Open-weights large language models remain difficult to deploy for Thai due to unstable generation under complex instructions, despite strong English performance. To mitigate these limitations, We present SiamGPT-32B, an open-weights model based on Qwen3-32B, fine-tuned with a Quality-First strategy emphasizing curated supervision over data scale. The fine-tuning pipeline combines translated high-complexity English instruction data with a Thai-adapted AutoIF framework for instruction and linguistic constraints. Using supervised fine-tuning only, without continual pretraining or corpus expansion, SiamGPT-32B improves instruction adherence, multi-turn robustness, and linguistic stability. Evaluations on the SEA-HELM benchmark show that SiamGPT-32B achieves the strongest overall performance among similar-scale open-weights Thai models, with consistent gains in instruction following, multi-turn dialogue, and natural language understanding.

翻译：尽管在英语任务上表现出色，但开源大语言模型在复杂指令下生成不稳定，导致其难以在泰语场景中部署。为缓解这些限制，我们提出了SiamGPT-32B——一个基于Qwen3-32B的开源模型，采用"质优优先"策略进行微调，强调精选监督数据而非数据规模。该微调流程结合了翻译的高复杂度英语指令数据，以及适用于泰语的AutoIF框架来施加指令与语言约束。仅通过监督微调（未进行持续预训练或语料扩展），SiamGPT-32B在指令遵循、多轮对话鲁棒性和语言稳定性方面均获得提升。在SEA-HELM基准测试中的评估表明，SiamGPT-32B在同等规模的开源泰语模型中取得了最佳综合性能，在指令遵循、多轮对话和自然语言理解任务上均保持稳定优势。