A chatbot demo with image input.
- extract llm model from huggingface model
python extract_xcomposer_llm.py # the llm part will saved to internlm_model folder.
- lanuch the demo
python app.py --model-name internlm-xcomposer-7b --llm-ckpt internlm_model
- lanuch the dmeo
python app.py --model-name qwen-vl-chat --hf-ckpt Qwen/Qwen-VL-Chat
- this demo uses the code in their repo to extract image features that might not very efficiency.
- this demo only contains the chat function. If you want to use localization ability in Qwen-VL-Chat or article generation function in InternLM-XComposer, you need implement these pre/post processes. The difference compared to chat is how to build prompts and use the output of model.