Create modeling_llamavision.py

modeling_llamavision.py

@@ -0,0 +1,12 @@
+# https://huggingface.co/qresearch/llama-3.1-8B-vision-378/blob/main/configuration_llamavision.py
+
+from transformers import PretrainedConfig, LlamaConfig, SiglipVisionConfig
+
+
+class LlamavisionConfig(PretrainedConfig):
+    model_type = "llamavision"
+
+    def __init__(self, **kwargs):
+        self.text_config = LlamaConfig(**kwargs.pop("text_config", {}))
+        self.vision_config = SiglipVisionConfig(**kwargs.pop("vision_config", {}))
+        super().__init__(**kwargs)