Update README.md

README.md

@@ -17,6 +17,7 @@ pinned: false
 
 <h4> |<a href="https://arxiv.org/abs/2401.10491"> 📑 FuseLLM Paper @ICLR2024 </a> |
 <a href="https://arxiv.org/abs/2408.07990"> 📑 FuseChat Tech Report </a> |
+  <a href="https://slit-ai.github.io/FuseChat-3.0/"> 🌐 FuseChat-3.0 Blog Post </a> |
 <a href="https://huggingface.co/FuseAI"> 🤗 HuggingFace Repo </a> |
 <a href="https://github.com/fanqiwan/FuseLLM"> 🐱 GitHub Repo </a> |
 </h4>
@@ -37,8 +38,17 @@ Welcome to join us!
 
 ## News
 
+### FuseChat-3.0
+
+- **Dec 12, 2024:** 🔥 We release [FuseChat-3.0](https://huggingface.co/collections/FuseAI/fusechat-30-6752d18dec430bad7a236a75) and [Blog Post](https://slit-ai.github.io/FuseChat-3.0/). FuseChat-3.0 contains a series of models crafted to enhance performance by integrating the strengths of multiple source LLMs into more compact target LLMs. To achieve this fusion, we utilized four powerful source LLMs: [Gemma-2-27b-It](https://huggingface.co/google/gemma-2-27b-it), [Mistral-Large-Instruct-2407](https://huggingface.co/mistralai/Mistral-Large-Instruct-2407), [Qwen-2.5-72B-Instruct](https://huggingface.co/Qwen/Qwen2-72B-Instruct), and [Llama-3.1-70B-Instruct](https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct). For the target LLMs, we employed three widely-used smaller models—[Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct), [Gemma-2-9B-It](https://huggingface.co/google/gemma-2-9b-it), and [Qwen-2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct)—along with two even more compact models—[Llama-3.2-3B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct) and [Llama-3.2-1B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct). 
+
+<p align="center">
+    <img src="FuseChat-3.0.png" width="60%"> <br>
+</p>
+
 ### FuseChat [SOTA 7B LLM on MT-Bench]
 
+
 - **Aug 16, 2024:** 🔥🔥🔥🔥 We update the [FuseChat tech report](https://arxiv.org/abs/2408.07990) and release [FuseChat-7B-v2.0](https://huggingface.co/FuseAI/FuseChat-7B-v2.0), which is the fusion of six prominent chat LLMs with diverse architectures and scales, namely [OpenChat-3.5-7B](https://huggingface.co/openchat/openchat_3.5), [Starling-LM-7B-alpha](https://huggingface.co/berkeley-nest/Starling-LM-7B-alpha), [NH2-Solar-10.7B](https://huggingface.co/NousResearch/Nous-Hermes-2-SOLAR-10.7B), [InternLM2-Chat-20B](https://huggingface.co/internlm/internlm2-chat-20b), [Mixtral-8x7B-Instruct](https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1), and [Qwen1.5-Chat-72B](https://huggingface.co/Qwen/Qwen1.5-72B-Chat). FuseChat-7B-v2.0 achieves an average performance of **7.38** on MT-Bench (GPT-4-0125-Preview as judge LLM), which is comparable to [Mixtral-8x7B-Instruct](https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1) and approaches [GPT-3.5-Turbo-1106](https://platform.openai.com/docs/models/gpt-3-5-turbo).  
 
 - **Mar 13, 2024:** 🔥🔥🔥 We release a HuggingFace Space for [FuseChat-7B](https://huggingface.co/spaces/FuseAI/FuseChat-7B), try it now!
@@ -91,3 +101,13 @@ Please cite the following paper if you reference our model, code, data, or paper
   year={2024}
 }
 ```
+
+Please cite the following paper if you reference our model, code, data, or paper related to FuseChat-3.0.
+```
+@article{yang2024wrpo,
+  title={Weighted-Reward Preference Optimization for Implicit Model Fusion},
+  author={Ziyi Yang and Fanqi Wan and Longguang Zhong and Tianyuan Shi and Xiaojun Quan},
+  journal={arXiv preprint arXiv:2412.03187},
+  year={2024}
+}
+```