Update README.md
Browse files
README.md
CHANGED
@@ -4,4 +4,35 @@ library_name: "transformers.js"
|
|
4 |
|
5 |
https://huggingface.co/gpt2 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/gpt2 with ONNX weights to be compatible with Transformers.js.
|
6 |
|
7 |
+
## Usage (Transformers.js)
|
8 |
+
|
9 |
+
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:
|
10 |
+
```bash
|
11 |
+
npm i @xenova/transformers
|
12 |
+
```
|
13 |
+
|
14 |
+
You can then use the model to generate text as follows:
|
15 |
+
|
16 |
+
```js
|
17 |
+
import { pipeline } from '@xenova/transformers';
|
18 |
+
|
19 |
+
// Create a text-generation pipeline
|
20 |
+
const generator = await pipeline('text-generation', 'Xenova/gpt2');
|
21 |
+
|
22 |
+
// Generate text (default parameters)
|
23 |
+
const text = 'Once upon a time,';
|
24 |
+
const output = await generator(text);
|
25 |
+
console.log(output);
|
26 |
+
// [{ generated_text: 'Once upon a time, I was in a room with a woman who was very attractive. She was' }]
|
27 |
+
|
28 |
+
// Generate text (custom parameters)
|
29 |
+
const output2 = await generator(text, {
|
30 |
+
max_new_tokens: 20,
|
31 |
+
do_sample: true,
|
32 |
+
top_k: 5,
|
33 |
+
});
|
34 |
+
console.log(output2);
|
35 |
+
// [{ generated_text: 'generated_text: 'Once upon a time, the first thing I did was put a small piece of paper on a table. I put the paper' }]
|
36 |
+
```
|
37 |
+
|
38 |
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`).
|