transformers
add shared experts for upcoming Granite 4.0 language models
#35894
Merged

Commits
  • Modular GraniteMoE with shared Experts.
    shawntan committed 321 days ago
  • Modified
    shawntan committed 321 days ago
  • Import order.
    shawntan committed 321 days ago
  • Modified for style
    shawntan committed 321 days ago
  • Fix space.
    shawntan committed 321 days ago
  • Test
    shawntan committed 321 days ago
  • Remove extra granitemoe file.
    shawntan committed 321 days ago
  • Merge branch 'main' into shared-experts
    shawntan committed 320 days ago
  • New converted file and tests
    shawntan committed 320 days ago
  • Modified __init__ files.
    shawntan committed 320 days ago
  • Formatting.
    shawntan committed 320 days ago
  • Dummy PT objects
    shawntan committed 320 days ago
  • register granitemoe shared model
    Ssukriti committed 317 days ago
  • Merge branch 'main' into shared-experts
    Ssukriti committed 317 days ago
  • fix linting of a file
    Ssukriti committed 317 days ago
  • fix import in modeling file
    Ssukriti committed 317 days ago
  • update generated modeling file
    Ssukriti committed 316 days ago
  • Merge branch 'main' into shared-experts
    Ssukriti committed 316 days ago
  • add documentation
    Ssukriti committed 316 days ago
  • update docstrings
    Ssukriti committed 315 days ago
  • Merge branch 'main' into shared-experts
    Ssukriti committed 315 days ago
  • update generated modeling file
    Ssukriti committed 315 days ago
  • fix docstrings in config class
    Ssukriti committed 315 days ago
  • Merge branch 'main' into shared-experts
    Ssukriti committed 313 days ago
  • merge main
    Ssukriti committed 313 days ago
Loading