Xenova HF staff commited on
Commit
3699966
1 Parent(s): bfac5b8

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +32 -0
README.md CHANGED
@@ -4,4 +4,36 @@ library_name: "transformers.js"
4
 
5
  https://huggingface.co/distilbert-base-uncased-finetuned-sst-2-english with ONNX weights to be compatible with Transformers.js.
6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7
  Note: Having a separate repo for ONNX weights is intended to be a temporary solution until WebML gains more traction. If you would like to make your models web-ready, we recommend converting to ONNX using [🤗 Optimum](https://huggingface.co/docs/optimum/index) and structuring your repo like this one (with ONNX weights located in a subfolder named `onnx`).
 
4
 
5
  https://huggingface.co/distilbert-base-uncased-finetuned-sst-2-english with ONNX weights to be compatible with Transformers.js.
6
 
7
+
8
+ ## Usage (Transformers.js)
9
+
10
+ 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:
11
+ ```bash
12
+ npm i @xenova/transformers
13
+ ```
14
+
15
+ You can then use the model to classify text like this:
16
+
17
+ ```js
18
+ import { pipeline } from "@xenova/transformers";
19
+
20
+ // Create a sentiment analysis pipeline
21
+ const classifier = await pipeline('sentiment-analysis', 'Xenova/distilbert-base-uncased-finetuned-sst-2-english');
22
+
23
+ // Classify input text
24
+ const output = await classifier('I love transformers!');
25
+ console.log(output);
26
+ // [{ label: 'POSITIVE', score: 0.999788761138916 }]
27
+
28
+ // Classify input text (and return all classes)
29
+ const output2 = await classifier('I love transformers!', { topk: null });
30
+ console.log(output2);
31
+ // [
32
+ // { label: 'POSITIVE', score: 0.999788761138916 },
33
+ // { label: 'NEGATIVE', score: 0.00021126774663571268 }
34
+ // ]
35
+ ```
36
+
37
+ ---
38
+
39
  Note: Having a separate repo for ONNX weights is intended to be a temporary solution until WebML gains more traction. If you would like to make your models web-ready, we recommend converting to ONNX using [🤗 Optimum](https://huggingface.co/docs/optimum/index) and structuring your repo like this one (with ONNX weights located in a subfolder named `onnx`).