T
timhigins
Article URL: VibeThinker-3B: Exploring the Frontier of Verifiable Reasoning in Small Language Models
Comments URL: VibeThinker: 3B param model that beats Opus 4.5 on reasoning with novel SFT+GRPO | Hacker News
Points: 161
# Comments: 58
Continue reading...
Comments URL: VibeThinker: 3B param model that beats Opus 4.5 on reasoning with novel SFT+GRPO | Hacker News
Points: 161
# Comments: 58
Continue reading...