c9a970ecd96f51d3754a88f9381e9136c1cae523ef8a6a77c15122accbc8f06c

config.json

@@ -21,16 +21,17 @@
   "num_attention_heads": 32,
   "num_hidden_layers": 32,
   "num_key_value_heads": 8,
+  "pad_token_id": 128004,
   "pretraining_tp": 1,
   "quantization_config": {
     "bits": 4,
     "checkpoint_format": "gptq",
     "damp_percent": 0.005,
-    "desc_act": true,
+    "desc_act": false,
     "group_size": 128,
     "lm_head": false,
     "meta": {
-      "quantizer": "gptqmodel:0.9.9-dev0"
+      "quantizer": "gptqmodel:0.9.10-dev0"
     },
     "model_file_base_name": null,
     "model_name_or_path": null,
@@ -53,4 +54,4 @@
   "transformers_version": "4.44.0.dev0",
   "use_cache": true,
   "vocab_size": 128256
-}
+}

quantize_config.json

@@ -1,7 +1,7 @@
 {
   "bits": 4,
   "group_size": 128,
-  "desc_act": true,
+  "desc_act": false,
   "static_groups": false,
   "sym": true,
   "lm_head": false,
@@ -12,6 +12,6 @@
   "quant_method": "gptq",
   "checkpoint_format": "gptq",
   "meta": {
-    "quantizer": "gptqmodel:0.9.9-dev0"
+    "quantizer": "gptqmodel:0.9.10-dev0"
   }
 }