On the Robustness of Answer Formats in Medical Reasoning Models Paper • 2509.20866 • Published Sep 25, 2025 • 2
Typhoon-S: Minimal Open Post-Training for Sovereign Large Language Models Paper • 2601.18129 • Published Jan 26 • 11
ThaiSafetyBench Collection ThaiSafetyBench, a benchmark of 1,954 malicious Thai prompts designed to evaluate large language model (LLM) safety within Thai language. • 3 items • Updated 8 days ago
typhoon-ai/typhoon-s-thaillm-8b-instruct-research-preview Text Generation • 8B • Updated 10 days ago • 1.37k • 3
Instruction & Reasoning Collection Datasets for instruction following, code, and reasoning. • 13 items • Updated 14 days ago • 7