Replies: 3 comments 2 replies
-
诚邀大家共同讨论。做垂直预训练的数据格式与微调的数据格式会有那些不同? |
Beta Was this translation helpful? Give feedback.
2 replies
-
请问解决了吗?我也有这个问题呢 |
Beta Was this translation helpful? Give feedback.
0 replies
-
同求数据格式,有人做过这样训练的吗? |
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
目前微调时候的数据格式是
{"conversations": [{"role": "user", "content": "类型#裤版型#宽松风格#性感图案#线条裤型#阔腿裤"}, {"role": "assistant", "content": "宽松的阔腿裤这两年真的吸粉不少,明星时尚达人的心头爱。毕竟好穿时尚,谁都能穿出腿长2米的效果宽松的裤腿,当然是遮肉小能手啊。上身随性自然不拘束,面料亲肤舒适贴身体验感棒棒哒。系带部分增加设计看点,还让单品的设计感更强。腿部线条若隐若现的,性感撩人。颜色敲温柔的,与裤子本身所呈现的风格有点反差萌。"}]}
那如果像将chatglm3-6b作为基座进行增量预训练的话,数据格式有什么要求?各位大佬们是怎么处理?
Beta Was this translation helpful? Give feedback.
All reactions