Refactor: Move PEFT config from training script to policy level (#2806)

* move peft config from `lerobot_train` to policy level

* Update src/lerobot/scripts/lerobot_train.py

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Signed-off-by: Michel Aractingi <michel.aractingi@huggingface.co>

* copilot response

* Change the polciy function to return targets rather than peft config.`_get_default_peft_targets()` override in PI0, PI0.5, SmolVLA

* remove none check when building config dict

---------

Signed-off-by: Michel Aractingi <michel.aractingi@huggingface.co>

src/lerobot/policies/pi05/modeling_pi05.py

@@ -1270,3 +1270,14 @@ class PI05Policy(PreTrainedPolicy):
             loss = losses.mean()
             loss_dict["loss"] = loss.item()
             return loss, loss_dict
+
+    def _get_default_peft_targets(self) -> dict[str, any]:
+        """Return default PEFT target modules for PI0.5 fine-tuning."""
+        common_projections = (
+            "state_proj|action_in_proj|action_out_proj|action_time_mlp_in|action_time_mlp_out"
+        )
+        target_modules = rf"(.*\.gemma_expert\..*\.self_attn\.(q|v)_proj|model\.({common_projections}))"
+        return {
+            "target_modules": target_modules,
+            "modules_to_save": [],
+        }