两款泰国语大模型，分别强化通用能力与推理能力。
OpenThaiGPT 1.6 and R1: Thai-Centric Open Source and Reasoning Large Language Models
- OTG-1.6用任务算术融合提升泛化，OTG-R1按多阶段训练结合少即是多推理假说
- 在泰语任务上表现优于同类开源模型，性能达新标准
- 适合需要高精度泰语理解与逻辑推理的应用场景
我们提出两款面向泰语的开源大语言模型——OTG-1.6与OTG-R1。OTG-1.6采用任务算术模型融合方法，旨在提升模型的泛化能力；OTG-R1则结合多阶段训练与“少即是多”推理假说（LIMO），增强复杂推理能力。在多项基准测试中，两款模型均在泰语任务上表现优异，性能达到与更大规模开源泰语模型相当的水平。本文详述了模型设计、训练流程、评测设置与结果，展示了相比前代模型的显著提升，并为泰语大模型设立了新的性能标杆。
原文摘要 · Abstract (English)
We present OpenThaiGPT 1.6 and R1 (OTG-1.6 and OTG-R1), Thai-centric Large Language Models (LLMs) developed through distinct methodologies to enhance generalization and reasoning capabilities. OTG-1.6 employs Task Arithmetic model merging for broad generalization, while OTG-R1 integrates multi-stage training with the Less-Is-More Reasoning Hypothesis (LIMO) for advanced reasoning. Benchmark evaluations demonstrate superior performance across Thai language tasks, achieving competitive results against larger-scale open-source Thai LLMs. This paper details the proposed models, training processes, benchmarks, and results, highlighting improvements over previous models and establishing new performance standards for Thai-centric LLMs.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。