update doc snippets + reject gemma4-hybrid with non-FA2 backend

2026-04-23 22:18:02 +00:00
parent 39226623d2
commit 434a484fe9
10 changed files with 47 additions and 27 deletions
--- a/docs/grpo.qmd
+++ b/docs/grpo.qmd
@@ -154,7 +154,7 @@ lr_scheduler: cosine
 warmup_steps: 10

 bf16: true
-flash_attention: true
+attn_implementation: flash_attention_2
 gradient_checkpointing: true

 special_tokens: