It seems eos_token_id is <|end|> (32007) instead of <|endoftext|> (32000).
Context: https://twitter.com/altryne/status/1783567596467491109?t=k5HHVmTCGDt4-TkXF8KyNw&s=19

Microsoft org

Please ensure that you are using the configuration defined in generation_config.json.

gugarosa changed pull request status to closed

That config is pretty lazy though.
You made 3 token_ids being the potential eos_token now?

Sign up or log in to comment