---
license: apache-2.0
datasets:
- SenseLLM/ReflectionSeq-GPT
- SenseLLM/ReflectionSeq-DS
language:
- en
---
## 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!

![](method.png)

<hr>

## Models

| Model | Checkpoint | Size | HumanEval (+) | MBPP (+) | License|
|:-------|:------------|:------|:---------------|:----------|:--------|
| ReflectionCoder-CL-7B   | 🤗 [HF Link](https://huggingface.co./SenseLLM/ReflectionCoder-CL-7B) | 7B   | 75.0 (68.9)     | 72.2 (61.4)     | [Llama2](https://ai.meta.com/llama/license/) |
| ReflectionCoder-CL-34B  | 🤗 [HF Link](https://huggingface.co./SenseLLM/ReflectionCoder-CL-34B) | 34B  | 70.7 (66.5)     | 68.4 (56.6)     | [Llama2](https://ai.meta.com/llama/license/) |
| ReflectionCoder-DS-6.7B | 🤗 [HF Link](https://huggingface.co./SenseLLM/ReflectionCoder-DS-6.7B) | 6.7B | 80.5 (74.4)     | 81.5 (69.6)     | [DeepSeek](https://github.com/deepseek-ai/DeepSeek-Coder/blob/main/LICENSE-MODEL) |
| ReflectionCoder-DS-33B  | 🤗 [HF Link](https://huggingface.co./SenseLLM/ReflectionCoder-DS-33B) | 33B  | 82.9 (76.8) | 84.1 (72.0) | [DeepSeek](https://github.com/deepseek-ai/DeepSeek-Coder/blob/main/LICENSE-MODEL) |

## Datasets

| Dataset           | Link           | License                                      |
|:-------------------|:----------------|:----------------------------------------------|
| ReflectionSeq-GPT | 🤗 [HF Link](https://huggingface.co./datasets/SenseLLM/ReflectionSeq-GPT) | [License](LICENSE) |
| ReflectionSeq-DS  | 🤗 [HF Link](https://huggingface.co./datasets/SenseLLM/ReflectionSeq-DS) | [License](LICENSE) |


## 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.

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

#### Inference Code
Please refer to our [GitHub Repo](https://github.com/SenseLLM/ReflectionCoder) 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](https://ai.meta.com/research/publications/code-llama-open-foundation-models-for-code/)
- [DeepSeek-Coder](https://github.com/deepseek-ai/DeepSeek-Coder)
- [WizardCoder](https://github.com/nlpxucan/WizardLM/tree/main/WizardCoder)
- [Evol-CodeAlpaca-v1](https://huggingface.co./datasets/theblackcat102/evol-codealpaca-v1)
- [MagiCoder](https://github.com/ise-uiuc/magicoder/tree/main)
- [EvalPlus](https://github.com/evalplus/evalplus)
- [OpenCoderInterpreter](https://github.com/OpenCodeInterpreter/OpenCodeInterpreter/tree/main)