huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-09-11 20:34:54 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix: setting the rotary base from the config for the grouped query models.

Browse Source
This commit is contained in:
Nilabhra 2024-05-14 10:14:18 +04:00
parent 46ada47963
commit c41573c67c
1 changed files with 2 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
server/text_generation_server/models/custom_modeling/flash_rw_modeling.py
View File

@ -481,6 +481,7 @@ class FlashRWLayer(nn.Module):
return mlp_output, residual
class FlashRWLayerNorm(nn.Module):
def __init__(self, config, prefix, weights):
super().__init__()
@ -602,7 +603,7 @@ class FlashRWLargeLayer(nn.Module):
def __init__(self, layer_id, config, weights):
super().__init__()
prefix = f"transformer.h.{layer_id}"
self.ln_layer = FlashRWLayerNorm(config, prefix, weights)
self.self_attention = FlashRWLargeAttention(