---
library_name: transformers
model_name: Phi-4-Argunaut-1-SPIN
pipeline_tag: text-generation
base_model: DebateLabKIT/Phi-4-Argunaut-1-SFT
datasets:
- DebateLabKIT/argdown_line-by-line
- DebateLabKIT/argument_mapping_dpo_pairs
- allenai/llama-3.1-tulu-3-70b-preference-mixture
tags:
- logic
- argumentation
- critical-thinking
- argument-mapping
- generated_from_trainer
- trl
- dpo
- spin
licence: mit
---

# Model Card for Phi-4-Argunaut-1-SPIN

This model is a fine-tuned version of [DebateLabKIT/Phi-4-Argunaut-1-SFT](https://huggingface.co/DebateLabKIT/Phi-4-Argunaut-1-SFT).
It has been trained using [TRL](https://github.com/huggingface/trl) and [vLLM](https://docs.vllm.ai/). Checkpoints are tagged.

📘 [HF Blog Article](https://huggingface.co/blog/ggbetz/argunauts-phase-2)




## Quick start

```python
from transformers import pipeline

question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
generator = pipeline("text-generation", model="DebateLabKIT/Llama-3.1-Argunaut-1-8B-SPIN", device="cuda")
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
print(output["generated_text"])
```

## Training procedure

<!--[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/ggbetz/argunauts-training/runs/s89n820x)-->

This model was trained with Self-Play Fine-Tuning (SPIN), a method introduced in [Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models](https://huggingface.co/papers/2401.01335).

More details about the training procedure can be found in the [blog post](https://huggingface.co/blog/ggbetz/argunauts-phase-2).

### Framework versions

- TRL: 0.14.0
- Transformers: 4.46.3
- Pytorch: 2.4.1
- Datasets: 3.1.0
- Tokenizers: 0.20.3

## Evaluation

### Chat Experience

_coming soon..._

### Metrics

_coming soon..._

## Citations

Cite SPIN as:

```bibtex
@misc{chen2024selfplayfinetuningconvertsweak,
      title={Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models}, 
      author={Zixiang Chen and Yihe Deng and Huizhuo Yuan and Kaixuan Ji and Quanquan Gu},
      year={2024},
      eprint={2401.01335},
      archivePrefix={arXiv},
      primaryClass={cs.LG},
      url={https://arxiv.org/abs/2401.01335}, 
}
```

Cite TRL as:
    
```bibtex
@misc{vonwerra2022trl,
	title        = {{TRL: Transformer Reinforcement Learning}},
	author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouédec},
	year         = 2020,
	journal      = {GitHub repository},
	publisher    = {GitHub},
	howpublished = {\url{https://github.com/huggingface/trl}}
}
```