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

Avra98
/
curriculum-cot-code

Model card Files Files and versions
xet
Community
curriculum-cot-code / latent_multi_output_cell_policy
184 kB
Ctrl+K
Ctrl+K
  • 4 contributors
History: 4 commits
Avra98's picture
Avra98
backtracking sweep summarizer
994f853 verified 4 months ago
  • backtracking
    backtracking sweep summarizer 4 months ago
  • __init__.py
    75 Bytes
    Initial code dump (rebuttal-ready snapshot) 5 months ago
  • grpo_multimode_latent_train.py
    869 Bytes
    Initial code dump (rebuttal-ready snapshot) 5 months ago
  • grpo_residual_projector_latent_train.py
    86.4 kB
    Initial code dump (rebuttal-ready snapshot) 5 months ago
  • residual_projector_warmstart_sft_latent_multi_output_train.py
    38.4 kB
    Initial code dump (rebuttal-ready snapshot) 5 months ago
  • sft_latent_multi_output_train.py
    53.2 kB
    latent SFT: cross-stage backtracking/rehearsal + baseline warm-up 4 months ago