This repository lists key projects and related demos about CodeFuse.
CodeFuse aims to develop Code Large Language Models (Code LLMs) to support and enhance full-lifecycle AI native sotware developing, covering crucial stages such as design requirements, coding, testing, building, deployment, operations, and insight analysis. Below is the overall framework of CodeFuse.
We listed repositories according to the lifecycle above.
| LifeCycle Stage | Project Repository | Repo-Description |
|---|---|---|
| Project Copilot | NA | NA |
| Code Copilot | MFTCoder | Instruction-Tuning Framework |
| FastTransformer4CodeFuse | FT based Inference Engine | |
| CodeFuse-Eval | Evaluation kits for CodeFuse | |
| Test&Build Copilot | TestAgent | TestGPT demo frontend |
| Ops Copilot | DevOps-Eval | Benchmark for DevOps |
| DevOps-Model | Index for DevOps Models | |
| Data Copilot | CodeFuse-Query (coming soon) | Semantic Code Analysis Engine for Data Quality |
| Others | ChatBot | General chatbot frontend for CodeFuse |
| ModelCache | Semantic Cache for LLM Serving | |
| CoCA | Colinear Attention | |
| Awesine-Code-LLM | Code-LLM Survey | |
| This Repo | General Introduction & index of CodeFuse Repos |
| ModelName | Short Description | Modele Linls |
|---|---|---|
| CodeFuse-13B | Training from scratch by CodeFuse | HF ; MS |
| CodeFuse-CodeLLaMA-34B | Finetuning on CodeLLaMA-34B | HF ; MS |
| ** CodeFuse-CodeLLaMA-34B-4bits | 4bits quantized 34B model | HF ; MS |
| CodeFuse-StarCoder-15B | Finetuning on StarCoder-15B | HF ; MS |
| CodeFuse-Qwen-14B | Finetuning on Qwen-14B | HF ; MS |
| CodeFuse-CodeGeeX2-6B | Finetuning on CodeGeeX2-6B | HF ; MS |
| CodeFuse-DevOps-14B-Chat | Finetuning on DevOps-14B | HF ; MS |
| CodeFuse-DevOps-14B-Base | Continue trianing on Qwen-14B | HF ; MS |
| CodeFuse-TestGPT-7B | FineTuning on CodeLLaMA-7B | HF ; MS |
-
Video demos: Chinese version at below, English version under preparation. https://user-images.githubusercontent.com/103973989/267514150-21012a5d-652d-4aea-bcea-582e67855ad7.mp4
-
Online Demo: You can try our CodeFuse-CodeLlama-34B model on ModelScope: CodeFuse-CodeLlama34B-MFT-Demo
- You can also try to install the CodeFuse-Chatbot to test our models locally.
- HuggingFace.
- ModelScope.
- WiseModel.
- Train or finetuning on your own models, you can try our MFTCoder, which enables efficient fine-tuning for multi-task, multi-model, and multi-training-framework scenarios.
For more technique details about CodeFuse, please refere to our paper MFTCoder.
If you find our work useful or helpful for your R&D works, please feel free to cite our papers as below.
@article{mftcoder2023,
title={MFTCoder: Boosting Code LLMs with Multitask Fine-Tuning},
author={Bingchang Liu and Chaoyu Chen and Cong Liao and Zi Gong and Huan Wang and Zhichao Lei and Ming Liang and Dajun Chen and Min Shen and Hailian Zhou and Hang Yu and Jianguo Li},
year={2023},
journal={arXiv preprint arXiv},
archivePrefix={arXiv},
eprint={2311.02303}
}
@misc{di2023codefuse13b,
title={CodeFuse-13B: A Pretrained Multi-lingual Code Large Language Model},
author={Peng Di and Jianguo Li and Hang Yu and Wei Jiang and Wenting Cai and Yang Cao and Chaoyu Chen and Dajun Chen and Hongwei Chen and Liang Chen and Gang Fan and Jie Gong and Zi Gong and Wen Hu and Tingting Guo and Zhichao Lei and Ting Li and Zheng Li and Ming Liang and Cong Liao and Bingchang Liu and Jiachen Liu and Zhiwei Liu and Shaojun Lu and Min Shen and Guangpei Wang and Huan Wang and Zhi Wang and Zhaogui Xu and Jiawei Yang and Qing Ye and Gehao Zhang and Yu Zhang and Zelin Zhao and Xunjin Zheng and Hailian Zhou and Lifu Zhu and Xianying Zhu},
year={2023},
eprint={2310.06266},
archivePrefix={arXiv},
primaryClass={cs.SE}
}