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/llama-2/fft_optimized.yml
+++ b/examples/llama-2/fft_optimized.yml
@@ -42,7 +42,7 @@ tf32: false
 gradient_checkpointing: true
 resume_from_checkpoint:
 logging_steps: 1
-flash_attention: true
+attn_implementation: flash_attention_2
 flash_attn_cross_entropy: false
 flash_attn_rms_norm: true
 flash_attn_fuse_mlp: true
--- a/examples/llama-2/gptq-lora.yml
+++ b/examples/llama-2/gptq-lora.yml
@@ -53,8 +53,6 @@ tf32: true
 gradient_checkpointing: true
 resume_from_checkpoint:
 logging_steps: 1
-flash_attention:
-sdp_attention:
 flash_optimum:
 warmup_ratio: 0.1
 evals_per_epoch: 4
--- a/examples/llama-2/lisa.yml
+++ b/examples/llama-2/lisa.yml
@@ -46,7 +46,7 @@ tf32: false
 gradient_checkpointing: true
 resume_from_checkpoint:
 logging_steps: 1
-flash_attention: true
+attn_implementation: flash_attention_2
 flash_attn_cross_entropy: false
 flash_attn_rms_norm: true
 flash_attn_fuse_mlp: true
--- a/examples/llama-2/loftq.yml
+++ b/examples/llama-2/loftq.yml
@@ -45,7 +45,7 @@ tf32: false
 gradient_checkpointing: true
 resume_from_checkpoint:
 logging_steps: 1
-flash_attention: true
+attn_implementation: flash_attention_2

 warmup_ratio: 0.1
 evals_per_epoch: 4
--- a/examples/llama-2/lora.yml
+++ b/examples/llama-2/lora.yml
@@ -45,7 +45,7 @@ tf32: false
 gradient_checkpointing: true
 resume_from_checkpoint:
 logging_steps: 1
-flash_attention: true
+attn_implementation: flash_attention_2

 warmup_ratio: 0.1
 evals_per_epoch: 4
--- a/examples/llama-2/qlora-fsdp.yml
+++ b/examples/llama-2/qlora-fsdp.yml
@@ -48,7 +48,7 @@ gradient_checkpointing_kwargs:
  use_reentrant: true
 resume_from_checkpoint:
 logging_steps: 1
-flash_attention: true
+attn_implementation: flash_attention_2

 warmup_ratio: 0.1
 evals_per_epoch: 4
--- a/examples/llama-2/qlora.yml
+++ b/examples/llama-2/qlora.yml
@@ -46,7 +46,7 @@ tf32: false
 gradient_checkpointing: true
 resume_from_checkpoint:
 logging_steps: 1
-flash_attention: true
+attn_implementation: flash_attention_2

 warmup_ratio: 0.1
 evals_per_epoch: 4
--- a/examples/llama-2/relora.yml
+++ b/examples/llama-2/relora.yml
@@ -51,7 +51,7 @@ tf32: false
 gradient_checkpointing: true
 resume_from_checkpoint:
 logging_steps: 1
-flash_attention: true
+attn_implementation: flash_attention_2

 warmup_ratio: 0.1
 evals_per_epoch: 4