github/concrete
1
1
Fork 0
mirror of https://github.com/zama-ai/concrete.git synced 2026-02-09 03:55:04 -05:00
Code Issues Packages Projects Releases Wiki Activity

feat: add ref issue 7b

Browse Source
This commit is contained in:
jfrery
2022-01-07 09:55:44 +01:00
committed by Jordan Fréry
parent 4a8c0c3d4d
commit 8f6d524c0f
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
concrete/quantization/post_training.py
View File

@@ -95,7 +95,7 @@ class PostTrainingAffineQuantization:
# compared to its quantized counterpart.
# Since this is the last layer and mostly used for classification,
# this does not have much impact.
# Put back 7 bits when 100% at 7b is achieved.
# TODO: Put back 7 bits when 100% at 7b is achieved (see issue #1332).
q_layer = QuantizedLinear(6, q_weights, q_bias)
else:
q_layer = QuantizedLinear(self.n_bits, q_weights, q_bias)