You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
reacted with thumbs up emoji reacted with thumbs down emoji reacted with laugh emoji reacted with hooray emoji reacted with confused emoji reacted with heart emoji reacted with rocket emoji reacted with eyes emoji
-
最近需要做一些微调工作与模型的推理评测工作,微调和推理评测时使用的对话模板必须对齐。在这里想问一下,在SFT时,对训练数据应用对话模板时,llama-factory是把特殊token(如bos)以字符串的形式拼接到输入字符串中再tokenize,还是将特殊token的id拼接到输入字符串的id序列中?
另外,模板中要添加的token除了bos这种外,还涉及到换行符\n。换行符在拼接时是怎样处理的?
如果能详细介绍一下拼接时的处理流程最好,因为一些模型的tokenizer比较特殊,同一个字符在不同的字符串里可能对应不同的id,拼接方式的不同会导致tokenize的结果不同。
万分感谢!
Beta Was this translation helpful? Give feedback.
All reactions