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

jacobeen06
/
genesis-2-rlhf-code

Model card Files Files and versions
xet
Community
genesis-2-rlhf-code
87.9 MB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 10 commits
jacobeen06's picture
jacobeen06
Skip eval, disable MoE aux loss, disable dropout to fix OOM
9d44c0c verified 5 days ago
  • .gitattributes
    1.7 kB
    Genesis-2.0 RLHF Phase 0 artifacts 5 days ago
  • build_pairs.py
    10.3 kB
    Genesis-2.0 RLHF Phase 0 artifacts 5 days ago
  • dpo_pairs_all.jsonl
    43.8 MB
    xet
    Genesis-2.0 RLHF Phase 0 artifacts 5 days ago
  • dpo_pairs_perturbed.jsonl
    26.4 MB
    xet
    Genesis-2.0 RLHF Phase 0 artifacts 5 days ago
  • dpo_pairs_scored.jsonl
    17.4 MB
    xet
    Genesis-2.0 RLHF Phase 0 artifacts 5 days ago
  • eval_benchmark.py
    7.02 kB
    Genesis-2.0 RLHF Phase 0 artifacts 5 days ago
  • eval_holdout.jsonl
    264 kB
    Genesis-2.0 RLHF Phase 0 artifacts 5 days ago
  • genesis-2-rlhf-plan.md
    7.2 kB
    Add full plan doc 5 days ago
  • rewards.py
    7.6 kB
    Genesis-2.0 RLHF Phase 0 artifacts 5 days ago
  • train_dpo.py
    8.57 kB
    Skip eval, disable MoE aux loss, disable dropout to fix OOM 5 days ago
  • train_grpo.py
    7.48 kB
    Genesis-2.0 RLHF Phase 0 artifacts 5 days ago