Create README.md

This model is built upon the LlaVA architecture. The visual extractor is sourced from the Enhanced VisualEncoder, which is designed to effectively capture and process visual information, enabling the model to have a better understanding of visual features.For the language component, the Qwen 7B language model is selected. The training dataset for this model is the mm_chain_of_thought_medical.

README.md

@@ -0,0 +1,6 @@
+---
+language:
+- en
+base_model:
+- Qwen/Qwen1.5-7B
+---