lmdeploy
lmdeploy copied to clipboard
[Feature] Support XTuner Lite Llava
In XTuner Lite, some modifications were made to HF Llava to support the LLM part which is remote code. As a result, the saved HF Llava model needs to be loaded using AutoModel.
https://github.com/pppppM/xtuner/tree/lite/xtuner/_lite/modelings/llava