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

- Upload fixed & optimized fp16/q4f16 ONNX weights (83472e1d1464b7a54aacf134dac895154e1f6463)


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:ddaf25d62ca2d9c7cc06ce1f6c6f1bfdc0857333418dc0b2c04057a754bbf876
-size 1727650806
+oid sha256:ce7defed5b1cc6b4bf104bc79b2eb472fafc1d0d68c3b1089fda35fe6402fc04
+size 915094963

onnx/decoder_model_merged_q4f16.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28125eb088192c7d29d328c99902899134d2c6498b7568d504c14883716913ff
-size 642447337
+oid sha256:b208afca1b23cc9aade0acc01731b96358ce9b2f20985060a5d8ffdb7cda3ebd
+size 336281436