rednote-hilab/dots.vlm1

Vision-language model built on DeepSeek V3

View on index · View in 3D Map

Related repos

• DeepSeek-VL2, a vision-language AI modelfor tasks like visual question answeringand OCR
• unified multimodal model for both understanding and generating images and text
• DeepClaude: Combines DeepSeek R1 and Claude 3.5 for AI reasoning and coding
• Document retrieval with vision language models
• An OCR model for visual text compression
• DeepSeek-R1 GitHub repo with model code and info
• VILA: Visual language models for AI tasks
• Jupyter replacement with an AI agent