Skip to content

pretrain llm weight load issue #12

@poem2018

Description

@poem2018

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

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions