AutoGPTQ model for facebook/opt-13b: 4bits, gr128, desc_act=False

config.json

@@ -25,7 +25,7 @@
   "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": 5120

gptq_model-4bit-128g.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e107c2c39053bea33e7cf65bc912020728984d2f9134457b8d0ee9e7ea84c60a
+size 7600657320

quantize_config.json

@@ -6,6 +6,6 @@
   "static_groups": false,
   "sym": true,
   "true_sequential": true,
-  "model_name_or_path": "opt-13b-gptq-4bit",
-  "model_file_base_name": "gptq_model-4bit-128g"
+  "model_name_or_path": null,
+  "model_file_base_name": null
 }