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/jamba/qlora.yaml
+++ b/examples/jamba/qlora.yaml
@@ -47,7 +47,8 @@ gradient_checkpointing_kwargs:
  use_reentrant: false
 resume_from_checkpoint:
 logging_steps: 1
-flash_attention: true
+attention: flash
+

 warmup_steps: 10
 evals_per_epoch:
--- a/examples/jamba/qlora_deepspeed.yaml
+++ b/examples/jamba/qlora_deepspeed.yaml
@@ -46,7 +46,8 @@ gradient_checkpointing_kwargs:
  use_reentrant: false
 resume_from_checkpoint:
 logging_steps: 1
-flash_attention: true
+attention: flash
+

 warmup_steps: 10
 evals_per_epoch:
--- a/examples/jamba/qlora_fsdp_large.yaml
+++ b/examples/jamba/qlora_fsdp_large.yaml
@@ -45,7 +45,8 @@ gradient_checkpointing: true
 gradient_checkpointing_kwargs:
  use_reentrant: true
 logging_steps: 1
-flash_attention: true
+attention: flash
+

 warmup_steps: 10
 evals_per_epoch: 1