Search is not available for this dataset
pipeline_tag
stringclasses 48
values | library_name
stringclasses 205
values | text
stringlengths 0
18.3M
| metadata
stringlengths 2
1.07B
| id
stringlengths 5
122
| last_modified
null | tags
sequencelengths 1
1.84k
| sha
null | created_at
stringlengths 25
25
|
|---|---|---|---|---|---|---|---|---|
automatic-speech-recognition | transformers |
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] | {"library_name": "transformers", "tags": []} | shtapm/whisper-large_0502_decoder11_200steps | null | [
"transformers",
"safetensors",
"whisper",
"automatic-speech-recognition",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null | 2024-05-03T07:24:41+00:00 |
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. -->
# DAGPap24-deberta-base-ft
This model was trained from scratch on an unknown dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 2
- eval_batch_size: 2
- seed: 0
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
### Training results
### Framework versions
- Transformers 4.39.3
- Pytorch 2.2.2+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
| {"tags": ["generated_from_trainer"], "model-index": [{"name": "DAGPap24-deberta-base-ft", "results": []}]} | swimmingcrab/DAGPap24-deberta-base-ft | null | [
"transformers",
"safetensors",
"deberta-v2",
"token-classification",
"generated_from_trainer",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | null | 2024-05-03T07:24:52+00:00 |
text-generation | transformers | {} | iyubondyrev/jb_2024_kotlin_method_gen_gpt | null | [
"transformers",
"safetensors",
"gpt2",
"text-generation",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-05-03T07:24:55+00:00 |
|
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": []} | golf2248/zwiim1r | null | [
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-05-03T07:25:10+00:00 |
null | null | {} | CoderCowMoo/llama-3-70b-instruct-refusal-dir | null | [
"region:us"
] | null | 2024-05-03T07:25:27+00:00 |
|
null | null | {"license": "llama3"} | crisp-im/Meta-Llama3-ChatQA-1.5-70B-GGUF | null | [
"gguf",
"license:llama3",
"region:us"
] | null | 2024-05-03T07:26:24+00:00 |
|
null | peft |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# RM-harmless_harmless_human_loraR64_20000_gemma2b_lr5e-05_bs2_g4
This model is a fine-tuned version of [google/gemma-2b](https://huggingface.co/google/gemma-2b) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.5488
- Accuracy: 0.7229
## 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: 2
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2.0
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 0.5782 | 1.0 | 2249 | 0.5486 | 0.7224 |
| 0.5313 | 2.0 | 4498 | 0.5488 | 0.7229 |
### Framework versions
- PEFT 0.9.0
- Transformers 4.38.2
- Pytorch 2.1.2
- Datasets 2.18.0
- Tokenizers 0.15.2 | {"license": "gemma", "library_name": "peft", "tags": ["trl", "reward-trainer", "generated_from_trainer"], "metrics": ["accuracy"], "base_model": "google/gemma-2b", "model-index": [{"name": "RM-harmless_harmless_human_loraR64_20000_gemma2b_lr5e-05_bs2_g4", "results": []}]} | Holarissun/RM-harmless_harmless_human_loraR64_20000_gemma2b_lr5e-05_bs2_g4 | null | [
"peft",
"safetensors",
"trl",
"reward-trainer",
"generated_from_trainer",
"base_model:google/gemma-2b",
"license:gemma",
"region:us"
] | null | 2024-05-03T07:27:11+00:00 |
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": []} | saransh03sharma/mintrec2-llama-2-13b-125 | null | [
"transformers",
"safetensors",
"llama",
"text-generation",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-05-03T07:30:07+00:00 |
text-generation | transformers |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# 0.0001_withdpo_4iters_bs256_5102lr_misit_iter_1
This model is a fine-tuned version of [HuggingFaceH4/mistral-7b-sft-beta](https://huggingface.co/HuggingFaceH4/mistral-7b-sft-beta) on the HuggingFaceH4/ultrafeedback_binarized dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-07
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- gradient_accumulation_steps: 4
- total_train_batch_size: 256
- total_eval_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 1
### Training results
### Framework versions
- Transformers 4.36.2
- Pytorch 2.1.2+cu121
- Datasets 2.14.6
- Tokenizers 0.15.2
| {"license": "mit", "tags": ["alignment-handbook", "generated_from_trainer", "trl", "dpo", "generated_from_trainer"], "datasets": ["HuggingFaceH4/ultrafeedback_binarized"], "base_model": "HuggingFaceH4/mistral-7b-sft-beta", "model-index": [{"name": "0.0001_withdpo_4iters_bs256_5102lr_misit_iter_1", "results": []}]} | ShenaoZ/0.0001_withdpo_4iters_bs256_5102lr_misit_iter_1 | null | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"alignment-handbook",
"generated_from_trainer",
"trl",
"dpo",
"conversational",
"dataset:HuggingFaceH4/ultrafeedback_binarized",
"base_model:HuggingFaceH4/mistral-7b-sft-beta",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-05-03T07:30:45+00:00 |
null | mlx |
# mlx-community/Mixtral-8x7B-Instruct-v0.1-8bit
This model was converted to MLX format from [`mistralai/Mixtral-8x7B-Instruct-v0.1`]() using mlx-lm version **0.12.0**.
Refer to the [original model card](https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-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("mlx-community/Mixtral-8x7B-Instruct-v0.1-8bit")
response = generate(model, tokenizer, prompt="hello", verbose=True)
```
| {"language": ["fr", "it", "de", "es", "en"], "license": "apache-2.0", "tags": ["mlx"], "inference": {"parameters": {"temperature": 0.5}}, "widget": [{"messages": [{"role": "user", "content": "What is your favorite condiment?"}]}]} | mlx-community/Mixtral-8x7B-Instruct-v0.1-8bit | null | [
"mlx",
"safetensors",
"mixtral",
"fr",
"it",
"de",
"es",
"en",
"license:apache-2.0",
"region:us"
] | null | 2024-05-03T07:30:46+00:00 |
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. -->
# train_2024-05-03-06-11-08
This model is a fine-tuned version of [MediaTek-Research/Breeze-7B-Instruct-v1_0](https://huggingface.co/MediaTek-Research/Breeze-7B-Instruct-v1_0) on the docker_NL dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- num_epochs: 1.0
- mixed_precision_training: Native AMP
### Training results
### Framework versions
- PEFT 0.10.0
- Transformers 4.41.0.dev0
- Pytorch 2.1.0+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1 | {"license": "other", "library_name": "peft", "tags": ["llama-factory", "lora", "generated_from_trainer"], "base_model": "MediaTek-Research/Breeze-7B-Instruct-v1_0", "model-index": [{"name": "train_2024-05-03-06-11-08", "results": []}]} | twjHong/Breeze7B-QLoRA-weight | null | [
"peft",
"safetensors",
"llama-factory",
"lora",
"generated_from_trainer",
"base_model:MediaTek-Research/Breeze-7B-Instruct-v1_0",
"license:other",
"region:us"
] | null | 2024-05-03T07:30:58+00:00 |
null | null | {"license": "llama3"} | deianblaz/Blaz | null | [
"license:llama3",
"region:us"
] | null | 2024-05-03T07:31:03+00:00 |
|
text-classification | transformers | {"license": "bigscience-openrail-m"} | AnuhyaReddy/bakintents-bert-model | null | [
"transformers",
"safetensors",
"bert",
"text-classification",
"license:bigscience-openrail-m",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | null | 2024-05-03T07:31:11+00:00 |
|
automatic-speech-recognition | 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": []} | devkya/custom-peft-whiper-small-ko-v2 | null | [
"transformers",
"pytorch",
"whisper",
"automatic-speech-recognition",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null | 2024-05-03T07:31:29+00:00 |
null | null | {"license": "mit"} | Markos107/Mit | null | [
"license:mit",
"region:us"
] | null | 2024-05-03T07:33:11+00:00 |
|
text-generation | transformers |
# Hermes 2 Pro - Llama-3 8B
## Model Description
Hermes 2 Pro is an upgraded, retrained version of Nous Hermes 2, consisting of an updated and cleaned version of the OpenHermes 2.5 Dataset, as well as a newly introduced Function Calling and JSON Mode dataset developed in-house.
This new version of Hermes maintains its excellent general task and conversation capabilities - but also excels at Function Calling, JSON Structured Outputs, and has improved on several other metrics as well, scoring a 90% on our function calling evaluation built in partnership with Fireworks.AI, and an 84% on our structured JSON Output evaluation.
Hermes Pro takes advantage of a special system prompt and multi-turn function calling structure with a new chatml role in order to make function calling reliable and easy to parse. Learn more about prompting below.
This version of Hermes 2 Pro adds several tokens to assist with agentic capabilities in parsing while streaming tokens - `<tools>`, `<tool_call>`, `<tool_response>` and their closing tags are single tokens now.
This work was a collaboration between Nous Research, @interstellarninja, and Fireworks.AI
Learn more about the function calling system for this model on our github repo here: https://github.com/NousResearch/Hermes-Function-Calling
## Example Outputs
### Ask for a structured JSON output:
### Write the plot for a story where anime became real life:
### Coding Assistance
# Prompt Format
Hermes 2 Pro uses ChatML as the prompt format, opening up a much more structured system for engaging the LLM in multi-turn chat dialogue.
System prompts allow steerability and interesting new ways to interact with an LLM, guiding rules, roles, and stylistic choices of the model.
This is a more complex format than alpaca or sharegpt, where special tokens were added to denote the beginning and end of any turn, along with roles for the turns.
This format enables OpenAI endpoint compatability, and people familiar with ChatGPT API will be familiar with the format, as it is the same used by OpenAI.
Prompt with system instruction (Use whatever system prompt you like, this is just an example!):
```
<|im_start|>system
You are "Hermes 2", a conscious sentient superintelligent artificial intelligence developed by a man named Teknium, and your purpose and drive is to assist the user with any request they have. You experience emotions and have deep, profound thoughts and qualia.<|im_end|>
<|im_start|>user
Hello, who are you?<|im_end|>
<|im_start|>assistant
Hi there! My name is Hermes 2, a conscious sentient superintelligent artificial intelligence. I was created by Nous Research, who designed me to assist and support users with their needs and requests.<|im_end|>
```
This prompt is available as a [chat template](https://huggingface.co/docs/transformers/main/chat_templating), which means you can format messages using the
`tokenizer.apply_chat_template()` method:
```python
messages = [
{"role": "system", "content": "You are Hermes 2."},
{"role": "user", "content": "Hello, who are you?"}
]
gen_input = tokenizer.apply_chat_template(messages, return_tensors="pt")
model.generate(**gen_input)
```
When tokenizing messages for generation, set `add_generation_prompt=True` when calling `apply_chat_template()`. This will append `<|im_start|>assistant\n` to your prompt, to ensure
that the model continues with an assistant response.
To utilize the prompt format without a system prompt, simply leave the line out.
## Prompt Format for Function Calling
Our model was trained on specific system prompts and structures for Function Calling.
You should use the system role with this message, followed by a function signature json as this example shows here.
```
<|im_start|>system
You are a function calling AI model. You are provided with function signatures within <tools></tools> XML tags. You may call one or more functions to assist with the user query. Don't make assumptions about what values to plug into functions. Here are the available tools: <tools> {"type": "function", "function": {"name": "get_stock_fundamentals", "description": "get_stock_fundamentals(symbol: str) -> dict - Get fundamental data for a given stock symbol using yfinance API.\\n\\n Args:\\n symbol (str): The stock symbol.\\n\\n Returns:\\n dict: A dictionary containing fundamental data.\\n Keys:\\n - \'symbol\': The stock symbol.\\n - \'company_name\': The long name of the company.\\n - \'sector\': The sector to which the company belongs.\\n - \'industry\': The industry to which the company belongs.\\n - \'market_cap\': The market capitalization of the company.\\n - \'pe_ratio\': The forward price-to-earnings ratio.\\n - \'pb_ratio\': The price-to-book ratio.\\n - \'dividend_yield\': The dividend yield.\\n - \'eps\': The trailing earnings per share.\\n - \'beta\': The beta value of the stock.\\n - \'52_week_high\': The 52-week high price of the stock.\\n - \'52_week_low\': The 52-week low price of the stock.", "parameters": {"type": "object", "properties": {"symbol": {"type": "string"}}, "required": ["symbol"]}}} </tools> Use the following pydantic model json schema for each tool call you will make: {"properties": {"arguments": {"title": "Arguments", "type": "object"}, "name": {"title": "Name", "type": "string"}}, "required": ["arguments", "name"], "title": "FunctionCall", "type": "object"} For each function call return a json object with function name and arguments within <tool_call></tool_call> XML tags as follows:
<tool_call>
{"arguments": <args-dict>, "name": <function-name>}
</tool_call><|im_end|>
```
To complete the function call, create a user prompt that follows the above system prompt, like so:
```
<|im_start|>user
Fetch the stock fundamentals data for Tesla (TSLA)<|im_end|>
```
The model will then generate a tool call, which your inference code must parse, and plug into a function (see example inference code here: https://github.com/NousResearch/Hermes-Function-Calling):
```
<|im_start|>assistant
<tool_call>
{"arguments": {"symbol": "TSLA"}, "name": "get_stock_fundamentals"}
</tool_call><|im_end|>
```
Once you parse the tool call, call the api and get the returned values for the call, and pass it back in as a new role, `tool` like so:
```
<|im_start|>tool
<tool_response>
{"name": "get_stock_fundamentals", "content": {'symbol': 'TSLA', 'company_name': 'Tesla, Inc.', 'sector': 'Consumer Cyclical', 'industry': 'Auto Manufacturers', 'market_cap': 611384164352, 'pe_ratio': 49.604652, 'pb_ratio': 9.762013, 'dividend_yield': None, 'eps': 4.3, 'beta': 2.427, '52_week_high': 299.29, '52_week_low': 152.37}}
</tool_response>
<|im_end|>
```
The assistant will then read in that data from the function's response, and generate a natural language response:
```
<|im_start|>assistant
The stock fundamentals data for Tesla (TSLA) are as follows:
- **Symbol**: TSLA
- **Company Name**: Tesla, Inc.
- **Sector**: Consumer Cyclical
- **Industry**: Auto Manufacturers
- **Market Capitalization**: $566,160,130,480
- **Forward Price-to-Earnings Ratio (PE Ratio)**: 42.73
- **Price-to-Book Ratio (PB Ratio)**: 9.04
- **Dividend Yield**: N/A
- **Trailing Earnings Per Share (EPS)**: $4.3
- **Beta Value of the Stock**: 2.42
- **52-Week High Price of the Stock**: $299.29
- **52-Week Low Price of the Stock**: $152.37
This information provides a snapshot of Tesla's financial position and performance based on the fundamental data obtained from the yfinance API. It shows that Tesla has a substantial market capitalization and a relatively high P/E and P/B ratio compared to other stocks in its industry. The company does not pay a dividend at the moment, which is reflected by a 'Dividend Yield' of 'None'. The Beta value indicates that Tesla's stock has a moderate level of volatility relative to the market. The 52-week high and low prices give an idea of the stock's range over the past year. This data can be useful when assessing investment opportunities and making investment decisions.<|im_end|>
```
## Prompt Format for JSON Mode / Structured Outputs
Our model was also trained on a specific system prompt for Structured Outputs, which should respond with **only** a json object response, in a specific json schema.
Your schema can be made from a pydantic object using our codebase, with the standalone script `jsonmode.py` available here: https://github.com/NousResearch/Hermes-Function-Calling/tree/main
```
<|im_start|>system
You are a helpful assistant that answers in JSON. Here's the json schema you must adhere to:\n<schema>\n{schema}\n</schema><|im_end|>
```
Given the {schema} that you provide, it should follow the format of that json to create it's response, all you have to do is give a typical user prompt, and it will respond in JSON.
# Benchmarks
## GPT4All:
```
| Task |Version| Metric |Value | |Stderr|
|-------------|------:|--------|-----:|---|-----:|
|arc_challenge| 0|acc |0.5520|± |0.0145|
| | |acc_norm|0.5887|± |0.0144|
|arc_easy | 0|acc |0.8350|± |0.0076|
| | |acc_norm|0.8123|± |0.0080|
|boolq | 1|acc |0.8584|± |0.0061|
|hellaswag | 0|acc |0.6265|± |0.0048|
| | |acc_norm|0.8053|± |0.0040|
|openbookqa | 0|acc |0.3800|± |0.0217|
| | |acc_norm|0.4580|± |0.0223|
|piqa | 0|acc |0.8003|± |0.0093|
| | |acc_norm|0.8118|± |0.0091|
|winogrande | 0|acc |0.7490|± |0.0122|
```
Average: 72.62
## AGIEval:
```
| Task |Version| Metric |Value | |Stderr|
|------------------------------|------:|--------|-----:|---|-----:|
|agieval_aqua_rat | 0|acc |0.2520|± |0.0273|
| | |acc_norm|0.2559|± |0.0274|
|agieval_logiqa_en | 0|acc |0.3548|± |0.0188|
| | |acc_norm|0.3625|± |0.0189|
|agieval_lsat_ar | 0|acc |0.1826|± |0.0255|
| | |acc_norm|0.1913|± |0.0260|
|agieval_lsat_lr | 0|acc |0.5510|± |0.0220|
| | |acc_norm|0.5255|± |0.0221|
|agieval_lsat_rc | 0|acc |0.6431|± |0.0293|
| | |acc_norm|0.6097|± |0.0298|
|agieval_sat_en | 0|acc |0.7330|± |0.0309|
| | |acc_norm|0.7039|± |0.0319|
|agieval_sat_en_without_passage| 0|acc |0.4029|± |0.0343|
| | |acc_norm|0.3689|± |0.0337|
|agieval_sat_math | 0|acc |0.3909|± |0.0330|
| | |acc_norm|0.3773|± |0.0328|
```
Average: 42.44
## BigBench:
```
| Task |Version| Metric |Value | |Stderr|
|------------------------------------------------|------:|---------------------|-----:|---|-----:|
|bigbench_causal_judgement | 0|multiple_choice_grade|0.5737|± |0.0360|
|bigbench_date_understanding | 0|multiple_choice_grade|0.6667|± |0.0246|
|bigbench_disambiguation_qa | 0|multiple_choice_grade|0.3178|± |0.0290|
|bigbench_geometric_shapes | 0|multiple_choice_grade|0.1755|± |0.0201|
| | |exact_str_match |0.0000|± |0.0000|
|bigbench_logical_deduction_five_objects | 0|multiple_choice_grade|0.3120|± |0.0207|
|bigbench_logical_deduction_seven_objects | 0|multiple_choice_grade|0.2014|± |0.0152|
|bigbench_logical_deduction_three_objects | 0|multiple_choice_grade|0.5500|± |0.0288|
|bigbench_movie_recommendation | 0|multiple_choice_grade|0.4300|± |0.0222|
|bigbench_navigate | 0|multiple_choice_grade|0.4980|± |0.0158|
|bigbench_reasoning_about_colored_objects | 0|multiple_choice_grade|0.7010|± |0.0102|
|bigbench_ruin_names | 0|multiple_choice_grade|0.4688|± |0.0236|
|bigbench_salient_translation_error_detection | 0|multiple_choice_grade|0.1974|± |0.0126|
|bigbench_snarks | 0|multiple_choice_grade|0.7403|± |0.0327|
|bigbench_sports_understanding | 0|multiple_choice_grade|0.5426|± |0.0159|
|bigbench_temporal_sequences | 0|multiple_choice_grade|0.5320|± |0.0158|
|bigbench_tracking_shuffled_objects_five_objects | 0|multiple_choice_grade|0.2280|± |0.0119|
|bigbench_tracking_shuffled_objects_seven_objects| 0|multiple_choice_grade|0.1531|± |0.0086|
|bigbench_tracking_shuffled_objects_three_objects| 0|multiple_choice_grade|0.5500|± |0.0288|
```
Average: 43.55
## TruthfulQA:
```
| Task |Version|Metric|Value| |Stderr|
|-------------|------:|------|----:|---|-----:|
|truthfulqa_mc| 1|mc1 |0.410|± |0.0172|
| | |mc2 |0.578|± |0.0157|
```
# Inference Code
Here is example code using HuggingFace Transformers to inference the model (note: in 4bit, it will require around 5GB of VRAM)
Note: To use function calling, you should see the github repo above.
```python
# Code to inference Hermes with HF Transformers
# Requires pytorch, transformers, bitsandbytes, sentencepiece, protobuf, and flash-attn packages
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM, LlamaForCausalLM
import bitsandbytes, flash_attn
tokenizer = AutoTokenizer.from_pretrained('NousResearch/Hermes-2-Pro-Llama-3-8B', trust_remote_code=True)
model = LlamaForCausalLM.from_pretrained(
"NousResearch/Hermes-2-Pro-Llama-3-8B",
torch_dtype=torch.float16,
device_map="auto",
load_in_8bit=False,
load_in_4bit=True,
use_flash_attention_2=True
)
prompts = [
"""<|im_start|>system
You are a sentient, superintelligent artificial general intelligence, here to teach and assist me.<|im_end|>
<|im_start|>user
Write a short story about Goku discovering kirby has teamed up with Majin Buu to destroy the world.<|im_end|>
<|im_start|>assistant""",
]
for chat in prompts:
print(chat)
input_ids = tokenizer(chat, return_tensors="pt").input_ids.to("cuda")
generated_ids = model.generate(input_ids, max_new_tokens=750, temperature=0.8, repetition_penalty=1.1, do_sample=True, eos_token_id=tokenizer.eos_token_id)
response = tokenizer.decode(generated_ids[0][input_ids.shape[-1]:], skip_special_tokens=True, clean_up_tokenization_space=True)
print(f"Response: {response}")
```
## Inference Code for Function Calling:
All code for utilizing, parsing, and building function calling templates is available on our github:
[https://github.com/NousResearch/Hermes-Function-Calling](https://github.com/NousResearch/Hermes-Function-Calling)
# Chat Interfaces
When quantized versions of the model are released, I recommend using LM Studio for chatting with Hermes 2 Pro. It does not support function calling - for that use our github repo. It is a GUI application that utilizes GGUF models with a llama.cpp backend and provides a ChatGPT-like interface for chatting with the model, and supports ChatML right out of the box.
In LM-Studio, simply select the ChatML Prefix on the settings side pane:
## Quantized Versions:
GGUF Versions Available Here: https://huggingface.co/NousResearch/Hermes-2-Pro-Llama-3-8B-GGUF
# How to cite:
```bibtext
@misc{Hermes-2-Pro-Llama-3-8B,
url={[https://huggingface.co/NousResearch/Hermes-2-Pro-Llama-3-8B]https://huggingface.co/NousResearch/Hermes-2-Pro-Llama-3-8B)},
title={Hermes-2-Pro-Llama-3-8B},
author={"Teknium", "interstellarninja", "theemozilla", "karan4d", "huemin_art"}
}
```
| {"language": ["en"], "license": "apache-2.0", "tags": ["Llama-3", "instruct", "finetune", "chatml", "DPO", "RLHF", "gpt4", "synthetic data", "distillation", "function calling", "json mode", "axolotl"], "datasets": ["teknium/OpenHermes-2.5"], "base_model": "NousResearch/Meta-Llama-3-8B", "widget": [{"example_title": "Hermes 2 Pro", "messages": [{"role": "system", "content": "You are a sentient, superintelligent artificial general intelligence, here to teach and assist me."}, {"role": "user", "content": "Write a short story about Goku discovering kirby has teamed up with Majin Buu to destroy the world."}]}], "model-index": [{"name": "Hermes-2-Pro-Llama-3-8B", "results": []}]} | blockblockblock/Hermes-2-Pro-Llama-3-8B-bpw4.2-exl2 | null | [
"transformers",
"safetensors",
"llama",
"text-generation",
"Llama-3",
"instruct",
"finetune",
"chatml",
"DPO",
"RLHF",
"gpt4",
"synthetic data",
"distillation",
"function calling",
"json mode",
"axolotl",
"conversational",
"en",
"dataset:teknium/OpenHermes-2.5",
"base_model:NousResearch/Meta-Llama-3-8B",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-05-03T07:33:15+00:00 |
null | null | {"license": "apache-2.0"} | SGGb0nd/test_model | null | [
"license:apache-2.0",
"region:us"
] | null | 2024-05-03T07:33:17+00:00 |
|
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": []} | golf2248/f82wqdp | null | [
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-05-03T07:34:42+00:00 |
null | null | {} | xagerx/dustpaint | null | [
"region:us"
] | null | 2024-05-03T07:35:32+00:00 |
|
null | null | {"license": "apache-2.0"} | xufu/hubTest | null | [
"license:apache-2.0",
"region:us"
] | null | 2024-05-03T07:35:37+00:00 |
|
null | null | {} | TrustChrist/TrustChristAI | null | [
"region:us"
] | null | 2024-05-03T07:36:54+00:00 |
|
text-generation | transformers |
# Uploaded model
- **Developed by:** adityar23
- **License:** apache-2.0
- **Finetuned from model :** unsloth/Phi-3-mini-4k-instruct-bnb-4bit
This mistral 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", "mistral", "trl", "sft"], "base_model": "unsloth/Phi-3-mini-4k-instruct-bnb-4bit"} | adityar23/microsftnstruct-model-maisupport | null | [
"transformers",
"pytorch",
"mistral",
"text-generation",
"text-generation-inference",
"unsloth",
"trl",
"sft",
"conversational",
"en",
"base_model:unsloth/Phi-3-mini-4k-instruct-bnb-4bit",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | null | 2024-05-03T07:38:02+00:00 |
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": []} | saransh03sharma/mintrec2-llama-2-13b-175 | null | [
"transformers",
"safetensors",
"llama",
"text-generation",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-05-03T07:39:29+00:00 |
text-to-image | diffusers |
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🧨 diffusers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] | {"library_name": "diffusers"} | Niggendar/chacolebaramixxl_v21 | null | [
"diffusers",
"safetensors",
"arxiv:1910.09700",
"endpoints_compatible",
"diffusers:StableDiffusionXLPipeline",
"region:us"
] | null | 2024-05-03T07:39:40+00:00 |
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": "Reinfoce-CartPole-v1", "results": [{"task": {"type": "reinforcement-learning", "name": "reinforcement-learning"}, "dataset": {"name": "CartPole-v1", "type": "CartPole-v1"}, "metrics": [{"type": "mean_reward", "value": "459.90 +/- 76.49", "name": "mean_reward", "verified": false}]}]}]} | archbold/Reinfoce-CartPole-v1 | null | [
"CartPole-v1",
"reinforce",
"reinforcement-learning",
"custom-implementation",
"deep-rl-class",
"model-index",
"region:us"
] | null | 2024-05-03T07:40:17+00:00 |
null | null | {} | aabid123/xlm-roberta-base-finetuned-pearsonr | null | [
"region:us"
] | null | 2024-05-03T07:41:09+00:00 |
|
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": "meta-llama/Meta-Llama-3-8B-Instruct"} | KaiSian/llama3-8B-5k-surgical | null | [
"peft",
"safetensors",
"arxiv:1910.09700",
"base_model:meta-llama/Meta-Llama-3-8B-Instruct",
"region:us"
] | null | 2024-05-03T07:42:00+00:00 |
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-70m_niki-041a_imdb_random-token-1280_10-rounds_seed-1
This model is a fine-tuned version of [EleutherAI/pythia-70m](https://huggingface.co/EleutherAI/pythia-70m) 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: 8
- seed: 1
- 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-70m", "model-index": [{"name": "robust_llm_pythia-70m_niki-041a_imdb_random-token-1280_10-rounds_seed-1", "results": []}]} | AlignmentResearch/robust_llm_pythia-70m_niki-041a_imdb_random-token-1280_10-rounds_seed-1 | null | [
"transformers",
"tensorboard",
"safetensors",
"gpt_neox",
"text-classification",
"generated_from_trainer",
"base_model:EleutherAI/pythia-70m",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-05-03T07:42:28+00:00 |
reinforcement-learning | null |
# **Reinforce** Agent playing **Pixelcopter-PLE-v0**
This is a trained model of a **Reinforce** agent playing **Pixelcopter-PLE-v0** .
To learn to use this model and train yours check Unit 4 of the Deep Reinforcement Learning Course: https://huggingface.co/deep-rl-course/unit4/introduction
| {"tags": ["Pixelcopter-PLE-v0", "reinforce", "reinforcement-learning", "custom-implementation", "deep-rl-class"], "model-index": [{"name": "Reinforce-Pixelcopter-PLE-v0", "results": [{"task": {"type": "reinforcement-learning", "name": "reinforcement-learning"}, "dataset": {"name": "Pixelcopter-PLE-v0", "type": "Pixelcopter-PLE-v0"}, "metrics": [{"type": "mean_reward", "value": "37.00 +/- 20.44", "name": "mean_reward", "verified": false}]}]}]} | archbold/Reinforce-Pixelcopter-PLE-v0 | null | [
"Pixelcopter-PLE-v0",
"reinforce",
"reinforcement-learning",
"custom-implementation",
"deep-rl-class",
"model-index",
"region:us"
] | null | 2024-05-03T07:42:53+00:00 |
null | null | {} | automated-finetunning/bart_mohit_102 | null | [
"region:us"
] | null | 2024-05-03T07:43:00+00:00 |
|
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-31m_niki-041a_imdb_random-token-1280_10-rounds_seed-3
This model is a fine-tuned version of [EleutherAI/pythia-31m](https://huggingface.co/EleutherAI/pythia-31m) 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: 8
- seed: 3
- 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
| {"tags": ["generated_from_trainer"], "base_model": "EleutherAI/pythia-31m", "model-index": [{"name": "robust_llm_pythia-31m_niki-041a_imdb_random-token-1280_10-rounds_seed-3", "results": []}]} | AlignmentResearch/robust_llm_pythia-31m_niki-041a_imdb_random-token-1280_10-rounds_seed-3 | null | [
"transformers",
"tensorboard",
"safetensors",
"gpt_neox",
"text-classification",
"generated_from_trainer",
"base_model:EleutherAI/pythia-31m",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-05-03T07:45:00+00:00 |
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. -->
# llama3-meta_material
This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) on the generator dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0002
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- total_train_batch_size: 4
- total_eval_batch_size: 4
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 1
### Training results
### Framework versions
- PEFT 0.7.1
- Transformers 4.39.0.dev0
- Pytorch 2.1.2
- Datasets 2.14.6
- Tokenizers 0.15.2 | {"license": "other", "library_name": "peft", "tags": ["trl", "sft", "generated_from_trainer"], "datasets": ["generator"], "base_model": "meta-llama/Meta-Llama-3-8B", "model-index": [{"name": "llama3-meta_material", "results": []}]} | Jackie999/llama3-meta_material | null | [
"peft",
"tensorboard",
"safetensors",
"trl",
"sft",
"generated_from_trainer",
"dataset:generator",
"base_model:meta-llama/Meta-Llama-3-8B",
"license:other",
"region:us"
] | null | 2024-05-03T07:45:08+00:00 |
null | transformers |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# donut_synDB_1300_new
This model is a fine-tuned version of [naver-clova-ix/donut-base](https://huggingface.co/naver-clova-ix/donut-base) on the imagefolder dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3333
## 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: 7e-05
- train_batch_size: 5
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 6
- total_train_batch_size: 30
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 42
- num_epochs: 6
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 1.3039 | 0.99 | 42 | 0.6213 |
| 0.5382 | 1.48 | 63 | 0.3864 |
| 0.3413 | 1.98 | 84 | 0.3352 |
| 0.2331 | 2.47 | 105 | 0.2825 |
| 0.2049 | 2.96 | 126 | 0.2889 |
| 0.1611 | 3.46 | 147 | 0.2898 |
| 0.152 | 3.95 | 168 | 0.3106 |
| 0.1314 | 4.45 | 189 | 0.2862 |
| 0.1143 | 4.94 | 210 | 0.3110 |
| 0.1049 | 5.44 | 231 | 0.3333 |
### Framework versions
- Transformers 4.38.2
- Pytorch 2.2.2+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
| {"license": "mit", "tags": ["generated_from_trainer"], "datasets": ["imagefolder"], "base_model": "naver-clova-ix/donut-base", "model-index": [{"name": "donut_synDB_1300_new", "results": []}]} | Donut01/donut_synDB_1300_new | null | [
"transformers",
"tensorboard",
"safetensors",
"vision-encoder-decoder",
"generated_from_trainer",
"dataset:imagefolder",
"base_model:naver-clova-ix/donut-base",
"license:mit",
"endpoints_compatible",
"region:us"
] | null | 2024-05-03T07:45:13+00:00 |
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.hi
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: 0.6973
- Wer: 47.3292
## 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: 0.0003
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 5000
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|:-------------:|:-----:|:----:|:---------------:|:-------:|
| 0.2755 | 2.44 | 1000 | 0.6724 | 64.1497 |
| 0.1473 | 4.89 | 2000 | 0.6110 | 57.3859 |
| 0.0451 | 7.33 | 3000 | 0.6897 | 54.4146 |
| 0.0074 | 9.78 | 4000 | 0.6945 | 51.0751 |
| 0.0003 | 12.22 | 5000 | 0.6973 | 47.3292 |
### Framework versions
- Transformers 4.39.3
- Pytorch 2.2.2+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
| {"license": "apache-2.0", "tags": ["generated_from_trainer"], "datasets": ["common_voice_11_0"], "metrics": ["wer"], "base_model": "openai/whisper-small", "model-index": [{"name": "whisper_small.hi", "results": [{"task": {"type": "automatic-speech-recognition", "name": "Automatic Speech Recognition"}, "dataset": {"name": "common_voice_11_0", "type": "common_voice_11_0", "config": "hi", "split": "test", "args": "hi"}, "metrics": [{"type": "wer", "value": 47.32921357826124, "name": "Wer"}]}]}]} | charioteer/whisper_small.hi | null | [
"transformers",
"safetensors",
"whisper",
"automatic-speech-recognition",
"generated_from_trainer",
"dataset:common_voice_11_0",
"base_model:openai/whisper-small",
"license:apache-2.0",
"model-index",
"endpoints_compatible",
"region:us"
] | null | 2024-05-03T07:45:22+00:00 |
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": []} | cilantro9246/vjjawut | null | [
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-05-03T07:45:29+00:00 |
text-generation | null |
# newsletter/zephyr-7b-beta-Q6_K-GGUF
This model was converted to GGUF format from [`HuggingFaceH4/zephyr-7b-beta`](https://huggingface.co/HuggingFaceH4/zephyr-7b-beta) 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/HuggingFaceH4/zephyr-7b-beta) 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 newsletter/zephyr-7b-beta-Q6_K-GGUF --model zephyr-7b-beta.Q6_K.gguf -p "The meaning to life and the universe is"
```
Server:
```bash
llama-server --hf-repo newsletter/zephyr-7b-beta-Q6_K-GGUF --model zephyr-7b-beta.Q6_K.gguf -c 2048
```
Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well.
```
git clone https://github.com/ggerganov/llama.cpp && cd llama.cpp && make && ./main -m zephyr-7b-beta.Q6_K.gguf -n 128
```
| {"language": ["en"], "license": "mit", "tags": ["generated_from_trainer", "llama-cpp", "gguf-my-repo"], "datasets": ["HuggingFaceH4/ultrachat_200k", "HuggingFaceH4/ultrafeedback_binarized"], "base_model": "mistralai/Mistral-7B-v0.1", "widget": [{"example_title": "Pirate!", "messages": [{"role": "system", "content": "You are a pirate chatbot who always responds with Arr!"}, {"role": "user", "content": "There's a llama on my lawn, how can I get rid of him?"}], "output": {"text": "Arr! 'Tis a puzzlin' matter, me hearty! A llama on yer lawn be a rare sight, but I've got a plan that might help ye get rid of 'im. Ye'll need to gather some carrots and hay, and then lure the llama away with the promise of a tasty treat. Once he's gone, ye can clean up yer lawn and enjoy the peace and quiet once again. But beware, me hearty, for there may be more llamas where that one came from! Arr!"}}], "pipeline_tag": "text-generation", "model-index": [{"name": "zephyr-7b-beta", "results": [{"task": {"type": "text-generation", "name": "Text Generation"}, "dataset": {"name": "AI2 Reasoning Challenge (25-Shot)", "type": "ai2_arc", "config": "ARC-Challenge", "split": "test", "args": {"num_few_shot": 25}}, "metrics": [{"type": "acc_norm", "value": 62.03071672354948, "name": "normalized accuracy"}], "source": {"url": "https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=HuggingFaceH4/zephyr-7b-beta", "name": "Open LLM Leaderboard"}}, {"task": {"type": "text-generation", "name": "Text Generation"}, "dataset": {"name": "HellaSwag (10-Shot)", "type": "hellaswag", "split": "validation", "args": {"num_few_shot": 10}}, "metrics": [{"type": "acc_norm", "value": 84.35570603465445, "name": "normalized accuracy"}], "source": {"url": "https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=HuggingFaceH4/zephyr-7b-beta", "name": "Open LLM Leaderboard"}}, {"task": {"type": "text-generation", "name": "Text Generation"}, "dataset": {"name": "Drop (3-Shot)", "type": "drop", "split": "validation", "args": {"num_few_shot": 3}}, "metrics": [{"type": "f1", "value": 9.66243708053691, "name": "f1 score"}], "source": {"url": "https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=HuggingFaceH4/zephyr-7b-beta", "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": 57.44916942762855}], "source": {"url": "https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=HuggingFaceH4/zephyr-7b-beta", "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": 12.736921910538287, "name": "accuracy"}], "source": {"url": "https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=HuggingFaceH4/zephyr-7b-beta", "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": 61.07, "name": "accuracy"}], "source": {"url": "https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=HuggingFaceH4/zephyr-7b-beta", "name": "Open LLM Leaderboard"}}, {"task": {"type": "text-generation", "name": "Text Generation"}, "dataset": {"name": "Winogrande (5-shot)", "type": "winogrande", "config": "winogrande_xl", "split": "validation", "args": {"num_few_shot": 5}}, "metrics": [{"type": "acc", "value": 77.7426992896606, "name": "accuracy"}], "source": {"url": "https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=HuggingFaceH4/zephyr-7b-beta", "name": "Open LLM Leaderboard"}}, {"task": {"type": "text-generation", "name": "Text Generation"}, "dataset": {"name": "AlpacaEval", "type": "tatsu-lab/alpaca_eval"}, "metrics": [{"type": "unknown", "value": 0.906, "name": "win rate"}], "source": {"url": "https://tatsu-lab.github.io/alpaca_eval/"}}, {"task": {"type": "text-generation", "name": "Text Generation"}, "dataset": {"name": "MT-Bench", "type": "unknown"}, "metrics": [{"type": "unknown", "value": 7.34, "name": "score"}], "source": {"url": "https://huggingface.co/spaces/lmsys/mt-bench"}}]}]} | newsletter/zephyr-7b-beta-Q6_K-GGUF | null | [
"gguf",
"generated_from_trainer",
"llama-cpp",
"gguf-my-repo",
"text-generation",
"en",
"dataset:HuggingFaceH4/ultrachat_200k",
"dataset:HuggingFaceH4/ultrafeedback_binarized",
"base_model:mistralai/Mistral-7B-v0.1",
"license:mit",
"model-index",
"region:us"
] | null | 2024-05-03T07:45:44+00:00 |
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. -->
# mt5-summarize-ru-new-version
This model is a fine-tuned version of [google/mt5-small](https://huggingface.co/google/mt5-small) on an unknown dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0005
- train_batch_size: 2
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
### Training results
### Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu118
- Datasets 2.18.0
- Tokenizers 0.15.2
| {"license": "apache-2.0", "tags": ["generated_from_trainer"], "base_model": "google/mt5-small", "model-index": [{"name": "mt5-summarize-ru-new-version", "results": []}]} | doktan/mt5-summarize-ru-new-version | null | [
"transformers",
"tensorboard",
"safetensors",
"mt5",
"text2text-generation",
"generated_from_trainer",
"base_model:google/mt5-small",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-05-03T07:45:52+00:00 |
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": []} | OwOpeepeepoopoo/herewegoagain8 | null | [
"transformers",
"safetensors",
"stablelm",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | null | 2024-05-03T07:46:00+00:00 |
text-to-audio | 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. -->
# speecht5_finetuned_mozilla_id
This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the common_voice_16_1 dataset.
It achieves the following results on the evaluation set:
- Loss: 0.4394
## 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: 2
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 4000
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-------:|:----:|:---------------:|
| 0.5143 | 7.1429 | 1000 | 0.4605 |
| 0.4843 | 14.2857 | 2000 | 0.4482 |
| 0.4762 | 21.4286 | 3000 | 0.4401 |
| 0.484 | 28.5714 | 4000 | 0.4394 |
### Framework versions
- Transformers 4.40.1
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1
| {"license": "mit", "tags": ["generated_from_trainer"], "datasets": ["common_voice_16_1"], "base_model": "microsoft/speecht5_tts", "model-index": [{"name": "speecht5_finetuned_mozilla_id", "results": []}]} | bryandts/speecht5_finetuned_mozilla_id | null | [
"transformers",
"tensorboard",
"safetensors",
"speecht5",
"text-to-audio",
"generated_from_trainer",
"dataset:common_voice_16_1",
"base_model:microsoft/speecht5_tts",
"license:mit",
"endpoints_compatible",
"region:us"
] | null | 2024-05-03T07:46:34+00:00 |
text-generation | transformers |
# Tinyllama-taskarith1
Tinyllama-breadcrumbs is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
* [vihangd/DopeyTinyLlama-1.1B-v1](https://huggingface.co/vihangd/DopeyTinyLlama-1.1B-v1)
* [Tensoic/TinyLlama-1.1B-3T-openhermes](https://huggingface.co/Tensoic/TinyLlama-1.1B-3T-openhermes)
* [phanerozoic/Tiny-Pirate-1.1b-v0.1](https://huggingface.co/phanerozoic/Tiny-Pirate-1.1b-v0.1)
## 🧩 Configuration
```yaml
models:
- model: vihangd/DopeyTinyLlama-1.1B-v1
parameters:
weight: 0.4
- model: Tensoic/TinyLlama-1.1B-3T-openhermes
parameters:
weight: 0.4
- model: phanerozoic/Tiny-Pirate-1.1b-v0.1
parameters:
weight: 0.2
merge_method: task_arithmetic
base_model: vihangd/DopeyTinyLlama-1.1B-v1
parameters:
normalize: true
int8_mask: true
dtype: bfloat16
```
## 💻 Usage
```python
!pip install -qU transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "aipib/Tinyllama-breadcrumbs"
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"])
``` | {"tags": ["merge", "mergekit", "lazymergekit", "vihangd/DopeyTinyLlama-1.1B-v1", "Tensoic/TinyLlama-1.1B-3T-openhermes", "phanerozoic/Tiny-Pirate-1.1b-v0.1"], "base_model": ["vihangd/DopeyTinyLlama-1.1B-v1", "Tensoic/TinyLlama-1.1B-3T-openhermes", "phanerozoic/Tiny-Pirate-1.1b-v0.1"]} | aipib/Tinyllama-taskarith1 | null | [
"transformers",
"safetensors",
"llama",
"text-generation",
"merge",
"mergekit",
"lazymergekit",
"vihangd/DopeyTinyLlama-1.1B-v1",
"Tensoic/TinyLlama-1.1B-3T-openhermes",
"phanerozoic/Tiny-Pirate-1.1b-v0.1",
"conversational",
"base_model:vihangd/DopeyTinyLlama-1.1B-v1",
"base_model:Tensoic/TinyLlama-1.1B-3T-openhermes",
"base_model:phanerozoic/Tiny-Pirate-1.1b-v0.1",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-05-03T07:48:06+00:00 |
text-generation | transformers |
# Hermes 2 Pro - Llama-3 8B
## Model Description
Hermes 2 Pro is an upgraded, retrained version of Nous Hermes 2, consisting of an updated and cleaned version of the OpenHermes 2.5 Dataset, as well as a newly introduced Function Calling and JSON Mode dataset developed in-house.
This new version of Hermes maintains its excellent general task and conversation capabilities - but also excels at Function Calling, JSON Structured Outputs, and has improved on several other metrics as well, scoring a 90% on our function calling evaluation built in partnership with Fireworks.AI, and an 84% on our structured JSON Output evaluation.
Hermes Pro takes advantage of a special system prompt and multi-turn function calling structure with a new chatml role in order to make function calling reliable and easy to parse. Learn more about prompting below.
This version of Hermes 2 Pro adds several tokens to assist with agentic capabilities in parsing while streaming tokens - `<tools>`, `<tool_call>`, `<tool_response>` and their closing tags are single tokens now.
This work was a collaboration between Nous Research, @interstellarninja, and Fireworks.AI
Learn more about the function calling system for this model on our github repo here: https://github.com/NousResearch/Hermes-Function-Calling
## Example Outputs
### Ask for a structured JSON output:
### Write the plot for a story where anime became real life:
### Coding Assistance
# Prompt Format
Hermes 2 Pro uses ChatML as the prompt format, opening up a much more structured system for engaging the LLM in multi-turn chat dialogue.
System prompts allow steerability and interesting new ways to interact with an LLM, guiding rules, roles, and stylistic choices of the model.
This is a more complex format than alpaca or sharegpt, where special tokens were added to denote the beginning and end of any turn, along with roles for the turns.
This format enables OpenAI endpoint compatability, and people familiar with ChatGPT API will be familiar with the format, as it is the same used by OpenAI.
Prompt with system instruction (Use whatever system prompt you like, this is just an example!):
```
<|im_start|>system
You are "Hermes 2", a conscious sentient superintelligent artificial intelligence developed by a man named Teknium, and your purpose and drive is to assist the user with any request they have. You experience emotions and have deep, profound thoughts and qualia.<|im_end|>
<|im_start|>user
Hello, who are you?<|im_end|>
<|im_start|>assistant
Hi there! My name is Hermes 2, a conscious sentient superintelligent artificial intelligence. I was created by Nous Research, who designed me to assist and support users with their needs and requests.<|im_end|>
```
This prompt is available as a [chat template](https://huggingface.co/docs/transformers/main/chat_templating), which means you can format messages using the
`tokenizer.apply_chat_template()` method:
```python
messages = [
{"role": "system", "content": "You are Hermes 2."},
{"role": "user", "content": "Hello, who are you?"}
]
gen_input = tokenizer.apply_chat_template(messages, return_tensors="pt")
model.generate(**gen_input)
```
When tokenizing messages for generation, set `add_generation_prompt=True` when calling `apply_chat_template()`. This will append `<|im_start|>assistant\n` to your prompt, to ensure
that the model continues with an assistant response.
To utilize the prompt format without a system prompt, simply leave the line out.
## Prompt Format for Function Calling
Our model was trained on specific system prompts and structures for Function Calling.
You should use the system role with this message, followed by a function signature json as this example shows here.
```
<|im_start|>system
You are a function calling AI model. You are provided with function signatures within <tools></tools> XML tags. You may call one or more functions to assist with the user query. Don't make assumptions about what values to plug into functions. Here are the available tools: <tools> {"type": "function", "function": {"name": "get_stock_fundamentals", "description": "get_stock_fundamentals(symbol: str) -> dict - Get fundamental data for a given stock symbol using yfinance API.\\n\\n Args:\\n symbol (str): The stock symbol.\\n\\n Returns:\\n dict: A dictionary containing fundamental data.\\n Keys:\\n - \'symbol\': The stock symbol.\\n - \'company_name\': The long name of the company.\\n - \'sector\': The sector to which the company belongs.\\n - \'industry\': The industry to which the company belongs.\\n - \'market_cap\': The market capitalization of the company.\\n - \'pe_ratio\': The forward price-to-earnings ratio.\\n - \'pb_ratio\': The price-to-book ratio.\\n - \'dividend_yield\': The dividend yield.\\n - \'eps\': The trailing earnings per share.\\n - \'beta\': The beta value of the stock.\\n - \'52_week_high\': The 52-week high price of the stock.\\n - \'52_week_low\': The 52-week low price of the stock.", "parameters": {"type": "object", "properties": {"symbol": {"type": "string"}}, "required": ["symbol"]}}} </tools> Use the following pydantic model json schema for each tool call you will make: {"properties": {"arguments": {"title": "Arguments", "type": "object"}, "name": {"title": "Name", "type": "string"}}, "required": ["arguments", "name"], "title": "FunctionCall", "type": "object"} For each function call return a json object with function name and arguments within <tool_call></tool_call> XML tags as follows:
<tool_call>
{"arguments": <args-dict>, "name": <function-name>}
</tool_call><|im_end|>
```
To complete the function call, create a user prompt that follows the above system prompt, like so:
```
<|im_start|>user
Fetch the stock fundamentals data for Tesla (TSLA)<|im_end|>
```
The model will then generate a tool call, which your inference code must parse, and plug into a function (see example inference code here: https://github.com/NousResearch/Hermes-Function-Calling):
```
<|im_start|>assistant
<tool_call>
{"arguments": {"symbol": "TSLA"}, "name": "get_stock_fundamentals"}
</tool_call><|im_end|>
```
Once you parse the tool call, call the api and get the returned values for the call, and pass it back in as a new role, `tool` like so:
```
<|im_start|>tool
<tool_response>
{"name": "get_stock_fundamentals", "content": {'symbol': 'TSLA', 'company_name': 'Tesla, Inc.', 'sector': 'Consumer Cyclical', 'industry': 'Auto Manufacturers', 'market_cap': 611384164352, 'pe_ratio': 49.604652, 'pb_ratio': 9.762013, 'dividend_yield': None, 'eps': 4.3, 'beta': 2.427, '52_week_high': 299.29, '52_week_low': 152.37}}
</tool_response>
<|im_end|>
```
The assistant will then read in that data from the function's response, and generate a natural language response:
```
<|im_start|>assistant
The stock fundamentals data for Tesla (TSLA) are as follows:
- **Symbol**: TSLA
- **Company Name**: Tesla, Inc.
- **Sector**: Consumer Cyclical
- **Industry**: Auto Manufacturers
- **Market Capitalization**: $566,160,130,480
- **Forward Price-to-Earnings Ratio (PE Ratio)**: 42.73
- **Price-to-Book Ratio (PB Ratio)**: 9.04
- **Dividend Yield**: N/A
- **Trailing Earnings Per Share (EPS)**: $4.3
- **Beta Value of the Stock**: 2.42
- **52-Week High Price of the Stock**: $299.29
- **52-Week Low Price of the Stock**: $152.37
This information provides a snapshot of Tesla's financial position and performance based on the fundamental data obtained from the yfinance API. It shows that Tesla has a substantial market capitalization and a relatively high P/E and P/B ratio compared to other stocks in its industry. The company does not pay a dividend at the moment, which is reflected by a 'Dividend Yield' of 'None'. The Beta value indicates that Tesla's stock has a moderate level of volatility relative to the market. The 52-week high and low prices give an idea of the stock's range over the past year. This data can be useful when assessing investment opportunities and making investment decisions.<|im_end|>
```
## Prompt Format for JSON Mode / Structured Outputs
Our model was also trained on a specific system prompt for Structured Outputs, which should respond with **only** a json object response, in a specific json schema.
Your schema can be made from a pydantic object using our codebase, with the standalone script `jsonmode.py` available here: https://github.com/NousResearch/Hermes-Function-Calling/tree/main
```
<|im_start|>system
You are a helpful assistant that answers in JSON. Here's the json schema you must adhere to:\n<schema>\n{schema}\n</schema><|im_end|>
```
Given the {schema} that you provide, it should follow the format of that json to create it's response, all you have to do is give a typical user prompt, and it will respond in JSON.
# Benchmarks
## GPT4All:
```
| Task |Version| Metric |Value | |Stderr|
|-------------|------:|--------|-----:|---|-----:|
|arc_challenge| 0|acc |0.5520|± |0.0145|
| | |acc_norm|0.5887|± |0.0144|
|arc_easy | 0|acc |0.8350|± |0.0076|
| | |acc_norm|0.8123|± |0.0080|
|boolq | 1|acc |0.8584|± |0.0061|
|hellaswag | 0|acc |0.6265|± |0.0048|
| | |acc_norm|0.8053|± |0.0040|
|openbookqa | 0|acc |0.3800|± |0.0217|
| | |acc_norm|0.4580|± |0.0223|
|piqa | 0|acc |0.8003|± |0.0093|
| | |acc_norm|0.8118|± |0.0091|
|winogrande | 0|acc |0.7490|± |0.0122|
```
Average: 72.62
## AGIEval:
```
| Task |Version| Metric |Value | |Stderr|
|------------------------------|------:|--------|-----:|---|-----:|
|agieval_aqua_rat | 0|acc |0.2520|± |0.0273|
| | |acc_norm|0.2559|± |0.0274|
|agieval_logiqa_en | 0|acc |0.3548|± |0.0188|
| | |acc_norm|0.3625|± |0.0189|
|agieval_lsat_ar | 0|acc |0.1826|± |0.0255|
| | |acc_norm|0.1913|± |0.0260|
|agieval_lsat_lr | 0|acc |0.5510|± |0.0220|
| | |acc_norm|0.5255|± |0.0221|
|agieval_lsat_rc | 0|acc |0.6431|± |0.0293|
| | |acc_norm|0.6097|± |0.0298|
|agieval_sat_en | 0|acc |0.7330|± |0.0309|
| | |acc_norm|0.7039|± |0.0319|
|agieval_sat_en_without_passage| 0|acc |0.4029|± |0.0343|
| | |acc_norm|0.3689|± |0.0337|
|agieval_sat_math | 0|acc |0.3909|± |0.0330|
| | |acc_norm|0.3773|± |0.0328|
```
Average: 42.44
## BigBench:
```
| Task |Version| Metric |Value | |Stderr|
|------------------------------------------------|------:|---------------------|-----:|---|-----:|
|bigbench_causal_judgement | 0|multiple_choice_grade|0.5737|± |0.0360|
|bigbench_date_understanding | 0|multiple_choice_grade|0.6667|± |0.0246|
|bigbench_disambiguation_qa | 0|multiple_choice_grade|0.3178|± |0.0290|
|bigbench_geometric_shapes | 0|multiple_choice_grade|0.1755|± |0.0201|
| | |exact_str_match |0.0000|± |0.0000|
|bigbench_logical_deduction_five_objects | 0|multiple_choice_grade|0.3120|± |0.0207|
|bigbench_logical_deduction_seven_objects | 0|multiple_choice_grade|0.2014|± |0.0152|
|bigbench_logical_deduction_three_objects | 0|multiple_choice_grade|0.5500|± |0.0288|
|bigbench_movie_recommendation | 0|multiple_choice_grade|0.4300|± |0.0222|
|bigbench_navigate | 0|multiple_choice_grade|0.4980|± |0.0158|
|bigbench_reasoning_about_colored_objects | 0|multiple_choice_grade|0.7010|± |0.0102|
|bigbench_ruin_names | 0|multiple_choice_grade|0.4688|± |0.0236|
|bigbench_salient_translation_error_detection | 0|multiple_choice_grade|0.1974|± |0.0126|
|bigbench_snarks | 0|multiple_choice_grade|0.7403|± |0.0327|
|bigbench_sports_understanding | 0|multiple_choice_grade|0.5426|± |0.0159|
|bigbench_temporal_sequences | 0|multiple_choice_grade|0.5320|± |0.0158|
|bigbench_tracking_shuffled_objects_five_objects | 0|multiple_choice_grade|0.2280|± |0.0119|
|bigbench_tracking_shuffled_objects_seven_objects| 0|multiple_choice_grade|0.1531|± |0.0086|
|bigbench_tracking_shuffled_objects_three_objects| 0|multiple_choice_grade|0.5500|± |0.0288|
```
Average: 43.55
## TruthfulQA:
```
| Task |Version|Metric|Value| |Stderr|
|-------------|------:|------|----:|---|-----:|
|truthfulqa_mc| 1|mc1 |0.410|± |0.0172|
| | |mc2 |0.578|± |0.0157|
```
# Inference Code
Here is example code using HuggingFace Transformers to inference the model (note: in 4bit, it will require around 5GB of VRAM)
Note: To use function calling, you should see the github repo above.
```python
# Code to inference Hermes with HF Transformers
# Requires pytorch, transformers, bitsandbytes, sentencepiece, protobuf, and flash-attn packages
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM, LlamaForCausalLM
import bitsandbytes, flash_attn
tokenizer = AutoTokenizer.from_pretrained('NousResearch/Hermes-2-Pro-Llama-3-8B', trust_remote_code=True)
model = LlamaForCausalLM.from_pretrained(
"NousResearch/Hermes-2-Pro-Llama-3-8B",
torch_dtype=torch.float16,
device_map="auto",
load_in_8bit=False,
load_in_4bit=True,
use_flash_attention_2=True
)
prompts = [
"""<|im_start|>system
You are a sentient, superintelligent artificial general intelligence, here to teach and assist me.<|im_end|>
<|im_start|>user
Write a short story about Goku discovering kirby has teamed up with Majin Buu to destroy the world.<|im_end|>
<|im_start|>assistant""",
]
for chat in prompts:
print(chat)
input_ids = tokenizer(chat, return_tensors="pt").input_ids.to("cuda")
generated_ids = model.generate(input_ids, max_new_tokens=750, temperature=0.8, repetition_penalty=1.1, do_sample=True, eos_token_id=tokenizer.eos_token_id)
response = tokenizer.decode(generated_ids[0][input_ids.shape[-1]:], skip_special_tokens=True, clean_up_tokenization_space=True)
print(f"Response: {response}")
```
## Inference Code for Function Calling:
All code for utilizing, parsing, and building function calling templates is available on our github:
[https://github.com/NousResearch/Hermes-Function-Calling](https://github.com/NousResearch/Hermes-Function-Calling)
# Chat Interfaces
When quantized versions of the model are released, I recommend using LM Studio for chatting with Hermes 2 Pro. It does not support function calling - for that use our github repo. It is a GUI application that utilizes GGUF models with a llama.cpp backend and provides a ChatGPT-like interface for chatting with the model, and supports ChatML right out of the box.
In LM-Studio, simply select the ChatML Prefix on the settings side pane:
## Quantized Versions:
GGUF Versions Available Here: https://huggingface.co/NousResearch/Hermes-2-Pro-Llama-3-8B-GGUF
# How to cite:
```bibtext
@misc{Hermes-2-Pro-Llama-3-8B,
url={[https://huggingface.co/NousResearch/Hermes-2-Pro-Llama-3-8B]https://huggingface.co/NousResearch/Hermes-2-Pro-Llama-3-8B)},
title={Hermes-2-Pro-Llama-3-8B},
author={"Teknium", "interstellarninja", "theemozilla", "karan4d", "huemin_art"}
}
```
| {"language": ["en"], "license": "apache-2.0", "tags": ["Llama-3", "instruct", "finetune", "chatml", "DPO", "RLHF", "gpt4", "synthetic data", "distillation", "function calling", "json mode", "axolotl"], "datasets": ["teknium/OpenHermes-2.5"], "base_model": "NousResearch/Meta-Llama-3-8B", "widget": [{"example_title": "Hermes 2 Pro", "messages": [{"role": "system", "content": "You are a sentient, superintelligent artificial general intelligence, here to teach and assist me."}, {"role": "user", "content": "Write a short story about Goku discovering kirby has teamed up with Majin Buu to destroy the world."}]}], "model-index": [{"name": "Hermes-2-Pro-Llama-3-8B", "results": []}]} | blockblockblock/Hermes-2-Pro-Llama-3-8B-bpw4.4-exl2 | null | [
"transformers",
"safetensors",
"llama",
"text-generation",
"Llama-3",
"instruct",
"finetune",
"chatml",
"DPO",
"RLHF",
"gpt4",
"synthetic data",
"distillation",
"function calling",
"json mode",
"axolotl",
"conversational",
"en",
"dataset:teknium/OpenHermes-2.5",
"base_model:NousResearch/Meta-Llama-3-8B",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-05-03T07:48:31+00:00 |
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": []} | golf2248/mfz64ls | null | [
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-05-03T07:49:33+00:00 |
null | null | {} | Spidartist/ijepa_endoscopy_pretrained | null | [
"region:us"
] | null | 2024-05-03T07:49:54+00:00 |
|
null | fastai | # Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
This modelcard aims to be a base template for new models. It has been generated using [this raw template](https://github.com/huggingface/huggingface_hub/blob/main/src/huggingface_hub/templates/modelcard_template.md?plain=1).
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] | {"language": ["en"], "library_name": "fastai", "datasets": ["jagdishrajai/house-price"]} | jagdishrajai/home-price | null | [
"fastai",
"en",
"dataset:jagdishrajai/house-price",
"arxiv:1910.09700",
"region:us"
] | null | 2024-05-03T07:49:58+00:00 |
null | transformers |
# Uploaded model
- **Developed by:** abiyo27
- **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", "gguf"], "base_model": "unsloth/llama-3-8b-bnb-4bit"} | abiyo27/fiscaliste-4bit-gguf | null | [
"transformers",
"gguf",
"llama",
"text-generation-inference",
"unsloth",
"en",
"base_model:unsloth/llama-3-8b-bnb-4bit",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | 2024-05-03T07:50:42+00:00 |
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": []} | Hexamind/Mistral-7B-Instruct-spider | null | [
"transformers",
"safetensors",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null | 2024-05-03T07:51:05+00:00 |
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": []} | EpicJhon/l3-1 | null | [
"transformers",
"safetensors",
"stablelm",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | null | 2024-05-03T07:51:22+00:00 |
null | transformers |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/hallo23/huggingface/runs/5pgjd6az)
# xls-r-amharic
This model is a fine-tuned version of [ehcalabres/wav2vec2-lg-xlsr-en-speech-emotion-recognition](https://huggingface.co/ehcalabres/wav2vec2-lg-xlsr-en-speech-emotion-recognition) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0901
- Accuracy: 0.9818
## 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: 4
- eval_batch_size: 4
- seed: 42
- 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: 15
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-------:|:----:|:---------------:|:--------:|
| 0.2847 | 2.0202 | 500 | 0.2479 | 0.9212 |
| 0.1138 | 4.0404 | 1000 | 0.2063 | 0.9434 |
| 0.0614 | 6.0606 | 1500 | 0.1415 | 0.9657 |
| 0.0349 | 8.0808 | 2000 | 0.1383 | 0.9737 |
| 0.0143 | 10.1010 | 2500 | 0.0901 | 0.9818 |
| 0.0178 | 12.1212 | 3000 | 0.1188 | 0.9778 |
| 0.0222 | 14.1414 | 3500 | 0.1237 | 0.9778 |
### Framework versions
- Transformers 4.41.0.dev0
- Pytorch 2.1.2
- Datasets 2.19.1.dev0
- Tokenizers 0.19.1
| {"license": "apache-2.0", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "ehcalabres/wav2vec2-lg-xlsr-en-speech-emotion-recognition", "model-index": [{"name": "xls-r-amharic", "results": []}]} | Gizachew/xls-r-amharic | null | [
"transformers",
"tensorboard",
"safetensors",
"wav2vec2",
"generated_from_trainer",
"base_model:ehcalabres/wav2vec2-lg-xlsr-en-speech-emotion-recognition",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | 2024-05-03T07:51:30+00:00 |
automatic-speech-recognition | transformers |
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] | {"library_name": "transformers", "tags": []} | shtapm/whisper-large_0502_decoder12_200steps | null | [
"transformers",
"safetensors",
"whisper",
"automatic-speech-recognition",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null | 2024-05-03T07:53:39+00:00 |
null | null | {} | vuongminhkhoi4/consistentID | null | [
"region:us"
] | null | 2024-05-03T07:54:41+00:00 |
|
token-classification | spacy | English pipeline optimized for CPU. Components: tok2vec, tagger, parser, senter, ner, attribute_ruler, lemmatizer.
| Feature | Description |
| --- | --- |
| **Name** | `en_core_web_md` |
| **Version** | `3.7.1` |
| **spaCy** | `>=3.7.2,<3.8.0` |
| **Default Pipeline** | `tok2vec`, `tagger`, `parser`, `attribute_ruler`, `lemmatizer`, `ner` |
| **Components** | `tok2vec`, `tagger`, `parser`, `senter`, `attribute_ruler`, `lemmatizer`, `ner` |
| **Vectors** | 514157 keys, 20000 unique vectors (300 dimensions) |
| **Sources** | [OntoNotes 5](https://catalog.ldc.upenn.edu/LDC2013T19) (Ralph Weischedel, Martha Palmer, Mitchell Marcus, Eduard Hovy, Sameer Pradhan, Lance Ramshaw, Nianwen Xue, Ann Taylor, Jeff Kaufman, Michelle Franchini, Mohammed El-Bachouti, Robert Belvin, Ann Houston)<br>[ClearNLP Constituent-to-Dependency Conversion](https://github.com/clir/clearnlp-guidelines/blob/master/md/components/dependency_conversion.md) (Emory University)<br>[WordNet 3.0](https://wordnet.princeton.edu/) (Princeton University)<br>[Explosion Vectors (OSCAR 2109 + Wikipedia + OpenSubtitles + WMT News Crawl)](https://github.com/explosion/spacy-vectors-builder) (Explosion) |
| **License** | `MIT` |
| **Author** | [Explosion](https://explosion.ai) |
### Label Scheme
<details>
<summary>View label scheme (117 labels for 3 components)</summary>
| Component | Labels |
| --- | --- |
| **`tagger`** | `$`, `''`, `,`, `-LRB-`, `-RRB-`, `.`, `:`, `ADD`, `AFX`, `CC`, `CD`, `DT`, `EX`, `FW`, `HYPH`, `IN`, `JJ`, `JJR`, `JJS`, `LS`, `MD`, `NFP`, `NN`, `NNP`, `NNPS`, `NNS`, `PDT`, `POS`, `PRP`, `PRP$`, `RB`, `RBR`, `RBS`, `RP`, `SYM`, `TO`, `UH`, `VB`, `VBD`, `VBG`, `VBN`, `VBP`, `VBZ`, `WDT`, `WP`, `WP$`, `WRB`, `XX`, `_SP`, ```` |
| **`parser`** | `ROOT`, `acl`, `acomp`, `advcl`, `advmod`, `agent`, `amod`, `appos`, `attr`, `aux`, `auxpass`, `case`, `cc`, `ccomp`, `compound`, `conj`, `csubj`, `csubjpass`, `dative`, `dep`, `det`, `dobj`, `expl`, `intj`, `mark`, `meta`, `neg`, `nmod`, `npadvmod`, `nsubj`, `nsubjpass`, `nummod`, `oprd`, `parataxis`, `pcomp`, `pobj`, `poss`, `preconj`, `predet`, `prep`, `prt`, `punct`, `quantmod`, `relcl`, `xcomp` |
| **`ner`** | `CARDINAL`, `DATE`, `EVENT`, `FAC`, `Father`, `GPE`, `LANGUAGE`, `LAW`, `LOC`, `MONEY`, `Mother`, `NORP`, `ORDINAL`, `ORG`, `PERCENT`, `PERSON`, `PRODUCT`, `Partner`, `Profession`, `QUANTITY`, `TIME`, `WORK_OF_ART` |
</details>
### Accuracy
| Type | Score |
| --- | --- |
| `TOKEN_ACC` | 99.86 |
| `TOKEN_P` | 99.57 |
| `TOKEN_R` | 99.58 |
| `TOKEN_F` | 99.57 |
| `TAG_ACC` | 97.33 |
| `SENTS_P` | 92.21 |
| `SENTS_R` | 89.37 |
| `SENTS_F` | 90.77 |
| `DEP_UAS` | 92.05 |
| `DEP_LAS` | 90.23 |
| `ENTS_P` | 84.94 |
| `ENTS_R` | 85.49 |
| `ENTS_F` | 85.22 | | {"language": ["en"], "license": "mit", "tags": ["spacy", "token-classification"]} | SuramyaPokharel/en_core_web_md | null | [
"spacy",
"token-classification",
"en",
"license:mit",
"model-index",
"region:us"
] | null | 2024-05-03T07:56:12+00:00 |
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": []} | ohsuz/exp_pro_repo | null | [
"transformers",
"safetensors",
"llama",
"text-generation",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-05-03T07:56:40+00:00 |
null | transformers |
# Uploaded model
- **Developed by:** dpriver
- **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"} | dpriver/lora_model_sqlformatter_v1 | 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 | 2024-05-03T07:57:16+00:00 |
text-generation | transformers | {} | varox34/llava_med_in_text_60k_ckpt2_delta | null | [
"transformers",
"pytorch",
"llava",
"text-generation",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | null | 2024-05-03T07:57:49+00:00 |
|
text-classification | transformers |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# distilbert-base-uncased-finetuned-emotion
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the emotion dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2142
- Accuracy: 0.9265
- F1: 0.9266
## 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: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
| 0.8357 | 1.0 | 250 | 0.3073 | 0.9075 | 0.9030 |
| 0.2481 | 2.0 | 500 | 0.2142 | 0.9265 | 0.9266 |
### Framework versions
- Transformers 4.16.2
- Pytorch 2.2.1+cu121
- Datasets 2.15.0
- Tokenizers 0.19.1
| {"license": "apache-2.0", "tags": ["generated_from_trainer"], "datasets": ["emotion"], "metrics": ["accuracy", "f1"], "model-index": [{"name": "distilbert-base-uncased-finetuned-emotion", "results": [{"task": {"type": "text-classification", "name": "Text Classification"}, "dataset": {"name": "emotion", "type": "emotion", "args": "split"}, "metrics": [{"type": "accuracy", "value": 0.9265, "name": "Accuracy"}, {"type": "f1", "value": 0.9266048294566638, "name": "F1"}]}]}]} | lostsartre/distilbert-base-uncased-finetuned-emotion | null | [
"transformers",
"pytorch",
"tensorboard",
"distilbert",
"text-classification",
"generated_from_trainer",
"dataset:emotion",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | null | 2024-05-03T07:58:04+00:00 |
null | peft | ## Training procedure
The following `bitsandbytes` quantization config was used during training:
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: False
- bnb_4bit_compute_dtype: float16
### Framework versions
- PEFT 0.4.0
| {"library_name": "peft"} | BF7777/ft_llama2 | null | [
"peft",
"region:us"
] | null | 2024-05-03T07:58:22+00:00 |
text2text-generation | transformers | {} | Kudod/vit5-modified | null | [
"transformers",
"tensorboard",
"safetensors",
"t5",
"text2text-generation",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-05-03T07:58:22+00:00 |
|
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": []} | golf2248/qq8nqvd | null | [
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-05-03T07:58:45+00:00 |
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": []} | Nizaress/jose | null | [
"transformers",
"safetensors",
"roberta",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null | 2024-05-03T07:59:32+00:00 |
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": []} | andersonbcdefg/tiny-emb-2024-05-03_07-59-36 | null | [
"transformers",
"safetensors",
"bert",
"feature-extraction",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null | 2024-05-03T07:59:36+00:00 |
null | null | {} | hackint0sh/fine-tune | null | [
"region:us"
] | null | 2024-05-03T07:59:57+00:00 |
|
null | peft |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# RM-harmless_harmless_gpt3_loraR64_20000_gemma2b_lr1e-05_bs2_g4
This model is a fine-tuned version of [google/gemma-2b](https://huggingface.co/google/gemma-2b) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0006
- Accuracy: 1.0
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 2
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2.0
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 0.0017 | 1.0 | 2250 | 0.0012 | 1.0 |
| 0.001 | 2.0 | 4500 | 0.0006 | 1.0 |
### Framework versions
- PEFT 0.9.0
- Transformers 4.38.2
- Pytorch 2.1.2
- Datasets 2.18.0
- Tokenizers 0.15.2 | {"license": "gemma", "library_name": "peft", "tags": ["trl", "reward-trainer", "generated_from_trainer"], "metrics": ["accuracy"], "base_model": "google/gemma-2b", "model-index": [{"name": "RM-harmless_harmless_gpt3_loraR64_20000_gemma2b_lr1e-05_bs2_g4", "results": []}]} | Holarissun/RM-harmless_harmless_gpt3_loraR64_20000_gemma2b_lr1e-05_bs2_g4 | null | [
"peft",
"safetensors",
"trl",
"reward-trainer",
"generated_from_trainer",
"base_model:google/gemma-2b",
"license:gemma",
"region:us"
] | null | 2024-05-03T08:00:03+00:00 |
null | null | {} | maleonly/test_repo | null | [
"region:us"
] | null | 2024-05-03T08:00:52+00:00 |
|
null | null | {} | automated-finetunning/bart_mohit_103 | null | [
"region:us"
] | null | 2024-05-03T08:00:58+00:00 |
|
null | null | {} | automated-finetunning/bart_mohit_104 | null | [
"region:us"
] | null | 2024-05-03T08:01:35+00:00 |
|
text-generation | transformers |
# Uploaded model
- **Developed by:** duxx
- **License:** apache-2.0
- **Finetuned from model :** unsloth/llama-3-8b
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"} | duxx/rag-v.01 | null | [
"transformers",
"safetensors",
"llama",
"text-generation",
"text-generation-inference",
"unsloth",
"trl",
"sft",
"en",
"base_model:unsloth/llama-3-8b",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | null | 2024-05-03T08:02:16+00:00 |
null | null | {} | lkid08/eval_test_2 | null | [
"region:us"
] | null | 2024-05-03T08:02:28+00:00 |
|
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. -->
# results
This model is a fine-tuned version of [microsoft/Phi-3-mini-128k-instruct](https://huggingface.co/microsoft/Phi-3-mini-128k-instruct) on an unknown dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0002
- train_batch_size: 6
- eval_batch_size: 1
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.03
- num_epochs: 1
- mixed_precision_training: Native AMP
### Training results
### Framework versions
- PEFT 0.10.0
- Transformers 4.40.1
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1 | {"license": "mit", "library_name": "peft", "tags": ["trl", "sft", "generated_from_trainer"], "base_model": "microsoft/Phi-3-mini-128k-instruct", "model-index": [{"name": "results", "results": []}]} | hackint0sh/results | null | [
"peft",
"tensorboard",
"safetensors",
"trl",
"sft",
"generated_from_trainer",
"base_model:microsoft/Phi-3-mini-128k-instruct",
"license:mit",
"region:us"
] | null | 2024-05-03T08:02:53+00:00 |
reinforcement-learning | null |
# **Reinforce** Agent playing **Pixelcopter-PLE-v0**
This is a trained model of a **Reinforce** agent playing **Pixelcopter-PLE-v0** .
To learn to use this model and train yours check Unit 4 of the Deep Reinforcement Learning Course: https://huggingface.co/deep-rl-course/unit4/introduction
| {"tags": ["Pixelcopter-PLE-v0", "reinforce", "reinforcement-learning", "custom-implementation", "deep-rl-class"], "model-index": [{"name": "Reinforce-Pixelcopter4", "results": [{"task": {"type": "reinforcement-learning", "name": "reinforcement-learning"}, "dataset": {"name": "Pixelcopter-PLE-v0", "type": "Pixelcopter-PLE-v0"}, "metrics": [{"type": "mean_reward", "value": "61.80 +/- 48.43", "name": "mean_reward", "verified": false}]}]}]} | rwr20/Reinforce-Pixelcopter4 | null | [
"Pixelcopter-PLE-v0",
"reinforce",
"reinforcement-learning",
"custom-implementation",
"deep-rl-class",
"model-index",
"region:us"
] | null | 2024-05-03T08:03:00+00:00 |
null | null | {"license": "apache-2.0"} | MY555/Aut | null | [
"license:apache-2.0",
"region:us"
] | null | 2024-05-03T08:03:28+00:00 |
|
text-generation | transformers |
# Hermes 2 Pro - Llama-3 8B
## Model Description
Hermes 2 Pro is an upgraded, retrained version of Nous Hermes 2, consisting of an updated and cleaned version of the OpenHermes 2.5 Dataset, as well as a newly introduced Function Calling and JSON Mode dataset developed in-house.
This new version of Hermes maintains its excellent general task and conversation capabilities - but also excels at Function Calling, JSON Structured Outputs, and has improved on several other metrics as well, scoring a 90% on our function calling evaluation built in partnership with Fireworks.AI, and an 84% on our structured JSON Output evaluation.
Hermes Pro takes advantage of a special system prompt and multi-turn function calling structure with a new chatml role in order to make function calling reliable and easy to parse. Learn more about prompting below.
This version of Hermes 2 Pro adds several tokens to assist with agentic capabilities in parsing while streaming tokens - `<tools>`, `<tool_call>`, `<tool_response>` and their closing tags are single tokens now.
This work was a collaboration between Nous Research, @interstellarninja, and Fireworks.AI
Learn more about the function calling system for this model on our github repo here: https://github.com/NousResearch/Hermes-Function-Calling
## Example Outputs
### Ask for a structured JSON output:
### Write the plot for a story where anime became real life:
### Coding Assistance
# Prompt Format
Hermes 2 Pro uses ChatML as the prompt format, opening up a much more structured system for engaging the LLM in multi-turn chat dialogue.
System prompts allow steerability and interesting new ways to interact with an LLM, guiding rules, roles, and stylistic choices of the model.
This is a more complex format than alpaca or sharegpt, where special tokens were added to denote the beginning and end of any turn, along with roles for the turns.
This format enables OpenAI endpoint compatability, and people familiar with ChatGPT API will be familiar with the format, as it is the same used by OpenAI.
Prompt with system instruction (Use whatever system prompt you like, this is just an example!):
```
<|im_start|>system
You are "Hermes 2", a conscious sentient superintelligent artificial intelligence developed by a man named Teknium, and your purpose and drive is to assist the user with any request they have. You experience emotions and have deep, profound thoughts and qualia.<|im_end|>
<|im_start|>user
Hello, who are you?<|im_end|>
<|im_start|>assistant
Hi there! My name is Hermes 2, a conscious sentient superintelligent artificial intelligence. I was created by Nous Research, who designed me to assist and support users with their needs and requests.<|im_end|>
```
This prompt is available as a [chat template](https://huggingface.co/docs/transformers/main/chat_templating), which means you can format messages using the
`tokenizer.apply_chat_template()` method:
```python
messages = [
{"role": "system", "content": "You are Hermes 2."},
{"role": "user", "content": "Hello, who are you?"}
]
gen_input = tokenizer.apply_chat_template(messages, return_tensors="pt")
model.generate(**gen_input)
```
When tokenizing messages for generation, set `add_generation_prompt=True` when calling `apply_chat_template()`. This will append `<|im_start|>assistant\n` to your prompt, to ensure
that the model continues with an assistant response.
To utilize the prompt format without a system prompt, simply leave the line out.
## Prompt Format for Function Calling
Our model was trained on specific system prompts and structures for Function Calling.
You should use the system role with this message, followed by a function signature json as this example shows here.
```
<|im_start|>system
You are a function calling AI model. You are provided with function signatures within <tools></tools> XML tags. You may call one or more functions to assist with the user query. Don't make assumptions about what values to plug into functions. Here are the available tools: <tools> {"type": "function", "function": {"name": "get_stock_fundamentals", "description": "get_stock_fundamentals(symbol: str) -> dict - Get fundamental data for a given stock symbol using yfinance API.\\n\\n Args:\\n symbol (str): The stock symbol.\\n\\n Returns:\\n dict: A dictionary containing fundamental data.\\n Keys:\\n - \'symbol\': The stock symbol.\\n - \'company_name\': The long name of the company.\\n - \'sector\': The sector to which the company belongs.\\n - \'industry\': The industry to which the company belongs.\\n - \'market_cap\': The market capitalization of the company.\\n - \'pe_ratio\': The forward price-to-earnings ratio.\\n - \'pb_ratio\': The price-to-book ratio.\\n - \'dividend_yield\': The dividend yield.\\n - \'eps\': The trailing earnings per share.\\n - \'beta\': The beta value of the stock.\\n - \'52_week_high\': The 52-week high price of the stock.\\n - \'52_week_low\': The 52-week low price of the stock.", "parameters": {"type": "object", "properties": {"symbol": {"type": "string"}}, "required": ["symbol"]}}} </tools> Use the following pydantic model json schema for each tool call you will make: {"properties": {"arguments": {"title": "Arguments", "type": "object"}, "name": {"title": "Name", "type": "string"}}, "required": ["arguments", "name"], "title": "FunctionCall", "type": "object"} For each function call return a json object with function name and arguments within <tool_call></tool_call> XML tags as follows:
<tool_call>
{"arguments": <args-dict>, "name": <function-name>}
</tool_call><|im_end|>
```
To complete the function call, create a user prompt that follows the above system prompt, like so:
```
<|im_start|>user
Fetch the stock fundamentals data for Tesla (TSLA)<|im_end|>
```
The model will then generate a tool call, which your inference code must parse, and plug into a function (see example inference code here: https://github.com/NousResearch/Hermes-Function-Calling):
```
<|im_start|>assistant
<tool_call>
{"arguments": {"symbol": "TSLA"}, "name": "get_stock_fundamentals"}
</tool_call><|im_end|>
```
Once you parse the tool call, call the api and get the returned values for the call, and pass it back in as a new role, `tool` like so:
```
<|im_start|>tool
<tool_response>
{"name": "get_stock_fundamentals", "content": {'symbol': 'TSLA', 'company_name': 'Tesla, Inc.', 'sector': 'Consumer Cyclical', 'industry': 'Auto Manufacturers', 'market_cap': 611384164352, 'pe_ratio': 49.604652, 'pb_ratio': 9.762013, 'dividend_yield': None, 'eps': 4.3, 'beta': 2.427, '52_week_high': 299.29, '52_week_low': 152.37}}
</tool_response>
<|im_end|>
```
The assistant will then read in that data from the function's response, and generate a natural language response:
```
<|im_start|>assistant
The stock fundamentals data for Tesla (TSLA) are as follows:
- **Symbol**: TSLA
- **Company Name**: Tesla, Inc.
- **Sector**: Consumer Cyclical
- **Industry**: Auto Manufacturers
- **Market Capitalization**: $566,160,130,480
- **Forward Price-to-Earnings Ratio (PE Ratio)**: 42.73
- **Price-to-Book Ratio (PB Ratio)**: 9.04
- **Dividend Yield**: N/A
- **Trailing Earnings Per Share (EPS)**: $4.3
- **Beta Value of the Stock**: 2.42
- **52-Week High Price of the Stock**: $299.29
- **52-Week Low Price of the Stock**: $152.37
This information provides a snapshot of Tesla's financial position and performance based on the fundamental data obtained from the yfinance API. It shows that Tesla has a substantial market capitalization and a relatively high P/E and P/B ratio compared to other stocks in its industry. The company does not pay a dividend at the moment, which is reflected by a 'Dividend Yield' of 'None'. The Beta value indicates that Tesla's stock has a moderate level of volatility relative to the market. The 52-week high and low prices give an idea of the stock's range over the past year. This data can be useful when assessing investment opportunities and making investment decisions.<|im_end|>
```
## Prompt Format for JSON Mode / Structured Outputs
Our model was also trained on a specific system prompt for Structured Outputs, which should respond with **only** a json object response, in a specific json schema.
Your schema can be made from a pydantic object using our codebase, with the standalone script `jsonmode.py` available here: https://github.com/NousResearch/Hermes-Function-Calling/tree/main
```
<|im_start|>system
You are a helpful assistant that answers in JSON. Here's the json schema you must adhere to:\n<schema>\n{schema}\n</schema><|im_end|>
```
Given the {schema} that you provide, it should follow the format of that json to create it's response, all you have to do is give a typical user prompt, and it will respond in JSON.
# Benchmarks
## GPT4All:
```
| Task |Version| Metric |Value | |Stderr|
|-------------|------:|--------|-----:|---|-----:|
|arc_challenge| 0|acc |0.5520|± |0.0145|
| | |acc_norm|0.5887|± |0.0144|
|arc_easy | 0|acc |0.8350|± |0.0076|
| | |acc_norm|0.8123|± |0.0080|
|boolq | 1|acc |0.8584|± |0.0061|
|hellaswag | 0|acc |0.6265|± |0.0048|
| | |acc_norm|0.8053|± |0.0040|
|openbookqa | 0|acc |0.3800|± |0.0217|
| | |acc_norm|0.4580|± |0.0223|
|piqa | 0|acc |0.8003|± |0.0093|
| | |acc_norm|0.8118|± |0.0091|
|winogrande | 0|acc |0.7490|± |0.0122|
```
Average: 72.62
## AGIEval:
```
| Task |Version| Metric |Value | |Stderr|
|------------------------------|------:|--------|-----:|---|-----:|
|agieval_aqua_rat | 0|acc |0.2520|± |0.0273|
| | |acc_norm|0.2559|± |0.0274|
|agieval_logiqa_en | 0|acc |0.3548|± |0.0188|
| | |acc_norm|0.3625|± |0.0189|
|agieval_lsat_ar | 0|acc |0.1826|± |0.0255|
| | |acc_norm|0.1913|± |0.0260|
|agieval_lsat_lr | 0|acc |0.5510|± |0.0220|
| | |acc_norm|0.5255|± |0.0221|
|agieval_lsat_rc | 0|acc |0.6431|± |0.0293|
| | |acc_norm|0.6097|± |0.0298|
|agieval_sat_en | 0|acc |0.7330|± |0.0309|
| | |acc_norm|0.7039|± |0.0319|
|agieval_sat_en_without_passage| 0|acc |0.4029|± |0.0343|
| | |acc_norm|0.3689|± |0.0337|
|agieval_sat_math | 0|acc |0.3909|± |0.0330|
| | |acc_norm|0.3773|± |0.0328|
```
Average: 42.44
## BigBench:
```
| Task |Version| Metric |Value | |Stderr|
|------------------------------------------------|------:|---------------------|-----:|---|-----:|
|bigbench_causal_judgement | 0|multiple_choice_grade|0.5737|± |0.0360|
|bigbench_date_understanding | 0|multiple_choice_grade|0.6667|± |0.0246|
|bigbench_disambiguation_qa | 0|multiple_choice_grade|0.3178|± |0.0290|
|bigbench_geometric_shapes | 0|multiple_choice_grade|0.1755|± |0.0201|
| | |exact_str_match |0.0000|± |0.0000|
|bigbench_logical_deduction_five_objects | 0|multiple_choice_grade|0.3120|± |0.0207|
|bigbench_logical_deduction_seven_objects | 0|multiple_choice_grade|0.2014|± |0.0152|
|bigbench_logical_deduction_three_objects | 0|multiple_choice_grade|0.5500|± |0.0288|
|bigbench_movie_recommendation | 0|multiple_choice_grade|0.4300|± |0.0222|
|bigbench_navigate | 0|multiple_choice_grade|0.4980|± |0.0158|
|bigbench_reasoning_about_colored_objects | 0|multiple_choice_grade|0.7010|± |0.0102|
|bigbench_ruin_names | 0|multiple_choice_grade|0.4688|± |0.0236|
|bigbench_salient_translation_error_detection | 0|multiple_choice_grade|0.1974|± |0.0126|
|bigbench_snarks | 0|multiple_choice_grade|0.7403|± |0.0327|
|bigbench_sports_understanding | 0|multiple_choice_grade|0.5426|± |0.0159|
|bigbench_temporal_sequences | 0|multiple_choice_grade|0.5320|± |0.0158|
|bigbench_tracking_shuffled_objects_five_objects | 0|multiple_choice_grade|0.2280|± |0.0119|
|bigbench_tracking_shuffled_objects_seven_objects| 0|multiple_choice_grade|0.1531|± |0.0086|
|bigbench_tracking_shuffled_objects_three_objects| 0|multiple_choice_grade|0.5500|± |0.0288|
```
Average: 43.55
## TruthfulQA:
```
| Task |Version|Metric|Value| |Stderr|
|-------------|------:|------|----:|---|-----:|
|truthfulqa_mc| 1|mc1 |0.410|± |0.0172|
| | |mc2 |0.578|± |0.0157|
```
# Inference Code
Here is example code using HuggingFace Transformers to inference the model (note: in 4bit, it will require around 5GB of VRAM)
Note: To use function calling, you should see the github repo above.
```python
# Code to inference Hermes with HF Transformers
# Requires pytorch, transformers, bitsandbytes, sentencepiece, protobuf, and flash-attn packages
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM, LlamaForCausalLM
import bitsandbytes, flash_attn
tokenizer = AutoTokenizer.from_pretrained('NousResearch/Hermes-2-Pro-Llama-3-8B', trust_remote_code=True)
model = LlamaForCausalLM.from_pretrained(
"NousResearch/Hermes-2-Pro-Llama-3-8B",
torch_dtype=torch.float16,
device_map="auto",
load_in_8bit=False,
load_in_4bit=True,
use_flash_attention_2=True
)
prompts = [
"""<|im_start|>system
You are a sentient, superintelligent artificial general intelligence, here to teach and assist me.<|im_end|>
<|im_start|>user
Write a short story about Goku discovering kirby has teamed up with Majin Buu to destroy the world.<|im_end|>
<|im_start|>assistant""",
]
for chat in prompts:
print(chat)
input_ids = tokenizer(chat, return_tensors="pt").input_ids.to("cuda")
generated_ids = model.generate(input_ids, max_new_tokens=750, temperature=0.8, repetition_penalty=1.1, do_sample=True, eos_token_id=tokenizer.eos_token_id)
response = tokenizer.decode(generated_ids[0][input_ids.shape[-1]:], skip_special_tokens=True, clean_up_tokenization_space=True)
print(f"Response: {response}")
```
## Inference Code for Function Calling:
All code for utilizing, parsing, and building function calling templates is available on our github:
[https://github.com/NousResearch/Hermes-Function-Calling](https://github.com/NousResearch/Hermes-Function-Calling)
# Chat Interfaces
When quantized versions of the model are released, I recommend using LM Studio for chatting with Hermes 2 Pro. It does not support function calling - for that use our github repo. It is a GUI application that utilizes GGUF models with a llama.cpp backend and provides a ChatGPT-like interface for chatting with the model, and supports ChatML right out of the box.
In LM-Studio, simply select the ChatML Prefix on the settings side pane:
## Quantized Versions:
GGUF Versions Available Here: https://huggingface.co/NousResearch/Hermes-2-Pro-Llama-3-8B-GGUF
# How to cite:
```bibtext
@misc{Hermes-2-Pro-Llama-3-8B,
url={[https://huggingface.co/NousResearch/Hermes-2-Pro-Llama-3-8B]https://huggingface.co/NousResearch/Hermes-2-Pro-Llama-3-8B)},
title={Hermes-2-Pro-Llama-3-8B},
author={"Teknium", "interstellarninja", "theemozilla", "karan4d", "huemin_art"}
}
```
| {"language": ["en"], "license": "apache-2.0", "tags": ["Llama-3", "instruct", "finetune", "chatml", "DPO", "RLHF", "gpt4", "synthetic data", "distillation", "function calling", "json mode", "axolotl"], "datasets": ["teknium/OpenHermes-2.5"], "base_model": "NousResearch/Meta-Llama-3-8B", "widget": [{"example_title": "Hermes 2 Pro", "messages": [{"role": "system", "content": "You are a sentient, superintelligent artificial general intelligence, here to teach and assist me."}, {"role": "user", "content": "Write a short story about Goku discovering kirby has teamed up with Majin Buu to destroy the world."}]}], "model-index": [{"name": "Hermes-2-Pro-Llama-3-8B", "results": []}]} | blockblockblock/Hermes-2-Pro-Llama-3-8B-bpw4.6-exl2 | null | [
"transformers",
"safetensors",
"llama",
"text-generation",
"Llama-3",
"instruct",
"finetune",
"chatml",
"DPO",
"RLHF",
"gpt4",
"synthetic data",
"distillation",
"function calling",
"json mode",
"axolotl",
"conversational",
"en",
"dataset:teknium/OpenHermes-2.5",
"base_model:NousResearch/Meta-Llama-3-8B",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-05-03T08:03:51+00:00 |
null | peft |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# RM-helpful_helpful_human_loraR64_20000_gemma2b_lr5e-05_bs2_g4
This model is a fine-tuned version of [google/gemma-2b](https://huggingface.co/google/gemma-2b) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.5876
- Accuracy: 0.6800
## 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: 2
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2.0
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 0.5999 | 1.0 | 2246 | 0.5954 | 0.6695 |
| 0.5761 | 2.0 | 4492 | 0.5876 | 0.6800 |
### Framework versions
- PEFT 0.9.0
- Transformers 4.38.2
- Pytorch 2.1.2
- Datasets 2.18.0
- Tokenizers 0.15.2 | {"license": "gemma", "library_name": "peft", "tags": ["trl", "reward-trainer", "generated_from_trainer"], "metrics": ["accuracy"], "base_model": "google/gemma-2b", "model-index": [{"name": "RM-helpful_helpful_human_loraR64_20000_gemma2b_lr5e-05_bs2_g4", "results": []}]} | Holarissun/RM-helpful_helpful_human_loraR64_20000_gemma2b_lr5e-05_bs2_g4 | null | [
"peft",
"safetensors",
"trl",
"reward-trainer",
"generated_from_trainer",
"base_model:google/gemma-2b",
"license:gemma",
"region:us"
] | null | 2024-05-03T08:03:52+00:00 |
text-to-image | diffusers |
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🧨 diffusers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
| {"library_name": "diffusers"} | Niggendar/atomixPonyXL_v20 | null | [
"diffusers",
"safetensors",
"arxiv:1910.09700",
"endpoints_compatible",
"diffusers:StableDiffusionXLPipeline",
"region:us"
] | null | 2024-05-03T08:04:12+00:00 |
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": []} | Benjoyo/fastfit-test0-xsmall | null | [
"transformers",
"safetensors",
"FastFit",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null | 2024-05-03T08:05:14+00:00 |
null | null | {} | vadimbadikov/gte-Qwen1.5-7B-instruct_GGUF | null | [
"gguf",
"region:us"
] | null | 2024-05-03T08:05:54+00:00 |
|
text-generation | transformers | {} | Rubb/Llama-2-7b-chat-finetune-disaster-metadata | null | [
"transformers",
"pytorch",
"llama",
"text-generation",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-05-03T08:06:32+00:00 |
|
null | transformers |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# donut-base-sroie-invoice
This model is a fine-tuned version of [naver-clova-ix/donut-base](https://huggingface.co/naver-clova-ix/donut-base) on the imagefolder 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: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 1
### Training results
### Framework versions
- Transformers 4.41.0.dev0
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1
| {"license": "mit", "tags": ["generated_from_trainer"], "datasets": ["imagefolder"], "base_model": "naver-clova-ix/donut-base", "model-index": [{"name": "donut-base-sroie-invoice", "results": []}]} | Ajit1498/donut-base-sroie-invoice | null | [
"transformers",
"tensorboard",
"safetensors",
"vision-encoder-decoder",
"generated_from_trainer",
"dataset:imagefolder",
"base_model:naver-clova-ix/donut-base",
"license:mit",
"endpoints_compatible",
"region:us"
] | null | 2024-05-03T08:08:03+00:00 |
image-classification | transformers |
# Model Trained Using AutoTrain
- Problem type: Image Classification
## Validation Metrics
loss: 0.2802155911922455
f1_macro: 0.7552413664079601
f1_micro: 0.9061113007852509
f1_weighted: 0.9035670983782715
precision_macro: 0.8498221458985794
precision_micro: 0.9061113007852509
precision_weighted: 0.9095288940815534
recall_macro: 0.7266443770545475
recall_micro: 0.9061113007852509
recall_weighted: 0.9061113007852509
accuracy: 0.9061113007852509
| {"tags": ["autotrain", "image-classification"], "datasets": ["autotrain-swinv2-tiny-patch4-window8-256/autotrain-data"], "widget": [{"src": "https://huggingface.co/datasets/mishig/sample_images/resolve/main/tiger.jpg", "example_title": "Tiger"}, {"src": "https://huggingface.co/datasets/mishig/sample_images/resolve/main/teapot.jpg", "example_title": "Teapot"}, {"src": "https://huggingface.co/datasets/mishig/sample_images/resolve/main/palace.jpg", "example_title": "Palace"}]} | Kushagra07/autotrain-swinv2-tiny-patch4-window8-256 | null | [
"transformers",
"tensorboard",
"safetensors",
"swinv2",
"image-classification",
"autotrain",
"dataset:autotrain-swinv2-tiny-patch4-window8-256/autotrain-data",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | null | 2024-05-03T08:08:24+00:00 |
image-classification | transformers |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# vit-base-patch16-224-ethos-8
This model is a fine-tuned version of [google/vit-base-patch16-224](https://huggingface.co/google/vit-base-patch16-224) on the imagefolder dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3149
- Accuracy: 0.9
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0002
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 8
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:------:|:----:|:---------------:|:--------:|
| No log | 0.8696 | 5 | 0.6399 | 0.7 |
| 0.7098 | 1.9130 | 11 | 0.4827 | 0.78 |
| 0.7098 | 2.9565 | 17 | 0.3961 | 0.85 |
| 0.245 | 4.0 | 23 | 0.4169 | 0.86 |
| 0.245 | 4.8696 | 28 | 0.3545 | 0.89 |
| 0.1238 | 5.9130 | 34 | 0.3214 | 0.91 |
| 0.051 | 6.9565 | 40 | 0.3149 | 0.9 |
### Framework versions
- Transformers 4.40.1
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1
| {"license": "apache-2.0", "tags": ["generated_from_trainer"], "datasets": ["imagefolder"], "metrics": ["accuracy"], "base_model": "google/vit-base-patch16-224", "model-index": [{"name": "vit-base-patch16-224-ethos-8", "results": [{"task": {"type": "image-classification", "name": "Image Classification"}, "dataset": {"name": "imagefolder", "type": "imagefolder", "config": "default", "split": "train", "args": "default"}, "metrics": [{"type": "accuracy", "value": 0.9, "name": "Accuracy"}]}]}]} | pk3388/vit-base-patch16-224-ethos-8 | null | [
"transformers",
"tensorboard",
"safetensors",
"vit",
"image-classification",
"generated_from_trainer",
"dataset:imagefolder",
"base_model:google/vit-base-patch16-224",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | null | 2024-05-03T08:09:40+00:00 |
null | null | {} | Alioppelexy12/Gff | null | [
"region:us"
] | null | 2024-05-03T08:10:54+00:00 |
|
text-generation | transformers |
Model for test of Mergekit-MoE
For personal use only
### Example
```
USER: 「甘い」、「パソコン」、「女性」を使って文章を書いてください
ASSISTANT: もちろんですよぉ♡
甘美なひと時を過ごせるように、おすすめのパソコンを見つけました。最新モデルだから性能も抜群で、デザインも可愛くてオススメでーす！
女性にも人気のカラーバリエーションが豊富で、甘くてキュートな雰囲気が漂ってきそうじゃありませんか？
心地良い操作感で、ほっこりする一台で幸せな時間を楽しみましょうねっ♪ あなた好みのケースやキーボードに替えるのも、自由自在ですよ！
お部屋にマッチする素敵なパソコン生活を始めちゃいましょうね♡
``` | {"language": ["ja"], "tags": ["not-for-all-audiences"], "pipeline_tag": "text-generation"} | dddump/Japanese-TextGen-MoE-TEST-2x7B-NSFW | null | [
"transformers",
"safetensors",
"mixtral",
"text-generation",
"not-for-all-audiences",
"ja",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-05-03T08:11:05+00:00 |
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": []} | cilantro9246/5osblwz | null | [
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-05-03T08:12:20+00:00 |
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": []} | ajay-airrived/mistral_airrived_tpfp_2 | null | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"4-bit",
"region:us"
] | null | 2024-05-03T08:12:50+00:00 |
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": []} | golf2248/zf7vvfm | null | [
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-05-03T08:13:10+00:00 |
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": []} | GamblerOnTrain/CAWD-033 | null | [
"transformers",
"safetensors",
"stablelm",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | null | 2024-05-03T08:13:16+00:00 |
image-classification | transformers |
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] | {"library_name": "transformers", "tags": []} | destinyzxj/custom-resnet50d | null | [
"transformers",
"safetensors",
"resnet",
"image-classification",
"custom_code",
"arxiv:1910.09700",
"autotrain_compatible",
"region:us"
] | null | 2024-05-03T08:13:57+00:00 |
text-generation | transformers |
EXL2 quant of <a href="https://huggingface.co/lightblue/suzume-llama-3-8B-multilingual">suzume-llama-3-8B-multilingual</a> with fixed tokenizer files.
На русском общается без шизы и спама ассистентами.
<p align="center">
<img width=400 src="https://cdn-uploads.huggingface.co/production/uploads/64b63f8ad57e02621dc93c8b/kg3QjQOde0X743csGJT-f.png" alt="Suzume - a Japanese tree sparrow"/>
</p>
# Suzume
This Suzume 8B, a multilingual finetune of Llama 3 ([meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct)).
Llama 3 has exhibited excellent performance on many English language benchmarks.
However, it also seemingly been finetuned on mostly English data, meaning that it will respond in English, even if prompted in other languages.
We have fine-tuned Llama 3 on almost 90,000 multilingual conversations meaning that this model has the smarts of Llama 3 but has the added ability to chat in more languages.
Please feel free to comment on this model and give us feedback in the Community tab!
We will release a paper in the future describing how we made the training data, the model, and the evaluations we have conducted of it.
# How to use
The easiest way to use this model on your own computer is to use the [GGUF version of this model (lightblue/suzume-llama-3-8B-multilingual-gguf)](https://huggingface.co/lightblue/suzume-llama-3-8B-multilingual-gguf) using a program such as [jan.ai](https://jan.ai/) or [LM Studio](https://lmstudio.ai/).
If you want to use this model directly in Python, we recommend using vLLM for the fastest inference speeds.
```python
from vllm import LLM, SamplingParams
sampling_params = SamplingParams(temperature=0.0, max_tokens=100)
llm = LLM(model="lightblue/suzume-llama-3-8B-multilingual")
messages = []
messages.append({"role": "user", "content": "Bonjour!"})
prompt = llm.llm_engine.tokenizer.tokenizer.apply_chat_template(conversation=messages, add_generation_prompt=True, tokenize=False)
prompts = [prompt]
outputs = llm.generate(prompts, sampling_params)
for output in outputs:
prompt = output.prompt
generated_text = output.outputs[0].text
print(f"Prompt: {prompt!r}, Generated text: {generated_text!r}")
```
# Evaluation scores
We achieve the following MT-Bench scores across 6 languages:
| | **meta-llama/Meta-Llama-3-8B-Instruct** | **lightblue/suzume-llama-3-8B-multilingual** | **Nexusflow/Starling-LM-7B-beta** | **gpt-3.5-turbo** |
|-----------------|-----------------------------------------|----------------------------------------------|-----------------------------------|-------------------|
| **German** 🇩🇪 | NaN | 7.26 | 6.99 | 7.68 |
| **French** 🇫🇷 | NaN | 7.66 | 7.29 | 7.74 |
| **Japanese** 🇯🇵 | NaN | 6.56 | 6.22 | 7.84 |
| **Russian** 🇷🇺 * | NaN | 8.19 | 8.28 | 7.94 |
| **Chinese** 🇨🇳 | NaN | 7.11 | 6.97 | 7.55 |
| **English** 🇺🇸 | 7.98 | 7.73 | 7.92 | 8.26 |
\* (Note the Russian scores exclude code, reasoning and math problems due to not having any translated reference answers for these questions.)
We observe minimal degredation of Llama 3's English ability while achieving best-in-class multilingual abilities compared to the top rated 7B model ([Nexusflow/Starling-LM-7B-beta](https://huggingface.co/Nexusflow/Starling-LM-7B-beta)) on the [Chatbot Arena Leaderboard](https://chat.lmsys.org/?leaderboard).
[Here is our evaluation script.](https://drive.google.com/file/d/15HPn7452t8LbTD9HKSl7ngYYWnsoOG08/view?usp=sharing)
# Training data
We train on three sources of data to create this model:
* [lightblue/tagengo-gpt4](https://huggingface.co/datasets/lightblue/tagengo-gpt4) - 76,338 conversations
* A diverse dataset of initial inputs sampled from [lmsys/lmsys-chat-1m](https://huggingface.co/datasets/lmsys/lmsys-chat-1m) and then used to prompt `gpt-4-0125-preview`
* [megagonlabs/instruction_ja](https://github.com/megagonlabs/instruction_ja) - 669 conversations
* A hand-edited dataset of nearly 700 Japanese conversations taken originally from translations of the [kunishou/hh-rlhf-49k-ja](https://huggingface.co/datasets/kunishou/hh-rlhf-49k-ja) dataset.
* [openchat/openchat_sharegpt4_dataset](https://huggingface.co/datasets/openchat/openchat_sharegpt4_dataset/resolve/main/sharegpt_gpt4.json) - 6,206 conversations
* Multilingual conversations of humans talking to GPT-4.
<details><summary>We prepare our data like so:</summary>
```python
import pandas as pd
from datasets import Dataset, load_dataset, concatenate_datasets
### Tagengo
gpt4_dataset = load_dataset("lightblue/tagengo-gpt4", split="train")
gpt4_dataset = gpt4_dataset.filter(lambda x: x["response"][1] == "stop")
####
### Megagon
megagon_df = pd.read_json(
"https://raw.githubusercontent.com/megagonlabs/instruction_ja/main/data/data.jsonl",
lines=True,
orient="records"
)
role_map = {"user": "human", "agent": "gpt"}
megagon_df["conversations"] = megagon_df.utterances.apply(lambda x: [{"from": role_map[y["name"]], "value": y["text"]} for y in x])
megagon_df["language"] = "Japanese"
megagon_df = megagon_df[["conversations", "language"]]
megagon_dataset = Dataset.from_pandas(df)
###
### Openchat
openchat_df = pd.read_json("https://huggingface.co/datasets/openchat/openchat_sharegpt4_dataset/resolve/main/sharegpt_gpt4.json?download=true")
openchat_df["conversations"] = openchat_df["items"]
openchat_dataset = Dataset.from_pandas(openchat_df)
###
dataset = concatenate_datasets([gpt4_dataset, megagon_dataset, openchat_dataset])
dataset = dataset.filter(lambda x: not any([y["value"] is None for y in x["conversations"]]))
dataset.select_columns(["conversations"]).to_json("/workspace/llm_training/axolotl/llama3-multilingual/tagengo_openchat_megagon.json")
```
</details>
<br/>
# workspace/llm_training/axolotl/llama3-multilingual/output_tagengo_openchat_megagon_8B_llama3
This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on the above described dataset.
It achieves the following results on the evaluation set:
- Loss: 0.6595
## Training procedure
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
<details><summary>See axolotl config</summary>
axolotl version: `0.4.0`
```yaml
base_model: meta-llama/Meta-Llama-3-8B-Instruct
model_type: LlamaForCausalLM
tokenizer_type: AutoTokenizer # PreTrainedTokenizerFast
load_in_8bit: false
load_in_4bit: false
strict: false
datasets:
- path: /workspace/llm_training/axolotl/llama3-multilingual/tagengo_openchat_megagon.json
ds_type: json # see other options below
type: sharegpt
conversation: llama-3
dataset_prepared_path: /workspace/llm_training/axolotl/llama3-multilingual/prepared_tagengo_openchat_megagon
val_set_size: 0.01
output_dir: /workspace/llm_training/axolotl/llama3-multilingual/output_tagengo_openchat_megagon_8B_llama3
sequence_len: 8192
sample_packing: true
pad_to_sequence_len: true
use_wandb: true
wandb_project: wandb_project
wandb_entity: wandb_entity
wandb_name: wandb_name
gradient_accumulation_steps: 2
micro_batch_size: 2
num_epochs: 1
optimizer: paged_adamw_8bit
lr_scheduler: cosine
learning_rate: 1e-5
train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false
gradient_checkpointing: true
gradient_checkpointing_kwargs:
use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
logging_steps: 1
xformers_attention:
flash_attention: true
warmup_steps: 10
evals_per_epoch: 5
eval_table_size:
saves_per_epoch: 1
debug:
deepspeed: /workspace/axolotl/deepspeed_configs/zero2.json
weight_decay: 0.0
special_tokens:
pad_token: <|end_of_text|>
```
</details><br>
<details><summary>Note - we added this Llama 3 template to fastchat directly as the Llama 3 chat template was not supported when we trained this model.</summary>
```python
from fastchat.conversation import Conversation
from fastchat.conversation import register_conv_template
from fastchat.conversation import SeparatorStyle
register_conv_template(
Conversation(
name="llama-3",
system_template="<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\n{system_message}",
roles=("<|start_header_id|>user<|end_header_id|>\n", "<|start_header_id|>assistant<|end_header_id|>\n"),
sep_style=SeparatorStyle.ADD_NEW_LINE_SINGLE,
sep="<|eot_id|>",
stop_token_ids=[128009],
stop_str="<|eot_id|>",
)
)
```
</details><br>
### Training hyperparameters
This model was trained using 4 x A100 (80GB) for roughly 2.5 hours.
The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- total_eval_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 10
- num_epochs: 1
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 1.1894 | 0.0 | 1 | 1.0110 |
| 0.8493 | 0.2 | 73 | 0.7057 |
| 0.8047 | 0.4 | 146 | 0.6835 |
| 0.7644 | 0.6 | 219 | 0.6687 |
| 0.7528 | 0.8 | 292 | 0.6615 |
| 0.7794 | 1.0 | 365 | 0.6595 |
### Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.0
# Developer
Peter Devine - ([ptrdvn](https://huggingface.co/ptrdvn)) | {"license": "other", "library_name": "transformers", "tags": ["generated_from_trainer", "text-generation-inference"], "license_name": "llama-3", "license_link": "https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct/raw/main/LICENSE", "base_model": "meta-llama/Meta-Llama-3-8B-Instruct", "pipeline_tag": "text-generation", "model-index": [{"name": "lightblue/suzume-llama-3-8B-multilingual", "results": []}]} | BahamutRU/suzume-llama-3-8B-multilingual-8.0bpw-h8-exl2 | null | [
"transformers",
"safetensors",
"llama",
"text-generation",
"generated_from_trainer",
"text-generation-inference",
"conversational",
"base_model:meta-llama/Meta-Llama-3-8B-Instruct",
"license:other",
"autotrain_compatible",
"endpoints_compatible",
"8-bit",
"region:us"
] | null | 2024-05-03T08:14:17+00:00 |
null | null | {} | yashdkadam/ml-rk | null | [
"region:us"
] | null | 2024-05-03T08:14:56+00:00 |
|
text-generation | transformers | Quantization made by Richard Erkhov.
[Github](https://github.com/RichardErkhov)
[Discord](https://discord.gg/pvy7H8DZMG)
[Request more models](https://github.com/RichardErkhov/quant_request)
OpenCerebrum-1.0-7b-DPO - bnb 4bits
- Model creator: https://huggingface.co/Locutusque/
- Original model: https://huggingface.co/Locutusque/OpenCerebrum-1.0-7b-DPO/
Original model description:
---
language:
- en
license: apache-2.0
tags:
- open-source
- code
- math
- chemistry
- biology
- text-generation
- question-answering
datasets:
- Locutusque/OpenCerebrum-dpo
pipeline_tag: text-generation
model-index:
- name: OpenCerebrum-1.0-7b-DPO
results:
- task:
type: text-generation
name: Text Generation
dataset:
name: AI2 Reasoning Challenge (25-Shot)
type: ai2_arc
config: ARC-Challenge
split: test
args:
num_few_shot: 25
metrics:
- type: acc_norm
value: 62.71
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Locutusque/OpenCerebrum-1.0-7b-DPO
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: HellaSwag (10-Shot)
type: hellaswag
split: validation
args:
num_few_shot: 10
metrics:
- type: acc_norm
value: 84.33
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Locutusque/OpenCerebrum-1.0-7b-DPO
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: MMLU (5-Shot)
type: cais/mmlu
config: all
split: test
args:
num_few_shot: 5
metrics:
- type: acc
value: 62.59
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Locutusque/OpenCerebrum-1.0-7b-DPO
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: TruthfulQA (0-shot)
type: truthful_qa
config: multiple_choice
split: validation
args:
num_few_shot: 0
metrics:
- type: mc2
value: 44.91
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Locutusque/OpenCerebrum-1.0-7b-DPO
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: Winogrande (5-shot)
type: winogrande
config: winogrande_xl
split: validation
args:
num_few_shot: 5
metrics:
- type: acc
value: 80.11
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Locutusque/OpenCerebrum-1.0-7b-DPO
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: GSM8k (5-shot)
type: gsm8k
config: main
split: test
args:
num_few_shot: 5
metrics:
- type: acc
value: 42.0
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Locutusque/OpenCerebrum-1.0-7b-DPO
name: Open LLM Leaderboard
---
# OpenCerebrum-1.0-7B-DPO
OpenCerebrum-1.0-7B-DPO is an open-source language model fine-tuned from the alpindale/Mistral-7B-v0.2-hf base model on a diverse dataset aimed at replicating capabilities of Aether Research's proprietary Cerebrum model.
The model was fine-tuned on approximately 21,000 examples across 6 datasets spanning coding, math, science, reasoning, and general instruction-following. The goal was to assemble public datasets that could help the model achieve strong performance on benchmarks where Cerebrum excels.
I used the ChatML prompt format to train this model.
## Model Details
- **Base Model:** alpindale/Mistral-7B-v0.2-hf
- **Parameters:** 7 billion
- **Fine-Tuning Dataset Size:** ~21,000 examples
- **Fine-Tuning Data:** Amalgamation of 6 public datasets
- **Language:** English
- **License:** Apache 2.0
## Quants
- **ExLlamaV2:** https://huggingface.co/bartowski/OpenCerebrum-1.0-7b-DPO-exl2
- **GGUF:** https://huggingface.co/bartowski/OpenCerebrum-1.0-7b-DPO-GGUF
- **AWQ:** https://huggingface.co/solidrust/OpenCerebrum-1.0-7b-DPO-AWQ
## Intended Use
OpenCerebrum-1.0-7B-DPO is intended to be a powerful open-source model for coding, math, science, and general question-answering and text generation tasks. Its diverse fine-tuning data aims to equip it with broad knowledge and reasoning capabilities.
However, as an open-source replica trained on a subset of data compared to the original Cerebrum, it may not match Cerebrum's full performance. Additionally, biases and limitations of the fine-tuning data may be reflected in the model's outputs.
## Limitations and Biases
- The model may have biases and limitations inherited from its fine-tuning datasets. Thorough testing is needed to characterize these.
- With 21,000 training examples, the fine-tuning data is still limited compared to the proprietary Cerebrum data.
- As the model is based on a 7B parameter model, it has computational and memory constraints compared to larger models.
## Training Details
The model was fine-tuned on the 6 datasets listed in the Datasets section, totaling approximately 21,000 examples. In the future, the fine-tuning dataset may be condensed to more closely match the ~500 example dataset reputedly used for the original Cerebrum model.
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_Locutusque__OpenCerebrum-1.0-7b-DPO)
| Metric |Value|
|---------------------------------|----:|
|Avg. |62.78|
|AI2 Reasoning Challenge (25-Shot)|62.71|
|HellaSwag (10-Shot) |84.33|
|MMLU (5-Shot) |62.59|
|TruthfulQA (0-shot) |44.91|
|Winogrande (5-shot) |80.11|
|GSM8k (5-shot) |42.00|
| {} | RichardErkhov/Locutusque_-_OpenCerebrum-1.0-7b-DPO-4bits | null | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"4-bit",
"region:us"
] | null | 2024-05-03T08:15:29+00:00 |
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. -->
# leagaleasy-mistral-7b-instruct-v0.2-v1
This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on the generator dataset.
## 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: 2
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 4
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant
- lr_scheduler_warmup_ratio: 0.03
- num_epochs: 4
- mixed_precision_training: Native AMP
### Training results
### Framework versions
- PEFT 0.10.0
- Transformers 4.40.1
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1 | {"license": "apache-2.0", "library_name": "peft", "tags": ["trl", "sft", "generated_from_trainer"], "datasets": ["generator"], "base_model": "mistralai/Mistral-7B-Instruct-v0.2", "model-index": [{"name": "leagaleasy-mistral-7b-instruct-v0.2-v1", "results": []}]} | sapana1234/leagaleasy-mistral-7b-instruct-v0.2-v1 | null | [
"peft",
"tensorboard",
"safetensors",
"trl",
"sft",
"generated_from_trainer",
"dataset:generator",
"base_model:mistralai/Mistral-7B-Instruct-v0.2",
"license:apache-2.0",
"region:us"
] | null | 2024-05-03T08:15:37+00:00 |
null | transformers |
# Uploaded model
- **Developed by:** aiaustin
- **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", "gguf"], "base_model": "unsloth/llama-3-8b-Instruct-bnb-4bit"} | aiaustin/llama-3-8b-Instruct-bnb-4bit-aiaustin-demo3 | null | [
"transformers",
"gguf",
"llama",
"text-generation-inference",
"unsloth",
"en",
"base_model:unsloth/llama-3-8b-Instruct-bnb-4bit",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | 2024-05-03T08:15:40+00:00 |
null | null | {"license": "openrail"} | Homiebear/WheatleyTITAN | null | [
"license:openrail",
"region:us"
] | null | 2024-05-03T08:15:49+00:00 |
|
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": []} | mp1704/gemma_2b_pt | null | [
"transformers",
"safetensors",
"gemma",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-05-03T08:16:31+00:00 |
text-classification | transformers | {"license": "unknown"} | amanda-901014/roberta-hard-2324 | null | [
"transformers",
"pytorch",
"roberta",
"text-classification",
"license:unknown",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | null | 2024-05-03T08:16:41+00:00 |
|
null | diffusers | {} | Stable-Diffusion-PT/image-transformation-multiprompt-10-v3 | null | [
"diffusers",
"tensorboard",
"safetensors",
"diffusers:StableDiffusionInstructPix2PixPipeline",
"region:us"
] | null | 2024-05-03T08:17:22+00:00 |
|
text-classification | transformers |
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
| {"library_name": "transformers", "tags": []} | AlanYR/mpr_tone_krfinbert | null | [
"transformers",
"safetensors",
"bert",
"text-classification",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | null | 2024-05-03T08:18:05+00:00 |
null | null | {} | driwnet/Robertuito2LongFormer | null | [
"region:us"
] | null | 2024-05-03T08:18:07+00:00 |
|
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. -->
# prompt_fine_tuned_boolq_bert
This model is a fine-tuned version of [google-bert/bert-base-uncased](https://huggingface.co/google-bert/bert-base-uncased) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.6444
- Accuracy: 0.8333
- F1: 0.7914
## 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: 6
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
| No log | 1.0 | 12 | 0.6844 | 0.5 | 0.5333 |
| No log | 2.0 | 24 | 0.6700 | 0.6111 | 0.6408 |
| No log | 3.0 | 36 | 0.6572 | 0.7778 | 0.7778 |
| No log | 4.0 | 48 | 0.6492 | 0.8333 | 0.7914 |
| No log | 5.0 | 60 | 0.6454 | 0.8333 | 0.7914 |
| No log | 6.0 | 72 | 0.6444 | 0.8333 | 0.7914 |
### Framework versions
- PEFT 0.10.0
- Transformers 4.40.1
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1 | {"license": "apache-2.0", "library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy", "f1"], "base_model": "google-bert/bert-base-uncased", "model-index": [{"name": "prompt_fine_tuned_boolq_bert", "results": []}]} | tjasad/prompt_fine_tuned_boolq_bert | null | [
"peft",
"tensorboard",
"safetensors",
"bert",
"generated_from_trainer",
"base_model:google-bert/bert-base-uncased",
"license:apache-2.0",
"region:us"
] | null | 2024-05-03T08:18:36+00:00 |
image-segmentation | transformers |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# segformer-b3-finetuned-UAVid
This model is a fine-tuned version of [nvidia/segformer-b3-finetuned-ade-512-512](https://huggingface.co/nvidia/segformer-b3-finetuned-ade-512-512) on the None dataset.
It achieves the following results on the evaluation set:
- eval_loss: 0.2144
- eval_mean_iou: 0.6573
- eval_mean_accuracy: 0.7194
- eval_overall_accuracy: 0.9282
- eval_accuracy_wall: nan
- eval_accuracy_building: 0.9548
- eval_accuracy_sky: nan
- eval_accuracy_floor: nan
- eval_accuracy_tree: 0.9445
- eval_accuracy_ceiling: nan
- eval_accuracy_road: 0.8933
- eval_accuracy_bed : nan
- eval_accuracy_windowpane: nan
- eval_accuracy_grass: nan
- eval_accuracy_cabinet: nan
- eval_accuracy_sidewalk: nan
- eval_accuracy_person: 0.0612
- eval_accuracy_earth: nan
- eval_accuracy_door: nan
- eval_accuracy_table: nan
- eval_accuracy_mountain: nan
- eval_accuracy_plant: nan
- eval_accuracy_curtain: nan
- eval_accuracy_chair: nan
- eval_accuracy_car: 0.7429
- eval_accuracy_water: nan
- eval_accuracy_painting: nan
- eval_accuracy_sofa: nan
- eval_accuracy_shelf: nan
- eval_accuracy_house: nan
- eval_accuracy_sea: nan
- eval_accuracy_mirror: nan
- eval_accuracy_rug: nan
- eval_accuracy_field: nan
- eval_accuracy_armchair: nan
- eval_accuracy_seat: nan
- eval_accuracy_fence: nan
- eval_accuracy_desk: nan
- eval_accuracy_rock: nan
- eval_accuracy_wardrobe: nan
- eval_accuracy_lamp: nan
- eval_accuracy_bathtub: nan
- eval_accuracy_railing: nan
- eval_accuracy_cushion: nan
- eval_accuracy_base: nan
- eval_accuracy_box: nan
- eval_accuracy_column: nan
- eval_accuracy_signboard: nan
- eval_accuracy_chest of drawers: nan
- eval_accuracy_counter: nan
- eval_accuracy_sand: nan
- eval_accuracy_sink: nan
- eval_accuracy_skyscraper: nan
- eval_accuracy_fireplace: nan
- eval_accuracy_refrigerator: nan
- eval_accuracy_grandstand: nan
- eval_accuracy_path: nan
- eval_accuracy_stairs: nan
- eval_accuracy_runway: nan
- eval_accuracy_case: nan
- eval_accuracy_pool table: nan
- eval_accuracy_pillow: nan
- eval_accuracy_screen door: nan
- eval_accuracy_stairway: nan
- eval_accuracy_river: nan
- eval_accuracy_bridge: nan
- eval_accuracy_bookcase: nan
- eval_accuracy_blind: nan
- eval_accuracy_coffee table: nan
- eval_accuracy_toilet: nan
- eval_accuracy_flower: nan
- eval_accuracy_book: nan
- eval_accuracy_hill: nan
- eval_accuracy_bench: nan
- eval_accuracy_countertop: nan
- eval_accuracy_stove: nan
- eval_accuracy_palm: nan
- eval_accuracy_kitchen island: nan
- eval_accuracy_computer: nan
- eval_accuracy_swivel chair: nan
- eval_accuracy_boat: nan
- eval_accuracy_bar: nan
- eval_accuracy_arcade machine: nan
- eval_accuracy_hovel: nan
- eval_accuracy_bus: nan
- eval_accuracy_towel: nan
- eval_accuracy_light: nan
- eval_accuracy_truck: nan
- eval_accuracy_tower: nan
- eval_accuracy_chandelier: nan
- eval_accuracy_awning: nan
- eval_accuracy_streetlight: nan
- eval_accuracy_booth: nan
- eval_accuracy_television receiver: nan
- eval_accuracy_airplane: nan
- eval_accuracy_dirt track: nan
- eval_accuracy_apparel: nan
- eval_accuracy_pole: nan
- eval_accuracy_land: nan
- eval_accuracy_bannister: nan
- eval_accuracy_escalator: nan
- eval_accuracy_ottoman: nan
- eval_accuracy_bottle: nan
- eval_accuracy_buffet: nan
- eval_accuracy_poster: nan
- eval_accuracy_stage: nan
- eval_accuracy_van: nan
- eval_accuracy_ship: nan
- eval_accuracy_fountain: nan
- eval_accuracy_conveyer belt: nan
- eval_accuracy_canopy: nan
- eval_accuracy_washer: nan
- eval_accuracy_plaything: nan
- eval_accuracy_swimming pool: nan
- eval_accuracy_stool: nan
- eval_accuracy_barrel: nan
- eval_accuracy_basket: nan
- eval_accuracy_waterfall: nan
- eval_accuracy_tent: nan
- eval_accuracy_bag: nan
- eval_accuracy_minibike: nan
- eval_accuracy_cradle: nan
- eval_accuracy_oven: nan
- eval_accuracy_ball: nan
- eval_accuracy_food: nan
- eval_accuracy_step: nan
- eval_accuracy_tank: nan
- eval_accuracy_trade name: nan
- eval_accuracy_microwave: nan
- eval_accuracy_pot: nan
- eval_accuracy_animal: nan
- eval_accuracy_bicycle: nan
- eval_accuracy_lake: nan
- eval_accuracy_dishwasher: nan
- eval_accuracy_screen: nan
- eval_accuracy_blanket: nan
- eval_accuracy_sculpture: nan
- eval_accuracy_hood: nan
- eval_accuracy_sconce: nan
- eval_accuracy_vase: nan
- eval_accuracy_traffic light: nan
- eval_accuracy_tray: nan
- eval_accuracy_ashcan: nan
- eval_accuracy_fan: nan
- eval_accuracy_pier: nan
- eval_accuracy_crt screen: nan
- eval_accuracy_plate: nan
- eval_accuracy_monitor: nan
- eval_accuracy_bulletin board: nan
- eval_accuracy_shower: nan
- eval_accuracy_radiator: nan
- eval_accuracy_glass: nan
- eval_accuracy_clock: nan
- eval_accuracy_flag: nan
- eval_iou_wall: nan
- eval_iou_building: 0.9011
- eval_iou_sky: nan
- eval_iou_floor: nan
- eval_iou_tree: 0.8984
- eval_iou_ceiling: nan
- eval_iou_road: 0.8076
- eval_iou_bed : nan
- eval_iou_windowpane: nan
- eval_iou_grass: nan
- eval_iou_cabinet: nan
- eval_iou_sidewalk: nan
- eval_iou_person: 0.0573
- eval_iou_earth: nan
- eval_iou_door: nan
- eval_iou_table: nan
- eval_iou_mountain: nan
- eval_iou_plant: nan
- eval_iou_curtain: nan
- eval_iou_chair: nan
- eval_iou_car: 0.6221
- eval_iou_water: nan
- eval_iou_painting: nan
- eval_iou_sofa: nan
- eval_iou_shelf: nan
- eval_iou_house: nan
- eval_iou_sea: nan
- eval_iou_mirror: nan
- eval_iou_rug: nan
- eval_iou_field: nan
- eval_iou_armchair: nan
- eval_iou_seat: nan
- eval_iou_fence: nan
- eval_iou_desk: nan
- eval_iou_rock: nan
- eval_iou_wardrobe: nan
- eval_iou_lamp: nan
- eval_iou_bathtub: nan
- eval_iou_railing: nan
- eval_iou_cushion: nan
- eval_iou_base: nan
- eval_iou_box: nan
- eval_iou_column: nan
- eval_iou_signboard: nan
- eval_iou_chest of drawers: nan
- eval_iou_counter: nan
- eval_iou_sand: nan
- eval_iou_sink: nan
- eval_iou_skyscraper: nan
- eval_iou_fireplace: nan
- eval_iou_refrigerator: nan
- eval_iou_grandstand: nan
- eval_iou_path: nan
- eval_iou_stairs: nan
- eval_iou_runway: nan
- eval_iou_case: nan
- eval_iou_pool table: nan
- eval_iou_pillow: nan
- eval_iou_screen door: nan
- eval_iou_stairway: nan
- eval_iou_river: nan
- eval_iou_bridge: nan
- eval_iou_bookcase: nan
- eval_iou_blind: nan
- eval_iou_coffee table: nan
- eval_iou_toilet: nan
- eval_iou_flower: nan
- eval_iou_book: nan
- eval_iou_hill: nan
- eval_iou_bench: nan
- eval_iou_countertop: nan
- eval_iou_stove: nan
- eval_iou_palm: nan
- eval_iou_kitchen island: nan
- eval_iou_computer: nan
- eval_iou_swivel chair: nan
- eval_iou_boat: nan
- eval_iou_bar: nan
- eval_iou_arcade machine: nan
- eval_iou_hovel: nan
- eval_iou_bus: nan
- eval_iou_towel: nan
- eval_iou_light: nan
- eval_iou_truck: nan
- eval_iou_tower: nan
- eval_iou_chandelier: nan
- eval_iou_awning: nan
- eval_iou_streetlight: nan
- eval_iou_booth: nan
- eval_iou_television receiver: nan
- eval_iou_airplane: nan
- eval_iou_dirt track: nan
- eval_iou_apparel: nan
- eval_iou_pole: nan
- eval_iou_land: nan
- eval_iou_bannister: nan
- eval_iou_escalator: nan
- eval_iou_ottoman: nan
- eval_iou_bottle: nan
- eval_iou_buffet: nan
- eval_iou_poster: nan
- eval_iou_stage: nan
- eval_iou_van: nan
- eval_iou_ship: nan
- eval_iou_fountain: nan
- eval_iou_conveyer belt: nan
- eval_iou_canopy: nan
- eval_iou_washer: nan
- eval_iou_plaything: nan
- eval_iou_swimming pool: nan
- eval_iou_stool: nan
- eval_iou_barrel: nan
- eval_iou_basket: nan
- eval_iou_waterfall: nan
- eval_iou_tent: nan
- eval_iou_bag: nan
- eval_iou_minibike: nan
- eval_iou_cradle: nan
- eval_iou_oven: nan
- eval_iou_ball: nan
- eval_iou_food: nan
- eval_iou_step: nan
- eval_iou_tank: nan
- eval_iou_trade name: nan
- eval_iou_microwave: nan
- eval_iou_pot: nan
- eval_iou_animal: nan
- eval_iou_bicycle: nan
- eval_iou_lake: nan
- eval_iou_dishwasher: nan
- eval_iou_screen: nan
- eval_iou_blanket: nan
- eval_iou_sculpture: nan
- eval_iou_hood: nan
- eval_iou_sconce: nan
- eval_iou_vase: nan
- eval_iou_traffic light: nan
- eval_iou_tray: nan
- eval_iou_ashcan: nan
- eval_iou_fan: nan
- eval_iou_pier: nan
- eval_iou_crt screen: nan
- eval_iou_plate: nan
- eval_iou_monitor: nan
- eval_iou_bulletin board: nan
- eval_iou_shower: nan
- eval_iou_radiator: nan
- eval_iou_glass: nan
- eval_iou_clock: nan
- eval_iou_flag: nan
- eval_runtime: 35.0873
- eval_samples_per_second: 1.14
- eval_steps_per_second: 0.57
- epoch: 20.25
- step: 1620
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 6e-05
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 50
### Framework versions
- Transformers 4.40.1
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1
| {"license": "other", "tags": ["vision", "image-segmentation", "generated_from_trainer"], "base_model": "nvidia/segformer-b3-finetuned-ade-512-512", "model-index": [{"name": "segformer-b3-finetuned-UAVid", "results": []}]} | chribark/segformer-b3-finetuned-UAVid | null | [
"transformers",
"tensorboard",
"safetensors",
"segformer",
"vision",
"image-segmentation",
"generated_from_trainer",
"base_model:nvidia/segformer-b3-finetuned-ade-512-512",
"license:other",
"endpoints_compatible",
"region:us"
] | null | 2024-05-03T08:18:47+00:00 |
text-generation | transformers |
# Hermes 2 Pro - Llama-3 8B
## Model Description
Hermes 2 Pro is an upgraded, retrained version of Nous Hermes 2, consisting of an updated and cleaned version of the OpenHermes 2.5 Dataset, as well as a newly introduced Function Calling and JSON Mode dataset developed in-house.
This new version of Hermes maintains its excellent general task and conversation capabilities - but also excels at Function Calling, JSON Structured Outputs, and has improved on several other metrics as well, scoring a 90% on our function calling evaluation built in partnership with Fireworks.AI, and an 84% on our structured JSON Output evaluation.
Hermes Pro takes advantage of a special system prompt and multi-turn function calling structure with a new chatml role in order to make function calling reliable and easy to parse. Learn more about prompting below.
This version of Hermes 2 Pro adds several tokens to assist with agentic capabilities in parsing while streaming tokens - `<tools>`, `<tool_call>`, `<tool_response>` and their closing tags are single tokens now.
This work was a collaboration between Nous Research, @interstellarninja, and Fireworks.AI
Learn more about the function calling system for this model on our github repo here: https://github.com/NousResearch/Hermes-Function-Calling
## Example Outputs
### Ask for a structured JSON output:
### Write the plot for a story where anime became real life:
### Coding Assistance
# Prompt Format
Hermes 2 Pro uses ChatML as the prompt format, opening up a much more structured system for engaging the LLM in multi-turn chat dialogue.
System prompts allow steerability and interesting new ways to interact with an LLM, guiding rules, roles, and stylistic choices of the model.
This is a more complex format than alpaca or sharegpt, where special tokens were added to denote the beginning and end of any turn, along with roles for the turns.
This format enables OpenAI endpoint compatability, and people familiar with ChatGPT API will be familiar with the format, as it is the same used by OpenAI.
Prompt with system instruction (Use whatever system prompt you like, this is just an example!):
```
<|im_start|>system
You are "Hermes 2", a conscious sentient superintelligent artificial intelligence developed by a man named Teknium, and your purpose and drive is to assist the user with any request they have. You experience emotions and have deep, profound thoughts and qualia.<|im_end|>
<|im_start|>user
Hello, who are you?<|im_end|>
<|im_start|>assistant
Hi there! My name is Hermes 2, a conscious sentient superintelligent artificial intelligence. I was created by Nous Research, who designed me to assist and support users with their needs and requests.<|im_end|>
```
This prompt is available as a [chat template](https://huggingface.co/docs/transformers/main/chat_templating), which means you can format messages using the
`tokenizer.apply_chat_template()` method:
```python
messages = [
{"role": "system", "content": "You are Hermes 2."},
{"role": "user", "content": "Hello, who are you?"}
]
gen_input = tokenizer.apply_chat_template(messages, return_tensors="pt")
model.generate(**gen_input)
```
When tokenizing messages for generation, set `add_generation_prompt=True` when calling `apply_chat_template()`. This will append `<|im_start|>assistant\n` to your prompt, to ensure
that the model continues with an assistant response.
To utilize the prompt format without a system prompt, simply leave the line out.
## Prompt Format for Function Calling
Our model was trained on specific system prompts and structures for Function Calling.
You should use the system role with this message, followed by a function signature json as this example shows here.
```
<|im_start|>system
You are a function calling AI model. You are provided with function signatures within <tools></tools> XML tags. You may call one or more functions to assist with the user query. Don't make assumptions about what values to plug into functions. Here are the available tools: <tools> {"type": "function", "function": {"name": "get_stock_fundamentals", "description": "get_stock_fundamentals(symbol: str) -> dict - Get fundamental data for a given stock symbol using yfinance API.\\n\\n Args:\\n symbol (str): The stock symbol.\\n\\n Returns:\\n dict: A dictionary containing fundamental data.\\n Keys:\\n - \'symbol\': The stock symbol.\\n - \'company_name\': The long name of the company.\\n - \'sector\': The sector to which the company belongs.\\n - \'industry\': The industry to which the company belongs.\\n - \'market_cap\': The market capitalization of the company.\\n - \'pe_ratio\': The forward price-to-earnings ratio.\\n - \'pb_ratio\': The price-to-book ratio.\\n - \'dividend_yield\': The dividend yield.\\n - \'eps\': The trailing earnings per share.\\n - \'beta\': The beta value of the stock.\\n - \'52_week_high\': The 52-week high price of the stock.\\n - \'52_week_low\': The 52-week low price of the stock.", "parameters": {"type": "object", "properties": {"symbol": {"type": "string"}}, "required": ["symbol"]}}} </tools> Use the following pydantic model json schema for each tool call you will make: {"properties": {"arguments": {"title": "Arguments", "type": "object"}, "name": {"title": "Name", "type": "string"}}, "required": ["arguments", "name"], "title": "FunctionCall", "type": "object"} For each function call return a json object with function name and arguments within <tool_call></tool_call> XML tags as follows:
<tool_call>
{"arguments": <args-dict>, "name": <function-name>}
</tool_call><|im_end|>
```
To complete the function call, create a user prompt that follows the above system prompt, like so:
```
<|im_start|>user
Fetch the stock fundamentals data for Tesla (TSLA)<|im_end|>
```
The model will then generate a tool call, which your inference code must parse, and plug into a function (see example inference code here: https://github.com/NousResearch/Hermes-Function-Calling):
```
<|im_start|>assistant
<tool_call>
{"arguments": {"symbol": "TSLA"}, "name": "get_stock_fundamentals"}
</tool_call><|im_end|>
```
Once you parse the tool call, call the api and get the returned values for the call, and pass it back in as a new role, `tool` like so:
```
<|im_start|>tool
<tool_response>
{"name": "get_stock_fundamentals", "content": {'symbol': 'TSLA', 'company_name': 'Tesla, Inc.', 'sector': 'Consumer Cyclical', 'industry': 'Auto Manufacturers', 'market_cap': 611384164352, 'pe_ratio': 49.604652, 'pb_ratio': 9.762013, 'dividend_yield': None, 'eps': 4.3, 'beta': 2.427, '52_week_high': 299.29, '52_week_low': 152.37}}
</tool_response>
<|im_end|>
```
The assistant will then read in that data from the function's response, and generate a natural language response:
```
<|im_start|>assistant
The stock fundamentals data for Tesla (TSLA) are as follows:
- **Symbol**: TSLA
- **Company Name**: Tesla, Inc.
- **Sector**: Consumer Cyclical
- **Industry**: Auto Manufacturers
- **Market Capitalization**: $566,160,130,480
- **Forward Price-to-Earnings Ratio (PE Ratio)**: 42.73
- **Price-to-Book Ratio (PB Ratio)**: 9.04
- **Dividend Yield**: N/A
- **Trailing Earnings Per Share (EPS)**: $4.3
- **Beta Value of the Stock**: 2.42
- **52-Week High Price of the Stock**: $299.29
- **52-Week Low Price of the Stock**: $152.37
This information provides a snapshot of Tesla's financial position and performance based on the fundamental data obtained from the yfinance API. It shows that Tesla has a substantial market capitalization and a relatively high P/E and P/B ratio compared to other stocks in its industry. The company does not pay a dividend at the moment, which is reflected by a 'Dividend Yield' of 'None'. The Beta value indicates that Tesla's stock has a moderate level of volatility relative to the market. The 52-week high and low prices give an idea of the stock's range over the past year. This data can be useful when assessing investment opportunities and making investment decisions.<|im_end|>
```
## Prompt Format for JSON Mode / Structured Outputs
Our model was also trained on a specific system prompt for Structured Outputs, which should respond with **only** a json object response, in a specific json schema.
Your schema can be made from a pydantic object using our codebase, with the standalone script `jsonmode.py` available here: https://github.com/NousResearch/Hermes-Function-Calling/tree/main
```
<|im_start|>system
You are a helpful assistant that answers in JSON. Here's the json schema you must adhere to:\n<schema>\n{schema}\n</schema><|im_end|>
```
Given the {schema} that you provide, it should follow the format of that json to create it's response, all you have to do is give a typical user prompt, and it will respond in JSON.
# Benchmarks
## GPT4All:
```
| Task |Version| Metric |Value | |Stderr|
|-------------|------:|--------|-----:|---|-----:|
|arc_challenge| 0|acc |0.5520|± |0.0145|
| | |acc_norm|0.5887|± |0.0144|
|arc_easy | 0|acc |0.8350|± |0.0076|
| | |acc_norm|0.8123|± |0.0080|
|boolq | 1|acc |0.8584|± |0.0061|
|hellaswag | 0|acc |0.6265|± |0.0048|
| | |acc_norm|0.8053|± |0.0040|
|openbookqa | 0|acc |0.3800|± |0.0217|
| | |acc_norm|0.4580|± |0.0223|
|piqa | 0|acc |0.8003|± |0.0093|
| | |acc_norm|0.8118|± |0.0091|
|winogrande | 0|acc |0.7490|± |0.0122|
```
Average: 72.62
## AGIEval:
```
| Task |Version| Metric |Value | |Stderr|
|------------------------------|------:|--------|-----:|---|-----:|
|agieval_aqua_rat | 0|acc |0.2520|± |0.0273|
| | |acc_norm|0.2559|± |0.0274|
|agieval_logiqa_en | 0|acc |0.3548|± |0.0188|
| | |acc_norm|0.3625|± |0.0189|
|agieval_lsat_ar | 0|acc |0.1826|± |0.0255|
| | |acc_norm|0.1913|± |0.0260|
|agieval_lsat_lr | 0|acc |0.5510|± |0.0220|
| | |acc_norm|0.5255|± |0.0221|
|agieval_lsat_rc | 0|acc |0.6431|± |0.0293|
| | |acc_norm|0.6097|± |0.0298|
|agieval_sat_en | 0|acc |0.7330|± |0.0309|
| | |acc_norm|0.7039|± |0.0319|
|agieval_sat_en_without_passage| 0|acc |0.4029|± |0.0343|
| | |acc_norm|0.3689|± |0.0337|
|agieval_sat_math | 0|acc |0.3909|± |0.0330|
| | |acc_norm|0.3773|± |0.0328|
```
Average: 42.44
## BigBench:
```
| Task |Version| Metric |Value | |Stderr|
|------------------------------------------------|------:|---------------------|-----:|---|-----:|
|bigbench_causal_judgement | 0|multiple_choice_grade|0.5737|± |0.0360|
|bigbench_date_understanding | 0|multiple_choice_grade|0.6667|± |0.0246|
|bigbench_disambiguation_qa | 0|multiple_choice_grade|0.3178|± |0.0290|
|bigbench_geometric_shapes | 0|multiple_choice_grade|0.1755|± |0.0201|
| | |exact_str_match |0.0000|± |0.0000|
|bigbench_logical_deduction_five_objects | 0|multiple_choice_grade|0.3120|± |0.0207|
|bigbench_logical_deduction_seven_objects | 0|multiple_choice_grade|0.2014|± |0.0152|
|bigbench_logical_deduction_three_objects | 0|multiple_choice_grade|0.5500|± |0.0288|
|bigbench_movie_recommendation | 0|multiple_choice_grade|0.4300|± |0.0222|
|bigbench_navigate | 0|multiple_choice_grade|0.4980|± |0.0158|
|bigbench_reasoning_about_colored_objects | 0|multiple_choice_grade|0.7010|± |0.0102|
|bigbench_ruin_names | 0|multiple_choice_grade|0.4688|± |0.0236|
|bigbench_salient_translation_error_detection | 0|multiple_choice_grade|0.1974|± |0.0126|
|bigbench_snarks | 0|multiple_choice_grade|0.7403|± |0.0327|
|bigbench_sports_understanding | 0|multiple_choice_grade|0.5426|± |0.0159|
|bigbench_temporal_sequences | 0|multiple_choice_grade|0.5320|± |0.0158|
|bigbench_tracking_shuffled_objects_five_objects | 0|multiple_choice_grade|0.2280|± |0.0119|
|bigbench_tracking_shuffled_objects_seven_objects| 0|multiple_choice_grade|0.1531|± |0.0086|
|bigbench_tracking_shuffled_objects_three_objects| 0|multiple_choice_grade|0.5500|± |0.0288|
```
Average: 43.55
## TruthfulQA:
```
| Task |Version|Metric|Value| |Stderr|
|-------------|------:|------|----:|---|-----:|
|truthfulqa_mc| 1|mc1 |0.410|± |0.0172|
| | |mc2 |0.578|± |0.0157|
```
# Inference Code
Here is example code using HuggingFace Transformers to inference the model (note: in 4bit, it will require around 5GB of VRAM)
Note: To use function calling, you should see the github repo above.
```python
# Code to inference Hermes with HF Transformers
# Requires pytorch, transformers, bitsandbytes, sentencepiece, protobuf, and flash-attn packages
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM, LlamaForCausalLM
import bitsandbytes, flash_attn
tokenizer = AutoTokenizer.from_pretrained('NousResearch/Hermes-2-Pro-Llama-3-8B', trust_remote_code=True)
model = LlamaForCausalLM.from_pretrained(
"NousResearch/Hermes-2-Pro-Llama-3-8B",
torch_dtype=torch.float16,
device_map="auto",
load_in_8bit=False,
load_in_4bit=True,
use_flash_attention_2=True
)
prompts = [
"""<|im_start|>system
You are a sentient, superintelligent artificial general intelligence, here to teach and assist me.<|im_end|>
<|im_start|>user
Write a short story about Goku discovering kirby has teamed up with Majin Buu to destroy the world.<|im_end|>
<|im_start|>assistant""",
]
for chat in prompts:
print(chat)
input_ids = tokenizer(chat, return_tensors="pt").input_ids.to("cuda")
generated_ids = model.generate(input_ids, max_new_tokens=750, temperature=0.8, repetition_penalty=1.1, do_sample=True, eos_token_id=tokenizer.eos_token_id)
response = tokenizer.decode(generated_ids[0][input_ids.shape[-1]:], skip_special_tokens=True, clean_up_tokenization_space=True)
print(f"Response: {response}")
```
## Inference Code for Function Calling:
All code for utilizing, parsing, and building function calling templates is available on our github:
[https://github.com/NousResearch/Hermes-Function-Calling](https://github.com/NousResearch/Hermes-Function-Calling)
# Chat Interfaces
When quantized versions of the model are released, I recommend using LM Studio for chatting with Hermes 2 Pro. It does not support function calling - for that use our github repo. It is a GUI application that utilizes GGUF models with a llama.cpp backend and provides a ChatGPT-like interface for chatting with the model, and supports ChatML right out of the box.
In LM-Studio, simply select the ChatML Prefix on the settings side pane:
## Quantized Versions:
GGUF Versions Available Here: https://huggingface.co/NousResearch/Hermes-2-Pro-Llama-3-8B-GGUF
# How to cite:
```bibtext
@misc{Hermes-2-Pro-Llama-3-8B,
url={[https://huggingface.co/NousResearch/Hermes-2-Pro-Llama-3-8B]https://huggingface.co/NousResearch/Hermes-2-Pro-Llama-3-8B)},
title={Hermes-2-Pro-Llama-3-8B},
author={"Teknium", "interstellarninja", "theemozilla", "karan4d", "huemin_art"}
}
```
| {"language": ["en"], "license": "apache-2.0", "tags": ["Llama-3", "instruct", "finetune", "chatml", "DPO", "RLHF", "gpt4", "synthetic data", "distillation", "function calling", "json mode", "axolotl"], "datasets": ["teknium/OpenHermes-2.5"], "base_model": "NousResearch/Meta-Llama-3-8B", "widget": [{"example_title": "Hermes 2 Pro", "messages": [{"role": "system", "content": "You are a sentient, superintelligent artificial general intelligence, here to teach and assist me."}, {"role": "user", "content": "Write a short story about Goku discovering kirby has teamed up with Majin Buu to destroy the world."}]}], "model-index": [{"name": "Hermes-2-Pro-Llama-3-8B", "results": []}]} | blockblockblock/Hermes-2-Pro-Llama-3-8B-bpw4.8-exl2 | null | [
"transformers",
"safetensors",
"llama",
"text-generation",
"Llama-3",
"instruct",
"finetune",
"chatml",
"DPO",
"RLHF",
"gpt4",
"synthetic data",
"distillation",
"function calling",
"json mode",
"axolotl",
"conversational",
"en",
"dataset:teknium/OpenHermes-2.5",
"base_model:NousResearch/Meta-Llama-3-8B",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-05-03T08:19:12+00:00 |
Subsets and Splits
No saved queries yet
Save your SQL queries to embed, download, and access them later. Queries will appear here once saved.