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

- Upload fixed & optimized fp16/q4f16 ONNX weights (b6940ab3a7808b050606dc5bc6d2ce214bae6c5f)


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:d7ae5559f23269315ae26f54d0f44bb9a9aa3882f2ba9219bce1d7d8721b87e5
-size 116161346
+oid sha256:292068f7a7e9c7fc8156ef2eff5b6ce307dc41780530c4529106b4c058698fac
+size 59421697

onnx/decoder_model_merged_q4f16.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:743d158dd9489527e02dd8ff540b475970f622f15c30a72b9c6864885ff25241
-size 90737213
+oid sha256:28c3fe1ba79ad15fc2eeb6bdb3e5e1cc65cd8525a8445b84a1552f7aef1dcba5
+size 45854576