### Model Introduction With the rapid development of artificial intelligence technology, large language models (LLMs) have made significant progress in fields such as natural language processing, computer vision, and scientific tasks. However, as the scale of these models increases, optimizing resource consumption while maintaining high performance has become a key challenge. To address this challenge, we have explored Mixture of Experts (MoE) models. The currently unveiled Hunyuan-Large (Hunyuan-MoE-A52B) model is the largest open-source Transformer-based MoE model in the industry, featuring a total of 389 billion parameters and 52 billion active parameters. This is currently the largest open-source Transformer-based MoE model in the industry, featuring a total of 389 billion parameters and 52 billion active parameters. By open-sourcing the Hunyuan-Large model and revealing related technical details, we hope to inspire more researchers with innovative ideas and collectively advance the progress and application of AI technology. We welcome you to join our open-source community to explore and optimize future AI models together! ### Introduction to Model Technical Advantages #### Model - **High-Quality Synthetic Data**: By enhancing training with synthetic data, Hunyuan-Large can learn richer representations, handle long-context inputs, and generalize better to unseen data. - **KV Cache Compression**: Utilizes Grouped Query Attention (GQA) and Cross-Layer Attention (CLA) strategies to significantly reduce memory usage and computational overhead of KV caches, improving inference throughput. - **Expert-Specific Learning Rate Scaling**: Sets different learning rates for different experts to ensure each sub-model effectively learns from the data and contributes to overall performance. - **Long-Context Processing Capability**: The pre-trained model supports text sequences up to 256K, and the Instruct model supports up to 128K, significantly enhancing the ability to handle long-context tasks. - **Extensive Benchmarking**: Conducts extensive experiments across various languages and tasks to validate the practical effectiveness and safety of Hunyuan-Large.   ## Benchmark Evaluation **Hunyuan-Large pre-trained model** achieves the best overall performance compared to both Dense and MoE based competitors having similar activated parameter sizes. For aggregated benchmarks such as MMLU, MMLU-Pro, and CMMLU, Hunyuan-Large consistently achieves the best performance, confirming its comprehensive abilities on aggregated tasks. Hunyuan-Large also shows superior performance in commonsense understanding and reasoning, and classical NLP tasks such as QA and reading comprehension tasks (e.g., CommonsenseQA, PIQA, SIQA, BoolQ and TriviaQA). For the mathematics capability, Hunyuan-Large outperforms all baselines in math datasets of GSM8K and MATH, and also gains the best results on CMATH in Chinese.We also observe that Hunyuan-Large achieves the overall best performance in all Chinese tasks (e.g., CMMLU, C-Eval). | Model | LLama3.1-405B | LLama3.1-70B | Mixtral-8x22B | DeepSeek-V2 | Hunyuan-Large | |------------------|---------------|--------------|---------------|-------------|---------------| | MMLU | 85.2 | 79.3 | 77.8 | 78.5 | **88.4** | | MMLU-Pro | **61.6** | 53.8 | 49.5 | - | 60.2 | | BBH | 85.9 | 81.6 | 78.9 | 78.9 | **86.3** | | HellaSwag | - | - | **88.7** | 87.8 | 86.8 | | CommonsenseQA | 85.8 | 84.1 | 78.5 | - | **92.9** | | WinoGrande | 86.7 | 85.3 | 85.0 | 84.9 | **88.7** | | PIQA | - | - | 83.6 | 83.7 | **88.3** | | SIQA | - | - | 64.6 | - | **83.6** | | NaturalQuestions | - | - | 39.6 | 38.7 | **52.8** | | BoolQ | 80.0 | 79.4 | 87.4 | 84.0 | **92.9** | | DROP | 84.8 | 79.6 | 80.4 | 80.1 | **88.9** | | ARC-C | **96.1** | 92.9 | 91.2 | 92.4 | 95.0 | | TriviaQA | - | - | 82.1 | 79.9 | **89.2** | | CMMLU | - | - | 60.0 | 84.0 | **90.2** | | C-Eval | - | - | 59.6 | 81.7 | **91.9** | | C3 | - | - | 71.4 | 77.4 | **82.3** | | GSM8K | 89.0 | 83.7 | 83.7 | 79.2 | **92.8** | | MATH | 53.8 | 41.4 | 42.5 | 43.6 | **69.8** | | CMATH | - | - | 72.3 | 78.7 | **91.3** | | HumanEval | 61.0 | 58.5 | 53.1 | 48.8 | **71.4** | | MBPP | **73.4** | 68.6 | 64.2 | 66.6 | 72.6 | **Hunyuan-Large-Instruct achieves** consistent improvements on most types of tasks compared to LLMs having similar activated parameters, indicating the effectiveness of our post-training. Delving into the model performance in different categories of benchmarks, we find that our instruct model achieves the best performance on MMLU and MATH dataset. Notably, on the MMLU dataset, our model demonstrates a significant improvement, outperforming the LLama3.1-405B model by 2.6%. This enhancement is not just marginal but indicative of the Hunyuan-Large-Instruct’s superior understanding and reasoning capabilities across a wide array of language understanding tasks. The model’s prowess is further underscored in its performance on the MATH dataset, where it surpasses the LLama3.1-405B by a notable margin of 3.6%. Remarkably, this leap in accuracy is achieved with only 52 billion activated parameters, underscoring the efficiency of our model. | Model | LLama3.1 405B Inst. | LLama3.1 70B Inst. | Mixtral 8x22B Inst. | DeepSeekV2.5 Chat | Hunyuan-Large Inst. | |----------------------|---------------------|--------------------|---------------------|-------------------|---------------------| | MMLU | 87.3 | 83.6 | 77.8 | 80.4 | **89.9** | | CMMLU | - | - | 61.0 | 79.5 | **90.4** | | C-Eval | - | - | 60.0 | 79.9 | **88.6** | | BBH | - | - | 82.0 | **87.1** | 81.2 | | HellaSwag | - | - | 86.0 | **90.3** | 88.5 | | ARC-C | **96.9** | 94.8 | 91.5 | 92.9 | 94.6 | | DROP | - | - | 67.5 | 79.5 | **88.3** | | GPQA_diamond | **50.7** | 46.7 | 38.4 | 42.4 | 42.4 | | MATH | 73.8 | 68.0 | 51.0 | 74.7 | **77.4** | | HumanEval | 89.0 | 80.5 | 75.6 | 89.0 | **90.0** | | AlignBench | 6.0 | 5.9 | 6.2 | 8.0 | **8.3** | | MT-Bench | 9.1 | 8.8 | 8.1 | 9.0 | **9.4** | | IFEval strict-prompt | **86.0** | 83.6 | 71.2 | - | 85.0 | ### Citation If you find our work helpful, feel free to give us a cite. ``` @article{Tencent-Hunyuan-Large, title={Hunyuan-Large: An Open-Source MoE Model with 52 Billion Activated Parameters by Tencent}, author={Xingwu Sun, Yanfeng Chen, Yiqing Huang, Ruobing Xie, Jiaqi Zhu, Kai Zhang, Shuaipeng Li, Zhen Yang, Jonny Han, Xiaobo Shu, Jiahao Bu, Zhongzhi Chen, Xuemeng Huang, Fengzong Lian, Saiyong Yang, Jianfeng Yan, Yuyuan Zeng, Xiaoqin Ren, Chao Yu, Lulu Wu, Yue Mao, Tao Yang, Suncong Zheng, Kan Wu, Dian Jiao, Jinbao Xue, Xipeng Zhang, Decheng Wu, Kai Liu, Dengpeng Wu, Guanghui Xu, Shaohua Chen, Shuang Chen, Xiao Feng, Yigeng Hong, Junqiang Zheng, Chengcheng Xu, Zongwei Li, Xiong Kuang, Jianglu Hu, Yiqi Chen, Yuchi Deng, Guiyang Li, Ao Liu, Chenchen Zhang, Shihui Hu, Zilong Zhao, Zifan Wu, Yao Ding, Weichao Wang, Han Liu, Roberts Wang, Hao Fei, Xun Cao, Hai Wang, Fusheng Xiang, Mengyuan Huang, Zhiyuan Xiong, Bin Hu, Xuebin Hou, Lei Jiang, Jiajia Wu, Yaping Deng, Yi Shen, Qian Wang, Weijie Liu, Jie Liu, Meng Chen, Liang Dong, Weiwen Jia, Hu Chen, Feifei Liu, Rui Yuan, Huilin Xu, Zhenxiang Yan, Tengfei Cao, Zhichao Hu, Xinhua Feng, Dong Du, Tinghao She, Yangyu Tao, Feng Zhang, Jianchen Zhu, Chengzhong Xu, Xirui Li, Chong Zha, Wen Ouyang, Yinben Xia, Xiang Li, Zekun He, Rongpeng Chen, Jiawei Song, Ruibin Chen, Fan Jiang, Chongqing Zhao, Bo Wang, Hao Gong, Rong Gan, Winston Hu, Zhanhui Kang, Yong Yang, Yuhong Liu, Di Wang, and Jie Jiang.}, journal={arXiv:}, year={2024} } ```