README.md

---
license: apache-2.0
pipeline_tag: text-generation
library_name: mlx
tags:
- vllm
- mlx
base_model: unsloth/gpt-oss-20b
---

# warshanks/gpt-oss-20b-8bit

This model [warshanks/gpt-oss-20b-8bit](https://huggingface.co/warshanks/gpt-oss-20b-8bit) was
converted to MLX format from [unsloth/gpt-oss-20b](https://huggingface.co/unsloth/gpt-oss-20b)
using mlx-lm version **0.26.3**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("warshanks/gpt-oss-20b-8bit")

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)
```