7 papers
Optimization Hyper-parameter Laws for Large Language Models
Xingyu Xie, Kuangyu Ding, Shuicheng Yan +2
Large Language Models have driven significant AI advancements, yet their training is resource-intensive and highly sensitive to hyper-parameter selection. While scaling laws provid…
Stacked from One: Multi-Scale Self-Injection for Context Window Extension
Wei Han, Pan Zhou, Soujanya Poria +1
The limited context window of contemporary large language models (LLMs) remains a primary bottleneck for their broader application across diverse domains. Although continual pre-tr…
Skywork-Reward: Bag of Tricks for Reward Modeling in LLMs
Chris Yuhao Liu, Liang Zeng, Jiacai Liu +6
In this report, we introduce a collection of methods to enhance reward modeling for LLMs, focusing specifically on data-centric techniques. We propose effective data selection and…
Q*: Improving Multi-step Reasoning for LLMs with Deliberative Planning
Chaojie Wang, Yanchen Deng, Zhiyi Lyu +4
Large Language Models (LLMs) have demonstrated impressive capability in many natural language tasks. However, the auto-regressive generation process makes LLMs prone to produce err…
Skywork-Math: Data Scaling Laws for Mathematical Reasoning in Large Language Models -- The Story Goes On
Liang Zeng, Liangjun Zhong, Liang Zhao +9
In this paper, we investigate the underlying factors that potentially enhance the mathematical reasoning capabilities of large language models (LLMs). We argue that the data scalin…
Skywork-MoE: A Deep Dive into Training Techniques for Mixture-of-Experts Language Models
Tianwen Wei, Bo Zhu, Liang Zhao +13
In this technical report, we introduce the training methodologies implemented in the development of Skywork-MoE, a high-performance mixture-of-experts (MoE) large language model (L…