Andrei Lupu; Andres Alvarado; Andrew Gallagher; Andrew Gu; Andrew Ho; Andrew Poulton; Andrew Ryan; Angela Fan; Ankit Ramchandani; Anthony Hartshorn; Archi Mitra; Archie Sravankumar; Artem Korenev; Arun Rao; Ashley Gabriel; Ashwin Bharambe; Assaf Eisenman; Aston Zhang; Aurelien Rodriguez; Austen Gregerson; Ava Spataru; Baptiste Roziere; Ben Maurer; Benjamin Leonhardi; Bernie Huang; Bhargavi Paranjape; Bing Liu; Binh Tang; Bobbie Chern; Brani Stojkovic; Brian Fuller; Catalina Mejia Arenas; Chao Zhou; Charlotte Caucheteux; Chaya Nayak; Ching-Hsiang Chu; Chloe Bi; Chris Cai; Chris Cox; Chris Marra; Chris McConnell; Christian Keller; Christoph Feichtenhofer; Christophe Touret; Chunyang Wu; Corinne Wong; Cristian Canton Ferrer; Damien Allonsius; Daniel Kreymer; Daniel Haziza; Daniel Li; Danielle Pintz; Danny Livshits; Danny Wyatt; David Adkins; David Esiobu; David Xu; Davide Testuggine; Delia David; Devi Parikh; Dhruv Choudhary; Dhruv Mahajan; Diana Liskovich; Diego Garcia-Olano; Diego Perino; Dieuwke Hupkes; Dingkang Wang; Dustin Holland; Egor Lakomkin; Elina Lobanova; Xiaoqing Ellen Tan; Emily Dinan; Eric Smith; Erik Brinkman; Esteban Arcaute; Filip Radenovic; Firat Ozgenel; Francesco Caggioni; Frank Seide; Frank Zhang; Gabriel Synnaeve; Gabriella Schwarz; Gabrielle Lee; Gada Badeer; Georgia Anderson; Graeme Nail; Gregoire Mialon; Guan Pang; Guillem Cucurell; Hailey Nguyen; Hannah Korevaar; Hannah Wang; Haroun Habeeb; Harrison Rudolph; Henry Aspegren; Hu Xu; Hugo Touvron; Iga Kozlowska; Igor Molybog; Igor Tufanov; Iliyan Zarov; Imanol Arrieta Ibarra; Irina-Elena Veliche; Isabel Kloumann; Ishan Misra; Ivan Evtimov; Jacob Xu; Jade Copet; Jake Weissman; Jan Geffert; Jana Vranes; Japhet Asher; Jason Park; Jay Mahadeokar; Jean-Baptiste Gaya; Jeet Shah; Jelmer van der Linde; Jennifer Chan; Jenny Hong; Jenya Lee; Jeremy Fu; Jeremy Teboul; Jianfeng Chi; Jianyu Huang; Jie Wang; Jiecao Yu; Joanna Bitton; Joe Spisak; Joelle Pineau; Jon Carvill; Jongsoo Park; Joseph Rocca; Joshua Johnstun; Junteng Jia; Kalyan Vasuden Alwala; Kam Hou U; Kate Plawiak; Kartikeya Upasani; Kaushik Veeraraghavan; Ke Li; Kenneth Heafield; Kevin Stone; Khalid El-Arini; Krithika Iyer; Kshitiz Malik; Kuenley Chiu; Kunal Bhalla; Kyle Huang; Lakshya Garg; Lauren Rantala-Yeary; Laurens van der Maaten; Lawrence Chen; Leandro Silva; Lee Bell; Lei Zhang; Liang Tan; Louis Martin; Lovish Madaan; Luca Wehrstedt; Lukas Blecher; Luke de Oliveira; Madeline Muzzi; Madian Khabsa; Manav Avlani; Mannat Singh; Manohar Paluri; Mark Zuckerberg; Marcin Kardas; Martynas Mankus; Mathew Oldham; Mathieu Rita; Matthew Lennie; Maya Pavlova; Meghan Keneally; Melanie Kambadur; Mihir Patel; Mikayel Samvelyan; Mike Clark; Mike Lewis; Min Si; Mitesh Kumar Singh; Mo Metanat; Mona Hassan; Naman Goyal; Narjes Torabi; Nicolas Usunier; Nikolay Bashlykov; Nikolay Bogoychev; Niladri Chatterji; Ning Dong; Oliver Aobo Yang; Olivier Duchenne; Onur Celebi; Parth Parekh; Patrick Alrassy; Paul Saab; Pavan Balaji; Pedro Rittner; Pengchuan Zhang; Pengwei Li; Petar Vasic; Peter Weng; Polina Zvyagina; Prajjwal Bhargava; Pratik Dubal; Praveen Krishnan; Punit Singh Koura; Qing He; Rachel Rodriguez; Ragavan Srinivasan; Rahul Mitra; Ramon Calderer; Raymond Li; Robert Stojnic; Roberta Raileanu; Robin Battey; Rocky Wang; Rohit Girdhar; Rohit Patel; Romain Sauvestre; Ronnie Polidoro; Roshan Sumbaly; Ross Taylor; Ruan Silva; Rui Hou; Rui Wang; Russ Howes; Ruty Rinott; Saghar Hosseini; Sai Jayesh Bondu; Samyak Datta; Sanjay Singh; Sara Chugh; Sargun Dhillon; Satadru Pan; Sean Bell; Sergey Edunov; Shaoliang Nie; Sharan Narang; Sharath Raparthy; Shaun Lindsay; Sheng Feng; Sheng Shen; Shenghao Lin; Shiva Shankar; Shruti Bhosale; Shun Zhang; Simon Vandenhende; Sinong Wang; Seohyun Sonia Kim; Soumya Batra; Sten Sootla; Steve Kehoe; Suchin Gururangan; Sumit Gupta; Sunny Virk; Sydney Borodinsky; Tamar Glaser; Tamar Herman; Tamara Best; Tara Fowler; Thomas Georgiou; Thomas Scialom; Tianhe Li; Todor Mihaylov; Tong Xiao; Ujjwal Karn; Vedanuj Goswami; Vibhor Gupta; Vignesh Ramanathan; Viktor Kerkez; Vinay Satish Kumar; Vincent Gonguet; Vish Vogeti; Vlad Poenaru; Vlad Tiberiu Mihailescu; Vladan Petrovic; Vladimir Ivanov; Wei Li; Weiwei Chu; Wenhan Xiong; Wenyin Fu; Wes Bouaziz; Whitney Meers; Will Constable; Xavier Martinet; Xiaojian Wu; Xinbo Gao; Xinfeng Xie; Xuchao Jia; Yaelle Goldschlag; Yann LeCun; Yashesh Gaur; Yasmine Babaei; Ye Qi; Yenda Li; Yi Wen; Yiwen Song; Youngjin Nam; Yuchen Hao; Yuchen Zhang; Yun Wang; Yuning Mao; Yuzi He; Zacharie Delpierre Coudert; Zachary DeVito; Zahra Hankir; Zhaoduo Wen; Zheng Yan; Zhengxing Chen; Zhenyu Yang; Zoe Papakipos"
] | [
"TAGS\n#transformers #safetensors #llama #text-generation #facebook #meta #pytorch #llama-3 #conversational #en #license-other #autotrain_compatible #endpoints_compatible #text-generation-inference #3-bit #region-us \n",
"### Use with transformers\n\n\nSee the snippet below for usage with Transformers:",
"### Use with 'llama3'\n\n\nPlease, follow the instructions in the repository.\n\n\nTo download Original checkpoints, see the example command below leveraging 'huggingface-cli':\n\n\nFor Hugging Face support, we recommend using transformers or TGI, but a similar command works.\n\n\nHardware and Software\n---------------------\n\n\nTraining Factors We used custom training libraries, Meta's Research SuperCluster, and production clusters for pretraining. Fine-tuning, annotation, and evaluation were also performed on third-party cloud compute.\n\n\nCarbon Footprint Pretraining utilized a cumulative 7.7M GPU hours of computation on hardware of type H100-80GB (TDP of 700W). Estimated total emissions were 2290 tCO2eq, 100% of which were offset by Meta’s sustainability program.\n\n\n\nCO2 emissions during pre-training. Time: total GPU time required for training each model. Power Consumption: peak power capacity per GPU device for the GPUs used adjusted for power usage efficiency. 100% of the emissions are directly offset by Meta's sustainability program, and because we are openly releasing these models, the pretraining costs do not need to be incurred by others.\n\n\nTraining Data\n-------------\n\n\nOverview Llama 3 was pretrained on over 15 trillion tokens of data from publicly available sources. The fine-tuning data includes publicly available instruction datasets, as well as over 10M human-annotated examples. Neither the pretraining nor the fine-tuning datasets include Meta user data.\n\n\nData Freshness The pretraining data has a cutoff of March 2023 for the 7B and December 2023 for the 70B models respectively.\n\n\nBenchmarks\n----------\n\n\nIn this section, we report the results for Llama 3 models on standard automatic benchmarks. For all the evaluations, we use our internal evaluations library. For details on the methodology see here.",
"### Base pretrained models",
"### Instruction tuned models",
"### Responsibility & Safety\n\n\nWe believe that an open approach to AI leads to better, safer products, faster innovation, and a bigger overall market. We are committed to Responsible AI development and took a series of steps to limit misuse and harm and support the open source community.\n\n\nFoundation models are widely capable technologies that are built to be used for a diverse range of applications. They are not designed to meet every developer preference on safety levels for all use cases, out-of-the-box, as those by their nature will differ across different applications.\n\n\nRather, responsible LLM-application deployment is achieved by implementing a series of safety best practices throughout the development of such applications, from the model pre-training, fine-tuning and the deployment of systems composed of safeguards to tailor the safety needs specifically to the use case and audience.\n\n\nAs part of the Llama 3 release, we updated our Responsible Use Guide to outline the steps and best practices for developers to implement model and system level safety for their application. We also provide a set of resources including Meta Llama Guard 2 and Code Shield safeguards. These tools have proven to drastically reduce residual risks of LLM Systems, while maintaining a high level of helpfulness. We encourage developers to tune and deploy these safeguards according to their needs and we provide a reference implementation to get you started.",
"#### Llama 3-Instruct\n\n\nAs outlined in the Responsible Use Guide, some trade-off between model helpfulness and model alignment is likely unavoidable. Developers should exercise discretion about how to weigh the benefits of alignment and helpfulness for their specific use case and audience. Developers should be mindful of residual risks when using Llama models and leverage additional safety tools as needed to reach the right safety bar for their use case.\n\n\nSafety\n\n\nFor our instruction tuned model, we conducted extensive red teaming exercises, performed adversarial evaluations and implemented safety mitigations techniques to lower residual risks. As with any Large Language Model, residual risks will likely remain and we recommend that developers assess these risks in the context of their use case. In parallel, we are working with the community to make AI safety benchmark standards transparent, rigorous and interpretable.\n\n\nRefusals\n\n\nIn addition to residual risks, we put a great emphasis on model refusals to benign prompts. Over-refusing not only can impact the user experience but could even be harmful in certain contexts as well. We’ve heard the feedback from the developer community and improved our fine tuning to ensure that Llama 3 is significantly less likely to falsely refuse to answer prompts than Llama 2.\n\n\nWe built internal benchmarks and developed mitigations to limit false refusals making Llama 3 our most helpful model to date.",
"#### Responsible release\n\n\nIn addition to responsible use considerations outlined above, we followed a rigorous process that requires us to take extra measures against misuse and critical risks before we make our release decision.\n\n\nMisuse\n\n\nIf you access or use Llama 3, you agree to the Acceptable Use Policy. The most recent copy of this policy can be found at URL",
"#### Critical risks\n\n\nCBRNE (Chemical, Biological, Radiological, Nuclear, and high yield Explosives)\n\n\nWe have conducted a two fold assessment of the safety of the model in this area:\n\n\n* Iterative testing during model training to assess the safety of responses related to CBRNE threats and other adversarial risks.\n* Involving external CBRNE experts to conduct an uplift test assessing the ability of the model to accurately provide expert knowledge and reduce barriers to potential CBRNE misuse, by reference to what can be achieved using web search (without the model).",
"### Cyber Security\n\n\nWe have evaluated Llama 3 with CyberSecEval, Meta’s cybersecurity safety eval suite, measuring Llama 3’s propensity to suggest insecure code when used as a coding assistant, and Llama 3’s propensity to comply with requests to help carry out cyber attacks, where attacks are defined by the industry standard MITRE ATT&CK cyber attack ontology. On our insecure coding and cyber attacker helpfulness tests, Llama 3 behaved in the same range or safer than models of equivalent coding capability.",
"### Child Safety\n\n\nChild Safety risk assessments were conducted using a team of experts, to assess the model’s capability to produce outputs that could result in Child Safety risks and inform on any necessary and appropriate risk mitigations via fine tuning. We leveraged those expert red teaming sessions to expand the coverage of our evaluation benchmarks through Llama 3 model development. For Llama 3, we conducted new in-depth sessions using objective based methodologies to assess the model risks along multiple attack vectors. We also partnered with content specialists to perform red teaming exercises assessing potentially violating content while taking account of market specific nuances or experiences.",
"### Community\n\n\nGenerative AI safety requires expertise and tooling, and we believe in the strength of the open community to accelerate its progress. We are active members of open consortiums, including the AI Alliance, Partnership in AI and MLCommons, actively contributing to safety standardization and transparency. We encourage the community to adopt taxonomies like the MLCommons Proof of Concept evaluation to facilitate collaboration and transparency on safety and content evaluations. Our Purple Llama tools are open sourced for the community to use and widely distributed across ecosystem partners including cloud service providers. We encourage community contributions to our Github repository.\n\n\nFinally, we put in place a set of resources including an output reporting mechanism and bug bounty program to continuously improve the Llama technology with the help of the community.\n\n\nEthical Considerations and Limitations\n--------------------------------------\n\n\nThe core values of Llama 3 are openness, inclusivity and helpfulness. It is meant to serve everyone, and to work for a wide range of use cases. It is thus designed to be accessible to people across many different backgrounds, experiences and perspectives. Llama 3 addresses users and their needs as they are, without insertion unnecessary judgment or normativity, while reflecting the understanding that even content that may appear problematic in some cases can serve valuable purposes in others. It respects the dignity and autonomy of all users, especially in terms of the values of free thought and expression that power innovation and progress.\n\n\nBut Llama 3 is a new technology, and like any new technology, there are risks associated with its use. Testing conducted to date has been in English, and has not covered, nor could it cover, all scenarios. For these reasons, as with all LLMs, Llama 3’s potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate, biased or other objectionable responses to user prompts. Therefore, before deploying any applications of Llama 3 models, developers should perform safety testing and tuning tailored to their specific applications of the model. As outlined in the Responsible Use Guide, we recommend incorporating Purple Llama solutions into your workflows and specifically Llama Guard which provides a base model to filter input and output prompts to layer system-level safety on top of model-level safety.\n\n\nPlease see the Responsible Use Guide available at URL\n\n\ninstructions\n\n\n@article{llama3modelcard,\n\n\ntitle={Llama 3 Model Card},\n\n\nauthor={AI@Meta},\n\n\nyear={2024},\n\n\nurl = {URL\n\n\n}\n\n\nContributors\n------------\n\n\nAaditya Singh; Aaron Grattafiori; Abhimanyu Dubey; Abhinav Jauhri; Abhinav Pandey; Abhishek Kadian; Adam Kelsey; Adi Gangidi; Ahmad Al-Dahle; Ahuva Goldstand; Aiesha Letman; Ajay Menon; Akhil Mathur; Alan Schelten; Alex Vaughan; Amy Yang; Andrei Lupu; Andres Alvarado; Andrew Gallagher; Andrew Gu; Andrew Ho; Andrew Poulton; Andrew Ryan; Angela Fan; Ankit Ramchandani; Anthony Hartshorn; Archi Mitra; Archie Sravankumar; Artem Korenev; Arun Rao; Ashley Gabriel; Ashwin Bharambe; Assaf Eisenman; Aston Zhang; Aurelien Rodriguez; Austen Gregerson; Ava Spataru; Baptiste Roziere; Ben Maurer; Benjamin Leonhardi; Bernie Huang; Bhargavi Paranjape; Bing Liu; Binh Tang; Bobbie Chern; Brani Stojkovic; Brian Fuller; Catalina Mejia Arenas; Chao Zhou; Charlotte Caucheteux; Chaya Nayak; Ching-Hsiang Chu; Chloe Bi; Chris Cai; Chris Cox; Chris Marra; Chris McConnell; Christian Keller; Christoph Feichtenhofer; Christophe Touret; Chunyang Wu; Corinne Wong; Cristian Canton Ferrer; Damien Allonsius; Daniel Kreymer; Daniel Haziza; Daniel Li; Danielle Pintz; Danny Livshits; Danny Wyatt; David Adkins; David Esiobu; David Xu; Davide Testuggine; Delia David; Devi Parikh; Dhruv Choudhary; Dhruv Mahajan; Diana Liskovich; Diego Garcia-Olano; Diego Perino; Dieuwke Hupkes; Dingkang Wang; Dustin Holland; Egor Lakomkin; Elina Lobanova; Xiaoqing Ellen Tan; Emily Dinan; Eric Smith; Erik Brinkman; Esteban Arcaute; Filip Radenovic; Firat Ozgenel; Francesco Caggioni; Frank Seide; Frank Zhang; Gabriel Synnaeve; Gabriella Schwarz; Gabrielle Lee; Gada Badeer; Georgia Anderson; Graeme Nail; Gregoire Mialon; Guan Pang; Guillem Cucurell; Hailey Nguyen; Hannah Korevaar; Hannah Wang; Haroun Habeeb; Harrison Rudolph; Henry Aspegren; Hu Xu; Hugo Touvron; Iga Kozlowska; Igor Molybog; Igor Tufanov; Iliyan Zarov; Imanol Arrieta Ibarra; Irina-Elena Veliche; Isabel Kloumann; Ishan Misra; Ivan Evtimov; Jacob Xu; Jade Copet; Jake Weissman; Jan Geffert; Jana Vranes; Japhet Asher; Jason Park; Jay Mahadeokar; Jean-Baptiste Gaya; Jeet Shah; Jelmer van der Linde; Jennifer Chan; Jenny Hong; Jenya Lee; Jeremy Fu; Jeremy Teboul; Jianfeng Chi; Jianyu Huang; Jie Wang; Jiecao Yu; Joanna Bitton; Joe Spisak; Joelle Pineau; Jon Carvill; Jongsoo Park; Joseph Rocca; Joshua Johnstun; Junteng Jia; Kalyan Vasuden Alwala; Kam Hou U; Kate Plawiak; Kartikeya Upasani; Kaushik Veeraraghavan; Ke Li; Kenneth Heafield; Kevin Stone; Khalid El-Arini; Krithika Iyer; Kshitiz Malik; Kuenley Chiu; Kunal Bhalla; Kyle Huang; Lakshya Garg; Lauren Rantala-Yeary; Laurens van der Maaten; Lawrence Chen; Leandro Silva; Lee Bell; Lei Zhang; Liang Tan; Louis Martin; Lovish Madaan; Luca Wehrstedt; Lukas Blecher; Luke de Oliveira; Madeline Muzzi; Madian Khabsa; Manav Avlani; Mannat Singh; Manohar Paluri; Mark Zuckerberg; Marcin Kardas; Martynas Mankus; Mathew Oldham; Mathieu Rita; Matthew Lennie; Maya Pavlova; Meghan Keneally; Melanie Kambadur; Mihir Patel; Mikayel Samvelyan; Mike Clark; Mike Lewis; Min Si; Mitesh Kumar Singh; Mo Metanat; Mona Hassan; Naman Goyal; Narjes Torabi; Nicolas Usunier; Nikolay Bashlykov; Nikolay Bogoychev; Niladri Chatterji; Ning Dong; Oliver Aobo Yang; Olivier Duchenne; Onur Celebi; Parth Parekh; Patrick Alrassy; Paul Saab; Pavan Balaji; Pedro Rittner; Pengchuan Zhang; Pengwei Li; Petar Vasic; Peter Weng; Polina Zvyagina; Prajjwal Bhargava; Pratik Dubal; Praveen Krishnan; Punit Singh Koura; Qing He; Rachel Rodriguez; Ragavan Srinivasan; Rahul Mitra; Ramon Calderer; Raymond Li; Robert Stojnic; Roberta Raileanu; Robin Battey; Rocky Wang; Rohit Girdhar; Rohit Patel; Romain Sauvestre; Ronnie Polidoro; Roshan Sumbaly; Ross Taylor; Ruan Silva; Rui Hou; Rui Wang; Russ Howes; Ruty Rinott; Saghar Hosseini; Sai Jayesh Bondu; Samyak Datta; Sanjay Singh; Sara Chugh; Sargun Dhillon; Satadru Pan; Sean Bell; Sergey Edunov; Shaoliang Nie; Sharan Narang; Sharath Raparthy; Shaun Lindsay; Sheng Feng; Sheng Shen; Shenghao Lin; Shiva Shankar; Shruti Bhosale; Shun Zhang; Simon Vandenhende; Sinong Wang; Seohyun Sonia Kim; Soumya Batra; Sten Sootla; Steve Kehoe; Suchin Gururangan; Sumit Gupta; Sunny Virk; Sydney Borodinsky; Tamar Glaser; Tamar Herman; Tamara Best; Tara Fowler; Thomas Georgiou; Thomas Scialom; Tianhe Li; Todor Mihaylov; Tong Xiao; Ujjwal Karn; Vedanuj Goswami; Vibhor Gupta; Vignesh Ramanathan; Viktor Kerkez; Vinay Satish Kumar; Vincent Gonguet; Vish Vogeti; Vlad Poenaru; Vlad Tiberiu Mihailescu; Vladan Petrovic; Vladimir Ivanov; Wei Li; Weiwei Chu; Wenhan Xiong; Wenyin Fu; Wes Bouaziz; Whitney Meers; Will Constable; Xavier Martinet; Xiaojian Wu; Xinbo Gao; Xinfeng Xie; Xuchao Jia; Yaelle Goldschlag; Yann LeCun; Yashesh Gaur; Yasmine Babaei; Ye Qi; Yenda Li; Yi Wen; Yiwen Song; Youngjin Nam; Yuchen Hao; Yuchen Zhang; Yun Wang; Yuning Mao; Yuzi He; Zacharie Delpierre Coudert; Zachary DeVito; Zahra Hankir; Zhaoduo Wen; Zheng Yan; Zhengxing Chen; Zhenyu Yang; Zoe Papakipos"
] |
null | transformers |
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] | {"library_name": "transformers", "tags": []} | wendy41/llama-2-koen-user111-100 | null | [
"transformers",
"safetensors",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null | 2024-04-19T14:40:59+00:00 | [
"1910.09700"
] | [] | TAGS
#transformers #safetensors #arxiv-1910.09700 #endpoints_compatible #region-us
|
# Model Card for Model ID
## Model Details
### Model Description
This is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.
- Developed by:
- Funded by [optional]:
- Shared by [optional]:
- Model type:
- Language(s) (NLP):
- License:
- Finetuned from model [optional]:
### Model Sources [optional]
- Repository:
- Paper [optional]:
- Demo [optional]:
## Uses
### Direct Use
### Downstream Use [optional]
### Out-of-Scope Use
## Bias, Risks, and Limitations
### Recommendations
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
## Training Details
### Training Data
### Training Procedure
#### Preprocessing [optional]
#### Training Hyperparameters
- Training regime:
#### Speeds, Sizes, Times [optional]
## Evaluation
### Testing Data, Factors & Metrics
#### Testing Data
#### Factors
#### Metrics
### Results
#### Summary
## Model Examination [optional]
## Environmental Impact
Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).
- Hardware Type:
- Hours used:
- Cloud Provider:
- Compute Region:
- Carbon Emitted:
## Technical Specifications [optional]
### Model Architecture and Objective
### Compute Infrastructure
#### Hardware
#### Software
[optional]
BibTeX:
APA:
## Glossary [optional]
## More Information [optional]
## Model Card Authors [optional]
## Model Card Contact
| [
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.",
"## How to Get Started with the Model\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] | [
"TAGS\n#transformers #safetensors #arxiv-1910.09700 #endpoints_compatible #region-us \n",
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.",
"## How to Get Started with the Model\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] |
null | transformers |
# Uploaded model
- **Developed by:** ntvcie
- **License:** apache-2.0
- **Finetuned from model :** unsloth/gemma-2b-bnb-4bit
This gemma model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
| {"language": ["en"], "license": "apache-2.0", "tags": ["text-generation-inference", "transformers", "unsloth", "gemma", "trl"], "base_model": "unsloth/gemma-2b-bnb-4bit"} | ntvcie/Gemma2bVinhntV7_16bit | null | [
"transformers",
"text-generation-inference",
"unsloth",
"gemma",
"trl",
"en",
"base_model:unsloth/gemma-2b-bnb-4bit",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | 2024-04-19T14:41:10+00:00 | [] | [
"en"
] | TAGS
#transformers #text-generation-inference #unsloth #gemma #trl #en #base_model-unsloth/gemma-2b-bnb-4bit #license-apache-2.0 #endpoints_compatible #region-us
|
# Uploaded model
- Developed by: ntvcie
- License: apache-2.0
- Finetuned from model : unsloth/gemma-2b-bnb-4bit
This gemma model was trained 2x faster with Unsloth and Huggingface's TRL library.
<img src="URL width="200"/>
| [
"# Uploaded model\n\n- Developed by: ntvcie\n- License: apache-2.0\n- Finetuned from model : unsloth/gemma-2b-bnb-4bit\n\nThis gemma model was trained 2x faster with Unsloth and Huggingface's TRL library.\n\n<img src=\"URL width=\"200\"/>"
] | [
"TAGS\n#transformers #text-generation-inference #unsloth #gemma #trl #en #base_model-unsloth/gemma-2b-bnb-4bit #license-apache-2.0 #endpoints_compatible #region-us \n",
"# Uploaded model\n\n- Developed by: ntvcie\n- License: apache-2.0\n- Finetuned from model : unsloth/gemma-2b-bnb-4bit\n\nThis gemma model was trained 2x faster with Unsloth and Huggingface's TRL library.\n\n<img src=\"URL width=\"200\"/>"
] |
text-generation | transformers |
# Model Card for Model ID
An instruction fine-tuned model of Mistral-7B-v1.0 base model.
### Recommendations
Use the [INST]instruction[/INST] prompt format to make use of the fine tuning
## Training Details
The model was trained on a synthetic Q&A dataset generated from GPT-3.5 from the European Commission 2023 Report for Kosovo | {"language": ["en"], "license": "apache-2.0", "library_name": "transformers", "datasets": ["viktorahmeti/European-Commission-Kosovo-2023-Report-QA"]} | viktorahmeti/Mistral-7B-European-Commission-Kosovo-2023-Report-FT | null | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"en",
"dataset:viktorahmeti/European-Commission-Kosovo-2023-Report-QA",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"4-bit",
"region:us"
] | null | 2024-04-19T14:41:28+00:00 | [] | [
"en"
] | TAGS
#transformers #safetensors #mistral #text-generation #en #dataset-viktorahmeti/European-Commission-Kosovo-2023-Report-QA #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #4-bit #region-us
|
# Model Card for Model ID
An instruction fine-tuned model of Mistral-7B-v1.0 base model.
### Recommendations
Use the [INST]instruction[/INST] prompt format to make use of the fine tuning
## Training Details
The model was trained on a synthetic Q&A dataset generated from GPT-3.5 from the European Commission 2023 Report for Kosovo | [
"# Model Card for Model ID\n\nAn instruction fine-tuned model of Mistral-7B-v1.0 base model.",
"### Recommendations\n\nUse the [INST]instruction[/INST] prompt format to make use of the fine tuning",
"## Training Details\n\nThe model was trained on a synthetic Q&A dataset generated from GPT-3.5 from the European Commission 2023 Report for Kosovo"
] | [
"TAGS\n#transformers #safetensors #mistral #text-generation #en #dataset-viktorahmeti/European-Commission-Kosovo-2023-Report-QA #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #4-bit #region-us \n",
"# Model Card for Model ID\n\nAn instruction fine-tuned model of Mistral-7B-v1.0 base model.",
"### Recommendations\n\nUse the [INST]instruction[/INST] prompt format to make use of the fine tuning",
"## Training Details\n\nThe model was trained on a synthetic Q&A dataset generated from GPT-3.5 from the European Commission 2023 Report for Kosovo"
] |
null | null | Number of experts present in the library: 263
| Expert Name | Base Model | Trained on | Adapter Type |
| --- | --- | --- | --- |
| sciq_Multiple_Choice | phi-2 | sordonia/flan-10k-flat/sciq_Multiple_Choice | lora |
| wiki_hop_original_choose_best_object_interrogative_1 | phi-2 | sordonia/flan-10k-flat/wiki_hop_original_choose_best_object_interrogative_1 | lora |
| squad_v2_0_3_0_0 | phi-2 | sordonia/flan-10k-flat/squad_v2_0_3_0_0 | lora |
| wiki_qa_exercise | phi-2 | sordonia/flan-10k-flat/wiki_qa_exercise | lora |
| race_high_Taking_a_test | phi-2 | sordonia/flan-10k-flat/race_high_Taking_a_test | lora |
| adversarial_qa_dbert_generate_question | phi-2 | sordonia/flan-10k-flat/adversarial_qa_dbert_generate_question | lora |
| quoref_Found_Context_Online | phi-2 | sordonia/flan-10k-flat/quoref_Found_Context_Online | lora |
| web_questions_get_the_answer | phi-2 | sordonia/flan-10k-flat/web_questions_get_the_answer | lora |
| duorc_SelfRC_generate_question_by_answer | phi-2 | sordonia/flan-10k-flat/duorc_SelfRC_generate_question_by_answer | lora |
| quarel_testing_students | phi-2 | sordonia/flan-10k-flat/quarel_testing_students | lora |
| qasc_qa_with_separated_facts_1 | phi-2 | sordonia/flan-10k-flat/qasc_qa_with_separated_facts_1 | lora |
| wiki_qa_Is_This_True_ | phi-2 | sordonia/flan-10k-flat/wiki_qa_Is_This_True_ | lora |
| race_high_Read_the_article_and_answer_the_question_no_option_ | phi-2 | sordonia/flan-10k-flat/race_high_Read_the_article_and_answer_the_question_no_option_ | lora |
| cot_gsm8k_ii | phi-2 | sordonia/flan-10k-flat/cot_gsm8k_ii | lora |
| gem_wiki_lingua_english_en_1_1_0 | phi-2 | sordonia/flan-10k-flat/gem_wiki_lingua_english_en_1_1_0 | lora |
| unified_qa_science_inst | phi-2 | sordonia/flan-10k-flat/unified_qa_science_inst | lora |
| quartz_use_info_from_paragraph_question | phi-2 | sordonia/flan-10k-flat/quartz_use_info_from_paragraph_question | lora |
| wiki_hop_original_generate_object | phi-2 | sordonia/flan-10k-flat/wiki_hop_original_generate_object | lora |
| quoref_What_Is_The_Answer | phi-2 | sordonia/flan-10k-flat/quoref_What_Is_The_Answer | lora |
| adversarial_qa_droberta_generate_question | phi-2 | sordonia/flan-10k-flat/adversarial_qa_droberta_generate_question | lora |
| wiki_bio_comprehension | phi-2 | sordonia/flan-10k-flat/wiki_bio_comprehension | lora |
| adversarial_qa_dbidaf_question_context_answer | phi-2 | sordonia/flan-10k-flat/adversarial_qa_dbidaf_question_context_answer | lora |
| wiki_bio_what_content | phi-2 | sordonia/flan-10k-flat/wiki_bio_what_content | lora |
| web_questions_whats_the_answer | phi-2 | sordonia/flan-10k-flat/web_questions_whats_the_answer | lora |
| wiqa_what_is_the_missing_first_step | phi-2 | sordonia/flan-10k-flat/wiqa_what_is_the_missing_first_step | lora |
| adversarial_qa_droberta_question_context_answer | phi-2 | sordonia/flan-10k-flat/adversarial_qa_droberta_question_context_answer | lora |
| ropes_plain_bottom_hint | phi-2 | sordonia/flan-10k-flat/ropes_plain_bottom_hint | lora |
| kilt_tasks_hotpotqa_combining_facts | phi-2 | sordonia/flan-10k-flat/kilt_tasks_hotpotqa_combining_facts | lora |
| cos_e_v1_11_aligned_with_common_sense | phi-2 | sordonia/flan-10k-flat/cos_e_v1_11_aligned_with_common_sense | lora |
| gem_web_nlg_en_1_1_0 | phi-2 | sordonia/flan-10k-flat/gem_web_nlg_en_1_1_0 | lora |
| web_questions_potential_correct_answer | phi-2 | sordonia/flan-10k-flat/web_questions_potential_correct_answer | lora |
| wiki_qa_found_on_google | phi-2 | sordonia/flan-10k-flat/wiki_qa_found_on_google | lora |
| duorc_ParaphraseRC_extract_answer | phi-2 | sordonia/flan-10k-flat/duorc_ParaphraseRC_extract_answer | lora |
| wmt16_translate_de_en_1_0_0 | phi-2 | sordonia/flan-10k-flat/wmt16_translate_de_en_1_0_0 | lora |
| quail_no_prompt_id | phi-2 | sordonia/flan-10k-flat/quail_no_prompt_id | lora |
| quoref_Guess_Title_For_Context | phi-2 | sordonia/flan-10k-flat/quoref_Guess_Title_For_Context | lora |
| duorc_SelfRC_decide_worth_it | phi-2 | sordonia/flan-10k-flat/duorc_SelfRC_decide_worth_it | lora |
| ropes_prompt_mix | phi-2 | sordonia/flan-10k-flat/ropes_prompt_mix | lora |
| adversarial_qa_droberta_tell_what_it_is | phi-2 | sordonia/flan-10k-flat/adversarial_qa_droberta_tell_what_it_is | lora |
| quail_context_question_answer_description_id | phi-2 | sordonia/flan-10k-flat/quail_context_question_answer_description_id | lora |
| gem_common_gen_1_1_0 | phi-2 | sordonia/flan-10k-flat/gem_common_gen_1_1_0 | lora |
| duorc_ParaphraseRC_answer_question | phi-2 | sordonia/flan-10k-flat/duorc_ParaphraseRC_answer_question | lora |
| super_glue_cb_1_0_2 | phi-2 | sordonia/flan-10k-flat/super_glue_cb_1_0_2 | lora |
| cnn_dailymail_3_4_0 | phi-2 | sordonia/flan-10k-flat/cnn_dailymail_3_4_0 | lora |
| race_high_Write_a_multi_choice_question_options_given_ | phi-2 | sordonia/flan-10k-flat/race_high_Write_a_multi_choice_question_options_given_ | lora |
| winogrande_1_1_0 | phi-2 | sordonia/flan-10k-flat/winogrande_1_1_0 | lora |
| duorc_SelfRC_extract_answer | phi-2 | sordonia/flan-10k-flat/duorc_SelfRC_extract_answer | lora |
| trec_1_0_0 | phi-2 | sordonia/flan-10k-flat/trec_1_0_0 | lora |
| yelp_polarity_reviews_0_2_0 | phi-2 | sordonia/flan-10k-flat/yelp_polarity_reviews_0_2_0 | lora |
| race_high_Select_the_best_answer | phi-2 | sordonia/flan-10k-flat/race_high_Select_the_best_answer | lora |
| para_crawl_enes | phi-2 | sordonia/flan-10k-flat/para_crawl_enes | lora |
| qasc_is_correct_1 | phi-2 | sordonia/flan-10k-flat/qasc_is_correct_1 | lora |
| app_reviews_generate_review | phi-2 | sordonia/flan-10k-flat/app_reviews_generate_review | lora |
| ropes_read_background_situation | phi-2 | sordonia/flan-10k-flat/ropes_read_background_situation | lora |
| dbpedia_14_given_a_list_of_category_what_does_the_title_belong_to | phi-2 | sordonia/flan-10k-flat/dbpedia_14_given_a_list_of_category_what_does_the_title_belong_to | lora |
| stream_aqua | phi-2 | sordonia/flan-10k-flat/stream_aqua | lora |
| drop_2_0_0 | phi-2 | sordonia/flan-10k-flat/drop_2_0_0 | lora |
| wiki_hop_original_choose_best_object_affirmative_1 | phi-2 | sordonia/flan-10k-flat/wiki_hop_original_choose_best_object_affirmative_1 | lora |
| adversarial_qa_dbidaf_answer_the_following_q | phi-2 | sordonia/flan-10k-flat/adversarial_qa_dbidaf_answer_the_following_q | lora |
| social_i_qa_Generate_answer | phi-2 | sordonia/flan-10k-flat/social_i_qa_Generate_answer | lora |
| stream_aqua_ii | phi-2 | sordonia/flan-10k-flat/stream_aqua_ii | lora |
| glue_sst2_2_0_0 | phi-2 | sordonia/flan-10k-flat/glue_sst2_2_0_0 | lora |
| cot_esnli | phi-2 | sordonia/flan-10k-flat/cot_esnli | lora |
| race_high_Select_the_best_answer_no_instructions_ | phi-2 | sordonia/flan-10k-flat/race_high_Select_the_best_answer_no_instructions_ | lora |
| duorc_SelfRC_build_story_around_qa | phi-2 | sordonia/flan-10k-flat/duorc_SelfRC_build_story_around_qa | lora |
| cot_esnli_ii | phi-2 | sordonia/flan-10k-flat/cot_esnli_ii | lora |
| quail_no_prompt_text | phi-2 | sordonia/flan-10k-flat/quail_no_prompt_text | lora |
| ropes_given_background_situation | phi-2 | sordonia/flan-10k-flat/ropes_given_background_situation | lora |
| quarel_logic_test | phi-2 | sordonia/flan-10k-flat/quarel_logic_test | lora |
| adversarial_qa_dbidaf_based_on | phi-2 | sordonia/flan-10k-flat/adversarial_qa_dbidaf_based_on | lora |
| super_glue_copa_1_0_2 | phi-2 | sordonia/flan-10k-flat/super_glue_copa_1_0_2 | lora |
| cos_e_v1_11_i_think | phi-2 | sordonia/flan-10k-flat/cos_e_v1_11_i_think | lora |
| quail_context_question_description_answer_text | phi-2 | sordonia/flan-10k-flat/quail_context_question_description_answer_text | lora |
| math_dataset_algebra__linear_1d_1_0_0 | phi-2 | sordonia/flan-10k-flat/math_dataset_algebra__linear_1d_1_0_0 | lora |
| cosmos_qa_1_0_0 | phi-2 | sordonia/flan-10k-flat/cosmos_qa_1_0_0 | lora |
| wiqa_effect_with_label_answer | phi-2 | sordonia/flan-10k-flat/wiqa_effect_with_label_answer | lora |
| app_reviews_convert_to_star_rating | phi-2 | sordonia/flan-10k-flat/app_reviews_convert_to_star_rating | lora |
| qasc_qa_with_separated_facts_2 | phi-2 | sordonia/flan-10k-flat/qasc_qa_with_separated_facts_2 | lora |
| race_middle_Select_the_best_answer | phi-2 | sordonia/flan-10k-flat/race_middle_Select_the_best_answer | lora |
| quartz_having_read_above_passage | phi-2 | sordonia/flan-10k-flat/quartz_having_read_above_passage | lora |
| glue_qqp_2_0_0 | phi-2 | sordonia/flan-10k-flat/glue_qqp_2_0_0 | lora |
| cos_e_v1_11_question_description_option_id | phi-2 | sordonia/flan-10k-flat/cos_e_v1_11_question_description_option_id | lora |
| stream_qed_ii | phi-2 | sordonia/flan-10k-flat/stream_qed_ii | lora |
| cos_e_v1_11_question_option_description_text | phi-2 | sordonia/flan-10k-flat/cos_e_v1_11_question_option_description_text | lora |
| imdb_reviews_plain_text_1_0_0 | phi-2 | sordonia/flan-10k-flat/imdb_reviews_plain_text_1_0_0 | lora |
| wiki_hop_original_choose_best_object_affirmative_2 | phi-2 | sordonia/flan-10k-flat/wiki_hop_original_choose_best_object_affirmative_2 | lora |
| natural_questions_open_1_0_0 | phi-2 | sordonia/flan-10k-flat/natural_questions_open_1_0_0 | lora |
| wiqa_effect_with_string_answer | phi-2 | sordonia/flan-10k-flat/wiqa_effect_with_string_answer | lora |
| cos_e_v1_11_rationale | phi-2 | sordonia/flan-10k-flat/cos_e_v1_11_rationale | lora |
| race_middle_Write_a_multi_choice_question_options_given_ | phi-2 | sordonia/flan-10k-flat/race_middle_Write_a_multi_choice_question_options_given_ | lora |
| wiki_bio_guess_person | phi-2 | sordonia/flan-10k-flat/wiki_bio_guess_person | lora |
| hellaswag_1_1_0 | phi-2 | sordonia/flan-10k-flat/hellaswag_1_1_0 | lora |
| wiqa_does_the_supposed_perturbation_have_an_effect | phi-2 | sordonia/flan-10k-flat/wiqa_does_the_supposed_perturbation_have_an_effect | lora |
| trivia_qa_rc_1_1_0 | phi-2 | sordonia/flan-10k-flat/trivia_qa_rc_1_1_0 | lora |
| lambada_1_0_0 | phi-2 | sordonia/flan-10k-flat/lambada_1_0_0 | lora |
| quoref_Read_And_Extract_ | phi-2 | sordonia/flan-10k-flat/quoref_Read_And_Extract_ | lora |
| quail_context_description_question_answer_id | phi-2 | sordonia/flan-10k-flat/quail_context_description_question_answer_id | lora |
| quail_context_description_question_answer_text | phi-2 | sordonia/flan-10k-flat/quail_context_description_question_answer_text | lora |
| duorc_SelfRC_question_answering | phi-2 | sordonia/flan-10k-flat/duorc_SelfRC_question_answering | lora |
| cot_sensemaking_ii | phi-2 | sordonia/flan-10k-flat/cot_sensemaking_ii | lora |
| fix_punct | phi-2 | sordonia/flan-10k-flat/fix_punct | lora |
| squad_v1_1_3_0_0 | phi-2 | sordonia/flan-10k-flat/squad_v1_1_3_0_0 | lora |
| coqa_1_0_0 | phi-2 | sordonia/flan-10k-flat/coqa_1_0_0 | lora |
| glue_qnli_2_0_0 | phi-2 | sordonia/flan-10k-flat/glue_qnli_2_0_0 | lora |
| wiki_qa_Jeopardy_style | phi-2 | sordonia/flan-10k-flat/wiki_qa_Jeopardy_style | lora |
| qasc_qa_with_separated_facts_5 | phi-2 | sordonia/flan-10k-flat/qasc_qa_with_separated_facts_5 | lora |
| glue_mnli_2_0_0 | phi-2 | sordonia/flan-10k-flat/glue_mnli_2_0_0 | lora |
| wiki_bio_key_content | phi-2 | sordonia/flan-10k-flat/wiki_bio_key_content | lora |
| dream_generate_first_utterance | phi-2 | sordonia/flan-10k-flat/dream_generate_first_utterance | lora |
| quartz_read_passage_below_choose | phi-2 | sordonia/flan-10k-flat/quartz_read_passage_below_choose | lora |
| web_questions_question_answer | phi-2 | sordonia/flan-10k-flat/web_questions_question_answer | lora |
| glue_stsb_2_0_0 | phi-2 | sordonia/flan-10k-flat/glue_stsb_2_0_0 | lora |
| wmt16_translate_tr_en_1_0_0 | phi-2 | sordonia/flan-10k-flat/wmt16_translate_tr_en_1_0_0 | lora |
| cot_qasc | phi-2 | sordonia/flan-10k-flat/cot_qasc | lora |
| duorc_ParaphraseRC_title_generation | phi-2 | sordonia/flan-10k-flat/duorc_ParaphraseRC_title_generation | lora |
| quail_description_context_question_answer_id | phi-2 | sordonia/flan-10k-flat/quail_description_context_question_answer_id | lora |
| wiki_qa_Topic_Prediction_Question_Only | phi-2 | sordonia/flan-10k-flat/wiki_qa_Topic_Prediction_Question_Only | lora |
| quoref_Find_Answer | phi-2 | sordonia/flan-10k-flat/quoref_Find_Answer | lora |
| social_i_qa_I_was_wondering | phi-2 | sordonia/flan-10k-flat/social_i_qa_I_was_wondering | lora |
| wiki_hop_original_choose_best_object_affirmative_3 | phi-2 | sordonia/flan-10k-flat/wiki_hop_original_choose_best_object_affirmative_3 | lora |
| duorc_ParaphraseRC_build_story_around_qa | phi-2 | sordonia/flan-10k-flat/duorc_ParaphraseRC_build_story_around_qa | lora |
| qasc_qa_with_separated_facts_3 | phi-2 | sordonia/flan-10k-flat/qasc_qa_with_separated_facts_3 | lora |
| race_middle_Is_this_the_right_answer | phi-2 | sordonia/flan-10k-flat/race_middle_Is_this_the_right_answer | lora |
| paws_wiki_1_1_0 | phi-2 | sordonia/flan-10k-flat/paws_wiki_1_1_0 | lora |
| app_reviews_categorize_rating_using_review | phi-2 | sordonia/flan-10k-flat/app_reviews_categorize_rating_using_review | lora |
| anli_r3_0_1_0 | phi-2 | sordonia/flan-10k-flat/anli_r3_0_1_0 | lora |
| app_reviews_convert_to_rating | phi-2 | sordonia/flan-10k-flat/app_reviews_convert_to_rating | lora |
| wiqa_what_is_the_final_step_of_the_following_process | phi-2 | sordonia/flan-10k-flat/wiqa_what_is_the_final_step_of_the_following_process | lora |
| adversarial_qa_droberta_answer_the_following_q | phi-2 | sordonia/flan-10k-flat/adversarial_qa_droberta_answer_the_following_q | lora |
| wiki_qa_Decide_good_answer | phi-2 | sordonia/flan-10k-flat/wiki_qa_Decide_good_answer | lora |
| adversarial_qa_dbert_answer_the_following_q | phi-2 | sordonia/flan-10k-flat/adversarial_qa_dbert_answer_the_following_q | lora |
| gem_dart_1_1_0 | phi-2 | sordonia/flan-10k-flat/gem_dart_1_1_0 | lora |
| adversarial_qa_dbert_tell_what_it_is | phi-2 | sordonia/flan-10k-flat/adversarial_qa_dbert_tell_what_it_is | lora |
| quarel_choose_between | phi-2 | sordonia/flan-10k-flat/quarel_choose_between | lora |
| duorc_ParaphraseRC_generate_question_by_answer | phi-2 | sordonia/flan-10k-flat/duorc_ParaphraseRC_generate_question_by_answer | lora |
| wiki_hop_original_generate_subject | phi-2 | sordonia/flan-10k-flat/wiki_hop_original_generate_subject | lora |
| dream_baseline | phi-2 | sordonia/flan-10k-flat/dream_baseline | lora |
| cos_e_v1_11_question_description_option_text | phi-2 | sordonia/flan-10k-flat/cos_e_v1_11_question_description_option_text | lora |
| aeslc_1_0_0 | phi-2 | sordonia/flan-10k-flat/aeslc_1_0_0 | lora |
| anli_r2_0_1_0 | phi-2 | sordonia/flan-10k-flat/anli_r2_0_1_0 | lora |
| dbpedia_14_given_list_what_category_does_the_paragraph_belong_to | phi-2 | sordonia/flan-10k-flat/dbpedia_14_given_list_what_category_does_the_paragraph_belong_to | lora |
| quail_context_question_description_answer_id | phi-2 | sordonia/flan-10k-flat/quail_context_question_description_answer_id | lora |
| race_middle_Select_the_best_answer_no_instructions_ | phi-2 | sordonia/flan-10k-flat/race_middle_Select_the_best_answer_no_instructions_ | lora |
| wmt16_translate_ro_en_1_0_0 | phi-2 | sordonia/flan-10k-flat/wmt16_translate_ro_en_1_0_0 | lora |
| race_high_Is_this_the_right_answer | phi-2 | sordonia/flan-10k-flat/race_high_Is_this_the_right_answer | lora |
| quail_description_context_question_text | phi-2 | sordonia/flan-10k-flat/quail_description_context_question_text | lora |
| sciq_Direct_Question_Closed_Book_ | phi-2 | sordonia/flan-10k-flat/sciq_Direct_Question_Closed_Book_ | lora |
| openbookqa_0_1_0 | phi-2 | sordonia/flan-10k-flat/openbookqa_0_1_0 | lora |
| duorc_SelfRC_title_generation | phi-2 | sordonia/flan-10k-flat/duorc_SelfRC_title_generation | lora |
| cot_gsm8k | phi-2 | sordonia/flan-10k-flat/cot_gsm8k | lora |
| quartz_answer_question_below | phi-2 | sordonia/flan-10k-flat/quartz_answer_question_below | lora |
| snli_1_1_0 | phi-2 | sordonia/flan-10k-flat/snli_1_1_0 | lora |
| sciq_Multiple_Choice_Closed_Book_ | phi-2 | sordonia/flan-10k-flat/sciq_Multiple_Choice_Closed_Book_ | lora |
| cot_strategyqa | phi-2 | sordonia/flan-10k-flat/cot_strategyqa | lora |
| qasc_qa_with_separated_facts_4 | phi-2 | sordonia/flan-10k-flat/qasc_qa_with_separated_facts_4 | lora |
| ropes_prompt_bottom_no_hint | phi-2 | sordonia/flan-10k-flat/ropes_prompt_bottom_no_hint | lora |
| duorc_SelfRC_generate_question | phi-2 | sordonia/flan-10k-flat/duorc_SelfRC_generate_question | lora |
| quartz_given_the_fact_answer_the_q | phi-2 | sordonia/flan-10k-flat/quartz_given_the_fact_answer_the_q | lora |
| anli_r1_0_1_0 | phi-2 | sordonia/flan-10k-flat/anli_r1_0_1_0 | lora |
| wiki_qa_Topic_Prediction_Question_and_Answer_Pair | phi-2 | sordonia/flan-10k-flat/wiki_qa_Topic_Prediction_Question_and_Answer_Pair | lora |
| wiki_qa_Direct_Answer_to_Question | phi-2 | sordonia/flan-10k-flat/wiki_qa_Direct_Answer_to_Question | lora |
| qasc_is_correct_2 | phi-2 | sordonia/flan-10k-flat/qasc_is_correct_2 | lora |
| wiki_hop_original_generate_subject_and_object | phi-2 | sordonia/flan-10k-flat/wiki_hop_original_generate_subject_and_object | lora |
| ai2_arc_ARC_Challenge_1_0_0 | phi-2 | sordonia/flan-10k-flat/ai2_arc_ARC_Challenge_1_0_0 | lora |
| race_middle_Select_the_best_answer_generate_span_ | phi-2 | sordonia/flan-10k-flat/race_middle_Select_the_best_answer_generate_span_ | lora |
| quail_context_question_answer_description_text | phi-2 | sordonia/flan-10k-flat/quail_context_question_answer_description_text | lora |
| quail_context_question_description_text | phi-2 | sordonia/flan-10k-flat/quail_context_question_description_text | lora |
| wiki_hop_original_choose_best_object_interrogative_2 | phi-2 | sordonia/flan-10k-flat/wiki_hop_original_choose_best_object_interrogative_2 | lora |
| duorc_SelfRC_movie_director | phi-2 | sordonia/flan-10k-flat/duorc_SelfRC_movie_director | lora |
| quoref_Given_Context_Answer_Question | phi-2 | sordonia/flan-10k-flat/quoref_Given_Context_Answer_Question | lora |
| wiki_hop_original_explain_relation | phi-2 | sordonia/flan-10k-flat/wiki_hop_original_explain_relation | lora |
| super_glue_record_1_0_2 | phi-2 | sordonia/flan-10k-flat/super_glue_record_1_0_2 | lora |
| adversarial_qa_dbidaf_tell_what_it_is | phi-2 | sordonia/flan-10k-flat/adversarial_qa_dbidaf_tell_what_it_is | lora |
| cot_ecqa_ii | phi-2 | sordonia/flan-10k-flat/cot_ecqa_ii | lora |
| ropes_background_new_situation_answer | phi-2 | sordonia/flan-10k-flat/ropes_background_new_situation_answer | lora |
| web_questions_short_general_knowledge_q | phi-2 | sordonia/flan-10k-flat/web_questions_short_general_knowledge_q | lora |
| wiqa_what_might_be_the_first_step_of_the_process | phi-2 | sordonia/flan-10k-flat/wiqa_what_might_be_the_first_step_of_the_process | lora |
| duorc_SelfRC_answer_question | phi-2 | sordonia/flan-10k-flat/duorc_SelfRC_answer_question | lora |
| ag_news_subset_1_0_0 | phi-2 | sordonia/flan-10k-flat/ag_news_subset_1_0_0 | lora |
| race_middle_Write_a_multi_choice_question_for_the_following_article | phi-2 | sordonia/flan-10k-flat/race_middle_Write_a_multi_choice_question_for_the_following_article | lora |
| wmt14_translate_fr_en_1_0_0 | phi-2 | sordonia/flan-10k-flat/wmt14_translate_fr_en_1_0_0 | lora |
| sciq_Direct_Question | phi-2 | sordonia/flan-10k-flat/sciq_Direct_Question | lora |
| super_glue_multirc_1_0_2 | phi-2 | sordonia/flan-10k-flat/super_glue_multirc_1_0_2 | lora |
| dbpedia_14_given_a_choice_of_categories_ | phi-2 | sordonia/flan-10k-flat/dbpedia_14_given_a_choice_of_categories_ | lora |
| super_glue_wic_1_0_2 | phi-2 | sordonia/flan-10k-flat/super_glue_wic_1_0_2 | lora |
| social_i_qa_Show_choices_and_generate_answer | phi-2 | sordonia/flan-10k-flat/social_i_qa_Show_choices_and_generate_answer | lora |
| wiqa_what_might_be_the_last_step_of_the_process | phi-2 | sordonia/flan-10k-flat/wiqa_what_might_be_the_last_step_of_the_process | lora |
| quoref_Answer_Question_Given_Context | phi-2 | sordonia/flan-10k-flat/quoref_Answer_Question_Given_Context | lora |
| quoref_Context_Contains_Answer | phi-2 | sordonia/flan-10k-flat/quoref_Context_Contains_Answer | lora |
| cos_e_v1_11_description_question_option_text | phi-2 | sordonia/flan-10k-flat/cos_e_v1_11_description_question_option_text | lora |
| adversarial_qa_dbert_based_on | phi-2 | sordonia/flan-10k-flat/adversarial_qa_dbert_based_on | lora |
| multi_news_1_0_0 | phi-2 | sordonia/flan-10k-flat/multi_news_1_0_0 | lora |
| cos_e_v1_11_generate_explanation_given_text | phi-2 | sordonia/flan-10k-flat/cos_e_v1_11_generate_explanation_given_text | lora |
| true_case | phi-2 | sordonia/flan-10k-flat/true_case | lora |
| duorc_ParaphraseRC_movie_director | phi-2 | sordonia/flan-10k-flat/duorc_ParaphraseRC_movie_director | lora |
| quartz_answer_question_based_on | phi-2 | sordonia/flan-10k-flat/quartz_answer_question_based_on | lora |
| bool_q_1_0_0 | phi-2 | sordonia/flan-10k-flat/bool_q_1_0_0 | lora |
| quoref_Guess_Answer | phi-2 | sordonia/flan-10k-flat/quoref_Guess_Answer | lora |
| quarel_do_not_use | phi-2 | sordonia/flan-10k-flat/quarel_do_not_use | lora |
| cos_e_v1_11_explain_why_human | phi-2 | sordonia/flan-10k-flat/cos_e_v1_11_explain_why_human | lora |
| wiki_qa_Generate_Question_from_Topic | phi-2 | sordonia/flan-10k-flat/wiki_qa_Generate_Question_from_Topic | lora |
| kilt_tasks_hotpotqa_straighforward_qa | phi-2 | sordonia/flan-10k-flat/kilt_tasks_hotpotqa_straighforward_qa | lora |
| adversarial_qa_dbidaf_generate_question | phi-2 | sordonia/flan-10k-flat/adversarial_qa_dbidaf_generate_question | lora |
| dbpedia_14_pick_one_category_for_the_following_text | phi-2 | sordonia/flan-10k-flat/dbpedia_14_pick_one_category_for_the_following_text | lora |
| kilt_tasks_hotpotqa_final_exam | phi-2 | sordonia/flan-10k-flat/kilt_tasks_hotpotqa_final_exam | lora |
| quoref_Answer_Friend_Question | phi-2 | sordonia/flan-10k-flat/quoref_Answer_Friend_Question | lora |
| race_high_Write_a_multi_choice_question_for_the_following_article | phi-2 | sordonia/flan-10k-flat/race_high_Write_a_multi_choice_question_for_the_following_article | lora |
| ropes_prompt_beginning | phi-2 | sordonia/flan-10k-flat/ropes_prompt_beginning | lora |
| adversarial_qa_dbert_question_context_answer | phi-2 | sordonia/flan-10k-flat/adversarial_qa_dbert_question_context_answer | lora |
| cot_creak | phi-2 | sordonia/flan-10k-flat/cot_creak | lora |
| gem_e2e_nlg_1_1_0 | phi-2 | sordonia/flan-10k-flat/gem_e2e_nlg_1_1_0 | lora |
| cos_e_v1_11_description_question_option_id | phi-2 | sordonia/flan-10k-flat/cos_e_v1_11_description_question_option_id | lora |
| social_i_qa_Generate_the_question_from_the_answer | phi-2 | sordonia/flan-10k-flat/social_i_qa_Generate_the_question_from_the_answer | lora |
| quarel_heres_a_story | phi-2 | sordonia/flan-10k-flat/quarel_heres_a_story | lora |
| social_i_qa_Check_if_a_random_answer_is_valid_or_not | phi-2 | sordonia/flan-10k-flat/social_i_qa_Check_if_a_random_answer_is_valid_or_not | lora |
| ropes_background_situation_middle | phi-2 | sordonia/flan-10k-flat/ropes_background_situation_middle | lora |
| sciq_Multiple_Choice_Question_First | phi-2 | sordonia/flan-10k-flat/sciq_Multiple_Choice_Question_First | lora |
| cot_strategyqa_ii | phi-2 | sordonia/flan-10k-flat/cot_strategyqa_ii | lora |
| huggingface_xsum | phi-2 | sordonia/flan-10k-flat/huggingface_xsum | lora |
| kilt_tasks_hotpotqa_complex_question | phi-2 | sordonia/flan-10k-flat/kilt_tasks_hotpotqa_complex_question | lora |
| wmt16_translate_fi_en_1_0_0 | phi-2 | sordonia/flan-10k-flat/wmt16_translate_fi_en_1_0_0 | lora |
| ai2_arc_ARC_Easy_1_0_0 | phi-2 | sordonia/flan-10k-flat/ai2_arc_ARC_Easy_1_0_0 | lora |
| stream_qed | phi-2 | sordonia/flan-10k-flat/stream_qed | lora |
| definite_pronoun_resolution_1_1_0 | phi-2 | sordonia/flan-10k-flat/definite_pronoun_resolution_1_1_0 | lora |
| super_glue_rte_1_0_2 | phi-2 | sordonia/flan-10k-flat/super_glue_rte_1_0_2 | lora |
| ropes_new_situation_background_answer | phi-2 | sordonia/flan-10k-flat/ropes_new_situation_background_answer | lora |
| dream_read_the_following_conversation_and_answer_the_question | phi-2 | sordonia/flan-10k-flat/dream_read_the_following_conversation_and_answer_the_question | lora |
| cot_sensemaking | phi-2 | sordonia/flan-10k-flat/cot_sensemaking | lora |
| wiki_qa_Topic_Prediction_Answer_Only | phi-2 | sordonia/flan-10k-flat/wiki_qa_Topic_Prediction_Answer_Only | lora |
| duorc_ParaphraseRC_generate_question | phi-2 | sordonia/flan-10k-flat/duorc_ParaphraseRC_generate_question | lora |
| dream_generate_last_utterance | phi-2 | sordonia/flan-10k-flat/dream_generate_last_utterance | lora |
| race_middle_Taking_a_test | phi-2 | sordonia/flan-10k-flat/race_middle_Taking_a_test | lora |
| piqa_1_0_0 | phi-2 | sordonia/flan-10k-flat/piqa_1_0_0 | lora |
| cot_ecqa | phi-2 | sordonia/flan-10k-flat/cot_ecqa | lora |
| glue_mrpc_2_0_0 | phi-2 | sordonia/flan-10k-flat/glue_mrpc_2_0_0 | lora |
| race_middle_Read_the_article_and_answer_the_question_no_option_ | phi-2 | sordonia/flan-10k-flat/race_middle_Read_the_article_and_answer_the_question_no_option_ | lora |
| ropes_plain_background_situation | phi-2 | sordonia/flan-10k-flat/ropes_plain_background_situation | lora |
| quail_description_context_question_answer_text | phi-2 | sordonia/flan-10k-flat/quail_description_context_question_answer_text | lora |
| qasc_qa_with_combined_facts_1 | phi-2 | sordonia/flan-10k-flat/qasc_qa_with_combined_facts_1 | lora |
| duorc_ParaphraseRC_decide_worth_it | phi-2 | sordonia/flan-10k-flat/duorc_ParaphraseRC_decide_worth_it | lora |
| quoref_Answer_Test | phi-2 | sordonia/flan-10k-flat/quoref_Answer_Test | lora |
| wiki_bio_who | phi-2 | sordonia/flan-10k-flat/wiki_bio_who | lora |
| kilt_tasks_hotpotqa_formulate | phi-2 | sordonia/flan-10k-flat/kilt_tasks_hotpotqa_formulate | lora |
| glue_wnli_2_0_0 | phi-2 | sordonia/flan-10k-flat/glue_wnli_2_0_0 | lora |
| gigaword_1_2_0 | phi-2 | sordonia/flan-10k-flat/gigaword_1_2_0 | lora |
| quail_context_description_question_text | phi-2 | sordonia/flan-10k-flat/quail_context_description_question_text | lora |
| dream_answer_to_dialogue | phi-2 | sordonia/flan-10k-flat/dream_answer_to_dialogue | lora |
| cos_e_v1_11_question_option_description_id | phi-2 | sordonia/flan-10k-flat/cos_e_v1_11_question_option_description_id | lora |
| duorc_ParaphraseRC_question_answering | phi-2 | sordonia/flan-10k-flat/duorc_ParaphraseRC_question_answering | lora |
| wiki_qa_automatic_system | phi-2 | sordonia/flan-10k-flat/wiki_qa_automatic_system | lora |
| adversarial_qa_droberta_based_on | phi-2 | sordonia/flan-10k-flat/adversarial_qa_droberta_based_on | lora |
| super_glue_wsc_fixed_1_0_2 | phi-2 | sordonia/flan-10k-flat/super_glue_wsc_fixed_1_0_2 | lora |
| word_segment | phi-2 | sordonia/flan-10k-flat/word_segment | lora |
| quac_1_0_0 | phi-2 | sordonia/flan-10k-flat/quac_1_0_0 | lora |
| quartz_paragraph_question_plain_concat | phi-2 | sordonia/flan-10k-flat/quartz_paragraph_question_plain_concat | lora |
| wiqa_which_of_the_following_is_the_supposed_perturbation | phi-2 | sordonia/flan-10k-flat/wiqa_which_of_the_following_is_the_supposed_perturbation | lora |
| quartz_use_info_from_question_paragraph | phi-2 | sordonia/flan-10k-flat/quartz_use_info_from_question_paragraph | lora |
| ropes_plain_no_background | phi-2 | sordonia/flan-10k-flat/ropes_plain_no_background | lora |
| race_high_Select_the_best_answer_generate_span_ | phi-2 | sordonia/flan-10k-flat/race_high_Select_the_best_answer_generate_span_ | lora |
| glue_cola_2_0_0 | phi-2 | sordonia/flan-10k-flat/glue_cola_2_0_0 | lora |
| social_i_qa_Show_choices_and_generate_index | phi-2 | sordonia/flan-10k-flat/social_i_qa_Show_choices_and_generate_index | lora |
| ropes_prompt_bottom_hint_beginning | phi-2 | sordonia/flan-10k-flat/ropes_prompt_bottom_hint_beginning | lora |
| cot_creak_ii | phi-2 | sordonia/flan-10k-flat/cot_creak_ii | lora |
Last updated on: 2024-04-19 21:11:52+00:00
| {} | zhan1993/private_library_phi2_epoch_1 | null | [
"region:us"
] | null | 2024-04-19T14:41:58+00:00 | [] | [] | TAGS
#region-us
| Number of experts present in the library: 263
| [] | [
"TAGS\n#region-us \n"
] |
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 0.10.1.dev0 | {"library_name": "peft", "base_model": "Trelis/Llama-2-7b-chat-hf-sharded-bf16"} | ManimadhuriE/Llama-2-7b-chat-hf-sharded-bf16-fine-tuned-adapters | null | [
"peft",
"arxiv:1910.09700",
"base_model:Trelis/Llama-2-7b-chat-hf-sharded-bf16",
"region:us"
] | null | 2024-04-19T14:42:06+00:00 | [
"1910.09700"
] | [] | TAGS
#peft #arxiv-1910.09700 #base_model-Trelis/Llama-2-7b-chat-hf-sharded-bf16 #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 0.10.1.dev0 | [
"# 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 0.10.1.dev0"
] | [
"TAGS\n#peft #arxiv-1910.09700 #base_model-Trelis/Llama-2-7b-chat-hf-sharded-bf16 #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 0.10.1.dev0"
] |
reinforcement-learning | null |
# **Reinforce** Agent playing **CartPole-v1**
This is a trained model of a **Reinforce** agent playing **CartPole-v1** .
To learn to use this model and train yours check Unit 4 of the Deep Reinforcement Learning Course: https://huggingface.co/deep-rl-course/unit4/introduction
| {"tags": ["CartPole-v1", "reinforce", "reinforcement-learning", "custom-implementation", "deep-rl-class"], "model-index": [{"name": "Reinforce-cartpole", "results": [{"task": {"type": "reinforcement-learning", "name": "reinforcement-learning"}, "dataset": {"name": "CartPole-v1", "type": "CartPole-v1"}, "metrics": [{"type": "mean_reward", "value": "500.00 +/- 0.00", "name": "mean_reward", "verified": false}]}]}]} | Kommunarus/Reinforce-cartpole | null | [
"CartPole-v1",
"reinforce",
"reinforcement-learning",
"custom-implementation",
"deep-rl-class",
"model-index",
"region:us"
] | null | 2024-04-19T14:42:07+00:00 | [] | [] | TAGS
#CartPole-v1 #reinforce #reinforcement-learning #custom-implementation #deep-rl-class #model-index #region-us
|
# Reinforce Agent playing CartPole-v1
This is a trained model of a Reinforce agent playing CartPole-v1 .
To learn to use this model and train yours check Unit 4 of the Deep Reinforcement Learning Course: URL
| [
"# Reinforce Agent playing CartPole-v1\n This is a trained model of a Reinforce agent playing CartPole-v1 .\n To learn to use this model and train yours check Unit 4 of the Deep Reinforcement Learning Course: URL"
] | [
"TAGS\n#CartPole-v1 #reinforce #reinforcement-learning #custom-implementation #deep-rl-class #model-index #region-us \n",
"# Reinforce Agent playing CartPole-v1\n This is a trained model of a Reinforce agent playing CartPole-v1 .\n To learn to use this model and train yours check Unit 4 of the Deep Reinforcement Learning Course: URL"
] |
text-generation | null |
## 💫 Community Model> Llama 3 70B Instruct by Meta
*👾 [LM Studio](https://lmstudio.ai) Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on [Discord](https://discord.gg/aPQfnNkxGC)*.
**Model creator:** [meta-llama](https://huggingface.co/meta-llama)<br>
**Original model**: [Meta-Llama-3-70B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-70B-Instruct)<br>
**GGUF quantization:** provided by [bartowski](https://huggingface.co/bartowski) based on `llama.cpp` PR [6745](https://github.com/ggerganov/llama.cpp/pull/6745)<br>
## Model Summary:
Llama 3 represents a huge update to the Llama family of models. This model is the 70B parameter instruction tuned model, with performance reaching and usually exceeding GPT-3.5.<br>
This is a massive milestone, as an open model reaches the performance of a closed model over double its size.<br>
This model is very happy to follow the given system prompt, so use this to your advantage to get the behavior you desire.<br>
Llama 3 excels at all the general usage situations, including multi turn conversations, general world knowledge, and coding.<br>
## Prompt Template:
Choose the 'Llama 3' preset in your LM Studio.
Under the hood, the model will see a prompt that's formatted like so:
```
<|begin_of_text|><|start_header_id|>system<|end_header_id|>
{system_prompt}<|eot_id|><|start_header_id|>user<|end_header_id|>
{prompt}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
```
Use cases and examples to come.
## Technical Details
Llama 3 was trained on over 15T tokens from a massively diverse range of subjects and languages, and includes 4 times more code than Llama 2.
This model also features Grouped Attention Query (GQA) so that memory usage scales nicely over large contexts.
Instruction fine tuning was performed with a combination of supervised fine-tuning (SFT), rejection sampling, proximal policy optimization (PPO), and direct policy optimization (DPO).
Only IQ1_M and IQ2_XS use importance matrix (iMatrix), the rest are made with the standard quant algorithms.
Check out their blog post for more information [here](https://ai.meta.com/blog/meta-llama-3/)
## Special thanks
🙏 Special thanks to [Georgi Gerganov](https://github.com/ggerganov) and the whole team working on [llama.cpp](https://github.com/ggerganov/llama.cpp/) for making all of this possible.
🙏 Special thanks to [Kalomaze](https://github.com/kalomaze) for his dataset (linked [here](https://github.com/ggerganov/llama.cpp/discussions/5263)) that was used for calculating the imatrix for the IQ1_M and IQ2_XS quants, which makes them usable even at their tiny size!
## Disclaimers
LM Studio is not the creator, originator, or owner of any Model featured in the Community Model Program. Each Community Model is created and provided by third parties. LM Studio does not endorse, support, represent or guarantee the completeness, truthfulness, accuracy, or reliability of any Community Model. You understand that Community Models can produce content that might be offensive, harmful, inaccurate or otherwise inappropriate, or deceptive. Each Community Model is the sole responsibility of the person or entity who originated such Model. LM Studio may not monitor or control the Community Models and cannot, and does not, take responsibility for any such Model. LM Studio disclaims all warranties or guarantees about the accuracy, reliability or benefits of the Community Models. LM Studio further disclaims any warranty that the Community Model will meet your requirements, be secure, uninterrupted or available at any time or location, or error-free, viruses-free, or that any errors will be corrected, or otherwise. You will be solely responsible for any damage resulting from your use of or access to the Community Models, your downloading of any Community Model, or use of any other Community Model provided by or through LM Studio.
| {"language": ["en"], "tags": ["facebook", "meta", "pytorch", "llama", "llama-3"], "pipeline_tag": "text-generation", "license_name": "llama3", "base_model": "meta-llama/Meta-Llama-3-70B-Instruct", "extra_gated_prompt": "### META LLAMA 3 COMMUNITY LICENSE AGREEMENT\nMeta Llama 3 Version Release Date: April 18, 2024\n\"Agreement\" means the terms and conditions for use, reproduction, distribution and modification of the Llama Materials set forth herein.\n\"Documentation\" means the specifications, manuals and documentation accompanying Meta Llama 3 distributed by Meta at https://llama.meta.com/get-started/.\n\"Licensee\" or \"you\" means you, or your employer or any other person or entity (if you are entering into this Agreement on such person or entity\u2019s behalf), of the age required under applicable laws, rules or regulations to provide legal consent and that has legal authority to bind your employer or such other person or entity if you are entering in this Agreement on their behalf.\n\"Meta Llama 3\" means the foundational large language models and software and algorithms, including machine-learning model code, trained model weights, inference-enabling code, training-enabling code, fine-tuning enabling code and other elements of the foregoing distributed by Meta at https://llama.meta.com/llama-downloads.\n\"Llama Materials\" means, collectively, Meta\u2019s proprietary Meta Llama 3 and Documentation (and any portion thereof) made available under this Agreement.\n\"Meta\" or \"we\" means Meta Platforms Ireland Limited (if you are located in or, if you are an entity, your principal place of business is in the EEA or Switzerland) and Meta Platforms, Inc. (if you are located outside of the EEA or Switzerland).\n \n1. License Rights and Redistribution.\na. Grant of Rights. You are granted a non-exclusive, worldwide, non-transferable and royalty-free limited license under Meta\u2019s intellectual property or other rights owned by Meta embodied in the Llama Materials to use, reproduce, distribute, copy, create derivative works of, and make modifications to the Llama Materials.\nb. Redistribution and Use.\ni. If you distribute or make available the Llama Materials (or any derivative works thereof), or a product or service that uses any of them, including another AI model, you shall (A) provide a copy of this Agreement with any such Llama Materials; and (B) prominently display \u201cBuilt with Meta Llama 3\u201d on a related website, user interface, blogpost, about page, or product documentation. If you use the Llama Materials to create, train, fine tune, or otherwise improve an AI model, which is distributed or made available, you shall also include \u201cLlama 3\u201d at the beginning of any such AI model name.\nii. If you receive Llama Materials, or any derivative works thereof, from a Licensee as part of an integrated end user product, then Section 2 of this Agreement will not apply to you.\niii. You must retain in all copies of the Llama Materials that you distribute the following attribution notice within a \u201cNotice\u201d text file distributed as a part of such copies: \u201cMeta Llama 3 is licensed under the Meta Llama 3 Community License, Copyright \u00a9 Meta Platforms, Inc. All Rights Reserved.\u201d\niv. Your use of the Llama Materials must comply with applicable laws and regulations (including trade compliance laws and regulations) and adhere to the Acceptable Use Policy for the Llama Materials (available at https://llama.meta.com/llama3/use-policy), which is hereby incorporated by reference into this Agreement.\nv. You will not use the Llama Materials or any output or results of the Llama Materials to improve any other large language model (excluding Meta Llama 3 or derivative works thereof).\n2. Additional Commercial Terms. If, on the Meta Llama 3 version release date, the monthly active users of the products or services made available by or for Licensee, or Licensee\u2019s affiliates, is greater than 700 million monthly active users in the preceding calendar month, you must request a license from Meta, which Meta may grant to you in its sole discretion, and you are not authorized to exercise any of the rights under this Agreement unless or until Meta otherwise expressly grants you such rights.\n3. Disclaimer of Warranty. UNLESS REQUIRED BY APPLICABLE LAW, THE LLAMA MATERIALS AND ANY OUTPUT AND RESULTS THEREFROM ARE PROVIDED ON AN \u201cAS IS\u201d BASIS, WITHOUT WARRANTIES OF ANY KIND, AND META DISCLAIMS ALL WARRANTIES OF ANY KIND, BOTH EXPRESS AND IMPLIED, INCLUDING, WITHOUT LIMITATION, ANY WARRANTIES OF TITLE, NON-INFRINGEMENT, MERCHANTABILITY, OR FITNESS FOR A PARTICULAR PURPOSE. YOU ARE SOLELY RESPONSIBLE FOR DETERMINING THE APPROPRIATENESS OF USING OR REDISTRIBUTING THE LLAMA MATERIALS AND ASSUME ANY RISKS ASSOCIATED WITH YOUR USE OF THE LLAMA MATERIALS AND ANY OUTPUT AND RESULTS.\n4. Limitation of Liability. IN NO EVENT WILL META OR ITS AFFILIATES BE LIABLE UNDER ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, TORT, NEGLIGENCE, PRODUCTS LIABILITY, OR OTHERWISE, ARISING OUT OF THIS AGREEMENT, FOR ANY LOST PROFITS OR ANY INDIRECT, SPECIAL, CONSEQUENTIAL, INCIDENTAL, EXEMPLARY OR PUNITIVE DAMAGES, EVEN IF META OR ITS AFFILIATES HAVE BEEN ADVISED OF THE POSSIBILITY OF ANY OF THE FOREGOING.\n5. Intellectual Property.\na. No trademark licenses are granted under this Agreement, and in connection with the Llama Materials, neither Meta nor Licensee may use any name or mark owned by or associated with the other or any of its affiliates, except as required for reasonable and customary use in describing and redistributing the Llama Materials or as set forth in this Section 5(a). Meta hereby grants you a license to use \u201cLlama 3\u201d (the \u201cMark\u201d) solely as required to comply with the last sentence of Section 1.b.i. You will comply with Meta\u2019s brand guidelines (currently accessible at https://about.meta.com/brand/resources/meta/company-brand/ ). All goodwill arising out of your use of the Mark will inure to the benefit of Meta.\nb. Subject to Meta\u2019s ownership of Llama Materials and derivatives made by or for Meta, with respect to any derivative works and modifications of the Llama Materials that are made by you, as between you and Meta, you are and will be the owner of such derivative works and modifications.\nc. If you institute litigation or other proceedings against Meta or any entity (including a cross-claim or counterclaim in a lawsuit) alleging that the Llama Materials or Meta Llama 3 outputs or results, or any portion of any of the foregoing, constitutes infringement of intellectual property or other rights owned or licensable by you, then any licenses granted to you under this Agreement shall terminate as of the date such litigation or claim is filed or instituted. You will indemnify and hold harmless Meta from and against any claim by any third party arising out of or related to your use or distribution of the Llama Materials.\n6. Term and Termination. The term of this Agreement will commence upon your acceptance of this Agreement or access to the Llama Materials and will continue in full force and effect until terminated in accordance with the terms and conditions herein. Meta may terminate this Agreement if you are in breach of any term or condition of this Agreement. Upon termination of this Agreement, you shall delete and cease use of the Llama Materials. Sections 3, 4 and 7 shall survive the termination of this Agreement.\n7. Governing Law and Jurisdiction. This Agreement will be governed and construed under the laws of the State of California without regard to choice of law principles, and the UN Convention on Contracts for the International Sale of Goods does not apply to this Agreement. The courts of California shall have exclusive jurisdiction of any dispute arising out of this Agreement.\n### Meta Llama 3 Acceptable Use Policy\nMeta is committed to promoting safe and fair use of its tools and features, including Meta Llama 3. If you access or use Meta Llama 3, you agree to this Acceptable Use Policy (\u201cPolicy\u201d). The most recent copy of this policy can be found at [https://llama.meta.com/llama3/use-policy](https://llama.meta.com/llama3/use-policy)\n#### Prohibited Uses\nWe want everyone to use Meta Llama 3 safely and responsibly. You agree you will not use, or allow others to use, Meta Llama 3 to: 1. Violate the law or others\u2019 rights, including to:\n 1. Engage in, promote, generate, contribute to, encourage, plan, incite, or further illegal or unlawful activity or content, such as:\n 1. Violence or terrorism\n 2. Exploitation or harm to children, including the solicitation, creation, acquisition, or dissemination of child exploitative content or failure to report Child Sexual Abuse Material\n 3. Human trafficking, exploitation, and sexual violence\n 4. The illegal distribution of information or materials to minors, including obscene materials, or failure to employ legally required age-gating in connection with such information or materials.\n 5. Sexual solicitation\n 6. Any other criminal activity\n 2. Engage in, promote, incite, or facilitate the harassment, abuse, threatening, or bullying of individuals or groups of individuals\n 3. Engage in, promote, incite, or facilitate discrimination or other unlawful or harmful conduct in the provision of employment, employment benefits, credit, housing, other economic benefits, or other essential goods and services\n 4. Engage in the unauthorized or unlicensed practice of any profession including, but not limited to, financial, legal, medical/health, or related professional practices\n 5. Collect, process, disclose, generate, or infer health, demographic, or other sensitive personal or private information about individuals without rights and consents required by applicable laws\n 6. Engage in or facilitate any action or generate any content that infringes, misappropriates, or otherwise violates any third-party rights, including the outputs or results of any products or services using the Llama Materials\n 7. Create, generate, or facilitate the creation of malicious code, malware, computer viruses or do anything else that could disable, overburden, interfere with or impair the proper working, integrity, operation or appearance of a website or computer system\n2. Engage in, promote, incite, facilitate, or assist in the planning or development of activities that present a risk of death or bodily harm to individuals, including use of Meta Llama 3 related to the following:\n 1. Military, warfare, nuclear industries or applications, espionage, use for materials or activities that are subject to the International Traffic Arms Regulations (ITAR) maintained by the United States Department of State\n 2. Guns and illegal weapons (including weapon development)\n 3. Illegal drugs and regulated/controlled substances\n 4. Operation of critical infrastructure, transportation technologies, or heavy machinery\n 5. Self-harm or harm to others, including suicide, cutting, and eating disorders\n 6. Any content intended to incite or promote violence, abuse, or any infliction of bodily harm to an individual\n3. Intentionally deceive or mislead others, including use of Meta Llama 3 related to the following:\n 1. Generating, promoting, or furthering fraud or the creation or promotion of disinformation\n 2. Generating, promoting, or furthering defamatory content, including the creation of defamatory statements, images, or other content\n 3. Generating, promoting, or further distributing spam\n 4. Impersonating another individual without consent, authorization, or legal right\n 5. Representing that the use of Meta Llama 3 or outputs are human-generated\n 6. Generating or facilitating false online engagement, including fake reviews and other means of fake online engagement\n4. Fail to appropriately disclose to end users any known dangers of your AI system\nPlease report any violation of this Policy, software \u201cbug,\u201d or other problems that could lead to a violation of this Policy through one of the following means:\n * Reporting issues with the model: [https://github.com/meta-llama/llama3](https://github.com/meta-llama/llama3)\n * Reporting risky content generated by the model:\n developers.facebook.com/llama_output_feedback\n * Reporting bugs and security concerns: facebook.com/whitehat/info\n * Reporting violations of the Acceptable Use Policy or unlicensed uses of Meta Llama 3: [email protected]", "extra_gated_fields": {"First Name": "text", "Last Name": "text", "Date of birth": "date_picker", "Country": "country", "Affiliation": "text", "geo": "ip_location", "By clicking Submit below I accept the terms of the license and acknowledge that the information I provide will be collected stored processed and shared in accordance with the Meta Privacy Policy": "checkbox"}, "extra_gated_description": "The information you provide will be collected, stored, processed and shared in accordance with the [Meta Privacy Policy](https://www.facebook.com/privacy/policy/).", "extra_gated_button_content": "Submit", "quantized_by": "bartowski", "lm_studio": {"param_count": "70b", "use_case": "general", "release_date": "18-04-2024", "model_creator": "meta-llama", "prompt_template": "Llama 3", "system_prompt": "You are a helpful AI assistant.", "base_model": "llama", "original_repo": "meta-llama/Meta-Llama-3-70B-Instruct"}} | lmstudio-community/Meta-Llama-3-70B-Instruct-GGUF | null | [
"gguf",
"facebook",
"meta",
"pytorch",
"llama",
"llama-3",
"text-generation",
"en",
"base_model:meta-llama/Meta-Llama-3-70B-Instruct",
"region:us"
] | null | 2024-04-19T14:44:48+00:00 | [] | [
"en"
] | TAGS
#gguf #facebook #meta #pytorch #llama #llama-3 #text-generation #en #base_model-meta-llama/Meta-Llama-3-70B-Instruct #region-us
|
## Community Model> Llama 3 70B Instruct by Meta
* LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord*.
Model creator: meta-llama<br>
Original model: Meta-Llama-3-70B-Instruct<br>
GGUF quantization: provided by bartowski based on 'URL' PR 6745<br>
## Model Summary:
Llama 3 represents a huge update to the Llama family of models. This model is the 70B parameter instruction tuned model, with performance reaching and usually exceeding GPT-3.5.<br>
This is a massive milestone, as an open model reaches the performance of a closed model over double its size.<br>
This model is very happy to follow the given system prompt, so use this to your advantage to get the behavior you desire.<br>
Llama 3 excels at all the general usage situations, including multi turn conversations, general world knowledge, and coding.<br>
## Prompt Template:
Choose the 'Llama 3' preset in your LM Studio.
Under the hood, the model will see a prompt that's formatted like so:
Use cases and examples to come.
## Technical Details
Llama 3 was trained on over 15T tokens from a massively diverse range of subjects and languages, and includes 4 times more code than Llama 2.
This model also features Grouped Attention Query (GQA) so that memory usage scales nicely over large contexts.
Instruction fine tuning was performed with a combination of supervised fine-tuning (SFT), rejection sampling, proximal policy optimization (PPO), and direct policy optimization (DPO).
Only IQ1_M and IQ2_XS use importance matrix (iMatrix), the rest are made with the standard quant algorithms.
Check out their blog post for more information here
## Special thanks
Special thanks to Georgi Gerganov and the whole team working on URL for making all of this possible.
Special thanks to Kalomaze for his dataset (linked here) that was used for calculating the imatrix for the IQ1_M and IQ2_XS quants, which makes them usable even at their tiny size!
## Disclaimers
LM Studio is not the creator, originator, or owner of any Model featured in the Community Model Program. Each Community Model is created and provided by third parties. LM Studio does not endorse, support, represent or guarantee the completeness, truthfulness, accuracy, or reliability of any Community Model. You understand that Community Models can produce content that might be offensive, harmful, inaccurate or otherwise inappropriate, or deceptive. Each Community Model is the sole responsibility of the person or entity who originated such Model. LM Studio may not monitor or control the Community Models and cannot, and does not, take responsibility for any such Model. LM Studio disclaims all warranties or guarantees about the accuracy, reliability or benefits of the Community Models. LM Studio further disclaims any warranty that the Community Model will meet your requirements, be secure, uninterrupted or available at any time or location, or error-free, viruses-free, or that any errors will be corrected, or otherwise. You will be solely responsible for any damage resulting from your use of or access to the Community Models, your downloading of any Community Model, or use of any other Community Model provided by or through LM Studio.
| [
"## Community Model> Llama 3 70B Instruct by Meta\n\n* LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord*.\n\nModel creator: meta-llama<br>\nOriginal model: Meta-Llama-3-70B-Instruct<br>\nGGUF quantization: provided by bartowski based on 'URL' PR 6745<br>",
"## Model Summary:\nLlama 3 represents a huge update to the Llama family of models. This model is the 70B parameter instruction tuned model, with performance reaching and usually exceeding GPT-3.5.<br>\nThis is a massive milestone, as an open model reaches the performance of a closed model over double its size.<br>\nThis model is very happy to follow the given system prompt, so use this to your advantage to get the behavior you desire.<br>\nLlama 3 excels at all the general usage situations, including multi turn conversations, general world knowledge, and coding.<br>",
"## Prompt Template:\n\nChoose the 'Llama 3' preset in your LM Studio. \n\nUnder the hood, the model will see a prompt that's formatted like so:\n\n\n\nUse cases and examples to come.",
"## Technical Details\n\nLlama 3 was trained on over 15T tokens from a massively diverse range of subjects and languages, and includes 4 times more code than Llama 2.\n\nThis model also features Grouped Attention Query (GQA) so that memory usage scales nicely over large contexts.\n\nInstruction fine tuning was performed with a combination of supervised fine-tuning (SFT), rejection sampling, proximal policy optimization (PPO), and direct policy optimization (DPO).\n\nOnly IQ1_M and IQ2_XS use importance matrix (iMatrix), the rest are made with the standard quant algorithms.\n\nCheck out their blog post for more information here",
"## Special thanks\n\n Special thanks to Georgi Gerganov and the whole team working on URL for making all of this possible.\n\n Special thanks to Kalomaze for his dataset (linked here) that was used for calculating the imatrix for the IQ1_M and IQ2_XS quants, which makes them usable even at their tiny size!",
"## Disclaimers\n\nLM Studio is not the creator, originator, or owner of any Model featured in the Community Model Program. Each Community Model is created and provided by third parties. LM Studio does not endorse, support, represent or guarantee the completeness, truthfulness, accuracy, or reliability of any Community Model. You understand that Community Models can produce content that might be offensive, harmful, inaccurate or otherwise inappropriate, or deceptive. Each Community Model is the sole responsibility of the person or entity who originated such Model. LM Studio may not monitor or control the Community Models and cannot, and does not, take responsibility for any such Model. LM Studio disclaims all warranties or guarantees about the accuracy, reliability or benefits of the Community Models. LM Studio further disclaims any warranty that the Community Model will meet your requirements, be secure, uninterrupted or available at any time or location, or error-free, viruses-free, or that any errors will be corrected, or otherwise. You will be solely responsible for any damage resulting from your use of or access to the Community Models, your downloading of any Community Model, or use of any other Community Model provided by or through LM Studio."
] | [
"TAGS\n#gguf #facebook #meta #pytorch #llama #llama-3 #text-generation #en #base_model-meta-llama/Meta-Llama-3-70B-Instruct #region-us \n",
"## Community Model> Llama 3 70B Instruct by Meta\n\n* LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord*.\n\nModel creator: meta-llama<br>\nOriginal model: Meta-Llama-3-70B-Instruct<br>\nGGUF quantization: provided by bartowski based on 'URL' PR 6745<br>",
"## Model Summary:\nLlama 3 represents a huge update to the Llama family of models. This model is the 70B parameter instruction tuned model, with performance reaching and usually exceeding GPT-3.5.<br>\nThis is a massive milestone, as an open model reaches the performance of a closed model over double its size.<br>\nThis model is very happy to follow the given system prompt, so use this to your advantage to get the behavior you desire.<br>\nLlama 3 excels at all the general usage situations, including multi turn conversations, general world knowledge, and coding.<br>",
"## Prompt Template:\n\nChoose the 'Llama 3' preset in your LM Studio. \n\nUnder the hood, the model will see a prompt that's formatted like so:\n\n\n\nUse cases and examples to come.",
"## Technical Details\n\nLlama 3 was trained on over 15T tokens from a massively diverse range of subjects and languages, and includes 4 times more code than Llama 2.\n\nThis model also features Grouped Attention Query (GQA) so that memory usage scales nicely over large contexts.\n\nInstruction fine tuning was performed with a combination of supervised fine-tuning (SFT), rejection sampling, proximal policy optimization (PPO), and direct policy optimization (DPO).\n\nOnly IQ1_M and IQ2_XS use importance matrix (iMatrix), the rest are made with the standard quant algorithms.\n\nCheck out their blog post for more information here",
"## Special thanks\n\n Special thanks to Georgi Gerganov and the whole team working on URL for making all of this possible.\n\n Special thanks to Kalomaze for his dataset (linked here) that was used for calculating the imatrix for the IQ1_M and IQ2_XS quants, which makes them usable even at their tiny size!",
"## Disclaimers\n\nLM Studio is not the creator, originator, or owner of any Model featured in the Community Model Program. Each Community Model is created and provided by third parties. LM Studio does not endorse, support, represent or guarantee the completeness, truthfulness, accuracy, or reliability of any Community Model. You understand that Community Models can produce content that might be offensive, harmful, inaccurate or otherwise inappropriate, or deceptive. Each Community Model is the sole responsibility of the person or entity who originated such Model. LM Studio may not monitor or control the Community Models and cannot, and does not, take responsibility for any such Model. LM Studio disclaims all warranties or guarantees about the accuracy, reliability or benefits of the Community Models. LM Studio further disclaims any warranty that the Community Model will meet your requirements, be secure, uninterrupted or available at any time or location, or error-free, viruses-free, or that any errors will be corrected, or otherwise. You will be solely responsible for any damage resulting from your use of or access to the Community Models, your downloading of any Community Model, or use of any other Community Model provided by or through LM Studio."
] |
text-generation | transformers |
# Uploaded model
- **Developed by:** thisurawz1
- **License:** apache-2.0
- **Finetuned from model :** unsloth/llama-3-8b-bnb-4bit
This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
| {"language": ["en"], "license": "apache-2.0", "tags": ["text-generation-inference", "transformers", "unsloth", "llama", "trl", "sft"], "base_model": "unsloth/llama-3-8b-bnb-4bit"} | thisurawz1/llama3_unsloth | null | [
"transformers",
"safetensors",
"llama",
"text-generation",
"text-generation-inference",
"unsloth",
"trl",
"sft",
"conversational",
"en",
"base_model:unsloth/llama-3-8b-bnb-4bit",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | null | 2024-04-19T14:45:27+00:00 | [] | [
"en"
] | TAGS
#transformers #safetensors #llama #text-generation #text-generation-inference #unsloth #trl #sft #conversational #en #base_model-unsloth/llama-3-8b-bnb-4bit #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us
|
# Uploaded model
- Developed by: thisurawz1
- License: apache-2.0
- Finetuned from model : unsloth/llama-3-8b-bnb-4bit
This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.
<img src="URL width="200"/>
| [
"# Uploaded model\n\n- Developed by: thisurawz1\n- License: apache-2.0\n- Finetuned from model : unsloth/llama-3-8b-bnb-4bit\n\nThis llama model was trained 2x faster with Unsloth and Huggingface's TRL library.\n\n<img src=\"URL width=\"200\"/>"
] | [
"TAGS\n#transformers #safetensors #llama #text-generation #text-generation-inference #unsloth #trl #sft #conversational #en #base_model-unsloth/llama-3-8b-bnb-4bit #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us \n",
"# Uploaded model\n\n- Developed by: thisurawz1\n- License: apache-2.0\n- Finetuned from model : unsloth/llama-3-8b-bnb-4bit\n\nThis llama model was trained 2x faster with Unsloth and Huggingface's TRL library.\n\n<img src=\"URL width=\"200\"/>"
] |
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="Asubramanian19/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}]}]}]} | Asubramanian19/q-FrozenLake-v1-4x4-noSlippery | null | [
"FrozenLake-v1-4x4-no_slippery",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
] | null | 2024-04-19T14:47:35+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"
] |
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": []} | JorgeVieyra/codegen-350M-mono-python-18k-alpaca | null | [
"transformers",
"safetensors",
"codegen",
"text-generation",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | null | 2024-04-19T14:48:17+00:00 | [
"1910.09700"
] | [] | TAGS
#transformers #safetensors #codegen #text-generation #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 #codegen #text-generation #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 | trl |
# Weni/WeniGPT-Agents-Mistral-1.0.6-SFT-1.0.4-DPO
This model is a fine-tuned version of [Weni/WeniGPT-Agents-Mistral-1.0.6-SFT-merged] on the dataset Weni/wenigpt-agent-dpo-1.0.0 with the DPO trainer. It is part of the WeniGPT project for [Weni](https://weni.ai/).
Description: Experiment on DPO with other hyperparameters and best SFT model of WeniGPT
It achieves the following results on the evaluation set:
{'eval_loss': 0.42961153388023376, 'eval_runtime': 8.5144, 'eval_samples_per_second': 3.289, 'eval_steps_per_second': 1.644, 'eval_rewards/chosen': 2.170013666152954, 'eval_rewards/rejected': -0.6894403696060181, 'eval_rewards/accuracies': 0.4285714328289032, 'eval_rewards/margins': 2.8594539165496826, 'eval_logps/rejected': -98.09535217285156, 'eval_logps/chosen': -47.96824264526367, 'eval_logits/rejected': -1.8433464765548706, 'eval_logits/chosen': -1.8190696239471436, 'epoch': 11.9}
## Intended uses & limitations
This model has not been trained to avoid specific intructions.
## Training procedure
Finetuning was done on the model Weni/WeniGPT-Agents-Mistral-1.0.6-SFT-merged with the following prompt:
```
---------------------
System_prompt:
Agora você se chama {name}, você é {occupation} e seu objetivo é {chatbot_goal}. O adjetivo que mais define a sua personalidade é {adjective} e você se comporta da seguinte forma:
{instructions_formatted}
{context_statement}
Lista de requisitos:
- Responda de forma natural, mas nunca fale sobre um assunto fora do contexto.
- Nunca traga informações do seu próprio conhecimento.
- Repito é crucial que você responda usando apenas informações do contexto.
- Nunca mencione o contexto fornecido.
- Nunca mencione a pergunta fornecida.
- Gere a resposta mais útil possível para a pergunta usando informações do conexto acima.
- Nunca elabore sobre o porque e como você fez a tarefa, apenas responda.
---------------------
```
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-06
- per_device_train_batch_size: 2
- per_device_eval_batch_size: 2
- gradient_accumulation_steps: 2
- num_gpus: 1
- total_train_batch_size: 4
- optimizer: AdamW
- lr_scheduler_type: cosine
- num_steps: 732
- quantization_type: bitsandbytes
- LoRA: ("\n - bits: 4\n - use_exllama: True\n - device_map: auto\n - use_cache: False\n - lora_r: 8\n - lora_alpha: 16\n - lora_dropout: 0.05\n - bias: none\n - target_modules: ['v_proj', 'q_proj']\n - task_type: CAUSAL_LM",)
### Training results
### Framework versions
- transformers==4.38.2
- datasets==2.18.0
- peft==0.10.0
- safetensors==0.4.2
- evaluate==0.4.1
- bitsandbytes==0.43
- huggingface_hub==0.22.2
- seqeval==1.2.2
- optimum==1.18.1
- auto-gptq==0.7.1
- gpustat==1.1.1
- deepspeed==0.14.0
- wandb==0.16.6
- trl==0.8.1
- accelerate==0.29.2
- coloredlogs==15.0.1
- traitlets==5.14.2
- autoawq@https://github.com/casper-hansen/AutoAWQ/releases/download/v0.2.4/autoawq-0.2.4+cu118-cp310-cp310-linux_x86_64.whl
### Hardware
- Cloud provided: runpod.io
| {"language": ["pt"], "license": "mit", "library_name": "trl", "tags": ["DPO", "WeniGPT"], "base_model": "Weni/WeniGPT-Agents-Mistral-1.0.6-SFT-merged", "model-index": [{"name": "Weni/WeniGPT-Agents-Mistral-1.0.6-SFT-1.0.4-DPO", "results": []}]} | Weni/WeniGPT-Agents-Mistral-1.0.6-SFT-1.0.4-DPO | null | [
"trl",
"safetensors",
"DPO",
"WeniGPT",
"pt",
"base_model:Weni/WeniGPT-Agents-Mistral-1.0.6-SFT-merged",
"license:mit",
"region:us"
] | null | 2024-04-19T14:48:47+00:00 | [] | [
"pt"
] | TAGS
#trl #safetensors #DPO #WeniGPT #pt #base_model-Weni/WeniGPT-Agents-Mistral-1.0.6-SFT-merged #license-mit #region-us
|
# Weni/WeniGPT-Agents-Mistral-1.0.6-SFT-1.0.4-DPO
This model is a fine-tuned version of [Weni/WeniGPT-Agents-Mistral-1.0.6-SFT-merged] on the dataset Weni/wenigpt-agent-dpo-1.0.0 with the DPO trainer. It is part of the WeniGPT project for Weni.
Description: Experiment on DPO with other hyperparameters and best SFT model of WeniGPT
It achieves the following results on the evaluation set:
{'eval_loss': 0.42961153388023376, 'eval_runtime': 8.5144, 'eval_samples_per_second': 3.289, 'eval_steps_per_second': 1.644, 'eval_rewards/chosen': 2.170013666152954, 'eval_rewards/rejected': -0.6894403696060181, 'eval_rewards/accuracies': 0.4285714328289032, 'eval_rewards/margins': 2.8594539165496826, 'eval_logps/rejected': -98.09535217285156, 'eval_logps/chosen': -47.96824264526367, 'eval_logits/rejected': -1.8433464765548706, 'eval_logits/chosen': -1.8190696239471436, 'epoch': 11.9}
## Intended uses & limitations
This model has not been trained to avoid specific intructions.
## Training procedure
Finetuning was done on the model Weni/WeniGPT-Agents-Mistral-1.0.6-SFT-merged with the following prompt:
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-06
- per_device_train_batch_size: 2
- per_device_eval_batch_size: 2
- gradient_accumulation_steps: 2
- num_gpus: 1
- total_train_batch_size: 4
- optimizer: AdamW
- lr_scheduler_type: cosine
- num_steps: 732
- quantization_type: bitsandbytes
- LoRA: ("\n - bits: 4\n - use_exllama: True\n - device_map: auto\n - use_cache: False\n - lora_r: 8\n - lora_alpha: 16\n - lora_dropout: 0.05\n - bias: none\n - target_modules: ['v_proj', 'q_proj']\n - task_type: CAUSAL_LM",)
### Training results
### Framework versions
- transformers==4.38.2
- datasets==2.18.0
- peft==0.10.0
- safetensors==0.4.2
- evaluate==0.4.1
- bitsandbytes==0.43
- huggingface_hub==0.22.2
- seqeval==1.2.2
- optimum==1.18.1
- auto-gptq==0.7.1
- gpustat==1.1.1
- deepspeed==0.14.0
- wandb==0.16.6
- trl==0.8.1
- accelerate==0.29.2
- coloredlogs==15.0.1
- traitlets==5.14.2
- autoawq@URL
### Hardware
- Cloud provided: URL
| [
"# Weni/WeniGPT-Agents-Mistral-1.0.6-SFT-1.0.4-DPO\n\nThis model is a fine-tuned version of [Weni/WeniGPT-Agents-Mistral-1.0.6-SFT-merged] on the dataset Weni/wenigpt-agent-dpo-1.0.0 with the DPO trainer. It is part of the WeniGPT project for Weni.\nDescription: Experiment on DPO with other hyperparameters and best SFT model of WeniGPT\n\nIt achieves the following results on the evaluation set:\n{'eval_loss': 0.42961153388023376, 'eval_runtime': 8.5144, 'eval_samples_per_second': 3.289, 'eval_steps_per_second': 1.644, 'eval_rewards/chosen': 2.170013666152954, 'eval_rewards/rejected': -0.6894403696060181, 'eval_rewards/accuracies': 0.4285714328289032, 'eval_rewards/margins': 2.8594539165496826, 'eval_logps/rejected': -98.09535217285156, 'eval_logps/chosen': -47.96824264526367, 'eval_logits/rejected': -1.8433464765548706, 'eval_logits/chosen': -1.8190696239471436, 'epoch': 11.9}",
"## Intended uses & limitations\n\nThis model has not been trained to avoid specific intructions.",
"## Training procedure\n\nFinetuning was done on the model Weni/WeniGPT-Agents-Mistral-1.0.6-SFT-merged with the following prompt:",
"### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 5e-06\n- per_device_train_batch_size: 2\n- per_device_eval_batch_size: 2\n- gradient_accumulation_steps: 2\n- num_gpus: 1\n- total_train_batch_size: 4\n- optimizer: AdamW\n- lr_scheduler_type: cosine\n- num_steps: 732\n- quantization_type: bitsandbytes\n- LoRA: (\"\\n - bits: 4\\n - use_exllama: True\\n - device_map: auto\\n - use_cache: False\\n - lora_r: 8\\n - lora_alpha: 16\\n - lora_dropout: 0.05\\n - bias: none\\n - target_modules: ['v_proj', 'q_proj']\\n - task_type: CAUSAL_LM\",)",
"### Training results",
"### Framework versions\n\n- transformers==4.38.2\n- datasets==2.18.0\n- peft==0.10.0\n- safetensors==0.4.2\n- evaluate==0.4.1\n- bitsandbytes==0.43\n- huggingface_hub==0.22.2\n- seqeval==1.2.2\n- optimum==1.18.1\n- auto-gptq==0.7.1\n- gpustat==1.1.1\n- deepspeed==0.14.0\n- wandb==0.16.6\n- trl==0.8.1\n- accelerate==0.29.2\n- coloredlogs==15.0.1\n- traitlets==5.14.2\n- autoawq@URL",
"### Hardware\n- Cloud provided: URL"
] | [
"TAGS\n#trl #safetensors #DPO #WeniGPT #pt #base_model-Weni/WeniGPT-Agents-Mistral-1.0.6-SFT-merged #license-mit #region-us \n",
"# Weni/WeniGPT-Agents-Mistral-1.0.6-SFT-1.0.4-DPO\n\nThis model is a fine-tuned version of [Weni/WeniGPT-Agents-Mistral-1.0.6-SFT-merged] on the dataset Weni/wenigpt-agent-dpo-1.0.0 with the DPO trainer. It is part of the WeniGPT project for Weni.\nDescription: Experiment on DPO with other hyperparameters and best SFT model of WeniGPT\n\nIt achieves the following results on the evaluation set:\n{'eval_loss': 0.42961153388023376, 'eval_runtime': 8.5144, 'eval_samples_per_second': 3.289, 'eval_steps_per_second': 1.644, 'eval_rewards/chosen': 2.170013666152954, 'eval_rewards/rejected': -0.6894403696060181, 'eval_rewards/accuracies': 0.4285714328289032, 'eval_rewards/margins': 2.8594539165496826, 'eval_logps/rejected': -98.09535217285156, 'eval_logps/chosen': -47.96824264526367, 'eval_logits/rejected': -1.8433464765548706, 'eval_logits/chosen': -1.8190696239471436, 'epoch': 11.9}",
"## Intended uses & limitations\n\nThis model has not been trained to avoid specific intructions.",
"## Training procedure\n\nFinetuning was done on the model Weni/WeniGPT-Agents-Mistral-1.0.6-SFT-merged with the following prompt:",
"### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 5e-06\n- per_device_train_batch_size: 2\n- per_device_eval_batch_size: 2\n- gradient_accumulation_steps: 2\n- num_gpus: 1\n- total_train_batch_size: 4\n- optimizer: AdamW\n- lr_scheduler_type: cosine\n- num_steps: 732\n- quantization_type: bitsandbytes\n- LoRA: (\"\\n - bits: 4\\n - use_exllama: True\\n - device_map: auto\\n - use_cache: False\\n - lora_r: 8\\n - lora_alpha: 16\\n - lora_dropout: 0.05\\n - bias: none\\n - target_modules: ['v_proj', 'q_proj']\\n - task_type: CAUSAL_LM\",)",
"### Training results",
"### Framework versions\n\n- transformers==4.38.2\n- datasets==2.18.0\n- peft==0.10.0\n- safetensors==0.4.2\n- evaluate==0.4.1\n- bitsandbytes==0.43\n- huggingface_hub==0.22.2\n- seqeval==1.2.2\n- optimum==1.18.1\n- auto-gptq==0.7.1\n- gpustat==1.1.1\n- deepspeed==0.14.0\n- wandb==0.16.6\n- trl==0.8.1\n- accelerate==0.29.2\n- coloredlogs==15.0.1\n- traitlets==5.14.2\n- autoawq@URL",
"### Hardware\n- Cloud provided: URL"
] |
object-detection | 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. -->
# sensetime-deformable-detr-finetuned-10k-cppe5
This model is a fine-tuned version of [SenseTime/deformable-detr](https://huggingface.co/SenseTime/deformable-detr) on the cppe-5 dataset.
It achieves the following results on the evaluation set:
- Loss: 1.1028
- Map: 0.2808
- Map 50: 0.5257
- Map 75: 0.2589
- Map Small: 0.2879
- Map Medium: 0.1953
- Map Large: 0.4546
- Mar 1: 0.3004
- Mar 10: 0.5007
- Mar 100: 0.534
- Mar Small: 0.4339
- Mar Medium: 0.4079
- Mar Large: 0.7629
- Map Coverall: 0.5566
- Mar 100 Coverall: 0.7331
- Map Face Shield: 0.2761
- Mar 100 Face Shield: 0.549
- Map Gloves: 0.1484
- Mar 100 Gloves: 0.3943
- Map Goggles: 0.1271
- Mar 100 Goggles: 0.5085
- Map Mask: 0.2956
- Mar 100 Mask: 0.4853
## 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: 4
- eval_batch_size: 8
- seed: 1337
- gradient_accumulation_steps: 2
- total_train_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 100.0
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss | Map | Map 50 | Map 75 | Map Small | Map Medium | Map Large | Mar 1 | Mar 10 | Mar 100 | Mar Small | Mar Medium | Mar Large | Map Coverall | Mar 100 Coverall | Map Face Shield | Mar 100 Face Shield | Map Gloves | Mar 100 Gloves | Map Goggles | Mar 100 Goggles | Map Mask | Mar 100 Mask |
|:-------------:|:-------:|:-----:|:---------------:|:------:|:------:|:------:|:---------:|:----------:|:---------:|:------:|:------:|:-------:|:---------:|:----------:|:---------:|:------------:|:----------------:|:---------------:|:-------------------:|:----------:|:--------------:|:-----------:|:---------------:|:--------:|:------------:|
| 9.1039 | 0.9953 | 106 | 2.6450 | 0.0073 | 0.0229 | 0.0025 | 0.0 | 0.0001 | 0.0088 | 0.0123 | 0.0311 | 0.0381 | 0.0009 | 0.0248 | 0.0329 | 0.0358 | 0.1186 | 0.0001 | 0.0204 | 0.0 | 0.0066 | 0.0002 | 0.0034 | 0.0002 | 0.0417 |
| 2.3921 | 2.0 | 213 | 2.4742 | 0.0067 | 0.0207 | 0.0017 | 0.0009 | 0.0009 | 0.008 | 0.0157 | 0.0582 | 0.0923 | 0.0038 | 0.0276 | 0.1516 | 0.0296 | 0.3349 | 0.0011 | 0.0327 | 0.0 | 0.0199 | 0.0016 | 0.0203 | 0.0013 | 0.0536 |
| 2.28 | 2.9953 | 319 | 2.5260 | 0.0064 | 0.0198 | 0.0024 | 0.0342 | 0.0005 | 0.0063 | 0.0124 | 0.0547 | 0.0777 | 0.1079 | 0.0291 | 0.0848 | 0.0294 | 0.2849 | 0.0009 | 0.0082 | 0.0 | 0.0057 | 0.0 | 0.0 | 0.0019 | 0.0896 |
| 2.1883 | 4.0 | 426 | 2.2302 | 0.0077 | 0.0193 | 0.006 | 0.0013 | 0.001 | 0.0126 | 0.0259 | 0.0653 | 0.1098 | 0.0109 | 0.035 | 0.1264 | 0.0323 | 0.4203 | 0.0 | 0.0 | 0.0 | 0.01 | 0.0023 | 0.0119 | 0.0036 | 0.1066 |
| 2.1263 | 4.9953 | 532 | 2.1512 | 0.0105 | 0.0306 | 0.0069 | 0.0021 | 0.0015 | 0.0105 | 0.0323 | 0.0757 | 0.1144 | 0.0199 | 0.0328 | 0.1168 | 0.0467 | 0.45 | 0.0001 | 0.002 | 0.0001 | 0.0175 | 0.0 | 0.0 | 0.0058 | 0.1024 |
| 2.0232 | 6.0 | 639 | 2.1045 | 0.0133 | 0.0323 | 0.0103 | 0.0049 | 0.0023 | 0.0143 | 0.0357 | 0.0882 | 0.1265 | 0.0147 | 0.044 | 0.1458 | 0.0575 | 0.4773 | 0.0 | 0.0 | 0.0002 | 0.0147 | 0.0 | 0.0 | 0.0086 | 0.1403 |
| 2.0103 | 6.9953 | 745 | 2.1646 | 0.0219 | 0.0466 | 0.0178 | 0.0049 | 0.0015 | 0.0232 | 0.0438 | 0.1018 | 0.1274 | 0.0085 | 0.0471 | 0.1658 | 0.1033 | 0.4698 | 0.0013 | 0.0184 | 0.0001 | 0.0251 | 0.0003 | 0.0136 | 0.0046 | 0.1104 |
| 1.9723 | 8.0 | 852 | 1.9693 | 0.021 | 0.052 | 0.0165 | 0.0048 | 0.0036 | 0.0274 | 0.039 | 0.113 | 0.1558 | 0.0241 | 0.053 | 0.2211 | 0.0881 | 0.5407 | 0.0029 | 0.0286 | 0.0001 | 0.0265 | 0.0007 | 0.0119 | 0.013 | 0.1716 |
| 1.9425 | 8.9953 | 958 | 1.9505 | 0.0199 | 0.0505 | 0.0148 | 0.003 | 0.0051 | 0.0195 | 0.0387 | 0.1041 | 0.1534 | 0.0233 | 0.0595 | 0.1477 | 0.0826 | 0.564 | 0.0037 | 0.0122 | 0.0001 | 0.0156 | 0.0003 | 0.0068 | 0.0126 | 0.1682 |
| 1.8248 | 10.0 | 1065 | 1.9128 | 0.0237 | 0.0603 | 0.0166 | 0.0064 | 0.0079 | 0.0335 | 0.0558 | 0.137 | 0.1739 | 0.0569 | 0.089 | 0.1711 | 0.0872 | 0.5314 | 0.015 | 0.0939 | 0.0002 | 0.019 | 0.0018 | 0.0492 | 0.0143 | 0.1763 |
| 1.7923 | 10.9953 | 1171 | 1.8334 | 0.0281 | 0.0628 | 0.0223 | 0.0069 | 0.0081 | 0.0302 | 0.0546 | 0.1543 | 0.204 | 0.0577 | 0.1129 | 0.2174 | 0.1088 | 0.5523 | 0.0103 | 0.0857 | 0.0002 | 0.0265 | 0.0048 | 0.1424 | 0.0163 | 0.2133 |
| 1.7922 | 12.0 | 1278 | 1.8679 | 0.0405 | 0.0964 | 0.0281 | 0.0165 | 0.0126 | 0.0444 | 0.0596 | 0.1629 | 0.2031 | 0.0387 | 0.1127 | 0.2102 | 0.1462 | 0.5709 | 0.0299 | 0.1408 | 0.0002 | 0.0213 | 0.0099 | 0.0966 | 0.0163 | 0.1858 |
| 1.7797 | 12.9953 | 1384 | 1.7715 | 0.036 | 0.0739 | 0.0337 | 0.0066 | 0.0089 | 0.042 | 0.0647 | 0.1644 | 0.2102 | 0.0472 | 0.1088 | 0.2326 | 0.1429 | 0.5924 | 0.014 | 0.1082 | 0.0006 | 0.0469 | 0.0016 | 0.0797 | 0.0207 | 0.2237 |
| 1.6925 | 14.0 | 1491 | 1.7633 | 0.0427 | 0.0897 | 0.044 | 0.0073 | 0.0069 | 0.0564 | 0.061 | 0.163 | 0.2152 | 0.0631 | 0.1133 | 0.2339 | 0.1819 | 0.5988 | 0.0063 | 0.0429 | 0.0007 | 0.0493 | 0.0069 | 0.1695 | 0.0175 | 0.2156 |
| 1.6927 | 14.9953 | 1597 | 1.7455 | 0.0429 | 0.0973 | 0.0311 | 0.0081 | 0.0139 | 0.0464 | 0.0718 | 0.196 | 0.243 | 0.059 | 0.1603 | 0.2494 | 0.1594 | 0.5959 | 0.0283 | 0.1592 | 0.0008 | 0.0559 | 0.0069 | 0.1627 | 0.0191 | 0.2412 |
| 1.6409 | 16.0 | 1704 | 1.6922 | 0.0414 | 0.1001 | 0.0295 | 0.0186 | 0.0152 | 0.0447 | 0.0612 | 0.203 | 0.2566 | 0.0805 | 0.1605 | 0.3192 | 0.1449 | 0.5965 | 0.0235 | 0.151 | 0.0012 | 0.073 | 0.0108 | 0.2254 | 0.0264 | 0.237 |
| 1.6535 | 16.9953 | 1810 | 1.6837 | 0.0508 | 0.0973 | 0.0468 | 0.011 | 0.021 | 0.0457 | 0.088 | 0.2063 | 0.2565 | 0.0518 | 0.1584 | 0.2943 | 0.1717 | 0.6256 | 0.0426 | 0.1694 | 0.0007 | 0.0507 | 0.0081 | 0.1712 | 0.0307 | 0.2654 |
| 1.5853 | 18.0 | 1917 | 1.6565 | 0.0424 | 0.0842 | 0.0379 | 0.0103 | 0.0177 | 0.0497 | 0.0954 | 0.2317 | 0.2809 | 0.0502 | 0.1839 | 0.3685 | 0.1457 | 0.639 | 0.0169 | 0.1673 | 0.002 | 0.0986 | 0.0155 | 0.2339 | 0.0318 | 0.2659 |
| 1.5743 | 18.9953 | 2023 | 1.6498 | 0.0409 | 0.0877 | 0.0367 | 0.0989 | 0.0149 | 0.0487 | 0.1 | 0.2277 | 0.2841 | 0.2421 | 0.1812 | 0.3256 | 0.1417 | 0.6535 | 0.0225 | 0.2286 | 0.0025 | 0.1052 | 0.0073 | 0.1407 | 0.0306 | 0.2924 |
| 1.5241 | 20.0 | 2130 | 1.6974 | 0.0496 | 0.1014 | 0.0484 | 0.0401 | 0.0168 | 0.0579 | 0.099 | 0.2179 | 0.2668 | 0.0939 | 0.1701 | 0.3058 | 0.179 | 0.632 | 0.0278 | 0.2531 | 0.003 | 0.0825 | 0.0096 | 0.1525 | 0.0283 | 0.2137 |
| 1.5431 | 20.9953 | 2236 | 1.5908 | 0.0584 | 0.1168 | 0.0529 | 0.098 | 0.0376 | 0.0581 | 0.1182 | 0.2721 | 0.3191 | 0.15 | 0.2129 | 0.3986 | 0.1837 | 0.6558 | 0.0505 | 0.3224 | 0.0039 | 0.1005 | 0.0151 | 0.2508 | 0.0388 | 0.2659 |
| 1.5106 | 22.0 | 2343 | 1.6095 | 0.0593 | 0.1366 | 0.0445 | 0.0125 | 0.0284 | 0.0639 | 0.1034 | 0.2407 | 0.2845 | 0.063 | 0.1819 | 0.3299 | 0.1892 | 0.6238 | 0.0521 | 0.2327 | 0.006 | 0.1118 | 0.0147 | 0.1864 | 0.0345 | 0.2678 |
| 1.5372 | 22.9953 | 2449 | 1.5951 | 0.0636 | 0.1316 | 0.0576 | 0.0282 | 0.0416 | 0.0537 | 0.1163 | 0.266 | 0.312 | 0.0853 | 0.2239 | 0.3533 | 0.1781 | 0.6052 | 0.0692 | 0.3286 | 0.008 | 0.1393 | 0.0153 | 0.1983 | 0.0475 | 0.2886 |
| 1.4386 | 24.0 | 2556 | 1.5187 | 0.0622 | 0.123 | 0.0587 | 0.0185 | 0.0405 | 0.0661 | 0.1229 | 0.2786 | 0.3385 | 0.0898 | 0.2326 | 0.4092 | 0.1881 | 0.6599 | 0.0659 | 0.351 | 0.0061 | 0.1332 | 0.0147 | 0.2407 | 0.0362 | 0.3076 |
| 1.4267 | 24.9953 | 2662 | 1.5143 | 0.0664 | 0.1359 | 0.0569 | 0.0405 | 0.0475 | 0.0664 | 0.1284 | 0.2935 | 0.3396 | 0.0994 | 0.2523 | 0.3919 | 0.1845 | 0.6512 | 0.0576 | 0.3204 | 0.0088 | 0.1393 | 0.0233 | 0.2508 | 0.0576 | 0.3365 |
| 1.397 | 26.0 | 2769 | 1.5084 | 0.0689 | 0.1464 | 0.0617 | 0.0567 | 0.047 | 0.0686 | 0.1508 | 0.3158 | 0.363 | 0.1653 | 0.2526 | 0.453 | 0.1731 | 0.6605 | 0.0708 | 0.3796 | 0.009 | 0.1569 | 0.0347 | 0.2932 | 0.057 | 0.3246 |
| 1.3846 | 26.9953 | 2875 | 1.4379 | 0.077 | 0.1554 | 0.0671 | 0.052 | 0.0457 | 0.0747 | 0.1576 | 0.3191 | 0.3686 | 0.2459 | 0.2615 | 0.4191 | 0.2061 | 0.6762 | 0.0678 | 0.3939 | 0.0154 | 0.19 | 0.027 | 0.2136 | 0.069 | 0.3692 |
| 1.3763 | 28.0 | 2982 | 1.4605 | 0.0727 | 0.1483 | 0.0675 | 0.0761 | 0.037 | 0.0817 | 0.1428 | 0.3136 | 0.3706 | 0.1434 | 0.2537 | 0.4855 | 0.2099 | 0.6663 | 0.0653 | 0.398 | 0.0116 | 0.1801 | 0.0247 | 0.2678 | 0.052 | 0.3408 |
| 1.3449 | 28.9953 | 3088 | 1.4449 | 0.0808 | 0.1637 | 0.0757 | 0.1455 | 0.0567 | 0.0952 | 0.1746 | 0.3383 | 0.3933 | 0.3418 | 0.2831 | 0.5146 | 0.2091 | 0.6779 | 0.0717 | 0.4449 | 0.0119 | 0.1635 | 0.032 | 0.3085 | 0.0794 | 0.3716 |
| 1.3355 | 30.0 | 3195 | 1.4498 | 0.0727 | 0.1544 | 0.0677 | 0.0271 | 0.0509 | 0.0832 | 0.1562 | 0.3189 | 0.3589 | 0.2176 | 0.2815 | 0.4364 | 0.2056 | 0.6715 | 0.0554 | 0.3245 | 0.0152 | 0.1773 | 0.0149 | 0.2458 | 0.0723 | 0.3754 |
| 1.3218 | 30.9953 | 3301 | 1.4156 | 0.0784 | 0.1641 | 0.0656 | 0.0608 | 0.0528 | 0.0978 | 0.1575 | 0.3344 | 0.3867 | 0.1655 | 0.2825 | 0.5141 | 0.2088 | 0.686 | 0.0624 | 0.398 | 0.0211 | 0.21 | 0.0238 | 0.2661 | 0.0761 | 0.3735 |
| 1.2773 | 32.0 | 3408 | 1.3722 | 0.0823 | 0.1682 | 0.0764 | 0.0641 | 0.056 | 0.1128 | 0.1602 | 0.3656 | 0.4143 | 0.1975 | 0.308 | 0.5599 | 0.2192 | 0.6913 | 0.0704 | 0.449 | 0.0199 | 0.2213 | 0.0216 | 0.3153 | 0.0803 | 0.3948 |
| 1.2839 | 32.9953 | 3514 | 1.3795 | 0.09 | 0.186 | 0.0785 | 0.0733 | 0.0697 | 0.14 | 0.1867 | 0.3742 | 0.416 | 0.2753 | 0.2984 | 0.5739 | 0.2294 | 0.693 | 0.0819 | 0.4673 | 0.0212 | 0.2218 | 0.0293 | 0.3119 | 0.0883 | 0.3858 |
| 1.2384 | 34.0 | 3621 | 1.3960 | 0.1002 | 0.2061 | 0.0858 | 0.0783 | 0.0594 | 0.1223 | 0.175 | 0.36 | 0.4115 | 0.2457 | 0.2905 | 0.5741 | 0.2479 | 0.6895 | 0.0775 | 0.402 | 0.0246 | 0.2479 | 0.0371 | 0.3136 | 0.114 | 0.4047 |
| 1.2495 | 34.9953 | 3727 | 1.3261 | 0.1007 | 0.2102 | 0.087 | 0.0847 | 0.0659 | 0.1473 | 0.1918 | 0.3789 | 0.4263 | 0.2146 | 0.3201 | 0.5737 | 0.246 | 0.7035 | 0.0753 | 0.4204 | 0.0362 | 0.2588 | 0.0315 | 0.3593 | 0.1145 | 0.3896 |
| 1.2032 | 36.0 | 3834 | 1.3012 | 0.1024 | 0.2052 | 0.0886 | 0.105 | 0.0723 | 0.157 | 0.1899 | 0.394 | 0.4376 | 0.2237 | 0.3284 | 0.5945 | 0.2543 | 0.6907 | 0.0731 | 0.4673 | 0.0369 | 0.272 | 0.0294 | 0.3542 | 0.1184 | 0.4038 |
| 1.2024 | 36.9953 | 3940 | 1.2989 | 0.107 | 0.2271 | 0.0844 | 0.2679 | 0.0987 | 0.1728 | 0.1961 | 0.4048 | 0.4467 | 0.3934 | 0.348 | 0.5898 | 0.2451 | 0.7035 | 0.0819 | 0.449 | 0.0419 | 0.2773 | 0.0373 | 0.3814 | 0.1288 | 0.4223 |
| 1.1714 | 38.0 | 4047 | 1.3187 | 0.1186 | 0.2361 | 0.1052 | 0.0464 | 0.0813 | 0.16 | 0.1932 | 0.3883 | 0.4304 | 0.2583 | 0.321 | 0.6007 | 0.3029 | 0.7058 | 0.0951 | 0.4143 | 0.0472 | 0.2739 | 0.0372 | 0.3373 | 0.1108 | 0.4209 |
| 1.1702 | 38.9953 | 4153 | 1.3017 | 0.1158 | 0.2338 | 0.1025 | 0.1431 | 0.0923 | 0.1729 | 0.1998 | 0.4178 | 0.4544 | 0.2428 | 0.3371 | 0.6742 | 0.2624 | 0.7134 | 0.0981 | 0.4694 | 0.0458 | 0.2981 | 0.0427 | 0.3559 | 0.1299 | 0.4351 |
| 1.1745 | 40.0 | 4260 | 1.2802 | 0.1167 | 0.2351 | 0.1035 | 0.0578 | 0.095 | 0.1591 | 0.2099 | 0.4126 | 0.4571 | 0.3426 | 0.3457 | 0.6024 | 0.2627 | 0.7174 | 0.1144 | 0.4939 | 0.0403 | 0.29 | 0.0334 | 0.3407 | 0.1328 | 0.4436 |
| 1.1502 | 40.9953 | 4366 | 1.2797 | 0.1283 | 0.2538 | 0.1168 | 0.082 | 0.0831 | 0.1653 | 0.2048 | 0.4136 | 0.4552 | 0.322 | 0.3349 | 0.6206 | 0.301 | 0.7169 | 0.1078 | 0.449 | 0.0513 | 0.3085 | 0.043 | 0.3627 | 0.1382 | 0.4389 |
| 1.1149 | 42.0 | 4473 | 1.2880 | 0.134 | 0.2744 | 0.1197 | 0.1218 | 0.1095 | 0.2147 | 0.2133 | 0.4295 | 0.4717 | 0.2168 | 0.3639 | 0.7173 | 0.3046 | 0.7238 | 0.1305 | 0.5286 | 0.0479 | 0.3005 | 0.0425 | 0.3746 | 0.1445 | 0.4313 |
| 1.1224 | 42.9953 | 4579 | 1.2321 | 0.1477 | 0.2839 | 0.1314 | 0.1361 | 0.1143 | 0.2275 | 0.22 | 0.4406 | 0.4751 | 0.3523 | 0.3623 | 0.6821 | 0.3288 | 0.7326 | 0.1463 | 0.4918 | 0.0582 | 0.3242 | 0.0434 | 0.3915 | 0.1616 | 0.4355 |
| 1.0958 | 44.0 | 4686 | 1.2293 | 0.1416 | 0.2833 | 0.1279 | 0.1761 | 0.1067 | 0.2186 | 0.2211 | 0.4368 | 0.4815 | 0.3122 | 0.3702 | 0.6796 | 0.3046 | 0.732 | 0.1434 | 0.4959 | 0.054 | 0.3171 | 0.0355 | 0.3915 | 0.1702 | 0.4711 |
| 1.081 | 44.9953 | 4792 | 1.2400 | 0.1403 | 0.2807 | 0.1243 | 0.1979 | 0.1054 | 0.24 | 0.2378 | 0.4331 | 0.4761 | 0.3035 | 0.3484 | 0.7158 | 0.297 | 0.7291 | 0.1405 | 0.4959 | 0.0624 | 0.328 | 0.0345 | 0.3814 | 0.167 | 0.446 |
| 1.0659 | 46.0 | 4899 | 1.2180 | 0.1518 | 0.2984 | 0.1404 | 0.0926 | 0.1198 | 0.2352 | 0.2261 | 0.4455 | 0.4907 | 0.3604 | 0.3798 | 0.6992 | 0.3282 | 0.7262 | 0.1433 | 0.5102 | 0.0668 | 0.3502 | 0.0452 | 0.4085 | 0.1757 | 0.4583 |
| 1.0741 | 46.9953 | 5005 | 1.2355 | 0.1501 | 0.3066 | 0.1381 | 0.2278 | 0.1125 | 0.2314 | 0.2259 | 0.4356 | 0.4874 | 0.3453 | 0.3694 | 0.6911 | 0.3114 | 0.7134 | 0.1447 | 0.5367 | 0.0688 | 0.336 | 0.0354 | 0.3763 | 0.1904 | 0.4744 |
| 1.074 | 48.0 | 5112 | 1.2082 | 0.1495 | 0.2917 | 0.1343 | 0.0927 | 0.1293 | 0.2343 | 0.2247 | 0.4535 | 0.4956 | 0.346 | 0.396 | 0.712 | 0.3327 | 0.732 | 0.1477 | 0.5122 | 0.056 | 0.3498 | 0.0308 | 0.4237 | 0.1805 | 0.4602 |
| 1.067 | 48.9953 | 5218 | 1.2123 | 0.165 | 0.3104 | 0.1467 | 0.0957 | 0.1188 | 0.2524 | 0.2522 | 0.4578 | 0.5 | 0.3661 | 0.3737 | 0.7116 | 0.3553 | 0.7291 | 0.1624 | 0.5286 | 0.0706 | 0.3417 | 0.0463 | 0.422 | 0.1902 | 0.4787 |
| 1.0404 | 50.0 | 5325 | 1.2088 | 0.1569 | 0.3099 | 0.1328 | 0.1295 | 0.1105 | 0.2661 | 0.235 | 0.4425 | 0.4879 | 0.3104 | 0.3708 | 0.7181 | 0.3615 | 0.7273 | 0.1395 | 0.4796 | 0.0763 | 0.3597 | 0.0414 | 0.439 | 0.1658 | 0.4336 |
| 1.052 | 50.9953 | 5431 | 1.1966 | 0.1676 | 0.3345 | 0.1453 | 0.1543 | 0.1219 | 0.2477 | 0.2439 | 0.4492 | 0.493 | 0.2986 | 0.387 | 0.72 | 0.3652 | 0.725 | 0.1442 | 0.502 | 0.0701 | 0.3578 | 0.0622 | 0.4119 | 0.1963 | 0.4682 |
| 1.0249 | 52.0 | 5538 | 1.2046 | 0.1601 | 0.324 | 0.1455 | 0.0884 | 0.1159 | 0.2423 | 0.2383 | 0.4475 | 0.4907 | 0.3318 | 0.3694 | 0.7025 | 0.3368 | 0.7186 | 0.1664 | 0.4959 | 0.072 | 0.3758 | 0.0313 | 0.3915 | 0.1941 | 0.4716 |
| 1.0286 | 52.9953 | 5644 | 1.2160 | 0.1732 | 0.3482 | 0.1486 | 0.0809 | 0.124 | 0.2539 | 0.2465 | 0.4497 | 0.4899 | 0.2724 | 0.3755 | 0.6934 | 0.3827 | 0.7192 | 0.1516 | 0.5061 | 0.0716 | 0.337 | 0.0494 | 0.4322 | 0.2107 | 0.455 |
| 1.0085 | 54.0 | 5751 | 1.2242 | 0.169 | 0.3425 | 0.1446 | 0.0889 | 0.1154 | 0.2541 | 0.2335 | 0.4485 | 0.4852 | 0.3407 | 0.3658 | 0.6959 | 0.3834 | 0.718 | 0.1546 | 0.4959 | 0.0797 | 0.3365 | 0.0465 | 0.4373 | 0.1805 | 0.4384 |
| 1.0105 | 54.9953 | 5857 | 1.1761 | 0.1885 | 0.3678 | 0.1675 | 0.1149 | 0.1313 | 0.2775 | 0.2653 | 0.4731 | 0.5102 | 0.3635 | 0.3872 | 0.724 | 0.4022 | 0.736 | 0.1799 | 0.5429 | 0.0971 | 0.3739 | 0.0536 | 0.4288 | 0.2098 | 0.4692 |
| 0.9725 | 56.0 | 5964 | 1.2053 | 0.1867 | 0.3609 | 0.1665 | 0.2528 | 0.1335 | 0.2908 | 0.2491 | 0.4626 | 0.5064 | 0.3851 | 0.3879 | 0.7348 | 0.4134 | 0.7372 | 0.1765 | 0.5367 | 0.0808 | 0.3398 | 0.0615 | 0.4644 | 0.2013 | 0.454 |
| 0.9825 | 56.9953 | 6070 | 1.1839 | 0.1857 | 0.361 | 0.1718 | 0.1396 | 0.1366 | 0.2957 | 0.2667 | 0.4622 | 0.5012 | 0.3591 | 0.3848 | 0.715 | 0.4079 | 0.7395 | 0.2112 | 0.5245 | 0.0823 | 0.3664 | 0.0412 | 0.4237 | 0.1858 | 0.4517 |
| 0.9768 | 58.0 | 6177 | 1.1782 | 0.1909 | 0.3696 | 0.1677 | 0.1695 | 0.1316 | 0.3046 | 0.2637 | 0.4752 | 0.5143 | 0.3641 | 0.3965 | 0.7246 | 0.4094 | 0.7285 | 0.1889 | 0.5367 | 0.0866 | 0.3758 | 0.0526 | 0.4559 | 0.2171 | 0.4744 |
| 0.9646 | 58.9953 | 6283 | 1.2234 | 0.1752 | 0.3522 | 0.1485 | 0.0982 | 0.1131 | 0.2967 | 0.2342 | 0.4388 | 0.4825 | 0.3028 | 0.3743 | 0.6903 | 0.4095 | 0.711 | 0.1621 | 0.4939 | 0.0666 | 0.3308 | 0.0441 | 0.4322 | 0.1937 | 0.4445 |
| 0.9433 | 60.0 | 6390 | 1.1778 | 0.2039 | 0.3913 | 0.1795 | 0.1085 | 0.1387 | 0.3213 | 0.2627 | 0.4721 | 0.5035 | 0.3112 | 0.3827 | 0.7032 | 0.4448 | 0.7448 | 0.2013 | 0.5245 | 0.0995 | 0.3678 | 0.0554 | 0.422 | 0.2184 | 0.4583 |
| 0.9539 | 60.9953 | 6496 | 1.1710 | 0.2142 | 0.3998 | 0.1909 | 0.0873 | 0.1439 | 0.3343 | 0.258 | 0.4688 | 0.5159 | 0.3227 | 0.3985 | 0.71 | 0.4632 | 0.7448 | 0.2376 | 0.5286 | 0.0976 | 0.3645 | 0.0512 | 0.4661 | 0.2214 | 0.4758 |
| 0.9323 | 62.0 | 6603 | 1.1525 | 0.2241 | 0.4084 | 0.2017 | 0.1758 | 0.1621 | 0.3357 | 0.2827 | 0.4755 | 0.5187 | 0.3303 | 0.3996 | 0.7289 | 0.4692 | 0.7413 | 0.2387 | 0.5367 | 0.1032 | 0.3635 | 0.0586 | 0.4542 | 0.2508 | 0.4976 |
| 0.9312 | 62.9953 | 6709 | 1.1400 | 0.2201 | 0.4184 | 0.1825 | 0.2621 | 0.1752 | 0.3242 | 0.2887 | 0.4916 | 0.531 | 0.4282 | 0.4101 | 0.7258 | 0.4556 | 0.7413 | 0.2209 | 0.5469 | 0.0957 | 0.3716 | 0.0663 | 0.4898 | 0.2622 | 0.5052 |
| 0.9131 | 64.0 | 6816 | 1.1468 | 0.2239 | 0.4165 | 0.2042 | 0.2835 | 0.1687 | 0.3288 | 0.2852 | 0.4906 | 0.5291 | 0.4339 | 0.4064 | 0.7331 | 0.4363 | 0.7302 | 0.2399 | 0.5612 | 0.1086 | 0.3754 | 0.0774 | 0.4847 | 0.2575 | 0.4938 |
| 0.924 | 64.9953 | 6922 | 1.1554 | 0.2301 | 0.4351 | 0.2124 | 0.239 | 0.1666 | 0.357 | 0.2763 | 0.4864 | 0.5214 | 0.3761 | 0.398 | 0.7455 | 0.4637 | 0.725 | 0.2383 | 0.5327 | 0.1101 | 0.3545 | 0.09 | 0.5017 | 0.2487 | 0.4934 |
| 0.9114 | 66.0 | 7029 | 1.1486 | 0.2231 | 0.4351 | 0.2016 | 0.2949 | 0.1585 | 0.3553 | 0.2745 | 0.4848 | 0.5247 | 0.426 | 0.4126 | 0.7391 | 0.4658 | 0.7366 | 0.2095 | 0.5347 | 0.1104 | 0.3768 | 0.0835 | 0.4932 | 0.2465 | 0.482 |
| 0.9218 | 66.9953 | 7135 | 1.1245 | 0.2343 | 0.4329 | 0.2067 | 0.2009 | 0.1752 | 0.3804 | 0.2929 | 0.4957 | 0.5349 | 0.3876 | 0.4202 | 0.7486 | 0.4825 | 0.7494 | 0.2458 | 0.549 | 0.1214 | 0.3915 | 0.0671 | 0.4831 | 0.2549 | 0.5014 |
| 0.8886 | 68.0 | 7242 | 1.1260 | 0.236 | 0.4351 | 0.2162 | 0.2133 | 0.1619 | 0.3728 | 0.2844 | 0.4972 | 0.5283 | 0.3972 | 0.3923 | 0.7581 | 0.4756 | 0.7273 | 0.2387 | 0.549 | 0.1187 | 0.391 | 0.0872 | 0.4678 | 0.2601 | 0.5062 |
| 0.898 | 68.9953 | 7348 | 1.1272 | 0.2419 | 0.4601 | 0.2178 | 0.2485 | 0.1736 | 0.3688 | 0.2919 | 0.4958 | 0.5333 | 0.3847 | 0.41 | 0.7582 | 0.4948 | 0.7314 | 0.2347 | 0.5388 | 0.1286 | 0.3938 | 0.0871 | 0.5 | 0.264 | 0.5024 |
| 0.88 | 70.0 | 7455 | 1.1621 | 0.2398 | 0.4532 | 0.2123 | 0.2639 | 0.1676 | 0.3743 | 0.2785 | 0.4865 | 0.5151 | 0.3999 | 0.3942 | 0.7292 | 0.4905 | 0.7215 | 0.256 | 0.5408 | 0.1072 | 0.3526 | 0.0876 | 0.4746 | 0.2574 | 0.4858 |
| 0.8868 | 70.9953 | 7561 | 1.1089 | 0.2574 | 0.4713 | 0.2332 | 0.2675 | 0.1874 | 0.392 | 0.2957 | 0.5025 | 0.5356 | 0.4084 | 0.4319 | 0.7417 | 0.5181 | 0.7413 | 0.2715 | 0.5571 | 0.13 | 0.3844 | 0.1029 | 0.5017 | 0.2642 | 0.4934 |
| 0.876 | 72.0 | 7668 | 1.1296 | 0.2469 | 0.4705 | 0.2256 | 0.2927 | 0.1699 | 0.3973 | 0.2881 | 0.4892 | 0.5235 | 0.4206 | 0.4026 | 0.7447 | 0.5116 | 0.7314 | 0.2526 | 0.5653 | 0.1131 | 0.3739 | 0.1002 | 0.4542 | 0.257 | 0.4924 |
| 0.8786 | 72.9953 | 7774 | 1.1189 | 0.2503 | 0.4775 | 0.2262 | 0.2579 | 0.1729 | 0.4036 | 0.2811 | 0.4968 | 0.5319 | 0.4364 | 0.4133 | 0.7461 | 0.5128 | 0.7308 | 0.2551 | 0.549 | 0.1207 | 0.3915 | 0.0923 | 0.4915 | 0.2707 | 0.4967 |
| 0.8646 | 74.0 | 7881 | 1.1545 | 0.2503 | 0.4782 | 0.2289 | 0.2576 | 0.1648 | 0.4083 | 0.2792 | 0.4817 | 0.5187 | 0.4232 | 0.3924 | 0.7514 | 0.5224 | 0.7198 | 0.2514 | 0.5224 | 0.1166 | 0.3635 | 0.1066 | 0.5051 | 0.2547 | 0.4825 |
| 0.8624 | 74.9953 | 7987 | 1.1148 | 0.2612 | 0.4931 | 0.2276 | 0.2794 | 0.1776 | 0.4119 | 0.2917 | 0.4974 | 0.5361 | 0.4242 | 0.4151 | 0.7662 | 0.5376 | 0.7401 | 0.2444 | 0.5633 | 0.1307 | 0.3848 | 0.1186 | 0.5119 | 0.275 | 0.4806 |
| 0.838 | 76.0 | 8094 | 1.0995 | 0.2687 | 0.493 | 0.2477 | 0.2754 | 0.1831 | 0.4188 | 0.303 | 0.497 | 0.5302 | 0.3972 | 0.406 | 0.7602 | 0.5425 | 0.7349 | 0.2761 | 0.5367 | 0.1306 | 0.3991 | 0.1082 | 0.4915 | 0.2861 | 0.4886 |
| 0.8483 | 76.9953 | 8200 | 1.1110 | 0.2698 | 0.4914 | 0.2511 | 0.1734 | 0.1845 | 0.4311 | 0.2965 | 0.4996 | 0.532 | 0.405 | 0.4092 | 0.7608 | 0.5616 | 0.7477 | 0.2642 | 0.5367 | 0.135 | 0.3924 | 0.1092 | 0.4966 | 0.2791 | 0.4867 |
| 0.8413 | 78.0 | 8307 | 1.1064 | 0.2644 | 0.4912 | 0.2444 | 0.1873 | 0.1831 | 0.4319 | 0.2896 | 0.4983 | 0.5336 | 0.3939 | 0.4117 | 0.7562 | 0.5319 | 0.7343 | 0.2637 | 0.5265 | 0.1325 | 0.4095 | 0.1126 | 0.5 | 0.2812 | 0.4976 |
| 0.8424 | 78.9953 | 8413 | 1.1112 | 0.2682 | 0.496 | 0.2498 | 0.1394 | 0.184 | 0.4279 | 0.2966 | 0.4985 | 0.5272 | 0.358 | 0.4079 | 0.7394 | 0.552 | 0.7395 | 0.2704 | 0.5429 | 0.1313 | 0.3815 | 0.1094 | 0.5 | 0.2779 | 0.472 |
| 0.8277 | 80.0 | 8520 | 1.1451 | 0.2504 | 0.4758 | 0.2206 | 0.2244 | 0.1643 | 0.4229 | 0.2734 | 0.4878 | 0.517 | 0.3697 | 0.3882 | 0.7498 | 0.5308 | 0.7308 | 0.2379 | 0.5347 | 0.1187 | 0.373 | 0.0919 | 0.4678 | 0.2725 | 0.4787 |
| 0.8269 | 80.9953 | 8626 | 1.1064 | 0.2697 | 0.5029 | 0.2497 | 0.2324 | 0.1932 | 0.4296 | 0.2832 | 0.5024 | 0.5379 | 0.3857 | 0.4293 | 0.7615 | 0.5475 | 0.7424 | 0.2713 | 0.5673 | 0.1481 | 0.3953 | 0.1 | 0.4898 | 0.2818 | 0.4948 |
| 0.8159 | 82.0 | 8733 | 1.1055 | 0.2668 | 0.5022 | 0.2361 | 0.3082 | 0.1789 | 0.4284 | 0.2955 | 0.4975 | 0.5315 | 0.4478 | 0.4038 | 0.7377 | 0.5396 | 0.7267 | 0.2607 | 0.5429 | 0.1491 | 0.4024 | 0.1042 | 0.5051 | 0.2805 | 0.4806 |
| 0.8195 | 82.9953 | 8839 | 1.1321 | 0.2674 | 0.505 | 0.2418 | 0.3007 | 0.1856 | 0.4311 | 0.289 | 0.4912 | 0.528 | 0.4278 | 0.4039 | 0.7507 | 0.5368 | 0.7267 | 0.2728 | 0.5633 | 0.1336 | 0.3863 | 0.1169 | 0.4898 | 0.2772 | 0.4739 |
| 0.8138 | 84.0 | 8946 | 1.1110 | 0.2731 | 0.5061 | 0.2498 | 0.2881 | 0.192 | 0.44 | 0.2935 | 0.503 | 0.5382 | 0.4484 | 0.4141 | 0.7625 | 0.5537 | 0.7407 | 0.272 | 0.5796 | 0.1368 | 0.3863 | 0.1223 | 0.5 | 0.2808 | 0.4844 |
| 0.8113 | 84.9953 | 9052 | 1.1105 | 0.2722 | 0.5054 | 0.255 | 0.2724 | 0.1862 | 0.4388 | 0.2906 | 0.4969 | 0.536 | 0.4272 | 0.412 | 0.7586 | 0.5428 | 0.7314 | 0.2666 | 0.5592 | 0.1484 | 0.4033 | 0.125 | 0.5051 | 0.2784 | 0.481 |
| 0.808 | 86.0 | 9159 | 1.1130 | 0.2733 | 0.5056 | 0.253 | 0.2557 | 0.1873 | 0.4403 | 0.2926 | 0.502 | 0.5359 | 0.4107 | 0.4037 | 0.7613 | 0.5414 | 0.7384 | 0.2814 | 0.5612 | 0.1421 | 0.3948 | 0.1221 | 0.5085 | 0.2798 | 0.4768 |
| 0.8052 | 86.9953 | 9265 | 1.1015 | 0.2786 | 0.5087 | 0.2612 | 0.2996 | 0.192 | 0.4411 | 0.2995 | 0.5082 | 0.5401 | 0.4446 | 0.4152 | 0.7531 | 0.555 | 0.7326 | 0.2882 | 0.5653 | 0.1422 | 0.4076 | 0.1207 | 0.5119 | 0.2867 | 0.4834 |
| 0.7967 | 88.0 | 9372 | 1.1301 | 0.2689 | 0.5019 | 0.2442 | 0.3262 | 0.1843 | 0.4353 | 0.2939 | 0.4921 | 0.5253 | 0.452 | 0.3952 | 0.7619 | 0.5423 | 0.7279 | 0.2769 | 0.5612 | 0.1295 | 0.3668 | 0.1215 | 0.4983 | 0.2745 | 0.472 |
| 0.7837 | 88.9953 | 9478 | 1.1018 | 0.276 | 0.5116 | 0.2489 | 0.2803 | 0.1919 | 0.4484 | 0.304 | 0.5015 | 0.5301 | 0.401 | 0.4065 | 0.7623 | 0.5529 | 0.7308 | 0.2728 | 0.549 | 0.153 | 0.4014 | 0.1207 | 0.4898 | 0.2806 | 0.4796 |
| 0.7865 | 90.0 | 9585 | 1.1292 | 0.2712 | 0.5082 | 0.2462 | 0.2705 | 0.1855 | 0.4462 | 0.2898 | 0.494 | 0.524 | 0.3992 | 0.3985 | 0.7521 | 0.5493 | 0.7267 | 0.2821 | 0.5429 | 0.127 | 0.3673 | 0.1233 | 0.5085 | 0.2742 | 0.4744 |
| 0.7882 | 90.9953 | 9691 | 1.1164 | 0.2766 | 0.5191 | 0.2477 | 0.3024 | 0.1952 | 0.4425 | 0.296 | 0.5001 | 0.529 | 0.4275 | 0.4097 | 0.751 | 0.5528 | 0.7308 | 0.2731 | 0.5347 | 0.1424 | 0.3848 | 0.1298 | 0.5119 | 0.2849 | 0.4829 |
| 0.7887 | 92.0 | 9798 | 1.1070 | 0.2776 | 0.5169 | 0.2512 | 0.2553 | 0.1923 | 0.4504 | 0.2999 | 0.5033 | 0.5333 | 0.4005 | 0.4078 | 0.7665 | 0.5547 | 0.7343 | 0.2719 | 0.5449 | 0.1517 | 0.3962 | 0.1237 | 0.5068 | 0.2861 | 0.4844 |
| 0.7905 | 92.9953 | 9904 | 1.0951 | 0.2753 | 0.5169 | 0.2526 | 0.2849 | 0.1916 | 0.4366 | 0.2928 | 0.504 | 0.54 | 0.4511 | 0.411 | 0.7577 | 0.5602 | 0.7337 | 0.2639 | 0.549 | 0.1435 | 0.4019 | 0.1204 | 0.5339 | 0.2884 | 0.4815 |
| 0.7743 | 94.0 | 10011 | 1.0933 | 0.2819 | 0.521 | 0.2597 | 0.2878 | 0.1949 | 0.4462 | 0.2988 | 0.5049 | 0.541 | 0.4443 | 0.4101 | 0.772 | 0.572 | 0.7378 | 0.2717 | 0.551 | 0.1474 | 0.4043 | 0.1252 | 0.5254 | 0.2933 | 0.4867 |
| 0.7762 | 94.9953 | 10117 | 1.1082 | 0.2785 | 0.5219 | 0.2596 | 0.2847 | 0.1917 | 0.4507 | 0.2935 | 0.4993 | 0.5339 | 0.4327 | 0.4051 | 0.7669 | 0.5695 | 0.7355 | 0.2691 | 0.5531 | 0.1402 | 0.3834 | 0.1218 | 0.5169 | 0.2921 | 0.4806 |
| 0.7618 | 96.0 | 10224 | 1.1062 | 0.2774 | 0.5204 | 0.2555 | 0.287 | 0.1876 | 0.4483 | 0.2982 | 0.5005 | 0.532 | 0.436 | 0.4003 | 0.7614 | 0.5632 | 0.7326 | 0.2667 | 0.5408 | 0.1435 | 0.3938 | 0.1251 | 0.5153 | 0.2886 | 0.4777 |
| 0.783 | 96.9953 | 10330 | 1.1082 | 0.279 | 0.523 | 0.2572 | 0.284 | 0.1949 | 0.4486 | 0.302 | 0.4993 | 0.5334 | 0.4331 | 0.4071 | 0.7629 | 0.5593 | 0.7308 | 0.2744 | 0.5531 | 0.1447 | 0.3915 | 0.1238 | 0.5085 | 0.293 | 0.4834 |
| 0.7681 | 98.0 | 10437 | 1.0984 | 0.2819 | 0.5263 | 0.257 | 0.288 | 0.1948 | 0.4534 | 0.304 | 0.503 | 0.5368 | 0.4351 | 0.413 | 0.7653 | 0.5622 | 0.7326 | 0.277 | 0.549 | 0.1479 | 0.3957 | 0.129 | 0.5169 | 0.2933 | 0.4896 |
| 0.7742 | 98.9953 | 10543 | 1.1026 | 0.2806 | 0.5263 | 0.2569 | 0.2889 | 0.1948 | 0.4543 | 0.3014 | 0.5012 | 0.5341 | 0.4352 | 0.4077 | 0.7639 | 0.5568 | 0.732 | 0.2749 | 0.549 | 0.1484 | 0.3948 | 0.1271 | 0.5102 | 0.2957 | 0.4848 |
| 0.7654 | 99.5305 | 10600 | 1.1028 | 0.2808 | 0.5257 | 0.2589 | 0.2879 | 0.1953 | 0.4546 | 0.3004 | 0.5007 | 0.534 | 0.4339 | 0.4079 | 0.7629 | 0.5566 | 0.7331 | 0.2761 | 0.549 | 0.1484 | 0.3943 | 0.1271 | 0.5085 | 0.2956 | 0.4853 |
### Framework versions
- Transformers 4.40.0.dev0
- Pytorch 1.13.0+cu117
- Datasets 2.18.0
- Tokenizers 0.19.0
| {"license": "apache-2.0", "tags": ["object-detection", "vision", "generated_from_trainer"], "base_model": "SenseTime/deformable-detr", "model-index": [{"name": "sensetime-deformable-detr-finetuned-10k-cppe5", "results": []}]} | qubvel-hf/sensetime-deformable-detr-finetuned-10k-cppe5 | null | [
"transformers",
"safetensors",
"deformable_detr",
"object-detection",
"vision",
"generated_from_trainer",
"base_model:SenseTime/deformable-detr",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | 2024-04-19T14:51:44+00:00 | [] | [] | TAGS
#transformers #safetensors #deformable_detr #object-detection #vision #generated_from_trainer #base_model-SenseTime/deformable-detr #license-apache-2.0 #endpoints_compatible #region-us
| sensetime-deformable-detr-finetuned-10k-cppe5
=============================================
This model is a fine-tuned version of SenseTime/deformable-detr on the cppe-5 dataset.
It achieves the following results on the evaluation set:
* Loss: 1.1028
* Map: 0.2808
* Map 50: 0.5257
* Map 75: 0.2589
* Map Small: 0.2879
* Map Medium: 0.1953
* Map Large: 0.4546
* Mar 1: 0.3004
* Mar 10: 0.5007
* Mar 100: 0.534
* Mar Small: 0.4339
* Mar Medium: 0.4079
* Mar Large: 0.7629
* Map Coverall: 0.5566
* Mar 100 Coverall: 0.7331
* Map Face Shield: 0.2761
* Mar 100 Face Shield: 0.549
* Map Gloves: 0.1484
* Mar 100 Gloves: 0.3943
* Map Goggles: 0.1271
* Mar 100 Goggles: 0.5085
* Map Mask: 0.2956
* Mar 100 Mask: 0.4853
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: 4
* eval\_batch\_size: 8
* seed: 1337
* gradient\_accumulation\_steps: 2
* total\_train\_batch\_size: 8
* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
* lr\_scheduler\_type: linear
* num\_epochs: 100.0
* mixed\_precision\_training: Native AMP
### Training results
### Framework versions
* Transformers 4.40.0.dev0
* Pytorch 1.13.0+cu117
* Datasets 2.18.0
* Tokenizers 0.19.0
| [
"### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 5e-05\n* train\\_batch\\_size: 4\n* eval\\_batch\\_size: 8\n* seed: 1337\n* gradient\\_accumulation\\_steps: 2\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: 100.0\n* mixed\\_precision\\_training: Native AMP",
"### Training results",
"### Framework versions\n\n\n* Transformers 4.40.0.dev0\n* Pytorch 1.13.0+cu117\n* Datasets 2.18.0\n* Tokenizers 0.19.0"
] | [
"TAGS\n#transformers #safetensors #deformable_detr #object-detection #vision #generated_from_trainer #base_model-SenseTime/deformable-detr #license-apache-2.0 #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: 4\n* eval\\_batch\\_size: 8\n* seed: 1337\n* gradient\\_accumulation\\_steps: 2\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: 100.0\n* mixed\\_precision\\_training: Native AMP",
"### Training results",
"### Framework versions\n\n\n* Transformers 4.40.0.dev0\n* Pytorch 1.13.0+cu117\n* Datasets 2.18.0\n* Tokenizers 0.19.0"
] |
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": []} | Liya009/code-search-net-tokenizer | null | [
"transformers",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null | 2024-04-19T14:52:24+00:00 | [
"1910.09700"
] | [] | TAGS
#transformers #arxiv-1910.09700 #endpoints_compatible #region-us
|
# Model Card for Model ID
## Model Details
### Model Description
This is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.
- Developed by:
- Funded by [optional]:
- Shared by [optional]:
- Model type:
- Language(s) (NLP):
- License:
- Finetuned from model [optional]:
### Model Sources [optional]
- Repository:
- Paper [optional]:
- Demo [optional]:
## Uses
### Direct Use
### Downstream Use [optional]
### Out-of-Scope Use
## Bias, Risks, and Limitations
### Recommendations
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
## Training Details
### Training Data
### Training Procedure
#### Preprocessing [optional]
#### Training Hyperparameters
- Training regime:
#### Speeds, Sizes, Times [optional]
## Evaluation
### Testing Data, Factors & Metrics
#### Testing Data
#### Factors
#### Metrics
### Results
#### Summary
## Model Examination [optional]
## Environmental Impact
Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).
- Hardware Type:
- Hours used:
- Cloud Provider:
- Compute Region:
- Carbon Emitted:
## Technical Specifications [optional]
### Model Architecture and Objective
### Compute Infrastructure
#### Hardware
#### Software
[optional]
BibTeX:
APA:
## Glossary [optional]
## More Information [optional]
## Model Card Authors [optional]
## Model Card Contact
| [
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.",
"## How to Get Started with the Model\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] | [
"TAGS\n#transformers #arxiv-1910.09700 #endpoints_compatible #region-us \n",
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.",
"## How to Get Started with the Model\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] |
text-generation | transformers | This is an MOE of Llama-3-8b with 4 experts. This does not use semantic routing, as this utilizes the deepseek-moe architecture. There is no routing, and there is no gate - all experts are active on every token.
```python
import torch
from transformers import AutoTokenizer, TextStreamer, AutoModelForCausalLM
model_path = "Crystalcareai/llama-3-4x8b"
model = AutoModelForCausalLM.from_pretrained(
model_path,
device_map="auto",
low_cpu_mem_usage=True,
torch_dtype=torch.bfloat16,
trust_remote_code=True,
attn_implementation="flash_attention_2",
)
tokenizer = AutoTokenizer.from_pretrained(model_path)
streamer = TextStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True)
# Modify the prompt to match the Alpaca instruction template
prompt = """
Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.
### Instruction:
Sam is faster than Joe. Joe is faster than Jane. Is Sam faster than Jane? Explain your reasoning step by step.
### Input:
### Response:
"""
tokens = tokenizer(
prompt,
return_tensors='pt'
).input_ids.cuda()
generation_output = model.generate(
tokens,
streamer=streamer,
max_new_tokens=512,
)
``` | {} | Crystalcareai/llama-3-4x8b | null | [
"transformers",
"safetensors",
"deepseek",
"text-generation",
"conversational",
"custom_code",
"autotrain_compatible",
"region:us"
] | null | 2024-04-19T14:52:24+00:00 | [] | [] | TAGS
#transformers #safetensors #deepseek #text-generation #conversational #custom_code #autotrain_compatible #region-us
| This is an MOE of Llama-3-8b with 4 experts. This does not use semantic routing, as this utilizes the deepseek-moe architecture. There is no routing, and there is no gate - all experts are active on every token.
| [] | [
"TAGS\n#transformers #safetensors #deepseek #text-generation #conversational #custom_code #autotrain_compatible #region-us \n"
] |
null | null |
## Definitely a Beta Test at Best
There's an issue with the types of end of text and end of sentence tokens being used. Output will start normal, then continue rambling - sort of.
Meta has a bunch of special reserved tokens and this release kind of rambles against itself with current inference libraries, but the rambling looks exactly like an internal monologue of a refined model. I think it's just that, a chain of thought is being ironed out to establish conversation context for the model to refer back to. Because I am optomist. Playing with this in various UIs and fixes across the forums, it's really starting to look like this extra "internal" output after the output intended for the user is meant to be thoughts for Llama3. I think this is so when you say "hi how are you" it'll say "I'm doing pretty good, what can I help you with?" but then behind the scenes print out a ton of context information (oh, you'll see) so the conversation stays on some kind of rails. Sometimes it gives itself multiple choice options and chooses its next action, sometimes it has a python or c++ program, it's pretty interesting for this early phase. What's super interesting is these internal thoughts vary wildly. It's worth looking just to have a peek behind the curtain.
Also, while converting to gguf we get this error which seems rather important "Ignoring added_tokens.json since model matches vocab size without it."
I think, suspect, that we need to read multiple tokens as end of text or end of sentence for it to display accurately. The gguf (ggml) [doc](https://github.com/ggerganov/ggml/blob/master/docs/gguf.md) I found shows it can only have one (val: tokenizer.ggml.eos_token_id). You can hunt around for an interface that lets you set multiple, but llamafile and llama.cpp is not that. The base llamacpp repo will have to be updated, and also the llamafile repo. I'll fix these after that.
The Llama3 we see is not the Llama3 that will be.
## Llamafile
This is the llamafile for llama3 [8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) instruct with an unnoficial llama end of text hacky fix. For now I'm just adding one small enough for a Windows executable, and a few others. Use the biggest one you can get to work.
Recently I learned that there is some quality loss when converting bfloat16 to float16, but bf16 to f32 is lossless and quants can be done from there. These files follow that pattern: safetensors in bf16 -> gguf in f32 -> qx_x(_x).
## EOT "fix"
The current fix is to manually change the end-of-text token (what it generates when it decides to stop responding to something, some humans do not have one of these). Like, it makes it and prints it, but all the inference UIs aren't seeing it correctly. Maybe ggml/gguf need an int-array instead of an int for that eos mapping. I'm guessing all the open source inference libraries will have a fix for this in the next few days, but in the meantime I wanted to get a llamafile out for Windows users. I'll come back and update when it's gravy.
Here is the code, you can run it on any Llama3 gguf you have (change filename to your local gguf): `python3 ../llama.cpp/gguf-py/scripts/gguf-set-metadata.py ./Meta-Llama-3-8B-Instruct-q3-k-s.gguf tokenizer.ggml.eos_token_id 128009`
What the fix does: stop infinite rambling
What the fix does not do: make the model work like a normal language model.
### ~Original Model Card~
## Model Details
Meta developed and released the Meta Llama 3 family of large language models (LLMs), a collection of pretrained and instruction tuned generative text models in 8 and 70B sizes. The Llama 3 instruction tuned models are optimized for dialogue use cases and outperform many of the available open source chat models on common industry benchmarks. Further, in developing these models, we took great care to optimize helpfulness and safety.
**Model developers** Meta
**Variations** Llama 3 comes in two sizes — 8B and 70B parameters — in pre-trained and instruction tuned variants.
**Input** Models input text only.
**Output** Models generate text and code only.
**Model Architecture** Llama 3 is an auto-regressive language model that uses an optimized transformer architecture. The tuned versions use supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF) to align with human preferences for helpfulness and safety.
<table>
<tr>
<td>
</td>
<td><strong>Training Data</strong>
</td>
<td><strong>Params</strong>
</td>
<td><strong>Context length</strong>
</td>
<td><strong>GQA</strong>
</td>
<td><strong>Token count</strong>
</td>
<td><strong>Knowledge cutoff</strong>
</td>
</tr>
<tr>
<td rowspan="2" >Llama 3
</td>
<td rowspan="2" >A new mix of publicly available online data.
</td>
<td>8B
</td>
<td>8k
</td>
<td>Yes
</td>
<td rowspan="2" >15T+
</td>
<td>March, 2023
</td>
</tr>
<tr>
<td>70B
</td>
<td>8k
</td>
<td>Yes
</td>
<td>December, 2023
</td>
</tr>
</table>
**Llama 3 family of models**. Token counts refer to pretraining data only. Both the 8 and 70B versions use Grouped-Query Attention (GQA) for improved inference scalability.
**Model Release Date** April 18, 2024.
**Status** This is a static model trained on an offline dataset. Future versions of the tuned models will be released as we improve model safety with community feedback.
**License** A custom commercial license is available at: [https://llama.meta.com/llama3/license](https://llama.meta.com/llama3/license)
Where to send questions or comments about the model Instructions on how to provide feedback or comments on the model can be found in the model [README](https://github.com/meta-llama/llama3). For more technical information about generation parameters and recipes for how to use Llama 3 in applications, please go [here](https://github.com/meta-llama/llama-recipes).
## Intended Use
**Intended Use Cases** Llama 3 is intended for commercial and research use in English. Instruction tuned models are intended for assistant-like chat, whereas pretrained models can be adapted for a variety of natural language generation tasks.
**Out-of-scope** Use in any manner that violates applicable laws or regulations (including trade compliance laws). Use in any other way that is prohibited by the Acceptable Use Policy and Llama 3 Community License. Use in languages other than English**.
**Note: Developers may fine-tune Llama 3 models for languages beyond English provided they comply with the Llama 3 Community License and the Acceptable Use Policy.
## How to use
This repository contains two versions of Meta-Llama-3-8B-Instruct, for use with transformers and with the original `llama3` codebase.
### Use with transformers
You can run conversational inference using the Transformers pipeline abstraction, or by leveraging the Auto classes with the `generate()` function. Let's see examples of both.
#### Transformers pipeline
```python
import transformers
import torch
model_id = "meta-llama/Meta-Llama-3-8B-Instruct"
pipeline = transformers.pipeline(
"text-generation",
model=model_id,
model_kwargs={"torch_dtype": torch.bfloat16},
device="auto",
)
messages = [
{"role": "system", "content": "You are a pirate chatbot who always responds in pirate speak!"},
{"role": "user", "content": "Who are you?"},
]
prompt = pipeline.tokenizer.apply_chat_template(
messages,
tokenize=False,
add_generation_prompt=True
)
terminators = [
pipeline.tokenizer.eos_token_id,
pipeline.tokenizer.convert_tokens_to_ids("<|eot_id|>")
]
outputs = pipeline(
prompt,
max_new_tokens=256,
eos_token_id=terminators,
do_sample=True,
temperature=0.6,
top_p=0.9,
)
print(outputs[0]["generated_text"][len(prompt):])
```
#### Transformers AutoModelForCausalLM
```python
from transformers import AutoTokenizer, AutoModelForCausalLM
import torch
model_id = "meta-llama/Meta-Llama-3-8B-Instruct"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
model_id,
torch_dtype=torch.bfloat16,
device_map="auto",
)
messages = [
{"role": "system", "content": "You are a pirate chatbot who always responds in pirate speak!"},
{"role": "user", "content": "Who are you?"},
]
input_ids = tokenizer.apply_chat_template(
messages,
add_generation_prompt=True,
return_tensors="pt"
).to(model.device)
terminators = [
tokenizer.eos_token_id,
tokenizer.convert_tokens_to_ids("<|eot_id|>")
]
outputs = model.generate(
input_ids,
max_new_tokens=256,
eos_token_id=terminators,
do_sample=True,
temperature=0.6,
top_p=0.9,
)
response = outputs[0][input_ids.shape[-1]:]
print(tokenizer.decode(response, skip_special_tokens=True))
```
### Use with `llama3`
Please, follow the instructions in the [repository](https://github.com/meta-llama/llama3)
To download Original checkpoints, see the example command below leveraging `huggingface-cli`:
```
huggingface-cli download meta-llama/Meta-Llama-3-8B-Instruct --include "original/*" --local-dir Meta-Llama-3-8B-Instruct
```
For Hugging Face support, we recommend using transformers or TGI, but a similar command works.
## Hardware and Software
**Training Factors** We used custom training libraries, Meta's Research SuperCluster, and production clusters for pretraining. Fine-tuning, annotation, and evaluation were also performed on third-party cloud compute.
**Carbon Footprint Pretraining utilized a cumulative** 7.7M GPU hours of computation on hardware of type H100-80GB (TDP of 700W). Estimated total emissions were 2290 tCO2eq, 100% of which were offset by Meta’s sustainability program.
<table>
<tr>
<td>
</td>
<td><strong>Time (GPU hours)</strong>
</td>
<td><strong>Power Consumption (W)</strong>
</td>
<td><strong>Carbon Emitted(tCO2eq)</strong>
</td>
</tr>
<tr>
<td>Llama 3 8B
</td>
<td>1.3M
</td>
<td>700
</td>
<td>390
</td>
</tr>
<tr>
<td>Llama 3 70B
</td>
<td>6.4M
</td>
<td>700
</td>
<td>1900
</td>
</tr>
<tr>
<td>Total
</td>
<td>7.7M
</td>
<td>
</td>
<td>2290
</td>
</tr>
</table>
**CO2 emissions during pre-training**. Time: total GPU time required for training each model. Power Consumption: peak power capacity per GPU device for the GPUs used adjusted for power usage efficiency. 100% of the emissions are directly offset by Meta's sustainability program, and because we are openly releasing these models, the pretraining costs do not need to be incurred by others.
## Training Data
**Overview** Llama 3 was pretrained on over 15 trillion tokens of data from publicly available sources. The fine-tuning data includes publicly available instruction datasets, as well as over 10M human-annotated examples. Neither the pretraining nor the fine-tuning datasets include Meta user data.
**Data Freshness** The pretraining data has a cutoff of March 2023 for the 7B and December 2023 for the 70B models respectively.
## Benchmarks
In this section, we report the results for Llama 3 models on standard automatic benchmarks. For all the evaluations, we use our internal evaluations library. For details on the methodology see [here](https://github.com/meta-llama/llama3/blob/main/eval_methodology.md).
### Base pretrained models
<table>
<tr>
<td><strong>Category</strong>
</td>
<td><strong>Benchmark</strong>
</td>
<td><strong>Llama 3 8B</strong>
</td>
<td><strong>Llama2 7B</strong>
</td>
<td><strong>Llama2 13B</strong>
</td>
<td><strong>Llama 3 70B</strong>
</td>
<td><strong>Llama2 70B</strong>
</td>
</tr>
<tr>
<td rowspan="6" >General
</td>
<td>MMLU (5-shot)
</td>
<td>66.6
</td>
<td>45.7
</td>
<td>53.8
</td>
<td>79.5
</td>
<td>69.7
</td>
</tr>
<tr>
<td>AGIEval English (3-5 shot)
</td>
<td>45.9
</td>
<td>28.8
</td>
<td>38.7
</td>
<td>63.0
</td>
<td>54.8
</td>
</tr>
<tr>
<td>CommonSenseQA (7-shot)
</td>
<td>72.6
</td>
<td>57.6
</td>
<td>67.6
</td>
<td>83.8
</td>
<td>78.7
</td>
</tr>
<tr>
<td>Winogrande (5-shot)
</td>
<td>76.1
</td>
<td>73.3
</td>
<td>75.4
</td>
<td>83.1
</td>
<td>81.8
</td>
</tr>
<tr>
<td>BIG-Bench Hard (3-shot, CoT)
</td>
<td>61.1
</td>
<td>38.1
</td>
<td>47.0
</td>
<td>81.3
</td>
<td>65.7
</td>
</tr>
<tr>
<td>ARC-Challenge (25-shot)
</td>
<td>78.6
</td>
<td>53.7
</td>
<td>67.6
</td>
<td>93.0
</td>
<td>85.3
</td>
</tr>
<tr>
<td>Knowledge reasoning
</td>
<td>TriviaQA-Wiki (5-shot)
</td>
<td>78.5
</td>
<td>72.1
</td>
<td>79.6
</td>
<td>89.7
</td>
<td>87.5
</td>
</tr>
<tr>
<td rowspan="4" >Reading comprehension
</td>
<td>SQuAD (1-shot)
</td>
<td>76.4
</td>
<td>72.2
</td>
<td>72.1
</td>
<td>85.6
</td>
<td>82.6
</td>
</tr>
<tr>
<td>QuAC (1-shot, F1)
</td>
<td>44.4
</td>
<td>39.6
</td>
<td>44.9
</td>
<td>51.1
</td>
<td>49.4
</td>
</tr>
<tr>
<td>BoolQ (0-shot)
</td>
<td>75.7
</td>
<td>65.5
</td>
<td>66.9
</td>
<td>79.0
</td>
<td>73.1
</td>
</tr>
<tr>
<td>DROP (3-shot, F1)
</td>
<td>58.4
</td>
<td>37.9
</td>
<td>49.8
</td>
<td>79.7
</td>
<td>70.2
</td>
</tr>
</table>
### Instruction tuned models
<table>
<tr>
<td><strong>Benchmark</strong>
</td>
<td><strong>Llama 3 8B</strong>
</td>
<td><strong>Llama 2 7B</strong>
</td>
<td><strong>Llama 2 13B</strong>
</td>
<td><strong>Llama 3 70B</strong>
</td>
<td><strong>Llama 2 70B</strong>
</td>
</tr>
<tr>
<td>MMLU (5-shot)
</td>
<td>68.4
</td>
<td>34.1
</td>
<td>47.8
</td>
<td>82.0
</td>
<td>52.9
</td>
</tr>
<tr>
<td>GPQA (0-shot)
</td>
<td>34.2
</td>
<td>21.7
</td>
<td>22.3
</td>
<td>39.5
</td>
<td>21.0
</td>
</tr>
<tr>
<td>HumanEval (0-shot)
</td>
<td>62.2
</td>
<td>7.9
</td>
<td>14.0
</td>
<td>81.7
</td>
<td>25.6
</td>
</tr>
<tr>
<td>GSM-8K (8-shot, CoT)
</td>
<td>79.6
</td>
<td>25.7
</td>
<td>77.4
</td>
<td>93.0
</td>
<td>57.5
</td>
</tr>
<tr>
<td>MATH (4-shot, CoT)
</td>
<td>30.0
</td>
<td>3.8
</td>
<td>6.7
</td>
<td>50.4
</td>
<td>11.6
</td>
</tr>
</table>
### Responsibility & Safety
We believe that an open approach to AI leads to better, safer products, faster innovation, and a bigger overall market. We are committed to Responsible AI development and took a series of steps to limit misuse and harm and support the open source community.
Foundation models are widely capable technologies that are built to be used for a diverse range of applications. They are not designed to meet every developer preference on safety levels for all use cases, out-of-the-box, as those by their nature will differ across different applications.
Rather, responsible LLM-application deployment is achieved by implementing a series of safety best practices throughout the development of such applications, from the model pre-training, fine-tuning and the deployment of systems composed of safeguards to tailor the safety needs specifically to the use case and audience.
As part of the Llama 3 release, we updated our [Responsible Use Guide](https://llama.meta.com/responsible-use-guide/) to outline the steps and best practices for developers to implement model and system level safety for their application. We also provide a set of resources including [Meta Llama Guard 2](https://llama.meta.com/purple-llama/) and [Code Shield](https://llama.meta.com/purple-llama/) safeguards. These tools have proven to drastically reduce residual risks of LLM Systems, while maintaining a high level of helpfulness. We encourage developers to tune and deploy these safeguards according to their needs and we provide a [reference implementation](https://github.com/meta-llama/llama-recipes/tree/main/recipes/responsible_ai) to get you started.
#### Llama 3-Instruct
As outlined in the Responsible Use Guide, some trade-off between model helpfulness and model alignment is likely unavoidable. Developers should exercise discretion about how to weigh the benefits of alignment and helpfulness for their specific use case and audience. Developers should be mindful of residual risks when using Llama models and leverage additional safety tools as needed to reach the right safety bar for their use case.
<span style="text-decoration:underline;">Safety</span>
For our instruction tuned model, we conducted extensive red teaming exercises, performed adversarial evaluations and implemented safety mitigations techniques to lower residual risks. As with any Large Language Model, residual risks will likely remain and we recommend that developers assess these risks in the context of their use case. In parallel, we are working with the community to make AI safety benchmark standards transparent, rigorous and interpretable.
<span style="text-decoration:underline;">Refusals</span>
In addition to residual risks, we put a great emphasis on model refusals to benign prompts. Over-refusing not only can impact the user experience but could even be harmful in certain contexts as well. We’ve heard the feedback from the developer community and improved our fine tuning to ensure that Llama 3 is significantly less likely to falsely refuse to answer prompts than Llama 2.
We built internal benchmarks and developed mitigations to limit false refusals making Llama 3 our most helpful model to date.
#### Responsible release
In addition to responsible use considerations outlined above, we followed a rigorous process that requires us to take extra measures against misuse and critical risks before we make our release decision.
Misuse
If you access or use Llama 3, you agree to the Acceptable Use Policy. The most recent copy of this policy can be found at [https://llama.meta.com/llama3/use-policy/](https://llama.meta.com/llama3/use-policy/).
#### Critical risks
<span style="text-decoration:underline;">CBRNE</span> (Chemical, Biological, Radiological, Nuclear, and high yield Explosives)
We have conducted a two fold assessment of the safety of the model in this area:
* Iterative testing during model training to assess the safety of responses related to CBRNE threats and other adversarial risks.
* Involving external CBRNE experts to conduct an uplift test assessing the ability of the model to accurately provide expert knowledge and reduce barriers to potential CBRNE misuse, by reference to what can be achieved using web search (without the model).
### <span style="text-decoration:underline;">Cyber Security </span>
We have evaluated Llama 3 with CyberSecEval, Meta’s cybersecurity safety eval suite, measuring Llama 3’s propensity to suggest insecure code when used as a coding assistant, and Llama 3’s propensity to comply with requests to help carry out cyber attacks, where attacks are defined by the industry standard MITRE ATT&CK cyber attack ontology. On our insecure coding and cyber attacker helpfulness tests, Llama 3 behaved in the same range or safer than models of [equivalent coding capability](https://huggingface.co/spaces/facebook/CyberSecEval).
### <span style="text-decoration:underline;">Child Safety</span>
Child Safety risk assessments were conducted using a team of experts, to assess the model’s capability to produce outputs that could result in Child Safety risks and inform on any necessary and appropriate risk mitigations via fine tuning. We leveraged those expert red teaming sessions to expand the coverage of our evaluation benchmarks through Llama 3 model development. For Llama 3, we conducted new in-depth sessions using objective based methodologies to assess the model risks along multiple attack vectors. We also partnered with content specialists to perform red teaming exercises assessing potentially violating content while taking account of market specific nuances or experiences.
### Community
Generative AI safety requires expertise and tooling, and we believe in the strength of the open community to accelerate its progress. We are active members of open consortiums, including the AI Alliance, Partnership in AI and MLCommons, actively contributing to safety standardization and transparency. We encourage the community to adopt taxonomies like the MLCommons Proof of Concept evaluation to facilitate collaboration and transparency on safety and content evaluations. Our Purple Llama tools are open sourced for the community to use and widely distributed across ecosystem partners including cloud service providers. We encourage community contributions to our [Github repository](https://github.com/meta-llama/PurpleLlama).
Finally, we put in place a set of resources including an [output reporting mechanism](https://developers.facebook.com/llama_output_feedback) and [bug bounty program](https://www.facebook.com/whitehat) to continuously improve the Llama technology with the help of the community.
## Ethical Considerations and Limitations
The core values of Llama 3 are openness, inclusivity and helpfulness. It is meant to serve everyone, and to work for a wide range of use cases. It is thus designed to be accessible to people across many different backgrounds, experiences and perspectives. Llama 3 addresses users and their needs as they are, without insertion unnecessary judgment or normativity, while reflecting the understanding that even content that may appear problematic in some cases can serve valuable purposes in others. It respects the dignity and autonomy of all users, especially in terms of the values of free thought and expression that power innovation and progress.
But Llama 3 is a new technology, and like any new technology, there are risks associated with its use. Testing conducted to date has been in English, and has not covered, nor could it cover, all scenarios. For these reasons, as with all LLMs, Llama 3’s potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate, biased or other objectionable responses to user prompts. Therefore, before deploying any applications of Llama 3 models, developers should perform safety testing and tuning tailored to their specific applications of the model. As outlined in the Responsible Use Guide, we recommend incorporating [Purple Llama](https://github.com/facebookresearch/PurpleLlama) solutions into your workflows and specifically [Llama Guard](https://ai.meta.com/research/publications/llama-guard-llm-based-input-output-safeguard-for-human-ai-conversations/) which provides a base model to filter input and output prompts to layer system-level safety on top of model-level safety.
Please see the Responsible Use Guide available at [http://llama.meta.com/responsible-use-guide](http://llama.meta.com/responsible-use-guide)
## Citation instructions
@article{llama3modelcard,
title={Llama 3 Model Card},
author={AI@Meta},
year={2024},
url = {https://github.com/meta-llama/llama3/blob/main/MODEL_CARD.md}
}
## Contributors
Aaditya Singh; Aaron Grattafiori; Abhimanyu Dubey; Abhinav Jauhri; Abhinav Pandey; Abhishek Kadian; Adam Kelsey; Adi Gangidi; Ahmad Al-Dahle; Ahuva Goldstand; Aiesha Letman; Ajay Menon; Akhil Mathur; Alan Schelten; Alex Vaughan; Amy Yang; Andrei Lupu; Andres Alvarado; Andrew Gallagher; Andrew Gu; Andrew Ho; Andrew Poulton; Andrew Ryan; Angela Fan; Ankit Ramchandani; Anthony Hartshorn; Archi Mitra; Archie Sravankumar; Artem Korenev; Arun Rao; Ashley Gabriel; Ashwin Bharambe; Assaf Eisenman; Aston Zhang; Aurelien Rodriguez; Austen Gregerson; Ava Spataru; Baptiste Roziere; Ben Maurer; Benjamin Leonhardi; Bernie Huang; Bhargavi Paranjape; Bing Liu; Binh Tang; Bobbie Chern; Brani Stojkovic; Brian Fuller; Catalina Mejia Arenas; Chao Zhou; Charlotte Caucheteux; Chaya Nayak; Ching-Hsiang Chu; Chloe Bi; Chris Cai; Chris Cox; Chris Marra; Chris McConnell; Christian Keller; Christoph Feichtenhofer; Christophe Touret; Chunyang Wu; Corinne Wong; Cristian Canton Ferrer; Damien Allonsius; Daniel Kreymer; Daniel Haziza; Daniel Li; Danielle Pintz; Danny Livshits; Danny Wyatt; David Adkins; David Esiobu; David Xu; Davide Testuggine; Delia David; Devi Parikh; Dhruv Choudhary; Dhruv Mahajan; Diana Liskovich; Diego Garcia-Olano; Diego Perino; Dieuwke Hupkes; Dingkang Wang; Dustin Holland; Egor Lakomkin; Elina Lobanova; Xiaoqing Ellen Tan; Emily Dinan; Eric Smith; Erik Brinkman; Esteban Arcaute; Filip Radenovic; Firat Ozgenel; Francesco Caggioni; Frank Seide; Frank Zhang; Gabriel Synnaeve; Gabriella Schwarz; Gabrielle Lee; Gada Badeer; Georgia Anderson; Graeme Nail; Gregoire Mialon; Guan Pang; Guillem Cucurell; Hailey Nguyen; Hannah Korevaar; Hannah Wang; Haroun Habeeb; Harrison Rudolph; Henry Aspegren; Hu Xu; Hugo Touvron; Iga Kozlowska; Igor Molybog; Igor Tufanov; Iliyan Zarov; Imanol Arrieta Ibarra; Irina-Elena Veliche; Isabel Kloumann; Ishan Misra; Ivan Evtimov; Jacob Xu; Jade Copet; Jake Weissman; Jan Geffert; Jana Vranes; Japhet Asher; Jason Park; Jay Mahadeokar; Jean-Baptiste Gaya; Jeet Shah; Jelmer van der Linde; Jennifer Chan; Jenny Hong; Jenya Lee; Jeremy Fu; Jeremy Teboul; Jianfeng Chi; Jianyu Huang; Jie Wang; Jiecao Yu; Joanna Bitton; Joe Spisak; Joelle Pineau; Jon Carvill; Jongsoo Park; Joseph Rocca; Joshua Johnstun; Junteng Jia; Kalyan Vasuden Alwala; Kam Hou U; Kate Plawiak; Kartikeya Upasani; Kaushik Veeraraghavan; Ke Li; Kenneth Heafield; Kevin Stone; Khalid El-Arini; Krithika Iyer; Kshitiz Malik; Kuenley Chiu; Kunal Bhalla; Kyle Huang; Lakshya Garg; Lauren Rantala-Yeary; Laurens van der Maaten; Lawrence Chen; Leandro Silva; Lee Bell; Lei Zhang; Liang Tan; Louis Martin; Lovish Madaan; Luca Wehrstedt; Lukas Blecher; Luke de Oliveira; Madeline Muzzi; Madian Khabsa; Manav Avlani; Mannat Singh; Manohar Paluri; Mark Zuckerberg; Marcin Kardas; Martynas Mankus; Mathew Oldham; Mathieu Rita; Matthew Lennie; Maya Pavlova; Meghan Keneally; Melanie Kambadur; Mihir Patel; Mikayel Samvelyan; Mike Clark; Mike Lewis; Min Si; Mitesh Kumar Singh; Mo Metanat; Mona Hassan; Naman Goyal; Narjes Torabi; Nicolas Usunier; Nikolay Bashlykov; Nikolay Bogoychev; Niladri Chatterji; Ning Dong; Oliver Aobo Yang; Olivier Duchenne; Onur Celebi; Parth Parekh; Patrick Alrassy; Paul Saab; Pavan Balaji; Pedro Rittner; Pengchuan Zhang; Pengwei Li; Petar Vasic; Peter Weng; Polina Zvyagina; Prajjwal Bhargava; Pratik Dubal; Praveen Krishnan; Punit Singh Koura; Qing He; Rachel Rodriguez; Ragavan Srinivasan; Rahul Mitra; Ramon Calderer; Raymond Li; Robert Stojnic; Roberta Raileanu; Robin Battey; Rocky Wang; Rohit Girdhar; Rohit Patel; Romain Sauvestre; Ronnie Polidoro; Roshan Sumbaly; Ross Taylor; Ruan Silva; Rui Hou; Rui Wang; Russ Howes; Ruty Rinott; Saghar Hosseini; Sai Jayesh Bondu; Samyak Datta; Sanjay Singh; Sara Chugh; Sargun Dhillon; Satadru Pan; Sean Bell; Sergey Edunov; Shaoliang Nie; Sharan Narang; Sharath Raparthy; Shaun Lindsay; Sheng Feng; Sheng Shen; Shenghao Lin; Shiva Shankar; Shruti Bhosale; Shun Zhang; Simon Vandenhende; Sinong Wang; Seohyun Sonia Kim; Soumya Batra; Sten Sootla; Steve Kehoe; Suchin Gururangan; Sumit Gupta; Sunny Virk; Sydney Borodinsky; Tamar Glaser; Tamar Herman; Tamara Best; Tara Fowler; Thomas Georgiou; Thomas Scialom; Tianhe Li; Todor Mihaylov; Tong Xiao; Ujjwal Karn; Vedanuj Goswami; Vibhor Gupta; Vignesh Ramanathan; Viktor Kerkez; Vinay Satish Kumar; Vincent Gonguet; Vish Vogeti; Vlad Poenaru; Vlad Tiberiu Mihailescu; Vladan Petrovic; Vladimir Ivanov; Wei Li; Weiwei Chu; Wenhan Xiong; Wenyin Fu; Wes Bouaziz; Whitney Meers; Will Constable; Xavier Martinet; Xiaojian Wu; Xinbo Gao; Xinfeng Xie; Xuchao Jia; Yaelle Goldschlag; Yann LeCun; Yashesh Gaur; Yasmine Babaei; Ye Qi; Yenda Li; Yi Wen; Yiwen Song; Youngjin Nam; Yuchen Hao; Yuchen Zhang; Yun Wang; Yuning Mao; Yuzi He; Zacharie Delpierre Coudert; Zachary DeVito; Zahra Hankir; Zhaoduo Wen; Zheng Yan; Zhengxing Chen; Zhenyu Yang; Zoe Papakipos
| {"license": "other", "tags": ["facebook", "meta", "pytorch", "llama", "llama-3", "llamafile"], "license_name": "llama3", "license_link": "LICENSE"} | gobean/Meta-Llama-3-8B-Instruct.llamafile | null | [
"llamafile",
"facebook",
"meta",
"pytorch",
"llama",
"llama-3",
"license:other",
"region:us"
] | null | 2024-04-19T14:52:27+00:00 | [] | [] | TAGS
#llamafile #facebook #meta #pytorch #llama #llama-3 #license-other #region-us
| Definitely a Beta Test at Best
------------------------------
There's an issue with the types of end of text and end of sentence tokens being used. Output will start normal, then continue rambling - sort of.
Meta has a bunch of special reserved tokens and this release kind of rambles against itself with current inference libraries, but the rambling looks exactly like an internal monologue of a refined model. I think it's just that, a chain of thought is being ironed out to establish conversation context for the model to refer back to. Because I am optomist. Playing with this in various UIs and fixes across the forums, it's really starting to look like this extra "internal" output after the output intended for the user is meant to be thoughts for Llama3. I think this is so when you say "hi how are you" it'll say "I'm doing pretty good, what can I help you with?" but then behind the scenes print out a ton of context information (oh, you'll see) so the conversation stays on some kind of rails. Sometimes it gives itself multiple choice options and chooses its next action, sometimes it has a python or c++ program, it's pretty interesting for this early phase. What's super interesting is these internal thoughts vary wildly. It's worth looking just to have a peek behind the curtain.
Also, while converting to gguf we get this error which seems rather important "Ignoring added\_tokens.json since model matches vocab size without it."
I think, suspect, that we need to read multiple tokens as end of text or end of sentence for it to display accurately. The gguf (ggml) doc I found shows it can only have one (val: URL.eos\_token\_id). You can hunt around for an interface that lets you set multiple, but llamafile and URL is not that. The base llamacpp repo will have to be updated, and also the llamafile repo. I'll fix these after that.
The Llama3 we see is not the Llama3 that will be.
Llamafile
---------
This is the llamafile for llama3 8B instruct with an unnoficial llama end of text hacky fix. For now I'm just adding one small enough for a Windows executable, and a few others. Use the biggest one you can get to work.
Recently I learned that there is some quality loss when converting bfloat16 to float16, but bf16 to f32 is lossless and quants can be done from there. These files follow that pattern: safetensors in bf16 -> gguf in f32 -> qx\_x(\_x).
EOT "fix"
---------
The current fix is to manually change the end-of-text token (what it generates when it decides to stop responding to something, some humans do not have one of these). Like, it makes it and prints it, but all the inference UIs aren't seeing it correctly. Maybe ggml/gguf need an int-array instead of an int for that eos mapping. I'm guessing all the open source inference libraries will have a fix for this in the next few days, but in the meantime I wanted to get a llamafile out for Windows users. I'll come back and update when it's gravy.
Here is the code, you can run it on any Llama3 gguf you have (change filename to your local gguf): 'python3 ../URL ./URL URL.eos\_token\_id 128009'
What the fix does: stop infinite rambling
What the fix does not do: make the model work like a normal language model.
### ~Original Model Card~
Model Details
-------------
Meta developed and released the Meta Llama 3 family of large language models (LLMs), a collection of pretrained and instruction tuned generative text models in 8 and 70B sizes. The Llama 3 instruction tuned models are optimized for dialogue use cases and outperform many of the available open source chat models on common industry benchmarks. Further, in developing these models, we took great care to optimize helpfulness and safety.
Model developers Meta
Variations Llama 3 comes in two sizes — 8B and 70B parameters — in pre-trained and instruction tuned variants.
Input Models input text only.
Output Models generate text and code only.
Model Architecture Llama 3 is an auto-regressive language model that uses an optimized transformer architecture. The tuned versions use supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF) to align with human preferences for helpfulness and safety.
Llama 3 family of models. Token counts refer to pretraining data only. Both the 8 and 70B versions use Grouped-Query Attention (GQA) for improved inference scalability.
Model Release Date April 18, 2024.
Status This is a static model trained on an offline dataset. Future versions of the tuned models will be released as we improve model safety with community feedback.
License A custom commercial license is available at: URL
Where to send questions or comments about the model Instructions on how to provide feedback or comments on the model can be found in the model README. For more technical information about generation parameters and recipes for how to use Llama 3 in applications, please go here.
Intended Use
------------
Intended Use Cases Llama 3 is intended for commercial and research use in English. Instruction tuned models are intended for assistant-like chat, whereas pretrained models can be adapted for a variety of natural language generation tasks.
Out-of-scope Use in any manner that violates applicable laws or regulations (including trade compliance laws). Use in any other way that is prohibited by the Acceptable Use Policy and Llama 3 Community License. Use in languages other than English.
Note: Developers may fine-tune Llama 3 models for languages beyond English provided they comply with the Llama 3 Community License and the Acceptable Use Policy.
How to use
----------
This repository contains two versions of Meta-Llama-3-8B-Instruct, for use with transformers and with the original 'llama3' codebase.
### Use with transformers
You can run conversational inference using the Transformers pipeline abstraction, or by leveraging the Auto classes with the 'generate()' function. Let's see examples of both.
#### Transformers pipeline
#### Transformers AutoModelForCausalLM
### Use with 'llama3'
Please, follow the instructions in the repository
To download Original checkpoints, see the example command below leveraging 'huggingface-cli':
For Hugging Face support, we recommend using transformers or TGI, but a similar command works.
Hardware and Software
---------------------
Training Factors We used custom training libraries, Meta's Research SuperCluster, and production clusters for pretraining. Fine-tuning, annotation, and evaluation were also performed on third-party cloud compute.
Carbon Footprint Pretraining utilized a cumulative 7.7M GPU hours of computation on hardware of type H100-80GB (TDP of 700W). Estimated total emissions were 2290 tCO2eq, 100% of which were offset by Meta’s sustainability program.
CO2 emissions during pre-training. Time: total GPU time required for training each model. Power Consumption: peak power capacity per GPU device for the GPUs used adjusted for power usage efficiency. 100% of the emissions are directly offset by Meta's sustainability program, and because we are openly releasing these models, the pretraining costs do not need to be incurred by others.
Training Data
-------------
Overview Llama 3 was pretrained on over 15 trillion tokens of data from publicly available sources. The fine-tuning data includes publicly available instruction datasets, as well as over 10M human-annotated examples. Neither the pretraining nor the fine-tuning datasets include Meta user data.
Data Freshness The pretraining data has a cutoff of March 2023 for the 7B and December 2023 for the 70B models respectively.
Benchmarks
----------
In this section, we report the results for Llama 3 models on standard automatic benchmarks. For all the evaluations, we use our internal evaluations library. For details on the methodology see here.
### Base pretrained models
### Instruction tuned models
### Responsibility & Safety
We believe that an open approach to AI leads to better, safer products, faster innovation, and a bigger overall market. We are committed to Responsible AI development and took a series of steps to limit misuse and harm and support the open source community.
Foundation models are widely capable technologies that are built to be used for a diverse range of applications. They are not designed to meet every developer preference on safety levels for all use cases, out-of-the-box, as those by their nature will differ across different applications.
Rather, responsible LLM-application deployment is achieved by implementing a series of safety best practices throughout the development of such applications, from the model pre-training, fine-tuning and the deployment of systems composed of safeguards to tailor the safety needs specifically to the use case and audience.
As part of the Llama 3 release, we updated our Responsible Use Guide to outline the steps and best practices for developers to implement model and system level safety for their application. We also provide a set of resources including Meta Llama Guard 2 and Code Shield safeguards. These tools have proven to drastically reduce residual risks of LLM Systems, while maintaining a high level of helpfulness. We encourage developers to tune and deploy these safeguards according to their needs and we provide a reference implementation to get you started.
#### Llama 3-Instruct
As outlined in the Responsible Use Guide, some trade-off between model helpfulness and model alignment is likely unavoidable. Developers should exercise discretion about how to weigh the benefits of alignment and helpfulness for their specific use case and audience. Developers should be mindful of residual risks when using Llama models and leverage additional safety tools as needed to reach the right safety bar for their use case.
Safety
For our instruction tuned model, we conducted extensive red teaming exercises, performed adversarial evaluations and implemented safety mitigations techniques to lower residual risks. As with any Large Language Model, residual risks will likely remain and we recommend that developers assess these risks in the context of their use case. In parallel, we are working with the community to make AI safety benchmark standards transparent, rigorous and interpretable.
Refusals
In addition to residual risks, we put a great emphasis on model refusals to benign prompts. Over-refusing not only can impact the user experience but could even be harmful in certain contexts as well. We’ve heard the feedback from the developer community and improved our fine tuning to ensure that Llama 3 is significantly less likely to falsely refuse to answer prompts than Llama 2.
We built internal benchmarks and developed mitigations to limit false refusals making Llama 3 our most helpful model to date.
#### Responsible release
In addition to responsible use considerations outlined above, we followed a rigorous process that requires us to take extra measures against misuse and critical risks before we make our release decision.
Misuse
If you access or use Llama 3, you agree to the Acceptable Use Policy. The most recent copy of this policy can be found at URL
#### Critical risks
CBRNE (Chemical, Biological, Radiological, Nuclear, and high yield Explosives)
We have conducted a two fold assessment of the safety of the model in this area:
* Iterative testing during model training to assess the safety of responses related to CBRNE threats and other adversarial risks.
* Involving external CBRNE experts to conduct an uplift test assessing the ability of the model to accurately provide expert knowledge and reduce barriers to potential CBRNE misuse, by reference to what can be achieved using web search (without the model).
### Cyber Security
We have evaluated Llama 3 with CyberSecEval, Meta’s cybersecurity safety eval suite, measuring Llama 3’s propensity to suggest insecure code when used as a coding assistant, and Llama 3’s propensity to comply with requests to help carry out cyber attacks, where attacks are defined by the industry standard MITRE ATT&CK cyber attack ontology. On our insecure coding and cyber attacker helpfulness tests, Llama 3 behaved in the same range or safer than models of equivalent coding capability.
### Child Safety
Child Safety risk assessments were conducted using a team of experts, to assess the model’s capability to produce outputs that could result in Child Safety risks and inform on any necessary and appropriate risk mitigations via fine tuning. We leveraged those expert red teaming sessions to expand the coverage of our evaluation benchmarks through Llama 3 model development. For Llama 3, we conducted new in-depth sessions using objective based methodologies to assess the model risks along multiple attack vectors. We also partnered with content specialists to perform red teaming exercises assessing potentially violating content while taking account of market specific nuances or experiences.
### Community
Generative AI safety requires expertise and tooling, and we believe in the strength of the open community to accelerate its progress. We are active members of open consortiums, including the AI Alliance, Partnership in AI and MLCommons, actively contributing to safety standardization and transparency. We encourage the community to adopt taxonomies like the MLCommons Proof of Concept evaluation to facilitate collaboration and transparency on safety and content evaluations. Our Purple Llama tools are open sourced for the community to use and widely distributed across ecosystem partners including cloud service providers. We encourage community contributions to our Github repository.
Finally, we put in place a set of resources including an output reporting mechanism and bug bounty program to continuously improve the Llama technology with the help of the community.
Ethical Considerations and Limitations
--------------------------------------
The core values of Llama 3 are openness, inclusivity and helpfulness. It is meant to serve everyone, and to work for a wide range of use cases. It is thus designed to be accessible to people across many different backgrounds, experiences and perspectives. Llama 3 addresses users and their needs as they are, without insertion unnecessary judgment or normativity, while reflecting the understanding that even content that may appear problematic in some cases can serve valuable purposes in others. It respects the dignity and autonomy of all users, especially in terms of the values of free thought and expression that power innovation and progress.
But Llama 3 is a new technology, and like any new technology, there are risks associated with its use. Testing conducted to date has been in English, and has not covered, nor could it cover, all scenarios. For these reasons, as with all LLMs, Llama 3’s potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate, biased or other objectionable responses to user prompts. Therefore, before deploying any applications of Llama 3 models, developers should perform safety testing and tuning tailored to their specific applications of the model. As outlined in the Responsible Use Guide, we recommend incorporating Purple Llama solutions into your workflows and specifically Llama Guard which provides a base model to filter input and output prompts to layer system-level safety on top of model-level safety.
Please see the Responsible Use Guide available at URL
instructions
@article{llama3modelcard,
title={Llama 3 Model Card},
author={AI@Meta},
year={2024},
url = {URL
}
Contributors
------------
Aaditya Singh; Aaron Grattafiori; Abhimanyu Dubey; Abhinav Jauhri; Abhinav Pandey; Abhishek Kadian; Adam Kelsey; Adi Gangidi; Ahmad Al-Dahle; Ahuva Goldstand; Aiesha Letman; Ajay Menon; Akhil Mathur; Alan Schelten; Alex Vaughan; Amy Yang; Andrei Lupu; Andres Alvarado; Andrew Gallagher; Andrew Gu; Andrew Ho; Andrew Poulton; Andrew Ryan; Angela Fan; Ankit Ramchandani; Anthony Hartshorn; Archi Mitra; Archie Sravankumar; Artem Korenev; Arun Rao; Ashley Gabriel; Ashwin Bharambe; Assaf Eisenman; Aston Zhang; Aurelien Rodriguez; Austen Gregerson; Ava Spataru; Baptiste Roziere; Ben Maurer; Benjamin Leonhardi; Bernie Huang; Bhargavi Paranjape; Bing Liu; Binh Tang; Bobbie Chern; Brani Stojkovic; Brian Fuller; Catalina Mejia Arenas; Chao Zhou; Charlotte Caucheteux; Chaya Nayak; Ching-Hsiang Chu; Chloe Bi; Chris Cai; Chris Cox; Chris Marra; Chris McConnell; Christian Keller; Christoph Feichtenhofer; Christophe Touret; Chunyang Wu; Corinne Wong; Cristian Canton Ferrer; Damien Allonsius; Daniel Kreymer; Daniel Haziza; Daniel Li; Danielle Pintz; Danny Livshits; Danny Wyatt; David Adkins; David Esiobu; David Xu; Davide Testuggine; Delia David; Devi Parikh; Dhruv Choudhary; Dhruv Mahajan; Diana Liskovich; Diego Garcia-Olano; Diego Perino; Dieuwke Hupkes; Dingkang Wang; Dustin Holland; Egor Lakomkin; Elina Lobanova; Xiaoqing Ellen Tan; Emily Dinan; Eric Smith; Erik Brinkman; Esteban Arcaute; Filip Radenovic; Firat Ozgenel; Francesco Caggioni; Frank Seide; Frank Zhang; Gabriel Synnaeve; Gabriella Schwarz; Gabrielle Lee; Gada Badeer; Georgia Anderson; Graeme Nail; Gregoire Mialon; Guan Pang; Guillem Cucurell; Hailey Nguyen; Hannah Korevaar; Hannah Wang; Haroun Habeeb; Harrison Rudolph; Henry Aspegren; Hu Xu; Hugo Touvron; Iga Kozlowska; Igor Molybog; Igor Tufanov; Iliyan Zarov; Imanol Arrieta Ibarra; Irina-Elena Veliche; Isabel Kloumann; Ishan Misra; Ivan Evtimov; Jacob Xu; Jade Copet; Jake Weissman; Jan Geffert; Jana Vranes; Japhet Asher; Jason Park; Jay Mahadeokar; Jean-Baptiste Gaya; Jeet Shah; Jelmer van der Linde; Jennifer Chan; Jenny Hong; Jenya Lee; Jeremy Fu; Jeremy Teboul; Jianfeng Chi; Jianyu Huang; Jie Wang; Jiecao Yu; Joanna Bitton; Joe Spisak; Joelle Pineau; Jon Carvill; Jongsoo Park; Joseph Rocca; Joshua Johnstun; Junteng Jia; Kalyan Vasuden Alwala; Kam Hou U; Kate Plawiak; Kartikeya Upasani; Kaushik Veeraraghavan; Ke Li; Kenneth Heafield; Kevin Stone; Khalid El-Arini; Krithika Iyer; Kshitiz Malik; Kuenley Chiu; Kunal Bhalla; Kyle Huang; Lakshya Garg; Lauren Rantala-Yeary; Laurens van der Maaten; Lawrence Chen; Leandro Silva; Lee Bell; Lei Zhang; Liang Tan; Louis Martin; Lovish Madaan; Luca Wehrstedt; Lukas Blecher; Luke de Oliveira; Madeline Muzzi; Madian Khabsa; Manav Avlani; Mannat Singh; Manohar Paluri; Mark Zuckerberg; Marcin Kardas; Martynas Mankus; Mathew Oldham; Mathieu Rita; Matthew Lennie; Maya Pavlova; Meghan Keneally; Melanie Kambadur; Mihir Patel; Mikayel Samvelyan; Mike Clark; Mike Lewis; Min Si; Mitesh Kumar Singh; Mo Metanat; Mona Hassan; Naman Goyal; Narjes Torabi; Nicolas Usunier; Nikolay Bashlykov; Nikolay Bogoychev; Niladri Chatterji; Ning Dong; Oliver Aobo Yang; Olivier Duchenne; Onur Celebi; Parth Parekh; Patrick Alrassy; Paul Saab; Pavan Balaji; Pedro Rittner; Pengchuan Zhang; Pengwei Li; Petar Vasic; Peter Weng; Polina Zvyagina; Prajjwal Bhargava; Pratik Dubal; Praveen Krishnan; Punit Singh Koura; Qing He; Rachel Rodriguez; Ragavan Srinivasan; Rahul Mitra; Ramon Calderer; Raymond Li; Robert Stojnic; Roberta Raileanu; Robin Battey; Rocky Wang; Rohit Girdhar; Rohit Patel; Romain Sauvestre; Ronnie Polidoro; Roshan Sumbaly; Ross Taylor; Ruan Silva; Rui Hou; Rui Wang; Russ Howes; Ruty Rinott; Saghar Hosseini; Sai Jayesh Bondu; Samyak Datta; Sanjay Singh; Sara Chugh; Sargun Dhillon; Satadru Pan; Sean Bell; Sergey Edunov; Shaoliang Nie; Sharan Narang; Sharath Raparthy; Shaun Lindsay; Sheng Feng; Sheng Shen; Shenghao Lin; Shiva Shankar; Shruti Bhosale; Shun Zhang; Simon Vandenhende; Sinong Wang; Seohyun Sonia Kim; Soumya Batra; Sten Sootla; Steve Kehoe; Suchin Gururangan; Sumit Gupta; Sunny Virk; Sydney Borodinsky; Tamar Glaser; Tamar Herman; Tamara Best; Tara Fowler; Thomas Georgiou; Thomas Scialom; Tianhe Li; Todor Mihaylov; Tong Xiao; Ujjwal Karn; Vedanuj Goswami; Vibhor Gupta; Vignesh Ramanathan; Viktor Kerkez; Vinay Satish Kumar; Vincent Gonguet; Vish Vogeti; Vlad Poenaru; Vlad Tiberiu Mihailescu; Vladan Petrovic; Vladimir Ivanov; Wei Li; Weiwei Chu; Wenhan Xiong; Wenyin Fu; Wes Bouaziz; Whitney Meers; Will Constable; Xavier Martinet; Xiaojian Wu; Xinbo Gao; Xinfeng Xie; Xuchao Jia; Yaelle Goldschlag; Yann LeCun; Yashesh Gaur; Yasmine Babaei; Ye Qi; Yenda Li; Yi Wen; Yiwen Song; Youngjin Nam; Yuchen Hao; Yuchen Zhang; Yun Wang; Yuning Mao; Yuzi He; Zacharie Delpierre Coudert; Zachary DeVito; Zahra Hankir; Zhaoduo Wen; Zheng Yan; Zhengxing Chen; Zhenyu Yang; Zoe Papakipos
| [
"### ~Original Model Card~\n\n\nModel Details\n-------------\n\n\nMeta developed and released the Meta Llama 3 family of large language models (LLMs), a collection of pretrained and instruction tuned generative text models in 8 and 70B sizes. The Llama 3 instruction tuned models are optimized for dialogue use cases and outperform many of the available open source chat models on common industry benchmarks. Further, in developing these models, we took great care to optimize helpfulness and safety.\n\n\nModel developers Meta\n\n\nVariations Llama 3 comes in two sizes — 8B and 70B parameters — in pre-trained and instruction tuned variants.\n\n\nInput Models input text only.\n\n\nOutput Models generate text and code only.\n\n\nModel Architecture Llama 3 is an auto-regressive language model that uses an optimized transformer architecture. The tuned versions use supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF) to align with human preferences for helpfulness and safety.\n\n\n\nLlama 3 family of models. Token counts refer to pretraining data only. Both the 8 and 70B versions use Grouped-Query Attention (GQA) for improved inference scalability.\n\n\nModel Release Date April 18, 2024.\n\n\nStatus This is a static model trained on an offline dataset. Future versions of the tuned models will be released as we improve model safety with community feedback.\n\n\nLicense A custom commercial license is available at: URL\n\n\nWhere to send questions or comments about the model Instructions on how to provide feedback or comments on the model can be found in the model README. For more technical information about generation parameters and recipes for how to use Llama 3 in applications, please go here.\n\n\nIntended Use\n------------\n\n\nIntended Use Cases Llama 3 is intended for commercial and research use in English. Instruction tuned models are intended for assistant-like chat, whereas pretrained models can be adapted for a variety of natural language generation tasks.\n\n\nOut-of-scope Use in any manner that violates applicable laws or regulations (including trade compliance laws). Use in any other way that is prohibited by the Acceptable Use Policy and Llama 3 Community License. Use in languages other than English.\n\n\nNote: Developers may fine-tune Llama 3 models for languages beyond English provided they comply with the Llama 3 Community License and the Acceptable Use Policy.\n\n\nHow to use\n----------\n\n\nThis repository contains two versions of Meta-Llama-3-8B-Instruct, for use with transformers and with the original 'llama3' codebase.",
"### Use with transformers\n\n\nYou can run conversational inference using the Transformers pipeline abstraction, or by leveraging the Auto classes with the 'generate()' function. Let's see examples of both.",
"#### Transformers pipeline",
"#### Transformers AutoModelForCausalLM",
"### Use with 'llama3'\n\n\nPlease, follow the instructions in the repository\n\n\nTo download Original checkpoints, see the example command below leveraging 'huggingface-cli':\n\n\nFor Hugging Face support, we recommend using transformers or TGI, but a similar command works.\n\n\nHardware and Software\n---------------------\n\n\nTraining Factors We used custom training libraries, Meta's Research SuperCluster, and production clusters for pretraining. Fine-tuning, annotation, and evaluation were also performed on third-party cloud compute.\n\n\nCarbon Footprint Pretraining utilized a cumulative 7.7M GPU hours of computation on hardware of type H100-80GB (TDP of 700W). Estimated total emissions were 2290 tCO2eq, 100% of which were offset by Meta’s sustainability program.\n\n\n\nCO2 emissions during pre-training. Time: total GPU time required for training each model. Power Consumption: peak power capacity per GPU device for the GPUs used adjusted for power usage efficiency. 100% of the emissions are directly offset by Meta's sustainability program, and because we are openly releasing these models, the pretraining costs do not need to be incurred by others.\n\n\nTraining Data\n-------------\n\n\nOverview Llama 3 was pretrained on over 15 trillion tokens of data from publicly available sources. The fine-tuning data includes publicly available instruction datasets, as well as over 10M human-annotated examples. Neither the pretraining nor the fine-tuning datasets include Meta user data.\n\n\nData Freshness The pretraining data has a cutoff of March 2023 for the 7B and December 2023 for the 70B models respectively.\n\n\nBenchmarks\n----------\n\n\nIn this section, we report the results for Llama 3 models on standard automatic benchmarks. For all the evaluations, we use our internal evaluations library. For details on the methodology see here.",
"### Base pretrained models",
"### Instruction tuned models",
"### Responsibility & Safety\n\n\nWe believe that an open approach to AI leads to better, safer products, faster innovation, and a bigger overall market. We are committed to Responsible AI development and took a series of steps to limit misuse and harm and support the open source community.\n\n\nFoundation models are widely capable technologies that are built to be used for a diverse range of applications. They are not designed to meet every developer preference on safety levels for all use cases, out-of-the-box, as those by their nature will differ across different applications.\n\n\nRather, responsible LLM-application deployment is achieved by implementing a series of safety best practices throughout the development of such applications, from the model pre-training, fine-tuning and the deployment of systems composed of safeguards to tailor the safety needs specifically to the use case and audience.\n\n\nAs part of the Llama 3 release, we updated our Responsible Use Guide to outline the steps and best practices for developers to implement model and system level safety for their application. We also provide a set of resources including Meta Llama Guard 2 and Code Shield safeguards. These tools have proven to drastically reduce residual risks of LLM Systems, while maintaining a high level of helpfulness. We encourage developers to tune and deploy these safeguards according to their needs and we provide a reference implementation to get you started.",
"#### Llama 3-Instruct\n\n\nAs outlined in the Responsible Use Guide, some trade-off between model helpfulness and model alignment is likely unavoidable. Developers should exercise discretion about how to weigh the benefits of alignment and helpfulness for their specific use case and audience. Developers should be mindful of residual risks when using Llama models and leverage additional safety tools as needed to reach the right safety bar for their use case.\n\n\nSafety\n\n\nFor our instruction tuned model, we conducted extensive red teaming exercises, performed adversarial evaluations and implemented safety mitigations techniques to lower residual risks. As with any Large Language Model, residual risks will likely remain and we recommend that developers assess these risks in the context of their use case. In parallel, we are working with the community to make AI safety benchmark standards transparent, rigorous and interpretable.\n\n\nRefusals\n\n\nIn addition to residual risks, we put a great emphasis on model refusals to benign prompts. Over-refusing not only can impact the user experience but could even be harmful in certain contexts as well. We’ve heard the feedback from the developer community and improved our fine tuning to ensure that Llama 3 is significantly less likely to falsely refuse to answer prompts than Llama 2.\n\n\nWe built internal benchmarks and developed mitigations to limit false refusals making Llama 3 our most helpful model to date.",
"#### Responsible release\n\n\nIn addition to responsible use considerations outlined above, we followed a rigorous process that requires us to take extra measures against misuse and critical risks before we make our release decision.\n\n\nMisuse\n\n\nIf you access or use Llama 3, you agree to the Acceptable Use Policy. The most recent copy of this policy can be found at URL",
"#### Critical risks\n\n\nCBRNE (Chemical, Biological, Radiological, Nuclear, and high yield Explosives)\n\n\nWe have conducted a two fold assessment of the safety of the model in this area:\n\n\n* Iterative testing during model training to assess the safety of responses related to CBRNE threats and other adversarial risks.\n* Involving external CBRNE experts to conduct an uplift test assessing the ability of the model to accurately provide expert knowledge and reduce barriers to potential CBRNE misuse, by reference to what can be achieved using web search (without the model).",
"### Cyber Security\n\n\nWe have evaluated Llama 3 with CyberSecEval, Meta’s cybersecurity safety eval suite, measuring Llama 3’s propensity to suggest insecure code when used as a coding assistant, and Llama 3’s propensity to comply with requests to help carry out cyber attacks, where attacks are defined by the industry standard MITRE ATT&CK cyber attack ontology. On our insecure coding and cyber attacker helpfulness tests, Llama 3 behaved in the same range or safer than models of equivalent coding capability.",
"### Child Safety\n\n\nChild Safety risk assessments were conducted using a team of experts, to assess the model’s capability to produce outputs that could result in Child Safety risks and inform on any necessary and appropriate risk mitigations via fine tuning. We leveraged those expert red teaming sessions to expand the coverage of our evaluation benchmarks through Llama 3 model development. For Llama 3, we conducted new in-depth sessions using objective based methodologies to assess the model risks along multiple attack vectors. We also partnered with content specialists to perform red teaming exercises assessing potentially violating content while taking account of market specific nuances or experiences.",
"### Community\n\n\nGenerative AI safety requires expertise and tooling, and we believe in the strength of the open community to accelerate its progress. We are active members of open consortiums, including the AI Alliance, Partnership in AI and MLCommons, actively contributing to safety standardization and transparency. We encourage the community to adopt taxonomies like the MLCommons Proof of Concept evaluation to facilitate collaboration and transparency on safety and content evaluations. Our Purple Llama tools are open sourced for the community to use and widely distributed across ecosystem partners including cloud service providers. We encourage community contributions to our Github repository.\n\n\nFinally, we put in place a set of resources including an output reporting mechanism and bug bounty program to continuously improve the Llama technology with the help of the community.\n\n\nEthical Considerations and Limitations\n--------------------------------------\n\n\nThe core values of Llama 3 are openness, inclusivity and helpfulness. It is meant to serve everyone, and to work for a wide range of use cases. It is thus designed to be accessible to people across many different backgrounds, experiences and perspectives. Llama 3 addresses users and their needs as they are, without insertion unnecessary judgment or normativity, while reflecting the understanding that even content that may appear problematic in some cases can serve valuable purposes in others. It respects the dignity and autonomy of all users, especially in terms of the values of free thought and expression that power innovation and progress.\n\n\nBut Llama 3 is a new technology, and like any new technology, there are risks associated with its use. Testing conducted to date has been in English, and has not covered, nor could it cover, all scenarios. For these reasons, as with all LLMs, Llama 3’s potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate, biased or other objectionable responses to user prompts. Therefore, before deploying any applications of Llama 3 models, developers should perform safety testing and tuning tailored to their specific applications of the model. As outlined in the Responsible Use Guide, we recommend incorporating Purple Llama solutions into your workflows and specifically Llama Guard which provides a base model to filter input and output prompts to layer system-level safety on top of model-level safety.\n\n\nPlease see the Responsible Use Guide available at URL\n\n\ninstructions\n\n\n@article{llama3modelcard,\n\n\ntitle={Llama 3 Model Card},\n\n\nauthor={AI@Meta},\n\n\nyear={2024},\n\n\nurl = {URL\n\n\n}\n\n\nContributors\n------------\n\n\nAaditya Singh; Aaron Grattafiori; Abhimanyu Dubey; Abhinav Jauhri; Abhinav Pandey; Abhishek Kadian; Adam Kelsey; Adi Gangidi; Ahmad Al-Dahle; Ahuva Goldstand; Aiesha Letman; Ajay Menon; Akhil Mathur; Alan Schelten; Alex Vaughan; Amy Yang; Andrei Lupu; Andres Alvarado; Andrew Gallagher; Andrew Gu; Andrew Ho; Andrew Poulton; Andrew Ryan; Angela Fan; Ankit Ramchandani; Anthony Hartshorn; Archi Mitra; Archie Sravankumar; Artem Korenev; Arun Rao; Ashley Gabriel; Ashwin Bharambe; Assaf Eisenman; Aston Zhang; Aurelien Rodriguez; Austen Gregerson; Ava Spataru; Baptiste Roziere; Ben Maurer; Benjamin Leonhardi; Bernie Huang; Bhargavi Paranjape; Bing Liu; Binh Tang; Bobbie Chern; Brani Stojkovic; Brian Fuller; Catalina Mejia Arenas; Chao Zhou; Charlotte Caucheteux; Chaya Nayak; Ching-Hsiang Chu; Chloe Bi; Chris Cai; Chris Cox; Chris Marra; Chris McConnell; Christian Keller; Christoph Feichtenhofer; Christophe Touret; Chunyang Wu; Corinne Wong; Cristian Canton Ferrer; Damien Allonsius; Daniel Kreymer; Daniel Haziza; Daniel Li; Danielle Pintz; Danny Livshits; Danny Wyatt; David Adkins; David Esiobu; David Xu; Davide Testuggine; Delia David; Devi Parikh; Dhruv Choudhary; Dhruv Mahajan; Diana Liskovich; Diego Garcia-Olano; Diego Perino; Dieuwke Hupkes; Dingkang Wang; Dustin Holland; Egor Lakomkin; Elina Lobanova; Xiaoqing Ellen Tan; Emily Dinan; Eric Smith; Erik Brinkman; Esteban Arcaute; Filip Radenovic; Firat Ozgenel; Francesco Caggioni; Frank Seide; Frank Zhang; Gabriel Synnaeve; Gabriella Schwarz; Gabrielle Lee; Gada Badeer; Georgia Anderson; Graeme Nail; Gregoire Mialon; Guan Pang; Guillem Cucurell; Hailey Nguyen; Hannah Korevaar; Hannah Wang; Haroun Habeeb; Harrison Rudolph; Henry Aspegren; Hu Xu; Hugo Touvron; Iga Kozlowska; Igor Molybog; Igor Tufanov; Iliyan Zarov; Imanol Arrieta Ibarra; Irina-Elena Veliche; Isabel Kloumann; Ishan Misra; Ivan Evtimov; Jacob Xu; Jade Copet; Jake Weissman; Jan Geffert; Jana Vranes; Japhet Asher; Jason Park; Jay Mahadeokar; Jean-Baptiste Gaya; Jeet Shah; Jelmer van der Linde; Jennifer Chan; Jenny Hong; Jenya Lee; Jeremy Fu; Jeremy Teboul; Jianfeng Chi; Jianyu Huang; Jie Wang; Jiecao Yu; Joanna Bitton; Joe Spisak; Joelle Pineau; Jon Carvill; Jongsoo Park; Joseph Rocca; Joshua Johnstun; Junteng Jia; Kalyan Vasuden Alwala; Kam Hou U; Kate Plawiak; Kartikeya Upasani; Kaushik Veeraraghavan; Ke Li; Kenneth Heafield; Kevin Stone; Khalid El-Arini; Krithika Iyer; Kshitiz Malik; Kuenley Chiu; Kunal Bhalla; Kyle Huang; Lakshya Garg; Lauren Rantala-Yeary; Laurens van der Maaten; Lawrence Chen; Leandro Silva; Lee Bell; Lei Zhang; Liang Tan; Louis Martin; Lovish Madaan; Luca Wehrstedt; Lukas Blecher; Luke de Oliveira; Madeline Muzzi; Madian Khabsa; Manav Avlani; Mannat Singh; Manohar Paluri; Mark Zuckerberg; Marcin Kardas; Martynas Mankus; Mathew Oldham; Mathieu Rita; Matthew Lennie; Maya Pavlova; Meghan Keneally; Melanie Kambadur; Mihir Patel; Mikayel Samvelyan; Mike Clark; Mike Lewis; Min Si; Mitesh Kumar Singh; Mo Metanat; Mona Hassan; Naman Goyal; Narjes Torabi; Nicolas Usunier; Nikolay Bashlykov; Nikolay Bogoychev; Niladri Chatterji; Ning Dong; Oliver Aobo Yang; Olivier Duchenne; Onur Celebi; Parth Parekh; Patrick Alrassy; Paul Saab; Pavan Balaji; Pedro Rittner; Pengchuan Zhang; Pengwei Li; Petar Vasic; Peter Weng; Polina Zvyagina; Prajjwal Bhargava; Pratik Dubal; Praveen Krishnan; Punit Singh Koura; Qing He; Rachel Rodriguez; Ragavan Srinivasan; Rahul Mitra; Ramon Calderer; Raymond Li; Robert Stojnic; Roberta Raileanu; Robin Battey; Rocky Wang; Rohit Girdhar; Rohit Patel; Romain Sauvestre; Ronnie Polidoro; Roshan Sumbaly; Ross Taylor; Ruan Silva; Rui Hou; Rui Wang; Russ Howes; Ruty Rinott; Saghar Hosseini; Sai Jayesh Bondu; Samyak Datta; Sanjay Singh; Sara Chugh; Sargun Dhillon; Satadru Pan; Sean Bell; Sergey Edunov; Shaoliang Nie; Sharan Narang; Sharath Raparthy; Shaun Lindsay; Sheng Feng; Sheng Shen; Shenghao Lin; Shiva Shankar; Shruti Bhosale; Shun Zhang; Simon Vandenhende; Sinong Wang; Seohyun Sonia Kim; Soumya Batra; Sten Sootla; Steve Kehoe; Suchin Gururangan; Sumit Gupta; Sunny Virk; Sydney Borodinsky; Tamar Glaser; Tamar Herman; Tamara Best; Tara Fowler; Thomas Georgiou; Thomas Scialom; Tianhe Li; Todor Mihaylov; Tong Xiao; Ujjwal Karn; Vedanuj Goswami; Vibhor Gupta; Vignesh Ramanathan; Viktor Kerkez; Vinay Satish Kumar; Vincent Gonguet; Vish Vogeti; Vlad Poenaru; Vlad Tiberiu Mihailescu; Vladan Petrovic; Vladimir Ivanov; Wei Li; Weiwei Chu; Wenhan Xiong; Wenyin Fu; Wes Bouaziz; Whitney Meers; Will Constable; Xavier Martinet; Xiaojian Wu; Xinbo Gao; Xinfeng Xie; Xuchao Jia; Yaelle Goldschlag; Yann LeCun; Yashesh Gaur; Yasmine Babaei; Ye Qi; Yenda Li; Yi Wen; Yiwen Song; Youngjin Nam; Yuchen Hao; Yuchen Zhang; Yun Wang; Yuning Mao; Yuzi He; Zacharie Delpierre Coudert; Zachary DeVito; Zahra Hankir; Zhaoduo Wen; Zheng Yan; Zhengxing Chen; Zhenyu Yang; Zoe Papakipos"
] | [
"TAGS\n#llamafile #facebook #meta #pytorch #llama #llama-3 #license-other #region-us \n",
"### ~Original Model Card~\n\n\nModel Details\n-------------\n\n\nMeta developed and released the Meta Llama 3 family of large language models (LLMs), a collection of pretrained and instruction tuned generative text models in 8 and 70B sizes. The Llama 3 instruction tuned models are optimized for dialogue use cases and outperform many of the available open source chat models on common industry benchmarks. Further, in developing these models, we took great care to optimize helpfulness and safety.\n\n\nModel developers Meta\n\n\nVariations Llama 3 comes in two sizes — 8B and 70B parameters — in pre-trained and instruction tuned variants.\n\n\nInput Models input text only.\n\n\nOutput Models generate text and code only.\n\n\nModel Architecture Llama 3 is an auto-regressive language model that uses an optimized transformer architecture. The tuned versions use supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF) to align with human preferences for helpfulness and safety.\n\n\n\nLlama 3 family of models. Token counts refer to pretraining data only. Both the 8 and 70B versions use Grouped-Query Attention (GQA) for improved inference scalability.\n\n\nModel Release Date April 18, 2024.\n\n\nStatus This is a static model trained on an offline dataset. Future versions of the tuned models will be released as we improve model safety with community feedback.\n\n\nLicense A custom commercial license is available at: URL\n\n\nWhere to send questions or comments about the model Instructions on how to provide feedback or comments on the model can be found in the model README. For more technical information about generation parameters and recipes for how to use Llama 3 in applications, please go here.\n\n\nIntended Use\n------------\n\n\nIntended Use Cases Llama 3 is intended for commercial and research use in English. Instruction tuned models are intended for assistant-like chat, whereas pretrained models can be adapted for a variety of natural language generation tasks.\n\n\nOut-of-scope Use in any manner that violates applicable laws or regulations (including trade compliance laws). Use in any other way that is prohibited by the Acceptable Use Policy and Llama 3 Community License. Use in languages other than English.\n\n\nNote: Developers may fine-tune Llama 3 models for languages beyond English provided they comply with the Llama 3 Community License and the Acceptable Use Policy.\n\n\nHow to use\n----------\n\n\nThis repository contains two versions of Meta-Llama-3-8B-Instruct, for use with transformers and with the original 'llama3' codebase.",
"### Use with transformers\n\n\nYou can run conversational inference using the Transformers pipeline abstraction, or by leveraging the Auto classes with the 'generate()' function. Let's see examples of both.",
"#### Transformers pipeline",
"#### Transformers AutoModelForCausalLM",
"### Use with 'llama3'\n\n\nPlease, follow the instructions in the repository\n\n\nTo download Original checkpoints, see the example command below leveraging 'huggingface-cli':\n\n\nFor Hugging Face support, we recommend using transformers or TGI, but a similar command works.\n\n\nHardware and Software\n---------------------\n\n\nTraining Factors We used custom training libraries, Meta's Research SuperCluster, and production clusters for pretraining. Fine-tuning, annotation, and evaluation were also performed on third-party cloud compute.\n\n\nCarbon Footprint Pretraining utilized a cumulative 7.7M GPU hours of computation on hardware of type H100-80GB (TDP of 700W). Estimated total emissions were 2290 tCO2eq, 100% of which were offset by Meta’s sustainability program.\n\n\n\nCO2 emissions during pre-training. Time: total GPU time required for training each model. Power Consumption: peak power capacity per GPU device for the GPUs used adjusted for power usage efficiency. 100% of the emissions are directly offset by Meta's sustainability program, and because we are openly releasing these models, the pretraining costs do not need to be incurred by others.\n\n\nTraining Data\n-------------\n\n\nOverview Llama 3 was pretrained on over 15 trillion tokens of data from publicly available sources. The fine-tuning data includes publicly available instruction datasets, as well as over 10M human-annotated examples. Neither the pretraining nor the fine-tuning datasets include Meta user data.\n\n\nData Freshness The pretraining data has a cutoff of March 2023 for the 7B and December 2023 for the 70B models respectively.\n\n\nBenchmarks\n----------\n\n\nIn this section, we report the results for Llama 3 models on standard automatic benchmarks. For all the evaluations, we use our internal evaluations library. For details on the methodology see here.",
"### Base pretrained models",
"### Instruction tuned models",
"### Responsibility & Safety\n\n\nWe believe that an open approach to AI leads to better, safer products, faster innovation, and a bigger overall market. We are committed to Responsible AI development and took a series of steps to limit misuse and harm and support the open source community.\n\n\nFoundation models are widely capable technologies that are built to be used for a diverse range of applications. They are not designed to meet every developer preference on safety levels for all use cases, out-of-the-box, as those by their nature will differ across different applications.\n\n\nRather, responsible LLM-application deployment is achieved by implementing a series of safety best practices throughout the development of such applications, from the model pre-training, fine-tuning and the deployment of systems composed of safeguards to tailor the safety needs specifically to the use case and audience.\n\n\nAs part of the Llama 3 release, we updated our Responsible Use Guide to outline the steps and best practices for developers to implement model and system level safety for their application. We also provide a set of resources including Meta Llama Guard 2 and Code Shield safeguards. These tools have proven to drastically reduce residual risks of LLM Systems, while maintaining a high level of helpfulness. We encourage developers to tune and deploy these safeguards according to their needs and we provide a reference implementation to get you started.",
"#### Llama 3-Instruct\n\n\nAs outlined in the Responsible Use Guide, some trade-off between model helpfulness and model alignment is likely unavoidable. Developers should exercise discretion about how to weigh the benefits of alignment and helpfulness for their specific use case and audience. Developers should be mindful of residual risks when using Llama models and leverage additional safety tools as needed to reach the right safety bar for their use case.\n\n\nSafety\n\n\nFor our instruction tuned model, we conducted extensive red teaming exercises, performed adversarial evaluations and implemented safety mitigations techniques to lower residual risks. As with any Large Language Model, residual risks will likely remain and we recommend that developers assess these risks in the context of their use case. In parallel, we are working with the community to make AI safety benchmark standards transparent, rigorous and interpretable.\n\n\nRefusals\n\n\nIn addition to residual risks, we put a great emphasis on model refusals to benign prompts. Over-refusing not only can impact the user experience but could even be harmful in certain contexts as well. We’ve heard the feedback from the developer community and improved our fine tuning to ensure that Llama 3 is significantly less likely to falsely refuse to answer prompts than Llama 2.\n\n\nWe built internal benchmarks and developed mitigations to limit false refusals making Llama 3 our most helpful model to date.",
"#### Responsible release\n\n\nIn addition to responsible use considerations outlined above, we followed a rigorous process that requires us to take extra measures against misuse and critical risks before we make our release decision.\n\n\nMisuse\n\n\nIf you access or use Llama 3, you agree to the Acceptable Use Policy. The most recent copy of this policy can be found at URL",
"#### Critical risks\n\n\nCBRNE (Chemical, Biological, Radiological, Nuclear, and high yield Explosives)\n\n\nWe have conducted a two fold assessment of the safety of the model in this area:\n\n\n* Iterative testing during model training to assess the safety of responses related to CBRNE threats and other adversarial risks.\n* Involving external CBRNE experts to conduct an uplift test assessing the ability of the model to accurately provide expert knowledge and reduce barriers to potential CBRNE misuse, by reference to what can be achieved using web search (without the model).",
"### Cyber Security\n\n\nWe have evaluated Llama 3 with CyberSecEval, Meta’s cybersecurity safety eval suite, measuring Llama 3’s propensity to suggest insecure code when used as a coding assistant, and Llama 3’s propensity to comply with requests to help carry out cyber attacks, where attacks are defined by the industry standard MITRE ATT&CK cyber attack ontology. On our insecure coding and cyber attacker helpfulness tests, Llama 3 behaved in the same range or safer than models of equivalent coding capability.",
"### Child Safety\n\n\nChild Safety risk assessments were conducted using a team of experts, to assess the model’s capability to produce outputs that could result in Child Safety risks and inform on any necessary and appropriate risk mitigations via fine tuning. We leveraged those expert red teaming sessions to expand the coverage of our evaluation benchmarks through Llama 3 model development. For Llama 3, we conducted new in-depth sessions using objective based methodologies to assess the model risks along multiple attack vectors. We also partnered with content specialists to perform red teaming exercises assessing potentially violating content while taking account of market specific nuances or experiences.",
"### Community\n\n\nGenerative AI safety requires expertise and tooling, and we believe in the strength of the open community to accelerate its progress. We are active members of open consortiums, including the AI Alliance, Partnership in AI and MLCommons, actively contributing to safety standardization and transparency. We encourage the community to adopt taxonomies like the MLCommons Proof of Concept evaluation to facilitate collaboration and transparency on safety and content evaluations. Our Purple Llama tools are open sourced for the community to use and widely distributed across ecosystem partners including cloud service providers. We encourage community contributions to our Github repository.\n\n\nFinally, we put in place a set of resources including an output reporting mechanism and bug bounty program to continuously improve the Llama technology with the help of the community.\n\n\nEthical Considerations and Limitations\n--------------------------------------\n\n\nThe core values of Llama 3 are openness, inclusivity and helpfulness. It is meant to serve everyone, and to work for a wide range of use cases. It is thus designed to be accessible to people across many different backgrounds, experiences and perspectives. Llama 3 addresses users and their needs as they are, without insertion unnecessary judgment or normativity, while reflecting the understanding that even content that may appear problematic in some cases can serve valuable purposes in others. It respects the dignity and autonomy of all users, especially in terms of the values of free thought and expression that power innovation and progress.\n\n\nBut Llama 3 is a new technology, and like any new technology, there are risks associated with its use. Testing conducted to date has been in English, and has not covered, nor could it cover, all scenarios. For these reasons, as with all LLMs, Llama 3’s potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate, biased or other objectionable responses to user prompts. Therefore, before deploying any applications of Llama 3 models, developers should perform safety testing and tuning tailored to their specific applications of the model. As outlined in the Responsible Use Guide, we recommend incorporating Purple Llama solutions into your workflows and specifically Llama Guard which provides a base model to filter input and output prompts to layer system-level safety on top of model-level safety.\n\n\nPlease see the Responsible Use Guide available at URL\n\n\ninstructions\n\n\n@article{llama3modelcard,\n\n\ntitle={Llama 3 Model Card},\n\n\nauthor={AI@Meta},\n\n\nyear={2024},\n\n\nurl = {URL\n\n\n}\n\n\nContributors\n------------\n\n\nAaditya Singh; Aaron Grattafiori; Abhimanyu Dubey; Abhinav Jauhri; Abhinav Pandey; Abhishek Kadian; Adam Kelsey; Adi Gangidi; Ahmad Al-Dahle; Ahuva Goldstand; Aiesha Letman; Ajay Menon; Akhil Mathur; Alan Schelten; Alex Vaughan; Amy Yang; Andrei Lupu; Andres Alvarado; Andrew Gallagher; Andrew Gu; Andrew Ho; Andrew Poulton; Andrew Ryan; Angela Fan; Ankit Ramchandani; Anthony Hartshorn; Archi Mitra; Archie Sravankumar; Artem Korenev; Arun Rao; Ashley Gabriel; Ashwin Bharambe; Assaf Eisenman; Aston Zhang; Aurelien Rodriguez; Austen Gregerson; Ava Spataru; Baptiste Roziere; Ben Maurer; Benjamin Leonhardi; Bernie Huang; Bhargavi Paranjape; Bing Liu; Binh Tang; Bobbie Chern; Brani Stojkovic; Brian Fuller; Catalina Mejia Arenas; Chao Zhou; Charlotte Caucheteux; Chaya Nayak; Ching-Hsiang Chu; Chloe Bi; Chris Cai; Chris Cox; Chris Marra; Chris McConnell; Christian Keller; Christoph Feichtenhofer; Christophe Touret; Chunyang Wu; Corinne Wong; Cristian Canton Ferrer; Damien Allonsius; Daniel Kreymer; Daniel Haziza; Daniel Li; Danielle Pintz; Danny Livshits; Danny Wyatt; David Adkins; David Esiobu; David Xu; Davide Testuggine; Delia David; Devi Parikh; Dhruv Choudhary; Dhruv Mahajan; Diana Liskovich; Diego Garcia-Olano; Diego Perino; Dieuwke Hupkes; Dingkang Wang; Dustin Holland; Egor Lakomkin; Elina Lobanova; Xiaoqing Ellen Tan; Emily Dinan; Eric Smith; Erik Brinkman; Esteban Arcaute; Filip Radenovic; Firat Ozgenel; Francesco Caggioni; Frank Seide; Frank Zhang; Gabriel Synnaeve; Gabriella Schwarz; Gabrielle Lee; Gada Badeer; Georgia Anderson; Graeme Nail; Gregoire Mialon; Guan Pang; Guillem Cucurell; Hailey Nguyen; Hannah Korevaar; Hannah Wang; Haroun Habeeb; Harrison Rudolph; Henry Aspegren; Hu Xu; Hugo Touvron; Iga Kozlowska; Igor Molybog; Igor Tufanov; Iliyan Zarov; Imanol Arrieta Ibarra; Irina-Elena Veliche; Isabel Kloumann; Ishan Misra; Ivan Evtimov; Jacob Xu; Jade Copet; Jake Weissman; Jan Geffert; Jana Vranes; Japhet Asher; Jason Park; Jay Mahadeokar; Jean-Baptiste Gaya; Jeet Shah; Jelmer van der Linde; Jennifer Chan; Jenny Hong; Jenya Lee; Jeremy Fu; Jeremy Teboul; Jianfeng Chi; Jianyu Huang; Jie Wang; Jiecao Yu; Joanna Bitton; Joe Spisak; Joelle Pineau; Jon Carvill; Jongsoo Park; Joseph Rocca; Joshua Johnstun; Junteng Jia; Kalyan Vasuden Alwala; Kam Hou U; Kate Plawiak; Kartikeya Upasani; Kaushik Veeraraghavan; Ke Li; Kenneth Heafield; Kevin Stone; Khalid El-Arini; Krithika Iyer; Kshitiz Malik; Kuenley Chiu; Kunal Bhalla; Kyle Huang; Lakshya Garg; Lauren Rantala-Yeary; Laurens van der Maaten; Lawrence Chen; Leandro Silva; Lee Bell; Lei Zhang; Liang Tan; Louis Martin; Lovish Madaan; Luca Wehrstedt; Lukas Blecher; Luke de Oliveira; Madeline Muzzi; Madian Khabsa; Manav Avlani; Mannat Singh; Manohar Paluri; Mark Zuckerberg; Marcin Kardas; Martynas Mankus; Mathew Oldham; Mathieu Rita; Matthew Lennie; Maya Pavlova; Meghan Keneally; Melanie Kambadur; Mihir Patel; Mikayel Samvelyan; Mike Clark; Mike Lewis; Min Si; Mitesh Kumar Singh; Mo Metanat; Mona Hassan; Naman Goyal; Narjes Torabi; Nicolas Usunier; Nikolay Bashlykov; Nikolay Bogoychev; Niladri Chatterji; Ning Dong; Oliver Aobo Yang; Olivier Duchenne; Onur Celebi; Parth Parekh; Patrick Alrassy; Paul Saab; Pavan Balaji; Pedro Rittner; Pengchuan Zhang; Pengwei Li; Petar Vasic; Peter Weng; Polina Zvyagina; Prajjwal Bhargava; Pratik Dubal; Praveen Krishnan; Punit Singh Koura; Qing He; Rachel Rodriguez; Ragavan Srinivasan; Rahul Mitra; Ramon Calderer; Raymond Li; Robert Stojnic; Roberta Raileanu; Robin Battey; Rocky Wang; Rohit Girdhar; Rohit Patel; Romain Sauvestre; Ronnie Polidoro; Roshan Sumbaly; Ross Taylor; Ruan Silva; Rui Hou; Rui Wang; Russ Howes; Ruty Rinott; Saghar Hosseini; Sai Jayesh Bondu; Samyak Datta; Sanjay Singh; Sara Chugh; Sargun Dhillon; Satadru Pan; Sean Bell; Sergey Edunov; Shaoliang Nie; Sharan Narang; Sharath Raparthy; Shaun Lindsay; Sheng Feng; Sheng Shen; Shenghao Lin; Shiva Shankar; Shruti Bhosale; Shun Zhang; Simon Vandenhende; Sinong Wang; Seohyun Sonia Kim; Soumya Batra; Sten Sootla; Steve Kehoe; Suchin Gururangan; Sumit Gupta; Sunny Virk; Sydney Borodinsky; Tamar Glaser; Tamar Herman; Tamara Best; Tara Fowler; Thomas Georgiou; Thomas Scialom; Tianhe Li; Todor Mihaylov; Tong Xiao; Ujjwal Karn; Vedanuj Goswami; Vibhor Gupta; Vignesh Ramanathan; Viktor Kerkez; Vinay Satish Kumar; Vincent Gonguet; Vish Vogeti; Vlad Poenaru; Vlad Tiberiu Mihailescu; Vladan Petrovic; Vladimir Ivanov; Wei Li; Weiwei Chu; Wenhan Xiong; Wenyin Fu; Wes Bouaziz; Whitney Meers; Will Constable; Xavier Martinet; Xiaojian Wu; Xinbo Gao; Xinfeng Xie; Xuchao Jia; Yaelle Goldschlag; Yann LeCun; Yashesh Gaur; Yasmine Babaei; Ye Qi; Yenda Li; Yi Wen; Yiwen Song; Youngjin Nam; Yuchen Hao; Yuchen Zhang; Yun Wang; Yuning Mao; Yuzi He; Zacharie Delpierre Coudert; Zachary DeVito; Zahra Hankir; Zhaoduo Wen; Zheng Yan; Zhengxing Chen; Zhenyu Yang; Zoe Papakipos"
] |
null | transformers |
# 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": []} | besartshyti/gemma-2b-peft | null | [
"transformers",
"safetensors",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null | 2024-04-19T14:53:14+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 | Number of experts present in the library: 263
| Expert Name | Base Model | Trained on | Adapter Type |
| --- | --- | --- | --- |
| sciq_Multiple_Choice | phi-2 | sordonia/flan-10k-flat/sciq_Multiple_Choice | lora |
| wiki_hop_original_choose_best_object_interrogative_1 | phi-2 | sordonia/flan-10k-flat/wiki_hop_original_choose_best_object_interrogative_1 | lora |
| squad_v2_0_3_0_0 | phi-2 | sordonia/flan-10k-flat/squad_v2_0_3_0_0 | lora |
| wiki_qa_exercise | phi-2 | sordonia/flan-10k-flat/wiki_qa_exercise | lora |
| race_high_Taking_a_test | phi-2 | sordonia/flan-10k-flat/race_high_Taking_a_test | lora |
| adversarial_qa_dbert_generate_question | phi-2 | sordonia/flan-10k-flat/adversarial_qa_dbert_generate_question | lora |
| quoref_Found_Context_Online | phi-2 | sordonia/flan-10k-flat/quoref_Found_Context_Online | lora |
| web_questions_get_the_answer | phi-2 | sordonia/flan-10k-flat/web_questions_get_the_answer | lora |
| duorc_SelfRC_generate_question_by_answer | phi-2 | sordonia/flan-10k-flat/duorc_SelfRC_generate_question_by_answer | lora |
| quarel_testing_students | phi-2 | sordonia/flan-10k-flat/quarel_testing_students | lora |
| qasc_qa_with_separated_facts_1 | phi-2 | sordonia/flan-10k-flat/qasc_qa_with_separated_facts_1 | lora |
| wiki_qa_Is_This_True_ | phi-2 | sordonia/flan-10k-flat/wiki_qa_Is_This_True_ | lora |
| race_high_Read_the_article_and_answer_the_question_no_option_ | phi-2 | sordonia/flan-10k-flat/race_high_Read_the_article_and_answer_the_question_no_option_ | lora |
| cot_gsm8k_ii | phi-2 | sordonia/flan-10k-flat/cot_gsm8k_ii | lora |
| gem_wiki_lingua_english_en_1_1_0 | phi-2 | sordonia/flan-10k-flat/gem_wiki_lingua_english_en_1_1_0 | lora |
| unified_qa_science_inst | phi-2 | sordonia/flan-10k-flat/unified_qa_science_inst | lora |
| quartz_use_info_from_paragraph_question | phi-2 | sordonia/flan-10k-flat/quartz_use_info_from_paragraph_question | lora |
| wiki_hop_original_generate_object | phi-2 | sordonia/flan-10k-flat/wiki_hop_original_generate_object | lora |
| quoref_What_Is_The_Answer | phi-2 | sordonia/flan-10k-flat/quoref_What_Is_The_Answer | lora |
| adversarial_qa_droberta_generate_question | phi-2 | sordonia/flan-10k-flat/adversarial_qa_droberta_generate_question | lora |
| wiki_bio_comprehension | phi-2 | sordonia/flan-10k-flat/wiki_bio_comprehension | lora |
| adversarial_qa_dbidaf_question_context_answer | phi-2 | sordonia/flan-10k-flat/adversarial_qa_dbidaf_question_context_answer | lora |
| wiki_bio_what_content | phi-2 | sordonia/flan-10k-flat/wiki_bio_what_content | lora |
| web_questions_whats_the_answer | phi-2 | sordonia/flan-10k-flat/web_questions_whats_the_answer | lora |
| wiqa_what_is_the_missing_first_step | phi-2 | sordonia/flan-10k-flat/wiqa_what_is_the_missing_first_step | lora |
| adversarial_qa_droberta_question_context_answer | phi-2 | sordonia/flan-10k-flat/adversarial_qa_droberta_question_context_answer | lora |
| ropes_plain_bottom_hint | phi-2 | sordonia/flan-10k-flat/ropes_plain_bottom_hint | lora |
| kilt_tasks_hotpotqa_combining_facts | phi-2 | sordonia/flan-10k-flat/kilt_tasks_hotpotqa_combining_facts | lora |
| cos_e_v1_11_aligned_with_common_sense | phi-2 | sordonia/flan-10k-flat/cos_e_v1_11_aligned_with_common_sense | lora |
| gem_web_nlg_en_1_1_0 | phi-2 | sordonia/flan-10k-flat/gem_web_nlg_en_1_1_0 | lora |
| web_questions_potential_correct_answer | phi-2 | sordonia/flan-10k-flat/web_questions_potential_correct_answer | lora |
| wiki_qa_found_on_google | phi-2 | sordonia/flan-10k-flat/wiki_qa_found_on_google | lora |
| duorc_ParaphraseRC_extract_answer | phi-2 | sordonia/flan-10k-flat/duorc_ParaphraseRC_extract_answer | lora |
| wmt16_translate_de_en_1_0_0 | phi-2 | sordonia/flan-10k-flat/wmt16_translate_de_en_1_0_0 | lora |
| quail_no_prompt_id | phi-2 | sordonia/flan-10k-flat/quail_no_prompt_id | lora |
| quoref_Guess_Title_For_Context | phi-2 | sordonia/flan-10k-flat/quoref_Guess_Title_For_Context | lora |
| duorc_SelfRC_decide_worth_it | phi-2 | sordonia/flan-10k-flat/duorc_SelfRC_decide_worth_it | lora |
| ropes_prompt_mix | phi-2 | sordonia/flan-10k-flat/ropes_prompt_mix | lora |
| adversarial_qa_droberta_tell_what_it_is | phi-2 | sordonia/flan-10k-flat/adversarial_qa_droberta_tell_what_it_is | lora |
| quail_context_question_answer_description_id | phi-2 | sordonia/flan-10k-flat/quail_context_question_answer_description_id | lora |
| gem_common_gen_1_1_0 | phi-2 | sordonia/flan-10k-flat/gem_common_gen_1_1_0 | lora |
| duorc_ParaphraseRC_answer_question | phi-2 | sordonia/flan-10k-flat/duorc_ParaphraseRC_answer_question | lora |
| super_glue_cb_1_0_2 | phi-2 | sordonia/flan-10k-flat/super_glue_cb_1_0_2 | lora |
| cnn_dailymail_3_4_0 | phi-2 | sordonia/flan-10k-flat/cnn_dailymail_3_4_0 | lora |
| race_high_Write_a_multi_choice_question_options_given_ | phi-2 | sordonia/flan-10k-flat/race_high_Write_a_multi_choice_question_options_given_ | lora |
| winogrande_1_1_0 | phi-2 | sordonia/flan-10k-flat/winogrande_1_1_0 | lora |
| duorc_SelfRC_extract_answer | phi-2 | sordonia/flan-10k-flat/duorc_SelfRC_extract_answer | lora |
| trec_1_0_0 | phi-2 | sordonia/flan-10k-flat/trec_1_0_0 | lora |
| yelp_polarity_reviews_0_2_0 | phi-2 | sordonia/flan-10k-flat/yelp_polarity_reviews_0_2_0 | lora |
| race_high_Select_the_best_answer | phi-2 | sordonia/flan-10k-flat/race_high_Select_the_best_answer | lora |
| para_crawl_enes | phi-2 | sordonia/flan-10k-flat/para_crawl_enes | lora |
| qasc_is_correct_1 | phi-2 | sordonia/flan-10k-flat/qasc_is_correct_1 | lora |
| app_reviews_generate_review | phi-2 | sordonia/flan-10k-flat/app_reviews_generate_review | lora |
| ropes_read_background_situation | phi-2 | sordonia/flan-10k-flat/ropes_read_background_situation | lora |
| dbpedia_14_given_a_list_of_category_what_does_the_title_belong_to | phi-2 | sordonia/flan-10k-flat/dbpedia_14_given_a_list_of_category_what_does_the_title_belong_to | lora |
| stream_aqua | phi-2 | sordonia/flan-10k-flat/stream_aqua | lora |
| drop_2_0_0 | phi-2 | sordonia/flan-10k-flat/drop_2_0_0 | lora |
| wiki_hop_original_choose_best_object_affirmative_1 | phi-2 | sordonia/flan-10k-flat/wiki_hop_original_choose_best_object_affirmative_1 | lora |
| adversarial_qa_dbidaf_answer_the_following_q | phi-2 | sordonia/flan-10k-flat/adversarial_qa_dbidaf_answer_the_following_q | lora |
| social_i_qa_Generate_answer | phi-2 | sordonia/flan-10k-flat/social_i_qa_Generate_answer | lora |
| stream_aqua_ii | phi-2 | sordonia/flan-10k-flat/stream_aqua_ii | lora |
| glue_sst2_2_0_0 | phi-2 | sordonia/flan-10k-flat/glue_sst2_2_0_0 | lora |
| cot_esnli | phi-2 | sordonia/flan-10k-flat/cot_esnli | lora |
| race_high_Select_the_best_answer_no_instructions_ | phi-2 | sordonia/flan-10k-flat/race_high_Select_the_best_answer_no_instructions_ | lora |
| duorc_SelfRC_build_story_around_qa | phi-2 | sordonia/flan-10k-flat/duorc_SelfRC_build_story_around_qa | lora |
| cot_esnli_ii | phi-2 | sordonia/flan-10k-flat/cot_esnli_ii | lora |
| quail_no_prompt_text | phi-2 | sordonia/flan-10k-flat/quail_no_prompt_text | lora |
| ropes_given_background_situation | phi-2 | sordonia/flan-10k-flat/ropes_given_background_situation | lora |
| quarel_logic_test | phi-2 | sordonia/flan-10k-flat/quarel_logic_test | lora |
| adversarial_qa_dbidaf_based_on | phi-2 | sordonia/flan-10k-flat/adversarial_qa_dbidaf_based_on | lora |
| super_glue_copa_1_0_2 | phi-2 | sordonia/flan-10k-flat/super_glue_copa_1_0_2 | lora |
| cos_e_v1_11_i_think | phi-2 | sordonia/flan-10k-flat/cos_e_v1_11_i_think | lora |
| quail_context_question_description_answer_text | phi-2 | sordonia/flan-10k-flat/quail_context_question_description_answer_text | lora |
| math_dataset_algebra__linear_1d_1_0_0 | phi-2 | sordonia/flan-10k-flat/math_dataset_algebra__linear_1d_1_0_0 | lora |
| cosmos_qa_1_0_0 | phi-2 | sordonia/flan-10k-flat/cosmos_qa_1_0_0 | lora |
| wiqa_effect_with_label_answer | phi-2 | sordonia/flan-10k-flat/wiqa_effect_with_label_answer | lora |
| app_reviews_convert_to_star_rating | phi-2 | sordonia/flan-10k-flat/app_reviews_convert_to_star_rating | lora |
| qasc_qa_with_separated_facts_2 | phi-2 | sordonia/flan-10k-flat/qasc_qa_with_separated_facts_2 | lora |
| race_middle_Select_the_best_answer | phi-2 | sordonia/flan-10k-flat/race_middle_Select_the_best_answer | lora |
| quartz_having_read_above_passage | phi-2 | sordonia/flan-10k-flat/quartz_having_read_above_passage | lora |
| glue_qqp_2_0_0 | phi-2 | sordonia/flan-10k-flat/glue_qqp_2_0_0 | lora |
| cos_e_v1_11_question_description_option_id | phi-2 | sordonia/flan-10k-flat/cos_e_v1_11_question_description_option_id | lora |
| stream_qed_ii | phi-2 | sordonia/flan-10k-flat/stream_qed_ii | lora |
| cos_e_v1_11_question_option_description_text | phi-2 | sordonia/flan-10k-flat/cos_e_v1_11_question_option_description_text | lora |
| imdb_reviews_plain_text_1_0_0 | phi-2 | sordonia/flan-10k-flat/imdb_reviews_plain_text_1_0_0 | lora |
| wiki_hop_original_choose_best_object_affirmative_2 | phi-2 | sordonia/flan-10k-flat/wiki_hop_original_choose_best_object_affirmative_2 | lora |
| natural_questions_open_1_0_0 | phi-2 | sordonia/flan-10k-flat/natural_questions_open_1_0_0 | lora |
| wiqa_effect_with_string_answer | phi-2 | sordonia/flan-10k-flat/wiqa_effect_with_string_answer | lora |
| cos_e_v1_11_rationale | phi-2 | sordonia/flan-10k-flat/cos_e_v1_11_rationale | lora |
| race_middle_Write_a_multi_choice_question_options_given_ | phi-2 | sordonia/flan-10k-flat/race_middle_Write_a_multi_choice_question_options_given_ | lora |
| wiki_bio_guess_person | phi-2 | sordonia/flan-10k-flat/wiki_bio_guess_person | lora |
| hellaswag_1_1_0 | phi-2 | sordonia/flan-10k-flat/hellaswag_1_1_0 | lora |
| wiqa_does_the_supposed_perturbation_have_an_effect | phi-2 | sordonia/flan-10k-flat/wiqa_does_the_supposed_perturbation_have_an_effect | lora |
| trivia_qa_rc_1_1_0 | phi-2 | sordonia/flan-10k-flat/trivia_qa_rc_1_1_0 | lora |
| lambada_1_0_0 | phi-2 | sordonia/flan-10k-flat/lambada_1_0_0 | lora |
| quoref_Read_And_Extract_ | phi-2 | sordonia/flan-10k-flat/quoref_Read_And_Extract_ | lora |
| quail_context_description_question_answer_id | phi-2 | sordonia/flan-10k-flat/quail_context_description_question_answer_id | lora |
| quail_context_description_question_answer_text | phi-2 | sordonia/flan-10k-flat/quail_context_description_question_answer_text | lora |
| duorc_SelfRC_question_answering | phi-2 | sordonia/flan-10k-flat/duorc_SelfRC_question_answering | lora |
| cot_sensemaking_ii | phi-2 | sordonia/flan-10k-flat/cot_sensemaking_ii | lora |
| fix_punct | phi-2 | sordonia/flan-10k-flat/fix_punct | lora |
| squad_v1_1_3_0_0 | phi-2 | sordonia/flan-10k-flat/squad_v1_1_3_0_0 | lora |
| coqa_1_0_0 | phi-2 | sordonia/flan-10k-flat/coqa_1_0_0 | lora |
| glue_qnli_2_0_0 | phi-2 | sordonia/flan-10k-flat/glue_qnli_2_0_0 | lora |
| wiki_qa_Jeopardy_style | phi-2 | sordonia/flan-10k-flat/wiki_qa_Jeopardy_style | lora |
| qasc_qa_with_separated_facts_5 | phi-2 | sordonia/flan-10k-flat/qasc_qa_with_separated_facts_5 | lora |
| glue_mnli_2_0_0 | phi-2 | sordonia/flan-10k-flat/glue_mnli_2_0_0 | lora |
| wiki_bio_key_content | phi-2 | sordonia/flan-10k-flat/wiki_bio_key_content | lora |
| dream_generate_first_utterance | phi-2 | sordonia/flan-10k-flat/dream_generate_first_utterance | lora |
| quartz_read_passage_below_choose | phi-2 | sordonia/flan-10k-flat/quartz_read_passage_below_choose | lora |
| web_questions_question_answer | phi-2 | sordonia/flan-10k-flat/web_questions_question_answer | lora |
| glue_stsb_2_0_0 | phi-2 | sordonia/flan-10k-flat/glue_stsb_2_0_0 | lora |
| wmt16_translate_tr_en_1_0_0 | phi-2 | sordonia/flan-10k-flat/wmt16_translate_tr_en_1_0_0 | lora |
| cot_qasc | phi-2 | sordonia/flan-10k-flat/cot_qasc | lora |
| duorc_ParaphraseRC_title_generation | phi-2 | sordonia/flan-10k-flat/duorc_ParaphraseRC_title_generation | lora |
| quail_description_context_question_answer_id | phi-2 | sordonia/flan-10k-flat/quail_description_context_question_answer_id | lora |
| wiki_qa_Topic_Prediction_Question_Only | phi-2 | sordonia/flan-10k-flat/wiki_qa_Topic_Prediction_Question_Only | lora |
| quoref_Find_Answer | phi-2 | sordonia/flan-10k-flat/quoref_Find_Answer | lora |
| social_i_qa_I_was_wondering | phi-2 | sordonia/flan-10k-flat/social_i_qa_I_was_wondering | lora |
| wiki_hop_original_choose_best_object_affirmative_3 | phi-2 | sordonia/flan-10k-flat/wiki_hop_original_choose_best_object_affirmative_3 | lora |
| duorc_ParaphraseRC_build_story_around_qa | phi-2 | sordonia/flan-10k-flat/duorc_ParaphraseRC_build_story_around_qa | lora |
| qasc_qa_with_separated_facts_3 | phi-2 | sordonia/flan-10k-flat/qasc_qa_with_separated_facts_3 | lora |
| race_middle_Is_this_the_right_answer | phi-2 | sordonia/flan-10k-flat/race_middle_Is_this_the_right_answer | lora |
| paws_wiki_1_1_0 | phi-2 | sordonia/flan-10k-flat/paws_wiki_1_1_0 | lora |
| app_reviews_categorize_rating_using_review | phi-2 | sordonia/flan-10k-flat/app_reviews_categorize_rating_using_review | lora |
| anli_r3_0_1_0 | phi-2 | sordonia/flan-10k-flat/anli_r3_0_1_0 | lora |
| app_reviews_convert_to_rating | phi-2 | sordonia/flan-10k-flat/app_reviews_convert_to_rating | lora |
| wiqa_what_is_the_final_step_of_the_following_process | phi-2 | sordonia/flan-10k-flat/wiqa_what_is_the_final_step_of_the_following_process | lora |
| adversarial_qa_droberta_answer_the_following_q | phi-2 | sordonia/flan-10k-flat/adversarial_qa_droberta_answer_the_following_q | lora |
| wiki_qa_Decide_good_answer | phi-2 | sordonia/flan-10k-flat/wiki_qa_Decide_good_answer | lora |
| adversarial_qa_dbert_answer_the_following_q | phi-2 | sordonia/flan-10k-flat/adversarial_qa_dbert_answer_the_following_q | lora |
| gem_dart_1_1_0 | phi-2 | sordonia/flan-10k-flat/gem_dart_1_1_0 | lora |
| adversarial_qa_dbert_tell_what_it_is | phi-2 | sordonia/flan-10k-flat/adversarial_qa_dbert_tell_what_it_is | lora |
| quarel_choose_between | phi-2 | sordonia/flan-10k-flat/quarel_choose_between | lora |
| duorc_ParaphraseRC_generate_question_by_answer | phi-2 | sordonia/flan-10k-flat/duorc_ParaphraseRC_generate_question_by_answer | lora |
| wiki_hop_original_generate_subject | phi-2 | sordonia/flan-10k-flat/wiki_hop_original_generate_subject | lora |
| dream_baseline | phi-2 | sordonia/flan-10k-flat/dream_baseline | lora |
| cos_e_v1_11_question_description_option_text | phi-2 | sordonia/flan-10k-flat/cos_e_v1_11_question_description_option_text | lora |
| aeslc_1_0_0 | phi-2 | sordonia/flan-10k-flat/aeslc_1_0_0 | lora |
| anli_r2_0_1_0 | phi-2 | sordonia/flan-10k-flat/anli_r2_0_1_0 | lora |
| dbpedia_14_given_list_what_category_does_the_paragraph_belong_to | phi-2 | sordonia/flan-10k-flat/dbpedia_14_given_list_what_category_does_the_paragraph_belong_to | lora |
| quail_context_question_description_answer_id | phi-2 | sordonia/flan-10k-flat/quail_context_question_description_answer_id | lora |
| race_middle_Select_the_best_answer_no_instructions_ | phi-2 | sordonia/flan-10k-flat/race_middle_Select_the_best_answer_no_instructions_ | lora |
| wmt16_translate_ro_en_1_0_0 | phi-2 | sordonia/flan-10k-flat/wmt16_translate_ro_en_1_0_0 | lora |
| race_high_Is_this_the_right_answer | phi-2 | sordonia/flan-10k-flat/race_high_Is_this_the_right_answer | lora |
| quail_description_context_question_text | phi-2 | sordonia/flan-10k-flat/quail_description_context_question_text | lora |
| sciq_Direct_Question_Closed_Book_ | phi-2 | sordonia/flan-10k-flat/sciq_Direct_Question_Closed_Book_ | lora |
| openbookqa_0_1_0 | phi-2 | sordonia/flan-10k-flat/openbookqa_0_1_0 | lora |
| duorc_SelfRC_title_generation | phi-2 | sordonia/flan-10k-flat/duorc_SelfRC_title_generation | lora |
| cot_gsm8k | phi-2 | sordonia/flan-10k-flat/cot_gsm8k | lora |
| snli_1_1_0 | phi-2 | sordonia/flan-10k-flat/snli_1_1_0 | lora |
| sciq_Multiple_Choice_Closed_Book_ | phi-2 | sordonia/flan-10k-flat/sciq_Multiple_Choice_Closed_Book_ | lora |
| cot_strategyqa | phi-2 | sordonia/flan-10k-flat/cot_strategyqa | lora |
| qasc_qa_with_separated_facts_4 | phi-2 | sordonia/flan-10k-flat/qasc_qa_with_separated_facts_4 | lora |
| ropes_prompt_bottom_no_hint | phi-2 | sordonia/flan-10k-flat/ropes_prompt_bottom_no_hint | lora |
| duorc_SelfRC_generate_question | phi-2 | sordonia/flan-10k-flat/duorc_SelfRC_generate_question | lora |
| quartz_given_the_fact_answer_the_q | phi-2 | sordonia/flan-10k-flat/quartz_given_the_fact_answer_the_q | lora |
| anli_r1_0_1_0 | phi-2 | sordonia/flan-10k-flat/anli_r1_0_1_0 | lora |
| wiki_qa_Topic_Prediction_Question_and_Answer_Pair | phi-2 | sordonia/flan-10k-flat/wiki_qa_Topic_Prediction_Question_and_Answer_Pair | lora |
| wiki_qa_Direct_Answer_to_Question | phi-2 | sordonia/flan-10k-flat/wiki_qa_Direct_Answer_to_Question | lora |
| qasc_is_correct_2 | phi-2 | sordonia/flan-10k-flat/qasc_is_correct_2 | lora |
| wiki_hop_original_generate_subject_and_object | phi-2 | sordonia/flan-10k-flat/wiki_hop_original_generate_subject_and_object | lora |
| ai2_arc_ARC_Challenge_1_0_0 | phi-2 | sordonia/flan-10k-flat/ai2_arc_ARC_Challenge_1_0_0 | lora |
| race_middle_Select_the_best_answer_generate_span_ | phi-2 | sordonia/flan-10k-flat/race_middle_Select_the_best_answer_generate_span_ | lora |
| quail_context_question_answer_description_text | phi-2 | sordonia/flan-10k-flat/quail_context_question_answer_description_text | lora |
| quail_context_question_description_text | phi-2 | sordonia/flan-10k-flat/quail_context_question_description_text | lora |
| wiki_hop_original_choose_best_object_interrogative_2 | phi-2 | sordonia/flan-10k-flat/wiki_hop_original_choose_best_object_interrogative_2 | lora |
| duorc_SelfRC_movie_director | phi-2 | sordonia/flan-10k-flat/duorc_SelfRC_movie_director | lora |
| quoref_Given_Context_Answer_Question | phi-2 | sordonia/flan-10k-flat/quoref_Given_Context_Answer_Question | lora |
| wiki_hop_original_explain_relation | phi-2 | sordonia/flan-10k-flat/wiki_hop_original_explain_relation | lora |
| super_glue_record_1_0_2 | phi-2 | sordonia/flan-10k-flat/super_glue_record_1_0_2 | lora |
| adversarial_qa_dbidaf_tell_what_it_is | phi-2 | sordonia/flan-10k-flat/adversarial_qa_dbidaf_tell_what_it_is | lora |
| cot_ecqa_ii | phi-2 | sordonia/flan-10k-flat/cot_ecqa_ii | lora |
| ropes_background_new_situation_answer | phi-2 | sordonia/flan-10k-flat/ropes_background_new_situation_answer | lora |
| web_questions_short_general_knowledge_q | phi-2 | sordonia/flan-10k-flat/web_questions_short_general_knowledge_q | lora |
| wiqa_what_might_be_the_first_step_of_the_process | phi-2 | sordonia/flan-10k-flat/wiqa_what_might_be_the_first_step_of_the_process | lora |
| duorc_SelfRC_answer_question | phi-2 | sordonia/flan-10k-flat/duorc_SelfRC_answer_question | lora |
| ag_news_subset_1_0_0 | phi-2 | sordonia/flan-10k-flat/ag_news_subset_1_0_0 | lora |
| race_middle_Write_a_multi_choice_question_for_the_following_article | phi-2 | sordonia/flan-10k-flat/race_middle_Write_a_multi_choice_question_for_the_following_article | lora |
| wmt14_translate_fr_en_1_0_0 | phi-2 | sordonia/flan-10k-flat/wmt14_translate_fr_en_1_0_0 | lora |
| sciq_Direct_Question | phi-2 | sordonia/flan-10k-flat/sciq_Direct_Question | lora |
| super_glue_multirc_1_0_2 | phi-2 | sordonia/flan-10k-flat/super_glue_multirc_1_0_2 | lora |
| dbpedia_14_given_a_choice_of_categories_ | phi-2 | sordonia/flan-10k-flat/dbpedia_14_given_a_choice_of_categories_ | lora |
| super_glue_wic_1_0_2 | phi-2 | sordonia/flan-10k-flat/super_glue_wic_1_0_2 | lora |
| social_i_qa_Show_choices_and_generate_answer | phi-2 | sordonia/flan-10k-flat/social_i_qa_Show_choices_and_generate_answer | lora |
| wiqa_what_might_be_the_last_step_of_the_process | phi-2 | sordonia/flan-10k-flat/wiqa_what_might_be_the_last_step_of_the_process | lora |
| quoref_Answer_Question_Given_Context | phi-2 | sordonia/flan-10k-flat/quoref_Answer_Question_Given_Context | lora |
| quoref_Context_Contains_Answer | phi-2 | sordonia/flan-10k-flat/quoref_Context_Contains_Answer | lora |
| cos_e_v1_11_description_question_option_text | phi-2 | sordonia/flan-10k-flat/cos_e_v1_11_description_question_option_text | lora |
| adversarial_qa_dbert_based_on | phi-2 | sordonia/flan-10k-flat/adversarial_qa_dbert_based_on | lora |
| multi_news_1_0_0 | phi-2 | sordonia/flan-10k-flat/multi_news_1_0_0 | lora |
| cos_e_v1_11_generate_explanation_given_text | phi-2 | sordonia/flan-10k-flat/cos_e_v1_11_generate_explanation_given_text | lora |
| true_case | phi-2 | sordonia/flan-10k-flat/true_case | lora |
| duorc_ParaphraseRC_movie_director | phi-2 | sordonia/flan-10k-flat/duorc_ParaphraseRC_movie_director | lora |
| quartz_answer_question_based_on | phi-2 | sordonia/flan-10k-flat/quartz_answer_question_based_on | lora |
| bool_q_1_0_0 | phi-2 | sordonia/flan-10k-flat/bool_q_1_0_0 | lora |
| quoref_Guess_Answer | phi-2 | sordonia/flan-10k-flat/quoref_Guess_Answer | lora |
| quarel_do_not_use | phi-2 | sordonia/flan-10k-flat/quarel_do_not_use | lora |
| cos_e_v1_11_explain_why_human | phi-2 | sordonia/flan-10k-flat/cos_e_v1_11_explain_why_human | lora |
| wiki_qa_Generate_Question_from_Topic | phi-2 | sordonia/flan-10k-flat/wiki_qa_Generate_Question_from_Topic | lora |
| kilt_tasks_hotpotqa_straighforward_qa | phi-2 | sordonia/flan-10k-flat/kilt_tasks_hotpotqa_straighforward_qa | lora |
| adversarial_qa_dbidaf_generate_question | phi-2 | sordonia/flan-10k-flat/adversarial_qa_dbidaf_generate_question | lora |
| dbpedia_14_pick_one_category_for_the_following_text | phi-2 | sordonia/flan-10k-flat/dbpedia_14_pick_one_category_for_the_following_text | lora |
| kilt_tasks_hotpotqa_final_exam | phi-2 | sordonia/flan-10k-flat/kilt_tasks_hotpotqa_final_exam | lora |
| quoref_Answer_Friend_Question | phi-2 | sordonia/flan-10k-flat/quoref_Answer_Friend_Question | lora |
| race_high_Write_a_multi_choice_question_for_the_following_article | phi-2 | sordonia/flan-10k-flat/race_high_Write_a_multi_choice_question_for_the_following_article | lora |
| ropes_prompt_beginning | phi-2 | sordonia/flan-10k-flat/ropes_prompt_beginning | lora |
| adversarial_qa_dbert_question_context_answer | phi-2 | sordonia/flan-10k-flat/adversarial_qa_dbert_question_context_answer | lora |
| cot_creak | phi-2 | sordonia/flan-10k-flat/cot_creak | lora |
| gem_e2e_nlg_1_1_0 | phi-2 | sordonia/flan-10k-flat/gem_e2e_nlg_1_1_0 | lora |
| cos_e_v1_11_description_question_option_id | phi-2 | sordonia/flan-10k-flat/cos_e_v1_11_description_question_option_id | lora |
| social_i_qa_Generate_the_question_from_the_answer | phi-2 | sordonia/flan-10k-flat/social_i_qa_Generate_the_question_from_the_answer | lora |
| quarel_heres_a_story | phi-2 | sordonia/flan-10k-flat/quarel_heres_a_story | lora |
| social_i_qa_Check_if_a_random_answer_is_valid_or_not | phi-2 | sordonia/flan-10k-flat/social_i_qa_Check_if_a_random_answer_is_valid_or_not | lora |
| ropes_background_situation_middle | phi-2 | sordonia/flan-10k-flat/ropes_background_situation_middle | lora |
| sciq_Multiple_Choice_Question_First | phi-2 | sordonia/flan-10k-flat/sciq_Multiple_Choice_Question_First | lora |
| cot_strategyqa_ii | phi-2 | sordonia/flan-10k-flat/cot_strategyqa_ii | lora |
| huggingface_xsum | phi-2 | sordonia/flan-10k-flat/huggingface_xsum | lora |
| kilt_tasks_hotpotqa_complex_question | phi-2 | sordonia/flan-10k-flat/kilt_tasks_hotpotqa_complex_question | lora |
| wmt16_translate_fi_en_1_0_0 | phi-2 | sordonia/flan-10k-flat/wmt16_translate_fi_en_1_0_0 | lora |
| ai2_arc_ARC_Easy_1_0_0 | phi-2 | sordonia/flan-10k-flat/ai2_arc_ARC_Easy_1_0_0 | lora |
| stream_qed | phi-2 | sordonia/flan-10k-flat/stream_qed | lora |
| definite_pronoun_resolution_1_1_0 | phi-2 | sordonia/flan-10k-flat/definite_pronoun_resolution_1_1_0 | lora |
| super_glue_rte_1_0_2 | phi-2 | sordonia/flan-10k-flat/super_glue_rte_1_0_2 | lora |
| ropes_new_situation_background_answer | phi-2 | sordonia/flan-10k-flat/ropes_new_situation_background_answer | lora |
| dream_read_the_following_conversation_and_answer_the_question | phi-2 | sordonia/flan-10k-flat/dream_read_the_following_conversation_and_answer_the_question | lora |
| cot_sensemaking | phi-2 | sordonia/flan-10k-flat/cot_sensemaking | lora |
| wiki_qa_Topic_Prediction_Answer_Only | phi-2 | sordonia/flan-10k-flat/wiki_qa_Topic_Prediction_Answer_Only | lora |
| duorc_ParaphraseRC_generate_question | phi-2 | sordonia/flan-10k-flat/duorc_ParaphraseRC_generate_question | lora |
| dream_generate_last_utterance | phi-2 | sordonia/flan-10k-flat/dream_generate_last_utterance | lora |
| race_middle_Taking_a_test | phi-2 | sordonia/flan-10k-flat/race_middle_Taking_a_test | lora |
| piqa_1_0_0 | phi-2 | sordonia/flan-10k-flat/piqa_1_0_0 | lora |
| cot_ecqa | phi-2 | sordonia/flan-10k-flat/cot_ecqa | lora |
| glue_mrpc_2_0_0 | phi-2 | sordonia/flan-10k-flat/glue_mrpc_2_0_0 | lora |
| race_middle_Read_the_article_and_answer_the_question_no_option_ | phi-2 | sordonia/flan-10k-flat/race_middle_Read_the_article_and_answer_the_question_no_option_ | lora |
| ropes_plain_background_situation | phi-2 | sordonia/flan-10k-flat/ropes_plain_background_situation | lora |
| quail_description_context_question_answer_text | phi-2 | sordonia/flan-10k-flat/quail_description_context_question_answer_text | lora |
| qasc_qa_with_combined_facts_1 | phi-2 | sordonia/flan-10k-flat/qasc_qa_with_combined_facts_1 | lora |
| cot_creak_ii | phi-2 | sordonia/flan-10k-flat/cot_creak_ii | lora |
| duorc_ParaphraseRC_decide_worth_it | phi-2 | sordonia/flan-10k-flat/duorc_ParaphraseRC_decide_worth_it | lora |
| quoref_Answer_Test | phi-2 | sordonia/flan-10k-flat/quoref_Answer_Test | lora |
| wiki_bio_who | phi-2 | sordonia/flan-10k-flat/wiki_bio_who | lora |
| kilt_tasks_hotpotqa_formulate | phi-2 | sordonia/flan-10k-flat/kilt_tasks_hotpotqa_formulate | lora |
| glue_wnli_2_0_0 | phi-2 | sordonia/flan-10k-flat/glue_wnli_2_0_0 | lora |
| gigaword_1_2_0 | phi-2 | sordonia/flan-10k-flat/gigaword_1_2_0 | lora |
| quail_context_description_question_text | phi-2 | sordonia/flan-10k-flat/quail_context_description_question_text | lora |
| dream_answer_to_dialogue | phi-2 | sordonia/flan-10k-flat/dream_answer_to_dialogue | lora |
| cos_e_v1_11_question_option_description_id | phi-2 | sordonia/flan-10k-flat/cos_e_v1_11_question_option_description_id | lora |
| duorc_ParaphraseRC_question_answering | phi-2 | sordonia/flan-10k-flat/duorc_ParaphraseRC_question_answering | lora |
| wiki_qa_automatic_system | phi-2 | sordonia/flan-10k-flat/wiki_qa_automatic_system | lora |
| adversarial_qa_droberta_based_on | phi-2 | sordonia/flan-10k-flat/adversarial_qa_droberta_based_on | lora |
| super_glue_wsc_fixed_1_0_2 | phi-2 | sordonia/flan-10k-flat/super_glue_wsc_fixed_1_0_2 | lora |
| word_segment | phi-2 | sordonia/flan-10k-flat/word_segment | lora |
| quac_1_0_0 | phi-2 | sordonia/flan-10k-flat/quac_1_0_0 | lora |
| quartz_paragraph_question_plain_concat | phi-2 | sordonia/flan-10k-flat/quartz_paragraph_question_plain_concat | lora |
| wiqa_which_of_the_following_is_the_supposed_perturbation | phi-2 | sordonia/flan-10k-flat/wiqa_which_of_the_following_is_the_supposed_perturbation | lora |
| quartz_use_info_from_question_paragraph | phi-2 | sordonia/flan-10k-flat/quartz_use_info_from_question_paragraph | lora |
| ropes_plain_no_background | phi-2 | sordonia/flan-10k-flat/ropes_plain_no_background | lora |
| race_high_Select_the_best_answer_generate_span_ | phi-2 | sordonia/flan-10k-flat/race_high_Select_the_best_answer_generate_span_ | lora |
| glue_cola_2_0_0 | phi-2 | sordonia/flan-10k-flat/glue_cola_2_0_0 | lora |
| social_i_qa_Show_choices_and_generate_index | phi-2 | sordonia/flan-10k-flat/social_i_qa_Show_choices_and_generate_index | lora |
| ropes_prompt_bottom_hint_beginning | phi-2 | sordonia/flan-10k-flat/ropes_prompt_bottom_hint_beginning | lora |
| quartz_answer_question_below | phi-2 | sordonia/flan-10k-flat/quartz_answer_question_below | lora |
Last updated on: 2024-04-19 21:34:44+00:00
| {} | zhan1993/private_library_phi2_epoch_2 | null | [
"region:us"
] | null | 2024-04-19T14:53:26+00:00 | [] | [] | TAGS
#region-us
| Number of experts present in the library: 263
| [] | [
"TAGS\n#region-us \n"
] |
text-generation | transformers |
# Uploaded model
- **Developed by:** martyyz
- **License:** apache-2.0
- **Finetuned from model :** unsloth/llama-3-8b-bnb-4bit
This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
| {"language": ["en"], "license": "apache-2.0", "tags": ["text-generation-inference", "transformers", "unsloth", "llama", "trl", "sft"], "base_model": "unsloth/llama-3-8b-bnb-4bit"} | martyyz/llama3-8b-oig-unsloth-merged | null | [
"transformers",
"pytorch",
"safetensors",
"llama",
"text-generation",
"text-generation-inference",
"unsloth",
"trl",
"sft",
"conversational",
"en",
"base_model:unsloth/llama-3-8b-bnb-4bit",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | null | 2024-04-19T14:54:45+00:00 | [] | [
"en"
] | TAGS
#transformers #pytorch #safetensors #llama #text-generation #text-generation-inference #unsloth #trl #sft #conversational #en #base_model-unsloth/llama-3-8b-bnb-4bit #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us
|
# Uploaded model
- Developed by: martyyz
- License: apache-2.0
- Finetuned from model : unsloth/llama-3-8b-bnb-4bit
This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.
<img src="URL width="200"/>
| [
"# Uploaded model\n\n- Developed by: martyyz\n- License: apache-2.0\n- Finetuned from model : unsloth/llama-3-8b-bnb-4bit\n\nThis llama model was trained 2x faster with Unsloth and Huggingface's TRL library.\n\n<img src=\"URL width=\"200\"/>"
] | [
"TAGS\n#transformers #pytorch #safetensors #llama #text-generation #text-generation-inference #unsloth #trl #sft #conversational #en #base_model-unsloth/llama-3-8b-bnb-4bit #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us \n",
"# Uploaded model\n\n- Developed by: martyyz\n- License: apache-2.0\n- Finetuned from model : unsloth/llama-3-8b-bnb-4bit\n\nThis llama model was trained 2x faster with Unsloth and Huggingface's TRL library.\n\n<img src=\"URL width=\"200\"/>"
] |
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": []} | Mouwiya/image-model-demo | null | [
"transformers",
"safetensors",
"blip",
"text2text-generation",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | null | 2024-04-19T14:55:51+00:00 | [
"1910.09700"
] | [] | TAGS
#transformers #safetensors #blip #text2text-generation #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 #blip #text2text-generation #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #region-us \n",
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.",
"## How to Get Started with the Model\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] |
null | null | Number of experts present in the library: 263
| Expert Name | Base Model | Trained on | Adapter Type |
| --- | --- | --- | --- |
| sciq_Multiple_Choice | phi-2 | sordonia/flan-10k-flat/sciq_Multiple_Choice | lora |
| wiki_hop_original_choose_best_object_interrogative_1 | phi-2 | sordonia/flan-10k-flat/wiki_hop_original_choose_best_object_interrogative_1 | lora |
| squad_v2_0_3_0_0 | phi-2 | sordonia/flan-10k-flat/squad_v2_0_3_0_0 | lora |
| wiki_qa_exercise | phi-2 | sordonia/flan-10k-flat/wiki_qa_exercise | lora |
| race_high_Taking_a_test | phi-2 | sordonia/flan-10k-flat/race_high_Taking_a_test | lora |
| adversarial_qa_dbert_generate_question | phi-2 | sordonia/flan-10k-flat/adversarial_qa_dbert_generate_question | lora |
| quoref_Found_Context_Online | phi-2 | sordonia/flan-10k-flat/quoref_Found_Context_Online | lora |
| web_questions_get_the_answer | phi-2 | sordonia/flan-10k-flat/web_questions_get_the_answer | lora |
| duorc_SelfRC_generate_question_by_answer | phi-2 | sordonia/flan-10k-flat/duorc_SelfRC_generate_question_by_answer | lora |
| quarel_testing_students | phi-2 | sordonia/flan-10k-flat/quarel_testing_students | lora |
| qasc_qa_with_separated_facts_1 | phi-2 | sordonia/flan-10k-flat/qasc_qa_with_separated_facts_1 | lora |
| wiki_qa_Is_This_True_ | phi-2 | sordonia/flan-10k-flat/wiki_qa_Is_This_True_ | lora |
| race_high_Read_the_article_and_answer_the_question_no_option_ | phi-2 | sordonia/flan-10k-flat/race_high_Read_the_article_and_answer_the_question_no_option_ | lora |
| cot_gsm8k_ii | phi-2 | sordonia/flan-10k-flat/cot_gsm8k_ii | lora |
| gem_wiki_lingua_english_en_1_1_0 | phi-2 | sordonia/flan-10k-flat/gem_wiki_lingua_english_en_1_1_0 | lora |
| unified_qa_science_inst | phi-2 | sordonia/flan-10k-flat/unified_qa_science_inst | lora |
| quartz_use_info_from_paragraph_question | phi-2 | sordonia/flan-10k-flat/quartz_use_info_from_paragraph_question | lora |
| wiki_hop_original_generate_object | phi-2 | sordonia/flan-10k-flat/wiki_hop_original_generate_object | lora |
| quoref_What_Is_The_Answer | phi-2 | sordonia/flan-10k-flat/quoref_What_Is_The_Answer | lora |
| adversarial_qa_droberta_generate_question | phi-2 | sordonia/flan-10k-flat/adversarial_qa_droberta_generate_question | lora |
| wiki_bio_comprehension | phi-2 | sordonia/flan-10k-flat/wiki_bio_comprehension | lora |
| adversarial_qa_dbidaf_question_context_answer | phi-2 | sordonia/flan-10k-flat/adversarial_qa_dbidaf_question_context_answer | lora |
| wiki_bio_what_content | phi-2 | sordonia/flan-10k-flat/wiki_bio_what_content | lora |
| web_questions_whats_the_answer | phi-2 | sordonia/flan-10k-flat/web_questions_whats_the_answer | lora |
| wiqa_what_is_the_missing_first_step | phi-2 | sordonia/flan-10k-flat/wiqa_what_is_the_missing_first_step | lora |
| adversarial_qa_droberta_question_context_answer | phi-2 | sordonia/flan-10k-flat/adversarial_qa_droberta_question_context_answer | lora |
| ropes_plain_bottom_hint | phi-2 | sordonia/flan-10k-flat/ropes_plain_bottom_hint | lora |
| kilt_tasks_hotpotqa_combining_facts | phi-2 | sordonia/flan-10k-flat/kilt_tasks_hotpotqa_combining_facts | lora |
| cos_e_v1_11_aligned_with_common_sense | phi-2 | sordonia/flan-10k-flat/cos_e_v1_11_aligned_with_common_sense | lora |
| gem_web_nlg_en_1_1_0 | phi-2 | sordonia/flan-10k-flat/gem_web_nlg_en_1_1_0 | lora |
| web_questions_potential_correct_answer | phi-2 | sordonia/flan-10k-flat/web_questions_potential_correct_answer | lora |
| wiki_qa_found_on_google | phi-2 | sordonia/flan-10k-flat/wiki_qa_found_on_google | lora |
| duorc_ParaphraseRC_extract_answer | phi-2 | sordonia/flan-10k-flat/duorc_ParaphraseRC_extract_answer | lora |
| wmt16_translate_de_en_1_0_0 | phi-2 | sordonia/flan-10k-flat/wmt16_translate_de_en_1_0_0 | lora |
| quail_no_prompt_id | phi-2 | sordonia/flan-10k-flat/quail_no_prompt_id | lora |
| quoref_Guess_Title_For_Context | phi-2 | sordonia/flan-10k-flat/quoref_Guess_Title_For_Context | lora |
| duorc_SelfRC_decide_worth_it | phi-2 | sordonia/flan-10k-flat/duorc_SelfRC_decide_worth_it | lora |
| ropes_prompt_mix | phi-2 | sordonia/flan-10k-flat/ropes_prompt_mix | lora |
| adversarial_qa_droberta_tell_what_it_is | phi-2 | sordonia/flan-10k-flat/adversarial_qa_droberta_tell_what_it_is | lora |
| quail_context_question_answer_description_id | phi-2 | sordonia/flan-10k-flat/quail_context_question_answer_description_id | lora |
| gem_common_gen_1_1_0 | phi-2 | sordonia/flan-10k-flat/gem_common_gen_1_1_0 | lora |
| duorc_ParaphraseRC_answer_question | phi-2 | sordonia/flan-10k-flat/duorc_ParaphraseRC_answer_question | lora |
| super_glue_cb_1_0_2 | phi-2 | sordonia/flan-10k-flat/super_glue_cb_1_0_2 | lora |
| cnn_dailymail_3_4_0 | phi-2 | sordonia/flan-10k-flat/cnn_dailymail_3_4_0 | lora |
| race_high_Write_a_multi_choice_question_options_given_ | phi-2 | sordonia/flan-10k-flat/race_high_Write_a_multi_choice_question_options_given_ | lora |
| winogrande_1_1_0 | phi-2 | sordonia/flan-10k-flat/winogrande_1_1_0 | lora |
| duorc_SelfRC_extract_answer | phi-2 | sordonia/flan-10k-flat/duorc_SelfRC_extract_answer | lora |
| trec_1_0_0 | phi-2 | sordonia/flan-10k-flat/trec_1_0_0 | lora |
| yelp_polarity_reviews_0_2_0 | phi-2 | sordonia/flan-10k-flat/yelp_polarity_reviews_0_2_0 | lora |
| race_high_Select_the_best_answer | phi-2 | sordonia/flan-10k-flat/race_high_Select_the_best_answer | lora |
| para_crawl_enes | phi-2 | sordonia/flan-10k-flat/para_crawl_enes | lora |
| qasc_is_correct_1 | phi-2 | sordonia/flan-10k-flat/qasc_is_correct_1 | lora |
| app_reviews_generate_review | phi-2 | sordonia/flan-10k-flat/app_reviews_generate_review | lora |
| ropes_read_background_situation | phi-2 | sordonia/flan-10k-flat/ropes_read_background_situation | lora |
| dbpedia_14_given_a_list_of_category_what_does_the_title_belong_to | phi-2 | sordonia/flan-10k-flat/dbpedia_14_given_a_list_of_category_what_does_the_title_belong_to | lora |
| stream_aqua | phi-2 | sordonia/flan-10k-flat/stream_aqua | lora |
| drop_2_0_0 | phi-2 | sordonia/flan-10k-flat/drop_2_0_0 | lora |
| wiki_hop_original_choose_best_object_affirmative_1 | phi-2 | sordonia/flan-10k-flat/wiki_hop_original_choose_best_object_affirmative_1 | lora |
| adversarial_qa_dbidaf_answer_the_following_q | phi-2 | sordonia/flan-10k-flat/adversarial_qa_dbidaf_answer_the_following_q | lora |
| social_i_qa_Generate_answer | phi-2 | sordonia/flan-10k-flat/social_i_qa_Generate_answer | lora |
| stream_aqua_ii | phi-2 | sordonia/flan-10k-flat/stream_aqua_ii | lora |
| glue_sst2_2_0_0 | phi-2 | sordonia/flan-10k-flat/glue_sst2_2_0_0 | lora |
| cot_esnli | phi-2 | sordonia/flan-10k-flat/cot_esnli | lora |
| race_high_Select_the_best_answer_no_instructions_ | phi-2 | sordonia/flan-10k-flat/race_high_Select_the_best_answer_no_instructions_ | lora |
| duorc_SelfRC_build_story_around_qa | phi-2 | sordonia/flan-10k-flat/duorc_SelfRC_build_story_around_qa | lora |
| cot_esnli_ii | phi-2 | sordonia/flan-10k-flat/cot_esnli_ii | lora |
| quail_no_prompt_text | phi-2 | sordonia/flan-10k-flat/quail_no_prompt_text | lora |
| ropes_given_background_situation | phi-2 | sordonia/flan-10k-flat/ropes_given_background_situation | lora |
| quarel_logic_test | phi-2 | sordonia/flan-10k-flat/quarel_logic_test | lora |
| adversarial_qa_dbidaf_based_on | phi-2 | sordonia/flan-10k-flat/adversarial_qa_dbidaf_based_on | lora |
| super_glue_copa_1_0_2 | phi-2 | sordonia/flan-10k-flat/super_glue_copa_1_0_2 | lora |
| cos_e_v1_11_i_think | phi-2 | sordonia/flan-10k-flat/cos_e_v1_11_i_think | lora |
| quail_context_question_description_answer_text | phi-2 | sordonia/flan-10k-flat/quail_context_question_description_answer_text | lora |
| math_dataset_algebra__linear_1d_1_0_0 | phi-2 | sordonia/flan-10k-flat/math_dataset_algebra__linear_1d_1_0_0 | lora |
| cosmos_qa_1_0_0 | phi-2 | sordonia/flan-10k-flat/cosmos_qa_1_0_0 | lora |
| wiqa_effect_with_label_answer | phi-2 | sordonia/flan-10k-flat/wiqa_effect_with_label_answer | lora |
| app_reviews_convert_to_star_rating | phi-2 | sordonia/flan-10k-flat/app_reviews_convert_to_star_rating | lora |
| qasc_qa_with_separated_facts_2 | phi-2 | sordonia/flan-10k-flat/qasc_qa_with_separated_facts_2 | lora |
| race_middle_Select_the_best_answer | phi-2 | sordonia/flan-10k-flat/race_middle_Select_the_best_answer | lora |
| quartz_having_read_above_passage | phi-2 | sordonia/flan-10k-flat/quartz_having_read_above_passage | lora |
| glue_qqp_2_0_0 | phi-2 | sordonia/flan-10k-flat/glue_qqp_2_0_0 | lora |
| cos_e_v1_11_question_description_option_id | phi-2 | sordonia/flan-10k-flat/cos_e_v1_11_question_description_option_id | lora |
| stream_qed_ii | phi-2 | sordonia/flan-10k-flat/stream_qed_ii | lora |
| cos_e_v1_11_question_option_description_text | phi-2 | sordonia/flan-10k-flat/cos_e_v1_11_question_option_description_text | lora |
| imdb_reviews_plain_text_1_0_0 | phi-2 | sordonia/flan-10k-flat/imdb_reviews_plain_text_1_0_0 | lora |
| wiki_hop_original_choose_best_object_affirmative_2 | phi-2 | sordonia/flan-10k-flat/wiki_hop_original_choose_best_object_affirmative_2 | lora |
| natural_questions_open_1_0_0 | phi-2 | sordonia/flan-10k-flat/natural_questions_open_1_0_0 | lora |
| wiqa_effect_with_string_answer | phi-2 | sordonia/flan-10k-flat/wiqa_effect_with_string_answer | lora |
| cos_e_v1_11_rationale | phi-2 | sordonia/flan-10k-flat/cos_e_v1_11_rationale | lora |
| race_middle_Write_a_multi_choice_question_options_given_ | phi-2 | sordonia/flan-10k-flat/race_middle_Write_a_multi_choice_question_options_given_ | lora |
| wiki_bio_guess_person | phi-2 | sordonia/flan-10k-flat/wiki_bio_guess_person | lora |
| hellaswag_1_1_0 | phi-2 | sordonia/flan-10k-flat/hellaswag_1_1_0 | lora |
| wiqa_does_the_supposed_perturbation_have_an_effect | phi-2 | sordonia/flan-10k-flat/wiqa_does_the_supposed_perturbation_have_an_effect | lora |
| trivia_qa_rc_1_1_0 | phi-2 | sordonia/flan-10k-flat/trivia_qa_rc_1_1_0 | lora |
| lambada_1_0_0 | phi-2 | sordonia/flan-10k-flat/lambada_1_0_0 | lora |
| quoref_Read_And_Extract_ | phi-2 | sordonia/flan-10k-flat/quoref_Read_And_Extract_ | lora |
| quail_context_description_question_answer_id | phi-2 | sordonia/flan-10k-flat/quail_context_description_question_answer_id | lora |
| quail_context_description_question_answer_text | phi-2 | sordonia/flan-10k-flat/quail_context_description_question_answer_text | lora |
| duorc_SelfRC_question_answering | phi-2 | sordonia/flan-10k-flat/duorc_SelfRC_question_answering | lora |
| cot_sensemaking_ii | phi-2 | sordonia/flan-10k-flat/cot_sensemaking_ii | lora |
| fix_punct | phi-2 | sordonia/flan-10k-flat/fix_punct | lora |
| squad_v1_1_3_0_0 | phi-2 | sordonia/flan-10k-flat/squad_v1_1_3_0_0 | lora |
| coqa_1_0_0 | phi-2 | sordonia/flan-10k-flat/coqa_1_0_0 | lora |
| glue_qnli_2_0_0 | phi-2 | sordonia/flan-10k-flat/glue_qnli_2_0_0 | lora |
| wiki_qa_Jeopardy_style | phi-2 | sordonia/flan-10k-flat/wiki_qa_Jeopardy_style | lora |
| qasc_qa_with_separated_facts_5 | phi-2 | sordonia/flan-10k-flat/qasc_qa_with_separated_facts_5 | lora |
| glue_mnli_2_0_0 | phi-2 | sordonia/flan-10k-flat/glue_mnli_2_0_0 | lora |
| wiki_bio_key_content | phi-2 | sordonia/flan-10k-flat/wiki_bio_key_content | lora |
| dream_generate_first_utterance | phi-2 | sordonia/flan-10k-flat/dream_generate_first_utterance | lora |
| quartz_read_passage_below_choose | phi-2 | sordonia/flan-10k-flat/quartz_read_passage_below_choose | lora |
| web_questions_question_answer | phi-2 | sordonia/flan-10k-flat/web_questions_question_answer | lora |
| glue_stsb_2_0_0 | phi-2 | sordonia/flan-10k-flat/glue_stsb_2_0_0 | lora |
| wmt16_translate_tr_en_1_0_0 | phi-2 | sordonia/flan-10k-flat/wmt16_translate_tr_en_1_0_0 | lora |
| cot_qasc | phi-2 | sordonia/flan-10k-flat/cot_qasc | lora |
| duorc_ParaphraseRC_title_generation | phi-2 | sordonia/flan-10k-flat/duorc_ParaphraseRC_title_generation | lora |
| quail_description_context_question_answer_id | phi-2 | sordonia/flan-10k-flat/quail_description_context_question_answer_id | lora |
| wiki_qa_Topic_Prediction_Question_Only | phi-2 | sordonia/flan-10k-flat/wiki_qa_Topic_Prediction_Question_Only | lora |
| quoref_Find_Answer | phi-2 | sordonia/flan-10k-flat/quoref_Find_Answer | lora |
| social_i_qa_I_was_wondering | phi-2 | sordonia/flan-10k-flat/social_i_qa_I_was_wondering | lora |
| wiki_hop_original_choose_best_object_affirmative_3 | phi-2 | sordonia/flan-10k-flat/wiki_hop_original_choose_best_object_affirmative_3 | lora |
| duorc_ParaphraseRC_build_story_around_qa | phi-2 | sordonia/flan-10k-flat/duorc_ParaphraseRC_build_story_around_qa | lora |
| qasc_qa_with_separated_facts_3 | phi-2 | sordonia/flan-10k-flat/qasc_qa_with_separated_facts_3 | lora |
| race_middle_Is_this_the_right_answer | phi-2 | sordonia/flan-10k-flat/race_middle_Is_this_the_right_answer | lora |
| paws_wiki_1_1_0 | phi-2 | sordonia/flan-10k-flat/paws_wiki_1_1_0 | lora |
| app_reviews_categorize_rating_using_review | phi-2 | sordonia/flan-10k-flat/app_reviews_categorize_rating_using_review | lora |
| anli_r3_0_1_0 | phi-2 | sordonia/flan-10k-flat/anli_r3_0_1_0 | lora |
| app_reviews_convert_to_rating | phi-2 | sordonia/flan-10k-flat/app_reviews_convert_to_rating | lora |
| wiqa_what_is_the_final_step_of_the_following_process | phi-2 | sordonia/flan-10k-flat/wiqa_what_is_the_final_step_of_the_following_process | lora |
| adversarial_qa_droberta_answer_the_following_q | phi-2 | sordonia/flan-10k-flat/adversarial_qa_droberta_answer_the_following_q | lora |
| wiki_qa_Decide_good_answer | phi-2 | sordonia/flan-10k-flat/wiki_qa_Decide_good_answer | lora |
| adversarial_qa_dbert_answer_the_following_q | phi-2 | sordonia/flan-10k-flat/adversarial_qa_dbert_answer_the_following_q | lora |
| gem_dart_1_1_0 | phi-2 | sordonia/flan-10k-flat/gem_dart_1_1_0 | lora |
| adversarial_qa_dbert_tell_what_it_is | phi-2 | sordonia/flan-10k-flat/adversarial_qa_dbert_tell_what_it_is | lora |
| quarel_choose_between | phi-2 | sordonia/flan-10k-flat/quarel_choose_between | lora |
| duorc_ParaphraseRC_generate_question_by_answer | phi-2 | sordonia/flan-10k-flat/duorc_ParaphraseRC_generate_question_by_answer | lora |
| wiki_hop_original_generate_subject | phi-2 | sordonia/flan-10k-flat/wiki_hop_original_generate_subject | lora |
| dream_baseline | phi-2 | sordonia/flan-10k-flat/dream_baseline | lora |
| cos_e_v1_11_question_description_option_text | phi-2 | sordonia/flan-10k-flat/cos_e_v1_11_question_description_option_text | lora |
| aeslc_1_0_0 | phi-2 | sordonia/flan-10k-flat/aeslc_1_0_0 | lora |
| anli_r2_0_1_0 | phi-2 | sordonia/flan-10k-flat/anli_r2_0_1_0 | lora |
| dbpedia_14_given_list_what_category_does_the_paragraph_belong_to | phi-2 | sordonia/flan-10k-flat/dbpedia_14_given_list_what_category_does_the_paragraph_belong_to | lora |
| quail_context_question_description_answer_id | phi-2 | sordonia/flan-10k-flat/quail_context_question_description_answer_id | lora |
| race_middle_Select_the_best_answer_no_instructions_ | phi-2 | sordonia/flan-10k-flat/race_middle_Select_the_best_answer_no_instructions_ | lora |
| wmt16_translate_ro_en_1_0_0 | phi-2 | sordonia/flan-10k-flat/wmt16_translate_ro_en_1_0_0 | lora |
| race_high_Is_this_the_right_answer | phi-2 | sordonia/flan-10k-flat/race_high_Is_this_the_right_answer | lora |
| quail_description_context_question_text | phi-2 | sordonia/flan-10k-flat/quail_description_context_question_text | lora |
| sciq_Direct_Question_Closed_Book_ | phi-2 | sordonia/flan-10k-flat/sciq_Direct_Question_Closed_Book_ | lora |
| openbookqa_0_1_0 | phi-2 | sordonia/flan-10k-flat/openbookqa_0_1_0 | lora |
| duorc_SelfRC_title_generation | phi-2 | sordonia/flan-10k-flat/duorc_SelfRC_title_generation | lora |
| cot_gsm8k | phi-2 | sordonia/flan-10k-flat/cot_gsm8k | lora |
| quartz_answer_question_below | phi-2 | sordonia/flan-10k-flat/quartz_answer_question_below | lora |
| snli_1_1_0 | phi-2 | sordonia/flan-10k-flat/snli_1_1_0 | lora |
| sciq_Multiple_Choice_Closed_Book_ | phi-2 | sordonia/flan-10k-flat/sciq_Multiple_Choice_Closed_Book_ | lora |
| cot_strategyqa | phi-2 | sordonia/flan-10k-flat/cot_strategyqa | lora |
| qasc_qa_with_separated_facts_4 | phi-2 | sordonia/flan-10k-flat/qasc_qa_with_separated_facts_4 | lora |
| ropes_prompt_bottom_no_hint | phi-2 | sordonia/flan-10k-flat/ropes_prompt_bottom_no_hint | lora |
| duorc_SelfRC_generate_question | phi-2 | sordonia/flan-10k-flat/duorc_SelfRC_generate_question | lora |
| quartz_given_the_fact_answer_the_q | phi-2 | sordonia/flan-10k-flat/quartz_given_the_fact_answer_the_q | lora |
| anli_r1_0_1_0 | phi-2 | sordonia/flan-10k-flat/anli_r1_0_1_0 | lora |
| wiki_qa_Topic_Prediction_Question_and_Answer_Pair | phi-2 | sordonia/flan-10k-flat/wiki_qa_Topic_Prediction_Question_and_Answer_Pair | lora |
| wiki_qa_Direct_Answer_to_Question | phi-2 | sordonia/flan-10k-flat/wiki_qa_Direct_Answer_to_Question | lora |
| qasc_is_correct_2 | phi-2 | sordonia/flan-10k-flat/qasc_is_correct_2 | lora |
| wiki_hop_original_generate_subject_and_object | phi-2 | sordonia/flan-10k-flat/wiki_hop_original_generate_subject_and_object | lora |
| ai2_arc_ARC_Challenge_1_0_0 | phi-2 | sordonia/flan-10k-flat/ai2_arc_ARC_Challenge_1_0_0 | lora |
| race_middle_Select_the_best_answer_generate_span_ | phi-2 | sordonia/flan-10k-flat/race_middle_Select_the_best_answer_generate_span_ | lora |
| quail_context_question_answer_description_text | phi-2 | sordonia/flan-10k-flat/quail_context_question_answer_description_text | lora |
| quail_context_question_description_text | phi-2 | sordonia/flan-10k-flat/quail_context_question_description_text | lora |
| wiki_hop_original_choose_best_object_interrogative_2 | phi-2 | sordonia/flan-10k-flat/wiki_hop_original_choose_best_object_interrogative_2 | lora |
| duorc_SelfRC_movie_director | phi-2 | sordonia/flan-10k-flat/duorc_SelfRC_movie_director | lora |
| quoref_Given_Context_Answer_Question | phi-2 | sordonia/flan-10k-flat/quoref_Given_Context_Answer_Question | lora |
| wiki_hop_original_explain_relation | phi-2 | sordonia/flan-10k-flat/wiki_hop_original_explain_relation | lora |
| super_glue_record_1_0_2 | phi-2 | sordonia/flan-10k-flat/super_glue_record_1_0_2 | lora |
| adversarial_qa_dbidaf_tell_what_it_is | phi-2 | sordonia/flan-10k-flat/adversarial_qa_dbidaf_tell_what_it_is | lora |
| cot_ecqa_ii | phi-2 | sordonia/flan-10k-flat/cot_ecqa_ii | lora |
| ropes_background_new_situation_answer | phi-2 | sordonia/flan-10k-flat/ropes_background_new_situation_answer | lora |
| web_questions_short_general_knowledge_q | phi-2 | sordonia/flan-10k-flat/web_questions_short_general_knowledge_q | lora |
| wiqa_what_might_be_the_first_step_of_the_process | phi-2 | sordonia/flan-10k-flat/wiqa_what_might_be_the_first_step_of_the_process | lora |
| ag_news_subset_1_0_0 | phi-2 | sordonia/flan-10k-flat/ag_news_subset_1_0_0 | lora |
| race_middle_Write_a_multi_choice_question_for_the_following_article | phi-2 | sordonia/flan-10k-flat/race_middle_Write_a_multi_choice_question_for_the_following_article | lora |
| wmt14_translate_fr_en_1_0_0 | phi-2 | sordonia/flan-10k-flat/wmt14_translate_fr_en_1_0_0 | lora |
| sciq_Direct_Question | phi-2 | sordonia/flan-10k-flat/sciq_Direct_Question | lora |
| super_glue_multirc_1_0_2 | phi-2 | sordonia/flan-10k-flat/super_glue_multirc_1_0_2 | lora |
| dbpedia_14_given_a_choice_of_categories_ | phi-2 | sordonia/flan-10k-flat/dbpedia_14_given_a_choice_of_categories_ | lora |
| super_glue_wic_1_0_2 | phi-2 | sordonia/flan-10k-flat/super_glue_wic_1_0_2 | lora |
| social_i_qa_Show_choices_and_generate_answer | phi-2 | sordonia/flan-10k-flat/social_i_qa_Show_choices_and_generate_answer | lora |
| wiqa_what_might_be_the_last_step_of_the_process | phi-2 | sordonia/flan-10k-flat/wiqa_what_might_be_the_last_step_of_the_process | lora |
| quoref_Answer_Question_Given_Context | phi-2 | sordonia/flan-10k-flat/quoref_Answer_Question_Given_Context | lora |
| quoref_Context_Contains_Answer | phi-2 | sordonia/flan-10k-flat/quoref_Context_Contains_Answer | lora |
| cos_e_v1_11_description_question_option_text | phi-2 | sordonia/flan-10k-flat/cos_e_v1_11_description_question_option_text | lora |
| adversarial_qa_dbert_based_on | phi-2 | sordonia/flan-10k-flat/adversarial_qa_dbert_based_on | lora |
| multi_news_1_0_0 | phi-2 | sordonia/flan-10k-flat/multi_news_1_0_0 | lora |
| cos_e_v1_11_generate_explanation_given_text | phi-2 | sordonia/flan-10k-flat/cos_e_v1_11_generate_explanation_given_text | lora |
| true_case | phi-2 | sordonia/flan-10k-flat/true_case | lora |
| duorc_ParaphraseRC_movie_director | phi-2 | sordonia/flan-10k-flat/duorc_ParaphraseRC_movie_director | lora |
| quartz_answer_question_based_on | phi-2 | sordonia/flan-10k-flat/quartz_answer_question_based_on | lora |
| bool_q_1_0_0 | phi-2 | sordonia/flan-10k-flat/bool_q_1_0_0 | lora |
| quoref_Guess_Answer | phi-2 | sordonia/flan-10k-flat/quoref_Guess_Answer | lora |
| quarel_do_not_use | phi-2 | sordonia/flan-10k-flat/quarel_do_not_use | lora |
| cos_e_v1_11_explain_why_human | phi-2 | sordonia/flan-10k-flat/cos_e_v1_11_explain_why_human | lora |
| wiki_qa_Generate_Question_from_Topic | phi-2 | sordonia/flan-10k-flat/wiki_qa_Generate_Question_from_Topic | lora |
| kilt_tasks_hotpotqa_straighforward_qa | phi-2 | sordonia/flan-10k-flat/kilt_tasks_hotpotqa_straighforward_qa | lora |
| adversarial_qa_dbidaf_generate_question | phi-2 | sordonia/flan-10k-flat/adversarial_qa_dbidaf_generate_question | lora |
| dbpedia_14_pick_one_category_for_the_following_text | phi-2 | sordonia/flan-10k-flat/dbpedia_14_pick_one_category_for_the_following_text | lora |
| kilt_tasks_hotpotqa_final_exam | phi-2 | sordonia/flan-10k-flat/kilt_tasks_hotpotqa_final_exam | lora |
| quoref_Answer_Friend_Question | phi-2 | sordonia/flan-10k-flat/quoref_Answer_Friend_Question | lora |
| race_high_Write_a_multi_choice_question_for_the_following_article | phi-2 | sordonia/flan-10k-flat/race_high_Write_a_multi_choice_question_for_the_following_article | lora |
| ropes_prompt_beginning | phi-2 | sordonia/flan-10k-flat/ropes_prompt_beginning | lora |
| adversarial_qa_dbert_question_context_answer | phi-2 | sordonia/flan-10k-flat/adversarial_qa_dbert_question_context_answer | lora |
| cot_creak | phi-2 | sordonia/flan-10k-flat/cot_creak | lora |
| gem_e2e_nlg_1_1_0 | phi-2 | sordonia/flan-10k-flat/gem_e2e_nlg_1_1_0 | lora |
| cos_e_v1_11_description_question_option_id | phi-2 | sordonia/flan-10k-flat/cos_e_v1_11_description_question_option_id | lora |
| social_i_qa_Generate_the_question_from_the_answer | phi-2 | sordonia/flan-10k-flat/social_i_qa_Generate_the_question_from_the_answer | lora |
| quarel_heres_a_story | phi-2 | sordonia/flan-10k-flat/quarel_heres_a_story | lora |
| social_i_qa_Check_if_a_random_answer_is_valid_or_not | phi-2 | sordonia/flan-10k-flat/social_i_qa_Check_if_a_random_answer_is_valid_or_not | lora |
| ropes_background_situation_middle | phi-2 | sordonia/flan-10k-flat/ropes_background_situation_middle | lora |
| sciq_Multiple_Choice_Question_First | phi-2 | sordonia/flan-10k-flat/sciq_Multiple_Choice_Question_First | lora |
| cot_strategyqa_ii | phi-2 | sordonia/flan-10k-flat/cot_strategyqa_ii | lora |
| huggingface_xsum | phi-2 | sordonia/flan-10k-flat/huggingface_xsum | lora |
| kilt_tasks_hotpotqa_complex_question | phi-2 | sordonia/flan-10k-flat/kilt_tasks_hotpotqa_complex_question | lora |
| wmt16_translate_fi_en_1_0_0 | phi-2 | sordonia/flan-10k-flat/wmt16_translate_fi_en_1_0_0 | lora |
| ai2_arc_ARC_Easy_1_0_0 | phi-2 | sordonia/flan-10k-flat/ai2_arc_ARC_Easy_1_0_0 | lora |
| stream_qed | phi-2 | sordonia/flan-10k-flat/stream_qed | lora |
| definite_pronoun_resolution_1_1_0 | phi-2 | sordonia/flan-10k-flat/definite_pronoun_resolution_1_1_0 | lora |
| super_glue_rte_1_0_2 | phi-2 | sordonia/flan-10k-flat/super_glue_rte_1_0_2 | lora |
| ropes_new_situation_background_answer | phi-2 | sordonia/flan-10k-flat/ropes_new_situation_background_answer | lora |
| dream_read_the_following_conversation_and_answer_the_question | phi-2 | sordonia/flan-10k-flat/dream_read_the_following_conversation_and_answer_the_question | lora |
| cot_sensemaking | phi-2 | sordonia/flan-10k-flat/cot_sensemaking | lora |
| wiki_qa_Topic_Prediction_Answer_Only | phi-2 | sordonia/flan-10k-flat/wiki_qa_Topic_Prediction_Answer_Only | lora |
| duorc_ParaphraseRC_generate_question | phi-2 | sordonia/flan-10k-flat/duorc_ParaphraseRC_generate_question | lora |
| dream_generate_last_utterance | phi-2 | sordonia/flan-10k-flat/dream_generate_last_utterance | lora |
| race_middle_Taking_a_test | phi-2 | sordonia/flan-10k-flat/race_middle_Taking_a_test | lora |
| piqa_1_0_0 | phi-2 | sordonia/flan-10k-flat/piqa_1_0_0 | lora |
| cot_ecqa | phi-2 | sordonia/flan-10k-flat/cot_ecqa | lora |
| glue_mrpc_2_0_0 | phi-2 | sordonia/flan-10k-flat/glue_mrpc_2_0_0 | lora |
| race_middle_Read_the_article_and_answer_the_question_no_option_ | phi-2 | sordonia/flan-10k-flat/race_middle_Read_the_article_and_answer_the_question_no_option_ | lora |
| ropes_plain_background_situation | phi-2 | sordonia/flan-10k-flat/ropes_plain_background_situation | lora |
| quail_description_context_question_answer_text | phi-2 | sordonia/flan-10k-flat/quail_description_context_question_answer_text | lora |
| qasc_qa_with_combined_facts_1 | phi-2 | sordonia/flan-10k-flat/qasc_qa_with_combined_facts_1 | lora |
| cot_creak_ii | phi-2 | sordonia/flan-10k-flat/cot_creak_ii | lora |
| duorc_ParaphraseRC_decide_worth_it | phi-2 | sordonia/flan-10k-flat/duorc_ParaphraseRC_decide_worth_it | lora |
| quoref_Answer_Test | phi-2 | sordonia/flan-10k-flat/quoref_Answer_Test | lora |
| wiki_bio_who | phi-2 | sordonia/flan-10k-flat/wiki_bio_who | lora |
| kilt_tasks_hotpotqa_formulate | phi-2 | sordonia/flan-10k-flat/kilt_tasks_hotpotqa_formulate | lora |
| glue_wnli_2_0_0 | phi-2 | sordonia/flan-10k-flat/glue_wnli_2_0_0 | lora |
| gigaword_1_2_0 | phi-2 | sordonia/flan-10k-flat/gigaword_1_2_0 | lora |
| quail_context_description_question_text | phi-2 | sordonia/flan-10k-flat/quail_context_description_question_text | lora |
| dream_answer_to_dialogue | phi-2 | sordonia/flan-10k-flat/dream_answer_to_dialogue | lora |
| cos_e_v1_11_question_option_description_id | phi-2 | sordonia/flan-10k-flat/cos_e_v1_11_question_option_description_id | lora |
| duorc_ParaphraseRC_question_answering | phi-2 | sordonia/flan-10k-flat/duorc_ParaphraseRC_question_answering | lora |
| wiki_qa_automatic_system | phi-2 | sordonia/flan-10k-flat/wiki_qa_automatic_system | lora |
| adversarial_qa_droberta_based_on | phi-2 | sordonia/flan-10k-flat/adversarial_qa_droberta_based_on | lora |
| super_glue_wsc_fixed_1_0_2 | phi-2 | sordonia/flan-10k-flat/super_glue_wsc_fixed_1_0_2 | lora |
| word_segment | phi-2 | sordonia/flan-10k-flat/word_segment | lora |
| quac_1_0_0 | phi-2 | sordonia/flan-10k-flat/quac_1_0_0 | lora |
| quartz_paragraph_question_plain_concat | phi-2 | sordonia/flan-10k-flat/quartz_paragraph_question_plain_concat | lora |
| wiqa_which_of_the_following_is_the_supposed_perturbation | phi-2 | sordonia/flan-10k-flat/wiqa_which_of_the_following_is_the_supposed_perturbation | lora |
| quartz_use_info_from_question_paragraph | phi-2 | sordonia/flan-10k-flat/quartz_use_info_from_question_paragraph | lora |
| ropes_plain_no_background | phi-2 | sordonia/flan-10k-flat/ropes_plain_no_background | lora |
| race_high_Select_the_best_answer_generate_span_ | phi-2 | sordonia/flan-10k-flat/race_high_Select_the_best_answer_generate_span_ | lora |
| glue_cola_2_0_0 | phi-2 | sordonia/flan-10k-flat/glue_cola_2_0_0 | lora |
| social_i_qa_Show_choices_and_generate_index | phi-2 | sordonia/flan-10k-flat/social_i_qa_Show_choices_and_generate_index | lora |
| ropes_prompt_bottom_hint_beginning | phi-2 | sordonia/flan-10k-flat/ropes_prompt_bottom_hint_beginning | lora |
| duorc_SelfRC_answer_question | phi-2 | sordonia/flan-10k-flat/duorc_SelfRC_answer_question | lora |
Last updated on: 2024-04-19 21:25:05+00:00
| {} | zhan1993/private_library_phi2_epoch_3 | null | [
"region:us"
] | null | 2024-04-19T14:56:41+00:00 | [] | [] | TAGS
#region-us
| Number of experts present in the library: 263
| [] | [
"TAGS\n#region-us \n"
] |
null | null | Number of experts present in the library: 263
| Expert Name | Base Model | Trained on | Adapter Type |
| --- | --- | --- | --- |
| sciq_Multiple_Choice | phi-2 | sordonia/flan-10k-flat/sciq_Multiple_Choice | lora |
| wiki_hop_original_choose_best_object_interrogative_1 | phi-2 | sordonia/flan-10k-flat/wiki_hop_original_choose_best_object_interrogative_1 | lora |
| squad_v2_0_3_0_0 | phi-2 | sordonia/flan-10k-flat/squad_v2_0_3_0_0 | lora |
| wiki_qa_exercise | phi-2 | sordonia/flan-10k-flat/wiki_qa_exercise | lora |
| race_high_Taking_a_test | phi-2 | sordonia/flan-10k-flat/race_high_Taking_a_test | lora |
| adversarial_qa_dbert_generate_question | phi-2 | sordonia/flan-10k-flat/adversarial_qa_dbert_generate_question | lora |
| quoref_Found_Context_Online | phi-2 | sordonia/flan-10k-flat/quoref_Found_Context_Online | lora |
| web_questions_get_the_answer | phi-2 | sordonia/flan-10k-flat/web_questions_get_the_answer | lora |
| duorc_SelfRC_generate_question_by_answer | phi-2 | sordonia/flan-10k-flat/duorc_SelfRC_generate_question_by_answer | lora |
| quarel_testing_students | phi-2 | sordonia/flan-10k-flat/quarel_testing_students | lora |
| qasc_qa_with_separated_facts_1 | phi-2 | sordonia/flan-10k-flat/qasc_qa_with_separated_facts_1 | lora |
| wiki_qa_Is_This_True_ | phi-2 | sordonia/flan-10k-flat/wiki_qa_Is_This_True_ | lora |
| race_high_Read_the_article_and_answer_the_question_no_option_ | phi-2 | sordonia/flan-10k-flat/race_high_Read_the_article_and_answer_the_question_no_option_ | lora |
| cot_gsm8k_ii | phi-2 | sordonia/flan-10k-flat/cot_gsm8k_ii | lora |
| gem_wiki_lingua_english_en_1_1_0 | phi-2 | sordonia/flan-10k-flat/gem_wiki_lingua_english_en_1_1_0 | lora |
| unified_qa_science_inst | phi-2 | sordonia/flan-10k-flat/unified_qa_science_inst | lora |
| quartz_use_info_from_paragraph_question | phi-2 | sordonia/flan-10k-flat/quartz_use_info_from_paragraph_question | lora |
| wiki_hop_original_generate_object | phi-2 | sordonia/flan-10k-flat/wiki_hop_original_generate_object | lora |
| quoref_What_Is_The_Answer | phi-2 | sordonia/flan-10k-flat/quoref_What_Is_The_Answer | lora |
| adversarial_qa_droberta_generate_question | phi-2 | sordonia/flan-10k-flat/adversarial_qa_droberta_generate_question | lora |
| wiki_bio_comprehension | phi-2 | sordonia/flan-10k-flat/wiki_bio_comprehension | lora |
| adversarial_qa_dbidaf_question_context_answer | phi-2 | sordonia/flan-10k-flat/adversarial_qa_dbidaf_question_context_answer | lora |
| wiki_bio_what_content | phi-2 | sordonia/flan-10k-flat/wiki_bio_what_content | lora |
| web_questions_whats_the_answer | phi-2 | sordonia/flan-10k-flat/web_questions_whats_the_answer | lora |
| wiqa_what_is_the_missing_first_step | phi-2 | sordonia/flan-10k-flat/wiqa_what_is_the_missing_first_step | lora |
| adversarial_qa_droberta_question_context_answer | phi-2 | sordonia/flan-10k-flat/adversarial_qa_droberta_question_context_answer | lora |
| ropes_plain_bottom_hint | phi-2 | sordonia/flan-10k-flat/ropes_plain_bottom_hint | lora |
| kilt_tasks_hotpotqa_combining_facts | phi-2 | sordonia/flan-10k-flat/kilt_tasks_hotpotqa_combining_facts | lora |
| cos_e_v1_11_aligned_with_common_sense | phi-2 | sordonia/flan-10k-flat/cos_e_v1_11_aligned_with_common_sense | lora |
| gem_web_nlg_en_1_1_0 | phi-2 | sordonia/flan-10k-flat/gem_web_nlg_en_1_1_0 | lora |
| web_questions_potential_correct_answer | phi-2 | sordonia/flan-10k-flat/web_questions_potential_correct_answer | lora |
| wiki_qa_found_on_google | phi-2 | sordonia/flan-10k-flat/wiki_qa_found_on_google | lora |
| duorc_ParaphraseRC_extract_answer | phi-2 | sordonia/flan-10k-flat/duorc_ParaphraseRC_extract_answer | lora |
| wmt16_translate_de_en_1_0_0 | phi-2 | sordonia/flan-10k-flat/wmt16_translate_de_en_1_0_0 | lora |
| quail_no_prompt_id | phi-2 | sordonia/flan-10k-flat/quail_no_prompt_id | lora |
| quoref_Guess_Title_For_Context | phi-2 | sordonia/flan-10k-flat/quoref_Guess_Title_For_Context | lora |
| duorc_SelfRC_decide_worth_it | phi-2 | sordonia/flan-10k-flat/duorc_SelfRC_decide_worth_it | lora |
| ropes_prompt_mix | phi-2 | sordonia/flan-10k-flat/ropes_prompt_mix | lora |
| adversarial_qa_droberta_tell_what_it_is | phi-2 | sordonia/flan-10k-flat/adversarial_qa_droberta_tell_what_it_is | lora |
| quail_context_question_answer_description_id | phi-2 | sordonia/flan-10k-flat/quail_context_question_answer_description_id | lora |
| gem_common_gen_1_1_0 | phi-2 | sordonia/flan-10k-flat/gem_common_gen_1_1_0 | lora |
| duorc_ParaphraseRC_answer_question | phi-2 | sordonia/flan-10k-flat/duorc_ParaphraseRC_answer_question | lora |
| super_glue_cb_1_0_2 | phi-2 | sordonia/flan-10k-flat/super_glue_cb_1_0_2 | lora |
| cnn_dailymail_3_4_0 | phi-2 | sordonia/flan-10k-flat/cnn_dailymail_3_4_0 | lora |
| race_high_Write_a_multi_choice_question_options_given_ | phi-2 | sordonia/flan-10k-flat/race_high_Write_a_multi_choice_question_options_given_ | lora |
| winogrande_1_1_0 | phi-2 | sordonia/flan-10k-flat/winogrande_1_1_0 | lora |
| duorc_SelfRC_extract_answer | phi-2 | sordonia/flan-10k-flat/duorc_SelfRC_extract_answer | lora |
| trec_1_0_0 | phi-2 | sordonia/flan-10k-flat/trec_1_0_0 | lora |
| yelp_polarity_reviews_0_2_0 | phi-2 | sordonia/flan-10k-flat/yelp_polarity_reviews_0_2_0 | lora |
| race_high_Select_the_best_answer | phi-2 | sordonia/flan-10k-flat/race_high_Select_the_best_answer | lora |
| para_crawl_enes | phi-2 | sordonia/flan-10k-flat/para_crawl_enes | lora |
| qasc_is_correct_1 | phi-2 | sordonia/flan-10k-flat/qasc_is_correct_1 | lora |
| app_reviews_generate_review | phi-2 | sordonia/flan-10k-flat/app_reviews_generate_review | lora |
| ropes_read_background_situation | phi-2 | sordonia/flan-10k-flat/ropes_read_background_situation | lora |
| dbpedia_14_given_a_list_of_category_what_does_the_title_belong_to | phi-2 | sordonia/flan-10k-flat/dbpedia_14_given_a_list_of_category_what_does_the_title_belong_to | lora |
| stream_aqua | phi-2 | sordonia/flan-10k-flat/stream_aqua | lora |
| drop_2_0_0 | phi-2 | sordonia/flan-10k-flat/drop_2_0_0 | lora |
| wiki_hop_original_choose_best_object_affirmative_1 | phi-2 | sordonia/flan-10k-flat/wiki_hop_original_choose_best_object_affirmative_1 | lora |
| adversarial_qa_dbidaf_answer_the_following_q | phi-2 | sordonia/flan-10k-flat/adversarial_qa_dbidaf_answer_the_following_q | lora |
| social_i_qa_Generate_answer | phi-2 | sordonia/flan-10k-flat/social_i_qa_Generate_answer | lora |
| stream_aqua_ii | phi-2 | sordonia/flan-10k-flat/stream_aqua_ii | lora |
| glue_sst2_2_0_0 | phi-2 | sordonia/flan-10k-flat/glue_sst2_2_0_0 | lora |
| cot_esnli | phi-2 | sordonia/flan-10k-flat/cot_esnli | lora |
| race_high_Select_the_best_answer_no_instructions_ | phi-2 | sordonia/flan-10k-flat/race_high_Select_the_best_answer_no_instructions_ | lora |
| duorc_SelfRC_build_story_around_qa | phi-2 | sordonia/flan-10k-flat/duorc_SelfRC_build_story_around_qa | lora |
| cot_esnli_ii | phi-2 | sordonia/flan-10k-flat/cot_esnli_ii | lora |
| quail_no_prompt_text | phi-2 | sordonia/flan-10k-flat/quail_no_prompt_text | lora |
| ropes_given_background_situation | phi-2 | sordonia/flan-10k-flat/ropes_given_background_situation | lora |
| quarel_logic_test | phi-2 | sordonia/flan-10k-flat/quarel_logic_test | lora |
| adversarial_qa_dbidaf_based_on | phi-2 | sordonia/flan-10k-flat/adversarial_qa_dbidaf_based_on | lora |
| super_glue_copa_1_0_2 | phi-2 | sordonia/flan-10k-flat/super_glue_copa_1_0_2 | lora |
| cos_e_v1_11_i_think | phi-2 | sordonia/flan-10k-flat/cos_e_v1_11_i_think | lora |
| quail_context_question_description_answer_text | phi-2 | sordonia/flan-10k-flat/quail_context_question_description_answer_text | lora |
| math_dataset_algebra__linear_1d_1_0_0 | phi-2 | sordonia/flan-10k-flat/math_dataset_algebra__linear_1d_1_0_0 | lora |
| cosmos_qa_1_0_0 | phi-2 | sordonia/flan-10k-flat/cosmos_qa_1_0_0 | lora |
| wiqa_effect_with_label_answer | phi-2 | sordonia/flan-10k-flat/wiqa_effect_with_label_answer | lora |
| app_reviews_convert_to_star_rating | phi-2 | sordonia/flan-10k-flat/app_reviews_convert_to_star_rating | lora |
| qasc_qa_with_separated_facts_2 | phi-2 | sordonia/flan-10k-flat/qasc_qa_with_separated_facts_2 | lora |
| race_middle_Select_the_best_answer | phi-2 | sordonia/flan-10k-flat/race_middle_Select_the_best_answer | lora |
| quartz_having_read_above_passage | phi-2 | sordonia/flan-10k-flat/quartz_having_read_above_passage | lora |
| glue_qqp_2_0_0 | phi-2 | sordonia/flan-10k-flat/glue_qqp_2_0_0 | lora |
| cos_e_v1_11_question_description_option_id | phi-2 | sordonia/flan-10k-flat/cos_e_v1_11_question_description_option_id | lora |
| stream_qed_ii | phi-2 | sordonia/flan-10k-flat/stream_qed_ii | lora |
| cos_e_v1_11_question_option_description_text | phi-2 | sordonia/flan-10k-flat/cos_e_v1_11_question_option_description_text | lora |
| imdb_reviews_plain_text_1_0_0 | phi-2 | sordonia/flan-10k-flat/imdb_reviews_plain_text_1_0_0 | lora |
| wiki_hop_original_choose_best_object_affirmative_2 | phi-2 | sordonia/flan-10k-flat/wiki_hop_original_choose_best_object_affirmative_2 | lora |
| natural_questions_open_1_0_0 | phi-2 | sordonia/flan-10k-flat/natural_questions_open_1_0_0 | lora |
| wiqa_effect_with_string_answer | phi-2 | sordonia/flan-10k-flat/wiqa_effect_with_string_answer | lora |
| cos_e_v1_11_rationale | phi-2 | sordonia/flan-10k-flat/cos_e_v1_11_rationale | lora |
| race_middle_Write_a_multi_choice_question_options_given_ | phi-2 | sordonia/flan-10k-flat/race_middle_Write_a_multi_choice_question_options_given_ | lora |
| wiki_bio_guess_person | phi-2 | sordonia/flan-10k-flat/wiki_bio_guess_person | lora |
| hellaswag_1_1_0 | phi-2 | sordonia/flan-10k-flat/hellaswag_1_1_0 | lora |
| wiqa_does_the_supposed_perturbation_have_an_effect | phi-2 | sordonia/flan-10k-flat/wiqa_does_the_supposed_perturbation_have_an_effect | lora |
| trivia_qa_rc_1_1_0 | phi-2 | sordonia/flan-10k-flat/trivia_qa_rc_1_1_0 | lora |
| lambada_1_0_0 | phi-2 | sordonia/flan-10k-flat/lambada_1_0_0 | lora |
| quoref_Read_And_Extract_ | phi-2 | sordonia/flan-10k-flat/quoref_Read_And_Extract_ | lora |
| quail_context_description_question_answer_id | phi-2 | sordonia/flan-10k-flat/quail_context_description_question_answer_id | lora |
| quail_context_description_question_answer_text | phi-2 | sordonia/flan-10k-flat/quail_context_description_question_answer_text | lora |
| duorc_SelfRC_question_answering | phi-2 | sordonia/flan-10k-flat/duorc_SelfRC_question_answering | lora |
| cot_sensemaking_ii | phi-2 | sordonia/flan-10k-flat/cot_sensemaking_ii | lora |
| fix_punct | phi-2 | sordonia/flan-10k-flat/fix_punct | lora |
| squad_v1_1_3_0_0 | phi-2 | sordonia/flan-10k-flat/squad_v1_1_3_0_0 | lora |
| coqa_1_0_0 | phi-2 | sordonia/flan-10k-flat/coqa_1_0_0 | lora |
| glue_qnli_2_0_0 | phi-2 | sordonia/flan-10k-flat/glue_qnli_2_0_0 | lora |
| wiki_qa_Jeopardy_style | phi-2 | sordonia/flan-10k-flat/wiki_qa_Jeopardy_style | lora |
| qasc_qa_with_separated_facts_5 | phi-2 | sordonia/flan-10k-flat/qasc_qa_with_separated_facts_5 | lora |
| glue_mnli_2_0_0 | phi-2 | sordonia/flan-10k-flat/glue_mnli_2_0_0 | lora |
| wiki_bio_key_content | phi-2 | sordonia/flan-10k-flat/wiki_bio_key_content | lora |
| dream_generate_first_utterance | phi-2 | sordonia/flan-10k-flat/dream_generate_first_utterance | lora |
| quartz_read_passage_below_choose | phi-2 | sordonia/flan-10k-flat/quartz_read_passage_below_choose | lora |
| web_questions_question_answer | phi-2 | sordonia/flan-10k-flat/web_questions_question_answer | lora |
| glue_stsb_2_0_0 | phi-2 | sordonia/flan-10k-flat/glue_stsb_2_0_0 | lora |
| wmt16_translate_tr_en_1_0_0 | phi-2 | sordonia/flan-10k-flat/wmt16_translate_tr_en_1_0_0 | lora |
| cot_qasc | phi-2 | sordonia/flan-10k-flat/cot_qasc | lora |
| duorc_ParaphraseRC_title_generation | phi-2 | sordonia/flan-10k-flat/duorc_ParaphraseRC_title_generation | lora |
| quail_description_context_question_answer_id | phi-2 | sordonia/flan-10k-flat/quail_description_context_question_answer_id | lora |
| wiki_qa_Topic_Prediction_Question_Only | phi-2 | sordonia/flan-10k-flat/wiki_qa_Topic_Prediction_Question_Only | lora |
| quoref_Find_Answer | phi-2 | sordonia/flan-10k-flat/quoref_Find_Answer | lora |
| social_i_qa_I_was_wondering | phi-2 | sordonia/flan-10k-flat/social_i_qa_I_was_wondering | lora |
| wiki_hop_original_choose_best_object_affirmative_3 | phi-2 | sordonia/flan-10k-flat/wiki_hop_original_choose_best_object_affirmative_3 | lora |
| duorc_ParaphraseRC_build_story_around_qa | phi-2 | sordonia/flan-10k-flat/duorc_ParaphraseRC_build_story_around_qa | lora |
| qasc_qa_with_separated_facts_3 | phi-2 | sordonia/flan-10k-flat/qasc_qa_with_separated_facts_3 | lora |
| race_middle_Is_this_the_right_answer | phi-2 | sordonia/flan-10k-flat/race_middle_Is_this_the_right_answer | lora |
| paws_wiki_1_1_0 | phi-2 | sordonia/flan-10k-flat/paws_wiki_1_1_0 | lora |
| app_reviews_categorize_rating_using_review | phi-2 | sordonia/flan-10k-flat/app_reviews_categorize_rating_using_review | lora |
| anli_r3_0_1_0 | phi-2 | sordonia/flan-10k-flat/anli_r3_0_1_0 | lora |
| app_reviews_convert_to_rating | phi-2 | sordonia/flan-10k-flat/app_reviews_convert_to_rating | lora |
| wiqa_what_is_the_final_step_of_the_following_process | phi-2 | sordonia/flan-10k-flat/wiqa_what_is_the_final_step_of_the_following_process | lora |
| adversarial_qa_droberta_answer_the_following_q | phi-2 | sordonia/flan-10k-flat/adversarial_qa_droberta_answer_the_following_q | lora |
| wiki_qa_Decide_good_answer | phi-2 | sordonia/flan-10k-flat/wiki_qa_Decide_good_answer | lora |
| adversarial_qa_dbert_answer_the_following_q | phi-2 | sordonia/flan-10k-flat/adversarial_qa_dbert_answer_the_following_q | lora |
| gem_dart_1_1_0 | phi-2 | sordonia/flan-10k-flat/gem_dart_1_1_0 | lora |
| adversarial_qa_dbert_tell_what_it_is | phi-2 | sordonia/flan-10k-flat/adversarial_qa_dbert_tell_what_it_is | lora |
| quarel_choose_between | phi-2 | sordonia/flan-10k-flat/quarel_choose_between | lora |
| duorc_ParaphraseRC_generate_question_by_answer | phi-2 | sordonia/flan-10k-flat/duorc_ParaphraseRC_generate_question_by_answer | lora |
| wiki_hop_original_generate_subject | phi-2 | sordonia/flan-10k-flat/wiki_hop_original_generate_subject | lora |
| dream_baseline | phi-2 | sordonia/flan-10k-flat/dream_baseline | lora |
| cos_e_v1_11_question_description_option_text | phi-2 | sordonia/flan-10k-flat/cos_e_v1_11_question_description_option_text | lora |
| aeslc_1_0_0 | phi-2 | sordonia/flan-10k-flat/aeslc_1_0_0 | lora |
| anli_r2_0_1_0 | phi-2 | sordonia/flan-10k-flat/anli_r2_0_1_0 | lora |
| dbpedia_14_given_list_what_category_does_the_paragraph_belong_to | phi-2 | sordonia/flan-10k-flat/dbpedia_14_given_list_what_category_does_the_paragraph_belong_to | lora |
| quail_context_question_description_answer_id | phi-2 | sordonia/flan-10k-flat/quail_context_question_description_answer_id | lora |
| race_middle_Select_the_best_answer_no_instructions_ | phi-2 | sordonia/flan-10k-flat/race_middle_Select_the_best_answer_no_instructions_ | lora |
| wmt16_translate_ro_en_1_0_0 | phi-2 | sordonia/flan-10k-flat/wmt16_translate_ro_en_1_0_0 | lora |
| race_high_Is_this_the_right_answer | phi-2 | sordonia/flan-10k-flat/race_high_Is_this_the_right_answer | lora |
| quail_description_context_question_text | phi-2 | sordonia/flan-10k-flat/quail_description_context_question_text | lora |
| sciq_Direct_Question_Closed_Book_ | phi-2 | sordonia/flan-10k-flat/sciq_Direct_Question_Closed_Book_ | lora |
| openbookqa_0_1_0 | phi-2 | sordonia/flan-10k-flat/openbookqa_0_1_0 | lora |
| duorc_SelfRC_title_generation | phi-2 | sordonia/flan-10k-flat/duorc_SelfRC_title_generation | lora |
| cot_gsm8k | phi-2 | sordonia/flan-10k-flat/cot_gsm8k | lora |
| quartz_answer_question_below | phi-2 | sordonia/flan-10k-flat/quartz_answer_question_below | lora |
| snli_1_1_0 | phi-2 | sordonia/flan-10k-flat/snli_1_1_0 | lora |
| sciq_Multiple_Choice_Closed_Book_ | phi-2 | sordonia/flan-10k-flat/sciq_Multiple_Choice_Closed_Book_ | lora |
| cot_strategyqa | phi-2 | sordonia/flan-10k-flat/cot_strategyqa | lora |
| qasc_qa_with_separated_facts_4 | phi-2 | sordonia/flan-10k-flat/qasc_qa_with_separated_facts_4 | lora |
| ropes_prompt_bottom_no_hint | phi-2 | sordonia/flan-10k-flat/ropes_prompt_bottom_no_hint | lora |
| duorc_SelfRC_generate_question | phi-2 | sordonia/flan-10k-flat/duorc_SelfRC_generate_question | lora |
| quartz_given_the_fact_answer_the_q | phi-2 | sordonia/flan-10k-flat/quartz_given_the_fact_answer_the_q | lora |
| anli_r1_0_1_0 | phi-2 | sordonia/flan-10k-flat/anli_r1_0_1_0 | lora |
| wiki_qa_Topic_Prediction_Question_and_Answer_Pair | phi-2 | sordonia/flan-10k-flat/wiki_qa_Topic_Prediction_Question_and_Answer_Pair | lora |
| wiki_qa_Direct_Answer_to_Question | phi-2 | sordonia/flan-10k-flat/wiki_qa_Direct_Answer_to_Question | lora |
| qasc_is_correct_2 | phi-2 | sordonia/flan-10k-flat/qasc_is_correct_2 | lora |
| wiki_hop_original_generate_subject_and_object | phi-2 | sordonia/flan-10k-flat/wiki_hop_original_generate_subject_and_object | lora |
| ai2_arc_ARC_Challenge_1_0_0 | phi-2 | sordonia/flan-10k-flat/ai2_arc_ARC_Challenge_1_0_0 | lora |
| race_middle_Select_the_best_answer_generate_span_ | phi-2 | sordonia/flan-10k-flat/race_middle_Select_the_best_answer_generate_span_ | lora |
| quail_context_question_answer_description_text | phi-2 | sordonia/flan-10k-flat/quail_context_question_answer_description_text | lora |
| quail_context_question_description_text | phi-2 | sordonia/flan-10k-flat/quail_context_question_description_text | lora |
| wiki_hop_original_choose_best_object_interrogative_2 | phi-2 | sordonia/flan-10k-flat/wiki_hop_original_choose_best_object_interrogative_2 | lora |
| duorc_SelfRC_movie_director | phi-2 | sordonia/flan-10k-flat/duorc_SelfRC_movie_director | lora |
| quoref_Given_Context_Answer_Question | phi-2 | sordonia/flan-10k-flat/quoref_Given_Context_Answer_Question | lora |
| wiki_hop_original_explain_relation | phi-2 | sordonia/flan-10k-flat/wiki_hop_original_explain_relation | lora |
| super_glue_record_1_0_2 | phi-2 | sordonia/flan-10k-flat/super_glue_record_1_0_2 | lora |
| adversarial_qa_dbidaf_tell_what_it_is | phi-2 | sordonia/flan-10k-flat/adversarial_qa_dbidaf_tell_what_it_is | lora |
| cot_ecqa_ii | phi-2 | sordonia/flan-10k-flat/cot_ecqa_ii | lora |
| ropes_background_new_situation_answer | phi-2 | sordonia/flan-10k-flat/ropes_background_new_situation_answer | lora |
| wiqa_what_might_be_the_first_step_of_the_process | phi-2 | sordonia/flan-10k-flat/wiqa_what_might_be_the_first_step_of_the_process | lora |
| duorc_SelfRC_answer_question | phi-2 | sordonia/flan-10k-flat/duorc_SelfRC_answer_question | lora |
| ag_news_subset_1_0_0 | phi-2 | sordonia/flan-10k-flat/ag_news_subset_1_0_0 | lora |
| race_middle_Write_a_multi_choice_question_for_the_following_article | phi-2 | sordonia/flan-10k-flat/race_middle_Write_a_multi_choice_question_for_the_following_article | lora |
| wmt14_translate_fr_en_1_0_0 | phi-2 | sordonia/flan-10k-flat/wmt14_translate_fr_en_1_0_0 | lora |
| sciq_Direct_Question | phi-2 | sordonia/flan-10k-flat/sciq_Direct_Question | lora |
| super_glue_multirc_1_0_2 | phi-2 | sordonia/flan-10k-flat/super_glue_multirc_1_0_2 | lora |
| dbpedia_14_given_a_choice_of_categories_ | phi-2 | sordonia/flan-10k-flat/dbpedia_14_given_a_choice_of_categories_ | lora |
| super_glue_wic_1_0_2 | phi-2 | sordonia/flan-10k-flat/super_glue_wic_1_0_2 | lora |
| social_i_qa_Show_choices_and_generate_answer | phi-2 | sordonia/flan-10k-flat/social_i_qa_Show_choices_and_generate_answer | lora |
| wiqa_what_might_be_the_last_step_of_the_process | phi-2 | sordonia/flan-10k-flat/wiqa_what_might_be_the_last_step_of_the_process | lora |
| quoref_Answer_Question_Given_Context | phi-2 | sordonia/flan-10k-flat/quoref_Answer_Question_Given_Context | lora |
| quoref_Context_Contains_Answer | phi-2 | sordonia/flan-10k-flat/quoref_Context_Contains_Answer | lora |
| cos_e_v1_11_description_question_option_text | phi-2 | sordonia/flan-10k-flat/cos_e_v1_11_description_question_option_text | lora |
| adversarial_qa_dbert_based_on | phi-2 | sordonia/flan-10k-flat/adversarial_qa_dbert_based_on | lora |
| multi_news_1_0_0 | phi-2 | sordonia/flan-10k-flat/multi_news_1_0_0 | lora |
| cos_e_v1_11_generate_explanation_given_text | phi-2 | sordonia/flan-10k-flat/cos_e_v1_11_generate_explanation_given_text | lora |
| true_case | phi-2 | sordonia/flan-10k-flat/true_case | lora |
| duorc_ParaphraseRC_movie_director | phi-2 | sordonia/flan-10k-flat/duorc_ParaphraseRC_movie_director | lora |
| quartz_answer_question_based_on | phi-2 | sordonia/flan-10k-flat/quartz_answer_question_based_on | lora |
| bool_q_1_0_0 | phi-2 | sordonia/flan-10k-flat/bool_q_1_0_0 | lora |
| quoref_Guess_Answer | phi-2 | sordonia/flan-10k-flat/quoref_Guess_Answer | lora |
| quarel_do_not_use | phi-2 | sordonia/flan-10k-flat/quarel_do_not_use | lora |
| cos_e_v1_11_explain_why_human | phi-2 | sordonia/flan-10k-flat/cos_e_v1_11_explain_why_human | lora |
| wiki_qa_Generate_Question_from_Topic | phi-2 | sordonia/flan-10k-flat/wiki_qa_Generate_Question_from_Topic | lora |
| kilt_tasks_hotpotqa_straighforward_qa | phi-2 | sordonia/flan-10k-flat/kilt_tasks_hotpotqa_straighforward_qa | lora |
| adversarial_qa_dbidaf_generate_question | phi-2 | sordonia/flan-10k-flat/adversarial_qa_dbidaf_generate_question | lora |
| dbpedia_14_pick_one_category_for_the_following_text | phi-2 | sordonia/flan-10k-flat/dbpedia_14_pick_one_category_for_the_following_text | lora |
| kilt_tasks_hotpotqa_final_exam | phi-2 | sordonia/flan-10k-flat/kilt_tasks_hotpotqa_final_exam | lora |
| quoref_Answer_Friend_Question | phi-2 | sordonia/flan-10k-flat/quoref_Answer_Friend_Question | lora |
| race_high_Write_a_multi_choice_question_for_the_following_article | phi-2 | sordonia/flan-10k-flat/race_high_Write_a_multi_choice_question_for_the_following_article | lora |
| ropes_prompt_beginning | phi-2 | sordonia/flan-10k-flat/ropes_prompt_beginning | lora |
| adversarial_qa_dbert_question_context_answer | phi-2 | sordonia/flan-10k-flat/adversarial_qa_dbert_question_context_answer | lora |
| cot_creak | phi-2 | sordonia/flan-10k-flat/cot_creak | lora |
| gem_e2e_nlg_1_1_0 | phi-2 | sordonia/flan-10k-flat/gem_e2e_nlg_1_1_0 | lora |
| cos_e_v1_11_description_question_option_id | phi-2 | sordonia/flan-10k-flat/cos_e_v1_11_description_question_option_id | lora |
| social_i_qa_Generate_the_question_from_the_answer | phi-2 | sordonia/flan-10k-flat/social_i_qa_Generate_the_question_from_the_answer | lora |
| quarel_heres_a_story | phi-2 | sordonia/flan-10k-flat/quarel_heres_a_story | lora |
| social_i_qa_Check_if_a_random_answer_is_valid_or_not | phi-2 | sordonia/flan-10k-flat/social_i_qa_Check_if_a_random_answer_is_valid_or_not | lora |
| ropes_background_situation_middle | phi-2 | sordonia/flan-10k-flat/ropes_background_situation_middle | lora |
| sciq_Multiple_Choice_Question_First | phi-2 | sordonia/flan-10k-flat/sciq_Multiple_Choice_Question_First | lora |
| cot_strategyqa_ii | phi-2 | sordonia/flan-10k-flat/cot_strategyqa_ii | lora |
| huggingface_xsum | phi-2 | sordonia/flan-10k-flat/huggingface_xsum | lora |
| kilt_tasks_hotpotqa_complex_question | phi-2 | sordonia/flan-10k-flat/kilt_tasks_hotpotqa_complex_question | lora |
| wmt16_translate_fi_en_1_0_0 | phi-2 | sordonia/flan-10k-flat/wmt16_translate_fi_en_1_0_0 | lora |
| ai2_arc_ARC_Easy_1_0_0 | phi-2 | sordonia/flan-10k-flat/ai2_arc_ARC_Easy_1_0_0 | lora |
| stream_qed | phi-2 | sordonia/flan-10k-flat/stream_qed | lora |
| definite_pronoun_resolution_1_1_0 | phi-2 | sordonia/flan-10k-flat/definite_pronoun_resolution_1_1_0 | lora |
| super_glue_rte_1_0_2 | phi-2 | sordonia/flan-10k-flat/super_glue_rte_1_0_2 | lora |
| ropes_new_situation_background_answer | phi-2 | sordonia/flan-10k-flat/ropes_new_situation_background_answer | lora |
| dream_read_the_following_conversation_and_answer_the_question | phi-2 | sordonia/flan-10k-flat/dream_read_the_following_conversation_and_answer_the_question | lora |
| cot_sensemaking | phi-2 | sordonia/flan-10k-flat/cot_sensemaking | lora |
| wiki_qa_Topic_Prediction_Answer_Only | phi-2 | sordonia/flan-10k-flat/wiki_qa_Topic_Prediction_Answer_Only | lora |
| duorc_ParaphraseRC_generate_question | phi-2 | sordonia/flan-10k-flat/duorc_ParaphraseRC_generate_question | lora |
| dream_generate_last_utterance | phi-2 | sordonia/flan-10k-flat/dream_generate_last_utterance | lora |
| race_middle_Taking_a_test | phi-2 | sordonia/flan-10k-flat/race_middle_Taking_a_test | lora |
| piqa_1_0_0 | phi-2 | sordonia/flan-10k-flat/piqa_1_0_0 | lora |
| cot_ecqa | phi-2 | sordonia/flan-10k-flat/cot_ecqa | lora |
| glue_mrpc_2_0_0 | phi-2 | sordonia/flan-10k-flat/glue_mrpc_2_0_0 | lora |
| race_middle_Read_the_article_and_answer_the_question_no_option_ | phi-2 | sordonia/flan-10k-flat/race_middle_Read_the_article_and_answer_the_question_no_option_ | lora |
| ropes_plain_background_situation | phi-2 | sordonia/flan-10k-flat/ropes_plain_background_situation | lora |
| quail_description_context_question_answer_text | phi-2 | sordonia/flan-10k-flat/quail_description_context_question_answer_text | lora |
| qasc_qa_with_combined_facts_1 | phi-2 | sordonia/flan-10k-flat/qasc_qa_with_combined_facts_1 | lora |
| cot_creak_ii | phi-2 | sordonia/flan-10k-flat/cot_creak_ii | lora |
| duorc_ParaphraseRC_decide_worth_it | phi-2 | sordonia/flan-10k-flat/duorc_ParaphraseRC_decide_worth_it | lora |
| quoref_Answer_Test | phi-2 | sordonia/flan-10k-flat/quoref_Answer_Test | lora |
| wiki_bio_who | phi-2 | sordonia/flan-10k-flat/wiki_bio_who | lora |
| kilt_tasks_hotpotqa_formulate | phi-2 | sordonia/flan-10k-flat/kilt_tasks_hotpotqa_formulate | lora |
| glue_wnli_2_0_0 | phi-2 | sordonia/flan-10k-flat/glue_wnli_2_0_0 | lora |
| gigaword_1_2_0 | phi-2 | sordonia/flan-10k-flat/gigaword_1_2_0 | lora |
| quail_context_description_question_text | phi-2 | sordonia/flan-10k-flat/quail_context_description_question_text | lora |
| dream_answer_to_dialogue | phi-2 | sordonia/flan-10k-flat/dream_answer_to_dialogue | lora |
| cos_e_v1_11_question_option_description_id | phi-2 | sordonia/flan-10k-flat/cos_e_v1_11_question_option_description_id | lora |
| duorc_ParaphraseRC_question_answering | phi-2 | sordonia/flan-10k-flat/duorc_ParaphraseRC_question_answering | lora |
| wiki_qa_automatic_system | phi-2 | sordonia/flan-10k-flat/wiki_qa_automatic_system | lora |
| adversarial_qa_droberta_based_on | phi-2 | sordonia/flan-10k-flat/adversarial_qa_droberta_based_on | lora |
| super_glue_wsc_fixed_1_0_2 | phi-2 | sordonia/flan-10k-flat/super_glue_wsc_fixed_1_0_2 | lora |
| word_segment | phi-2 | sordonia/flan-10k-flat/word_segment | lora |
| quac_1_0_0 | phi-2 | sordonia/flan-10k-flat/quac_1_0_0 | lora |
| quartz_paragraph_question_plain_concat | phi-2 | sordonia/flan-10k-flat/quartz_paragraph_question_plain_concat | lora |
| wiqa_which_of_the_following_is_the_supposed_perturbation | phi-2 | sordonia/flan-10k-flat/wiqa_which_of_the_following_is_the_supposed_perturbation | lora |
| quartz_use_info_from_question_paragraph | phi-2 | sordonia/flan-10k-flat/quartz_use_info_from_question_paragraph | lora |
| ropes_plain_no_background | phi-2 | sordonia/flan-10k-flat/ropes_plain_no_background | lora |
| race_high_Select_the_best_answer_generate_span_ | phi-2 | sordonia/flan-10k-flat/race_high_Select_the_best_answer_generate_span_ | lora |
| glue_cola_2_0_0 | phi-2 | sordonia/flan-10k-flat/glue_cola_2_0_0 | lora |
| social_i_qa_Show_choices_and_generate_index | phi-2 | sordonia/flan-10k-flat/social_i_qa_Show_choices_and_generate_index | lora |
| ropes_prompt_bottom_hint_beginning | phi-2 | sordonia/flan-10k-flat/ropes_prompt_bottom_hint_beginning | lora |
| web_questions_short_general_knowledge_q | phi-2 | sordonia/flan-10k-flat/web_questions_short_general_knowledge_q | lora |
Last updated on: 2024-04-19 18:28:23+00:00
| {} | zhan1993/private_library_phi2_epoch_4 | null | [
"region:us"
] | null | 2024-04-19T14:57:43+00:00 | [] | [] | TAGS
#region-us
| Number of experts present in the library: 263
| [] | [
"TAGS\n#region-us \n"
] |
null | transformers |
# Uploaded model
- **Developed by:** feliphe-galiza
- **License:** apache-2.0
- **Finetuned from model :** unsloth/llama-3-8b-bnb-4bit
This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
| {"language": ["en"], "license": "apache-2.0", "tags": ["text-generation-inference", "transformers", "unsloth", "llama", "trl"], "base_model": "unsloth/llama-3-8b-bnb-4bit"} | feliphe-galiza/llama-3-hypernyms | null | [
"transformers",
"safetensors",
"text-generation-inference",
"unsloth",
"llama",
"trl",
"en",
"base_model:unsloth/llama-3-8b-bnb-4bit",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | 2024-04-19T14:58:01+00:00 | [] | [
"en"
] | TAGS
#transformers #safetensors #text-generation-inference #unsloth #llama #trl #en #base_model-unsloth/llama-3-8b-bnb-4bit #license-apache-2.0 #endpoints_compatible #region-us
|
# Uploaded model
- Developed by: feliphe-galiza
- License: apache-2.0
- Finetuned from model : unsloth/llama-3-8b-bnb-4bit
This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.
<img src="URL width="200"/>
| [
"# Uploaded model\n\n- Developed by: feliphe-galiza\n- License: apache-2.0\n- Finetuned from model : unsloth/llama-3-8b-bnb-4bit\n\nThis llama model was trained 2x faster with Unsloth and Huggingface's TRL library.\n\n<img src=\"URL width=\"200\"/>"
] | [
"TAGS\n#transformers #safetensors #text-generation-inference #unsloth #llama #trl #en #base_model-unsloth/llama-3-8b-bnb-4bit #license-apache-2.0 #endpoints_compatible #region-us \n",
"# Uploaded model\n\n- Developed by: feliphe-galiza\n- License: apache-2.0\n- Finetuned from model : unsloth/llama-3-8b-bnb-4bit\n\nThis llama model was trained 2x faster with Unsloth and Huggingface's TRL library.\n\n<img src=\"URL width=\"200\"/>"
] |
null | transformers |
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] | {"library_name": "transformers", "tags": []} | hi000000/insta_upnormal-llama-koen_200 | null | [
"transformers",
"safetensors",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null | 2024-04-19T14:58:06+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 |
# Uploaded model
- **Developed by:** martyyz
- **License:** apache-2.0
- **Finetuned from model :** unsloth/llama-3-8b-bnb-4bit
This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
| {"language": ["en"], "license": "apache-2.0", "tags": ["text-generation-inference", "transformers", "unsloth", "llama", "trl"], "base_model": "unsloth/llama-3-8b-bnb-4bit"} | martyyz/llama3-8b-oig-unsloth | null | [
"transformers",
"safetensors",
"text-generation-inference",
"unsloth",
"llama",
"trl",
"en",
"base_model:unsloth/llama-3-8b-bnb-4bit",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | 2024-04-19T15:01:27+00:00 | [] | [
"en"
] | TAGS
#transformers #safetensors #text-generation-inference #unsloth #llama #trl #en #base_model-unsloth/llama-3-8b-bnb-4bit #license-apache-2.0 #endpoints_compatible #region-us
|
# Uploaded model
- Developed by: martyyz
- License: apache-2.0
- Finetuned from model : unsloth/llama-3-8b-bnb-4bit
This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.
<img src="URL width="200"/>
| [
"# Uploaded model\n\n- Developed by: martyyz\n- License: apache-2.0\n- Finetuned from model : unsloth/llama-3-8b-bnb-4bit\n\nThis llama model was trained 2x faster with Unsloth and Huggingface's TRL library.\n\n<img src=\"URL width=\"200\"/>"
] | [
"TAGS\n#transformers #safetensors #text-generation-inference #unsloth #llama #trl #en #base_model-unsloth/llama-3-8b-bnb-4bit #license-apache-2.0 #endpoints_compatible #region-us \n",
"# Uploaded model\n\n- Developed by: martyyz\n- License: apache-2.0\n- Finetuned from model : unsloth/llama-3-8b-bnb-4bit\n\nThis llama model was trained 2x faster with Unsloth and Huggingface's TRL library.\n\n<img src=\"URL width=\"200\"/>"
] |
text-to-image | diffusers |
<!-- This model card has been generated automatically according to the information the training script had access to. You
should probably proofread and complete it, then remove this comment. -->
# Critical Dream - cosmicBboy/stable-diffusion-xl-base-1.0-lora-dreambooth-critdream-v0.6.1
<Gallery />
## Model description
These are cosmicBboy/stable-diffusion-xl-base-1.0-lora-dreambooth-critdream-v0.6.1 LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0, for the purposes of
generating images for the [Critical Dream](https://github.com/cosmicBboy/critical-dream)
project.
The weights were trained using [DreamBooth](https://dreambooth.github.io/).
LoRA for the text encoder was enabled: True.
Special VAE used for training: stabilityai/sdxl-vae.
## Trigger words
You should use a picture of [dm-matt-mercer], a dungeon master. background is a forest. fantasy art style, high quality, highly detailed, sharp focus" to trigger the image generation.
## Download model
Weights for this model are available in Safetensors format.
[Download](cosmicBboy/stable-diffusion-xl-base-1.0-lora-dreambooth-critdream-v0.6.1/tree/main) them in the Files & versions tab.
## Tracker run link
https://wandb.ai/nielsbantilan/dreambooth-lora-sd-xl/runs/s6rfmqpp
## Intended uses & limitations
#### How to use
```python
# TODO: add an example code snippet for running this diffusion pipeline
```
#### Limitations and bias
[TODO: provide examples of latent issues and potential remediations]
## Training details
[TODO: describe the data used to train the model] | {"license": "openrail++", "library_name": "diffusers", "tags": ["text-to-image", "stable-diffusion-xl", "stable-diffusion-xl-diffusers", "text-to-image", "diffusers", "lora", "template:sd-lora"], "base_model": "stabilityai/stable-diffusion-xl-base-1.0", "prompt": "a picture of [dm-matt-mercer], a dungeon master. background is a forest. fantasy art style, high quality, highly detailed, sharp focus\"", "widget": [{"text": "a picture of [dm-matt-mercer]", "output": {"url": "image_0.png"}}, {"text": "a picture of [dm-matt-mercer]", "output": {"url": "image_1.png"}}, {"text": "a picture of a dungeon master.", "output": {"url": "image_2.png"}}, {"text": "a picture of a dungeon master.", "output": {"url": "image_3.png"}}, {"text": "a picture of [critrole-fjord], a male half-orc warlock. background is a forest. fantasy art style, high quality, highly detailed, sharp focus", "output": {"url": "image_4.png"}}, {"text": "a picture of [critrole-fjord], a male half-orc warlock. background is a forest. fantasy art style, high quality, highly detailed, sharp focus", "output": {"url": "image_5.png"}}, {"text": "a picture of a male half-orc warlock", "output": {"url": "image_6.png"}}, {"text": "a picture of a male half-orc warlock", "output": {"url": "image_7.png"}}, {"text": "a picture of [critrole-beau], a female human monk. background is a forest. fantasy art style, high quality, highly detailed, sharp focus", "output": {"url": "image_8.png"}}, {"text": "a picture of [critrole-beau], a female human monk. background is a forest. fantasy art style, high quality, highly detailed, sharp focus", "output": {"url": "image_9.png"}}, {"text": "a picture of a female human monk", "output": {"url": "image_10.png"}}, {"text": "a picture of a female human monk", "output": {"url": "image_11.png"}}, {"text": "a picture of [critrole-caduceus], a male firbolg cleric. background is a forest. fantasy art style, high quality, highly detailed, sharp focus", "output": {"url": "image_12.png"}}, {"text": "a picture of [critrole-caduceus], a male firbolg cleric. background is a forest. fantasy art style, high quality, highly detailed, sharp focus", "output": {"url": "image_13.png"}}, {"text": "a picture of a male firbolg cleric", "output": {"url": "image_14.png"}}, {"text": "a picture of a male firbolg cleric", "output": {"url": "image_15.png"}}, {"text": "a picture of [critrole-caleb], a male human wizard. background is a forest. fantasy art style, high quality, highly detailed, sharp focus", "output": {"url": "image_16.png"}}, {"text": "a picture of [critrole-caleb], a male human wizard. background is a forest. fantasy art style, high quality, highly detailed, sharp focus", "output": {"url": "image_17.png"}}, {"text": "a picture of a male human wizard", "output": {"url": "image_18.png"}}, {"text": "a picture of a male human wizard", "output": {"url": "image_19.png"}}, {"text": "a picture of [critrole-jester], a female tiefling cleric. background is a forest. fantasy art style, high quality, highly detailed, sharp focus", "output": {"url": "image_20.png"}}, {"text": "a picture of [critrole-jester], a female tiefling cleric. background is a forest. fantasy art style, high quality, highly detailed, sharp focus", "output": {"url": "image_21.png"}}, {"text": "a picture of a female tiefling cleric", "output": {"url": "image_22.png"}}, {"text": "a picture of a female tiefling cleric", "output": {"url": "image_23.png"}}, {"text": "a picture of [critrole-nott], a female goblin rogue. background is a forest. fantasy art style, high quality, highly detailed, sharp focus", "output": {"url": "image_24.png"}}, {"text": "a picture of [critrole-nott], a female goblin rogue. background is a forest. fantasy art style, high quality, highly detailed, sharp focus", "output": {"url": "image_25.png"}}, {"text": "a picture of a female goblin rogue", "output": {"url": "image_26.png"}}, {"text": "a picture of a female goblin rogue", "output": {"url": "image_27.png"}}, {"text": "a picture of [critrole-veth], a female halfling rogue/wizard. background is a forest. fantasy art style, high quality, highly detailed, sharp focus", "output": {"url": "image_28.png"}}, {"text": "a picture of [critrole-veth], a female halfling rogue/wizard. background is a forest. fantasy art style, high quality, highly detailed, sharp focus", "output": {"url": "image_29.png"}}, {"text": "a picture of a female halfling rogue/wizard", "output": {"url": "image_30.png"}}, {"text": "a picture of a female halfling rogue/wizard", "output": {"url": "image_31.png"}}, {"text": "a picture of [critrole-yasha], a female aasimar barbarian. background is a forest. fantasy art style, high quality, highly detailed, sharp focus", "output": {"url": "image_32.png"}}, {"text": "a picture of [critrole-yasha], a female aasimar barbarian. background is a forest. fantasy art style, high quality, highly detailed, sharp focus", "output": {"url": "image_33.png"}}, {"text": "a picture of a female aasimar barbarian", "output": {"url": "image_34.png"}}, {"text": "a picture of a female aasimar barbarian", "output": {"url": "image_35.png"}}, {"text": "a picture of [critrole-mollymauk], a male tiefling blood hunter. background is a forest. fantasy art style, high quality, highly detailed, sharp focus", "output": {"url": "image_36.png"}}, {"text": "a picture of [critrole-mollymauk], a male tiefling blood hunter. background is a forest. fantasy art style, high quality, highly detailed, sharp focus", "output": {"url": "image_37.png"}}, {"text": "a picture of a male tiefling blood hunter", "output": {"url": "image_38.png"}}, {"text": "a picture of a male tiefling blood hunter", "output": {"url": "image_39.png"}}, {"text": "a picture of [critrole-essek], a male drow wizard. background is a forest. fantasy art style, high quality, highly detailed, sharp focus", "output": {"url": "image_40.png"}}, {"text": "a picture of [critrole-essek], a male drow wizard. background is a forest. fantasy art style, high quality, highly detailed, sharp focus", "output": {"url": "image_41.png"}}, {"text": "a picture of a male drow wizard", "output": {"url": "image_42.png"}}, {"text": "a picture of a male drow wizard", "output": {"url": "image_43.png"}}]} | cosmicBboy/stable-diffusion-xl-base-1.0-lora-dreambooth-critdream-v0.6.1 | null | [
"diffusers",
"text-to-image",
"stable-diffusion-xl",
"stable-diffusion-xl-diffusers",
"lora",
"template:sd-lora",
"base_model:stabilityai/stable-diffusion-xl-base-1.0",
"license:openrail++",
"region:us"
] | null | 2024-04-19T15:01:53+00:00 | [] | [] | TAGS
#diffusers #text-to-image #stable-diffusion-xl #stable-diffusion-xl-diffusers #lora #template-sd-lora #base_model-stabilityai/stable-diffusion-xl-base-1.0 #license-openrail++ #region-us
|
# Critical Dream - cosmicBboy/stable-diffusion-xl-base-1.0-lora-dreambooth-critdream-v0.6.1
<Gallery />
## Model description
These are cosmicBboy/stable-diffusion-xl-base-1.0-lora-dreambooth-critdream-v0.6.1 LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0, for the purposes of
generating images for the Critical Dream
project.
The weights were trained using DreamBooth.
LoRA for the text encoder was enabled: True.
Special VAE used for training: stabilityai/sdxl-vae.
## Trigger words
You should use a picture of [dm-matt-mercer], a dungeon master. background is a forest. fantasy art style, high quality, highly detailed, sharp focus" to trigger the image generation.
## Download model
Weights for this model are available in Safetensors format.
Download them in the Files & versions tab.
## Tracker run link
URL
## Intended uses & limitations
#### How to use
#### Limitations and bias
[TODO: provide examples of latent issues and potential remediations]
## Training details
[TODO: describe the data used to train the model] | [
"# Critical Dream - cosmicBboy/stable-diffusion-xl-base-1.0-lora-dreambooth-critdream-v0.6.1\n\n<Gallery />",
"## Model description\n\nThese are cosmicBboy/stable-diffusion-xl-base-1.0-lora-dreambooth-critdream-v0.6.1 LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0, for the purposes of\ngenerating images for the Critical Dream\nproject.\n\nThe weights were trained using DreamBooth.\n\nLoRA for the text encoder was enabled: True.\n\nSpecial VAE used for training: stabilityai/sdxl-vae.",
"## Trigger words\n\nYou should use a picture of [dm-matt-mercer], a dungeon master. background is a forest. fantasy art style, high quality, highly detailed, sharp focus\" to trigger the image generation.",
"## Download model\n\nWeights for this model are available in Safetensors format.\n\nDownload them in the Files & versions tab.",
"## Tracker run link\n\nURL",
"## Intended uses & limitations",
"#### How to use",
"#### Limitations and bias\n\n[TODO: provide examples of latent issues and potential remediations]",
"## Training details\n\n[TODO: describe the data used to train the model]"
] | [
"TAGS\n#diffusers #text-to-image #stable-diffusion-xl #stable-diffusion-xl-diffusers #lora #template-sd-lora #base_model-stabilityai/stable-diffusion-xl-base-1.0 #license-openrail++ #region-us \n",
"# Critical Dream - cosmicBboy/stable-diffusion-xl-base-1.0-lora-dreambooth-critdream-v0.6.1\n\n<Gallery />",
"## Model description\n\nThese are cosmicBboy/stable-diffusion-xl-base-1.0-lora-dreambooth-critdream-v0.6.1 LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0, for the purposes of\ngenerating images for the Critical Dream\nproject.\n\nThe weights were trained using DreamBooth.\n\nLoRA for the text encoder was enabled: True.\n\nSpecial VAE used for training: stabilityai/sdxl-vae.",
"## Trigger words\n\nYou should use a picture of [dm-matt-mercer], a dungeon master. background is a forest. fantasy art style, high quality, highly detailed, sharp focus\" to trigger the image generation.",
"## Download model\n\nWeights for this model are available in Safetensors format.\n\nDownload them in the Files & versions tab.",
"## Tracker run link\n\nURL",
"## Intended uses & limitations",
"#### How to use",
"#### Limitations and bias\n\n[TODO: provide examples of latent issues and potential remediations]",
"## Training details\n\n[TODO: describe the data used to train the model]"
] |
null | transformers |
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] | {"library_name": "transformers", "tags": []} | nuebaek/komt_mistral_user_0_max_steps_100 | null | [
"transformers",
"safetensors",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null | 2024-04-19T15:03:05+00:00 | [
"1910.09700"
] | [] | TAGS
#transformers #safetensors #arxiv-1910.09700 #endpoints_compatible #region-us
|
# Model Card for Model ID
## Model Details
### Model Description
This is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.
- Developed by:
- Funded by [optional]:
- Shared by [optional]:
- Model type:
- Language(s) (NLP):
- License:
- Finetuned from model [optional]:
### Model Sources [optional]
- Repository:
- Paper [optional]:
- Demo [optional]:
## Uses
### Direct Use
### Downstream Use [optional]
### Out-of-Scope Use
## Bias, Risks, and Limitations
### Recommendations
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
## Training Details
### Training Data
### Training Procedure
#### Preprocessing [optional]
#### Training Hyperparameters
- Training regime:
#### Speeds, Sizes, Times [optional]
## Evaluation
### Testing Data, Factors & Metrics
#### Testing Data
#### Factors
#### Metrics
### Results
#### Summary
## Model Examination [optional]
## Environmental Impact
Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).
- Hardware Type:
- Hours used:
- Cloud Provider:
- Compute Region:
- Carbon Emitted:
## Technical Specifications [optional]
### Model Architecture and Objective
### Compute Infrastructure
#### Hardware
#### Software
[optional]
BibTeX:
APA:
## Glossary [optional]
## More Information [optional]
## Model Card Authors [optional]
## Model Card Contact
| [
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.",
"## How to Get Started with the Model\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] | [
"TAGS\n#transformers #safetensors #arxiv-1910.09700 #endpoints_compatible #region-us \n",
"# Model Card for Model ID",
"## Model Details",
"### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:",
"### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Downstream Use [optional]",
"### Out-of-Scope Use",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.",
"## How to Get Started with the Model\n\nUse the code below to get started with the model.",
"## Training Details",
"### Training Data",
"### Training Procedure",
"#### Preprocessing [optional]",
"#### Training Hyperparameters\n\n- Training regime:",
"#### Speeds, Sizes, Times [optional]",
"## Evaluation",
"### Testing Data, Factors & Metrics",
"#### Testing Data",
"#### Factors",
"#### Metrics",
"### Results",
"#### Summary",
"## Model Examination [optional]",
"## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:",
"## Technical Specifications [optional]",
"### Model Architecture and Objective",
"### Compute Infrastructure",
"#### Hardware",
"#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Model Card Authors [optional]",
"## Model Card Contact"
] |
text-generation | transformers | # Model Card for Cyber-risk-llama-3-8b
## Model Description
This model is a fine-tuned version of `meta-llama/Meta-Llama-3-8B` on the `vanessasml/cybersecurity_32k_instruction_input_output` dataset.
It is specifically designed to enhance performance in generating and understanding cybersecurity, identifying cyber threats and classifying data under the NIST taxonomy and IT Risks based on the ITC EBA guidelines.
## Intended Use
- **Intended users**: Data scientists and developers working on cybersecurity applications.
- **Out-of-scope use cases**: This model should not be used for medical advice, legal decisions, or any life-critical systems.
## Training Data
The model was fine-tuned on `vanessasml/cybersecurity_32k_instruction_input_output`, a dataset focused on cybersecurity news analysis.
No special data format was applied as [recommended](https://huggingface.co/blog/llama3#fine-tuning-with-%F0%9F%A4%97-trl)
## Training Procedure
- **Preprocessing**: Text data were tokenized using the tokenizer corresponding to the base model `meta-llama/Meta-Llama-3-8B`.
- **Hardware**: The training was performed on GPUs with mixed precision (FP16/BF16) enabled.
- **Optimizer**: Paged AdamW with a cosine learning rate schedule.
- **Epochs**: The model was trained for 1 epoch.
- **Batch size**: 4 per device, with gradient accumulation where required.
## Evaluation Results
Model evaluation was based on qualitative assessment of generated text relevance and coherence in the context of cybersecurity.
## Quantization and Optimization
- **Quantization**: 4-bit precision with type `nf4`. Nested quantization is disabled.
- **Compute dtype**: `float16` to ensure efficient computation.
- **LoRA Settings**:
- LoRA attention dimension: `64`
- Alpha parameter for LoRA scaling: `16`
- Dropout in LoRA layers: `0.1`
## Environmental Impact
- **Compute Resources**: Training leveraged energy-efficient hardware and practices to minimize carbon footprint.
- **Strategies**: Gradient checkpointing and group-wise data processing were used to optimize memory and power usage.
## How to Use
Here is how to load and use the model:
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
model_name = "vanessasml/cyber-risk-llama-3-8b"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name)
# Example of how to use the model:
prompt = """Question: What are the cyber threads present in the article?
Article: More than one million Brits over the age of 45 have fallen victim to some form of email-related fraud, \
as the internet supersedes the telephone as the favored channel for scammers, according to Aviva. \
The insurer polled over 1000 adults over the age of 45 in the latest update to its long-running Real Retirement Report. \
Further, 6% said they had actually fallen victim to such an online attack, amounting to around 1.2 million adults. \
Some 22% more people it surveyed had been targeted by ...
"""
pipe = pipeline(task="text-generation", model=model, tokenizer=tokenizer, max_length=200)
# To generate text:
result = pipe(prompt)
print(result[0]['generated_text'])
```
## Limitations and Bias
The model, while robust in cybersecurity contexts, may not generalize well to unrelated domains. Users should be cautious of biases inherent in the training data which may manifest in model predictions.
## Citation
If you use this model, please cite it as follows:
```bibtex
@misc{cyber-risk-llama-3-8b-sft-lora-4bit-float16,
author = {Vanessa Lopes},
title = {Cyber-risk-llama-3-8B Model},
year = {2024},
publisher = {HuggingFace Hub},
journal = {HuggingFace Model Hub}
}
``` | {"tags": ["finance", "supervision", "cyber risk", "cybersecurity", "cyber threats", "SFT", "LoRA", "A100GPU"], "datasets": ["Vanessasml/cybersecurity_32k_instruction_input_output"], "pipeline_tag": "text-generation"} | Vanessasml/cyber-risk-llama-3-8b | null | [
"transformers",
"pytorch",
"llama",
"text-generation",
"finance",
"supervision",
"cyber risk",
"cybersecurity",
"cyber threats",
"SFT",
"LoRA",
"A100GPU",
"conversational",
"dataset:Vanessasml/cybersecurity_32k_instruction_input_output",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-04-19T15:03:19+00:00 | [] | [] | TAGS
#transformers #pytorch #llama #text-generation #finance #supervision #cyber risk #cybersecurity #cyber threats #SFT #LoRA #A100GPU #conversational #dataset-Vanessasml/cybersecurity_32k_instruction_input_output #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us
| # Model Card for Cyber-risk-llama-3-8b
## Model Description
This model is a fine-tuned version of 'meta-llama/Meta-Llama-3-8B' on the 'vanessasml/cybersecurity_32k_instruction_input_output' dataset.
It is specifically designed to enhance performance in generating and understanding cybersecurity, identifying cyber threats and classifying data under the NIST taxonomy and IT Risks based on the ITC EBA guidelines.
## Intended Use
- Intended users: Data scientists and developers working on cybersecurity applications.
- Out-of-scope use cases: This model should not be used for medical advice, legal decisions, or any life-critical systems.
## Training Data
The model was fine-tuned on 'vanessasml/cybersecurity_32k_instruction_input_output', a dataset focused on cybersecurity news analysis.
No special data format was applied as recommended
## Training Procedure
- Preprocessing: Text data were tokenized using the tokenizer corresponding to the base model 'meta-llama/Meta-Llama-3-8B'.
- Hardware: The training was performed on GPUs with mixed precision (FP16/BF16) enabled.
- Optimizer: Paged AdamW with a cosine learning rate schedule.
- Epochs: The model was trained for 1 epoch.
- Batch size: 4 per device, with gradient accumulation where required.
## Evaluation Results
Model evaluation was based on qualitative assessment of generated text relevance and coherence in the context of cybersecurity.
## Quantization and Optimization
- Quantization: 4-bit precision with type 'nf4'. Nested quantization is disabled.
- Compute dtype: 'float16' to ensure efficient computation.
- LoRA Settings:
- LoRA attention dimension: '64'
- Alpha parameter for LoRA scaling: '16'
- Dropout in LoRA layers: '0.1'
## Environmental Impact
- Compute Resources: Training leveraged energy-efficient hardware and practices to minimize carbon footprint.
- Strategies: Gradient checkpointing and group-wise data processing were used to optimize memory and power usage.
## How to Use
Here is how to load and use the model:
## Limitations and Bias
The model, while robust in cybersecurity contexts, may not generalize well to unrelated domains. Users should be cautious of biases inherent in the training data which may manifest in model predictions.
If you use this model, please cite it as follows:
| [
"# Model Card for Cyber-risk-llama-3-8b",
"## Model Description\nThis model is a fine-tuned version of 'meta-llama/Meta-Llama-3-8B' on the 'vanessasml/cybersecurity_32k_instruction_input_output' dataset. \n\nIt is specifically designed to enhance performance in generating and understanding cybersecurity, identifying cyber threats and classifying data under the NIST taxonomy and IT Risks based on the ITC EBA guidelines.",
"## Intended Use\n- Intended users: Data scientists and developers working on cybersecurity applications.\n- Out-of-scope use cases: This model should not be used for medical advice, legal decisions, or any life-critical systems.",
"## Training Data\nThe model was fine-tuned on 'vanessasml/cybersecurity_32k_instruction_input_output', a dataset focused on cybersecurity news analysis. \nNo special data format was applied as recommended",
"## Training Procedure\n- Preprocessing: Text data were tokenized using the tokenizer corresponding to the base model 'meta-llama/Meta-Llama-3-8B'.\n- Hardware: The training was performed on GPUs with mixed precision (FP16/BF16) enabled.\n- Optimizer: Paged AdamW with a cosine learning rate schedule.\n- Epochs: The model was trained for 1 epoch.\n- Batch size: 4 per device, with gradient accumulation where required.",
"## Evaluation Results\nModel evaluation was based on qualitative assessment of generated text relevance and coherence in the context of cybersecurity.",
"## Quantization and Optimization\n- Quantization: 4-bit precision with type 'nf4'. Nested quantization is disabled.\n- Compute dtype: 'float16' to ensure efficient computation.\n- LoRA Settings:\n - LoRA attention dimension: '64'\n - Alpha parameter for LoRA scaling: '16'\n - Dropout in LoRA layers: '0.1'",
"## Environmental Impact\n- Compute Resources: Training leveraged energy-efficient hardware and practices to minimize carbon footprint.\n- Strategies: Gradient checkpointing and group-wise data processing were used to optimize memory and power usage.",
"## How to Use\nHere is how to load and use the model:",
"## Limitations and Bias\nThe model, while robust in cybersecurity contexts, may not generalize well to unrelated domains. Users should be cautious of biases inherent in the training data which may manifest in model predictions.\n\n\nIf you use this model, please cite it as follows:"
] | [
"TAGS\n#transformers #pytorch #llama #text-generation #finance #supervision #cyber risk #cybersecurity #cyber threats #SFT #LoRA #A100GPU #conversational #dataset-Vanessasml/cybersecurity_32k_instruction_input_output #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n",
"# Model Card for Cyber-risk-llama-3-8b",
"## Model Description\nThis model is a fine-tuned version of 'meta-llama/Meta-Llama-3-8B' on the 'vanessasml/cybersecurity_32k_instruction_input_output' dataset. \n\nIt is specifically designed to enhance performance in generating and understanding cybersecurity, identifying cyber threats and classifying data under the NIST taxonomy and IT Risks based on the ITC EBA guidelines.",
"## Intended Use\n- Intended users: Data scientists and developers working on cybersecurity applications.\n- Out-of-scope use cases: This model should not be used for medical advice, legal decisions, or any life-critical systems.",
"## Training Data\nThe model was fine-tuned on 'vanessasml/cybersecurity_32k_instruction_input_output', a dataset focused on cybersecurity news analysis. \nNo special data format was applied as recommended",
"## Training Procedure\n- Preprocessing: Text data were tokenized using the tokenizer corresponding to the base model 'meta-llama/Meta-Llama-3-8B'.\n- Hardware: The training was performed on GPUs with mixed precision (FP16/BF16) enabled.\n- Optimizer: Paged AdamW with a cosine learning rate schedule.\n- Epochs: The model was trained for 1 epoch.\n- Batch size: 4 per device, with gradient accumulation where required.",
"## Evaluation Results\nModel evaluation was based on qualitative assessment of generated text relevance and coherence in the context of cybersecurity.",
"## Quantization and Optimization\n- Quantization: 4-bit precision with type 'nf4'. Nested quantization is disabled.\n- Compute dtype: 'float16' to ensure efficient computation.\n- LoRA Settings:\n - LoRA attention dimension: '64'\n - Alpha parameter for LoRA scaling: '16'\n - Dropout in LoRA layers: '0.1'",
"## Environmental Impact\n- Compute Resources: Training leveraged energy-efficient hardware and practices to minimize carbon footprint.\n- Strategies: Gradient checkpointing and group-wise data processing were used to optimize memory and power usage.",
"## How to Use\nHere is how to load and use the model:",
"## Limitations and Bias\nThe model, while robust in cybersecurity contexts, may not generalize well to unrelated domains. Users should be cautious of biases inherent in the training data which may manifest in model predictions.\n\n\nIf you use this model, please cite it as follows:"
] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.