hugging-quants
/

Meta-Llama-3.1-405B-Instruct-GPTQ-INT4

Text Generation

text-generation-inference

Inference Endpoints

4-bit precision

Model card Files Files and versions Community

shuyuej commited on Aug 3

Commit

306e168

•

1 Parent(s): 043ae54

Update config.json

Files changed (1) hide show

config.json +1 -1

config.json CHANGED Viewed

@@ -28,7 +28,7 @@
     "desc_act": true,
     "group_size": 128,
     "is_marlin_format": false,
-    "model_file_base_name": "gptq_model-4bit-128g",
     "model_name_or_path": "/fsx/llama405b/4bit-gptq-instruct",
     "quant_method": "gptq",
     "static_groups": false,

     "desc_act": true,
     "group_size": 128,
     "is_marlin_format": false,
+    "model_file_base_name": "model",
     "model_name_or_path": "/fsx/llama405b/4bit-gptq-instruct",
     "quant_method": "gptq",
     "static_groups": false,