Hunyuan-TurboS: Advancing Large Language Models through Mamba-Transformer Synergy and Adaptive Chain-of-Thought

As Large Language Models (LLMs) rapidly advance, we introduce Hunyuan-TurboS, a novel large hybrid Transformer-Mamba Mixture of Experts (MoE) model. It synergistically combines Mamba's long-sequence processing efficiency with Transformer's superior contextual understanding. Hunyuan-TurboS features an adaptive long-short chain-of-thought (CoT) mechanism, dynamically switching between rapid responses for simple queries and deep "thinking" modes for complex problems, optimizing computational resources. Architecturally, this 56B activated (560B total) parameter model employs 128 layers (Mamba2, Attention, FFN) with an innovative AMF/MF block pattern. Faster Mamba2 ensures linear complexity, Grouped-Query Attention minimizes KV cache, and FFNs use an MoE structure. Pre-trained on 16T high-quality tokens, it supports a 256K context length and is the first industry-deployed large-scale Mamba model. Our comprehensive post-training strategy enhances capabilities via Supervised Fine-Tuning (3M instructions), a novel Adaptive Long-short CoT Fusion method, Multi-round Deliberation Learning for iterative improvement, and a two-stage Large-scale Reinforcement Learning process targeting STEM and general instruction-following. Evaluations show strong performance: overall top 7 rank on LMSYS Chatbot Arena with a score of 1356, outperforming leading models like Gemini-2.0-Flash-001 (1352) and o4-mini-2025-04-16 (1345). TurboS also achieves an average of 77.9% across 23 automated benchmarks. Hunyuan-TurboS balances high performance and efficiency, offering substantial capabilities at lower inference costs than many reasoning models, establishing a new paradigm for efficient large-scale pre-trained models.

Hunyuan-Large: An Open-Source MoE Model with 52 Billion Activated Parameters by Tencent

In this paper, we introduce Hunyuan-Large, which is currently the largest open-source Transformer-based mixture of experts model, with a total of 389 billion parameters and 52 billion activation parameters, capable of handling up to 256K tokens. We conduct a thorough evaluation of Hunyuan-Large's superior performance across various benchmarks including language understanding and generation, logical reasoning, mathematical problem-solving, coding, long-context, and aggregated tasks, where it outperforms LLama3.1-70B and exhibits comparable performance when compared to the significantly larger LLama3.1-405B model. Key practice of Hunyuan-Large include large-scale synthetic data that is orders larger than in previous literature, a mixed expert routing strategy, a key-value cache compression technique, and an expert-specific learning rate strategy. Additionally, we also investigate the scaling laws and learning rate schedule of mixture of experts models, providing valuable insights and guidances for future model development and optimization. The code and checkpoints of Hunyuan-Large are released to facilitate future innovations and applications. Codes: https://github.com/Tencent/Hunyuan-Large Models: https://huggingface.co/tencent/Tencent-Hunyuan-Large

Large Language Model based Long-tail Query Rewriting in Taobao Search

In the realm of e-commerce search, the significance of semantic matching cannot be overstated, as it directly impacts both user experience and company revenue. Along this line, query rewriting, serving as an important technique to bridge the semantic gaps inherent in the semantic matching process, has attached wide attention from the industry and academia. However, existing query rewriting methods often struggle to effectively optimize long-tail queries and alleviate the phenomenon of "few-recall" caused by semantic gap. In this paper, we present BEQUE, a comprehensive framework that Bridges the sEmantic gap for long-tail QUEries. In detail, BEQUE comprises three stages: multi-instruction supervised fine tuning (SFT), offline feedback, and objective alignment. We first construct a rewriting dataset based on rejection sampling and auxiliary tasks mixing to fine-tune our large language model (LLM) in a supervised fashion. Subsequently, with the well-trained LLM, we employ beam search to generate multiple candidate rewrites, and feed them into Taobao offline system to obtain the partial order. Leveraging the partial order of rewrites, we introduce a contrastive learning method to highlight the distinctions between rewrites, and align the model with the Taobao online objectives. Offline experiments prove the effectiveness of our method in bridging semantic gap. Online A/B tests reveal that our method can significantly boost gross merchandise volume (GMV), number of transaction (#Trans) and unique visitor (UV) for long-tail queries. BEQUE has been deployed on Taobao, one of most popular online shopping platforms in China, since October 2023.