Mirrors
/
hf_text-generation-inference
mirror of https://github.com/huggingface/text-generation-inference.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

fix: prefer hidden_activation over hidden_act in gemma2 (#2381)

This commit is contained in:
drbh 2024-08-08 14:08:56 -04:00 committed by GitHub
parent 2ca5980634
commit f852190060
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
server/text_generation_server/models/custom_modeling/flash_gemma2_modeling.py
View File

@ -265,7 +265,7 @@ class FlashGemma2Attention(torch.nn.Module):
class Gemma2MLP(nn.Module): class Gemma2MLP(nn.Module):
def __init__(self, prefix, config, weights): def __init__(self, prefix, config, weights):
super().__init__() super().__init__()
act = config.hidden_act act = config.hidden_activation
self.act = ( self.act = (
ACT2FN[act] ACT2FN[act]
if "gelu" not in act if "gelu" not in act