"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

Sign up or log in to comment