A unified language model server built upon vllm and infinity.
pip install -U imitater
python -m imitater.service.app -c config/example.yaml
Note
Chat template is required for the chat models.
Use export USE_MODELSCOPE_HUB=1
to download model from modelscope.
python tests/test_openai.py -c config/example.yaml
- Response choices.
- Rerank model support.