transformers
[`Qwen4 Exp`] Use partial to avoid skipping mask more easily
#48456
Merged

Commits
  • cleaner
    vasqu committed 78 days ago
  • use proper layer mappings
    vasqu committed 78 days ago
  • Merge remote-tracking branch 'upstream/main' into force-mask-qwen4
    vasqu committed 77 days ago
Loading