Skip to content

[quantization] [draft] Introduce smse_for_gptq#597

Draft
stamalakhov wants to merge 3 commits into
Samsung:mainfrom
stamalakhov:smse_for_gptq
Draft

[quantization] [draft] Introduce smse_for_gptq#597
stamalakhov wants to merge 3 commits into
Samsung:mainfrom
stamalakhov:smse_for_gptq

Conversation

@stamalakhov
Copy link
Copy Markdown
Contributor

@stamalakhov stamalakhov commented Mar 31, 2026

This PR introduces smse_for_gptq to improve accuracy.

Config ID train_PPL test_PPL
FP32 11.09 11.05

where
train_ppl - perplexity evaluated on calibration dataset,
test_ppl is perplexity evaluated on test dataset.

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

@stamalakhov stamalakhov self-assigned this Mar 31, 2026
@stamalakhov stamalakhov force-pushed the smse_for_gptq branch 3 times, most recently from c0e6f86 to 46dff36 Compare May 14, 2026 06:02
This PR introduces smse_for_gptq to improve accuracy.

TICO-DCO-1.0-Signed-off-by: s.malakhov <s.malakhov@partner.samsung.com>
TICO-DCO-1.0-Signed-off-by: s.malakhov <s.malakhov@partner.samsung.com>
@stamalakhov stamalakhov force-pushed the smse_for_gptq branch 2 times, most recently from c7ad123 to 566d34b Compare May 14, 2026 10:27
TICO-DCO-1.0-Signed-off-by: s.malakhov <s.malakhov@partner.samsung.com>
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.

1 participant