five

HCY123902/llama-3-8b-inst-utf-self-judge-on-utf

收藏
Hugging Face2026-04-29 更新2026-05-03 收录
下载链接:
https://hf-mirror.com/datasets/HCY123902/llama-3-8b-inst-utf-self-judge-on-utf
下载链接
链接失效反馈
官方服务:
资源简介:
一个用于对话或文本生成任务的训练和测试数据集,包含提示、被选中的响应和被拒绝的响应,以及相关的权重和标记信息,适用于偏好学习或强化学习。

A dataset for training and testing in dialogue or text generation tasks, containing prompts, chosen and rejected responses, along with associated weights and token information, used for preference learning or reinforcement learning.
提供机构:
HCY123902
二维码
社区交流群
二维码
科研交流群
商业服务