replace attention in the yaml config with an enum

2025-04-04 23:37:30 -04:00
parent 0d71b0aa5f
commit ba47adc24b
101 changed files with 268 additions and 122 deletions
--- a/examples/mistral/mixtral.yml
+++ b/examples/mistral/mixtral.yml
@@ -69,7 +69,8 @@ tf32: false
 gradient_checkpointing: true
 resume_from_checkpoint:
 logging_steps: 1
-flash_attention: true
+attention: flash
+

 loss_watchdog_threshold: 5.0
 loss_watchdog_patience: 3