After finetuning llava, can I run it without xtuner? about xtuner

[StarCycle]

Here is the answer from @pppppM:

1. LLaVA finetuned by xtuner cannot be loaded like Qwen-VL. Developers of Qwen-VL also put a model file (modeling_qwen.py) in their huggingface repo so they can load their model in this way. However, it also means Qwen-VL only allows a fixed model architecture. By contrast, LLaVA finetuned by xtuner allows different model architectures, like CLIP+Vicuna, CLIP+internlm, CLIP+internlm2, Dinov2+internlm, etc.

2. LLaVA finetuned by xtuner can be deployed in another way (pull #317, still under development). You can deploy the LLaVA model with huggingface llava chatbot (based on Huggingface transformers) or lmdeplot llava chatbot (based on LMDeploy Turbomind). The two chatbots share the same interface.