Upload folder using huggingface_hub

config.json

@@ -24,10 +24,10 @@
   "pretraining_tp": 1,
   "quantization_config": {
     "bits": 4,
-    "checkpoint_format": "gptq",
-    "damp_percent": 0.01,
+    "damp_percent": 0.1,
     "desc_act": true,
     "group_size": 128,
+    "is_marlin_format": false,
     "model_file_base_name": "model",
     "model_name_or_path": null,
     "quant_method": "gptq",
@@ -46,7 +46,7 @@
   "rope_theta": 500000.0,
   "tie_word_embeddings": false,
   "torch_dtype": "float16",
-  "transformers_version": "4.43.2",
+  "transformers_version": "4.44.0",
   "use_cache": true,
   "vocab_size": 128256
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf009a22aa36f14072da925d73bb584cc83138f95007b123358f6b41d86d80ed
-size 5732943784
+oid sha256:5b65a3d34b7b4d350f0cbee60f4e690d1eee1411e7f484db0a8cfae081458602
+size 5735720552

quantize_config.json

@@ -1,13 +1,13 @@
 {
   "bits": 4,
   "group_size": 128,
-  "damp_percent": 0.01,
+  "damp_percent": 0.1,
   "desc_act": true,
   "static_groups": false,
   "sym": true,
   "true_sequential": true,
   "model_name_or_path": null,
   "model_file_base_name": "model",
-  "quant_method": "gptq",
-  "checkpoint_format": "gptq"
+  "is_marlin_format": false,
+  "quant_method": "gptq"
 }