Members-Only
Recent Talks & Demos are for members only
You must be an AI Tinkerers active member to view these talks and demos.
Fine-tune your own Llama 2 to replace GPT-3.5/4
Learn to fine-tune Llama 2 to replace GPT-3.5/4. This talk covers the process, its strengths/weaknesses, and how to get started with a cost-effective, often more accurate alternative.
I recently put together a set of Python code files that walk you through how to replace GPT-3.5 with your own fine-tuned Llama 2 model. The replacement model is 1/50th the cost and often more accurate. You can see the pretty active thread where I shared it with HN here: https://news.ycombinator.com/item?id=37484135
This isn’t a pitch for our company or anything – in fact the project only uses a small piece of OpenPipe functionality for convenience and is mostly standalone.
Demonstrates Llama 2 fine-tuning for recipe classification using GPT-4 generated data.
Fine-tuning Llama 2 7B replaces GPT-4, drastically reducing inference costs.
Compose Email
Loading recent emails...