【求助贴】多模态课程video-llava运行报错 #334

New Issue

12535224197cs · 2024-10-31T17:06:39+08:00

12535224197cs commented

2024-10-31 17:06:39 +08:00

python -m videollava.serve.gradio_web_server
林希老师方不方便分享一下课程运行video-llava conda环境的yaml文件

Traceback (most recent call last):
  File "/home/hsw/anaconda3/envs/videollava/lib/python3.10/runpy.py", line 196, in _run_module_as_main
    return _run_code(code, main_globals, None,
  File "/home/hsw/anaconda3/envs/videollava/lib/python3.10/runpy.py", line 86, in _run_code
    exec(code, run_globals)
  File "/mnt/wksp/agi2/11multimodal/Video-LLaVA/videollava/serve/gradio_web_server.py", line 134, in <module>
    handler = Chat(model_path, conv_mode=conv_mode, load_8bit=load_8bit, load_4bit=load_8bit, device=device, cache_dir=cache_dir)
  File "/mnt/wksp/agi2/11multimodal/Video-LLaVA/videollava/serve/gradio_utils.py", line 55, in __init__
    self.tokenizer, self.model, processor, context_len = load_pretrained_model(model_path, model_base, model_name,
  File "/mnt/wksp/agi2/11multimodal/Video-LLaVA/videollava/model/builder.py", line 150, in load_pretrained_model
    if model.config.mm_image_tower is not None:
  File "/home/hsw/anaconda3/envs/videollava/lib/python3.10/site-packages/transformers/configuration_utils.py", line 261, in __getattribute__
    return super().__getattribute__(key)
AttributeError: 'LlavaConfig' object has no attribute 'mm_image_tower'

python -m videollava.serve.gradio_web_server 林希老师方不方便分享一下课程运行video-llava conda环境的yaml文件 ``` Traceback (most recent call last): File "/home/hsw/anaconda3/envs/videollava/lib/python3.10/runpy.py", line 196, in _run_module_as_main return _run_code(code, main_globals, None, File "/home/hsw/anaconda3/envs/videollava/lib/python3.10/runpy.py", line 86, in _run_code exec(code, run_globals) File "/mnt/wksp/agi2/11multimodal/Video-LLaVA/videollava/serve/gradio_web_server.py", line 134, in <module> handler = Chat(model_path, conv_mode=conv_mode, load_8bit=load_8bit, load_4bit=load_8bit, device=device, cache_dir=cache_dir) File "/mnt/wksp/agi2/11multimodal/Video-LLaVA/videollava/serve/gradio_utils.py", line 55, in __init__ self.tokenizer, self.model, processor, context_len = load_pretrained_model(model_path, model_base, model_name, File "/mnt/wksp/agi2/11multimodal/Video-LLaVA/videollava/model/builder.py", line 150, in load_pretrained_model if model.config.mm_image_tower is not None: File "/home/hsw/anaconda3/envs/videollava/lib/python3.10/site-packages/transformers/configuration_utils.py", line 261, in __getattribute__ return super().__getattribute__(key) AttributeError: 'LlavaConfig' object has no attribute 'mm_image_tower' ```

12535224197cs closed this issue

2024-10-31 17:35:31 +08:00

Sign in to join this conversation.