README.md

---
base_model: Gryphe/Codex-24B-Small-3.2
tags:
- instruct
- finetune
- chatml
- axolotl
- roleplay
- mlx
- mlx-my-repo
license: apache-2.0
language:
- en
---

# isetnefret/Codex-24B-Small-3.2-mlx-4Bit

The Model [isetnefret/Codex-24B-Small-3.2-mlx-4Bit](https://huggingface.co/isetnefret/Codex-24B-Small-3.2-mlx-4Bit) was converted to MLX format from [Gryphe/Codex-24B-Small-3.2](https://huggingface.co/Gryphe/Codex-24B-Small-3.2) using mlx-lm version **0.22.3**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("isetnefret/Codex-24B-Small-3.2-mlx-4Bit")

prompt="hello"

if hasattr(tokenizer, "apply_chat_template") and tokenizer.chat_template is not None:
    messages = [{"role": "user", "content": prompt}]
    prompt = tokenizer.apply_chat_template(
        messages, tokenize=False, add_generation_prompt=True
    )

response = generate(model, tokenizer, prompt=prompt, verbose=True)
```