Skip to content
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

How to load the TransGPT-MM-v0 model? #12

Open
qingchunlizhi opened this issue Aug 14, 2023 · 5 comments
Open

How to load the TransGPT-MM-v0 model? #12

qingchunlizhi opened this issue Aug 14, 2023 · 5 comments

Comments

@qingchunlizhi
Copy link

No description provided.

@qingchunlizhi qingchunlizhi changed the title How to How to load the TransGPT-MM-v0 model? Aug 14, 2023
@qingchunlizhi
Copy link
Author

I have found that multimodal models cannot be used directly. Can you provide more detailed explanations to reproduce the performence of multimodality
image

@threeColorFr
Copy link
Collaborator

threeColorFr commented Aug 17, 2023

请说出您的具体问题,具体推理参考https://github.com/DUOMO/TransGPT/tree/main/multi_modal

@threeColorFr
Copy link
Collaborator

threeColorFr commented Aug 17, 2023

比如终端形式,你可以传参数你的模型路径--from_pretrained your-model-path,比如你的图中就是TransGPT-MM-v0或者TransGPT-MM-v1
image

@kangxiao18
Copy link

tokenizer = AutoTokenizer.from_pretrained("THUDM/chatglm-6b", trust_remote_code=True)
到这一步时会出错,我将这里改为DUOMO-Lab/TransGPT-MM-v1,也就是在huggingface里下载的TransGPT-MM-v1文件夹,则会报出config.json找不到的问题

@corkiyao
Copy link

tokenizer = AutoTokenizer.from_pretrained("THUDM/chatglm-6b", trust_remote_code=True) 到这一步时会出错,我将这里改为DUOMO-Lab/TransGPT-MM-v1,也就是在huggingface里下载的TransGPT-MM-v1文件夹,则会报出config.json找不到的问题

你把你的config.json里面的chat模型路径修改成本地就好了。

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

4 participants