adicionando quantização fp16 do modelo
#2
by eduardoworrel - opened
- onnx/model_fp16.onnx +3 -0
onnx/model_fp16.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f74914dce09c973e03e289ceeaa9ed3dc035e32b0b8d9683079867aa1bd845d5
|
| 3 |
+
size 217169108
|