---
language: en
license: mit
tags:
- mlx
base_model: openai-community/gpt2-xl
---

# MCES10/gpt2-xl-mlx-fp16

The Model [MCES10/gpt2-xl-mlx-fp16](https://huggingface.co/MCES10/gpt2-xl-mlx-fp16) was converted to MLX format from [openai-community/gpt2-xl](https://huggingface.co/openai-community/gpt2-xl) using mlx-lm version **0.22.3**.

## Use with mlx

```bash
pip install mlx-lm
```

```python
from mlx_lm import load, generate

model, tokenizer = load("MCES10/gpt2-xl-mlx-fp16")

prompt="hello"

if hasattr(tokenizer, "apply_chat_template") and tokenizer.chat_template is not None:
    messages = [{"role": "user", "content": prompt}]
    prompt = tokenizer.apply_chat_template(
        messages, tokenize=False, add_generation_prompt=True
    )

response = generate(model, tokenizer, prompt=prompt, verbose=True)
```