ChatGLM3-6b Compatibility is expected as soon as possible.
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 39.5k
- Forks
- 4.8k
- PR merge metrics
- No merged PRs in 30d
Description
ChatGLM3-6B adopts a newly designed [Prompt format](https://github.com/THUDM/ChatGLM3/blob/main/PROMPT_en.md), supporting multi-turn dialogues as usual. It also natively supports [tool invocation](https://github.com/THUDM/ChatGLM3/blob/main/tools_using_demo/README_en.md) (Function Call), code execution (Code Interpreter), and Agent tasks in complex scenarios.
We have launched open source model API deployment code in OpenAI / ZhipuAI format, which can be used as the backend of any ChatGPT-based application. Currently, you can deploy by running [api_server.py](https://github.com/THUDM/ChatGLM3/blob/main/openai_api_demo/api_server.py) in the warehouse
project details: https://github.com/THUDM/ChatGLM3
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start with ChatGLM3's openai_api_demo/api_server.py and the linked prompt and tool-invocation documentation to understand the compatibility surface. Then locate the corresponding FastChat model-serving entry point and define done as supporting ChatGLM3-6B's prompt format and stated API capabilities; the issue names no FastChat files or tests.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- ai, backend
- Issue type
- Feature
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100