huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-09-10 11:54:52 +00:00
Code Issues Packages Projects Releases Wiki Activity

Fixing non 4bits quantization.

Browse Source
This commit is contained in:
Nicolas Patry 2023-08-07 12:19:02 +02:00
parent 16fadcec57
commit a217b4df5a
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/utils/gptq/quant_linear.py
View File

@ -263,7 +263,7 @@ class QuantLinear(nn.Module):
self.groupsize = groupsize
self.outfeatures = qweight.shape[1]
self.infeatures = qweight.shape[0] * 32 // 4
self.infeatures = qweight.shape[0] * 32 // bits
@classmethod
def new(cls, bits, groupsize, infeatures, outfeatures, bias):