Zoyd/SenseLLM_ReflectionCoder-DS-6.7B-3_75bpw_exl2

Exllamav2 quant (exl2 / 3.75 bpw) made with ExLlamaV2 v0.1.1

Other EXL2 quants: | Quant | Model Size | lm_head | | ----- | ---------- | ------- | |<center>[2.2](https://huggingface.co/Zoyd/SenseLLM_ReflectionCoder-DS-6.7B-2_2bpw_exl2)</center> | <center>2055 MB</center> | <center>6</center> | |<center>[2.5](https://huggingface.co/Zoyd/SenseLLM_ReflectionCoder-DS-6.7B-2_5bpw_exl2)</center> | <center>2276 MB</center> | <center>6</center> | |<center>[3.0](https://huggingface.co/Zoyd/SenseLLM_ReflectionCoder-DS-6.7B-3_0bpw_exl2)</center> | <center>2665 MB</center> | <center>6</center> | |<center>[3.5](https://huggingface.co/Zoyd/SenseLLM_ReflectionCoder-DS-6.7B-3_5bpw_exl2)</center> | <center>3051 MB</center> | <center>6</center> | |<center>[3.75](https://huggingface.co/Zoyd/SenseLLM_ReflectionCoder-DS-6.7B-3_75bpw_exl2)</center> | <center>3245 MB</center> | <center>6</center> | |<center>[4.0](https://huggingface.co/Zoyd/SenseLLM_ReflectionCoder-DS-6.7B-4_0bpw_exl2)</center> | <center>3437 MB</center> | <center>6</center> | |<center>[4.25](https://huggingface.co/Zoyd/SenseLLM_ReflectionCoder-DS-6.7B-4_25bpw_exl2)</center> | <center>3630 MB</center> | <center>6</center> | |<center>[5.0](https://huggingface.co/Zoyd/SenseLLM_ReflectionCoder-DS-6.7B-5_0bpw_exl2)</center> | <center>4208 MB</center> | <center>6</center> | |<center>[6.0](https://huggingface.co/Zoyd/SenseLLM_ReflectionCoder-DS-6.7B-6_0bpw_exl2)</center> | <center>5000 MB</center> | <center>8</center> | |<center>[6.5](https://huggingface.co/Zoyd/SenseLLM_ReflectionCoder-DS-6.7B-6_5bpw_exl2)</center> | <center>5388 MB</center> | <center>8</center> | |<center>[8.0](https://huggingface.co/Zoyd/SenseLLM_ReflectionCoder-DS-6.7B-8_0bpw_exl2)</center> | <center>6232 MB</center> | <center>8</center> |

ReflectionCoder: Learning from Reflection Sequence for Enhanced One-off Code Generation

<p align="center"> <a href="https://arxiv.org/abs/2405.17057">📄 Paper</a> • <a href="https://github.com/SenseLLM/ReflectionCoder">🏠 Repo</a> • <a href="https://huggingface.co/SenseLLM/ReflectionCoder-DS-33B">🤖 Models</a> • <a href="https://huggingface.co/datasets/SenseLLM/ReflectionSeq-GPT">📚 Datasets </a> </p>

Introduction

ReflectionCoder is a novel approach that effectively leverages reflection sequences constructed by integrating compiler feedback to improve one-off code generation performance. Please refer to our paper and repo for more details!

[image]

<hr>

Models

Datasets

How to Use

Chat Format

Following chat templates of most models, we use two special tokens to wrap the message of user and assistant, i.e., `<|user|>, <|assistant|>, and <|endofmessage|>. Furthermore, we use two special tokens to wrap the content of different blocks, *i.e.*, <|text|> and <|endofblock|>`. You can use the following template to prompt our ReflectionCoder.

<|user|><|text|> 
Your Instruction
<|endofblock|><|endofmessage|><|assistant|>

Inference Code

Please refer to our GitHub Repo for more technical details.

Citation

If you find this repo useful for your research, please kindly cite our paper:

@misc{ren2024reflectioncoder,
    title={ReflectionCoder: Learning from Reflection Sequence for Enhanced One-off Code Generation}, 
    author={Houxing Ren and Mingjie Zhan and Zhongyuan Wu and Aojun Zhou and Junting Pan and Hongsheng Li},
    year={2024},
    eprint={2405.17057},
    archivePrefix={arXiv},
    primaryClass={cs.CL}
}

Acknowledgments

We thank the following amazing projects that truly inspired us:

• —CodeLlama
• —DeepSeek-Coder
• —WizardCoder
• —Evol-CodeAlpaca-v1
• —MagiCoder
• —EvalPlus
• —OpenCoderInterpreter