InternLM / InternLM-XComposer

InternLM-XComposer-2.5: A Versatile Large Vision Language Model Supporting Long-Contextual Input and Output
2.06k stars 127 forks source link

couldn't find it in the cached files and it looks like openai/clip-vit-large-patch14-336 is not the path to a directory containing a file named config.json. #206

Closed Litong-sTs closed 3 months ago

Litong-sTs commented 4 months ago

couldn't find it in the cached files and it looks like openai/clip-vit-large-patch14-336 is not the path to a directory containing a file named config.json.请问一下,我是要下载这个openai/clip-vit-large-patch14-336模型配套使用吗?要是下载的话我要放在哪里,改哪里的代码? 微信图片_20240306160447

yhcao6 commented 4 months ago

It seems your network fails to connect to huggingface.

You can manually download openai/clip-vit-large-patch14-336, then change the path in the function build_vision_tower to your local path as follows:

def build_vision_tower():
    # vision_tower = 'openai/clip-vit-large-patch14-336'
    vision_tower = your_local_path
    return CLIPVisionTower(vision_tower)

You can find the file define the function build_vision_tower in the error traceback.

deku0818 commented 2 months ago

我更改了对应文件的函数,但是执行后就会恢复成原来的样子