README.md

---
license: other
license_name: qwen
license_link: https://huggingface.co/skt/A.X-4.0/blob/main/LICENSE
language:
- en
- ko
pipeline_tag: text-generation
library_name: mlx
model_id: skt/A.X-4.0
developers: SKT AI Model Lab
tags:
- mlx
base_model: skt/A.X-4.0
model-index:
- name: A.X-4.0
  results:
  - task:
      type: generate_until
      name: mmlu
    dataset:
      name: mmlu (chat CoT)
      type: hails/mmlu_no_train
    metrics:
    - type: exact_match
      value: 86.62
      name: exact_match
  - task:
      type: generate_until
      name: kmmlu
    dataset:
      name: kmmlu (chat CoT)
      type: HAERAE-HUB/KMMLU
    metrics:
    - type: exact_match
      value: 78.32
      name: exact_match
---

# litmudoc/A.X-4.0-72B-MLX-Q4

This model [litmudoc/A.X-4.0-72B-MLX-Q4](https://huggingface.co/litmudoc/A.X-4.0-72B-MLX-Q4) was
converted to MLX format from [skt/A.X-4.0](https://huggingface.co/skt/A.X-4.0)
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/A.X-4.0-72B-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)
```