AutoGPTQ model for facebook/opt-6.7b: 4bits, gr128, desc_act=False

config.json

@@ -24,7 +24,7 @@
   "pad_token_id": 1,
   "prefix": "</s>",
   "torch_dtype": "float16",
-  "transformers_version": "4.35.2",
+  "transformers_version": "4.44.2",
   "use_cache": true,
   "vocab_size": 50272,
   "word_embed_proj_dim": 4096

gptq_model-4bit-128g.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9e90bc63a45d81363a0a5d4576983475c8f4038464af54aeb91aada1b261cf8
+size 4195775904

quantize_config.json

@@ -6,6 +6,6 @@
   "static_groups": false,
   "sym": true,
   "true_sequential": true,
-  "model_name_or_path": "opt-6.7b-gptq-4bit",
-  "model_file_base_name": "gptq_model-4bit-128g"
+  "model_name_or_path": null,
+  "model_file_base_name": null
 }