Add/update the quantized ONNX model files and README.md for Transformers.js v3 (#1)

- Add/update the quantized ONNX model files and README.md for Transformers.js v3 (ea85188173c238928830c9049c03551e1fe30329)


Co-authored-by: Yuichiro Tachibana <whitphx@users.noreply.huggingface.co>

README.md

@@ -7,14 +7,14 @@ https://huggingface.co/cross-encoder/ms-marco-MiniLM-L-2-v2 with ONNX weights to
 
 ## Usage (Transformers.js)
 
-If you haven't already, you can install the [Transformers.js](https://huggingface.co/docs/transformers.js) JavaScript library from [NPM](https://www.npmjs.com/package/@xenova/transformers) using:
+If you haven't already, you can install the [Transformers.js](https://huggingface.co/docs/transformers.js) JavaScript library from [NPM](https://www.npmjs.com/package/@huggingface/transformers) using:
 ```bash
-npm i @xenova/transformers
+npm i @huggingface/transformers
 ```
 
 **Example:** Information Retrieval w/ `Xenova/ms-marco-MiniLM-L-2-v2`.
 ```js
-import { AutoTokenizer, AutoModelForSequenceClassification } from '@xenova/transformers';
+import { AutoTokenizer, AutoModelForSequenceClassification } from '@huggingface/transformers';
 
 const model = await AutoModelForSequenceClassification.from_pretrained('Xenova/ms-marco-MiniLM-L-2-v2');
 const tokenizer = await AutoTokenizer.from_pretrained('Xenova/ms-marco-MiniLM-L-2-v2');
@@ -31,7 +31,7 @@ const features = tokenizer(
     }
 )
 
-const scores = await model(features)
+const scores = await model(features);
 console.log(scores);
 // quantized:   [ 9.063430786132812, -11.72588062286377 ]
 // unquantized: [ 8.843852043151855, -11.74354362487793 ]

onnx/model_bnb4.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21dffc322519eb3d410ff8e452780722ac09247f882386d1ccc5b632bc9aaa54
+size 50359445

onnx/model_int8.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1857c1a59b01c1641a46a47fd85b01d98c6e15e1e48588eac1f6a97ff83479c7
+size 15727674

onnx/model_q4.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:502ef6a208c5d3fb2201766ace086ed958686a7c543caf56b942eb0e2829d8b0
+size 50580553

onnx/model_q4f16.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f3f71f29e377347bce07bf60adc2751e956729d6f1d2808eab5c85e491c269a
+size 26205942

onnx/model_uint8.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ee7f8e2a4c6a69e8fcbd0ee513ccb7843b55d2bd501f229aa9b3a5f5869c63f
+size 15727686