deepseek-ai/DeepSeek-V3.2-Exp
Model with sparse attention for long-context scenarios
View on index · View in 3D Map
Related repos
- DeepSeek-R1 GitHub repo with model code and info
- DeepSeek-VL2, a vision-language AI modelfor tasks like visual question answeringand OCR
- open-source language and vision models with huge context window and hybrid attention
- DeepClaude: Combines DeepSeek R1 and Claude 3.5 for AI reasoning and coding
- Not new, but still interesting
- unified multimodal model for both understanding and generating images and text
- n8n node for DeepSeek AI automations
- DeepEP — communication library for Mixture-of-Experts and expert parallelism, with all-to-all GPU kernels and low-precision support
- World’s first open-weight hybrid-attention reasoning model with 1M token context and 456B parameters
