Is there a ver of Transformers that we can use to run this yet?

#1
by samwit - opened

Is there a ver of Transformers that we can use to run this yet? eg gh pr?

Or something coming before the official release ?

samwit changed discussion title from Is there a ver of Transformer that we can use to run this yet? to Is there a ver of Transformers that we can use to run this yet?
Google org

There's a custom wheel here: https://huggingface.co/gg-tt/gemma-2-9b-it/tree/main/transformers

Please, note that this is work in progress and additional changes may be needed before release.

I am trying to access this model through TGI by huggingface. I am facing below issue
2024-06-27T06:31:02.081198Z ERROR warmup{max_input_length=1024 max_prefill_tokens=1024 max_total_tokens=2048 max_batch_size=Some(1)}:warmup: text_generation_client: router/client/src/lib.rs:33: Server error: Expected (head_size % 8 == 0) && (head_size <= 128) to be true, but got false. (Could this error message be improved? If so, please report an enhancement request to PyTorch.)
202
Could you please look into this

Google org

Gemma 2 support in TGI is coming later today.

Closing the original issue, the latest transformers release includes support for Gemma 2.

pcuenq changed discussion status to closed

Sign up or log in to comment