请问是否会公开训练数据集？

#11

by ycchen - opened Jun 13, 2023

请问是否会公开Ziya的训练数据？

Fengshenbang-LM org Jun 13, 2023

目前不公开

@yuxin Ziya-LLaMA-7B-Reward 模型的训练和reward代码开源了吗

请问Ziya-LLaMA-7B-Reward 的tokenizer.model为何没有扩展中文预料，那这样能与已经扩展了中文的其他模型联合做rlhf嘛？

Fengshenbang-LM org Jun 25, 2023

@zongqiang 目前没有开源

Fengshenbang-LM org Jun 25, 2023

@Deepmarry 与其他模型联合RLHF需要在RM inference时使用RM的tokenizer重新tokenize

yuxin changed discussion status to closed Jul 13, 2023

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment