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
When using DeepSpeed MII, there are some parameters that do not work when querying the model that otherwise work when using model.generate or when using huggingface pipelines. I have also tried these parameters using DeepSpeed inference on its own and found them to work
The parameters that cause issues for me are num_beams and bad_words_ids but there may be more.
I have found do_sample, max_length, min_length, top_k, top_p, temperature, repetition_penalty, and early_stopping to not cause issues but there may be more.
The text was updated successfully, but these errors were encountered:
details = "Exception calling application: DeepSpeed does not support `num_beams` > 1, if this is important to you please add your request to: https://github.com/microsoft/DeepSpeed/issues/2506"
When using DeepSpeed MII, there are some parameters that do not work when querying the model that otherwise work when using model.generate or when using huggingface pipelines. I have also tried these parameters using DeepSpeed inference on its own and found them to work
The parameters that cause issues for me are
num_beams
andbad_words_ids
but there may be more.I have found
do_sample
,max_length
,min_length
,top_k
,top_p
,temperature
,repetition_penalty
, andearly_stopping
to not cause issues but there may be more.The text was updated successfully, but these errors were encountered: