Transformers.js v2 -> v3

README.md

@@ -7,15 +7,15 @@ https://huggingface.co/thenlper/gte-small with ONNX weights to be compatible wit
 
 ## 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
 ```
 
 You can then use the model to compute embeddings like this:
 
 ```js
-import { pipeline } from '@xenova/transformers';
+import { pipeline } from '@huggingface/transformers';
 
 // Create a feature-extraction pipeline
 const extractor = await pipeline('feature-extraction', 'Xenova/gte-small');
@@ -32,7 +32,7 @@ console.log(output);
 // }
 
 // Compute cosine similarity
-import { cos_sim } from '@xenova/transformers';
+import { cos_sim } from '@huggingface/transformers';
 console.log(cos_sim(output[0].data, output[1].data))
 // 0.9798319649182318
 ```
@@ -46,9 +46,9 @@ console.log(output.tolist());
 // ]
 ```
 
-By default, an 8-bit quantized version of the model is used, but you can choose to use the full-precision (fp32) version by specifying `{ quantized: false }` in the `pipeline` function:
+By default, an 8-bit quantized version of the model is used, but you can choose to use the full-precision (fp32) version by specifying `{ dtype: 'fp32' }` in the `pipeline` function:
 ```js
-const extractor = await pipeline('feature-extraction', 'Xenova/gte-small', { quantized: false });
+const extractor = await pipeline('feature-extraction', 'Xenova/gte-small', { dtype: 'fp32' });
 ```
 
 ---