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

Add support for "google/gemma-7b-it" #357

Closed
kurtome opened this issue Mar 2, 2024 · 1 comment · Fixed by #358
Closed

Add support for "google/gemma-7b-it" #357

kurtome opened this issue Mar 2, 2024 · 1 comment · Fixed by #358

Comments

@kurtome
Copy link

kurtome commented Mar 2, 2024

HuggingFace now has the Gemma model: https://huggingface.co/google/gemma-7b-it

Expected

    {:ok, nx_model_info} =
      Bumblebee.load_model({:hf, "google/gemma-7b-it", [auth_token: @hf_token]})

    {:ok, nx_tokenizer} =
      Bumblebee.load_tokenizer({:hf, "google/gemma-7b-it", [auth_token: @hf_token]})

Actual

ArgumentError
could not match the class name "GemmaForCausalLM" to any of the supported models,
please specify the :module and :architecture options
@seanmor5 seanmor5 mentioned this issue Mar 2, 2024
@seanmor5
Copy link
Contributor

seanmor5 commented Mar 2, 2024

See: #358

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

Successfully merging a pull request may close this issue.

2 participants