build: AutoGPTQ for meta-llama/Llama-2-13b-chat-hf: 4bits, gr128, desc_act=False

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "llama-2-13b-chat-hf-gptq",
+  "_name_or_path": "meta-llama/Llama-2-13b-chat-hf",
   "architectures": [
     "LlamaForCausalLM"
   ],

gptq_model-4bit-128g.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b0348502ed12fbb94f68b654aa73b4621c349eed96d7b97cd58942208f8d7f7
-size 7259404840
+oid sha256:475ae41986b3baaad008f8da3731d83f1ff13eecdcd95119c1ca13725f52dcc3
+size 7259449424

quantize_config.json

@@ -5,6 +5,6 @@
   "desc_act": false,
   "sym": true,
   "true_sequential": true,
-  "model_name_or_path": "llama-2-13b-chat-hf-gptq",
-  "model_file_base_name": "gptq_model-4bit-128g"
+  "model_name_or_path": null,
+  "model_file_base_name": null
 }