Update README.md

README.md

@@ -1,13 +1,16 @@
 ---
 base_model:
 - Qwen/Qwen2.5-VL-3B-Instruct
-pipeline_tag: text-generation
+pipeline_tag: image-text-to-text
 ---
 
 [<img src="https://raw.githubusercontent.com/csabakecskemeti/devquasar/main/dq_logo_black-transparent.png" width="200"/>](https://devquasar.com)
 
 Quantized version of: [Qwen/Qwen2.5-VL-3B-Instruct](https://huggingface.co/Qwen/Qwen2.5-VL-3B-Instruct)
 
+You have to use the backend from [HimariO's](https://github.com/HimariO/llama.cpp.qwen2vl/tree/qwen25-vl) branch. Big thanks to add Qwen2.5VL support!
+Additional [discussions](https://github.com/ggml-org/llama.cpp/issues/11483#issuecomment-2727577078)
+
 'Make knowledge free for everyone'
 
 <p align="center">
@@ -17,4 +20,4 @@ Quantized version of: [Qwen/Qwen2.5-VL-3B-Instruct](https://huggingface.co/Qwen/
   </a>
 </p>
 
-<a href='https://ko-fi.com/L4L416YX7C' target='_blank'><img height='36' style='border:0px;height:36px;' src='https://storage.ko-fi.com/cdn/kofi6.png?v=6' border='0' alt='Buy Me a Coffee at ko-fi.com' /></a>
+<a href='https://ko-fi.com/L4L416YX7C' target='_blank'><img height='36' style='border:0px;height:36px;' src='https://storage.ko-fi.com/cdn/kofi6.png?v=6' border='0' alt='Buy Me a Coffee at ko-fi.com' /></a>