Upload 6 files

config.json

@@ -22,7 +22,7 @@
   "rotary_pct": 0.25,
   "tie_word_embeddings": false,
   "torch_dtype": "float16",
-  "transformers_version": "4.31.0",
+  "transformers_version": "4.33.0.dev0",
   "use_cache": true,
   "use_parallel_residual": true,
   "vocab_size": 50277

gptq_model-4bit-128g.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30beb64c82f07a3b8b2f9722e80688678e207a6e76dc380be93f74c88fc7ca1b
+oid sha256:6b2edc1ce5b2c411b090bd8808d35c91f7a23ebe2c145c2a1d255311d89f4baf
 size 6297627136

quantize_config.json

@@ -2,9 +2,9 @@
   "bits": 4,
   "group_size": 128,
   "damp_percent": 0.01,
-  "desc_act": false,
+  "desc_act": true,
   "sym": true,
   "true_sequential": true,
-  "model_name_or_path": null,
-  "model_file_base_name": null
+  "model_name_or_path": "opt-125m-4bit-128g",
+  "model_file_base_name": "gptq_model-4bit-128g"
 }

tokenizer_config.json

@@ -1,5 +1,5 @@
 {
   "clean_up_tokenization_spaces": true,
-  "model_max_length": 1024,
+  "model_max_length": 1000000000000000019884624838656,
   "tokenizer_class": "PreTrainedTokenizerFast"
 }