openlm-research / open_llama

OpenLLaMA, a permissively licensed open source reproduction of Meta AI’s LLaMA 7B trained on the RedPajama dataset
Apache License 2.0
7.27k stars 370 forks source link

Beginner Question #96

Open coffeebe4code opened 6 months ago

coffeebe4code commented 6 months ago

I am quite new to this space, are there any resources anyone would recommend?

Further, what I am looking to do is have a set of "Context" that I would want to ask a question. For example, I would want the model to operate on an additional set of data related to business rules and anything else, so when I ask a question "How do I do x,y,z?" I would want stronger weights on the additional data I have provided. Do I need to retrain the model?