Intel
/

Qwen2-57B-A14B-Instruct-int4-inc

4-bit precision

intel/auto-round

Model card Files Files and versions Community

weiweiz1 commited on Aug 14

Commit

679bddf

•

1 Parent(s): 4fc4a80

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -115,7 +115,7 @@ python3 main.py \
 --bits 4 \
 --iter 1000 \
 --disable_eval \
---fp_layers_list "shared_expert_gate,gate" \
 --deployment_device 'auto_round' \
 --output_dir "./tmp_autoround"
 ```

 --bits 4 \
 --iter 1000 \
 --disable_eval \
+--fp_layers "shared_expert_gate,gate" \
 --deployment_device 'auto_round' \
 --output_dir "./tmp_autoround"
 ```