Update pipeline tag to image-text-to-text

README.md

@@ -1,24 +1,25 @@
 ---
-license: apache-2.0
+base_model:
+- llava-hf/llava-1.5-7b-hf
+- OpenGVLab/InternVL-Chat-ViT-6B-Vicuna-7B
+datasets:
+- MLLM-CL/MLLM-CL-ReplayData
 language:
 - en
+library_name: transformers
+license: apache-2.0
 metrics:
 - accuracy
-base_model:
-- llava-hf/llava-1.5-7b-hf
-- OpenGVLab/InternVL-Chat-ViT-6B-Vicuna-7B
-base_model_relation: adapter
+pipeline_tag: image-text-to-text
 tags:
 - router
 - MLLM-CL
 - llava
 - internvl
 - MR-LoRA
-pipeline_tag: visual-question-answering
-library_name: transformers
-datasets:
-- MLLM-CL/MLLM-CL-ReplayData
+base_model_relation: adapter
 ---
+
 ## MLLM-CL Benchmark Description
 MLLM-CL is a novel benchmark encompassing domain and ability continual learning, where the former focuses on independently and identically distributed (IID) evaluation across evolving mainstream domains, 
 whereas the latter evaluates on non-IID scenarios with emerging model ability.