ofa-sys/ditto

A self-ailgnment method for role-play. Benchmark for role-play. Resources for "Large Language Models are Superpositions of All Characters: Attaining Arbitrary Role-play via Self-Alignment".

ditto's Issues

role_meta_info中wiki信息过长

您好，我有如下的一个问题：
role_meta_info中一个角色的wiki信息内容很长，在拼接角色A和角色B相关内容prompt用于Query Simulation时，sequence_length远超部分Qwen模型的max_length，请问你们在做非Qwen-72B的DITTO时是如何处理这个情况，让模型可以得到Query和Response Simulation的回复的呀？

Could you please provide the full list of the characters?

Hi,

Thanks for your excellent work! Could you please provide the full list of the characters? And is there an ethical risk in using data of living characters? I also want to construct such dataset and I have such concerns.

[character_AI_open] 相关工作，开源了代码，数据，模型

https://github.com/Minami-su/character_AI_open

麻烦数据提供下，gitlfs没法下载，感谢

This repository is over its data quota. Account responsible for LFS bandwidth should purchase more data packs to restore access. Failed to fetch some objects from 'https://github.com/OFA-Sys/Ditto.git/info/lfs'

[character_AI_open] Related works with open-source code, data, models, and it's two months ahead.

https://github.com/Minami-su/character_AI_open

"This repository is over its data quota"，无法下载git lfs的内容

batch response: This repository is over its data quota. Account responsible for LFS bandwidth should purchase more data packs to restore access.
error: failed to fetch some objects from 'https://github.com/OFA-Sys/Ditto.git/info/lfs'

无法下载git lfs的内容，请问有其他方式下载data里的内容吗？