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

Physicsru
/
compgen-checkpoints

Safetensors
English
compositional-generalization
interpretability
recall-then-assemble
grpo
Model card Files Files and versions
xet
Community
compgen-checkpoints
315 GB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 39 commits
Physicsru's picture
Physicsru
For Minegishi: training documentation, reproducibility files and line plots 4/4
a1fcfb7 verified 4 days ago
  • eval
    add eval files 20 days ago
  • for Minegishi
    For Minegishi: training documentation, reproducibility files and line plots 4/4 4 days ago
  • loop_transformer_halting_2026-09-24
    data/chain_loop (k = 1 default data dir) and README section on resuming 5 days ago
  • rl-mda-step100
    add rl-mda-step100 20 days ago
  • rl-mda-step5
    add rl-mda-step5 20 days ago
  • rl-mda-step50
    add rl-mda-step50 20 days ago
  • rl-mdb-step100
    add rl-mdb-step100 20 days ago
  • rl-r1a-step100
    add rl-r1a-step100 20 days ago
  • rl-r1b-step100
    add rl-r1b-step100 20 days ago
  • sft-c1-s1
    add sft-c1-s1 20 days ago
  • sft-c4-s1
    add sft-c4-s1 20 days ago
  • sft-c4b-s1
    add sft-c4b-s1 20 days ago
  • sft-d1-s1
    add sft-d1-s1 20 days ago
  • sft-eco-s1
    add sft-eco-s1 20 days ago
  • sft-matched-grouped-s1
    add sft-matched-grouped-s1 20 days ago
  • sft-matched-isolated-s1
    add sft-matched-isolated-s1 20 days ago
  • sft-v1-s1
    add sft-v1-s1 20 days ago
  • stage15b-init
    add stage15b-init 20 days ago
  • .gitattributes
    4.05 kB
    For Minegishi: training documentation, reproducibility files and line plots 3/4 4 days ago
  • README.md
    11.1 kB
    README: TL;DR with pairwise contrasts (fixed nested code fences) 20 days ago