weepcat/compute_weights_hh_partial_reward_model_random_length-3
收藏Hugging Face2025-01-08 更新2025-02-15 收录
下载链接：
https://hf-mirror.com/datasets/weepcat/compute_weights_hh_partial_reward_model_random_length-3
下载链接
链接失效反馈官方服务：
资源简介：
该数据集包含了用户选择的(chosen)和拒绝的(rejected)内容及其角色信息，同时还包括了与不同模型相关的奖励和权重信息。数据集分为训练集(train)，提供了相应的字节数和示例数。
The dataset includes user-chosen and rejected content along with their role information, as well as reward and weight information related to different models. The dataset is split into a training set (train) with provided byte size and example count.
提供机构：
weepcat
