Yeah, the dream is to have a "reasoning kernel" that you can plug specific knowledge and skills into ("I know kung fu"). I'm not aware of any progress on the dream though. Plenty of people are making LoRAs for general-purpose open models and there are companies like Thinking Machines that will help you. I'm not sure how you'd choose which base model to start with. I'm also not sure how to draw the boundary between LoRA and RAG.
I'm not exactly sure what you are asking. You can however construct a RAG based on a training corpus and then if you ask questions that when vecroized have no sufficiently similar match in your corpus you tell your llm to just say it cant answer that question.
Concretely, index the tax documents into your data base then ask a question about Mount Everest. Vectorize that question and search your vectoized corpus for something similar. Find nothing then instruct your llm to formulate a response saying it could not answer
Don't think RAG is the most common method for now. In my knowledge now it is mostly about post training and reenforcement learning for adding specific knowledge to base model. RAG is mostly like an add-on to a fully trained model and not so stable or inherent?
Yeah, the dream is to have a "reasoning kernel" that you can plug specific knowledge and skills into ("I know kung fu"). I'm not aware of any progress on the dream though. Plenty of people are making LoRAs for general-purpose open models and there are companies like Thinking Machines that will help you. I'm not sure how you'd choose which base model to start with. I'm also not sure how to draw the boundary between LoRA and RAG.
Some links I found but I can't vouch for them:
https://github.com/oobabooga/textgen/wiki/05-%E2%80%90-Train...
https://thinkingmachines.ai/tinker/
I'm not exactly sure what you are asking. You can however construct a RAG based on a training corpus and then if you ask questions that when vecroized have no sufficiently similar match in your corpus you tell your llm to just say it cant answer that question.
Concretely, index the tax documents into your data base then ask a question about Mount Everest. Vectorize that question and search your vectoized corpus for something similar. Find nothing then instruct your llm to formulate a response saying it could not answer
Don't think RAG is the most common method for now. In my knowledge now it is mostly about post training and reenforcement learning for adding specific knowledge to base model. RAG is mostly like an add-on to a fully trained model and not so stable or inherent?