OPEA
/

Qwen2.5-1.5B-Instruct-int4-sym-inc

4-bit precision

Model card Files Files and versions

cicdatopea commited on Sep 23

Commit

7ed1d10

·

verified ·

1 Parent(s): 8f7abbc

Update config.json

Files changed (1) hide show

config.json +1 -1

config.json CHANGED Viewed

@@ -19,7 +19,7 @@
   "quantization_config": {
     "amp": true,
     "autoround_version": "0.4.0.dev",
-    "packing_format": "auto_round:auto_gptq:exllamav2",
     "batch_size": 8,
     "bits": 4,
     "data_type": "int",

   "quantization_config": {
     "amp": true,
     "autoround_version": "0.4.0.dev",
+    "packing_format": "auto_round:auto_gptq",
     "batch_size": 8,
     "bits": 4,
     "data_type": "int",