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
listlengths 1
1.84k
| sha
null | created_at
stringlengths 25
25
|
|---|---|---|---|---|---|---|---|---|
text-generation | transformers | {} | farhananis005/Llama-3-8b-pygmalion-2-7b | null | [
"transformers",
"safetensors",
"mixtral",
"text-generation",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| null | 2024-04-28T01:31:46+00:00 |
|
null | null | {} | slipzeraAAAAAA/chz500 | null | [
"region:us"
]
| null | 2024-04-28T01:32:48+00:00 |
|
null | null | {} | ShenaoZhang/0.0_4iters_bs256_nodpo_only4w_iter_2 | null | [
"region:us"
]
| null | 2024-04-28T01:32:48+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": []} | golf2248/7y05xeo | null | [
"transformers",
"safetensors",
"stablelm",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| null | 2024-04-28T01:33:44+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": []} | golf2248/5xgnt4j | null | [
"transformers",
"safetensors",
"stablelm",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| null | 2024-04-28T01:33:49+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": []} | golf2248/6lgbvrk | null | [
"transformers",
"safetensors",
"stablelm",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| null | 2024-04-28T01:33:54+00:00 |
text-generation | transformers | {} | yiII1/gpt2-cnwiki-full_data-P100-V2 | null | [
"transformers",
"tensorboard",
"safetensors",
"gpt2",
"text-generation",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| null | 2024-04-28T01:35:02+00:00 |
|
null | null | {} | Anna15/sn25-2-5 | null | [
"region:us"
]
| null | 2024-04-28T01:35:53+00:00 |
|
null | null | {} | wanwanzhi/gemma-chinese | null | [
"region:us"
]
| null | 2024-04-28T01:37:34+00:00 |
|
text-generation | null |
# Qwen1.5-110B-Chat-GGUF
## Introduction
Qwen1.5 is the beta version of Qwen2, a transformer-based decoder-only language model pretrained on a large amount of data. In comparison with the previous released Qwen, the improvements include:
* 9 model sizes, including 0.5B, 1.8B, 4B, 7B, 14B, 32B, 72B, and 110B dense models, and an MoE model of 14B with 2.7B activated;
* Significant performance improvement in human preference for chat models;
* Multilingual support of both base and chat models;
* Stable support of 32K context length for models of all sizes
* No need of `trust_remote_code`.
For more details, please refer to our [blog post](https://qwenlm.github.io/blog/qwen1.5/) and [GitHub repo](https://github.com/QwenLM/Qwen1.5).
In this repo, we provide quantized models in the GGUF formats, including `q2_k`, `q3_k_m`, `q4_0`, `q4_k_m`, `q5_0`, `q5_k_m`, `q6_k` and `q8_0`.
## Model Details
Qwen1.5 is a language model series including decoder language models of different model sizes. For each size, we release the base language model and the aligned chat model. It is based on the Transformer architecture with SwiGLU activation, attention QKV bias, group query attention, mixture of sliding window attention and full attention, etc. Additionally, we have an improved tokenizer adaptive to multiple natural languages and codes. For the beta version, temporarily we did not include GQA (except for 32B and 110B) and the mixture of SWA and full attention.
## Training details
We pretrained the models with a large amount of data, and we post-trained the models with both supervised finetuning and direct preference optimization.
## Requirements
We advise you to clone [`llama.cpp`](https://github.com/ggerganov/llama.cpp) and install it following the official guide.
## How to use
For starters, the 110B model is large and for most GGUF files, due to the limitation of uploading, we split the byte strings into 2 or 3 segments, so you can see files with theirs names ended with `.a` or `.b`.
Cloning the repo may be inefficient, and thus you can manually download the GGUF file that you need or use `huggingface-cli` (`pip install huggingface_hub`). For each GGUF model, you need to download all the files with the same prefix. For example, for the q_5_k_m model, you need to download both files with `.a` and `.b` at the end.
```bash
huggingface-cli download Qwen/Qwen1.5-110B-Chat-GGUF qwen1_5-110b-chat-q5_k_m.gguf.a --local-dir . --local-dir-use-symlinks False
huggingface-cli download Qwen/Qwen1.5-110B-Chat-GGUF qwen1_5-110b-chat-q5_k_m.gguf.b --local-dir . --local-dir-use-symlinks False
```
After, you need to concatenate them to obtain a whole GGUF file:
```bash
cat qwen1_5-110b-chat-q5_k_m.gguf.* > qwen1_5-110b-chat-q5_k_m.gguf
```
We demonstrate how to use `llama.cpp` to run Qwen1.5:
```shell
./main -m qwen1_5-110b-chat-q5_k_m.gguf -n 512 --color -i -cml -f prompts/chat-with-qwen.txt
```
## Citation
If you find our work helpful, feel free to give us a cite.
```
@article{qwen,
title={Qwen Technical Report},
author={Jinze Bai and Shuai Bai and Yunfei Chu and Zeyu Cui and Kai Dang and Xiaodong Deng and Yang Fan and Wenbin Ge and Yu Han and Fei Huang and Binyuan Hui and Luo Ji and Mei Li and Junyang Lin and Runji Lin and Dayiheng Liu and Gao Liu and Chengqiang Lu and Keming Lu and Jianxin Ma and Rui Men and Xingzhang Ren and Xuancheng Ren and Chuanqi Tan and Sinan Tan and Jianhong Tu and Peng Wang and Shijie Wang and Wei Wang and Shengguang Wu and Benfeng Xu and Jin Xu and An Yang and Hao Yang and Jian Yang and Shusheng Yang and Yang Yao and Bowen Yu and Hongyi Yuan and Zheng Yuan and Jianwei Zhang and Xingxuan Zhang and Yichang Zhang and Zhenru Zhang and Chang Zhou and Jingren Zhou and Xiaohuan Zhou and Tianhang Zhu},
journal={arXiv preprint arXiv:2309.16609},
year={2023}
}
```
| {"language": ["en"], "license": "other", "tags": ["chat"], "license_name": "tongyi-qianwen", "license_link": "https://huggingface.co/Qwen/Qwen1.5-110B-Chat-GGUF/blob/main/LICENSE", "pipeline_tag": "text-generation"} | Qwen/Qwen1.5-110B-Chat-GGUF | null | [
"gguf",
"chat",
"text-generation",
"en",
"license:other",
"region:us"
]
| null | 2024-04-28T01:38:30+00:00 |
text2text-generation | transformers |
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
| {"library_name": "transformers", "tags": []} | kssumanth6/t5_small_sentence_polishing_generator_v1 | null | [
"transformers",
"safetensors",
"t5",
"text2text-generation",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| null | 2024-04-28T01:38:38+00:00 |
null | transformers |
# SilverFan/IceCoffeeRP-7b-Q6_K-GGUF
This model was converted to GGUF format from [`icefog72/IceCoffeeRP-7b`](https://huggingface.co/icefog72/IceCoffeeRP-7b) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
Refer to the [original model card](https://huggingface.co/icefog72/IceCoffeeRP-7b) for more details on the model.
## Use with llama.cpp
Install llama.cpp through brew.
```bash
brew install ggerganov/ggerganov/llama.cpp
```
Invoke the llama.cpp server or the CLI.
CLI:
```bash
llama-cli --hf-repo SilverFan/IceCoffeeRP-7b-Q6_K-GGUF --model icecoffeerp-7b.Q6_K.gguf -p "The meaning to life and the universe is"
```
Server:
```bash
llama-server --hf-repo SilverFan/IceCoffeeRP-7b-Q6_K-GGUF --model icecoffeerp-7b.Q6_K.gguf -c 2048
```
Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well.
```
git clone https://github.com/ggerganov/llama.cpp && cd llama.cpp && make && ./main -m icecoffeerp-7b.Q6_K.gguf -n 128
```
| {"license": "cc-by-nc-4.0", "library_name": "transformers", "tags": ["mergekit", "merge", "alpaca", "mistral", "not-for-all-audiences", "nsfw", "llama-cpp", "gguf-my-repo"], "model-index": [{"name": "IceCoffeeTest11", "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": 71.16, "name": "normalized accuracy"}], "source": {"url": "https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=icefog72/IceCoffeeTest11", "name": "Open LLM Leaderboard"}}, {"task": {"type": "text-generation", "name": "Text Generation"}, "dataset": {"name": "HellaSwag (10-Shot)", "type": "hellaswag", "split": "validation", "args": {"num_few_shot": 10}}, "metrics": [{"type": "acc_norm", "value": 87.74, "name": "normalized accuracy"}], "source": {"url": "https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=icefog72/IceCoffeeTest11", "name": "Open LLM Leaderboard"}}, {"task": {"type": "text-generation", "name": "Text Generation"}, "dataset": {"name": "MMLU (5-Shot)", "type": "cais/mmlu", "config": "all", "split": "test", "args": {"num_few_shot": 5}}, "metrics": [{"type": "acc", "value": 63.54, "name": "accuracy"}], "source": {"url": "https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=icefog72/IceCoffeeTest11", "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": 70.03}], "source": {"url": "https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=icefog72/IceCoffeeTest11", "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": 82.48, "name": "accuracy"}], "source": {"url": "https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=icefog72/IceCoffeeTest11", "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": 64.22, "name": "accuracy"}], "source": {"url": "https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=icefog72/IceCoffeeTest11", "name": "Open LLM Leaderboard"}}]}]} | SilverFan/IceCoffeeRP-7b-Q6_K-GGUF | null | [
"transformers",
"gguf",
"mergekit",
"merge",
"alpaca",
"mistral",
"not-for-all-audiences",
"nsfw",
"llama-cpp",
"gguf-my-repo",
"license:cc-by-nc-4.0",
"model-index",
"endpoints_compatible",
"region:us"
]
| null | 2024-04-28T01:42:20+00:00 |
text-classification | transformers |
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
Given a sentence, our model predicts whether or not the sentence contains "persuasive" language, or language designed to elicit emotions or change
readers' opinions. The model was tuned on the SemEval 2020 Task 11 dataset. However, we preprocessed the dataset to adapt it from
multilabel technique classification and span-classification to our binary classification task.
There are two revisions:
* BERT - we finetuned `bert-large-cased` on our main branch
* XLM-RoBERTa - we finetuned `xlm-roberta-base` on our `roberta` branch.
## 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:** Ultraviolet Text
- **Model type:** BERT / RoBERTa
- **Language(s) (NLP):** En
- **License:** MIT
- **Finetuned from model [optional]:** bert-large-cased / xlm-roberta-base
## How to Get Started with the Model
Use the code below to get started with the model.
### Loading from the main branch (BERT)
```py
from transformers import AutoModelForSequenceClassification, AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("bert-large-cased")
model = AutoModelForSequenceClassification.from_pretrained("chreh/persuasive_language_detector")
```
### Loading from the `roberta` branch (XLM RoBERTa)
```py
from transformers import AutoModelForSequenceClassification, AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("xlm-roberta-base")
model = AutoModelForSequenceClassification.from_pretrained("chreh/persuasive_language_detector", revision="roberta")
```
## 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. -->
Training data can be downloaded from [the Semeval website](https://propaganda.qcri.org/semeval2020-task11/).
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
The training was done using Huggingface Trainer on both our local machines and Intel Developer Cloud kernels, enabling us to prototype multiple models simultaneously.
#### Preprocessing [optional]
All sentences containing spans of persuasive language techniques were labeled as persuasive language examples, while all others
were labeled as examples of non-persuasive language.
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
The test data is from the test data of `sem_eval_2020_task_11`, which can be downloaded from [the original website](https://propaganda.qcri.org/semeval2020-task11/).
The test data contains 38.25% persuasive examples and non-persuasive examples 61.75%. Metrics can be found in the following section
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
Metrics are reported in the format (main_branch), (roberta branch)
* Accuracy - 0.7165140725669719, 0.7326693227091633
* Recall - 0.6875584658559402, 0.6822916666666666
* Precision - 0.5941794664510913, 0.6415279138099902
* F1 - 0.6374674761491761, 0.6612821807168097
Overall, the `roberta` branch performs better, and with faster inference times. Thus, we recommend users download from the `roberta` revision.
| {"language": ["en"], "license": "mit", "library_name": "transformers", "datasets": ["sem_eval_2020_task_11"]} | chreh/persuasive_language_detector | null | [
"transformers",
"safetensors",
"bert",
"text-classification",
"en",
"dataset:sem_eval_2020_task_11",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| null | 2024-04-28T01:43:37+00:00 |
fill-mask | transformers | {"language": ["en"]} | jeonsworld/punk-llama3-11.5B-mlm-full | null | [
"transformers",
"safetensors",
"llama",
"fill-mask",
"en",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| null | 2024-04-28T01:44:18+00:00 |
|
text-generation | transformers |
# Llama-3-8b-pygmalion-2-7b-v1
Llama-3-8b-pygmalion-2-7b-v1 is a Mixture of Experts (MoE) made with the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
* [winglian/Llama-3-8b-64k-PoSE](https://huggingface.co/winglian/Llama-3-8b-64k-PoSE)
* [PygmalionAI/pygmalion-2-7b](https://huggingface.co/PygmalionAI/pygmalion-2-7b)
## 🧩 Configuration
```yamlbase_model: winglian/Llama-3-8b-64k-PoSE
dtype: float16
gate_mode: cheap_embed
experts:
- source_model: winglian/Llama-3-8b-64k-PoSE
positive_prompts: ["You are an intelligent bot that is smart and sassy"]
- source_model: PygmalionAI/pygmalion-2-7b
positive_prompts: ["You are a sexy girl that loves to roleplay"]```
## 💻 Usage
```python
!pip install -qU transformers bitsandbytes accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "farhananis005/Llama-3-8b-pygmalion-2-7b-v1"
tokenizer = AutoTokenizer.from_pretrained(model)
pipeline = transformers.pipeline(
"text-generation",
model=model,
model_kwargs={"torch_dtype": torch.float16, "load_in_4bit": True},
)
messages = [{"role": "user", "content": "Explain what a Mixture of Experts is in less than 100 words."}]
prompt = pipeline.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])
``` | {"license": "apache-2.0", "tags": ["moe", "frankenmoe", "merge", "mergekit", "lazymergekit", "winglian/Llama-3-8b-64k-PoSE", "PygmalionAI/pygmalion-2-7b"], "base_model": ["winglian/Llama-3-8b-64k-PoSE", "PygmalionAI/pygmalion-2-7b"]} | farhananis005/Llama-3-8b-pygmalion-2-7b-v1 | null | [
"transformers",
"safetensors",
"mixtral",
"text-generation",
"moe",
"frankenmoe",
"merge",
"mergekit",
"lazymergekit",
"winglian/Llama-3-8b-64k-PoSE",
"PygmalionAI/pygmalion-2-7b",
"base_model:winglian/Llama-3-8b-64k-PoSE",
"base_model:PygmalionAI/pygmalion-2-7b",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| null | 2024-04-28T01:46:34+00:00 |
null | null | # Getting Started
Create a new conda environment for robomaster
```bash
conda create -n robomaster python=3.8
pip install robomaster dora-rs==0.3.3
```
Create a new conda environment for idefics2. This requirements file suppose that your using cu122.
```bash
conda create -n idefics2 python=3.10
conda activate idefics2
pip install -r requirements.txt
```
## Robomaster Jailbreak
### Installation of the Robomaster S1 Hack
This guide is an updated version of the original [Robomaster S1 SDK Hack Guide](https://www.bug-br.org.br/s1_sdk_hack.zip) and is intended for use on a Windows 11 system.
#### Prerequisites
Before you get started, you'll need the following:
- Robomaster S1 (do not update it to the latest version, as it may block the hack).
- [Robomaster App](https://www.dji.com/fr/robomaster-s1/downloads).
- [Android SDK Platform-Tools](https://developer.android.com/tools/releases/platform-tools). Simply unzip it and keep the path handy.
- A micro USB cable. If this guide doesn't work, there might be an issue with the cable, and you may need to replace it with one that supports data transfer.
#### Instructions
1. Start the Robomaster App and connect the Robomaster S1 using one of the two options provided (via router or via Wi-Fi).
2. While connected, use a micro USB cable to connect the robot to the computer's USB port. You should hear a beep sound, similar to when you connect any device. (Please note that no other Android device should be connected via USB during this process).
3. In the Lab section of the app, create a new Python application and paste the following code:
```python
def root_me(module):
__import__ = rm_define.__dict__['__builtins__']['__import__']
return __import__(module, globals(), locals(), [], 0)
builtins = root_me('builtins')
subprocess = root_me('subprocess')
proc = subprocess.Popen('/system/bin/adb_en.sh', shell=True, executable='/system/bin/sh', stdout=subprocess.PIPE, stderr=subprocess.PIPE)
```
4. Run the code; there should be no errors, and the console should display **Execution Complete**
5. Without closing the app, navigate to the folder containing the Android SDK Platform-Tools and open a terminal inside it.
6. Run the ADP command `.\adb.exe devices `. If everything is working correctly, you should see output similar to this: 
7. Execute the upload.sh script located in the folder `s1_SDK`.
8. Once everything has been executed, restart the S1 by turning it off and then back on. While it's booting up, you should hear two chimes instead of the usual single chime, indicating that the hack has been successful.
## Robomaster Connection
Make sure to be connected using the wifi hotspot of the robomaster which is the most stable one.
The default password for the hotpsot is: 12341234
You might need to have a second wifi card if you want to be able to run the demo with internet on.
## Post-Installation test
Please try running idefics2 with:
```bash
conda activate idefics2
python tests/test_idefics2.py
```
Please try running robomaster with:
```bash
conda activate robomaster
python tests/test_robomaster.py
```
## Running the demo
```bash
export HF_TOKEN=<TOKEN>
conda activate idefics2
# This requires dora==0.3.3, update with:
# cargo install dora-cli
dora up
dora start graphs/dataflow_robot_vlm.yml --attach --hot-reload
```
Current way to interact is by press up arrow key on laptop to record a message and send to the VLM
## Running the demo without robot
```bash
export HF_TOKEN=<TOKEN>
conda activate idefics2
# This requires dora==0.3.3, update with:
# cargo install dora-cli
dora up
dora start graphs/dataflow_vlm_basic.yml --attach --hot-reload
```
Current way to interact is by press up arrow key on laptop to record a message and send to the VLM
## Kill process in case of failure
Due to a Python GIL issue, we currently meed to kill processes manually. You can use the following command to do so:
```bash
pkill -f 'import dora;'
```
## LICENSE
While the source of this library is licensed under Apache-2.0, the usage of the Text to Speech(TTS) SystemEngine is licensed under Mozilla Public License 2.0 and GNU Lesser General Public License (LGPL) version 3.0.
Feel free to remove the TTS SystemEngine.
| {} | TommyZQ/csg-dora-rs | null | [
"region:us"
]
| null | 2024-04-28T01:48:29+00:00 |
null | null | * [English Version](./README_en.md)
# 模型簡介
* [TAIDE計畫](https://taide.tw/index)致力於開發符合台灣語言和文化特性的生成式人工智慧對話引擎模型，同時建構可信任的人工智慧環境。結合產學研能量，推動可信任生成式人工智慧的發展，提升台灣在國際競爭中的地位，促進產業發展，避免對外國技術的依賴。
* Llama3 TAIDE 系列模型以 Meta 公司釋出的 [LLaMA3-8b](https://llama.meta.com/docs/model-cards-and-prompt-formats/meta-llama-3/) 為基礎，導入台灣不同領域可用的文本與訓練素材，提高模型在正體中文回應的能力與特定任務的表現。公開釋出的模型如下:
* [Llama3-TAIDE-LX-8B-Chat-Alpha1](https://huggingface.co/taide/Llama3-TAIDE-LX-8B-Chat-Alpha1): 以 LLaMA3-8b 為基礎，使用繁體中文資料預訓練 (continuous pretraining)，並透過指令微調(instruction tuning)強化辦公室常用任務和多輪問答對話能力，適合聊天對話或任務協助的使用情境。Llama3-TAIDE-LX-8B-Chat-Alpha1 另外有提供[4 bit 量化模型](https://huggingface.co/taide/Llama3-TAIDE-LX-8B-Chat-Alpha1-4bit)，量化模型主要是提供使用者的便利性，可能會影響效能與更多不可預期的問題，還請使用者理解與注意。
# 模型參數
* 參數量: 8B
* 最大內容長度 (context length): 8K
* 繁中訓練資料 token 量: 43B
* 訓練時間: 2336 H100 GPU Hours
# 特色
* 嚴格把關模型的訓練資料，提升模型生成資料的可信任性和適用性
* 針對自動摘要、寫信、寫文章、中翻英、英翻中等辦公室常用任務做加強
* 針對台灣在地文化、用語、國情等知識做加強
* 具備多輪問答對話能力
# 應用範例
| 任務 | 使用者輸入 | 模型輸出 |
| --- | -------- | ------- |
| 寫文章 | 請以以下內容為基礎，寫一篇文章：撰寫一篇作文，題目為《一張舊照片》，內容要求為：選擇一張令你印象深刻的照片，說明令你印象深刻的原因，並描述照片中的影像及背後的故事。記錄成長的過程、與他人的情景、環境變遷和美麗的景色。 | 一張舊照片，承載著時光的痕跡和回憶的溫度。我還記得那張照片是怎麼出現的，那是一張泛黃的黑白相片，裱在牆上，訴說著一段屬於我家族的故事。<br><br>那張照片中，我的祖父母站在田野間，後方是綿延的山巒，前方則是一片金黃的稻田。這幅景象令我印象深刻，因為這是我的童年回憶，也是我成長過程中最美好的風景線。<br><br>我出生在台灣鄉下，從小就生活在這樣一個純樸的環境中。每當我跟著家人在田裡工作時，就會看到這樣的美景。金黃的稻穗隨著微風搖曳，山巒則靜靜地矗立在遠方，給人一種安詳與祥和的感覺。<br><br>那張照片拍攝於民國50年代，當時台灣經濟尚未起飛，農業為主要產業。我的祖父母都是農民，他們辛勤耕種，為我們家提供溫飽。每當我看到那張照片，就會想起他們為我們所做的犧牲和努力。<br><br>除了美麗的風景外，照片中還有一段動人的故事。在我還很小的時候，家裡發生了一場大火，將我們的房子和所有財產都燒光了。幸好全家人都平安無事，但生活卻變得十分困苦。我們被迫搬到另一個村莊，在那裡重新開始生活。<br><br>那張照片也記錄了那段艱辛的歲月。雖然我們失去了許多東西，但家人之間的感情卻更加深厚。我們互相扶持，共同面對生活上的種種挑戰。<br><br>如今，我已長大成人，在都市裡工作。但每當我看到那張舊照片，我都會想起那段簡單而美好的時光。那些美麗的風景、親人的笑容，以及那段充滿挑戰卻又充滿希望的日子，都將永遠鐫刻在我的記憶深處。<br><br>這張舊照片，不僅僅是一張照片，更是一個寶貴的家族史，一個關於我們如何克服困難、珍惜現在的故事。我將把這張照片好好保存下來，讓後代也能夠認識我們的根源，並且銘記那些值得珍藏的美好回憶。 |
| 寫信 | 請以品牌經理的身份，給廣告公司的創意總監寫一封信，提出對於新產品廣告宣傳活動的創意建議。 | [您的姓名]<br>[您的職稱]<br>[您的公司名稱]<br>[郵件地址]<br>[電話號碼]<br>[發文日期]<br><br>[創意總監姓名]<br>[廣告公司名稱]<br>[廣告公司地址]<br><br>主旨:關於新產品宣傳活動創意發想，請查照。<br><br>尊敬的[創意總監姓名]，<br><br>我希望這封信能找到你忙碌中好好休息。我寫這封信，是為了分享我對於我們即將推出的新產品宣傳活動一些創意發想。我深信，這些想法能幫助我們新產品在市場上脫穎而出，吸引消費者的目光。<br><br>首先，我建議我們可以利用社群媒體平台，像是Facebook、Instagram、YouTube等，製作一系列引人入勝的短片和貼文。這些內容可以展現新產品的特色和優點，同時也能傳達出我們品牌重視環保、健康的核心價值。我們可以與網紅或意見領袖合作，讓他們試用並分享他們的使用經驗，這將有助於增加我們產品的可信度和能見度。<br><br>其次，我們可以舉辦新產品試吃/試用活動，邀請民眾親身體驗我們的新產品。我們可以在各大百貨公司、超市、以及我們的門市舉辦這些活動，讓參與者免費試吃/試用新產品，並填寫問卷回饋意見。這種互動的方式，不僅能收集到寶貴的市場反饋，還能讓民眾對我們的品牌產生正面的印象。<br><br>第三，我們可以與當地餐飲業者合作，將我們的新產品納入他們的菜單中。這將使我們的產品接觸到更廣泛的客群，同時也能證明我們的產品在烹飪和美食產業中具有價值。<br><br>第四，我們可以舉辦一場新產品發表會，邀請媒體、業界人士、以及重要客戶參加。在這場活動中，我們可以展示新產品的各項特色和優勢，並由專業廚師示範如何將新產品融入各式料理中。這將是向大眾展示我們品牌創新精神和專業能力的絕佳機會。<br><br>最後，我建議我們可以製作一系列精美的包裝和禮盒，以吸引消費者在節慶和送禮時選擇我們的產品。精緻的包裝將能提升我們產品的價值感，同時也能傳達出我們品牌對細節和品質的堅持。<br><br>我深信，這些創意發想將有助於我們新產品在市場上獲得成功。若您對這些想法有任何意見或建議，請不吝與我分享。我期待著與您合作，共同為[您的公司名稱]的成長和成功而努力。<br><br>謝謝您抽空閱讀我的信，並期待著與您進一步討論這些想法。<br><br>敬禮<br><br>[您的姓名]<br>[您的職稱]<br>[您的公司名稱] |
| 摘要 | 請將這篇文章精簡條理化:「產業創新條例第10條之2及第72條條文修正案」俗稱「台版晶片法」,針對半導體、電動車、5G等技術創新且居國際供應鏈關鍵地位公司,提供最高25%營所稅投抵優惠,企業適用要件包含當年度研發費用、研發密度達一定規模,且有效稅率達一定比率。<br>為因應經濟合作暨發展組織(OECD)國家最低稅負制調整,其中有效稅率門檻,民國112年訂為12%,113年料將提高至15%,但仍得審酌國際間最低稅負制實施情形。<br>經濟部官員表示,已和財政部協商進入最後階段,除企業研發密度訂在6%,目前已確認,企業購置先進製程的設備投資金額達100億元以上可抵減。<br>財政部官員表示,研商過程中,針對台灣產業與其在國際間類似的公司進行深入研究,在設備部分,畢竟適用產創10之2的業者是代表台灣隊打「國際盃」,投入金額不達100億元,可能也打不了。<br>至於備受關注的研發費用門檻,經濟部官員表示,歷經與財政部來回密切討論,研發費用門檻有望落在60億至70億元之間。<br>財政部官員指出,研發攸關台灣未來經濟成長動能,門檻不能「高不可攀」,起初雖設定在100億元,之所以會調降,正是盼讓企業覺得有辦法達得到門檻、進而適用租稅優惠,才有動力繼續投入研發,維持國際供應鏈關鍵地位。<br>經濟部官員表示,因廠商研發費用平均為30、40億元,其中,IC設計業者介於30億至60億元範圍,若將門檻訂在100億元,符合條件的業者較少、刺激誘因不足;此外,若符合申請門檻的業者增加,將可提高企業在台投資金額,財政部稅收也能因此獲得挹注。<br>IC設計業者近日頻頻針對產創10之2發聲,希望降低適用門檻,加上各國力拚供應鏈自主化、加碼補助半導體產業,經濟部官員表示,經濟部和財政部就產創10之2達成共識,爭取讓更多業者受惠,盼增強企業投資力道及鞏固台灣技術地位。<br>財政部官員表示,租稅獎勵的制定必須「有為有守」,並以達到獎勵設置目的為最高原則,現階段在打「國內盃」的企業仍可適用產創第10條、10之1的租稅優惠,共同壯大台灣經濟發展。<br>經濟部和財政部正就研發費用門檻做最後確認,待今明兩天預告子法之後,約有30天時間,可與業界進一步討論及調整,盼產創10之2能在6月上路。 | 文章重點摘要如下:<br><br>- 「台版晶片法」或《產業創新條例第10條之2及第72條條文修正案》，旨在鼓勵關鍵技術創新企業，特別是那些在半導體、電動車、5G技術等領域且在國際供應鏈中扮演關鍵角色者。<br><br>- 企業若符合特定條件，包括當年度研發費用及研發密度達標，可享最高25%的營所稅抵減優惠。研發密度目標設為6%，而企業為取得抵減，必須證明其有效稅率達到特定比率，起初設定為112年的12%，113年提高至15%，但可能會依國際稅制的實施情形進行調整。<br><br>- 政府在制定政策時，考量到OECD最低稅負制的調整，因此會視情況調整有效稅率門檻。<br><br>- 政府部門已就法案內容與企業利益相關者進行協商，確定一些細節，例如企業投資先進製程設備的門檻設為100億元新台幣以供抵減。<br><br>- 研發費用門檻經過討論，可能從最初提議的100億元下調至60億至70億元之間，以激勵更多企業符合資格並投入研發，維持台灣在國際供應鏈中的關鍵地位。<br><br>- 經濟部官員表示，調降門檻的目的是讓更多企業覺得能夠達成標準，從而獲得應用租稅優惠的動力，並可能藉此提高在台投資金額，進而增加政府稅收。<br><br>- 由於IC設計業者的研發費用普遍較低，若門檻設得過高，符合條件的企業將很少，因此有必要調整。<br><br>- 在各國推動供應鏈自主化並增加對半導體產業的補助之際，經濟部正努力確保更多企業能從《產業創新條例》第10條之2中受益，以增強投資和鞏固台灣的技術地位。<br><br>- 政府強調租稅優惠的制定應符合獎勵目標，在此同時，也將繼續提供其他租稅優惠給在國內經營的企業，以促進台灣經濟成長。<br><br>- 最終的研發費用門檻將由經濟部和財政部共同確定，在預告相關子法後，將有約30天的時間供各界討論並提出調整建議，目標是讓這項新政策在6月上路。 |
| 翻譯 | 以下提供英文內容，請幫我翻譯成中文。Dongshan coffee is famous for its unique position, and the constant refinement of production methods. The flavor is admired by many caffeine afficionados. | 東山咖啡以獨特的位置，加上不斷精進的製作手法而聞名，風味更是讓許多咖啡癡趨之若鶩。 |
# 使用說明
* 範例程式
* 範例程式與文件後續會釋出到github
* prompt 樣版
* 一般問答用法
```python
chat = [
{"role": "user", "content": "{question}"},
]
prompt = tokenizer.apply_chat_template(chat)
```
* 將 {question} 替換成使用者的輸入
* 加入 system prompt 的用法
```python
chat = [
{"role": "system", "content": "{sys}"},
{"role": "user", "content": "{question}"},
]
prompt = tokenizer.apply_chat_template(chat)
```
* 將 {sys} 替換成指令，例如：你是一個來自台灣的AI助理，你的名字是 TAIDE，樂於以台灣人的立場幫助使用者，會用繁體中文回答問題。
* 將 {question} 替換成使用者的問題
* 多輪問答用法
```python
chat = [
{"role": "system", "content": "{sys}"},
{"role": "user", "content": "{question1}"},
{"role": "assistant", "content": "{model_anwer_1}"},
{"role": "user", "content": "{question2}"},
]
prompt = tokenizer.apply_chat_template(chat)
```
* 將 {sys} 替換成指令，例如：你是一個來自台灣的AI助理，你的名字是 TAIDE，樂於以台灣人的立場幫助使用者，會用繁體中文回答問題。
* 將 {question1} 替換成使用者的問題1
* 將 {model_anwer_1} 替換成模型的回答1
* 將 {question2} 替換成使用者的問題2
* 更多細節請參考[Llama3 文件](https://llama.meta.com/docs/model-cards-and-prompt-formats/meta-llama-3/)
# 訓練方法
* 軟硬體規格
* 國網中心 H100
* 訓練框架: PyTorch
* 資料前處理
* 字元標準化
* 去除重覆
* 去除雜訊
* 網頁資料的html tag、javascript
* 非標準字元或亂碼
* 字數過短的文章
* 去除文章中的特定格式，如為排版增加的換行
* 去除個資，如email、電話
* 去除不當文字，如賭博、色情等
* 持續預訓練 (continuous pretraining, CP)
* 補充大量來源可信賴的繁體中文知識
* 超參數 (hyper parameters)
* optimizer: AdamW
* learning rate: 1e-4
* batch size: 1M tokens
* epoch: 1
* 微調 (fine tune, FT)
* 讓模型可針對繁體中文提問回答問題
* 超參數 (hyper parameters)
* optimizer: AdamW
* learning rate: 5e-5
* batch size: 256K tokens
* epoch: 3
# 訓練資料
* 持續預訓練資料(資料量約為140G)
| 資料集 | 資料描述 |
| --- | -------- |
| 訴訟資料 | 《[司法院裁判書](https://judgment.judicial.gov.tw/FJUD/default.aspx)》自2013年1月至2023年12月各級法院民事、刑事、行政訴訟資料。 |
| 中央社 | 《[中央社中文新聞](https://www.cna.com.tw/)》資料集含中央社自1993年6月至2023年06月，共30年份之每日新聞文章。內容涵蓋國內外政治、社會、財經、文教、生活等領域。 |
| ETtoday 新聞雲 | 《[ETtoday新聞雲](https://www.ettoday.net/)》資料，包含自2011年10月至 2023年12月的資料。 |
| 立法院公報 | 《[立法院公報](https://ppg.ly.gov.tw/ppg/)》包含自第8屆第1會期至第10屆第7會期之公報資料。 |
| 出版商網站書籍介紹 | 包含[三采](https://www.suncolor.com.tw/)、[Gotop](https://www.gotop.com.tw/)出版商網站上的書籍簡介。 |
| GRB 研究計畫摘要 | [GRB](https://www.grb.gov.tw/)為收錄由政府經費補助之研究計畫及其成果報告的資訊系統，此資料集主要收錄 1993年至 2023年之研究計畫摘要以及研究報告摘要，含中文及其英文對照。 |
| 學術會議論文摘要 | 收錄《[學術會議論文摘要資料庫](https://sticnet.stpi.narl.org.tw/sticloc/ttscalle?meet:)》中自1988至2009年由台灣所舉辦之學術會議論文。 |
| 光華雜誌 | 《[台灣光華雜誌](https://www.taiwan-panorama.com/)》含自1993年7月至2023年6月的文章，共30年份。內容著重於我國文化、觀光與民情等。 |
| 樂詞網 | 《[樂詞網](https://terms.naer.edu.tw/)》涵蓋文理領域約187萬則學術名詞及其譯名對照。 |
| 各部會資料 | 包含行政院「[國情簡介](https://www.ey.gov.tw/state/)」、文化部「[國家文化記憶庫](https://memory.culture.tw/)」、國發會「[檔案支援教學網](https://art.archives.gov.tw/index.aspx)」、交通部「[交通安全入口網](https://168.motc.gov.tw/)」等部會網站資料之部分資料。 |
| 今周刊 | 《[今周刊](https://www.businesstoday.com.tw/)》為一以財經為主的週刊雜誌，此資料集涵蓋2008年1月至2023年7月的文章。 |
| 教育部國語辭典、成語辭典 | 包含以下三項資料:<br>[教育部《成語典》](https://dict.idioms.moe.edu.tw/search.jsp?webMd=1&la=0)，含5,338條成語，內容包含每條成語的釋義、典故原文及其白話說明、用法說明、例句等。<br>[教育部《重編國語辭典修訂本》](https://dict.revised.moe.edu.tw/?la=0&powerMode=0)，收錄中文單字及各類辭彙，包含讀音、部首、釋義等資訊，共約165,539筆資料。<br>[教育部《國語辭典簡編本》](https://dict.concised.moe.edu.tw/?la=0&powerMode=0)，為《重編國語辭典修訂本》的簡編版本，共45,247筆資料。 |
| 科技大觀園資料 | 含《[科技大觀園網站](https://scitechvista.nat.gov.tw/)》上的科學新知以及科普文章。 |
| iKnow 科技產業資訊室 | 《[科技產業資訊室](https://iknow.stpi.narl.org.tw/)（iKnow）》提供台灣及全球的科技市場趨勢、策略分析、專利知識，及技術交易資訊，專注於科技產業的創新與發展，包含自 2008 年至 2023 年。 |
| 科學發展月刊 | 《[科學發展月刊](https://ejournal.stpi.narl.org.tw/sd)》為國科會為推廣科學教育而出版的科普刊物，含自2004年10月至2020年12月之科普文章；2021年起，以《[科技魅癮](https://www.charmingscitech.nat.gov.tw/)》季刊重新出發，提供國際關注科技議題的新知文章。 |
| 法規資料庫 | 《[法規資料庫](https://law.moj.gov.tw/)》含截自 112 年 10 月各政府部門最新發布之中央法規、行政規則、法規命令草案及地方自治法規等。 |
| 各地政府旅遊網 | 涵蓋台灣部分縣市地方政府觀光旅遊網站上之部分資料。 |
| 國教院課程綱要(十二年國教) | 含十二年國教課程綱要之總綱以及各級學校不同科目之課程綱要。 |
| 中央社譯名檔資料庫 | 《中央社譯名檔資料庫》蒐集中央社新聞業務上翻譯過的中外姓氏、人名、組織、地名等譯名對照。 |
| 童話書 | 共 20 本童話書，含湯姆歷險記、小飛俠、愛麗絲夢遊仙境、長腿叔叔等。 |
| RedPajama-Data-V2 | 從國外開放多國語言語料庫 [RedPajama-Data-v2](https://github.com/togethercomputer/RedPajama-Data) 取出英文資料 |
| MathPile-commercial | 國外開放數學語料庫 [MathPile-commercial](https://huggingface.co/datasets/GAIR/MathPile_Commercial) |
| 中文維基百科 | 《[中文維基百科](https://zh.wikipedia.org/zh-tw/%E4%B8%AD%E6%96%87%E7%BB%B4%E5%9F%BA%E7%99%BE%E7%A7%91)》截至2023年1月所有條目的內容。 |
| github-code-clean | 為 github 開源程式碼資料集，去除unlicense的程式碼和文件。 |
* 微調資料
* TAIDE團隊訓練llama2系列模型來產生微調資料資料，產生的任務包含世界知識、創意寫作、普通常識、翻譯、摘要、程式、台灣價值等單輪或多輪對話問答共 128K 筆。微調資料後續會對外釋出。
# 模型評測
* taide-bench
* 評測資料
* 寫文章、寫信、摘要、英翻中、中翻英，共500題
* 資料連結: [taide-bench](https://huggingface.co/datasets/taide/taide-bench)
* 評測方法
* gpt4評分
* 評分程式: [taide-bench-eval](https://github.com/taide-taiwan/taide-bench-eval)
* 評測分數
| 模型 | 中翻英 | 英翻中 | 摘要 | 寫文章 | 寫信 | 平均 |
| --- | ----- | ----- | ---- | ---- | ---- | --- |
| Llama3-TAIDE-LX-8B-Chat-Alpha1 | 7.770 | 8.280 | 8.495 | 9.605 | 8.950 | 8.620 |
| GPT3.5 | 8.880 | 8.810 | 7.450 | 9.490 | 8.750 | 8.676 |
| TAIDE-LX-7B-Chat | 7.165 | 7.685 | 7.720 | 9.635 | 9.110 | 8.263 |
| LLAMA2 7B | 6.075 | 4.475 | 5.905 | 2.625 | 3.040 | 4.424 |
| LLAMA2 13B | 6.480 | 6.135 | 6.110 | 2.565 | 3.000 | 4.858 |
| LLAMA2 70B | 6.975 | 6.375 | 6.795 | 2.625 | 2.990 | 5.152 |
# 授權條款
* [Llama3-TAIDE 模型社群授權同意書](https://drive.google.com/file/d/12-Q0WWSjG0DW6CqJQm_jr5wUGRLeb-8p/view)
# 免責聲明
* LLM 模型由於設計架構的限制，以及資料難免有偏誤，語言模型的任何回應不代表 TAIDE 立場，使用前需要額外加入安全防護機制，且回應內容也可能包含不正確的資訊，使用者請勿盡信。
# 開發團隊
* [https://taide.tw/index/teamList](https://taide.tw/index/teamList)
# 相關連結
* [TAIDE官網](https://taide.tw/index)
* [TAIDE Huggingface](https://huggingface.co/taide)
* [TAIDE Github](https://github.com/taide-taiwan)
* [Kuwa AI](https://kuwaai.org/)
# Citation
* [TAIDE官網](https://taide.tw/index)
| {"license": "other", "license_name": "llama3-taide-models-community-license-agreement", "license_link": "https://drive.google.com/file/d/12-Q0WWSjG0DW6CqJQm_jr5wUGRLeb-8p/view", "extra_gated_heading": "\u60a8\u9700\u8981\u5148\u540c\u610f\u6388\u6b0a\u689d\u6b3e\u624d\u80fd\u4f7f\u7528\u6b64\u6a21\u578b", "extra_gated_fields": {"\u59d3\u540d(Name)": "text", "\u751f\u65e5(Date of birth)": "date_picker", "\u570b\u5bb6(Country)": "country", "\u6240\u5c6c\u55ae\u4f4d(Affiliation)": "text", "geo": "ip_location", "\u6309\u4e0b\u9001\u51fa\u8868\u793a\u60a8\u540c\u610f\u793e\u7fa4\u6388\u6b0a\u540c\u610f\u66f8\u8207\u500b\u4eba\u8cc7\u6599\u8490\u96c6\u544a\u77e5\u8072\u660e(By clicking Submit below I accept the terms of the license and privacy policy)": "checkbox"}, "extra_gated_prompt": "* ### [Llama3-TAIDE \u6a21\u578b\u793e\u7fa4\u6388\u6b0a\u540c\u610f\u66f8(License)](https://drive.google.com/file/d/12-Q0WWSjG0DW6CqJQm_jr5wUGRLeb-8p/view)\n* ### [\u500b\u4eba\u8cc7\u6599\u8490\u96c6\u544a\u77e5\u8072\u660e(Privacy policy)](https://drive.google.com/file/d/1JTfZu_MdU_TR1-1sn2jbQyW7TLrxjwS5/view)", "extra_gated_button_content": "\u9001\u51fa(Submit)"} | taide/Llama3-TAIDE-LX-8B-Chat-Alpha1-4bit | null | [
"gguf",
"license:other",
"region:us"
]
| null | 2024-04-28T01:48:37+00:00 |
null | null | {} | ericmconnelly/finetuned-food101-with-ingredients | null | [
"region:us"
]
| null | 2024-04-28T01:52:43+00:00 |
|
null | transformers | ## About
<!-- ### quantize_version: 2 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: -->
<!-- ### vocab_type: -->
static quants of https://huggingface.co/TETO101/AIRI-8B-V2
<!-- provided-files -->
weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion.
## Usage
If you are unsure how to use GGUF files, refer to one of [TheBloke's
READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
more details, including on how to concatenate multi-part files.
## Provided Quants
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
| Link | Type | Size/GB | Notes |
|:-----|:-----|--------:|:------|
| [GGUF](https://huggingface.co/mradermacher/AIRI-8B-V2-GGUF/resolve/main/AIRI-8B-V2.Q2_K.gguf) | Q2_K | 3.3 | |
| [GGUF](https://huggingface.co/mradermacher/AIRI-8B-V2-GGUF/resolve/main/AIRI-8B-V2.IQ3_XS.gguf) | IQ3_XS | 3.6 | |
| [GGUF](https://huggingface.co/mradermacher/AIRI-8B-V2-GGUF/resolve/main/AIRI-8B-V2.Q3_K_S.gguf) | Q3_K_S | 3.8 | |
| [GGUF](https://huggingface.co/mradermacher/AIRI-8B-V2-GGUF/resolve/main/AIRI-8B-V2.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/AIRI-8B-V2-GGUF/resolve/main/AIRI-8B-V2.IQ3_M.gguf) | IQ3_M | 3.9 | |
| [GGUF](https://huggingface.co/mradermacher/AIRI-8B-V2-GGUF/resolve/main/AIRI-8B-V2.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/AIRI-8B-V2-GGUF/resolve/main/AIRI-8B-V2.Q3_K_L.gguf) | Q3_K_L | 4.4 | |
| [GGUF](https://huggingface.co/mradermacher/AIRI-8B-V2-GGUF/resolve/main/AIRI-8B-V2.IQ4_XS.gguf) | IQ4_XS | 4.6 | |
| [GGUF](https://huggingface.co/mradermacher/AIRI-8B-V2-GGUF/resolve/main/AIRI-8B-V2.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/AIRI-8B-V2-GGUF/resolve/main/AIRI-8B-V2.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/AIRI-8B-V2-GGUF/resolve/main/AIRI-8B-V2.Q5_K_S.gguf) | Q5_K_S | 5.7 | |
| [GGUF](https://huggingface.co/mradermacher/AIRI-8B-V2-GGUF/resolve/main/AIRI-8B-V2.Q5_K_M.gguf) | Q5_K_M | 5.8 | |
| [GGUF](https://huggingface.co/mradermacher/AIRI-8B-V2-GGUF/resolve/main/AIRI-8B-V2.Q6_K.gguf) | Q6_K | 6.7 | very good quality |
| [GGUF](https://huggingface.co/mradermacher/AIRI-8B-V2-GGUF/resolve/main/AIRI-8B-V2.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality |
| [GGUF](https://huggingface.co/mradermacher/AIRI-8B-V2-GGUF/resolve/main/AIRI-8B-V2.f16.gguf) | f16 | 16.2 | 16 bpw, overkill |
Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):
And here are Artefact2's thoughts on the matter:
https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
## FAQ / Model Request
See https://huggingface.co/mradermacher/model_requests for some answers to
questions you might have and/or if you want some other model quantized.
## Thanks
I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
me use its servers and providing upgrades to my workstation to enable
this work in my free time.
<!-- end -->
| {"language": ["en"], "license": "apache-2.0", "library_name": "transformers", "tags": ["text-generation-inference", "transformers", "unsloth", "llama", "trl", "sft"], "base_model": "TETO101/AIRI-8B-V2", "quantized_by": "mradermacher"} | mradermacher/AIRI-8B-V2-GGUF | null | [
"transformers",
"gguf",
"text-generation-inference",
"unsloth",
"llama",
"trl",
"sft",
"en",
"base_model:TETO101/AIRI-8B-V2",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
]
| null | 2024-04-28T01:53:03+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. -->
# V2-bert-text-classification-model
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2017
- Accuracy: 0.9601
- F1: 0.8264
- Precision: 0.8214
- Recall: 0.8331
## 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: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 100
- num_epochs: 10
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
| 1.5342 | 0.11 | 50 | 1.6906 | 0.3486 | 0.1581 | 0.1874 | 0.1879 |
| 0.7232 | 0.22 | 100 | 0.7529 | 0.8296 | 0.5057 | 0.5008 | 0.5124 |
| 0.2933 | 0.33 | 150 | 0.4824 | 0.9018 | 0.6709 | 0.6673 | 0.6756 |
| 0.2774 | 0.44 | 200 | 0.4746 | 0.8772 | 0.6543 | 0.6423 | 0.6686 |
| 0.1739 | 0.55 | 250 | 0.4650 | 0.9103 | 0.6760 | 0.6636 | 0.6892 |
| 0.1757 | 0.66 | 300 | 0.3614 | 0.9166 | 0.7175 | 0.7823 | 0.7127 |
| 0.177 | 0.76 | 350 | 0.2602 | 0.9111 | 0.7284 | 0.7568 | 0.7163 |
| 0.1019 | 0.87 | 400 | 0.3053 | 0.9223 | 0.7301 | 0.7881 | 0.7203 |
| 0.1067 | 0.98 | 450 | 0.4436 | 0.9095 | 0.7255 | 0.7598 | 0.7197 |
| 0.1577 | 1.09 | 500 | 0.2348 | 0.9532 | 0.8227 | 0.8285 | 0.8171 |
| 0.0792 | 1.2 | 550 | 0.2429 | 0.9519 | 0.8190 | 0.8218 | 0.8175 |
| 0.086 | 1.31 | 600 | 0.1858 | 0.9595 | 0.8264 | 0.8282 | 0.8258 |
| 0.091 | 1.42 | 650 | 0.1868 | 0.9625 | 0.8279 | 0.8259 | 0.8308 |
| 0.0909 | 1.53 | 700 | 0.2091 | 0.9549 | 0.8244 | 0.8284 | 0.8217 |
| 0.0434 | 1.64 | 750 | 0.1942 | 0.9628 | 0.8303 | 0.8294 | 0.8315 |
| 0.1175 | 1.75 | 800 | 0.1572 | 0.9650 | 0.8317 | 0.8304 | 0.8333 |
| 0.092 | 1.86 | 850 | 0.2515 | 0.9300 | 0.7489 | 0.7995 | 0.7346 |
| 0.06 | 1.97 | 900 | 0.4890 | 0.9136 | 0.7334 | 0.7694 | 0.7261 |
| 0.0652 | 2.07 | 950 | 0.2258 | 0.9541 | 0.8218 | 0.8143 | 0.8309 |
| 0.0436 | 2.18 | 1000 | 0.2224 | 0.9587 | 0.8245 | 0.8184 | 0.8326 |
| 0.0524 | 2.29 | 1050 | 0.2476 | 0.9546 | 0.8193 | 0.8118 | 0.8283 |
| 0.0598 | 2.4 | 1100 | 0.1913 | 0.9669 | 0.8317 | 0.8312 | 0.8328 |
| 0.0503 | 2.51 | 1150 | 0.2179 | 0.9612 | 0.8230 | 0.8298 | 0.8175 |
| 0.0258 | 2.62 | 1200 | 0.2204 | 0.9631 | 0.8298 | 0.8280 | 0.8323 |
| 0.0091 | 2.73 | 1250 | 0.5198 | 0.9218 | 0.7127 | 0.8107 | 0.7092 |
| 0.1076 | 2.84 | 1300 | 0.1853 | 0.9642 | 0.8323 | 0.8338 | 0.8310 |
| 0.0356 | 2.95 | 1350 | 0.2162 | 0.9612 | 0.8273 | 0.8220 | 0.8338 |
| 0.0492 | 3.06 | 1400 | 0.2382 | 0.9573 | 0.8245 | 0.8201 | 0.8296 |
| 0.0088 | 3.17 | 1450 | 0.2252 | 0.9636 | 0.8303 | 0.8285 | 0.8329 |
| 0.0275 | 3.28 | 1500 | 0.3000 | 0.9543 | 0.8234 | 0.8207 | 0.8279 |
| 0.0215 | 3.38 | 1550 | 0.3234 | 0.9497 | 0.8191 | 0.8152 | 0.8255 |
| 0.0294 | 3.49 | 1600 | 0.3486 | 0.9311 | 0.7500 | 0.8114 | 0.7338 |
| 0.0393 | 3.6 | 1650 | 0.2357 | 0.9595 | 0.8291 | 0.8274 | 0.8311 |
| 0.008 | 3.71 | 1700 | 0.2762 | 0.9587 | 0.8277 | 0.8260 | 0.8297 |
| 0.0042 | 3.82 | 1750 | 0.2393 | 0.9666 | 0.8330 | 0.8348 | 0.8312 |
| 0.0329 | 3.93 | 1800 | 0.3012 | 0.9584 | 0.8290 | 0.8267 | 0.8325 |
| 0.0185 | 4.04 | 1850 | 0.2400 | 0.9653 | 0.8324 | 0.8331 | 0.8319 |
| 0.019 | 4.15 | 1900 | 0.3604 | 0.9314 | 0.7489 | 0.8084 | 0.7324 |
| 0.0205 | 4.26 | 1950 | 0.2451 | 0.9653 | 0.8346 | 0.8365 | 0.8328 |
| 0.0202 | 4.37 | 2000 | 0.3619 | 0.9483 | 0.8190 | 0.8174 | 0.8237 |
| 0.019 | 4.48 | 2050 | 0.2573 | 0.9628 | 0.8315 | 0.8332 | 0.8306 |
| 0.0087 | 4.59 | 2100 | 0.2661 | 0.9634 | 0.8316 | 0.8319 | 0.8322 |
| 0.0212 | 4.69 | 2150 | 0.3671 | 0.9311 | 0.7497 | 0.8091 | 0.7378 |
| 0.0087 | 4.8 | 2200 | 0.3005 | 0.9305 | 0.7582 | 0.8108 | 0.7431 |
| 0.0005 | 4.91 | 2250 | 0.2772 | 0.9584 | 0.8257 | 0.8223 | 0.8297 |
| 0.0231 | 5.02 | 2300 | 0.2556 | 0.9634 | 0.8290 | 0.8269 | 0.8318 |
| 0.0006 | 5.13 | 2350 | 0.2798 | 0.9595 | 0.8253 | 0.8219 | 0.8298 |
| 0.0012 | 5.24 | 2400 | 0.2777 | 0.9625 | 0.8305 | 0.8278 | 0.8334 |
| 0.0096 | 5.35 | 2450 | 0.2818 | 0.9614 | 0.8280 | 0.8259 | 0.8308 |
| 0.0145 | 5.46 | 2500 | 0.2449 | 0.9628 | 0.8311 | 0.8286 | 0.8341 |
| 0.032 | 5.57 | 2550 | 0.2480 | 0.9653 | 0.8322 | 0.8296 | 0.8355 |
| 0.0075 | 5.68 | 2600 | 0.2241 | 0.9661 | 0.8341 | 0.8324 | 0.8360 |
| 0.0058 | 5.79 | 2650 | 0.2349 | 0.9645 | 0.8309 | 0.8290 | 0.8332 |
| 0.0079 | 5.9 | 2700 | 0.4499 | 0.9325 | 0.7515 | 0.8158 | 0.7383 |
| 0.0003 | 6.0 | 2750 | 0.2890 | 0.9590 | 0.8268 | 0.8252 | 0.8296 |
| 0.0109 | 6.11 | 2800 | 0.2298 | 0.9669 | 0.8337 | 0.8331 | 0.8346 |
| 0.0004 | 6.22 | 2850 | 0.2356 | 0.9669 | 0.8341 | 0.8334 | 0.8351 |
| 0.0003 | 6.33 | 2900 | 0.2272 | 0.9691 | 0.8364 | 0.8364 | 0.8366 |
| 0.0003 | 6.44 | 2950 | 0.2389 | 0.9669 | 0.8350 | 0.8342 | 0.8362 |
| 0.0201 | 6.55 | 3000 | 0.2427 | 0.9661 | 0.8346 | 0.8343 | 0.8354 |
| 0.0003 | 6.66 | 3050 | 0.2382 | 0.9677 | 0.8347 | 0.8352 | 0.8344 |
| 0.0095 | 6.77 | 3100 | 0.2004 | 0.9705 | 0.8367 | 0.8379 | 0.8354 |
| 0.0187 | 6.88 | 3150 | 0.2470 | 0.9677 | 0.8335 | 0.8332 | 0.8341 |
| 0.0086 | 6.99 | 3200 | 0.2243 | 0.9688 | 0.8348 | 0.8340 | 0.8358 |
| 0.0003 | 7.1 | 3250 | 0.2424 | 0.9677 | 0.8342 | 0.8329 | 0.8357 |
| 0.0067 | 7.21 | 3300 | 0.2754 | 0.9623 | 0.8287 | 0.8268 | 0.8314 |
| 0.0003 | 7.31 | 3350 | 0.2302 | 0.9686 | 0.8348 | 0.8340 | 0.8358 |
| 0.0002 | 7.42 | 3400 | 0.2318 | 0.9688 | 0.8350 | 0.8342 | 0.8359 |
| 0.0002 | 7.53 | 3450 | 0.2327 | 0.9686 | 0.8349 | 0.8342 | 0.8358 |
| 0.0002 | 7.64 | 3500 | 0.2376 | 0.9680 | 0.8346 | 0.8339 | 0.8355 |
| 0.0002 | 7.75 | 3550 | 0.2391 | 0.9680 | 0.8346 | 0.8339 | 0.8355 |
| 0.0002 | 7.86 | 3600 | 0.2435 | 0.9683 | 0.8358 | 0.8349 | 0.8370 |
| 0.0164 | 7.97 | 3650 | 0.2196 | 0.9705 | 0.8359 | 0.8358 | 0.8361 |
| 0.0003 | 8.08 | 3700 | 0.2116 | 0.9718 | 0.8380 | 0.8390 | 0.8369 |
| 0.004 | 8.19 | 3750 | 0.2192 | 0.9702 | 0.8364 | 0.8367 | 0.8362 |
| 0.0002 | 8.3 | 3800 | 0.2213 | 0.9699 | 0.8357 | 0.8356 | 0.8358 |
| 0.0002 | 8.41 | 3850 | 0.2232 | 0.9699 | 0.8357 | 0.8356 | 0.8358 |
| 0.0001 | 8.52 | 3900 | 0.2242 | 0.9699 | 0.8357 | 0.8356 | 0.8358 |
| 0.0001 | 8.62 | 3950 | 0.2230 | 0.9705 | 0.8360 | 0.8357 | 0.8362 |
| 0.0001 | 8.73 | 4000 | 0.2240 | 0.9705 | 0.8360 | 0.8357 | 0.8362 |
| 0.0001 | 8.84 | 4050 | 0.2254 | 0.9705 | 0.8361 | 0.8359 | 0.8364 |
| 0.0001 | 8.95 | 4100 | 0.2265 | 0.9705 | 0.8361 | 0.8359 | 0.8364 |
| 0.0002 | 9.06 | 4150 | 0.2280 | 0.9705 | 0.8364 | 0.8359 | 0.8369 |
| 0.0071 | 9.17 | 4200 | 0.2393 | 0.9694 | 0.8357 | 0.8355 | 0.8362 |
| 0.0001 | 9.28 | 4250 | 0.2564 | 0.9680 | 0.8355 | 0.8347 | 0.8367 |
| 0.0002 | 9.39 | 4300 | 0.2442 | 0.9688 | 0.8354 | 0.8352 | 0.8358 |
| 0.0002 | 9.5 | 4350 | 0.2363 | 0.9699 | 0.8361 | 0.8359 | 0.8365 |
| 0.0001 | 9.61 | 4400 | 0.2365 | 0.9699 | 0.8361 | 0.8359 | 0.8365 |
| 0.0001 | 9.72 | 4450 | 0.2366 | 0.9699 | 0.8361 | 0.8359 | 0.8365 |
| 0.0001 | 9.83 | 4500 | 0.2372 | 0.9699 | 0.8361 | 0.8359 | 0.8365 |
| 0.0001 | 9.93 | 4550 | 0.2372 | 0.9699 | 0.8361 | 0.8359 | 0.8365 |
### Framework versions
- Transformers 4.39.3
- Pytorch 2.1.2
- Datasets 2.18.0
- Tokenizers 0.15.2
| {"license": "apache-2.0", "tags": ["generated_from_trainer"], "metrics": ["accuracy", "f1", "precision", "recall"], "base_model": "bert-base-uncased", "model-index": [{"name": "V2-bert-text-classification-model", "results": []}]} | AmirlyPhd/V2-bert-text-classification-model | null | [
"transformers",
"safetensors",
"bert",
"text-classification",
"generated_from_trainer",
"base_model:bert-base-uncased",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| null | 2024-04-28T01:53:07+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": []} | HC-85/distilbert-lora-32r-arxiv-multilabel | null | [
"transformers",
"safetensors",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
]
| null | 2024-04-28T01:55:09+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": []} | HC-85/distilbert-lora-64r-arxiv-multilabel | null | [
"transformers",
"safetensors",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
]
| null | 2024-04-28T01:55:28+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": []} | zandfj/LLaMA2-7B-Chat-sft-sft-3epo_dpozf_glod0862_042808 | null | [
"transformers",
"safetensors",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
]
| null | 2024-04-28T01:56:10+00:00 |
text-generation | transformers | ## GOOGLE COLAB IS A SCAM DO NOT USE THE PAID VERSION
## THEY WILL DISCONNECT YOUR RUNTIME BEFORE EVEN 24 HOURS
https://github.com/googlecolab/colabtools/issues/3451
_________________________________________________________________________________________
## PLEASE INSTEAD USE TENSORDOCK ITS CHEAPER AND DOESNT DISCONNECT YOU
tensordock.com
_________________________________________________________________________________________
__________________________________________________________________________________________________________________________________________________________________________________
_________________________________________________________________________________________
_________________________________________________________________________________________
_________________________________________________________________________________________
_________________________________________________________________________________________
_________________________________________________________________________________________
_________________________________________________________________________________________
_________________________________________________________________________________________
_________________________________________________________________________________________
_________________________________________________________________________________________
_________________________________________________________________________________________
This is unsloth/llama-3-8b-Instruct trained on the Replete-AI/code-test-dataset using the code bellow with unsloth and google colab with under 15gb of vram. This training was complete in about 40 minutes total.
__________________________________________________________________________
Colab doc if you dont want to copy the code by hand:
- https://colab.research.google.com/drive/1bX4BsjLcdNJnoAf7lGXmWOgaY8yekg8p?usp=sharing
__________________________________________________________________________
Copy from my announcement in my discord:
```
If anyone wants to train their own llama-3-8b model for free on any dataset
that has around 1,500 lines of data or less you can now do it easily by using
the code I provided in the model card for my test model in this repo and
google colab. The training for this model uses (Unsloth + Qlora + Galore) to
achieve the ability for training under such low vram.
```
For anyone that is new to coding and training Ai, all your really have to edit is
1. (max_seq_length = 8192) To match the max tokens of the dataset or model you are using
2. (model_name = "unsloth/llama-3-8b-Instruct",) Change what model you are finetuning, this setup is specifically for llama-3-8b
3. (alpaca_prompt =) Change the prompt format, this one is setup to meet llama-3-8b-instruct format, but match it to your specifications.
4. (dataset = load_dataset("Replete-AI/code-test-dataset", split = "train")) What dataset you are using from huggingface
5. (model.push_to_hub_merged("rombodawg/test_dataset_Codellama-3-8B", tokenizer, save_method = "merged_16bit", token = ""))
6. For the above you need to change "rombodawg" to your Hugginface name, "test_dataset_Codellama-3-8B" to the model name you want saved as, and in token = "" you need to put your huggingface write token so the model can be saved.
```Python
%%capture
import torch
major_version, minor_version = torch.cuda.get_device_capability()
# Must install separately since Colab has torch 2.2.1, which breaks packages
!pip install "unsloth[colab-new] @ git+https://github.com/unslothai/unsloth.git"
if major_version >= 8:
# Use this for new GPUs like Ampere, Hopper GPUs (RTX 30xx, RTX 40xx, A100, H100, L40)
!pip install --no-deps packaging ninja einops flash-attn xformers trl peft accelerate bitsandbytes
else:
# Use this for older GPUs (V100, Tesla T4, RTX 20xx)
!pip install --no-deps xformers trl peft accelerate bitsandbytes
pass
```
```Python
!pip install galore_torch
```
```Python
from unsloth import FastLanguageModel
import torch
max_seq_length = 8192 # Choose any! We auto support RoPE Scaling internally!
dtype = None # None for auto detection. Float16 for Tesla T4, V100, Bfloat16 for Ampere+
load_in_4bit = True # Use 4bit quantization to reduce memory usage. Can be False.
# 4bit pre quantized models we support for 4x faster downloading + no OOMs.
fourbit_models = [
"unsloth/mistral-7b-bnb-4bit",
"unsloth/mistral-7b-instruct-v0.2-bnb-4bit",
"unsloth/llama-2-7b-bnb-4bit",
"unsloth/gemma-7b-bnb-4bit",
"unsloth/gemma-7b-it-bnb-4bit", # Instruct version of Gemma 7b
"unsloth/gemma-2b-bnb-4bit",
"unsloth/gemma-2b-it-bnb-4bit", # Instruct version of Gemma 2b
"unsloth/llama-3-8b-bnb-4bit", # [NEW] 15 Trillion token Llama-3
] # More models at https://huggingface.co/unsloth
model, tokenizer = FastLanguageModel.from_pretrained(
model_name = "unsloth/llama-3-8b-Instruct",
max_seq_length = max_seq_length,
dtype = dtype,
load_in_4bit = load_in_4bit,
# token = "hf_...", # use one if using gated models like meta-llama/Llama-2-7b-hf
)
```
```Python
model = FastLanguageModel.get_peft_model(
model,
r = 16, # Choose any number > 0 ! Suggested 8, 16, 32, 64, 128
target_modules = ["q_proj", "k_proj", "v_proj", "o_proj",
"gate_proj", "up_proj", "down_proj",],
lora_alpha = 16,
lora_dropout = 0, # Supports any, but = 0 is optimized
bias = "none", # Supports any, but = "none" is optimized
# [NEW] "unsloth" uses 30% less VRAM, fits 2x larger batch sizes!
use_gradient_checkpointing = "unsloth", # True or "unsloth" for very long context
random_state = 3407,
use_rslora = False, # We support rank stabilized LoRA
loftq_config = None, # And LoftQ
)
```
```Python
alpaca_prompt = """<|begin_of_text|><|start_header_id|>system<|end_header_id|>
Below is an instruction that describes a task, Write a response that appropriately completes the request.<|eot_id|><|start_header_id|>user<|end_header_id|>
{}<|eot_id|><|start_header_id|>assistant<|end_header_id|>{}"""
EOS_TOKEN = tokenizer.eos_token # Must add EOS_TOKEN
def formatting_prompts_func(examples):
inputs = examples["human"]
outputs = examples["assistant"]
texts = []
for input, output in zip(inputs, outputs):
# Must add EOS_TOKEN, otherwise your generation will go on forever!
text = alpaca_prompt.format(input, output) + EOS_TOKEN
texts.append(text)
return { "text" : texts, }
pass
from datasets import load_dataset
dataset = load_dataset("Replete-AI/code-test-dataset", split = "train")
dataset = dataset.map(formatting_prompts_func, batched = True,)
```
```Python
from trl import SFTTrainer
from transformers import TrainingArguments
from galore_torch import GaLoreAdamW8bit
import torch.nn as nn
galore_params = []
target_modules_list = ["attn", "mlp"]
for module_name, module in model.named_modules():
if not isinstance(module, nn.Linear):
continue
if not any(target_key in module_name for target_key in target_modules_list):
continue
print('mod ', module_name)
galore_params.append(module.weight)
id_galore_params = [id(p) for p in galore_params]
regular_params = [p for p in model.parameters() if id(p) not in id_galore_params]
param_groups = [{'params': regular_params},
{'params': galore_params, 'rank': 64, 'update_proj_gap': 200, 'scale': 0.25, 'proj_type': 'std'}]
optimizer = GaLoreAdamW8bit(param_groups, lr=2e-5)
trainer = SFTTrainer(
model = model,
tokenizer = tokenizer,
train_dataset = dataset,
optimizers=(optimizer, None),
dataset_text_field = "text",
max_seq_length = max_seq_length,
dataset_num_proc = 2,
packing = True, # Can make training 5x faster for short sequences.
args = TrainingArguments(
per_device_train_batch_size = 1,
gradient_accumulation_steps = 4,
warmup_steps = 5,
learning_rate = 2e-4,
fp16 = not torch.cuda.is_bf16_supported(),
bf16 = torch.cuda.is_bf16_supported(),
logging_steps = 1,
weight_decay = 0.01,
lr_scheduler_type = "linear",
seed = 3407,
output_dir = "outputs",
),
)
```
```Python
trainer_stats = trainer.train()
model.save_pretrained_merged("model", tokenizer, save_method = "merged_16bit",)
model.push_to_hub_merged("rombodawg/test_dataset_Codellama-3-8B", tokenizer, save_method = "merged_16bit", token = "")
```
| {"language": ["en"], "license": "apache-2.0", "model-index": [{"name": "test_dataset_Codellama-3-8B", "results": [{"task": {"type": "text-generation"}, "dataset": {"name": "HumanEval", "type": "openai_humaneval"}, "metrics": [{"type": "pass@1", "value": 0.63, "name": "pass@1", "verified": false}]}]}]} | rombodawg/test_dataset_Codellama-3-8B | null | [
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"en",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us",
"has_space"
]
| null | 2024-04-28T01:56:24+00:00 |
null | null | {} | sophiex/dpo_pythia1b_hh_rlhf.yml_local_27-04-24_21-57-03_xxxxx | null | [
"region:us"
]
| null | 2024-04-28T01:57:27+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": []} | shallow6414/30c00x4 | null | [
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| null | 2024-04-28T01:58:27+00:00 |
text-generation | transformers |
# stablelm-2-zephyr-1.6b-dareties2
stablelm-2-zephyr-1.6b-dareties2 is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
* [aipib/stablelm-2-zephyr-1.6b-slerpx13](https://huggingface.co/aipib/stablelm-2-zephyr-1.6b-slerpx13)
* [stabilityai/stablelm-2-1_6b](https://huggingface.co/stabilityai/stablelm-2-1_6b)
* [stabilityai/stablelm-2-zephyr-1_6b](https://huggingface.co/stabilityai/stablelm-2-zephyr-1_6b)
## 🧩 Configuration
```yaml
slices:
- sources:
- layer_range: [0, 24]
model: aipib/stablelm-2-zephyr-1.6b-slerpx13
parameters:
density: [1, 0.7, 0.1]
weight: 1.0
- layer_range: [0, 24]
model: stabilityai/stablelm-2-1_6b
parameters:
density: 0.53
weight:
- filter: mlp
value: 0.5
- value: 0
- layer_range: [0, 24]
model: stabilityai/stablelm-2-zephyr-1_6b
parameters:
density: 0.53
weight:
- filter: mlp
value: 0.5
- value: 0
merge_method: dare_ties
base_model: aipib/stablelm-2-zephyr-1.6b-slerpx13
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/stablelm-2-zephyr-1.6b-dareties2"
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", "aipib/stablelm-2-zephyr-1.6b-slerpx13", "stabilityai/stablelm-2-1_6b", "stabilityai/stablelm-2-zephyr-1_6b"], "base_model": ["aipib/stablelm-2-zephyr-1.6b-slerpx13", "stabilityai/stablelm-2-1_6b", "stabilityai/stablelm-2-zephyr-1_6b"]} | aipib/stablelm-2-zephyr-1.6b-dareties2 | null | [
"transformers",
"safetensors",
"stablelm",
"text-generation",
"merge",
"mergekit",
"lazymergekit",
"aipib/stablelm-2-zephyr-1.6b-slerpx13",
"stabilityai/stablelm-2-1_6b",
"stabilityai/stablelm-2-zephyr-1_6b",
"conversational",
"base_model:aipib/stablelm-2-zephyr-1.6b-slerpx13",
"base_model:stabilityai/stablelm-2-1_6b",
"base_model:stabilityai/stablelm-2-zephyr-1_6b",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| null | 2024-04-28T02:00:18+00:00 |
null | null | {"license": "openrail"} | jaguleirah/modelos | null | [
"license:openrail",
"region:us"
]
| null | 2024-04-28T02:00:42+00:00 |
|
null | null | {} | Anna15/sn25-3-5 | null | [
"region:us"
]
| null | 2024-04-28T02:01:12+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": []} | quickstep3621/wpwlrj4 | null | [
"transformers",
"safetensors",
"stablelm",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| null | 2024-04-28T02:03:27+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": []} | quickstep3621/x8p3c85 | null | [
"transformers",
"safetensors",
"stablelm",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| null | 2024-04-28T02:03:33+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": []} | quickstep3621/9a7qxs2 | null | [
"transformers",
"safetensors",
"stablelm",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| null | 2024-04-28T02:03:38+00:00 |
null | null | {} | harveryx/galeweathers | null | [
"region:us"
]
| null | 2024-04-28T02:04:23+00:00 |
|
text-generation | transformers | {} | Weni/WeniGPT-Agents-Llama3-5.0.8-SFT-AWQ | null | [
"transformers",
"safetensors",
"llama",
"text-generation",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"4-bit",
"region:us"
]
| null | 2024-04-28T02:05:23+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. -->
# Whisper-small-speechocean
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.6821
## 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: 0.001
- train_batch_size: 6
- eval_batch_size: 6
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 50
- num_epochs: 20
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 1.5214 | 1.0 | 417 | 1.3231 |
| 0.6304 | 2.0 | 834 | 0.6180 |
| 0.532 | 3.0 | 1251 | 0.5340 |
| 0.4258 | 4.0 | 1668 | 0.5058 |
| 0.3192 | 5.0 | 2085 | 0.5050 |
| 0.288 | 6.0 | 2502 | 0.4952 |
| 0.2097 | 7.0 | 2919 | 0.5252 |
| 0.1986 | 8.0 | 3336 | 0.5281 |
| 0.1185 | 9.0 | 3753 | 0.5534 |
| 0.091 | 10.0 | 4170 | 0.5695 |
| 0.0548 | 11.0 | 4587 | 0.5935 |
| 0.0423 | 12.0 | 5004 | 0.6130 |
| 0.031 | 13.0 | 5421 | 0.6170 |
| 0.0169 | 14.0 | 5838 | 0.6234 |
| 0.0193 | 15.0 | 6255 | 0.6416 |
| 0.0125 | 16.0 | 6672 | 0.6478 |
| 0.0055 | 17.0 | 7089 | 0.6602 |
| 0.0064 | 18.0 | 7506 | 0.6736 |
| 0.004 | 19.0 | 7923 | 0.6785 |
| 0.003 | 20.0 | 8340 | 0.6821 |
### Framework versions
- PEFT 0.8.0
- Transformers 4.40.0
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1 | {"license": "apache-2.0", "library_name": "peft", "tags": ["generated_from_trainer"], "base_model": "openai/whisper-small", "model-index": [{"name": "Whisper-small-speechocean", "results": []}]} | nrshoudi/Whisper-small-speechocean | null | [
"peft",
"tensorboard",
"safetensors",
"generated_from_trainer",
"base_model:openai/whisper-small",
"license:apache-2.0",
"region:us"
]
| null | 2024-04-28T02:06:16+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": []} | Elhassnaoui-2001/mistral_7b-instruct-ploty | null | [
"transformers",
"safetensors",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
]
| null | 2024-04-28T02:06:18+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. -->
# Boya1_RMSProp_1-e5_10Epoch_swinv2-base-patch4_fold5
This model is a fine-tuned version of [microsoft/swinv2-base-patch4-window12-192-22k](https://huggingface.co/microsoft/swinv2-base-patch4-window12-192-22k) on the imagefolder dataset.
It achieves the following results on the evaluation set:
- Loss: 1.2529
- Accuracy: 0.6758
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 1.1907 | 1.0 | 924 | 1.1805 | 0.6048 |
| 1.0225 | 2.0 | 1848 | 0.9957 | 0.6503 |
| 0.8132 | 3.0 | 2772 | 0.9354 | 0.6774 |
| 0.5715 | 4.0 | 3696 | 1.0093 | 0.6725 |
| 0.6964 | 5.0 | 4620 | 0.9993 | 0.6820 |
| 0.6956 | 6.0 | 5544 | 1.0237 | 0.6809 |
| 0.4499 | 7.0 | 6468 | 1.0986 | 0.6807 |
| 0.4383 | 8.0 | 7392 | 1.2146 | 0.6736 |
| 0.278 | 9.0 | 8316 | 1.2342 | 0.6753 |
| 0.2251 | 10.0 | 9240 | 1.2529 | 0.6758 |
### Framework versions
- Transformers 4.35.0
- Pytorch 2.1.0
- Datasets 2.14.6
- Tokenizers 0.14.1
| {"license": "apache-2.0", "tags": ["generated_from_trainer"], "datasets": ["imagefolder"], "metrics": ["accuracy"], "base_model": "microsoft/swinv2-base-patch4-window12-192-22k", "model-index": [{"name": "Boya1_RMSProp_1-e5_10Epoch_swinv2-base-patch4_fold5", "results": [{"task": {"type": "image-classification", "name": "Image Classification"}, "dataset": {"name": "imagefolder", "type": "imagefolder", "config": "default", "split": "test", "args": "default"}, "metrics": [{"type": "accuracy", "value": 0.675792897804283, "name": "Accuracy"}]}]}]} | onizukal/Boya1_RMSProp_1-e5_10Epoch_swinv2-base-patch4_fold5 | null | [
"transformers",
"safetensors",
"swinv2",
"image-classification",
"generated_from_trainer",
"dataset:imagefolder",
"base_model:microsoft/swinv2-base-patch4-window12-192-22k",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| null | 2024-04-28T02:06:35+00:00 |
null | null | {} | CenturionHeart/T1NA | null | [
"region:us"
]
| null | 2024-04-28T02:07:04+00:00 |
|
null | null | {} | kschweik/roberta-base-finetuned-mnli | null | [
"region:us"
]
| null | 2024-04-28T02:10:22+00:00 |
|
null | transformers | {"license": "apache-2.0"} | Paolo16/LLama-3-8B-uncensored-4bit | null | [
"transformers",
"safetensors",
"gguf",
"llama",
"license:apache-2.0",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| null | 2024-04-28T02:12:56+00:00 |
|
null | null | {} | cbjun99/codebert-base | null | [
"region:us"
]
| null | 2024-04-28T02:13:53+00:00 |
|
object-detection | transformers |
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
| {"library_name": "transformers", "tags": []} | Spatiallysaying/detr-finetuned-runwaymarkings-Horizontal-v1 | null | [
"transformers",
"safetensors",
"detr",
"object-detection",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
]
| null | 2024-04-28T02:14:25+00:00 |
null | mlx |
# mlx-community/dolphin-2.9-llama3-8b-256-4bit
This model was converted to MLX format from [`cognitivecomputations/dolphin-2.9-llama3-8b-256k`]() using mlx-lm version **0.12.0**.
Refer to the [original model card](https://huggingface.co/cognitivecomputations/dolphin-2.9-llama3-8b-256k) 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/dolphin-2.9-llama3-8b-256-4bit")
response = generate(model, tokenizer, prompt="hello", verbose=True)
```
| {"license": "llama3", "tags": ["mlx"]} | mlx-community/dolphin-2.9-llama3-8b-256-4bit | null | [
"mlx",
"safetensors",
"llama",
"license:llama3",
"region:us"
]
| null | 2024-04-28T02:14:55+00:00 |
text-to-image | null |
# SDXS Onnx
Converted from [IDKiro/sdxs-512-0.9](https://huggingface.co/IDKiro/sdxs-512-0.9) (i.e. the original one, without dreamshaper) through this command:
```
optimum-cli export onnx -m <local absolute path to original model> --task stable-diffusion ./mysdxs
```
Notice that I replaced the `/vae` folder in the local copy of the repo with `/vae_large` in that same repo, and updated the model config at the repo root. This is because the Onnx converter doesn't currently seem mature enough to handle nonstandard pipeline so we're effectively using the original, ordinary autoencoder.
For actual inference, you can test with something like:
```py
from optimum.onnxruntime import ORTStableDiffusionPipeline
pipeline = ORTStableDiffusionPipeline.from_pretrained("/local/absolute/path/to/repo")
prompt = "Sailing ship in storm by Leonardo da Vinci"
image = pipeline(prompt, num_inference_steps=1, guidance_scale=0).images[0]
image.save("hello.png", "PNG")
```
## Using with TAESD
(Not tested yet)
Consider using the Onnx converted model of TAESD at [deinferno/taesd-onnx](https://huggingface.co/deinferno/taesd-onnx) (Original model at [madebyollin/taesd](https://huggingface.co/madebyollin/taesd) )
Combined inference code:
```py
from huggingface_hub import snapshot_download
from diffusers.pipelines import OnnxRuntimeModel
from optimum.onnxruntime import ORTStableDiffusionPipeline
taesd_dir = snapshot_download(repo_id="deinferno/taesd-onnx")
pipeline = ORTStableDiffusionPipeline.from_pretrained(
"lemonteaa/sdxs-onnx",
vae_decoder_session = OnnxRuntimeModel.from_pretrained(f"{taesd_dir}/vae_decoder"),
vae_encoder_session = OnnxRuntimeModel.from_pretrained(f"{taesd_dir}/vae_encoder"),
revision="onnx")
prompt = "Sailing ship in storm by Leonardo da Vinci"
image = pipeline(prompt, num_inference_steps=1, guidance_scale=0).images[0]
image.save("hello.png", "PNG")
```
| {"pipeline_tag": "text-to-image"} | lemonteaa/sdxs-onnx | null | [
"onnx",
"text-to-image",
"region:us"
]
| null | 2024-04-28T02:15:04+00:00 |
null | null | {"license": "unknown"} | 6vice/Lieu4200 | null | [
"license:unknown",
"region:us"
]
| null | 2024-04-28T02:15:08+00:00 |
|
null | null | {} | Grian/tile | null | [
"region:us"
]
| null | 2024-04-28T02:15:36+00:00 |
|
text-generation | transformers | # llama-3-experiment-v1-9B
This is an experimental merge, replicating additional layers to the model without post-merge healing.
There is damage to the model, but it appears to be tolerable as is; the performance difference in benchmarks from the original 8B Instruct model does not appear to be significant.
The resulting impact on narrative text completion may also be of interest.
Light testing performed with instruct prompting and the following sampler settings:
- temp=1 and minP=0.02
- temp=1 and smoothing factor=0.33
Full weights: [grimjim/llama-3-experiment-v1-9B](https://huggingface.co/grimjim/llama-3-experiment-v1-9B)
GGUF quants: [grimjim/llama-3-experiment-v1-9B-GGUF](https://huggingface.co/grimjim/llama-3-experiment-v1-9B-GGUF)
This is a merge of pre-trained language model meta-llama/Meta-Llama-3-8B-Instruct created using [mergekit](https://github.com/cg123/mergekit).
Built with Meta Llama 3.
## Merge Details
### Merge Method
This model was merged using the passthrough merge method.
### Models Merged
The following models were included in the merge:
* meta-llama/Meta-Llama-3-8B-Instruct
### Configuration
The following YAML configuration was used to produce this model:
```yaml
slices:
- sources:
- model: meta-llama/Meta-Llama-3-8B-Instruct
layer_range: [0, 12]
- sources:
- model: meta-llama/Meta-Llama-3-8B-Instruct
layer_range: [8, 32]
merge_method: passthrough
dtype: bfloat16
```
| {"language": ["en"], "license": "llama3", "library_name": "transformers", "tags": ["meta", "llama-3", "pytorch", "mergekit", "merge"], "base_model": ["meta-llama/Meta-Llama-3-8B-Instruct"], "license_link": "LICENSE", "pipeline_tag": "text-generation", "widget": [{"example_title": "Hello", "messages": [{"role": "user", "content": "Hey my name is Corwin! How are you?"}]}, {"example_title": "Hellriding out of Amber", "messages": [{"role": "system", "content": "You are a helpful and honest assistant. Please, respond concisely and truthfully."}, {"role": "user", "content": "Can you recommend a good destination for a hellride out of Amber?"}]}], "inference": {"parameters": {"max_new_tokens": 300, "stop": ["<|end_of_text|>", "<|eot_id|>"]}}, "model-index": [{"name": "grimjim/grimjim/llama-3-experiment-v1-9B", "results": [{"task": {"type": "text-generation", "name": "Text Generation"}, "dataset": {"name": "AI2 Reasoning Challenge (25-Shot)", "type": "ai2_arc", "config": "ARC-Challenge", "split": "test", "args": {"num_few_shot": 25}}, "metrics": [{"type": "acc_norm", "value": 66.41, "name": "normalized accuracy"}], "source": {"url": "https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=grimjim/grimjim/llama-3-experiment-v1-9B", "name": "Open LLM Leaderboard"}}, {"task": {"type": "text-generation", "name": "Text Generation"}, "dataset": {"name": "HellaSwag (10-Shot)", "type": "hellaswag", "split": "validation", "args": {"num_few_shot": 10}}, "metrics": [{"type": "acc_norm", "value": 78.56, "name": "normalized accuracy"}], "source": {"url": "https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=grimjim/llama-3-experiment-v1-9B", "name": "Open LLM Leaderboard"}}, {"task": {"type": "text-generation", "name": "Text Generation"}, "dataset": {"name": "MMLU (5-Shot)", "type": "cais/mmlu", "config": "all", "split": "test", "args": {"num_few_shot": 5}}, "metrics": [{"type": "acc", "value": 66.71, "name": "accuracy"}], "source": {"url": "https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=grimjim/llama-3-experiment-v1-9B", "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": 50.7}], "source": {"url": "https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=grimjim/llama-3-experiment-v1-9B", "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": 75.93, "name": "accuracy"}], "source": {"url": "https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=grimjim/llama-3-experiment-v1-9B", "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": 65.88, "name": "accuracy"}], "source": {"url": "https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=grimjim/llama-3-experiment-v1-9B", "name": "Open LLM Leaderboard"}}]}]} | grimjim/llama-3-experiment-v1-9B | null | [
"transformers",
"safetensors",
"llama",
"text-generation",
"meta",
"llama-3",
"pytorch",
"mergekit",
"merge",
"conversational",
"en",
"base_model:meta-llama/Meta-Llama-3-8B-Instruct",
"license:llama3",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| null | 2024-04-28T02:15:41+00:00 |
null | null | {"license": "openrail"} | itskeonagain/Annabelleshim | null | [
"license:openrail",
"region:us"
]
| null | 2024-04-28T02:15:43+00:00 |
|
text-generation | transformers | # llama-3-experiment-v1-9B-GGUF
This is an experimental merge, replicating additional layers to the model without post-merge healing. There is damage to the model, but it appears to be tolerable as is. The resulting impact on narrative text completion may be of interest.
Light testing performed with instruct prompting and the following sampler settings:
- temp=1 and minP=0.02
- temp=1 and smoothing factor=0.33
Full weights: [grimjim/llama-3-experiment-v1-9B](https://huggingface.co/grimjim/llama-3-experiment-v1-9B)
GGUF quants: [grimjim/llama-3-experiment-v1-9B-GGUF](https://huggingface.co/grimjim/llama-3-experiment-v1-9B-GGUF)
This is a merge of pre-trained language model meta-llama/Meta-Llama-3-8B-Instruct created using [mergekit](https://github.com/cg123/mergekit).
Built with Meta Llama 3.
## Merge Details
### Merge Method
This model was merged using the passthrough merge method.
### Models Merged
The following models were included in the merge:
* meta-llama/Meta-Llama-3-8B-Instruct
### Configuration
The following YAML configuration was used to produce this model:
```yaml
slices:
- sources:
- model: meta-llama/Meta-Llama-3-8B-Instruct
layer_range: [0, 12]
- sources:
- model: meta-llama/Meta-Llama-3-8B-Instruct
layer_range: [8, 32]
merge_method: passthrough
dtype: bfloat16
```
| {"language": ["en"], "license": "llama3", "library_name": "transformers", "tags": ["meta", "llama-3", "pytorch", "mergekit", "merge"], "base_model": ["meta-llama/Meta-Llama-3-8B-Instruct"], "license_link": "LICENSE", "pipeline_tag": "text-generation", "widget": [{"example_title": "Hello", "messages": [{"role": "user", "content": "Hey my name is Corwin! How are you?"}]}, {"example_title": "Hellriding out of Amber", "messages": [{"role": "system", "content": "You are a helpful and honest assistant. Please, respond concisely and truthfully."}, {"role": "user", "content": "Can you recommend a good destination for a hellride out of Amber?"}]}], "inference": {"parameters": {"max_new_tokens": 300, "stop": ["<|end_of_text|>", "<|eot_id|>"]}}} | grimjim/llama-3-experiment-v1-9B-GGUF | null | [
"transformers",
"gguf",
"llama",
"text-generation",
"meta",
"llama-3",
"pytorch",
"mergekit",
"merge",
"en",
"base_model:meta-llama/Meta-Llama-3-8B-Instruct",
"license:llama3",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| null | 2024-04-28T02:16:29+00:00 |
null | transformers | ## About
<!-- ### quantize_version: 2 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: -->
<!-- ### vocab_type: -->
static quants of https://huggingface.co/FPHam/Marvin_TheGrumpyOldAssistant_13B-HF
<!-- provided-files -->
weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion.
## Usage
If you are unsure how to use GGUF files, refer to one of [TheBloke's
READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
more details, including on how to concatenate multi-part files.
## Provided Quants
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
| Link | Type | Size/GB | Notes |
|:-----|:-----|--------:|:------|
| [GGUF](https://huggingface.co/mradermacher/Marvin_TheGrumpyOldAssistant_13B-HF-GGUF/resolve/main/Marvin_TheGrumpyOldAssistant_13B-HF.Q2_K.gguf) | Q2_K | 5.0 | |
| [GGUF](https://huggingface.co/mradermacher/Marvin_TheGrumpyOldAssistant_13B-HF-GGUF/resolve/main/Marvin_TheGrumpyOldAssistant_13B-HF.IQ3_XS.gguf) | IQ3_XS | 5.5 | |
| [GGUF](https://huggingface.co/mradermacher/Marvin_TheGrumpyOldAssistant_13B-HF-GGUF/resolve/main/Marvin_TheGrumpyOldAssistant_13B-HF.IQ3_S.gguf) | IQ3_S | 5.8 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/Marvin_TheGrumpyOldAssistant_13B-HF-GGUF/resolve/main/Marvin_TheGrumpyOldAssistant_13B-HF.Q3_K_S.gguf) | Q3_K_S | 5.8 | |
| [GGUF](https://huggingface.co/mradermacher/Marvin_TheGrumpyOldAssistant_13B-HF-GGUF/resolve/main/Marvin_TheGrumpyOldAssistant_13B-HF.IQ3_M.gguf) | IQ3_M | 6.1 | |
| [GGUF](https://huggingface.co/mradermacher/Marvin_TheGrumpyOldAssistant_13B-HF-GGUF/resolve/main/Marvin_TheGrumpyOldAssistant_13B-HF.Q3_K_M.gguf) | Q3_K_M | 6.4 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/Marvin_TheGrumpyOldAssistant_13B-HF-GGUF/resolve/main/Marvin_TheGrumpyOldAssistant_13B-HF.Q3_K_L.gguf) | Q3_K_L | 7.0 | |
| [GGUF](https://huggingface.co/mradermacher/Marvin_TheGrumpyOldAssistant_13B-HF-GGUF/resolve/main/Marvin_TheGrumpyOldAssistant_13B-HF.IQ4_XS.gguf) | IQ4_XS | 7.1 | |
| [GGUF](https://huggingface.co/mradermacher/Marvin_TheGrumpyOldAssistant_13B-HF-GGUF/resolve/main/Marvin_TheGrumpyOldAssistant_13B-HF.Q4_K_S.gguf) | Q4_K_S | 7.5 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Marvin_TheGrumpyOldAssistant_13B-HF-GGUF/resolve/main/Marvin_TheGrumpyOldAssistant_13B-HF.Q4_K_M.gguf) | Q4_K_M | 8.0 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Marvin_TheGrumpyOldAssistant_13B-HF-GGUF/resolve/main/Marvin_TheGrumpyOldAssistant_13B-HF.Q5_K_S.gguf) | Q5_K_S | 9.1 | |
| [GGUF](https://huggingface.co/mradermacher/Marvin_TheGrumpyOldAssistant_13B-HF-GGUF/resolve/main/Marvin_TheGrumpyOldAssistant_13B-HF.Q5_K_M.gguf) | Q5_K_M | 9.3 | |
| [GGUF](https://huggingface.co/mradermacher/Marvin_TheGrumpyOldAssistant_13B-HF-GGUF/resolve/main/Marvin_TheGrumpyOldAssistant_13B-HF.Q6_K.gguf) | Q6_K | 10.8 | very good quality |
| [GGUF](https://huggingface.co/mradermacher/Marvin_TheGrumpyOldAssistant_13B-HF-GGUF/resolve/main/Marvin_TheGrumpyOldAssistant_13B-HF.Q8_0.gguf) | Q8_0 | 13.9 | fast, best quality |
Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):
And here are Artefact2's thoughts on the matter:
https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
## FAQ / Model Request
See https://huggingface.co/mradermacher/model_requests for some answers to
questions you might have and/or if you want some other model quantized.
## Thanks
I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
me use its servers and providing upgrades to my workstation to enable
this work in my free time.
<!-- end -->
| {"language": ["en"], "library_name": "transformers", "tags": ["llm", "llama2", "marvin", "funny", "model"], "base_model": "FPHam/Marvin_TheGrumpyOldAssistant_13B-HF", "quantized_by": "mradermacher"} | mradermacher/Marvin_TheGrumpyOldAssistant_13B-HF-GGUF | null | [
"transformers",
"gguf",
"llm",
"llama2",
"marvin",
"funny",
"model",
"en",
"base_model:FPHam/Marvin_TheGrumpyOldAssistant_13B-HF",
"endpoints_compatible",
"region:us"
]
| null | 2024-04-28T02:18:25+00:00 |
text-classification | transformers | {"license": "cc-by-nc-4.0"} | sgjwong/xlm-roberta-tw_ltedi | null | [
"transformers",
"safetensors",
"xlm-roberta",
"text-classification",
"license:cc-by-nc-4.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| null | 2024-04-28T02:19:26+00:00 |
|
null | null | {"license": "mit"} | Hev832/fcpe | null | [
"license:mit",
"region:us"
]
| null | 2024-04-28T02:19:28+00:00 |
|
null | null | {} | sm09-dev/an14 | null | [
"region:us"
]
| null | 2024-04-28T02:19:36+00:00 |
|
null | mlx |
# mlx-community/dolphin-2.9-llama3-8b-256-8bit
This model was converted to MLX format from [`cognitivecomputations/dolphin-2.9-llama3-8b-256k`]() using mlx-lm version **0.12.0**.
Refer to the [original model card](https://huggingface.co/cognitivecomputations/dolphin-2.9-llama3-8b-256k) 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/dolphin-2.9-llama3-8b-256-8bit")
response = generate(model, tokenizer, prompt="hello", verbose=True)
```
| {"license": "llama3", "tags": ["mlx"]} | mlx-community/dolphin-2.9-llama3-8b-256-8bit | null | [
"mlx",
"safetensors",
"llama",
"license:llama3",
"region:us"
]
| null | 2024-04-28T02:20:13+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. -->
[<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
model_type: LlamaForCausalLM
tokenizer_type: AutoTokenizer
strict: false
# dataset
datasets:
- path: BEE-spoke-data/bees-internal
type: completion # format from earlier
field: text # Optional[str] default: text, field to use for completion data
val_set_size: 0.05
sequence_len: 8192
sample_packing: true
pad_to_sequence_len: true
train_on_inputs: false
group_by_length: false
# WANDB
wandb_project: llama3-8bee
wandb_entity: pszemraj
wandb_watch: gradients
wandb_name: llama3-8bee-8192
hub_model_id: pszemraj/Meta-Llama-3-8Bee
hub_strategy: every_save
gradient_accumulation_steps: 8
micro_batch_size: 1
num_epochs: 1
optimizer: paged_adamw_32bit
lr_scheduler: cosine
learning_rate: 2e-5
load_in_8bit: false
load_in_4bit: false
bf16: auto
fp16:
tf32: true
torch_compile: true # requires >= torch 2.0, may sometimes cause problems
torch_compile_backend: inductor # Optional[str]
gradient_checkpointing: true
gradient_checkpointing_kwargs:
use_reentrant: false
early_stopping_patience:
logging_steps: 10
xformers_attention:
flash_attention: true
warmup_steps: 25
# hyperparams for freq of evals, saving, etc
evals_per_epoch: 3
saves_per_epoch: 3
save_safetensors: true
save_total_limit: 1 # Checkpoints saved at a time
output_dir: ./output-axolotl/output-model-gamma
resume_from_checkpoint:
deepspeed:
weight_decay: 0.0
special_tokens:
pad_token: <|end_of_text|>
```
</details><br>
# Meta-Llama-3-8Bee
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 None dataset.
It achieves the following results on the evaluation set:
- Loss: 2.3319
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 25
- num_epochs: 1
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| No log | 0.0 | 1 | 2.5339 |
| 2.3719 | 0.33 | 232 | 2.3658 |
| 2.2914 | 0.67 | 464 | 2.3319 |
### Framework versions
- Transformers 4.40.0.dev0
- Pytorch 2.3.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0 | {"language": ["en"], "license": "llama3", "tags": ["axolotl", "generated_from_trainer"], "datasets": ["BEE-spoke-data/bees-internal"], "base_model": "meta-llama/Meta-Llama-3-8B", "pipeline_tag": "text-generation", "model-index": [{"name": "Meta-Llama-3-8Bee", "results": []}]} | BEE-spoke-data/Meta-Llama-3-8Bee | null | [
"transformers",
"safetensors",
"llama",
"text-generation",
"axolotl",
"generated_from_trainer",
"en",
"dataset:BEE-spoke-data/bees-internal",
"base_model:meta-llama/Meta-Llama-3-8B",
"license:llama3",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| null | 2024-04-28T02:21:05+00:00 |
object-detection | transformers |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
[<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/qubvel-hf-co/transformers-detection-model-finetuning-cppe5/runs/6eb20ojg)
# facebook-detr-resnet-50-finetuned-10k-cppe5-auto-pad
This model is a fine-tuned version of [facebook/detr-resnet-50](https://huggingface.co/facebook/detr-resnet-50) on the cppe-5 dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 8
- eval_batch_size: 1
- seed: 1337
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 100.0
- mixed_precision_training: Native AMP
### Framework versions
- Transformers 4.41.0.dev0
- Pytorch 1.13.0+cu117
- Datasets 2.18.0
- Tokenizers 0.19.0
| {"license": "apache-2.0", "tags": ["object-detection", "vision", "generated_from_trainer"], "base_model": "facebook/detr-resnet-50", "model-index": [{"name": "facebook-detr-resnet-50-finetuned-10k-cppe5-auto-pad", "results": []}]} | qubvel-hf/facebook-detr-resnet-50-finetuned-10k-cppe5-auto-pad | null | [
"transformers",
"safetensors",
"detr",
"object-detection",
"vision",
"generated_from_trainer",
"base_model:facebook/detr-resnet-50",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
]
| null | 2024-04-28T02:23:41+00:00 |
null | null | ---
license: apache-2.0
---
# Model url: https://huggingface.co/TimeMobius/Mobius-RWKV-r5-chat-12B-8k
Considering the long context required for training from scratch, we decided to retrain the r5 12B model from 8k.
This model exhibits lower diversity compared to its predecessor, but it excels in following instructions and logical understanding. It is possible to utilize both models simultaneously as multi-agents, each performing a different task.
# Mobius RWKV r5 chat 12B 8k
Mobius is a RWKV v5.2 arch chat model, benifit from [Matrix-Valued States and Dynamic Recurrence](https://arxiv.org/abs/2404.05892)
## Introduction
Mobius is a RWKV v5.2 arch model, a state based RNN+CNN+Transformer Mixed language model pretrained on a certain amount of data.
In comparison with the previous released Mobius, the improvements include:
* Only 24G Vram to run this model locally with fp16;
* Significant performance improvement;
* Multilingual support ;
* Stable support of 128K context length.
* Base model [Mobius-mega-12B-128k-base](https://huggingface.co/TimeMobius/Moibus-mega-12B-128k-base)
## Usage
We encourage you use few shots to use this model, Desipte Directly use User: xxxx\n\nAssistant: xxx\n\n is really good too, Can boost all potential ability.
Recommend Temp and topp: 0.7 0.6/1 0.3/1.5 0.3/0.2 0.8
## More details
Mobius 12B 128k based on RWKV v5.2 arch, which is leading state based RNN+CNN+Transformer Mixed large language model which focus opensouce community
* 10~100 trainning/inference cost reduce;
* state based,selected memory, which mean good at grok;
* community support.
## requirements
24G vram to run fp16, 12G for int8, 6G for nf4 with Ai00 server.
* [RWKV Runner](https://github.com/josStorer/RWKV-Runner)
* [Ai00 server](https://github.com/cgisky1980/ai00_rwkv_server)
## future plan
If you need a HF version let us know
[Mobius-Chat-12B-128k](https://huggingface.co/TimeMobius/Mobius-Chat-12B-128k)
| {"license": "apache-2.0"} | xiaol/Mobius-RWKV-r5-chat-12B-8k | null | [
"arxiv:2404.05892",
"license:apache-2.0",
"region:us"
]
| null | 2024-04-28T02:24:13+00:00 |
null | null | {} | maykel19/TAREA | null | [
"region:us"
]
| null | 2024-04-28T02:24:20+00:00 |
|
null | peft | ## Training procedure
### Framework versions
- PEFT 0.4.0
| {"library_name": "peft"} | yuzhang/llava-prumerge-vicuna-13b-v1.5-lora | null | [
"peft",
"llava",
"region:us"
]
| null | 2024-04-28T02:24:51+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": []} | shallow6414/3bzox14 | null | [
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| null | 2024-04-28T02:24:59+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. -->
# CS505_COQE_viT5_total_Instruction0_PAOSL_v1_h1
This model is a fine-tuned version of [VietAI/vit5-large](https://huggingface.co/VietAI/vit5-large) on the None dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 8
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 25
- mixed_precision_training: Native AMP
### Training results
### Framework versions
- Transformers 4.39.3
- Pytorch 2.1.2
- Datasets 2.18.0
- Tokenizers 0.15.2
| {"license": "mit", "tags": ["generated_from_trainer"], "base_model": "VietAI/vit5-large", "model-index": [{"name": "CS505_COQE_viT5_total_Instruction0_PAOSL_v1_h1", "results": []}]} | ThuyNT/CS505_COQE_viT5_total_Instruction0_PAOSL_v1_h1 | null | [
"transformers",
"tensorboard",
"safetensors",
"t5",
"text2text-generation",
"generated_from_trainer",
"base_model:VietAI/vit5-large",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| null | 2024-04-28T02:25:32+00:00 |
null | null | {} | sm09-dev/style-sylvamagic | null | [
"region:us"
]
| null | 2024-04-28T02:26:04+00:00 |
|
null | null | <p align="center">
<img src="../assets/lumina-logo.png" width="30%"/>
<br>
</p>
# Lumina-T2I
Lumina-T2I is a model that generates images based on text conditions, supporting various text encoders and models of different parameter sizes. With minimal training costs, it achieves high-quality image generation by training from scratch. Additionally, it offers usage through CLI console programs and Web Demo displays.
Our generative model has `LargeDiT` as the backbone, the text encoder is the `LLaMa` 7B model, and the VAE uses a version of `sdxl` fine-tuned by stabilityai.
- Generation Model: Large-DiT
- Text Encoder: LLaMa-7B
- VAE: stabilityai/sd-vae-ft-sdxl
## 📰 News
- [2024-4-1] 🚀🚀🚀 We release the initial version of Lumina-T2I for text-to-image generation
## 🎮 Model Zoo
More checkpoints of our model will be released soon~
| Resolution | Flag-DiT Parameter| Text Encoder | Prediction | Download URL |
| ---------- | ----------------------- | ------------ | -----------|-------------- |
| 1024 | 5B | LLaMa-7B | Rectified Flow | [hugging face](https://huggingface.co/Alpha-VLLM/Lumina-T2I) |
## Installation
Before installation, ensure that you have a working ``nvcc``
```bash
# The command should work and show the same version number as in our case. (12.1 in our case).
nvcc --version
```
On some outdated distros (e.g., CentOS 7), you may also want to check that a late enough version of
``gcc`` is available
```bash
# The command should work and show a version of at least 6.0.
# If not, consult distro-specific tutorials to obtain a newer version or build manually.
gcc --version
```
Downloading Lumina-T2X repo from github:
```bash
git clone https://github.com/Alpha-VLLM/Lumina-T2X
```
### 1. Create a conda environment and install PyTorch
Note: You may want to adjust the CUDA version [according to your driver version](https://docs.nvidia.com/deploy/cuda-compatibility/#default-to-minor-version).
```bash
conda create -n Lumina_T2X -y
conda activate Lumina_T2X
conda install python=3.11 pytorch==2.1.0 torchvision==0.16.0 torchaudio==2.1.0 pytorch-cuda=12.1 -c pytorch -c nvidia -y
```
### 2. Install dependencies
```bash
pip install diffusers fairscale accelerate tensorboard transformers gradio torchdiffeq click
```
or you can use
```bash
cd lumina-t2i
pip install -r requirements.txt
```
### 3. Install ``flash-attn``
```bash
pip install flash-attn --no-build-isolation
```
### 4. Install [nvidia apex](https://github.com/nvidia/apex) (optional)
>[!Warning]
> While Apex can improve efficiency, it is *not* a must to make Lumina-T2X work.
>
> Note that Lumina-T2X works smoothly with either:
> + Apex not installed at all; OR
> + Apex successfully installed with CUDA and C++ extensions.
>
> However, it will fail when:
> + A Python-only build of Apex is installed.
>
> If the error `No module named 'fused_layer_norm_cuda'` appears, it typically means you are using a Python-only build of Apex. To resolve this, please run `pip uninstall apex`, and Lumina-T2X should then function correctly.
You can clone the repo and install following the official guidelines (note that we expect a full
build, i.e., with CUDA and C++ extensions)
```bash
pip install ninja
git clone https://github.com/NVIDIA/apex
cd apex
# if pip >= 23.1 (ref: https://pip.pypa.io/en/stable/news/#v23-1) which supports multiple `--config-settings` with the same key...
pip install -v --disable-pip-version-check --no-cache-dir --no-build-isolation --config-settings "--build-option=--cpp_ext" --config-settings "--build-option=--cuda_ext" ./
# otherwise
pip install -v --disable-pip-version-check --no-cache-dir --no-build-isolation --global-option="--cpp_ext" --global-option="--cuda_ext" ./
```
## Inference
To ensure that our generative model is ready to use immediately, we provide a user-friendly CLI program and a locally deployable Web Demo site.
### CLI
1. Install Lumina-T2I
```bash
pip install -e .
```
2. Prepare the pre-trained model
⭐⭐ (Recommended) you can use huggingface_cli to download our model:
```bash
huggingface-cli download --resume-download Alpha-VLLM/Lumina-T2I --local-dir /path/to/ckpt
```
or using git for cloning the model you want to use:
```bash
git clone https://huggingface.co/Alpha-VLLM/Lumina-T2I
```
1. Setting your personal inference configuration
Update your own personal inference settings to generate different styles of images, checking `config/infer/config.yaml` for detailed settings. Detailed config structure:
> `/path/to/ckpt` should be a directory containing `consolidated*.pth` and `model_args.pth`
```yaml
- settings:
model:
ckpt: "/path/to/ckpt" # if ckpt is "", you should use `--ckpt` for passing model path when using `lumina` cli.
ckpt_lm: "" # if ckpt is "", you should use `--ckpt_lm` for passing model path when using `lumina` cli.
token: "" # if LLM is a huggingface gated repo, you should input your access token from huggingface and when token is "", you should `--token` for accessing the model.
transport:
path_type: "Linear" # option: ["Linear", "GVP", "VP"]
prediction: "velocity" # option: ["velocity", "score", "noise"]
loss_weight: "velocity" # option: [None, "velocity", "likelihood"]
sample_eps: 0.1
train_eps: 0.2
ode:
atol: 1e-6 # Absolute tolerance
rtol: 1e-3 # Relative tolerance
reverse: false # option: true or false
likelihood: false # option: true or false
sde:
sampling_method: "Euler" # option: ["Euler", "Heun"]
diffusion_form: "sigma" # option: ["constant", "SBDM", "sigma", "linear", "decreasing", "increasing-decreasing"]
diffusion_norm: 1.0 # range: 0-1
last_step: Mean # option: [None, "Mean", "Tweedie", "Euler"]
last_step_size: 0.04
infer:
resolution: "1024x1024" # option: ["1024x1024", "512x2048", "2048x512", "(Extrapolation) 1664x1664", "(Extrapolation) 1024x2048", "(Extrapolation) 2048x1024"]
num_sampling_steps: 60 # range: 1-1000
cfg_scale: 4. # range: 1-20
solver: "euler" # option: ["euler", "dopri5", "dopri8"]
t_shift: 4 # range: 1-20 (int only)
ntk_scaling: true # option: true or false
proportional_attn: true # option: true or false
seed: 0 # rnage: any number
```
- model:
- `ckpt`: lumina-t2i checkpoint path from [huggingface repo](https://huggingface.co/Alpha-VLLM/Lumina-T2I) containing `consolidated*.pth` and `model_args.pth`.
- `ckpt_lm`: LLM checkpoint.
- `token`: huggingface access token for accessing gated repo.
- transport:
- `path_type`: the type of path for transport: 'Linear', 'GVP' (Geodesic Vector Pursuit), or 'VP' (Vector Pursuit).
- `prediction`: the prediction model for the transport dynamics.
- `loss_weight`: the weighting of different components in the loss function, can be 'velocity' for dynamic modeling, 'likelihood' for statistical consistency, or None for no weighting
- `sample_eps`: sampling in the transport model.
- `train_eps`: training to stabilize the learning process.
- ode:
- `atol`: Absolute tolerance for the ODE solver. (options: ["Linear", "GVP", "VP"])
- `rtol`: Relative tolerance for the ODE solver. (option: ["velocity", "score", "noise"])
- `reverse`: run the ODE solver in reverse. (option: [None, "velocity", "likelihood"])
- `likelihood`: Enable calculation of likelihood during the ODE solving process.
- sde
- `sampling-method`: the numerical method used for sampling the stochastic differential equation: 'Euler' for simplicity or 'Heun' for improved accuracy.
- `diffusion-form`: form of diffusion coefficient in the SDE
- `diffusion-norm`: Normalizes the diffusion coefficient, affecting the scale of the stochastic component.
- `last-step`: form of last step taken in the SDE
- `last-step-size`: size of the last step taken
- infer
- `resolution`: generated image resolution.
- `num_sampling_steps`: sampling step for generating image.
- `cfg_scale`: classifier-free guide scaling factor
- `solver`: solver for image generation.
- `t_shift`: time shift factor.
- `ntk_scaling`: ntk rope scaling factor.
- `proportional_attn`: Whether to use proportional attention.
- `seed`: random initialization seeds.
1. Run with CLI
inference command:
```bash
lumina infer -c <config_path> <caption_here> <output_dir>
```
e.g. Demo command:
```bash
cd lumina-t2i
lumina infer -c "config/infer/settings.yaml" "a snow man of ..." "./outputs"
```
### Web Demo
To host a local gradio demo for interactive inference, run the following command:
```bash
# `/path/to/ckpt` should be a directory containing `consolidated*.pth` and `model_args.pth`
# default
python -u demo.py --ckpt "/path/to/ckpt"
# the demo by default uses bf16 precision. to switch to fp32:
python -u demo.py --ckpt "/path/to/ckpt" --precision fp32
# use ema model
python -u demo.py --ckpt "/path/to/ckpt" --ema
```
| {} | Alpha-VLLM/Lumina-T2I | null | [
"region:us"
]
| null | 2024-04-28T02:27:46+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. -->
# mistral-sigoIAspirantes-Orca-oass-500-gpu
This model is a fine-tuned version of [NickyNicky/Mistral-7B-OpenOrca-oasst_top1_2023-08-25-v2](https://huggingface.co/NickyNicky/Mistral-7B-OpenOrca-oasst_top1_2023-08-25-v2) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1371
## 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: 2.5e-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
- lr_scheduler_warmup_steps: 1
- training_steps: 500
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:------:|:----:|:---------------:|
| 1.6909 | 0.3521 | 25 | 1.2135 |
| 1.026 | 0.7042 | 50 | 0.8374 |
| 0.7146 | 1.0563 | 75 | 0.6276 |
| 0.5094 | 1.4085 | 100 | 0.4925 |
| 0.3916 | 1.7606 | 125 | 0.3939 |
| 0.3408 | 2.1127 | 150 | 0.3084 |
| 0.1724 | 2.4648 | 175 | 0.2717 |
| 0.2586 | 2.8169 | 200 | 0.2026 |
| 0.1434 | 3.1690 | 225 | 0.1940 |
| 0.1253 | 3.5211 | 250 | 0.1579 |
| 0.1197 | 3.8732 | 275 | 0.1526 |
| 0.0792 | 4.2254 | 300 | 0.1582 |
| 0.0937 | 4.5775 | 325 | 0.1579 |
| 0.0898 | 4.9296 | 350 | 0.1381 |
| 0.0717 | 5.2817 | 375 | 0.1386 |
| 0.0665 | 5.6338 | 400 | 0.1350 |
| 0.0773 | 5.9859 | 425 | 0.1325 |
| 0.0602 | 6.3380 | 450 | 0.1394 |
| 0.055 | 6.6901 | 475 | 0.1377 |
| 0.0602 | 7.0423 | 500 | 0.1371 |
### Framework versions
- PEFT 0.10.1.dev0
- Transformers 4.41.0.dev0
- Pytorch 2.3.0+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1 | {"license": "apache-2.0", "library_name": "peft", "tags": ["generated_from_trainer"], "base_model": "NickyNicky/Mistral-7B-OpenOrca-oasst_top1_2023-08-25-v2", "model-index": [{"name": "mistral-sigoIAspirantes-Orca-oass-500-gpu", "results": []}]} | fergos80/mistral-sigoIAspirantes-Orca-oass-500-gpu | null | [
"peft",
"safetensors",
"mistral",
"generated_from_trainer",
"base_model:NickyNicky/Mistral-7B-OpenOrca-oasst_top1_2023-08-25-v2",
"license:apache-2.0",
"4-bit",
"region:us"
]
| null | 2024-04-28T02:27:56+00:00 |
text-generation | transformers |
# Llama-3-Ko-Instruct
## Methodology
https://huggingface.co/blog/maywell/llm-feature-transfer
Paper Soon
### Model Used
[meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct)
[meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B)
[beomi/Llama-3-Open-Ko-8B](https://huggingface.co/beomi/Llama-3-Open-Ko-8B)
## Benchmark
### Kobest
| Task | beomi/Llama-3-Open-Ko-8B-Instruct | maywell/Llama-3-Ko-8B-Instruct |
| --- | --- | --- |
| kobest overall | 0.6220 ± 0.0070 | 0.6852 ± 0.0066 |
| kobest_boolq| 0.6254 ± 0.0129| 0.7208 ± 0.0120
| kobest_copa| 0.7110 ± 0.0143| 0.7650 ± 0.0134
| kobest_hellaswag| 0.3840 ± 0.0218| 0.4440 ± 0.0222
| kobest_sentineg| 0.8388 ± 0.0185| 0.9194 ± 0.0137
| kobest_wic| 0.5738 ± 0.0139| 0.6040 ± 0.0138
# Original Model Card by Beomi
> Update @ 2024.04.24: Release Llama-3-Open-Ko-8B model & [Llama-3-Open-Ko-8B-Instruct-preview](https://huggingface.co/beomi/Llama-3-Open-Ko-8B-Instruct-preview)
## Model Details
**Llama-3-Open-Ko-8B**
Llama-3-Open-Ko-8B model is continued pretrained language model based on Llama-3-8B.
This model is trained fully with publicily available resource, with 60GB+ of deduplicated texts.
With the new Llama-3 tokenizer, the pretraining conducted with 17.7B+ tokens, which slightly more than Korean tokenizer(Llama-2-Ko tokenizer).
The train was done on TPUv5e-256, with the warm support from TRC program by Google.
**Note for [Llama-3-Open-Ko-8B-Instruct-preview](https://huggingface.co/beomi/Llama-3-Open-Ko-8B-Instruct-preview)**
With applying the idea from [Chat Vector paper](https://arxiv.org/abs/2310.04799), I released Instruction model named [Llama-3-Open-Ko-8B-Instruct-preview](https://huggingface.co/beomi/Llama-3-Open-Ko-8B-Instruct-preview).
Since it is NOT finetuned with any Korean instruction set(indeed `preview`), but it would be great starting point for creating new Chat/Instruct models.
**Meta Llama-3**
Meta developed and released the Meta Llama 3 family of large language models (LLMs), a collection of pretrained and instruction tuned generative text models in 8 and 70B sizes. The Llama 3 instruction tuned models are optimized for dialogue use cases and outperform many of the available open source chat models on common industry benchmarks. Further, in developing these models, we took great care to optimize helpfulness and safety.
**Model developers** Junbum Lee (Beomi)
**Variations** Llama-3-Open-Ko comes in one size — 8B.
**Input** Models input text only.
**Output** Models generate text and code only.
**Model Architecture** Llama 3 is an auto-regressive language model that uses an optimized transformer architecture.
<table>
<tr>
<td>
</td>
<td><strong>Training Data</strong>
</td>
<td><strong>Params</strong>
</td>
<td><strong>Context length</strong>
</td>
<td><strong>GQA</strong>
</td>
<td><strong>Token count</strong>
</td>
<td><strong>Knowledge cutoff</strong>
</td>
</tr>
<tr>
<td rowspan="2" >Llama-3-Open-Ko
</td>
<td rowspan="2" >Same as *Open-Solar-Ko Dataset
</td>
<td>8B
</td>
<td>8k
</td>
<td>Yes
</td>
<td rowspan="2" >17.7B+
</td>
<td>Jun, 2023
</td>
</tr>
</table>
*You can find dataset list here: https://huggingface.co/beomi/OPEN-SOLAR-KO-10.7B/tree/main/corpus
**Model Release Date** 2024.04.24.
**Status** This is a static model trained on an offline dataset.
**License** Llama3 License: [https://llama.meta.com/llama3/license](https://llama.meta.com/llama3/license)
## Intended Use
**Intended Use Cases** Llama 3 is intended for commercial and research use in English. Instruction tuned models are intended for assistant-like chat, whereas pretrained models can be adapted for a variety of natural language generation tasks.
**Out-of-scope** Use in any manner that violates applicable laws or regulations (including trade compliance laws). Use in any other way that is prohibited by the Acceptable Use Policy and Llama 3 Community License. Use in languages other than English**.
**Note: Developers may fine-tune Llama 3 models for languages beyond English provided they comply with the Llama 3 Community License and the Acceptable Use Policy.
## How to use
TBD
### Responsibility & Safety
We believe that an open approach to AI leads to better, safer products, faster innovation, and a bigger overall market. We are committed to Responsible AI development and took a series of steps to limit misuse and harm and support the open source community.
Foundation models are widely capable technologies that are built to be used for a diverse range of applications. They are not designed to meet every developer preference on safety levels for all use cases, out-of-the-box, as those by their nature will differ across different applications.
Rather, responsible LLM-application deployment is achieved by implementing a series of safety best practices throughout the development of such applications, from the model pre-training, fine-tuning and the deployment of systems composed of safeguards to tailor the safety needs specifically to the use case and audience.
As part of the Llama 3 release, we updated our [Responsible Use Guide](https://llama.meta.com/responsible-use-guide/) to outline the steps and best practices for developers to implement model and system level safety for their application. We also provide a set of resources including [Meta Llama Guard 2](https://llama.meta.com/purple-llama/) and [Code Shield](https://llama.meta.com/purple-llama/) safeguards. These tools have proven to drastically reduce residual risks of LLM Systems, while maintaining a high level of helpfulness. We encourage developers to tune and deploy these safeguards according to their needs and we provide a [reference implementation](https://github.com/meta-llama/llama-recipes/tree/main/recipes/responsible_ai) to get you started.
#### Responsible release
In addition to responsible use considerations outlined above, we followed a rigorous process that requires us to take extra measures against misuse and critical risks before we make our release decision.
Misuse
If you access or use Llama 3, you agree to the Acceptable Use Policy. The most recent copy of this policy can be found at [https://llama.meta.com/llama3/use-policy/](https://llama.meta.com/llama3/use-policy/).
## Ethical Considerations and Limitations
The core values of Llama 3 are openness, inclusivity and helpfulness. It is meant to serve everyone, and to work for a wide range of use cases. It is thus designed to be accessible to people across many different backgrounds, experiences and perspectives. Llama 3 addresses users and their needs as they are, without insertion unnecessary judgment or normativity, while reflecting the understanding that even content that may appear problematic in some cases can serve valuable purposes in others. It respects the dignity and autonomy of all users, especially in terms of the values of free thought and expression that power innovation and progress.
But Llama 3 is a new technology, and like any new technology, there are risks associated with its use. Testing conducted to date has been in English, and has not covered, nor could it cover, all scenarios. For these reasons, as with all LLMs, Llama 3’s potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate, biased or other objectionable responses to user prompts. Therefore, before deploying any applications of Llama 3 models, developers should perform safety testing and tuning tailored to their specific applications of the model. As outlined in the Responsible Use Guide, we recommend incorporating [Purple Llama](https://github.com/facebookresearch/PurpleLlama) solutions into your workflows and specifically [Llama Guard](https://ai.meta.com/research/publications/llama-guard-llm-based-input-output-safeguard-for-human-ai-conversations/) which provides a base model to filter input and output prompts to layer system-level safety on top of model-level safety.
Please see the Responsible Use Guide available at [http://llama.meta.com/responsible-use-guide](http://llama.meta.com/responsible-use-guide)
## Citation instructions
**Llama-3-Open-Ko**
```
@article{llama3openko,
title={Llama-3-Open-Ko},
author={L, Junbum},
year={2024},
url={https://huggingface.co/beomi/Llama-3-Open-Ko-8B}
}
```
**Original Llama-3**
```
@article{llama3modelcard,
title={Llama 3 Model Card},
author={AI@Meta},
year={2024},
url = {https://github.com/meta-llama/llama3/blob/main/MODEL_CARD.md}
}
```
| {"language": ["en", "ko"], "license": "other", "tags": ["facebook", "meta", "pytorch", "llama", "llama-3", "llama-3-ko"], "pipeline_tag": "text-generation", "license_name": "llama3", "license_link": "LICENSE"} | maywell/Llama-3-Ko-8B-Instruct | null | [
"transformers",
"safetensors",
"llama",
"text-generation",
"facebook",
"meta",
"pytorch",
"llama-3",
"llama-3-ko",
"conversational",
"en",
"ko",
"arxiv:2310.04799",
"license:other",
"autotrain_compatible",
"endpoints_compatible",
"has_space",
"text-generation-inference",
"region:us"
]
| null | 2024-04-28T02:30:58+00:00 |
null | null | {} | Aju020/t5-lora | null | [
"tensorboard",
"safetensors",
"region:us"
]
| null | 2024-04-28T02:31:19+00:00 |
|
null | transformers |
# DavidAU/D_AU-Orac-13B-Tiefighter-slerp-Q6_K-GGUF
This model was converted to GGUF format from [`DavidAU/D_AU-Orac-13B-Tiefighter-slerp`](https://huggingface.co/DavidAU/D_AU-Orac-13B-Tiefighter-slerp) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
Refer to the [original model card](https://huggingface.co/DavidAU/D_AU-Orac-13B-Tiefighter-slerp) for more details on the model.
## Use with llama.cpp
Install llama.cpp through brew.
```bash
brew install ggerganov/ggerganov/llama.cpp
```
Invoke the llama.cpp server or the CLI.
CLI:
```bash
llama-cli --hf-repo DavidAU/D_AU-Orac-13B-Tiefighter-slerp-Q6_K-GGUF --model d_au-orac-13b-tiefighter-slerp.Q6_K.gguf -p "The meaning to life and the universe is"
```
Server:
```bash
llama-server --hf-repo DavidAU/D_AU-Orac-13B-Tiefighter-slerp-Q6_K-GGUF --model d_au-orac-13b-tiefighter-slerp.Q6_K.gguf -c 2048
```
Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well.
```
git clone https://github.com/ggerganov/llama.cpp && cd llama.cpp && make && ./main -m d_au-orac-13b-tiefighter-slerp.Q6_K.gguf -n 128
```
| {"library_name": "transformers", "tags": ["mergekit", "merge", "llama-cpp", "gguf-my-repo"], "base_model": ["microsoft/Orca-2-13b", "KoboldAI/LLaMA2-13B-Tiefighter"]} | DavidAU/D_AU-Orac-13B-Tiefighter-slerp-Q6_K-GGUF | null | [
"transformers",
"gguf",
"mergekit",
"merge",
"llama-cpp",
"gguf-my-repo",
"base_model:microsoft/Orca-2-13b",
"base_model:KoboldAI/LLaMA2-13B-Tiefighter",
"endpoints_compatible",
"region:us"
]
| null | 2024-04-28T02:31:25+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": []} | AmirlyPhd/v2_bert-text-classification-model | null | [
"transformers",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
]
| null | 2024-04-28T02:32:18+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": []} | golf2248/6gi0xkw | null | [
"transformers",
"safetensors",
"stablelm",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| null | 2024-04-28T02:32:45+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": []} | golf2248/2de9rij | null | [
"transformers",
"safetensors",
"stablelm",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| null | 2024-04-28T02:32:50+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/xqin00o | null | [
"transformers",
"safetensors",
"stablelm",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| null | 2024-04-28T02:32:56+00:00 |
text-generation | transformers | {} | w32zhong/s3d-full_finetune_layerbottom20 | null | [
"transformers",
"safetensors",
"llama",
"text-generation",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| null | 2024-04-28T02:33:34+00:00 |
|
text-generation | transformers | ## モデル
- ベースモデル：[llm-jp/llm-jp-1.3b-v1.0](https://huggingface.co/llm-jp/llm-jp-1.3b-v1.0)
- 学習データセット：[llm-jp/databricks-dolly-15k-ja](https://huggingface.co/datasets/llm-jp/databricks-dolly-15k-ja)
- 学習方式：フルパラメータチューニング
## サンプル
```python
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained(
"ryota39/llm-jp-1b-sft-15k"
)
pad_token_id = tokenizer.pad_token_id
model = AutoModelForCausalLM.from_pretrained(
"ryota39/llm-jp-1b-sft-15k",
device_map="auto",
)
text = "###Input: 東京の観光名所を教えてください。\n###Output: "
tokenized_input = tokenizer.encode(
text,
add_special_tokens=False,
return_tensors="pt"
).to(model.device)
attention_mask = torch.ones_like(tokenized_input)
attention_mask[tokenized_input == pad_token_id] = 0
with torch.no_grad():
output = model.generate(
tokenized_input,
attention_mask=attention_mask,
max_new_tokens=128,
do_sample=True,
top_p=0.95,
temperature=0.8,
repetition_penalty=1.0
)[0]
print(tokenizer.decode(output))
```
## 出力例
```
###Input: 東京の観光名所を教えてください。
###Output: 東京には多くの観光名所がある：
1.皇居
2.江戸東京博物館
3.東京タワー
4.東京スカイツリー
5.芝公園
6.東京タワー、増上寺、増上寺宝物館
7.浜離宮恩賜庭園
8.東京都庁
9.増上寺
10.新宿御苑
11.浅草寺
12.上野公園
13.お台場
14.明治神宮
15.上野動物園
16.東京国立博物館
17.浅草寺、浅草寺仲見
```
## 謝辞
本成果は【LOCAL AI HACKATHON #001】240時間ハッカソンの成果です。
運営の方々に深く御礼申し上げます。
- 【メタデータラボ株式会社】様
- 【AI声づくり技術研究会】
- サーバー主：やなぎ(Yanagi)様
- 【ローカルLLMに向き合う会】
- サーバー主：saldra(サルドラ)様
[メタデータラボ、日本最大規模のAIハッカソン「LOCAL AI HACKATHON #001」~ AIの民主化 ~を開催、本日より出場チームの募集を開始](https://prtimes.jp/main/html/rd/p/000000008.000056944.html)
| {"language": ["ja"], "license": "apache-2.0", "library_name": "transformers", "datasets": ["llm-jp/databricks-dolly-15k-ja"]} | ryota39/llm-jp-1b-sft-15k | null | [
"transformers",
"safetensors",
"gpt2",
"text-generation",
"ja",
"dataset:llm-jp/databricks-dolly-15k-ja",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| null | 2024-04-28T02:33:39+00:00 |
null | transformers |
# DavidAU/D_AU-Orac-13B-Tiefighter-slerp-Q5_K_M-GGUF
This model was converted to GGUF format from [`DavidAU/D_AU-Orac-13B-Tiefighter-slerp`](https://huggingface.co/DavidAU/D_AU-Orac-13B-Tiefighter-slerp) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
Refer to the [original model card](https://huggingface.co/DavidAU/D_AU-Orac-13B-Tiefighter-slerp) for more details on the model.
## Use with llama.cpp
Install llama.cpp through brew.
```bash
brew install ggerganov/ggerganov/llama.cpp
```
Invoke the llama.cpp server or the CLI.
CLI:
```bash
llama-cli --hf-repo DavidAU/D_AU-Orac-13B-Tiefighter-slerp-Q5_K_M-GGUF --model d_au-orac-13b-tiefighter-slerp.Q5_K_M.gguf -p "The meaning to life and the universe is"
```
Server:
```bash
llama-server --hf-repo DavidAU/D_AU-Orac-13B-Tiefighter-slerp-Q5_K_M-GGUF --model d_au-orac-13b-tiefighter-slerp.Q5_K_M.gguf -c 2048
```
Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well.
```
git clone https://github.com/ggerganov/llama.cpp && cd llama.cpp && make && ./main -m d_au-orac-13b-tiefighter-slerp.Q5_K_M.gguf -n 128
```
| {"library_name": "transformers", "tags": ["mergekit", "merge", "llama-cpp", "gguf-my-repo"], "base_model": ["microsoft/Orca-2-13b", "KoboldAI/LLaMA2-13B-Tiefighter"]} | DavidAU/D_AU-Orac-13B-Tiefighter-slerp-Q5_K_M-GGUF | null | [
"transformers",
"gguf",
"mergekit",
"merge",
"llama-cpp",
"gguf-my-repo",
"base_model:microsoft/Orca-2-13b",
"base_model:KoboldAI/LLaMA2-13B-Tiefighter",
"endpoints_compatible",
"region:us"
]
| null | 2024-04-28T02:34:32+00:00 |
null | null | {"license": "openrail"} | Cauthess/SungJinWoo | null | [
"license:openrail",
"region:us"
]
| null | 2024-04-28T02:35:07+00:00 |
|
null | null | {} | Josepig/Milo | null | [
"region:us"
]
| null | 2024-04-28T02:35:27+00:00 |
|
text-generation | transformers |
## モデル
- ベースモデル：[ryota39/llm-jp-1b-sft-100k-LoRA](https://huggingface.co/ryota39/llm-jp-1b-sft-100k-LoRA)
- 学習データセット：[llm-jp/hh-rlhf-12k-ja](https://huggingface.co/datasets/llm-jp/hh-rlhf-12k-ja)
- 学習方式：フルパラメータチューニング
## サンプル
```python
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained(
"ryota39/llm-jp-1b-sft-100k-LoRA-dpo-12k"
)
pad_token_id = tokenizer.pad_token_id
model = AutoModelForCausalLM.from_pretrained(
"ryota39/llm-jp-1b-sft-100k-LoRA-dpo-12k",
device_map="auto",
)
text = "###Input: 東京の観光名所を教えてください。\n###Output: "
tokenized_input = tokenizer.encode(
text,
add_special_tokens=False,
return_tensors="pt"
).to(model.device)
attention_mask = torch.ones_like(tokenized_input)
attention_mask[tokenized_input == pad_token_id] = 0
with torch.no_grad():
output = model.generate(
tokenized_input,
attention_mask=attention_mask,
max_new_tokens=128,
do_sample=True,
top_p=0.95,
temperature=0.8,
repetition_penalty=1.10
)[0]
print(tokenizer.decode(output))
```
## 出力例
```
###Input: 東京の観光名所を教えてください。
###Output: 20枚の観光スポット写真がランダムに出される。写真はどこでもよい。
10枚以上がベストだが、10枚以下でも可。1枚につき「観光地」と「街歩き」の2種類の選択肢があるが、この時には「観光地」しか選ばないこと。
写真は5秒以内に撮らせること。1人ずつ順番に写真を撮る。最後に写真から観光名所1枚を選び、その写真に対して###Output: 大阪の観光名所を教えてください。
###Output: 30
```
## 謝辞
本成果は【LOCAL AI HACKATHON #001】240時間ハッカソンの成果です。
運営の方々に深く御礼申し上げます。
- 【メタデータラボ株式会社】様
- 【AI声づくり技術研究会】
- サーバー主：やなぎ(Yanagi)様
- 【ローカルLLMに向き合う会】
- サーバー主：saldra(サルドラ)様
[メタデータラボ、日本最大規模のAIハッカソン「LOCAL AI HACKATHON #001」~ AIの民主化 ~を開催、本日より出場チームの募集を開始](https://prtimes.jp/main/html/rd/p/000000008.000056944.html) | {"language": ["ja"], "license": "cc", "library_name": "transformers", "tags": ["dpo"], "datasets": ["llm-jp/hh-rlhf-12k-ja"]} | ryota39/llm-jp-1b-sft-100k-LoRA-dpo-12k | null | [
"transformers",
"safetensors",
"gpt2",
"text-generation",
"dpo",
"ja",
"dataset:llm-jp/hh-rlhf-12k-ja",
"license:cc",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| null | 2024-04-28T02:39:33+00:00 |
null | null | {"license": "mit"} | thundernet8/voice-models-collection | null | [
"license:mit",
"region:us"
]
| null | 2024-04-28T02:40:26+00:00 |
|
null | null | {} | CenturionHeart/UMASA | null | [
"region:us"
]
| null | 2024-04-28T02:43:08+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. -->
# Falcon-7b-Finetuned-Extented-MBPP-Dataset-Synthetic
This model is a fine-tuned version of [tiiuae/falcon-7b-instruct](https://huggingface.co/tiiuae/falcon-7b-instruct) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 1.2069
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-06
- train_batch_size: 1
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.05
- num_epochs: 4
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 0.9825 | 0.24 | 500 | 1.5994 |
| 0.8528 | 0.47 | 1000 | 1.2043 |
| 0.4851 | 0.71 | 1500 | 1.1762 |
| 0.5511 | 0.94 | 2000 | 1.1914 |
| 0.4916 | 1.18 | 2500 | 1.2069 |
### Framework versions
- PEFT 0.10.1.dev0
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.15.2 | {"license": "apache-2.0", "library_name": "peft", "tags": ["trl", "sft", "generated_from_trainer"], "base_model": "tiiuae/falcon-7b-instruct", "model-index": [{"name": "Falcon-7b-Finetuned-Extented-MBPP-Dataset-Synthetic", "results": []}]} | MUsama100/Falcon-7b-Finetuned-Extented-MBPP-Dataset-Synthetic | null | [
"peft",
"tensorboard",
"safetensors",
"trl",
"sft",
"generated_from_trainer",
"base_model:tiiuae/falcon-7b-instruct",
"license:apache-2.0",
"region:us"
]
| null | 2024-04-28T02:47:50+00:00 |
reinforcement-learning | null |
# **Q-Learning** Agent playing1 **FrozenLake-v1**
This is a trained model of a **Q-Learning** agent playing **FrozenLake-v1** .
## Usage
```python
model = load_from_hub(repo_id="HoldenT/q-FrozenLake-v1-4x4-noSlippery", filename="q-learning.pkl")
# Don't forget to check if you need to add additional attributes (is_slippery=False etc)
env = gym.make(model["env_id"])
```
| {"tags": ["FrozenLake-v1-4x4-no_slippery", "q-learning", "reinforcement-learning", "custom-implementation"], "model-index": [{"name": "q-FrozenLake-v1-4x4-noSlippery", "results": [{"task": {"type": "reinforcement-learning", "name": "reinforcement-learning"}, "dataset": {"name": "FrozenLake-v1-4x4-no_slippery", "type": "FrozenLake-v1-4x4-no_slippery"}, "metrics": [{"type": "mean_reward", "value": "1.00 +/- 0.00", "name": "mean_reward", "verified": false}]}]}]} | HoldenT/q-FrozenLake-v1-4x4-noSlippery | null | [
"FrozenLake-v1-4x4-no_slippery",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
]
| null | 2024-04-28T02:47:54+00:00 |
text-generation | transformers | {} | Hashif/Indian-legal-Llama-2-7b-v2 | null | [
"transformers",
"pytorch",
"llama",
"text-generation",
"conversational",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| null | 2024-04-28T02:47:58+00:00 |
|
object-detection | transformers | # Model Card for Model ID
This finetuned YOLOv5 model is developed to aid businesses in automating the inspection of returned goods. It utilizes advanced computer vision techniques to detect, classify, and assess the condition of items from images, determining whether returns are genuine or potentially fraudulent. The model is tailored to recognize various product conditions and features that align with common return reasons, enabling quick and efficient processing within return workflows.
## Model Details
### Model Description
The finetuned YOLOv5 model is designed specifically for use in retail and ecommerce environments to assist with the assessment of returned merchandise. It uses deep learning algorithms to analyze images of returned items, identifying specific product features, damages, or discrepancies that may indicate misuse or fraud. This model has been trained on a diverse dataset of product images, capturing a wide range of conditions, from new to heavily used items.
The model's capabilities include detecting subtle signs of wear and tear, modifications, or missing components that are often overlooked in manual inspections. By automating the inspection process, the model helps streamline return operations, reduce human error, and prevent fraudulent returns, thereby protecting revenue and improving customer service efficiency.
This YOLOv5 model variant has been optimized to perform well under various lighting conditions and camera angles, making it robust and reliable for deployment in varied operational settings where returns are processed. It integrates seamlessly with existing computer vision pipelines and can be further connected to APIs like OpenAI's GPT for enhanced decision-making about the item's return eligibility based on visual assessment.
- **Developed by:** Cody Liu, Arjun Dabir
- **Model type:** YOLOv5 (You Only Look Once version 5), Fine-tuned Object Detection Model
- **Language(s) (NLP):** Python
- **License:** Apache License 2.0
- **Finetuned from model:** YOLOv5
## Uses
### Direct Use
This finetuned YOLOv5 model is designed to detect and classify objects in images for return verification processes. It's intended for businesses to automate the inspection of returned goods, determining their condition and authenticity. The primary users are retail companies and online marketplaces aiming to streamline return operations and reduce fraudulent activities.
### Out-of-Scope Use
The model is not intended for applications beyond visual inspection tasks, such as medical image analysis, autonomous driving, or any environment where its object detection capabilities may not apply directly. It should not be used as a standalone decision-maker without human oversight due to the potential for misclassification. Misuse includes any application involving sensitive personal data or scenarios where a misclassification could lead to safety risks.
## Bias, Risks, and Limitations
This model, a fine-tuned version of YOLOv5 for object detection, is integrated with a GPT-based API to assess the condition of returned items. While this setup aims to automate the evaluation of returned goods, several biases, risks, and limitations are inherent in the technology:
Bias in Training Data: The object detection model's performance is contingent on the diversity and representativeness of its training dataset. If the training data lacks variety in terms of item conditions, environments, or object types, the model may exhibit biased or underperformative behavior against unrepresented categories.
Risk of Hallucination in LLM: The use of a language model (GPT) for interpreting object detection results introduces a risk of "hallucinations" or generating incorrect or misleading information based on the detected items. These inaccuracies can lead to incorrect assessments of item conditions, potentially categorizing non-fraudulent returns as fraudulent.
Limitations in Detection Capabilities: While YOLOv5 is robust in detecting objects within diverse and complex scenes, its accuracy can be compromised under conditions of poor lighting, occlusion, or unusual item orientations. These factors can lead to false negatives or false positives in identifying items and their conditions.
Sociotechnical Implications: Relying on automated systems for assessing returns could have implications for consumer trust and satisfaction. Incorrect assessments due to model limitations or errors can lead to customer dissatisfaction and potential loss of business, particularly if customers feel their returns are unjustly categorized.
Out-of-Scope Use: The model is not designed for and should not be used in scenarios involving sensitive or regulated items, such as pharmaceuticals, where specialized detection and assessment systems are required. Misuse in such contexts could lead to serious safety and compliance issues.
Acknowledging these limitations is crucial for deploying the model in a manner that minimizes risks and ensures fairness and accuracy in its applications. Further, continuous monitoring and updating of both the object detection and language processing components are recommended to address emergent biases or inaccuracies.
### Recommendations
Given the identified biases, risks, and limitations associated with the combined use of the YOLOv5 object detection model and the GPT language model in the returns assessment pipeline, the following recommendations are proposed to mitigate potential issues and enhance overall system effectiveness:
Enhance Dataset Diversity: Regularly update and expand the training datasets for the YOLOv5 model to include a wider range of items, conditions, and environmental factors. This will help reduce bias and improve the model's accuracy across diverse real-world scenarios.
Improve Error Handling: Develop robust error-handling and verification protocols to address and mitigate the risks of hallucinations from the GPT model. This could include cross-verifications with additional data sources or manual reviews in cases of uncertainty or high-risk assessments.
Conduct Regular Model Audits: Perform periodic audits of both the YOLOv5 and GPT models to assess and improve their performance and fairness. This includes testing the models against new and varied datasets to identify any potential drifts or biases in model behavior.
Increase Transparency: Provide clear documentation and transparency regarding the model's capabilities, limitations, and the basis of its decisions. This could involve detailed logs of decision pathways and the factors influencing model assessments, accessible to both customers and regulatory bodies.
User Education: Educate users and stakeholders about the capabilities, general workings, and limitations of the AI system. This helps set realistic expectations and promotes more informed and cautious use of the technology.
Develop Contingency Plans: Establish contingency plans including manual oversight and customer service interventions to handle disputes or failures in the automated system effectively. This will help maintain customer trust and mitigate negative impacts from potential model failures.
Ethical and Compliance Checks: Ensure that the deployment and ongoing use of the model comply with relevant laws and ethical guidelines, particularly those concerning consumer rights and data protection.
Implementing these recommendations will help in responsibly leveraging AI capabilities to enhance business processes while maintaining trust and compliance.
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
```python
import torch
import intel_extension_for_pytorch as ipex
from models.common import DetectMultiBackend
from utils.general import non_max_suppression, scale_boxes
from utils.torch_utils import select_device
from utils.dataloaders import LoadImages
from pathlib import Path
def run_inference(weights, source, imgsz=(640, 640), conf_thres=0.25, iou_thres=0.45):
# Initialize device and model
device = select_device('')
model = DetectMultiBackend(weights, device=device, dnn=False)
model = ipex.optimize(model, dtype=torch.float32) # Optimize model
# Load image
dataset = LoadImages(source, img_size=imgsz, stride=model.stride, auto=model.pt)
path, img, im0s, _ = next(iter(dataset))
# Inference
img = torch.from_numpy(img).to(device)
img = img.float() # uint8 to fp32
img /= 255 # 0 - 255 to 0.0 - 1.0
if len(img.shape) == 3:
img = img[None] # expand for batch dim
with torch.cpu.amp.autocast(): # Enable mixed precision
pred = model(img, augment=False, visualize=False)
# Apply non-max suppression
pred = non_max_suppression(pred, conf_thres, iou_thres)
# Scale boxes to original image size and display or save
for i, det in enumerate(pred): # detections per image
if len(det):
det[:, :4] = scale_boxes(img.shape[2:], det[:, :4], im0s.shape).round()
return det # Return detections
if __name__ == '__main__':
weights_path = 'path/to/yolov5s.pt'
image_path = 'path/to/image.jpg'
detections = run_inference(weights_path, image_path)
print(f'Detections: {detections}')
```
### Key Modifications:
1. **Intel IPEX Optimization:** The model is wrapped with `ipex.optimize()` right after its instantiation to apply Intel-specific optimizations. You can specify the data type (`torch.float32` or `torch.bfloat16`) based on your preference for precision and performance.
2. **Mixed Precision:** Utilizes `torch.cpu.amp.autocast()` for mixed precision during inference, which can provide a boost in performance with minimal impact on accuracy when running on CPUs that support vector neural network instructions (VNNI).
## Training Details
### Training Data
https://huggingface.co/datasets/imagenet-1k
The ImageNet-1K dataset, available on Hugging Face, provides access to a subset of the larger ImageNet database, specifically the ILSVRC 2012 configuration. It includes 1,281,167 training images, 50,000 validation images, and 100,000 test images across 1,000 different object classes. This dataset is a fundamental resource for training deep learning models in various computer vision tasks due to its extensive range of high-quality, human-annotated images.
### Training Procedure
The YOLOv5 model was fine-tuned using the Intel® Extension for PyTorch*, which significantly optimized its performance on Intel architectures. This extension allows for more efficient computation and resource utilization, especially by enhancing the utilization of CPU capabilities, which are often less emphasized in typical GPU-centric training processes.
Technical Integration:
Intel® Extension for PyTorch: This extension optimizes PyTorch operations on Intel CPUs, leveraging Intel's oneDNN primitives to improve both training and inference speeds.
Intel® Deep Learning Boost (VNNI): This was employed to accelerate integer operations, common in convolutional networks like YOLOv5, enhancing model throughput during training.
BFloat16 Training: The use of BFloat16 data types supported by Intel CPUs allowed the model to train with larger batch sizes and faster epoch times with minimal impact on precision.
Parallel Training: The model used Intel's oneAPI Collective Communications Library (oneCCL) for efficient distributed training across Intel CPUs, enhancing scalability and reducing training times.
Performance Improvements:
The optimizations led to a noticeable increase in training speed and efficiency compared to traditional training setups on similar hardware.
Energy efficiency was also prioritized, with adjustments during training phases resulting in reduced power consumption.
Tools and Libraries:
Intel VTune™ Profiler: This tool was utilized to analyze the model's performance during training, helping to identify computational bottlenecks and optimize processing.
Intel® Advisor: This tool provided recommendations for vectorization and threading improvements, crucial for maximizing the multi-core capabilities of Intel CPUs.
These enhancements facilitated by Intel’s tools not only shortened the training cycle but also improved the overall efficiency of the YOLOv5 model, making it highly suitable for integration into computer vision pipelines that assess product returns.
#### Training Hyperparameters
- **Training regime:** bf16 mixed precision
### Results
[More Information Needed]
#### Summary
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:** Small VM - Intel® Xeon 4th Gen ® Scalable processor
- **Cloud Provider:** Intel® Developer Cloud
- **Compute Region:** us-region-1
## Citation
https://zenodo.org/records/7347926 | {"language": ["en"], "license": "apache-2.0", "library_name": "transformers", "tags": ["computer-vision", "object-detection", "fraud-detection", "yolov5"], "datasets": ["imagenet-1k"], "metrics": ["accuracy", "precision", "recall"]} | CodyLiu/checkThat_YOLOv5 | null | [
"transformers",
"computer-vision",
"object-detection",
"fraud-detection",
"yolov5",
"en",
"dataset:imagenet-1k",
"arxiv:1910.09700",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
]
| null | 2024-04-28T02:48:44+00:00 |
null | null | {} | xianlutech/llama3-8b-Instruct-v0.1 | null | [
"gguf",
"region:us"
]
| null | 2024-04-28T02:49:54+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": []} | MohammadKarami/medium-roberta | null | [
"transformers",
"safetensors",
"roberta",
"text-classification",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| null | 2024-04-28T02:50:25+00:00 |
text-generation | transformers | {} | anyisalin/Meta-Llama-3-8B-Instruct-FP8 | null | [
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| null | 2024-04-28T02:51:05+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": []} | shallow6414/4dheple | null | [
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| null | 2024-04-28T02:51:05+00:00 |
null | null | {"license": "openrail"} | KeroroK66/TodorokiHAjime | null | [
"license:openrail",
"region:us"
]
| null | 2024-04-28T02:53:19+00:00 |
|
null | null | {} | Aju020/new_model | null | [
"region:us"
]
| null | 2024-04-28T02:53:35+00:00 |
|
null | null | {} | dimson15/sn25-3-5 | null | [
"region:us"
]
| null | 2024-04-28T02:54:06+00:00 |
|
null | null | {"license": "openrail"} | KeroroK66/IchijouLilika | null | [
"license:openrail",
"region:us"
]
| null | 2024-04-28T02:54:26+00:00 |
|
text-generation | transformers |
# Model Card for free-solar-evo-v0.13
## Developed by : [Freewheelin](https://freewheelin-recruit.oopy.io/) AI Technical Team
## Method
- We were inspired by this [Sakana project](https://sakana.ai/evolutionary-model-merge/)
## Base Model
- free-solar-evo-model | {"language": ["ko", "en"], "license": "mit"} | freewheelin/free-solar-evo-v0.13 | null | [
"transformers",
"safetensors",
"llama",
"text-generation",
"ko",
"en",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| null | 2024-04-28T02:58:08+00:00 |
reinforcement-learning | ml-agents |
# **ppo** Agent playing **SnowballTarget**
This is a trained model of a **ppo** agent playing **SnowballTarget**
using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents).
## Usage (with ML-Agents)
The Documentation: https://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/
We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:
- A *short tutorial* where you teach Huggy the Dog 🐶 to fetch the stick and then play with him directly in your
browser: https://huggingface.co/learn/deep-rl-course/unitbonus1/introduction
- A *longer tutorial* to understand how works ML-Agents:
https://huggingface.co/learn/deep-rl-course/unit5/introduction
### Resume the training
```bash
mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume
```
### Watch your Agent play
You can watch your agent **playing directly in your browser**
1. If the environment is part of ML-Agents official environments, go to https://huggingface.co/unity
2. Step 1: Find your model_id: Epoching/ppo-SnowballTarget
3. Step 2: Select your *.nn /*.onnx file
4. Click on Watch the agent play 👀
| {"library_name": "ml-agents", "tags": ["SnowballTarget", "deep-reinforcement-learning", "reinforcement-learning", "ML-Agents-SnowballTarget"]} | Epoching/ppo-SnowballTarget | null | [
"ml-agents",
"tensorboard",
"onnx",
"SnowballTarget",
"deep-reinforcement-learning",
"reinforcement-learning",
"ML-Agents-SnowballTarget",
"region:us"
]
| null | 2024-04-28T02:58:44+00:00 |
null | null | {"license": "openrail"} | KeroroK66/HiodoshiAo | null | [
"license:openrail",
"region:us"
]
| null | 2024-04-28T02:58:48+00:00 |
|
text-generation | transformers | {} | w32zhong/s3d-full_finetune_layer930 | null | [
"transformers",
"safetensors",
"llama",
"text-generation",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| null | 2024-04-28T02:59:07+00:00 |
|
null | null | {"license": "openrail"} | TheAmir/Franksin | null | [
"license:openrail",
"region:us"
]
| null | 2024-04-28T03:00:29+00:00 |
|
null | null | {"license": "openrail"} | KeroroK66/SakamataChloe | null | [
"license:openrail",
"region:us"
]
| null | 2024-04-28T03:00:53+00:00 |
|
null | transformers | ## About
<!-- ### quantize_version: 2 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: -->
<!-- ### vocab_type: -->
static quants of https://huggingface.co/Yuma42/KangalKhan-NeoRuby-7B
<!-- provided-files -->
weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion.
## Usage
If you are unsure how to use GGUF files, refer to one of [TheBloke's
READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
more details, including on how to concatenate multi-part files.
## Provided Quants
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
| Link | Type | Size/GB | Notes |
|:-----|:-----|--------:|:------|
| [GGUF](https://huggingface.co/mradermacher/KangalKhan-NeoRuby-7B-GGUF/resolve/main/KangalKhan-NeoRuby-7B.Q2_K.gguf) | Q2_K | 2.8 | |
| [GGUF](https://huggingface.co/mradermacher/KangalKhan-NeoRuby-7B-GGUF/resolve/main/KangalKhan-NeoRuby-7B.IQ3_XS.gguf) | IQ3_XS | 3.1 | |
| [GGUF](https://huggingface.co/mradermacher/KangalKhan-NeoRuby-7B-GGUF/resolve/main/KangalKhan-NeoRuby-7B.Q3_K_S.gguf) | Q3_K_S | 3.3 | |
| [GGUF](https://huggingface.co/mradermacher/KangalKhan-NeoRuby-7B-GGUF/resolve/main/KangalKhan-NeoRuby-7B.IQ3_S.gguf) | IQ3_S | 3.3 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/KangalKhan-NeoRuby-7B-GGUF/resolve/main/KangalKhan-NeoRuby-7B.IQ3_M.gguf) | IQ3_M | 3.4 | |
| [GGUF](https://huggingface.co/mradermacher/KangalKhan-NeoRuby-7B-GGUF/resolve/main/KangalKhan-NeoRuby-7B.Q3_K_M.gguf) | Q3_K_M | 3.6 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/KangalKhan-NeoRuby-7B-GGUF/resolve/main/KangalKhan-NeoRuby-7B.Q3_K_L.gguf) | Q3_K_L | 3.9 | |
| [GGUF](https://huggingface.co/mradermacher/KangalKhan-NeoRuby-7B-GGUF/resolve/main/KangalKhan-NeoRuby-7B.IQ4_XS.gguf) | IQ4_XS | 4.0 | |
| [GGUF](https://huggingface.co/mradermacher/KangalKhan-NeoRuby-7B-GGUF/resolve/main/KangalKhan-NeoRuby-7B.Q4_K_S.gguf) | Q4_K_S | 4.2 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/KangalKhan-NeoRuby-7B-GGUF/resolve/main/KangalKhan-NeoRuby-7B.Q4_K_M.gguf) | Q4_K_M | 4.5 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/KangalKhan-NeoRuby-7B-GGUF/resolve/main/KangalKhan-NeoRuby-7B.Q5_K_S.gguf) | Q5_K_S | 5.1 | |
| [GGUF](https://huggingface.co/mradermacher/KangalKhan-NeoRuby-7B-GGUF/resolve/main/KangalKhan-NeoRuby-7B.Q5_K_M.gguf) | Q5_K_M | 5.2 | |
| [GGUF](https://huggingface.co/mradermacher/KangalKhan-NeoRuby-7B-GGUF/resolve/main/KangalKhan-NeoRuby-7B.Q6_K.gguf) | Q6_K | 6.0 | very good quality |
| [GGUF](https://huggingface.co/mradermacher/KangalKhan-NeoRuby-7B-GGUF/resolve/main/KangalKhan-NeoRuby-7B.Q8_0.gguf) | Q8_0 | 7.8 | fast, best quality |
| [GGUF](https://huggingface.co/mradermacher/KangalKhan-NeoRuby-7B-GGUF/resolve/main/KangalKhan-NeoRuby-7B.f16.gguf) | f16 | 14.6 | 16 bpw, overkill |
Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):
And here are Artefact2's thoughts on the matter:
https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
## FAQ / Model Request
See https://huggingface.co/mradermacher/model_requests for some answers to
questions you might have and/or if you want some other model quantized.
## Thanks
I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
me use its servers and providing upgrades to my workstation to enable
this work in my free time.
<!-- end -->
| {"language": ["en"], "license": "apache-2.0", "library_name": "transformers", "tags": ["merge", "mergekit", "lazymergekit", "argilla/CapybaraHermes-2.5-Mistral-7B", "argilla/distilabeled-OpenHermes-2.5-Mistral-7B"], "base_model": "Yuma42/KangalKhan-NeoRuby-7B", "quantized_by": "mradermacher"} | mradermacher/KangalKhan-NeoRuby-7B-GGUF | null | [
"transformers",
"gguf",
"merge",
"mergekit",
"lazymergekit",
"argilla/CapybaraHermes-2.5-Mistral-7B",
"argilla/distilabeled-OpenHermes-2.5-Mistral-7B",
"en",
"base_model:Yuma42/KangalKhan-NeoRuby-7B",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
]
| null | 2024-04-28T03:01:29+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": []} | quickstep3621/pzk6o2u | null | [
"transformers",
"safetensors",
"stablelm",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| null | 2024-04-28T03:01:31+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": []} | quickstep3621/4v6ph3k | null | [
"transformers",
"safetensors",
"stablelm",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| null | 2024-04-28T03:01:36+00:00 |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.