search

HazyResearch / safari

Convolutions for Sequence Modeling
Apache License 2.0
864 stars 71 forks source link

Downstream evaluation on SuperGLUE #29

Open moranant opened 1 year ago

moranant commented 1 year ago

Thank you for your great work! In the paper, you described LM over SuperGLUE being evaluated for zero-shot learning. Could you please share the code for that evaluation?

DanFu09 commented 1 year ago

We plugged the models into manifest and used the zero-shot baseline code from AMA.

moranant commented 1 year ago

Thank you for the quick response! If I use a transformer LM based on the experiment from state-spaces repository, what client should I use to plug it into manifest?