README.md

---
license: other
license_name: hyperclovax-seed
license_link: LICENSE
tags:
- mlx
base_model: naver-hyperclovax/HyperCLOVAX-SEED-Text-Instruct-0.5B
---

# senaw/HyperCLOVAX-SEED-Text-Instruct-0.5B-MLX-Q4

The Model [senaw/HyperCLOVAX-SEED-Text-Instruct-0.5B-MLX-Q4](https://huggingface.co/senaw/HyperCLOVAX-SEED-Text-Instruct-0.5B-MLX-Q4) was
converted to MLX format from [naver-hyperclovax/HyperCLOVAX-SEED-Text-Instruct-0.5B](https://huggingface.co/naver-hyperclovax/HyperCLOVAX-SEED-Text-Instruct-0.5B)
using mlx-lm version **0.21.4**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("senaw/HyperCLOVAX-SEED-Text-Instruct-0.5B-MLX-Q4")

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)
```