Improve model card: Add pipeline tag, library name, and GitHub link

README.md

@@ -1,12 +1,16 @@
 ---
-license: mit
+base_model:
+- Qwen/Qwen2.5-VL-7B-Instruct
 language:
 - en
 - zh
+license: mit
 metrics:
 - accuracy
-base_model:
-- Qwen/Qwen2.5-VL-7B-Instruct
+pipeline_tag: image-text-to-text
+library_name: transformers
 ---
 
-The CodeV-SFT model is used to continue training CodeV-RL, as described in the referenced [paper](https://arxiv.org/abs/2511.19661).
+The CodeV-SFT model is used to continue training CodeV-RL, as described in the paper [CodeV: Code with Images for Faithful Visual Reasoning via Tool-Aware Policy Optimization](https://huggingface.co/papers/2511.19661).
+
+For the code repository, please refer to: [https://github.com/RenlyH/CodeV](https://github.com/RenlyH/CodeV)