Thanks, that's a great example "Panza produces a fine-tuned LLM that matches your writing style, pairing it with a Retrieval-Augmented Generation (RAG) component which helps it produce relevant emails." So fine-tuning for writing style, RAG for knowledge
@simonw
-
Input vs Output Token Pricing for LLMs
By
–
Are those prices for input or output tokens? I think they're for output tokens, but usually I find the input tokens price is more relevant – especially since most models with long context have a much lower cap on output tokens (eg Claude 3 allows 200k input but only 4k output)
-
RAG vs Fine-tuning: Understanding AI Model Enhancement Techniques
By
–
"Continue will use similarity search to automatically find important sections when answering your question" sounds like an implementation of RAG, not fine-tuning
-
MacBook Pro M2/M3 pricing impacts personal laptop ownership trends
By
–
A good M2/M3 MacBook Pro is $4,000+ I imagine a lot of people no longer have a personal laptop in the same class as their work laptop these days
-
Gemini Pro 1.5 Long-Context Performance and Pricing Tradeoffs
By
–
The one downside I've seen from super long-context models like that is performance – my experiments with Gemini Pro 1.5 really long prompts has been that they can take 30-90s or more to return a response Also price: input is $7/1m tokens!
-
Demo Access for Monthly Updated LoRA Models Available?
By
–
Is there a demo anywhere where I can talk to one of these models that's had a "monthly update" LoRA and see the working end result?
-
Deep Understanding of Fine-tuning in AI Models
By
–
Same here The best I've seen are loose explanations that fine-tuning is better for setting things like the tone of the response or teaching the model new styles of output – or helping with problems like questions-to-SQL I want deeper understanding than that
-
Fine-tuning vs RAG: Adding Knowledge to Language Models
By
–
The question here is about whether you can use fine-tuning to add small amounts of additional knowledge to an LLM – to solve the "chat about information in this documentation" problem RAG is the common solution to that problem. Can fine-tuning solve that problem too?
-
LoRA Fine-Tuning Chatbot Demo: Proof of Concept Needed
By
–
So far I haven't had a single reply that has linked me to a demo of a chatbot that has used LoRA fine-tuning to learn something new I want to believe it works! But I need to see it working
-
Vector Databases and RAG: Training Approaches
By
–
Training – a vector database is RAG and I know that works already