Skip to content

[quantization] Change default bits for lm_head#721

Merged
mhs4670go merged 1 commit into
Samsung:mainfrom
stamalakhov:change_def_weight
May 21, 2026
Merged

[quantization] Change default bits for lm_head#721
mhs4670go merged 1 commit into
Samsung:mainfrom
stamalakhov:change_def_weight

Conversation

@stamalakhov
Copy link
Copy Markdown
Contributor

This PR changes lm_head_weight_bits to be equal to embedding_weight_bits and adjusts help string accordingly.

TICO-DCO-1.0-Signed-off-by: s.malakhov s.malakhov@partner.samsung.com

This PR changes `lm_head_weight_bits` to be equal to `embedding_weight_bits` and adjusts help string accordingly.

TICO-DCO-1.0-Signed-off-by: s.malakhov <s.malakhov@partner.samsung.com>
@stamalakhov stamalakhov requested a review from mhs4670go May 21, 2026 06:20
@stamalakhov stamalakhov self-assigned this May 21, 2026
Copy link
Copy Markdown
Contributor

@mhs4670go mhs4670go left a comment

Choose a reason for hiding this comment

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

LGTM

@mhs4670go mhs4670go merged commit fe5b325 into Samsung:main May 21, 2026
7 checks passed
@stamalakhov stamalakhov deleted the change_def_weight branch May 21, 2026 07:47
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants