Members-Only
Recent Talks & Demos are for members only
You must be an AI Tinkerers active member to view these talks and demos.
January 30, 2024
·
London
Mistral Fine-Tuning: Synthetic Data
Explains how to fine‑tune Mistral 7B with synthetic data, covering data cleaning, formatting, and achieving cost‑effective, low‑latency performance comparable to GPT‑3.5.
Overview
Fine-tuning an open source model such as Mistral 7B for a specific use case can bring remarkable accuracy, cost and latency improvements. However, data cleaning and formatting is tedious and often the biggest challenge when fine-tuning. We’ll share learnings from fine-tuning with synthetic data to build a substitute for GPT-3.5.
Links
PVS agent automates workflows reliably using LLMs and integrated tools.
Tech stack