Update README.md

README.md

@@ -15,7 +15,10 @@ tags:
 Original model: [biomed-Qwen2-VL-2B-Instruct](https://huggingface.co/AdaptLLM/biomed-Qwen2-VL-2B-Instruct) by [AdaptLLM](https://huggingface.co/AdaptLLM)  
 Based on: [Qwen2-VL-2B](https://huggingface.co/Qwen/Qwen2-VL-2B) by [Qwen](https://huggingface.co/Qwen)
 ## Quantization notes
-Made with llama.cpp-b4608 with imatrix based on exllamav2 default dataset.
+Made with llama.cpp-b4608 with imatrix based on exllamav2 default dataset.  
+I was curious to try to quantize this model but I don't have qualifications to evaluate the result.  
+I briefly checked it with KoboldCpp with multiple images, sometimes it was right, sometimes wrong.  
+There's a big possibility that it requires a good knowledge about its capabilities and scope for proper use.  
 
 # Original model card
 # Adapting Multimodal Large Language Models to Domains via Post-Training