logoalt Hacker News

flux3125today at 6:39 PM1 replyview on HN

That’s not what it means. "-it" just indicates the model is instruction-tuned, i.e. trained to follow prompts and behave like an assistant. It doesn’t imply anything about whether thinking tokens like <think>....</think> were included or excluded during training. Thats a separate design choice and varies by model.


Replies

DeepYogurttoday at 6:45 PM

What does that mean for a user of the model? Is the "-it" version more direct with solutions or something?

show 2 replies