Ablation 141 A128.dpo.armorm.rp Shisa V2 Llama 3.1 8b

🚀 Model Card for outputs/ablation-141-a128.dpo.armorm.rp-shisa-v2-llama-3.1-8b

This model is a fine - tuned language model. It is based on an unspecified base model from None and is trained using TRL, offering enhanced performance in text - related tasks.

🚀 Quick Start

Here is a simple example to show you how to use this model for text generation:

Basic Usage

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="None", device="cuda")
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
print(output["generated_text"])

✨ Features

• Fine - tuned Model: Built upon an unspecified base model, it has been fine - tuned to better suit specific tasks.
• DPO Training: Trained using the Direct Preference Optimization (DPO) method, which is introduced in Direct Preference Optimization: Your Language Model is Secretly a Reward Model.

📦 Installation

The library used for this model is transformers. You can install it using the following command:

pip install transformers

🔧 Technical Details

Training Procedure

This model was trained with DPO, a method introduced in Direct Preference Optimization: Your Language Model is Secretly a Reward Model.

Framework Versions

• TRL: 0.15.1
• Transformers: 4.50.0
• Pytorch: 2.6.0
• Datasets: 3.4.1
• Tokenizers: 0.21.1

📄 License

The model is released under the license.

📚 Documentation

Citations

If you use DPO in your work, please cite it as:

@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},
}

If you use TRL in your work, please cite it as:

@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}}
}