---
base_model:
- meta-llama/Llama-3.1-8B
- cluebbers/Llama-3.1-8B-paraphrase-type-generation-etpc
datasets:
- worta/apty
language:
- en
library_name: transformers
license: apache-2.0
model_name: Llama-3.1-8B-paraphrase-type-generation-apty-ipo
pipeline_tag: text-generation
tags:
- generated_from_trainer
- trl
- dpo
- ipo
licence: license
---

# Model Card for Llama-3.1-8B-paraphrase-type-generation-apty-ipo

This model is a fine-tuned version of [meta-llama/Llama-3.1-8B](https://huggingface.co/meta-llama/Llama-3.1-8B).
It has been trained using [TRL](https://github.com/huggingface/trl).

## 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="cluebbers/Llama-3.1-8B-paraphrase-type-generation-apty-ipo", device="cuda")
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
print(output["generated_text"])
```

## Training procedure

This model was previously finetuned on the ETPC dataset: cluebbers/Llama-3.1-8B-paraphrase-type-generation-etpc-apty-reward

This model was trained with DPO, a method introduced in [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://huggingface.co/papers/2305.18290).

### Framework versions

- TRL: 0.12.0
- Transformers: 4.46.2
- Pytorch: 2.5.1
- Datasets: 3.1.0
- Tokenizers: 0.20.3

## Citations

Cite DPO as:

```bibtex
@inproceedings{rafailov2023direct,
    title        = {{Direct Preference Optimization: Your Language Model is Secretly a Reward Model}},
    author       = {Rafael Rafailov and Archit Sharma and Eric Mitchell and Christopher D. Manning and Stefano Ermon and Chelsea Finn},
    year         = 2023,
    booktitle    = {Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans, LA, USA, December 10 - 16, 2023},
    url          = {http://papers.nips.cc/paper_files/paper/2023/hash/a85b405ed65c6477a4fe8302b5e06ce7-Abstract-Conference.html},
    editor       = {Alice Oh and Tristan Naumann and Amir Globerson and Kate Saenko and Moritz Hardt and Sergey Levine},
}
```

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}}
}
```

Cite ETPC as:

```bibtex
@inproceedings{kovatchev-etal-2018-etpc,
    title = "{ETPC} - A Paraphrase Identification Corpus Annotated with Extended Paraphrase Typology and Negation",
    author = "Kovatchev, Venelin  and
      Mart{\'\i}, M. Ant{\`o}nia  and
      Salam{\'o}, Maria",
    booktitle = "Proceedings of the Eleventh International Conference on Language Resources and Evaluation ({LREC} 2018)",
    month = may,
    year = "2018",
    address = "Miyazaki, Japan",
    publisher = "European Language Resources Association (ELRA)",
    url = "https://aclanthology.org/L18-1221",
}
```

Cite SFT/ETPC model as

```bibtex
@inproceedings{wahle-etal-2023-paraphrase,
    title = "Paraphrase Types for Generation and Detection",
    author = "Wahle, Jan Philip  and
      Gipp, Bela  and
      Ruas, Terry",
    editor = "Bouamor, Houda  and
      Pino, Juan  and
      Bali, Kalika",
    booktitle = "Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing",
    month = dec,
    year = "2023",
    address = "Singapore",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2023.emnlp-main.746",
    doi = "10.18653/v1/2023.emnlp-main.746",
    pages = "12148--12164",
    abstract = "Current approaches in paraphrase generation and detection heavily rely on a single general similarity score, ignoring the intricate linguistic properties of language. This paper introduces two new tasks to address this shortcoming by considering paraphrase types - specific linguistic perturbations at particular text positions. We name these tasks Paraphrase Type Generation and Paraphrase Type Detection. Our results suggest that while current techniques perform well in a binary classification scenario, i.e., paraphrased or not, the inclusion of fine-grained paraphrase types poses a significant challenge. While most approaches are good at generating and detecting general semantic similar content, they fail to understand the intrinsic linguistic variables they manipulate. Models trained in generating and identifying paraphrase types also show improvements in tasks without them. In addition, scaling these models further improves their ability to understand paraphrase types. We believe paraphrase types can unlock a new paradigm for developing paraphrase models and solving tasks in the future.",
}
```