Update README.md

README.md

@@ -16,16 +16,17 @@ language:
 
 # Mantis: Interleaved Multi-Image Instruction Tuning
 
-**Mantis** is a multimodal conversational AI model that can chat with users about images and text. It's optimized for multi-image reasoning, where interleaved text and images can be used fed as the input to generate responses.
+**Mantis** is a multimodal conversational AI model that can chat with users about images and text. It's optimized for multi-image reasoning, where interleaved text and images can be used to generate responses.
 
 Mantis is trained on the newly curated dataset **Mantis-Instruct**, a large-scale multi-image QA dataset that covers various multi-image reasoning tasks.
 
-Mantis is an active work in progress. Check our [Blog](https://tiger-ai-lab.github.io/Blog/mantis) for more details!
-
-[Paper](https://arxiv.org/abs/2405.01483) |[Demo](https://huggingface.co/spaces/TIGER-Lab/Mantis) | [Github](https://github.com/TIGER-AI-Lab/Mantis) | [Models](https://huggingface.co/collections/TIGER-Lab/mantis-6619b0834594c878cdb1d6e4) |  
+|[Demo](https://huggingface.co/spaces/TIGER-Lab/Mantis) | [Github](https://github.com/TIGER-AI-Lab/Mantis) |  [Models](https://huggingface.co/collections/TIGER-Lab/mantis-6619b0834594c878cdb1d6e4) |  
 
 ![Mantis](https://raw.githubusercontent.com/TIGER-AI-Lab/Mantis/main/docs/assets/images/overall_barchart.jpeg)
 
+**Note that this is an older version of Mantis**, please refer to our newest version at [mantis-Siglip-llama3](https://huggingface.co/TIGER-Lab/Mantis-8B-siglip-llama3). The newer version improves significantly over both multi-image and single-image tasks.
+
+
 ## Inference
 
 You can install Mantis's GitHub codes as a Python package