huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-04-21 14:52:20 +00:00
Code Issues Packages Projects Releases Wiki Activity

Neox.

Browse Source
This commit is contained in:
Ubuntu 2023-06-13 16:05:53 +00:00 committed by Nicolas Patry
parent 3fb8979a6d
commit dadbbc27d5
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_neox_modeling.py
View File

@ -58,7 +58,7 @@ def load_row(config, prefix: str, weights, bias: bool):
def load_qkv(config, prefix: str, weights, num_heads, head_size, hidden_size):
weight = weights.get_multi_weights_col([prefix], quantize=config.quantize)
weight = weights.get_multi_weights_col([prefix], quantize=config.quantize, dim=0)
if isinstance(weight, torch.Tensor):
# Only on non quantized versions
weight = (