Alibaba-NLP

/

gme-Qwen2-VL-7B-Instruct

like 71

Follow

Alibaba-NLP 1.6k

I want load model in vllm;

vllm == 0.9.2
torch == 2.7.0

transformers == 4.52.0

i can load model and run gme-2b when i use transformers == 4.52.0, but load gme-7b had some issue -> Should have a video_processor_type key in its video_preprocessor_config.json of config.json, or one of the following model_type keys in its config.json: instructblip, instructblipvideo, internvl, llava_next_video, llava_onevision, qwen2_5_omni, qwen2_5_vl, qwen2_vl, smolvlm, video_llava

i have tried transformers == 4.51.3, it also had some issue when i load gme-7b -> ModuleNotFoundError: No module named 'transformers.models.qwen2_vl.video_processing_qwen2_vl'

so confused!

Hope anyone can help me ..