Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Buckets new
  • Docs
  • Enterprise
  • Pricing

  • Log In
  • Sign Up

Spaces:
InosLihka
/
rhythm_env
Sleeping

App Files Files Community
Fetching metadata from the HF Docker repository...
rhythm_env / scripts
Ctrl+K
Ctrl+K
  • 3 contributors
History: 15 commits
InosLihka's picture
InosLihka
Add SFT v3 + GRPO refine results to README + results.md
666b4ce 9 days ago
  • analyze_iter.py
    6.89 kB
    tooling: scripts/analyze_iter.py + docs/results.md template 12 days ago
  • eval_on_hf.py
    2.85 kB
    Fix max_new_tokens for CoT format + add eval-only HF Jobs script 12 days ago
  • generate_teacher_trajectories.py
    20.9 kB
    Algorithm Distillation: grader v2 with belief_accuracy + SFT pipeline 12 days ago
  • plot_from_log.py
    8 kB
    feat: HF Jobs training script + plot generator 12 days ago
  • plot_v3_results.py
    2.4 kB
    Post-deadline: full eval results + bigger plots via Git LFS 11 days ago
  • reeval_teacher_trajectories.py
    5.31 kB
    Algorithm Distillation: grader v2 with belief_accuracy + SFT pipeline 12 days ago
  • sft_on_hf.py
    5.53 kB
    Add SKIP_EVAL flag to sft_on_hf.py for faster training-only runs 12 days ago
  • train_on_hf.py
    7.69 kB
    Refactor grader to use openenv.core.rubrics.WeightedSum + Rubric subclasses 11 days ago
  • upload_teacher_data.py
    3.71 kB
    Algorithm Distillation: grader v2 with belief_accuracy + SFT pipeline 12 days ago
  • validate-submission.sh
    5.54 kB
    restore: validate-submission.sh to scripts/ 13 days ago
  • verify_rubric_equivalence.py
    3.86 kB
    Add SFT v3 + GRPO refine results to README + results.md 9 days ago