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

pretrain llm weight load issue #12

Open
poem2018 opened this issue Dec 24, 2024 · 1 comment
Open

pretrain llm weight load issue #12

poem2018 opened this issue Dec 24, 2024 · 1 comment

Comments

@poem2018
Copy link

Hi,

Thanks for the great work! I am trying to run the inference code according to the instruction, and met this error when loading the pretraining weight, is there any issue to resolve this?

llm = AutoModelForCausalLM.from_pretrained(model_name_or_path, config=llm_cfg, torch_dtype=eval(config.model_dtype), *args, **kwargs)

Error: safetensors_rust.SafetensorError: Error while deserializing header: HeaderTooLarge

@zhuoyang20
Copy link
Collaborator

Hi @poem2018 ,

Could you provide more details about your intended purpose and usage? The pre-trained weights for VILA-U can be easily loaded using the following command:

import vila_u
vila_u.load("vila-u-7b-256") # pre-trained model path 

Best,
Zhuoyang

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

2 participants