Upload optimized ONNX files w/ GQA

onnx/decoder_model_merged_fp16.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:59bff9c12eba82bcc6c6893eacd61118e7d69ec9a1e9595eb66a19db72665dde
-size 546702610
+oid sha256:91fe49a027c173c2ee620da92291c47cc559a283d642a792b75c1d055d2b042a
+size 546702655

onnx/decoder_model_merged_q4f16.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35462bc13ce0af9df13a0233fb3e214cf6587ea6a1c51ab0c8fd616619f7ee1e
-size 739917090
+oid sha256:76bbee9e65863a1b393a1c406f132164d98aa58fcdc9c983f85b069c13c295f5
+size 739917135