Model repeating information and "spitting out" random characters

#12
by brazilianslib - opened

First of all, congratulations on the launch. Gemma 2 9B is, at least in my tests, the best model for PT-BR. Much better than much larger models.
However, problems are constantly happening, such as:

  1. Repeat information;
  2. "Spit" text infinitely;
  3. Place tags like "</start_of" at the end of your answer.

I am eagerly awaiting a solution.

Once again, I thank the entire Google Gemma team.

Google org

Would recommend you to use eager attention implementation

The same error even with eager attention and bf16.

Google org

Hi @brazilianslib , Could you please try again by updating the latest transformer version (!pip install -U transformers) and let us know if the issue still persists? Thank you.

Sign up or log in to comment