In this report, we present a series of math-specific large language models: Qwen2. 5-Math
and Qwen2. 5-Math-Instruct-1.5 B/7B/72B. The core innovation of the Qwen2. 5 series lies in …

Mathematical reasoning presents a significant challenge for Large Language Models
(LLMs) due to the extensive and precise chain of reasoning required for accuracy. Ensuring …

Numina is an open AI4Maths initiative dedicated to advancing both artificial and human
intelligence in the field of mathematics. In this paper, we present the NuminaMath dataset, a …

Supervised fine-tuning (SFT) is crucial for aligning Large Language Models (LLMs) with
human instructions. The primary goal during SFT is to select a small yet representative …

Self-correction is a novel method that can stimulate the potential reasoning abilities of large
language models (LLMs). It involves detecting and correcting errors during the inference …

With the rise of multimodal applications, instruction data has become critical for training
multimodal language models capable of understanding complex image-based queries …

Continual pre-training (CPT) has been an important approach for adapting language models
to specific domains or tasks. To make the CPT approach more traceable, this paper presents …

Recently, test-time scaling has garnered significant attention from the research community,
largely due to the substantial advancements of the o1 model released by OpenAI. By …

Adapting general large language models (LLMs) to specialized domains presents great
challenges due to varied data distributions. This adaptation typically requires continual pre …

Large language models (LLMs) are still struggling in aligning with human preference in
complex tasks and scenarios. They are prone to overfit into the unexpected patterns or …