WGNW
/

Llama-2-ko-7b-Chat-auto-gptq-4bit

Text Generation

text-generation-inference

Inference Endpoints

4-bit precision

Model card Files Files and versions Community

WGNW commited on Sep 11, 2023

Commit

f05801e

·

1 Parent(s): 677bfb9

Update config.json

Files changed (1) hide show

config.json +12 -1

config.json CHANGED Viewed

@@ -23,5 +23,16 @@
   "torch_dtype": "float16",
   "transformers_version": "4.33.1",
   "use_cache": true,
-  "vocab_size": 46336
 }

   "torch_dtype": "float16",
   "transformers_version": "4.33.1",
   "use_cache": true,
+  "vocab_size": 46336,
+  "quantization_config": {
+    "bits": 4,
+    "group_size": 128,
+    "damp_percent": 0.01,
+    "desc_act": false,
+    "static_groups": false,
+    "sym": true,
+    "true_sequential": true,
+    "model_name_or_path": null,
+    "model_file_base_name": null
+  }
 }