ModelCloud
/

GRIN-MoE-gptq-4bit

4-bit precision

Model card Files Files and versions Community

lrl-modelcloud commited on Sep 19

Commit

7e2210a

•

1 Parent(s): 90537f1

Update README.md

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -10,9 +10,9 @@ This model has been quantized using [GPTQModel](https://github.com/ModelCloud/GP
 - **bits**: 4
 - **group_size**: 128
-- **desc_act**: true
 - **static_groups**: false
-- **sym**: false
 - **lm_head**: false
 - **damp_percent**: 0.0025
 - **damp_auto_increment**: 0.0015

 - **bits**: 4
 - **group_size**: 128
+- **desc_act**: false
 - **static_groups**: false
+- **sym**: true
 - **lm_head**: false
 - **damp_percent**: 0.0025
 - **damp_auto_increment**: 0.0015