api-for-open-llm
Openai style api for open large language models, using LLMs just as chatgpt! Support for LLaMA, LLaMA-2, BLOOM, Falcon, Baichuan, Qwen, Xverse, SqlCoder, CodeLLaMA, ChatGLM, ChatGLM2, ChatGLM3 etc. 开源大模型的统一后端接口
- stars
- 2,458
- 30-day movement
- starts with the next reading
- Related entries
- 60
- Connections
- 1
api-for-open-llm exposes an OpenAI-style API for open-source large language models, so you can call models like LLaMA, LLaMA-2, BLOOM, Falcon, Baichuan, Qwen, ChatGLM and CodeLLaMA as if they were ChatGPT. It is a Python backend (Docker-deployable, LangChain-tagged) that provides a unified interface across many model families.
Use it when you want existing OpenAI-compatible clients and tooling to talk to self-hosted open LLMs without rewriting integration code per model.
Use it to
- Serve open LLMs behind an OpenAI-compatible endpoint
- Swap ChatGPT clients onto self-hosted models
- Standardize access across multiple model families
- Deploy a unified LLM backend with Docker
- Wire open models into LangChain workflows
For Developers self-hosting open LLMs behind OpenAI-compatible APIs
- Role
- agent-framework
- Language
- Python
- Licence
- Apache-2.0
- Forks
- 270
- Open issues
- 21
- Last push
- 2024-09-26
- Latest release
- api-for-open-llm-v0.0.1 · 2023-08-11