TheBloke
/

Llama-2-13B-chat-AWQ

Text Generation

text-generation-inference

4-bit precision

Model card Files Files and versions

ybelkada commited on Oct 30, 2023

Commit

a436462

·

1 Parent(s): 74a5357

Update config.json

Files changed (1) hide show

config.json +2 -2

config.json CHANGED Viewed

@@ -26,8 +26,8 @@
     "quantization_config": {
         "quant_method": "awq",
         "zero_point": true,
-        "q_group_size": 128,
-        "w_bit": 4,
         "version": "GEMM",
         "backend": "autoawq"
     }

     "quantization_config": {
         "quant_method": "awq",
         "zero_point": true,
+        "group_size": 128,
+        "bits": 4,
         "version": "GEMM",
         "backend": "autoawq"
     }