Kimi k1.5
Kimi k1.5 is an advanced multi-modal model trained with reinforcement learning (RL) that achieves state-of-the-art reasoning performance across multiple benchmarks and modalities. It outperforms existing models such as GPT-4o and Claude Sonnet 3.5 in short-CoT tasks by a large margin and matches OpenAI's o1 in long-CoT performance.
Detailed Introduction
Kimi k1.5 is an o1-level multi-modal model trained with reinforcement learning (RL) that achieves state-of-the-art reasoning performance across multiple benchmarks and modalities. It outperforms existing models such as GPT-4o and Claude Sonnet 3.5 in short-CoT tasks by a large margin and matches OpenAI's o1 in long-CoT performance. Key ingredients of Kimi k1.5 include long context scaling, improved policy optimization, a simplistic RL framework, and multi-modal training.
MoreAI
LifeHack - Get the most out of life. Fast.
From Questions To Actions Transform your mindset and achieve your goals with the Lifehack App. Access AI and human coaching, reflection tools, and a LifeHack empowers time-strapped individuals to boost productivity, transform their mindset, achieve goals, and gain more time for what truly matters.
Emotional First Aid Raw Dataset: Psychological Counseling QA Raw Corpus
The Emotional First Aid Raw Dataset is a collection of raw, unannotated psychological counseling Q&A data, designed to support research in AI applications for mental health. It contains over 172,000 topics with 2,381,273 messages, totaling 44,514,786 characters, providing a rich source of data for natural language processing and AI development.
Stamina Expert-Backed AI Therapy | Your AI Mental Health Ally
Stamina AI is your 24/7 mental health ally with personalized, evidence-based therapy, supported by over 200 mental health professionals. Embark on a transformative journey with our product designed for up to 1000 tailored sessions. Join 6,500+ Individuals Prioritizing Their Mental Health With Us. Accessible Anytime, Personalized for You. Free During Testing.