Qwen2.5-1M Technical Report

• URL: http://arxiv.org/abs/2501.15383v1
• Date: Sun, 26 Jan 2025 03:47:25 GMT
• Title: Qwen2.5-1M Technical Report
• Authors: An Yang, Bowen Yu, Chengyuan Li, Dayiheng Liu, Fei Huang, Haoyan Huang, Jiandong Jiang, Jianhong Tu, Jianwei Zhang, Jingren Zhou, Junyang Lin, Kai Dang, Kexin Yang, Le Yu, Mei Li, Minmin Sun, Qin Zhu, Rui Men, Tao He, Weijia Xu, Wenbiao Yin, Wenyuan Yu, Xiafei Qiu, Xingzhang Ren, Xinlong Yang, Yong Li, Zhiying Xu, Zipeng Zhang,
• Abstract summary: We introduce Qwen2.5-1M, a series of models that extend the context length to 1 million tokens. By leveraging our inference framework, the Qwen2.5-1M models achieve a remarkable 3x to 7x prefill speedup.
• Score: 72.09755998661568
• License:
• Abstract: We introduce Qwen2.5-1M, a series of models that extend the context length to 1 million tokens. Compared to the previous 128K version, the Qwen2.5-1M series have significantly enhanced long-context capabilities through long-context pre-training and post-training. Key techniques such as long data synthesis, progressive pre-training, and multi-stage supervised fine-tuning are employed to effectively enhance long-context performance while reducing training costs. To promote the use of long-context models among a broader user base, we present and open-source our inference framework. This framework includes a length extrapolation method that can expand the model context lengths by at least four times, or even more, without additional training. To reduce inference costs, we implement a sparse attention method along with chunked prefill optimization for deployment scenarios and a sparsity refinement method to improve precision. Additionally, we detail our optimizations in the inference engine, including kernel optimization, pipeline parallelism, and scheduling optimization, which significantly enhance overall inference performance. By leveraging our inference framework, the Qwen2.5-1M models achieve a remarkable 3x to 7x prefill speedup in scenarios with 1 million tokens of context. This framework provides an efficient and powerful solution for developing applications that require long-context processing using open-source models. The Qwen2.5-1M series currently includes the open-source models Qwen2.5-7B-Instruct-1M and Qwen2.5-14B-Instruct-1M, as well as the API-accessed model Qwen2.5-Turbo. Evaluations show that Qwen2.5-1M models have been greatly improved in long-context tasks without compromising performance in short-context scenarios. Specifically, the Qwen2.5-14B-Instruct-1M model significantly outperforms GPT-4o-mini in long-context tasks and supports contexts eight times longer.

Related papers

• Qwen2.5 Technical Report [122.13958993185952]
  We introduce Qwen2.5, a comprehensive series of large language models (LLMs) designed to meet diverse needs. Compared to previous iterations, Qwen 2.5 has been significantly improved during both the pre-training and post-training stages. Open-weight offerings include base and instruction-tuned models, with quantized versions available. For hosted solutions, the proprietary models currently include two mixture-of-experts (MoE) variants: Qwen2.5-Turbo and Qwen2.5-Plus.
  arXiv  Detail & Related papers  (2024-12-19T17:56:09Z)
• Enhancing the Reasoning Ability of Multimodal Large Language Models via Mixed Preference Optimization [65.64108848398696]
  We introduce a preference optimization process to enhance the multimodal reasoning capabilities of MLLMs. We develop a simple yet effective method, termed Mixed Preference Optimization (MPO), which boosts multimodal CoT performance. Our model, InternVL2-8B-MPO, achieves an accuracy of 67.0 on MathVista, outperforming InternVL2-8B by 8.7 points and achieving performance comparable to the 10x larger InternVL2-76B.
  arXiv  Detail & Related papers  (2024-11-15T18:59:27Z)
• EPS-MoE: Expert Pipeline Scheduler for Cost-Efficient MoE Inference [49.94169109038806]
  This paper introduces EPS-MoE, a novel expert pipeline scheduler for MoE that surpasses the existing parallelism schemes. Our results demonstrate at most 52.4% improvement in prefill throughput compared to existing parallel inference methods.
  arXiv  Detail & Related papers  (2024-10-16T05:17:49Z)
• Correlation-Aware Select and Merge Attention for Efficient Fine-Tuning and Context Length Extension [21.729875191721984]
  We introduce correlation-aware selection and merging mechanisms to facilitate efficient sparse attention. We also propose a novel data augmentation technique involving positional encodings to enhance generalization to unseen positions. Our method achieves 100% accuracy on the passkey task with a context length of 4M and maintains stable perplexity at a 1M context length.
  arXiv  Detail & Related papers  (2024-10-05T15:59:32Z)
• 1.5-Pints Technical Report: Pretraining in Days, Not Months -- Your Language Model Thrives on Quality Data [0.0]
  This paper presents a compute-efficient approach to pre-training a Language Model-the "1.5-Pints"-in only 9 days. Based on MT-Bench (a benchmark that emulates human judgments), 1.5-Pints outperforms Apple's OpenELM and Microsoft's Phi. This is achieved by a carefully curated pre-training dataset of 57 billion tokens, using a mix of automated and manual human review.
  arXiv  Detail & Related papers  (2024-08-07T02:14:52Z)
• LongSkywork: A Training Recipe for Efficiently Extending Context Length in Large Language Models [61.12177317970258]
  LongSkywork is a long-context Large Language Model capable of processing up to 200,000 tokens. We develop two novel methods for creating synthetic data. LongSkywork achieves outstanding performance on a variety of long-context benchmarks.
  arXiv  Detail & Related papers  (2024-06-02T03:34:41Z)
• DSEE: Dually Sparsity-embedded Efficient Tuning of Pre-trained Language Models [152.29364079385635]
  As pre-trained models grow bigger, the fine-tuning process can be time-consuming and computationally expensive. We propose a framework for resource- and parameter-efficient fine-tuning by leveraging the sparsity prior in both weight updates and the final model weights. Our proposed framework, dubbed Dually Sparsity-Embedded Efficient Tuning (DSEE), aims to achieve two key objectives: (i) parameter efficient fine-tuning and (ii) resource-efficient inference.
  arXiv  Detail & Related papers  (2021-10-30T03:29:47Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.