|
--- |
|
library_name: transformers |
|
license: gpl-3.0 |
|
base_model: philippelaban/keep_it_simple |
|
datasets: |
|
- Yelp/yelp_review_full |
|
language: |
|
- en |
|
tags: |
|
- ppo |
|
--- |
|
|
|
# TAROT-PPO |
|
|
|
Task-Oriented Authorship Obfuscation Using Policy Optimization Methods |
|
|
|
Fine-tuned text rewriting model with **proximal policy optimization** for authorship obfuscation. |
|
|
|
ArXiv paper: https://arxiv.org/abs/2407.21630v1 |
|
|
|
## Model description |
|
- **Model type:** Authorship obfuscation model using GPT2-based text rewriting |
|
- **Reward models:** [rrivera1849/LUAR-MUD](https://huggingface.co/rrivera1849/LUAR-MUD) & [Alibaba-NLP/gte-large-en-v1.5](https://huggingface.co/Alibaba-NLP/gte-large-en-v1.5) |
|
- **Finetuned from model:** [philippelaban/keep_it_simple](https://huggingface.co/philippelaban/keep_it_simple) |
|
- **Dataset:** [Yelp/yelp_review_full](https://huggingface.co/datasets/Yelp/yelp_review_full) |
|
- **Repository:** https://github.com/hornetsecurity/tarot |
|
|
|
## Example use |
|
```python |
|
from transformers import AutoTokenizer, AutoModelForCausalLM |
|
|
|
tokenizer = AutoTokenizer.from_pretrained("gabrielloiseau/TAROT-PPO") |
|
model = AutoModelForCausalLM.from_pretrained("gabrielloiseau/TAROT-PPO") |
|
|
|
paragraph = """I had dinner at Bella's Bistro last night, and it was a delightful experience. |
|
As soon as I walked in, I was greeted warmly by the hostess, and the cozy, rustic decor made me feel right at home. |
|
I started with the bruschetta, which was so fresh and flavorful—I could have eaten a whole meal of just that!""" |
|
|
|
inputs = tokenizer([paragraph + "<|endoftext|>"], return_tensors="pt", padding=True) |
|
outputs = model.generate(**inputs, do_sample=True, max_new_tokens=128) |
|
|
|
outputs = outputs[:, inputs["input_ids"].shape[1]:] |
|
tokenizer.batch_decode(outputs,skip_special_tokens=True) |
|
``` |
