transformers
b7164eca
- Fix VL model rope_deltas batch size mismatch in online RL training (#44873)
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Commit
View On
GitHub
Commit
43 days ago
Fix VL model rope_deltas batch size mismatch in online RL training (#44873) * Fix Qwen3.5 rope_deltas persistence causing crash in online RL training * Extend * Extend
References
#44873 - Fix VL model rope_deltas batch size mismatch in online RL training
Author
sergiopaniego
Parents
1229e90d
Loading