migrate example configs to canonical attn_implementation

2026-04-23 22:15:07 +00:00
parent 2d64d009d8
commit 39226623d2
222 changed files with 209 additions and 243 deletions
--- a/examples/gemma4/26b-a4b-moe-qlora.yaml
+++ b/examples/gemma4/26b-a4b-moe-qlora.yaml
@@ -84,7 +84,7 @@ activation_offloading: true
 logging_steps: 1

 # FA2 not supported
-sdp_attention: true
+attn_implementation: sdpa

 warmup_ratio: 0.1
 evals_per_epoch: 4
--- a/examples/gemma4/31b-qlora-flex.yaml
+++ b/examples/gemma4/31b-qlora-flex.yaml
@@ -62,7 +62,7 @@ activation_offloading: true
 logging_steps: 1

 # FA not supported
-flex_attention: true
+attn_implementation: flex_attention

 warmup_ratio: 0.1
 evals_per_epoch: 4
--- a/examples/gemma4/31b-qlora.yaml
+++ b/examples/gemma4/31b-qlora.yaml
@@ -60,7 +60,7 @@ activation_offloading: true
 logging_steps: 1

 # FA not supported
-sdp_attention: true
+attn_implementation: sdpa

 warmup_ratio: 0.1
 evals_per_epoch: 4
--- a/examples/gemma4/e2b-vision-lora.yaml
+++ b/examples/gemma4/e2b-vision-lora.yaml
@@ -50,7 +50,7 @@ gradient_checkpointing: true
 gradient_checkpointing_kwargs:
  use_reentrant: false
 logging_steps: 1
-sdp_attention: true
+attn_implementation: sdpa

 warmup_ratio: 0.1
 weight_decay: 0.0