SmolLM2-135M-Pedantic-Reward-Model

Model Card for SmolLM2-135M-Pedantic-Reward-Model

This model is a fine-tuned version of HuggingFaceTB/SmolLM2-135M-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="eZWALT/trainer_output", 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 trained with the RewardTrainer interface provided by the TRL library for RLHF.

Framework versions

• TRL: 0.23.1
• Transformers: 4.57.0
• Pytorch: 2.8.0
• Datasets: 4.2.0
• Tokenizers: 0.22.1

Citations

Cite as:

@misc{ezwalt2025PRLLM,
	title        = {{Pedantically Reinforced Large Language Model}},
	author       = {Walter J. Troiani Vargas},
	year         = 2025,
	journal      = {GitHub repository},
	publisher    = {GitHub},
	howpublished = {\url{https://github.com/eZWALT/RL-Reinforcement-Learning/tree/main/PROJECT}}
}

@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 Gallou{\'e}dec},
	year         = 2020,
	journal      = {GitHub repository},
	publisher    = {GitHub},
	howpublished = {\url{https://github.com/huggingface/trl}}
}