Upload fixed & optimized fp16/q4f16 ONNX weights (#1)

- Upload fixed & optimized fp16/q4f16 ONNX weights (424a798f855410695ece7652ce686600d4149724)


Co-authored-by: Joshua <[email protected]>

onnx/decoder_model_merged_fp16.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4657629a4e2279995a42e855b9c530235cce0f2569b82a4847b759a8e3d2b833
-size 586895494
+oid sha256:a46ed110545acf0c76b81162abf04ccb59994a1a999a792fb3e4a1560b8ee06e
+size 308072830

onnx/decoder_model_merged_q4f16.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1444f79dceae11fc39d80255f7dc66c05a9ce4db331bd6e8abe78e44cb3cf1a7
-size 281698141
+oid sha256:a863f00364adb1ac6c77f5751c6a47fcdd16944bf6743813693b13aead43b70e
+size 145279679