DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models Paper โข 2402.03300 โข Published Feb 5, 2024 โข 139
Whisper Release Collection Whisper includes both English-only and multilingual checkpoints for ASR and ST, ranging from 38M params for the tiny models to 1.5B params for large. โข 12 items โข Updated Sep 13, 2023 โข 148
gpt-oss Collection Open-weight models designed for powerful reasoning, agentic tasks, and versatile developer use cases. โข 2 items โข Updated Aug 7, 2025 โข 405
gpt-oss-safeguard Collection gpt-oss-safeguard-120b and gpt-oss-safeguard-20b are safety reasoning models built-upon gpt-oss โข 2 items โข Updated Oct 29, 2025 โข 59
Metacognitive Reuse: Turning Recurring LLM Reasoning Into Concise Behaviors Paper โข 2509.13237 โข Published Sep 16, 2025 โข 2 โข 1