Skip to content

fix mixtral quantization scaler axis when dimension > 2 #132

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Jun 20, 2024
Merged

fix mixtral quantization scaler axis when dimension > 2 #132

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion convert_checkpoints.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -586,7 +586,7 @@ def main(argv) -> None:
if FLAGS.quantize_weights:
quantize_num_bits = 8 if "int8" in FLAGS.quantize_type else 4
is_blockwise = "blockwise" in FLAGS.quantize_type
weight_axis = lambda x: 0 if x in quantize_embedding_weight_map else 1
weight_axis = lambda x: 0 if x in quantize_embedding_weight_map else -1
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Great! Thanks Xiang for fixing it!

start = time.perf_counter()
state_dict = _quantize_state_dict(
state_dict,
Expand Down