Add image-text-to-text pipeline tag

README.md

@@ -1,7 +1,7 @@
 ---
+base_model: Qwen/Qwen2-VL-72B-Instruct
 library_name: transformers
 license: apache-2.0
-base_model: Qwen/Qwen2-VL-72B-Instruct
 tags:
 - llama-factory
 - full
@@ -9,6 +9,7 @@ tags:
 model-index:
 - name: TVC-7B
   results: []
+pipeline_tag: image-text-to-text
 ---
 
 ## Model Summary
@@ -19,7 +20,6 @@ The TVC models are 72B parameter models based on Qwen2-VL-72B-Instruct model wit
 - **Languages:** English, Chinese
 - **Paper:** https://arxiv.org/abs/2503.13360
 
-
 ### Model Architecture
 
 - **Architecture:** Qwen2-VL-72B-Instruct