TechnicalAI glossary
Mid-training
A phase that extends pre-training, but on a carefully chosen corpus: code, legal texts, an under-represented language. The model does not change its nature, it shifts its centre of gravity towards one domain. Far cheaper than pre-training, it is often what makes it possible to specialise an open model.
In other words
After general secondary school, a preparatory year focused on a single subject: the same student, but a whole different level in that field.
Alyriaz articles that mention it
- Why your AI changes version every week
AI models now change version almost every week. Why the pace, what it means for you, and how to keep track.
- Mid-training, final fine-tuning: what happens after pre-training
Between a base model and a usable model, there are several distinct training phases. We explain what each one does and why that is where the value now lies.
- A startup is valued at 1.4 billion and doesn't train any model from scratch
A young Chinese company reaches a $1.42 billion valuation in seven months by specialising open models rather than training them. We analyse this model and what it reveals.