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 sha256:4e9e6e4affb9311fcd06025f9928e8a74f72d878ec1466b3837f68c6173089c6
+size 39160702

onnx/decoder_model_merged_fp16.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0bdab5c318b78fc6e340f11ec6b47850748d80f510c342ce14dc1867501a12ef
-size 122705474
+oid sha256:6366361cf39da790286a7fe96ab2af7bcbe9b6dc39aaa6b53c9f8e90e5f13fa0
+size 119485418

onnx/decoder_model_merged_int8.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e21871668eb31312532444f3f07a950ddb47c53b0b480d1614a36cdd93c450a
+size 64675320

onnx/decoder_model_merged_q4.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b04e270a668741cbdd5cd58eb6710945b8450bce30802b5e23031cb13c0001c8
+size 42788125

onnx/decoder_model_merged_q4f16.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a8418e21c7d74348c1eed9bbc744fe14937238ccf33eac5dfaeae9d5fe9090e
+size 36111051

onnx/decoder_model_merged_uint8.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7038765cd1f9b29c8ac8fa0306b27f3f604e784bbf8c91efec10aa7c47388234
+size 64675353