Working with Giant Language Fashions
Evaluating totally different strategies for reasoning
11 hours in the past
In the event you’re not a member however need to learn this text, see this pal hyperlink right here.
Chain of Thought (CoT) has been round for fairly a while and is technically a sort of superior immediate engineering, nevertheless it stays related even now, a number of years after it was first launched. CoT, in its varied types, is often an effort to drive giant language fashions to cause.
After OpenAI’s preview of their mannequin o1 was launched this September, we noticed the hype round CoT improve.
Nobody fully is aware of how o1 works (aside from OpenAI, that’s), whether or not it’s a mix system, what sort of knowledge it has been fine-tuned with, if they’re utilizing reinforcement studying, or if there are a number of fashions working collectively.
Perhaps one mannequin does the planning, one other the pondering, and a 3rd charges. However we do know they’re using some kind of step-by-step reasoning.
There was various open analysis round this that you just may need to dig into. So for this piece, I’ll undergo what’s on the market so what you should utilize. Naturally I’ll take a look at the totally different strategies to see how…