marcsun13
/

opt-125m-awq

Text Generation

text-generation-inference

Inference Endpoints

4-bit precision

Model card Files Files and versions Community

ybelkada commited on Oct 30, 2023

Commit

1acb926

•

1 Parent(s): f7c0b2e

Update config.json

Files changed (1) hide show

config.json +2 -2

config.json CHANGED Viewed

@@ -25,10 +25,10 @@
   "prefix": "</s>",
   "quantization_config": {
     "backend": "autoawq",
-    "q_group_size": 128,
     "quant_method": "awq",
     "version": "GEMM",
-    "w_bit": 4,
     "zero_point": true
   },
   "torch_dtype": "float16",

   "prefix": "</s>",
   "quantization_config": {
     "backend": "autoawq",
+    "group_size": 128,
     "quant_method": "awq",
     "version": "GEMM",
+    "bits": 4,
     "zero_point": true
   },
   "torch_dtype": "float16",