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

tbukuai
/
parameter-golf-submission

Model card Files Files and versions
xet
Community
parameter-golf-submission
171 kB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 18 commits
tbukuai's picture
tbukuai
Add DeepSeek comparison, data filtering phase, and approach matrix
60a575c verified 3 months ago
  • .gitattributes
    1.52 kB
    initial commit 3 months ago
  • README.md
    7.49 kB
    Update README: add Kaggle notebook, detailed Kaggle setup guide, Colab vs Kaggle comparison 3 months ago
  • claude.md
    3.96 kB
    Add claude.md with project context and strategy notes 3 months ago
  • distillation_plan.md
    25.7 kB
    Add DeepSeek comparison, data filtering phase, and approach matrix 3 months ago
  • launch_training.py
    4.46 kB
    Upload launch_training.py with huggingface_hub 3 months ago
  • launch_training_competitive.py
    6.3 kB
    Add competitive launcher: SP4096 data from HF cache, 6hr/30K iter defaults, optimized hyperparams 3 months ago
  • parameter_golf_colab.ipynb
    18.2 kB
    Fix: total_mem โ†’ total_memory (PyTorch 2.10+ compat) 3 months ago
  • parameter_golf_kaggle.ipynb
    18.2 kB
    Fix: total_mem โ†’ total_memory (PyTorch 2.10+ compat) 3 months ago
  • roadmap.md
    9.71 kB
    Add Phase 7 (Distillation) to roadmap + update decision log 3 months ago
  • sota_train_gpt.py
    16.6 kB
    Upload sota_train_gpt.py with huggingface_hub 3 months ago
  • train_gpt.py
    59.3 kB
    Upload train_gpt.py with huggingface_hub 3 months ago