huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-09-10 20:04:52 +00:00
Code Issues Packages Projects Releases Wiki Activity

bugfix

Browse Source
This commit is contained in:
Yessen Kanapin 2023-08-29 22:22:40 +00:00
parent f4932aec89
commit 6a017f5208
1 changed files with 1 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
server/text_generation_server/models/custom_modeling/flash_llama_modeling.py
View File

@ -189,6 +189,7 @@ class FlashLlamaAttention(torch.nn.Module):
self.rotary_emb = PositionRotaryEmbedding.static( self.rotary_emb = PositionRotaryEmbedding.static(
dim=self.head_size, base=config.rope_theta, device=weights.device, dim=self.head_size, base=config.rope_theta, device=weights.device,
config=config
) )
self.softmax_scale = self.head_size**-0.5 self.softmax_scale = self.head_size**-0.5