OpenManus
OpenManus is an open-source project that allows users to achieve Manus-like functionality without an invite code. It provides a simple implementation for creating and customizing AI agents.
詳細な紹介
OpenManus is an open-source implementation of Manus, built by the MetaGPT contributors. It allows you to create and customize your own AI agents without needing an invite code. The project was developed within 3 hours by the team members @mannaandpoem, @XiangJinyu, @MoshiQAQ, and @didiforgithub. OpenManus supports various LLM APIs and provides configuration options for different models.
もっとLLM
Hugging Face Dataset - bfuzzy1/gunny_x
Every veteran knows and has had a 'Gunny': Semper Fidelis. This dataset is designed for conversational AI systems to assist veterans from various military branches, including U.S. and U.K. armed forces.
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.
Psy-Insight: Mental Health Counseling Dataset
Psy-Insight is a bilingual, interpretable multi-turn dataset for mental health counseling dialogues. It includes 6,208 rounds of multi-turn counseling dialogues in English and 5,776 rounds in Chinese, annotated with step-by-step reasoning labels and multi-task labels. This dataset is designed to support the application of large language models in mental health and is suitable for tasks such as emotion classification and psychological treatment interpretation.