README.md

---
license: mit
language:
- en
base_model: microsoft/NextCoder-32B
pipeline_tag: text-generation
library_name: mlx
tags:
- code
- chat
- microsoft
- nextcoder
- selekt
- mlx
datasets:
- microsoft/NextCoderDataset
- microsoft/NextCoderDataset-Conversational
- bigcode/commitpackft
- bigcode/starcoderdata
---

# jedisct1/NextCoder-32B-q8-mlx

This model [jedisct1/NextCoder-32B-q8-mlx](https://huggingface.co/jedisct1/NextCoder-32B-q8-mlx) was
converted to MLX format from [microsoft/NextCoder-32B](https://huggingface.co/microsoft/NextCoder-32B)
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("jedisct1/NextCoder-32B-q8-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)
```