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:c4ea70729c71902fee5a8cd693ce769648805673fe98ae5afa4c6930c071aafe
-size 555163373
+oid sha256:59bff9c12eba82bcc6c6893eacd61118e7d69ec9a1e9595eb66a19db72665dde
+size 546702610

onnx/decoder_model_merged_fp16.onnx_data

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a1bfb3d72c0476db9d4d20510ccef2b50a09ad2a9738254ba2e8f5105a07b18
-size 2071986176
+oid sha256:707a678ab9e378fb739d8574b2668b73e8b7354fb2bc275a34e97b81215c098c
+size 2080374784

onnx/decoder_model_merged_q4.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7bc872a71d27ea5846619c1c22d195c30335380e23cb868ef5ec19ea9276849d
-size 823291250
+oid sha256:00e5f3de4b5329d46d90190909a5b53eac6883a616c5f973f433d60756272f3c
+size 739917026

onnx/decoder_model_merged_q4f16.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:267c5a8447be319209cdbb49bf2b61e4a1c2c25ba2dfb6d29aa66022ae88068b
-size 739988237
+oid sha256:35462bc13ce0af9df13a0233fb3e214cf6587ea6a1c51ab0c8fd616619f7ee1e
+size 739917090