add unime (#34)

- add qqmm (aa65c27b94fd6688e121c037a24bc77a56487954)
- fixed (9198f1f4c54b6c885c3cec4de0a25f82ce27866b)
- add unime (890840c38867b6924ccd7733e1d4c76b3752f831)

results.csv

@@ -23,4 +23,7 @@ VLM2Vec (Qwen2-VL-7B-LoRA-HighRes),8.29,TIGER-Lab,65.8,62.6,57.8,69.9,81.7
 VLM2Vec (Qwen2-VL-2B-LoRA-HighRes),2.21,TIGER-Lab,59.3,59.0,49.4,65.4,73.4
 LLaVE-7B,8.03,Self-Reported,70.3,65.7,65.4,70.9,91.9
 LLaVE-2B,1.95,Self-Reported,65.2,62.1,60.2,65.2,84.9
-LLaVE-0.5B,0.894,Self-Reported,59.1,57.4,50.3,59.8,82.9
+LLaVE-0.5B,0.894,Self-Reported,59.1,57.4,50.3,59.8,82.9
+UniME(LLaVA-OneVision-7B-LoRA-Res336),8.03,Self-Reported,70.7,66.8,66.6,70.5,90.9
+UniME(LLaVA-1.6-7B-LoRA-LowRes),7.57,Self-Reported,66.6,60.6,52.9,67.9,85.1
+UniME(Phi-3.5-V-LoRA),4.2,Self-Reported,64.2,54.8,55.9,64.5,81.8

utils.py

@@ -41,6 +41,8 @@ or a combination of both. MMEB is divided into 20 in-distribution datasets, whic
 training, and 16 out-of-distribution datasets, reserved for evaluation.
 
 The detailed explanation of the benchmark and datasets can be found in our paper: https://doi.org/10.48550/arXiv.2410.05160.
+Github link: https://github.com/TIGER-AI-Lab/VLM2Vec
+Overview: https://tiger-ai-lab.github.io/VLM2Vec/
 """
 
 TABLE_INTRODUCTION = """"""
@@ -94,6 +96,8 @@ SUBMIT_INTRODUCTION = """# Submit on MMEB Leaderboard Introduction
     }, 
 ]
 ```
+You may refer to the Github page for instructions about evaluating your model. 
+Github link: https://github.com/TIGER-AI-Lab/VLM2Vec
 Please send us an email at m7su@uwaterloo.ca, attaching the JSON file. We will review your submission and update the leaderboard accordingly.
 """
 
@@ -117,7 +121,10 @@ MODEL_URLS = {
     "MM-Embed": "https://huggingface.co/nvidia/MM-Embed", 
     "LLaVE-7B": "https://huggingface.co/zhibinlan/LLaVE-7B", 
     "LLaVE-2B": "https://huggingface.co/zhibinlan/LLaVE-2B", 
-    "LLaVE-0.5B": "https://huggingface.co/zhibinlan/LLaVE-0.5B"
+    "LLaVE-0.5B": "https://huggingface.co/zhibinlan/LLaVE-0.5B", 
+    "UniME(LLaVA-OneVision-7B-LoRA-Res336)": "https://huggingface.co/DeepGlint-AI/UniME-LLaVA-OneVision-7B", 
+    "UniME(LLaVA-1.6-7B-LoRA-LowRes)": "https://huggingface.co/DeepGlint-AI/UniME-LLaVA-1.6-7B", 
+    "UniME(Phi-3.5-V-LoRA)": "https://huggingface.co/DeepGlint-AI/UniME-Phi3.5-V-4.2B"
 }
 
 def create_hyperlinked_names(df):