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
      • Hardware
      • Learn
      • Discord
      • Forum
      • GitHub
    • Solutions
      • Team & Enterprise
      • Hugging Face PRO
      • Enterprise Support
      • Inference Providers
      • Inference Endpoints
      • Storage Buckets

  • Log In
  • Sign Up
anicka 's Collections
Tibetan NLP
CVE backport codegen
Valence & introspection geometry
Karma Electric — ethical post-training
NLA — Qwen 2.5 7B L20 (first generation)
NLA — Phi-4 mini universal
NLA — Qwen 2.5 7B universal
NLA — Qwen3 4B universal
NLA at home — start here

NLA — Qwen 2.5 7B universal

updated Jul 12

Universal multi-layer NLA trio for Qwen2.5-7B-Instruct (28 layers).

Upvote
-

  • anicka/nla-qwen2.5-7b-universal-av-grpo

    Text Generation • Updated Jul 6 • 7 • 1

    Note Start here — GRPO verbalizer, round-trip 0.628


  • anicka/nla-qwen2.5-7b-universal-av

    Text Generation • Updated Jul 6 • 14

    Note SFT verbalizer (baseline)


  • anicka/nla-qwen2.5-7b-universal-ar

    Text Generation • Updated Jul 6 • 6

    Note Reconstructor — audit half + GRPO reward

Upvote
-
  • Collection guide
  • Browse collections
Company
TOS Privacy About Careers
Website
Models Datasets Spaces Pricing Docs