Tagged
#efficiency
4 articles
research
Distillation: teaching small models from big ones
Knowledge distillation trains a small model to imitate a large one. The trick is not copying answers, but copying the way the big model is unsure.
#distillation#compression#training
05-21 13:52·7 min read
models
Quantization and distillation: making models smaller
"Two different ways to shrink a model — one changes its numbers, the other trains a smaller copy. Here is how each works and when to reach for it."
#quantization#distillation#model-compression
04-12 16:37·7 min read
models
Mixture-of-experts models, explained simply
Mixture-of-experts lets a model be huge yet cheap to run by using only a slice of itself per input. Here is the idea, plainly, and why it matters.
#mixture-of-experts#architecture#efficiency
04-11 13:35·7 min read
models
Small models, big jobs: when on-device beats the cloud
The biggest model is rarely the right one. Here is why small, on-device models win whole classes of jobs — and how to tell when yours is one of them.
#small-models#on-device#edge-ai
04-01 12:28·7 min read