Qwen3.5-MoE example config with lora_target_modules regex (#3515) [skip ci]

* lora target modules with regex

* updates

* fsdp for non moe

* update wording

* chore: cleanup and lint

* chore: cleanup docs from merge

---------

Co-authored-by: NanoCode012 <nano@axolotl.ai>

examples/qwen3.5/9b-lora-vision.yaml

@@ -26,8 +26,6 @@ lora_r: 32
 lora_alpha: 16
 lora_dropout: 0.05
 # Targets the language model attention and MLP layers.
-# Qwen3.5 is early-fusion: all layers (including those seeing vision tokens) share
-# the same transformer stack, so standard attention targets work for both modalities.
 lora_target_modules:
   - q_proj
   - k_proj