awesome-deepseek-coder/README.md
2024-04-03 11:19:27 +08:00

62 lines
6.9 KiB
Markdown
Raw Permalink Blame History

This file contains invisible Unicode characters

This file contains invisible Unicode characters that are indistinguishable to humans but may be processed differently by a computer. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

<p align="center">
<img width="1000px" alt="Awesome DeepSeek Coder" src="images/Awesome_DeepSeek_Coder.png">
</p>
📚 [English] | [中文](https://github.com/deepseek-ai/awesome-deepseek-coder/blob/main/README_CN.md)
<br>
# awesome-deepseek-coder ![Awesome](https://cdn.rawgit.com/sindresorhus/awesome/d7305f38d29fed78fa85652e3a63e154dd8e8829/media/badge.svg)
A curated list of open-source projects related to DeepSeek Coder.
## Chat with DeepSeek Coder
Chat Website: [coder.deepseek.com](https://coder.deepseek.com/)
## Official Resources
### Released Models
All models are available on Hugging Face: [huggingface.co/deepseek-ai](https://huggingface.co/deepseek-ai)
| Model Size | Base | Instruct |
|------------|------|----------|
| **1.3B** | [deepseek-coder-1.3b-base](https://huggingface.co/deepseek-ai/deepseek-coder-1.3b-base) | [deepseek-coder-1.3b-instruct](https://huggingface.co/deepseek-ai/deepseek-coder-1.3b-instruct) |
| **5.7B** | [deepseek-coder-5.7bmqa-base](https://huggingface.co/deepseek-ai/deepseek-coder-5.7bmqa-base) | [deepseek-coder-5.7bmqa-instruct](https://huggingface.co/deepseek-ai/deepseek-coder-5.7bmqa-instruct)(coming soon) |
| **6.7B** | [deepseek-coder-6.7B-base](https://huggingface.co/deepseek-ai/deepseek-coder-6.7B-base) | [deepseek-coder-6.7B-instruct](https://huggingface.co/deepseek-ai/deepseek-coder-6.7B-instruct) |
| **33B** | [deepseek-coder-33B-base](https://huggingface.co/deepseek-ai/deepseek-coder-33B-base) | [deepseek-coder-33B-instruct](https://huggingface.co/deepseek-ai/deepseek-coder-33B-instruct) |
## Community Resources
### Models built upon DeepSeek Coder
| Model Size | Models |
|------------|------|
| **1.3B** | [OpenCodeInterpreter-DS-1.3B](https://huggingface.co/m-a-p/OpenCodeInterpreter-DS-1.3B) |
| **6.7B** | [Magicoder-DS-6.7B](https://huggingface.co/ise-uiuc/Magicoder-DS-6.7B) <br> [Magicoder-S-DS-6.7B](https://huggingface.co/ise-uiuc/Magicoder-S-DS-6.7B) <br> [OpenCodeInterpreter-DS-6.7B](https://huggingface.co/m-a-p/OpenCodeInterpreter-DS-6.7B) <br> [openbuddy-deepseekcoder-6b-v16.1-32k](https://huggingface.co/OpenBuddy/openbuddy-deepseekcoder-6b-v16.1-32k) |
| **33B** | [WizardCoder-33B-V1.1](https://huggingface.co/WizardLM/WizardCoder-33B-V1.1) <br> [CodeFuse-DeepSeek-33B](https://huggingface.co/codefuse-ai/CodeFuse-DeepSeek-33B) <br> [OpenCodeInterpreter-DS-33B](https://huggingface.co/m-a-p/OpenCodeInterpreter-DS-33B) <br> [openbuddy-deepseekcoder-33b-v16.1-32k](https://huggingface.co/OpenBuddy/openbuddy-deepseekcoder-33b-v16.1-32k)|
### Quantized Models
- [TheBloke](https://huggingface.co/TheBloke) - TheBloke develops AWQ/GGUF/GPTQ format model files for DeepSeek's Deepseek Coder 1B/7B/33B models.
| Model Size | Base | Instruct |
|------------|------|----------|
| **1.3B** | [deepseek-coder-1.3b-base-AWQ](https://huggingface.co/TheBloke/deepseek-coder-1.3b-base-AWQ) <br> [deepseek-coder-1.3b-base-GGUF](https://huggingface.co/TheBloke/deepseek-coder-1.3b-base-GGUF) <br> [deepseek-coder-1.3b-base-GPTQ](https://huggingface.co/TheBloke/deepseek-coder-1.3b-base-GPTQ) | [deepseek-coder-1.3b-instruct-AWQ](https://huggingface.co/TheBloke/deepseek-coder-1.3b-instruct-AWQ) <br> [deepseek-coder-1.3b-instruct-GGUF](https://huggingface.co/TheBloke/deepseek-coder-1.3b-instruct-GGUF) <br> [deepseek-coder-1.3b-instruct-GPTQ](https://huggingface.co/TheBloke/deepseek-coder-1.3b-instruct-GPTQ) |
| **5.7B** | [deepseek-coder-5.7bmqa-base-AWQ](https://huggingface.co/TheBloke/deepseek-coder-5.7bmqa-base-AWQ) <br> [deepseek-coder-5.7bmqa-base-GGUF](https://huggingface.co/TheBloke/deepseek-coder-5.7bmqa-base-GGUF) <br> [deepseek-coder-5.7bmqa-base-GPTQ](https://huggingface.co/TheBloke/deepseek-coder-5.7bmqa-base-GPTQ) | [deepseek-coder-5.7bmqa-instruct-AWQ](https://huggingface.co/TheBloke/deepseek-coder-5.7bmqa-instruct-AWQ)(coming soon) <br> [deepseek-coder-5.7bmqa-instruct-GGUF](https://huggingface.co/TheBloke/deepseek-coder-5.7bmqa-instruct-GGUF)(coming soon) <br> [deepseek-coder-5.7bmqa-instruct-GPTQ](https://huggingface.co/TheBloke/deepseek-coder-5.7bmqa-instruct-GPTQ)(coming soon) |
| **6.7B** | [deepseek-coder-6.7B-base-AWQ](https://huggingface.co/TheBloke/deepseek-coder-6.7B-base-AWQ) <br> [deepseek-coder-6.7B-base-GGUF](https://huggingface.co/TheBloke/deepseek-coder-6.7B-base-GGUF) <br> [deepseek-coder-6.7B-base-GPTQ](https://huggingface.co/TheBloke/deepseek-coder-6.7B-base-GPTQ) | [deepseek-coder-6.7B-instruct-AWQ](https://huggingface.co/TheBloke/deepseek-coder-6.7B-instruct-AWQ) <br> [deepseek-coder-6.7B-instruct-GGUF](https://huggingface.co/TheBloke/deepseek-coder-6.7B-instruct-GGUF) <br> [deepseek-coder-6.7B-instruct-GPTQ](https://huggingface.co/TheBloke/deepseek-coder-6.7B-instruct-GPTQ) |
| **33B** | [deepseek-coder-33B-base-AWQ](https://huggingface.co/TheBloke/deepseek-coder-33B-base-AWQ) <br> [deepseek-coder-33B-base-GGUF](https://huggingface.co/TheBloke/deepseek-coder-33B-base-GGUF) <br> [deepseek-coder-33B-base-GPTQ](https://huggingface.co/TheBloke/deepseek-coder-33B-base-GPTQ) | [deepseek-coder-33B-instruct-AWQ](https://huggingface.co/TheBloke/deepseek-coder-33B-instruct-AWQ) <br> [deepseek-coder-33B-instruct-GGUF](https://huggingface.co/TheBloke/deepseek-coder-33B-instruct-GGUF) <br> [deepseek-coder-33B-instruct-GPTQ](https://huggingface.co/TheBloke/deepseek-coder-33B-instruct-GPTQ) |
### Copilot
[refact](https://github.com/smallcloudai/refact), an open-source AI coding assistant with blazing-fast code completion, powerful code improvement tools, and chat. It supports `deepseek-coder/1.3b/base`, `deepseek-coder/5.7b/mqa-base`, `deepseek-coder/6.7b/instruct`, `deepseek-coder/33b/instruct`.
[Tabby](https://github.com/TabbyML/tabby), a self-hosted and open-source AI coding assistant, presents itself as a formidable alternative to GitHub Copilot. Its latest leaderboard showcases deepseek-coder-6.7B as the top performer in code completion (https://leaderboard.tabbyml.com/). Dive in and explore the robust code completion features of DeepSeek Coder with Tabby [(link)](https://tabby.tabbyml.com/docs/models/).
<p align="center">
<img width="500px" alt="Tabby-Leaderboard" src="images/Tabby-Leaderboard.png">
</p>
[🧙AutoDev](https://github.com/unit-mesh/auto-dev), an open-source JetBrains' IDE AI coding assistant. It provide Deepseek 6.7b finetune data tools by [Unit Eval](https://github.com/unit-mesh/unit-eval), related to AutoDev prompts' [datasets](https://huggingface.co/datasets/unit-mesh/unit-eval-completion) and [finetuned model](https://huggingface.co/unit-mesh/autodev-deepseek-6.7b-finetunes), and [API server example](https://github.com/unit-mesh/unit-eval/blob/master/finetunes/deepseek/api-server-python38.py)
### APIs
- [limcheekin/deepseek-coder-6.7B-instruct-GGUF](https://huggingface.co/spaces/limcheekin/deepseek-coder-6.7B-instruct-GGUF): limcheekin provides API for `deepseek-coder-6.7B-instruct-GGUF` model.
## Contributing
Excited to see the awesome stuff you guys will create with DeepSeek Coder!