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/archived/cerebras/btlm-ft.yml
+++ b/examples/archived/cerebras/btlm-ft.yml
@@ -59,8 +59,7 @@ gradient_checkpointing: false
 resume_from_checkpoint:
 logging_steps: 1

-flash_attention: true
-sdp_attention:
+attn_implementation: flash_attention_2
 flash_optimum:

 gptq_groupsize:
--- a/examples/archived/cerebras/qlora.yml
+++ b/examples/archived/cerebras/qlora.yml
@@ -39,8 +39,7 @@ tf32: true
 gradient_checkpointing: true
 resume_from_checkpoint:
 logging_steps: 1
-xformers_attention: true
-flash_attention:
+attn_implementation: xformers
 gptq_groupsize:
 gptq_model_v1:
 warmup_ratio: 0.1