Skip to content

Error If I try to load "gpt2" with model = GPT.from_pretrained('gpt2') #103

Description

@Terrambc

Good evening,

I have trouble to load the pre-trained weights from GPT.from_pretrained().
I get the following error message: OSError: Error no file named pytorch_model.bin, model.safetensors, tf_model.h5, model.ckpt.index or flax_model.msgpack found in directory gpt2.

So maybe some of you have a solution. I´m really new to the topic and I have worked through Mister Karpathy Video on Youtube. And there he tried it and it worked. However I get the error above. I checked the code and even copied the code from this repository to unchecked tipping error.

Best regards
Terra

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions