diff --git a/unsloth/models/llama.py b/unsloth/models/llama.py
index c1e9110759..89c25e7316 100644
--- a/unsloth/models/llama.py
+++ b/unsloth/models/llama.py
@@ -3072,7 +3072,14 @@ class FastLlamaModel:
                 gc.collect()
                 clean_gpu_cache()
 
-        model = _get_peft_model(model, lora_config)
+        import warnings as _w
+
+        with _w.catch_warnings():
+            _w.filterwarnings(
+                "ignore",
+                message = ".*target_parameters.*were set but no parameter was matched.*",
+            )
+            model = _get_peft_model(model, lora_config)
         # Fix LoraConfig.auto_mapping is None
         fix_lora_auto_mapping(model)
 
diff --git a/unsloth/models/vision.py b/unsloth/models/vision.py
index 2c1371a4a2..735c28d917 100644
--- a/unsloth/models/vision.py
+++ b/unsloth/models/vision.py
@@ -1209,7 +1209,14 @@ class FastBaseModel:
             model,
             use_gradient_checkpointing = use_gradient_checkpointing,
         )
-        model = _get_peft_model(model, lora_config)
+        import warnings as _w
+
+        with _w.catch_warnings():
+            _w.filterwarnings(
+                "ignore",
+                message = ".*target_parameters.*were set but no parameter was matched.*",
+            )
+            model = _get_peft_model(model, lora_config)
         # Apply QAT + LoRA if specified
         if qat_scheme is not None:
             print("Unsloth: Applying QAT to mitigate quantization degradation")