Repository Showcase
A curated collection of interesting GitHub repositories
deepseek-ai/DeepSeek-VL2
DeepSeek-VL2, a vision-language AI modelfor tasks like visual question answeringand OCR
Related repos
- An OCR model for visual text compression
- unified multimodal model for both understanding and generating images and text
- DeepSeek-V3, a Mixture-of-Experts language model with 671B parameters and 37B active per token, focused on math and coding tasks
- DeepClaude: Combines DeepSeek R1 and Claude 3.5 for AI reasoning and coding
- vision-language model using reinforcement learning for visual understanding tasks
- agentic language model for deep research and reasoning tasks
- fast vision-language model for on-device AI
- DeepSeek-R1 GitHub repo with model code and info
- VILA: Visual language models for AI tasks
- Not new, but still interesting
