|
--- |
|
library_name: transformers |
|
tags: |
|
- transformers.js |
|
- tokenizers |
|
--- |
|
|
|
# Nemotron-4-340B-Instruct Tokenizer |
|
|
|
A 🤗-compatible version of the **Nemotron-4-340B-Instruct** (adapted from [nvidia/Nemotron-4-340B-Instruct](https://huggingface.co/nvidia/Nemotron-4-340B-Instruct)). This means it can be used with Hugging Face libraries including [Transformers](https://github.com/huggingface/transformers), [Tokenizers](https://github.com/huggingface/tokenizers), and [Transformers.js](https://github.com/xenova/transformers.js). |
|
|
|
## Example usage: |
|
|
|
### Transformers/Tokenizers |
|
```py |
|
from transformers import PreTrainedTokenizerFast |
|
|
|
tokenizer = PreTrainedTokenizerFast.from_pretrained('Xenova/Nemotron-4-340B-Instruct-Tokenizer') |
|
assert tokenizer.encode('hello world') == [38150, 2268] |
|
``` |
|
|
|
### Transformers.js |
|
```js |
|
import { AutoTokenizer } from '@xenova/transformers'; |
|
|
|
const tokenizer = await AutoTokenizer.from_pretrained('Xenova/Nemotron-4-340B-Instruct-Tokenizer'); |
|
const tokens = tokenizer.encode('hello world'); // [38150, 2268] |
|
``` |
|
|
