You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Models like llama-3 use a chat template where the expected stop sequence is <|eot_id|> instead of the common EOS token used in other models. This means that generative benchmarks like ifeval continue generating past the EOS token and give incorrect results.
One way to handle this would be to either include this special token as a default in the generative benchmarks or alternatively expose --stop_sequence as an argument in the main script that users can control.
The text was updated successfully, but these errors were encountered:
Hi @lewtun , just to clarify, is <|eot_id|> a different stop token for the chat template specifically?
And is the model using <|end_of_text|> for the rest?
Other question, do you think fixing #16 would be enough to solve this too?
Models like
llama-3
use a chat template where the expected stop sequence is<|eot_id|>
instead of the common EOS token used in other models. This means that generative benchmarks likeifeval
continue generating past the EOS token and give incorrect results.One way to handle this would be to either include this special token as a default in the generative benchmarks or alternatively expose
--stop_sequence
as an argument in the main script that users can control.The text was updated successfully, but these errors were encountered: