README.md

---
library_name: transformers
license: apache-2.0
base_model: open-thoughts/OpenThinker2-32B
tags:
- llama-factory
- full
- generated_from_trainer
- mlx
- mlx-my-repo
datasets:
- open-thoughts/OpenThoughts2-1M
model-index:
- name: OpenThinker2-32B
  results: []
---

# alexgusevski/OpenThinker2-32B-mlx-fp16

The Model [alexgusevski/OpenThinker2-32B-mlx-fp16](https://huggingface.co/alexgusevski/OpenThinker2-32B-mlx-fp16) was converted to MLX format from [open-thoughts/OpenThinker2-32B](https://huggingface.co/open-thoughts/OpenThinker2-32B) using mlx-lm version **0.22.1**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("alexgusevski/OpenThinker2-32B-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)
```