README.md

---
license: llama3.3
datasets:
- DebateLabKIT/deepa2-conversations
- DebateLabKIT/deep-argmap-conversations
- allenai/tulu-3-sft-mixture
base_model: DebateLabKIT/Llama-3.3-Argunaut-1-70B-SFT
pipeline_tag: text-generation
library_name: transformers
tags:
- logic
- argumentation
- critical-thinking
- argument-mapping
- trl
- sft
- mlx
- mlx-my-repo
---

# ggbetz/Llama-3.3-Argunaut-1-70B-SFT-Q4-mlx

The Model [ggbetz/Llama-3.3-Argunaut-1-70B-SFT-Q4-mlx](https://huggingface.co/ggbetz/Llama-3.3-Argunaut-1-70B-SFT-Q4-mlx) was converted to MLX format from [DebateLabKIT/Llama-3.3-Argunaut-1-70B-SFT](https://huggingface.co/DebateLabKIT/Llama-3.3-Argunaut-1-70B-SFT) using mlx-lm version **0.20.5**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("ggbetz/Llama-3.3-Argunaut-1-70B-SFT-Q4-mlx")

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)
```