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/gemma3/gemma-3-1b-qlora.yml
+++ b/examples/gemma3/gemma-3-1b-qlora.yml
@@ -57,7 +57,8 @@ gradient_checkpointing_kwargs:
  use_reentrant: false
 resume_from_checkpoint:
 logging_steps: 1
-flash_attention: true
+attention: flash
+

 warmup_ratio: 0.1
 evals_per_epoch:
--- a/examples/gemma3/gemma-3-4b-qlora.yml
+++ b/examples/gemma3/gemma-3-4b-qlora.yml
@@ -51,8 +51,7 @@ gradient_checkpointing: true
 gradient_checkpointing_kwargs:
  use_reentrant: false
 logging_steps: 1
-flash_attention: true
-eager_attention:
+attention: flash

 warmup_ratio: 0.1
 evals_per_epoch: 1
--- a/examples/gemma3/gemma-3-4b-vision-qlora.yml
+++ b/examples/gemma3/gemma-3-4b-vision-qlora.yml
@@ -53,8 +53,7 @@ gradient_checkpointing: true
 gradient_checkpointing_kwargs:
  use_reentrant: false
 logging_steps: 1
-flash_attention: true
-eager_attention:
+attention: flash

 warmup_ratio: 0.1
 evals_per_epoch: 1