-
Notifications
You must be signed in to change notification settings - Fork 4.3k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
qwen2-vl微调,freeze_vision_tower设为false时报错 #5324
Comments
请问一下为什么我使用了4.45.0.dev0,还是会出现AttributeError: 'NoneType' object has no attribute 'image_processor'这个错误 |
你的torch版本是多少?我之前也遇到了这个问题,torch升级到2.4.0就没这个问题了 |
torch已经升级到2.4.0了,cuda是12.2,python版本试了好几个了都会报错。 |
我这边的配置: |
fixed |
使用examples/train_lora/qwen2vl_lora_sft.yaml脚本微调,一切正常。
将freeze_vision_tower设置为false后,运行脚本报错:ValueError: Target module Conv3d(3, 1280, kernel_size=(2, 14, 14), stride=(2, 14, 14), bias=False) is not supported. Currently, only the following modules are supported:
torch.nn.Linear
,torch.nn.Embedding
,torch.nn.Conv2d
,transformers.pytorch_utils.Conv1D
.更多信息:
torch 2.4.0+cu118
cuda 11.8
transformers 4.45.0.dev0(按照qwen2-vl的readme, pip install git+https://github.com/huggingface/transformers)
The text was updated successfully, but these errors were encountered: