README.md

---
license: mit
language:
- en
- ko
tags:
- KT
- K-intelligence
- Mi:dm
- mlx
inference: true
pipeline_tag: text-generation
library_name: mlx
base_model: K-intelligence/Midm-2.0-Base-Instruct
---

# litmudoc/Midm-2.0-Base-Instruct-MLX-Q8

This model [litmudoc/Midm-2.0-Base-Instruct-MLX-Q8](https://huggingface.co/litmudoc/Midm-2.0-Base-Instruct-MLX-Q8) was
converted to MLX format from [K-intelligence/Midm-2.0-Base-Instruct](https://huggingface.co/K-intelligence/Midm-2.0-Base-Instruct)
using mlx-lm version **0.25.3**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("litmudoc/Midm-2.0-Base-Instruct-MLX-Q8")

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)
```