abetlen / abetlen/llama-cpp-python
Add the possibility to pass all the generation parameters to the API of the server
Open
enhancement
- Dominant language
- Python
- Stars
- 10.6k
- Forks
- 1.4k
- PR merge metrics
- PR metrics pending
Description
Add the possibility to pass to the REST API of the server in the docker image ghcr.io/abetlen/llama-cpp-python:latest all the generation runtime parameters like temperature, repeat_penalty, max_tokens, grammar, stop, top_k, etc.
Contributor guide
Assessment
This issue has not been assessed yet.