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

eac123
/
ptr-recurrent-depth

vanilla-pytorch
ml-intern
research
recurrent-depth
length-generalization
pointer-chasing
Model card Files Files and versions
xet
Community
ptr-recurrent-depth
67 MB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 209 commits
eac123's picture
eac123
typo: close italic
a7a1ab5 verified about 8 hours ago
  • ckpts
    Upload ckpts/rec1m4dense-seed2.pt with huggingface_hub about 20 hours ago
  • plots
    Upload plots/training_curves.png with huggingface_hub about 20 hours ago
  • ptr
    margin + stem accounting 1 day ago
  • results
    Upload results/results_table.csv with huggingface_hub about 20 hours ago
  • .gitattributes
    1.82 kB
    Upload plots/perk_zoom.png with huggingface_hub 1 day ago
  • README.md
    7.21 kB
    README: v2 family rows + dense-supervision finding in headline about 8 hours ago
  • REPORT.md
    28.5 kB
    Upload REPORT.md with huggingface_hub about 8 hours ago
  • evaluate.py
    5.27 kB
    margin-aware R=k+4 readout, stem loading 1 day ago
  • job_main.py
    641 Bytes
    generic job wrapper 4 days ago
  • job_runner.py
    580 Bytes
    generic stage runner for jobs 4 days ago
  • make_report.py
    53.6 kB
    prose catch-up: what-remains tested/untested, reproduce stages 3-5, dense dynamics about 8 hours ago
  • run_all.py
    8.68 kB
    stage5 resume support about 23 hours ago
  • smoke_gpu.py
    1.58 kB
    GPU smoke wrapper 4 days ago
  • train.py
    9.98 kB
    aligned4 mode, dense hold-target supervision, stem 1 day ago
  • validate.py
    5.85 kB
    architecture validation suite 4 days ago