Harvard-DCML/boomerang-llama-3.2-1.9B
2B
•
Updated
•
7
Boomerang Distillation
Distilled models from the boomerang distillation paper (https://arxiv.org/abs/2510.05064).
-
-
Harvard-DCML/boomerang-pythia-1.6B
2B • Updated • 13 -
Harvard-DCML/boomerang-qwen3-4.9B
5B • Updated • 15 -
Harvard-DCML/boomerang-qwen3-2.3B
Text Generation • 3B • Updated • 171 • 1 -
Harvard-DCML/boomerang-pythia-3.8B
4B • Updated • 7 -
Boomerang Distillation Enables Zero-Shot Model Size Interpolation
Paper • 2510.05064 • Published • 1