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

  • Log In
  • Sign Up

geoore
/
SHOREKEEPER

PyTorch
English
mixture-of-experts
language-model
reasoning
grpo
Model card Files Files and versions
xet
Community
SHOREKEEPER / scripts
69.6 kB
Ctrl+K
Ctrl+K
  • 2 contributors
History: 2 commits
geoore's picture
geoore
Restructure to src/ layout with attention, per-layer MoE, and working chat
73400c8 5 days ago
  • 01_download_15b_data.py
    3.66 kB
    Restructure to src/ layout with attention, per-layer MoE, and working chat 5 days ago
  • 01_download_7b_150gb.py
    10.1 kB
    Restructure to src/ layout with attention, per-layer MoE, and working chat 5 days ago
  • 01_download_stem_data.py
    5.2 kB
    Restructure to src/ layout with attention, per-layer MoE, and working chat 5 days ago
  • 04_train.py
    10.1 kB
    Restructure to src/ layout with attention, per-layer MoE, and working chat 5 days ago
  • 04_train_5090_optimized.py
    4.58 kB
    Restructure to src/ layout with attention, per-layer MoE, and working chat 5 days ago
  • 04_train_stem.py
    4.15 kB
    Restructure to src/ layout with attention, per-layer MoE, and working chat 5 days ago
  • 04_train_universal.py
    14.5 kB
    Restructure to src/ layout with attention, per-layer MoE, and working chat 5 days ago
  • 05_grpo_train.py
    10.5 kB
    Restructure to src/ layout with attention, per-layer MoE, and working chat 5 days ago
  • 07_run_shorekeeper.py
    4.65 kB
    Restructure to src/ layout with attention, per-layer MoE, and working chat 5 days ago
  • 09_run_tests.py
    2.12 kB
    Restructure to src/ layout with attention, per-layer MoE, and working chat 5 days ago