README.md

---
base_model: LGAI-EXAONE/EXAONE-Deep-2.4B
base_model_relation: finetune
license: other
license_name: exaone
license_link: LICENSE
language:
- en
- ko
tags:
- lg-ai
- exaone
- exaone-deep
- mlx
pipeline_tag: text-generation
library_name: transformers
---

# alexgusevski/EXAONE-Deep-2.4B-fp16-mlx

The Model [alexgusevski/EXAONE-Deep-2.4B-fp16-mlx](https://huggingface.co/alexgusevski/EXAONE-Deep-2.4B-fp16-mlx) was
converted to MLX format from [LGAI-EXAONE/EXAONE-Deep-2.4B](https://huggingface.co/LGAI-EXAONE/EXAONE-Deep-2.4B)
using mlx-lm version **0.22.0**.

**P.S. Don't forget to change the prompt template according to this https://github.com/LG-AI-EXAONE/EXAONE-Deep#lm-studio**

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("alexgusevski/EXAONE-Deep-2.4B-fp16-mlx")

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)
```