|
--- |
|
base_model: Salesforce/codegen-350M-mono |
|
library_name: transformers.js |
|
--- |
|
|
|
https://huggingface.co/Salesforce/codegen-350M-mono with ONNX weights to be compatible with Transformers.js. |
|
|
|
|
|
## 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/@huggingface/transformers) using: |
|
```bash |
|
npm i @huggingface/transformers |
|
``` |
|
|
|
**Example:** Code completion w/ `Xenova/codegen-350M-mono`. |
|
```js |
|
import { pipeline } from "@huggingface/transformers"; |
|
|
|
// Create a text generation pipeline |
|
const generator = await pipeline("text-generation", "Xenova/codegen-350M-mono"); |
|
|
|
// Define the prompt |
|
const text = `def fib(n): |
|
"""Calculates the nth Fibonacci number"""`; |
|
|
|
// Generate a response |
|
const output = await generator(text, { max_new_tokens: 45 }); |
|
console.log(output[0].generated_text); |
|
``` |
|
|
|
--- |
|
|
|
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`). |
