Add/update the quantized ONNX model files and README.md for Transformers.js v3

## Applied Quantizations

### ✅ Based on `decoder_model_merged.onnx` *with* slimming

↳ ✅ `fp16`: `decoder_model_merged_fp16.onnx` (replaced because it was invalid)
↳ ✅ `int8`: `decoder_model_merged_int8.onnx` (added)
↳ ✅ `uint8`: `decoder_model_merged_uint8.onnx` (added)
↳ ✅ `q4`: `decoder_model_merged_q4.onnx` (added)
↳ ✅ `q4f16`: `decoder_model_merged_q4f16.onnx` (added)
↳ ✅ `bnb4`: `decoder_model_merged_bnb4.onnx` (added)

onnx/decoder_model_merged_bnb4.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f2befccb4f7e0d410cf9efee1a4cfa09a2bf0eebc2eed53e0cff997cf2ba6c1
+size 80327861

onnx/decoder_model_merged_fp16.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:531fff55e795e57f7d696d8882b2f74c3180c2f2b30eed0300018147d8be660c
-size 83700305
+oid sha256:4783d27bcd81e513c1851b4215d094a1e81676ef458a51078f0d28961c91adba
+size 83579006

onnx/decoder_model_merged_int8.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4e5a592a9ebedf9523ccbe89f5eb18e8309c3bd808fd92e02d4f7df5cd56ebe
+size 107906032

onnx/decoder_model_merged_q4.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e2467480571c53168d7ec4d1fd3851dbd8d308289ad31a34390a68b643a195e
+size 81899816

onnx/decoder_model_merged_q4f16.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4bec6aee1ecb9c424764f1d812dd9b8ee68f8ca7258e91abbac60caeac05c0cd
+size 47418678

onnx/decoder_model_merged_uint8.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c0ce152658a0778457930cde58117caca81810ce5fc8c8b902e46f417d0d72f
+size 107906071