Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Buckets new
  • Docs
  • Enterprise
  • Pricing
    • Website
      • Tasks
      • HuggingChat
      • Collections
      • Languages
      • Organizations
    • Community
      • Blog
      • Posts
      • Daily Papers
      • Learn
      • Discord
      • Forum
      • GitHub
    • Solutions
      • Team & Enterprise
      • Hugging Face PRO
      • Enterprise Support
      • Inference Providers
      • Inference Endpoints
      • Storage Buckets

  • Log In
  • Sign Up
Harvard-DCML 's Collections
Targeted Instruction Selection
Boomerang Distillation

Boomerang Distillation

updated Oct 14, 2025

Distilled models from the boomerang distillation paper (https://arxiv.org/abs/2510.05064).

Upvote
1

  • Harvard-DCML/boomerang-llama-3.2-1.9B

    2B • Updated Oct 14, 2025 • 25.2k

  • Harvard-DCML/boomerang-pythia-1.6B

    2B • Updated Oct 14, 2025 • 19.1k

  • Harvard-DCML/boomerang-qwen3-4.9B

    5B • Updated Oct 14, 2025 • 25.3k

  • Harvard-DCML/boomerang-qwen3-2.3B

    Text Generation • 3B • Updated Nov 18, 2025 • 14k • 3

  • Harvard-DCML/boomerang-pythia-3.8B

    4B • Updated Oct 14, 2025 • 16.7k

  • Boomerang Distillation Enables Zero-Shot Model Size Interpolation

    Paper • 2510.05064 • Published Oct 6, 2025 • 1
Upvote
1
  • Collection guide
  • Browse collections
Company
TOS Privacy About Careers
Website
Models Datasets Spaces Pricing Docs