[GRPO] Fix re-tokenization bug in tool-calling loop by concatenating token IDs#5242
Merged
Commits
Commits on Mar 5, 2026
- committed
- committed
- committed
- committed
- committed
- committed
- committed
Commits on Mar 6, 2026
- authored
- authored
- committed
- committed
- committed
- committed
- authored
- authored
Commits on Mar 7, 2026
- committed
- authored
- authored
- authored
- committed
- committed
- committed
- committed
- committed
- committed
- authored
- committed
- committed
- committed
- committed
- committed
- committed
- committed
- committed
- authored
- authored
- committed
- committed
- authored
- authored
- committed
Commits on Mar 9, 2026
- committed
- authored
- authored
- authored
- authored
- authored
- authored
- authored
- committed
- authored
- authored
- authored
- authored
- authored
- authored
- authored
- authored
- authored
- authored
- authored
Commits on Mar 10, 2026
- authored
- authored
- authored
- authored
- authored
- andauthored
- andauthored
- authored
- andauthored
- andauthored
- authored
- authored
- committed
- andauthored
- andauthored
- authored
- authored
- authored
- authored
- committed
- committed
- authored
- authored
- authored
- authored
- authored
- authored
- authored
- authored
- committed
- committed
- committed
- authored
- committed
- committed
