Skip to content

Commit

Permalink
fix 3x gptq acc issue (#1654)
Browse files Browse the repository at this point in the history
Signed-off-by: Tang, Kaihui <[email protected]>
  • Loading branch information
Kaihui-intel authored Mar 8, 2024
1 parent 9a7ddda commit c701eaf
Showing 1 changed file with 1 addition and 1 deletion.
Original file line number Diff line number Diff line change
Expand Up @@ -328,7 +328,7 @@ def run_fn_for_gptq(model, dataloader_for_calibration, *args):
)
quant_config.set_local("lm_head", GPTQConfig(dtype="fp32"))
user_model = quantize(
model=user_model, quant_config=quant_config, run_fn=run_fn_for_gptq, run_args=dataloader_for_calibration
model=user_model, quant_config=quant_config, run_fn=run_fn_for_gptq, run_args=(dataloader_for_calibration, )
)
else:
# TODO: smooth quant
Expand Down

0 comments on commit c701eaf

Please sign in to comment.