Upload folder using huggingface_hub

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "/mnt/models/Mistral-7B-Instruct-v0.2-Neural-Story",
+  "_name_or_path": "/models/models/Mistral-7B-Instruct-v0.2-Neural-Story",
   "architectures": [
     "MistralForCausalLM"
   ],
@@ -15,19 +15,6 @@
   "num_attention_heads": 32,
   "num_hidden_layers": 32,
   "num_key_value_heads": 8,
-  "quantization_config": {
-    "bits": 4,
-    "damp_percent": 0.01,
-    "desc_act": true,
-    "group_size": 32,
-    "is_marlin_format": false,
-    "model_file_base_name": null,
-    "model_name_or_path": null,
-    "quant_method": "gptq",
-    "static_groups": false,
-    "sym": true,
-    "true_sequential": true
-  },
   "rms_norm_eps": 1e-05,
   "rope_theta": 1000000.0,
   "sliding_window": 4096,

gptq_model-4bit-32g.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0e9d192fd76e3c7a8652a1ee862cf5ee3ffd85ea7e0bcd1502cbc17fb1f68d4
-size 4567607288
+oid sha256:dd416564abf65fdefc716d5029a54d6b2121f0eda0d7b2c9b570ef20a178b975
+size 4567607264

quantize_config.json

@@ -7,7 +7,5 @@
   "sym": true,
   "true_sequential": true,
   "model_name_or_path": null,
-  "model_file_base_name": null,
-  "is_marlin_format": false,
-  "quant_method": "gptq"
+  "model_file_base_name": null
 }