add YoutuVLForConditionalGeneration architectures (#18620)

* Support Youtu-VL Model
---------

Co-authored-by: Xuan-Son Nguyen <son@huggingface.co>
Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

convert_hf_to_gguf.py

@@ -7212,6 +7212,7 @@ class DeepseekModel(TextModel):
     "DeepseekV3ForCausalLM",
     "KimiVLForConditionalGeneration",
     "YoutuForCausalLM",
+    "YoutuVLForConditionalGeneration"
 )
 class DeepseekV2Model(TextModel):
     model_arch = gguf.MODEL_ARCH.DEEPSEEK2
@@ -10674,8 +10675,8 @@ class JanusProVisionModel(MmprojModel):
         return []
 
 
-@ModelBase.register("YOUTUVLForConditionalGeneration", "YOUTUVLForCausalLM")
-class YOUTUVLVisionModel(MmprojModel):
+@ModelBase.register("YoutuVLForConditionalGeneration")
+class YoutuVLVisionModel(MmprojModel):
     def __init__(self, *args, **kwargs):
         super().__init__(*args, **kwargs)
         assert self.hparams_vision is not None