---
license: mit
library_name: transformers
tags:
- transformers.js
- tokenizers
datasets:
- LPM/Emotionen
language:
- de
metrics:
- accuracy
base_model:
- mistral-community/pixtral-12b-240910
pipeline_tag: text-classification
---

# GPT-4o Tokenizer

A 🤗-compatible version of the **GPT-4o tokenizer** (adapted from [openai/tiktoken](https://github.com/openai/tiktoken)). 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 GPT2TokenizerFast

tokenizer = GPT2TokenizerFast.from_pretrained('Xenova/gpt-4o')
assert tokenizer.encode('hello world') == [24912, 2375]
```

### Transformers.js
```js
import { AutoTokenizer } from '@xenova/transformers';

const tokenizer = await AutoTokenizer.from_pretrained('Xenova/gpt-4o');
const tokens = tokenizer.encode('hello world'); // [24912, 2375]
```