"hidden_act" required by vLLM for loading the model

#8

Hi, I get this error when loading ShieldGemma9B and ShieldGemma27B.
"""
AttributeError: 'Gemma2Config' object has no attribute 'hidden_act'
"""
This happen because the config file miss the "hidden_act": "gelu_pytorch_tanh", line!

Thoguht we added this when we updated the 2B and 9B. Thanks for catching this!

RyanMullins changed pull request status to merged
Your need to confirm your account before you can post a new comment.

Sign up or log in to comment