README.md

---
library_name: transformers
license: cc-by-4.0
language:
- en
- fr
- de
- it
- pt
- es
pipeline_tag: text-generation
base_model: kyutai/helium-1-preview-2b
tags:
- mlx
---

# mlx-community/helium-1-preview-2b-float32

The Model [mlx-community/helium-1-preview-2b-float32](https://huggingface.co/mlx-community/helium-1-preview-2b-float32) was
converted to MLX format from [kyutai/helium-1-preview-2b](https://huggingface.co/kyutai/helium-1-preview-2b)
using mlx-lm version **0.21.0**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/helium-1-preview-2b-float32")

prompt = "hello"

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

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