AutoGPTQ model for bigscience/bloom-560m: 4bits, gr128, desc_act=False

config.json

@@ -25,7 +25,7 @@
   "skip_bias_add_qkv": false,
   "slow_but_exact": false,
   "torch_dtype": "float16",
-  "transformers_version": "4.35.2",
+  "transformers_version": "4.44.2",
   "unk_token_id": 0,
   "use_cache": true,
   "vocab_size": 250880

gptq_model-4bit-128g.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:800923678f2b9531beb85aa6fb2dbba30240b9becd30395e37fe3ec25f21a8b3
+size 1185900200

quantize_config.json

@@ -6,6 +6,6 @@
   "static_groups": false,
   "sym": true,
   "true_sequential": true,
-  "model_name_or_path": "bloom-560m-gptq-4bit",
-  "model_file_base_name": "gptq_model-4bit-128g"
+  "model_name_or_path": null,
+  "model_file_base_name": null
 }