RLHF-And-Friends/Humans-vs-Llama-SmallSFT-PPO

本数据集包含来自RLHF-And-Friends/tldr-sft测试分割和RLHF-And-Friends/TLDR-Llama-3.1-8B-SmallSFT-PPO模型的完成部分的人类完成数据。数据集中的prompt列包含了同时提供给人类和模型的提示。使用的模型是TLDR-Llama-3.1-8B-SmallSFT-PPO。原始数据集包含提示和人类的完成部分，来源于RLHF-And-Friends/tldr-sft。This dataset contains human completions from the RLHF-And-Friends/tldr-sft test split and RLHF-And-Friends/TLDR-Llama-3.1-8B-SmallSFT-PPO model completions. The prompt column in the dataset includes the prompts given to both humans and models. The model used is TLDR-Llama-3.1-8B-SmallSFT-PPO. The original dataset with prompts and human completions is sourced from RLHF-And-Friends/tldr-sft.