error with AutoModel GmeQwen2VLConfig after upgrade
Great work, but I have a question. After the latest update, the transform library is used to automatically load the model.
But when I run the latest inference code example, I get an error:
ValueError: Unrecognized configuration class <class 'transformers_modules.gme-Qwen2-VL-2B-Instruct.modeling_gme_qwen2vl.GmeQwen2VLConfig'> for this kind of AutoModel: AutoModel.
What is the reason for this error? Looking forward to your reply
same error
same error
Hi, a quick fix : Downgrade transformers<=4.51.3 and Replace "model_type": "gme_qwen2_vl", with "model_type": "qwen2_vl", in the config.json.
I will update the change soon.
same error
Hi, a quick fix : Replace
"model_type": "gme_qwen2_vl",with"model_type": "qwen2_vl",in theconfig.json.I will update the change soon.
Unrecognized video processor in Alibaba-NLP/gme-Qwen2-VL-2B-Instruct. 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
Hi, a quick fix : Replace
"model_type": "gme_qwen2_vl",with"model_type": "qwen2_vl",in theconfig.json.I will update the change soon.
Unrecognized video processor in Alibaba-NLP/gme-Qwen2-VL-2B-Instruct. Should have a
video_processor_typekey in its video_preprocessor_config.json of config.json, or one of the followingmodel_typekeys in its config.json: instructblip, instructblipvideo, internvl, llava_next_video, llava_onevision, qwen2_5_omni, qwen2_5_vl, qwen2_vl, smolvlm, video_llava
I finally downgraded transformer==4.46.0 to solve the problem
Hi all, I updated the code as a temporary solution. Do remember downgrade transformers to 4.51.3 or just use sentence_transformers.