How do you fine-tune Mistral 7B on your own data?
Train a LoRA adapter on the bf16 Mistral 7B on one 48 GB GPU, with memory math, a TrainingJob manifest and the break-even rule for faster GPUs.
data
2 posts with the tag “data”
Continued pretraining vs fine-tuning: which do you need?
Continued pretraining teaches a model new domain text. Fine-tuning teaches it behavior from examples. A decision rule, cost math and Nodus configs.