DeepSeek-VL2 is an advanced series of large Mixture-of-Experts (MoE) Vision-Language Models designed for advanced multimodal understanding. It demonstrates superior capabilities across various tasks, including visual question answering, optical character recognition, document/table/chart understanding, and visual grounding. The model series includes three variants with 1 billion, 2.8 billion, and 4.5 billion activated parameters respectively.
DeepSeek-VL2 is an advanced series of large Mixture-of-Experts (MoE) Vision-Language Models designed for advanced multimodal understanding. It demonstrates superior capabilities across various tasks, including visual question answering, optical character recognition, document/table/chart understanding, and visual grounding. The model series includes three variants with 1 billion, 2.8 billion, and 4.5 billion activated parameters respectively, achieving competitive or state-of-the-art performance with similar or fewer activated parameters compared to existing models.
Pulse is an AI-powered app designed to offer a chat-like interface that acts as a supportive companion, helping users talk about their feelings, organize their thoughts, and engage in mental health exercises. PulseAI aims to enable people to grow and better understand themselves through reflecting. Dive into intuitive conversations with our advanced AI, ready to understand and resonate with your feelings. Whether it's a moment of joy or a challenging day, PulseAI is here to chat. Set up weekly chat sessions, ensuring you have a dedicated time to check in with your emotions and well-being. It's like a coffee date, but with your mind. Engage in curated exercises designed to boost your mental clarity, resilience, and overall well-being. A mini-workout for your mind!
Mentalyc offers automated progress notes and treatment plans for mental health providers.
The Weibo User Depression Detection Dataset is a large-scale dataset for detecting depression in Weibo users. It includes user profiles, tweets, and labels indicating whether the user is depressed. The dataset is useful for researchers working on mental health and social media analysis.