---
license: mit
library_name: mlx
datasets:
- PrimeIntellect/verifiable-coding-problems
- likaixin/TACO-verified
- livecodebench/code_generation_lite
language:
- en
base_model: agentica-org/DeepCoder-14B-Preview
pipeline_tag: text-generation
tags:
- mlx
---

# mlx-community/DeepCoder-14B-Preview-6bit

This model [mlx-community/DeepCoder-14B-Preview-6bit](https://huggingface.co/mlx-community/DeepCoder-14B-Preview-6bit) was
converted to MLX format from [agentica-org/DeepCoder-14B-Preview](https://huggingface.co/agentica-org/DeepCoder-14B-Preview)
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("mlx-community/DeepCoder-14B-Preview-6bit")

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)
```