update metadata

- feat: link dataset (no replay data used in experts)
- feat: force adapter
- feat: add tags as in [OpenGVLab/InternVL-Chat-ViT-6B-Vicuna-7B](https://huggingface.co/OpenGVLab/InternVL-Chat-ViT-6B-Vicuna-7B), [llava-hf/llava-1.5-7b-hf](https://huggingface.co/llava-hf/llava-1.5-7b-hf), and [Qwen/Qwen2.5-VL-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-VL-7B-Instruct)

README.md

@@ -7,6 +7,7 @@ metrics:
 base_model:
 - llava-hf/llava-1.5-7b-hf
 - OpenGVLab/InternVL-Chat-ViT-6B-Vicuna-7B
+base_model_relation: adapter
 tags:
 - finance
 - medical
@@ -20,8 +21,14 @@ tags:
 - GUI-Agent
 - DCL
 - ACL
+- llava
+- multimodal
+- image-to-text
+- text-generation
 pipeline_tag: visual-question-answering
 library_name: transformers
+datasets:
+- MLLM-CL/MLLM-CL
 ---
 
 ## MLLM-CL Benchmark Description