llama3_false_positives_0312_KTO_optimised_model_2104

Model Card for llama3_false_positives_0312_KTO_optimised_model_2104

This model is a fine-tuned version of meta-llama/Meta-Llama-3-8B-Instruct. It has been trained using TRL.

Quick start

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="PaulD/llama3_false_positives_0312_KTO_optimised_model_2104", 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"/>

This model was trained with KTO, a method introduced in KTO: Model Alignment as Prospect Theoretic Optimization.

Framework versions

• TRL: 0.16.0
• Transformers: 4.50.0.dev0
• Pytorch: 2.6.0+cu126
• Datasets: 3.5.0
• Tokenizers: 0.21.1

Citations

Cite KTO as:

@article{ethayarajh2024kto,
    title        = {{KTO: Model Alignment as Prospect Theoretic Optimization}},
    author       = {Kawin Ethayarajh and Winnie Xu and Niklas Muennighoff and Dan Jurafsky and Douwe Kiela},
    year         = 2024,
    eprint       = {arXiv:2402.01306},
}

Cite TRL 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}}
}