Upload quantize_config.json

quantize_config.json

@@ -1,13 +1,13 @@
 {
-  "bits": 4,
+  "bits": 8,
   "group_size": 128,
   "damp_percent": 0.01,
   "desc_act": false,
   "static_groups": false,
   "sym": true,
   "true_sequential": true,
-  "model_name_or_path": "Qwen-7B-125m-4bit-128g",
-  "model_file_base_name": "gptq_model-4bit-128g",
+  "model_name_or_path": "Qwen-7B-8bit",
+  "model_file_base_name": "gptq_model-8bit-128g",
   "is_marlin_format": false,
   "quant_method": "gptq"
 }