Update README.md

README.md

@@ -33,6 +33,8 @@ We investigate domain adaptation of MLLMs through post-training, focusing on dat
 
 
 ## Resources
+**🤗 We share our data and models with example usages, feel free to open any issues or discussions! 🤗**
+
 | Model                                                                       | Repo ID in HF 🤗                           | Domain       | Base Model              | Training Data                                                                                  | Evaluation Benchmark |
 |:----------------------------------------------------------------------------|:--------------------------------------------|:--------------|:-------------------------|:------------------------------------------------------------------------------------------------|-----------------------|
 | [Visual Instruction Synthesizer](https://huggingface.co/AdaptLLM/visual-instruction-synthesizer) | AdaptLLM/visual-instruction-synthesizer     | -  | open-llava-next-llama3-8b    | TBD | -                   |
@@ -43,6 +45,9 @@ We investigate domain adaptation of MLLMs through post-training, focusing on dat
 | [AdaMLLM-med-11B](https://huggingface.co/AdaptLLM/medicine-Llama-3.2-11B-Vision-Instruct) | AdaptLLM/medicine-Llama-3.2-11B-Vision-Instruct     | Biomedicine  | Llama-3.2-11B-Vision-Instruct    | [medicine-visual-instructions](https://huggingface.co/datasets/AdaptLLM/medicine-visual-instructions) | TBD                   |
 | [AdaMLLM-food-11B](https://huggingface.co/AdaptLLM/food-Llama-3.2-11B-Vision-Instruct) | AdaptLLM/food-Llama-3.2-11B-Vision-Instruct     | Food | Llama-3.2-11B-Vision-Instruct    | TBD | TBD                   |
 
+## Contact  
+Daixuan Cheng: `daixuancheng6@gmail.com`
+
 ## About
 
 AdaMLLM represents our latest advancement in building domain-specific foundation models through post-training on synthetic supervised tasks derived from unsupervised contexts.
@@ -59,6 +64,7 @@ AdaMLLM represents our latest advancement in building domain-specific foundation
   We extend supervised task synthesis to multimodality, introducing a unified visual instruction synthesizer to extract instruction-response pairs from domain-specific image-caption pairs. Our synthetic tasks outperform those generated by manual rules, GPT-4, and GPT-4V in improving domain-specific performance for MLLMs.
 
 
+
 ## Citation
 If you find our work helpful, please cite us.