LocalLLaMA

1 readers

1 users here now

Community to discuss about Llama, the family of large language models created by Meta AI.

founded 10 months ago

MODERATORS

communick@poweruser.forum

Fine Tuning vs. Context? (alien.top)

submitted 10 months ago by masticore514219@alien.top to c/localllama@poweruser.forum

2 comments fedilink hide all child comments

Was diving deeper into local LLM tinkering and I wanted to understand: when would I want to fine tune vs. use context? What use cases would either cater to? Sorry if this is a bit basic, but still learning the ropes in terms of LLM tinkering and got confused between the two. An answer to this will really help me focus on learning the right thing. Thanks.

If it helps, I currently want my LLM to “understand” some essays/blog entries then spit back summaries/comparisons between them.

you are viewing a single comment's thread
view the rest of the comments

[–] Kno010@alien.top 1 points 10 months ago

It depends on a lot of factors obviously, but in general I have found that fine tuning is best used to make the model respond in specific ways using the information it already possessed before the fine tuning, while context is best used to add knowledge that the model doesn’t have.