Community to discuss about Llama, the family of large language models created by Meta AI.
iam looking to do something similar using RAG piplines might be usefull as far as i understand to give the model extra context about the sides you want to summarize.
https://agi-sphere.com/retrieval-augmented-generation-llama2/
maybe you already know all this but i am also new and just recently stumbled upon this :)
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.