README.md

---
license: apache-2.0
datasets:
- seeklhy/SynSQL-2.5M
language:
- en
tags:
- Text-to-SQL
- SQL
- NL2SQL
- Text2SQL
- mlx
library_name: mlx
base_model: seeklhy/OmniSQL-7B
pipeline_tag: text-generation
---

# sazak/OmniSQL-7B-4bit-mlx

This model [sazak/OmniSQL-7B-4bit-mlx](https://huggingface.co/sazak/OmniSQL-7B-4bit-mlx) was
converted to MLX format from [seeklhy/OmniSQL-7B](https://huggingface.co/seeklhy/OmniSQL-7B)
using mlx-lm version **0.26.2**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("sazak/OmniSQL-7B-4bit-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)
```