Why Methods Like Qlora Fall Short In Domain Knowledge Injection 2
Source
Arcee AI editorial sitemap
Author
Arcee AI editorial sitemap
Date
Terms in this piece · Glossary
pretraining — The first, biggest phase of building a model: training it on enormous amounts of text so it learns language, facts, and reasoning in general.
token — The chunk of text a model reads and writes in — roughly three-quarters of a word — and the unit AI usage is billed in.
alignment — The work of making AI systems actually pursue what their builders and users intend, rather than something subtly or dangerously different.
Why it matters
QLoRA suits instruction tuning and preference alignmentThe work of making AI systems actually pursue what their builders and users intend, rather than something subtly or dangerously different.Full definition → but not knowledge injection. If the model has to learn new facts, budget for full continual pretrainingThe first, biggest phase of building a model: training it on enormous amounts of text so it learns language, facts, and reasoning in general.Full definition → rather than a low-rank adapter.
