TheBloke
/

Llama-2-13B-chat-AWQ

Text Generation

text-generation-inference

4-bit precision

Model card Files Files and versions Community

ybelkada commited on Oct 27, 2023

Commit

ea9528d

•

1 Parent(s): f15f8b3

Update config.json

Files changed (1) hide show

config.json +8 -1

config.json CHANGED Viewed

@@ -22,5 +22,12 @@
     "transformers_version": "4.31.0.dev0",
     "use_cache": true,
     "vocab_size": 32000,
-    "pad_token_id": 0
 }

     "transformers_version": "4.31.0.dev0",
     "use_cache": true,
     "vocab_size": 32000,
+    "pad_token_id": 0,
+    "quantization_config": {
+        "zero_point": true,
+        "q_group_size": 128,
+        "w_bit": 4,
+        "version": "GEMM",
+        "backend": "autoawq",
+    }
 }