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

  • Log In
  • Sign Up

Lgr54HFi
/
chomera

chimera51
custom_code
Model card Files Files and versions
xet
Community
chomera / chimera /training
Ctrl+K
Ctrl+K
  • 1 contributor
History: 18 commits
Lgr54HFi's picture
Lgr54HFi
fix: MoE intermediate_size not scaled for tiny โ€” 158Mโ†’4M MoE params
6cb7b4d verified 11 days ago
  • __init__.py
    1.51 kB
    feat: export ProgressiveLoopScheduler" 12 days ago
  • benchmark.py
    6.36 kB
    Upload folder using huggingface_hub 12 days ago
  • common.py
    5.02 kB
    fix: MoE intermediate_size not scaled for tiny โ€” 158Mโ†’4M MoE params 11 days ago
  • datasets.py
    6.84 kB
    Upload folder using huggingface_hub 12 days ago
  • hyper.py
    6.73 kB
    Upload chimera/training/hyper.py 11 days ago
  • loops.py
    8.48 kB
    fix: print every step + first-step timing to diagnose slow forward 11 days ago
  • optimizers.py
    4.5 kB
    Upload folder using huggingface_hub 12 days ago