onnx-community
/

Llama-3.2-1B-Instruct-q4f16

Text Generation

Transformers.js

Model card Files Files and versions Community

Xenova HF staff commited on Sep 27

Commit

7ed3d8d

•

1 Parent(s): 70b1b63

Update config.json

Files changed (1) hide show

config.json +1 -1

config.json CHANGED Viewed

@@ -35,7 +35,7 @@
   "torch_dtype": "bfloat16",
   "transformers_version": "4.45.0.dev0",
   "transformers.js_config": {
-    "dtype": "q4",
     "kv_cache_dtype": "float16"
   },
   "use_cache": true,

   "torch_dtype": "bfloat16",
   "transformers_version": "4.45.0.dev0",
   "transformers.js_config": {
+    "dtype": "q4f16",
     "kv_cache_dtype": "float16"
   },
   "use_cache": true,