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

gptq_model-4bit-128g.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e1e45c277508446d0342f0a2acec488e927532facd118559b77adeeece85efc
+oid sha256:d27dc000b2640364fda1211ccaab74e3c61f6f742b576671b1a0bdc9280d18ed
 size 7259435192

quantize_config.json

@@ -6,6 +6,6 @@
   "static_groups": false,
   "sym": true,
   "true_sequential": true,
-  "model_name_or_path": "Llama-2-13b-chat-q4bit",
-  "model_file_base_name": "gptq_model-4bit-128g"
+  "model_name_or_path": null,
+  "model_file_base_name": null
 }