We’ve built a template for fine-tuning Mistral 7B on Valohai. Mistral is an excellent combination of size and performance, and by fine-tuning it using a technique called LoRA, we can be very cost-efficient.
Mistral 7B vs LLaMa
Fine-tuning LLMs via Hugging Face on IBM Cloud
Product Update: Datum Improvements
Mistral 7B Tutorial: A Step-by-Step Guide to Using and Fine-Tuning
Introducing LoraLand: 25 fine-tuned Mistral-7b models that
TensorBoard + Valohai Tutorial
Product Update: End-to-End Automation
Toni Perämäki on LinkedIn: When to retrain an ML model?
How to Fine-Tune Mistral 7B on Your Own Data
How we got fine-tuning Mistral-7B to not suck: Helix Project