--- base_model: meta-llama/Llama-3.1-8B-Instruct datasets: trl-lib/ultrafeedback_binarized library_name: transformers model_name: RM-UltrafeedbackBinarized-Llama-3.1-8B-Instruct-Q4-LoRA8-Batch-16-Tok-1024 tags: - generated_from_trainer - trl - reward-trainer licence: license --- # Model Card for RM-UltrafeedbackBinarized-Llama-3.1-8B-Instruct-Q4-LoRA8-Batch-16-Tok-1024 This model is a fine-tuned version of [meta-llama/Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct) on the [trl-lib/ultrafeedback_binarized](https://huggingface.co/datasets/trl-lib/ultrafeedback_binarized) dataset. 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="RLHF-And-Friends/RM-UltrafeedbackBinarized-Llama-3.1-8B-Instruct-Q4-LoRA8-Batch-16-Tok-1024", device="cuda") output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0] print(output["generated_text"]) ``` ## Training procedure [Visualize in Weights & Biases](https://wandb.ai/RADFAN/RM-UltrafeedbackBinarized/runs/6t8jl6dt) This model was trained with Reward. ### Framework versions - TRL: 0.13.0 - Transformers: 4.47.1 - Pytorch: 2.5.1 - Datasets: 3.2.0 - Tokenizers: 0.21.0 ## Citations 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}} } ```