Upload of AutoGPTQ quantized model

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "meta-llama/Llama-2-7b-chat-hf",
+  "_name_or_path": "limerooster/Llama-2-7b-chat-hf-4bit-32g-hf",
   "architectures": [
     "LlamaForCausalLM"
   ],

gptq_model-4bit-32g.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90f95666e7e60ef5eed49444e82d8f1800d38b3f8a02ba9f18ac44076ced34cf
-size 4276448187
+oid sha256:e4b3880e940ec50647e8b9dc3df5ddbd2171228ac363b2cba7270507217efbb5
+size 7512816872

quantize_config.json

@@ -6,6 +6,6 @@
   "static_groups": false,
   "sym": true,
   "true_sequential": true,
-  "model_name_or_path": null,
-  "model_file_base_name": null
+  "model_name_or_path": "limerooster/Llama-2-7b-chat-hf-4bit-32g-hf",
+  "model_file_base_name": "gptq_model-4bit-32g"
 }