ai
Official repository of "SAMURAI: Adapting Segment Anything Model for Zero-Shot Visual Tracking with Motion-Aware Memory"
中文文本分类，TextCNN，TextRNN，FastText，TextRCNN，BiLSTM_Attention，DPCNN，Transformer，基于pytorch，开箱即用。
TensorFlow code and pre-trained models for BERT
DeepSeek Coder: Let the Code Write Itself
DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model
《自动驾驶中的SLAM技术》对应开源代码 1. 添加详细代码注释 2. 添加深蓝第一期课后习题与大作业的修改（若想要原始的激光SLAM定位与建图的效果，请前往高博github拉取最新分支）
OCR & Document Extraction using vision models
🚀🚀 「大模型」2小时完全从0训练26M的小参数GPT！🌏 Train a 26M-parameter GPT from scratch in just 2h!
🚀 「大模型」1小时从0训练26M参数的视觉多模态VLM！🌏 Train a 26M-parameter VLM from scratch in just 1 hours!
The official repo of MiniMax-Text-01 and MiniMax-VL-01, large-language-model & vision-language-model based on Linear Attention
DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
DeepSeek-VL: Towards Real-World Vision-Language Understanding
A curated list of open-source projects related to DeepSeek Coder
[ICLR 2024] Official implementation of DreamCraft3D: Hierarchical 3D Generation with Bootstrapped Diffusion Prior
Janus-Series: Unified Multimodal Understanding and Generation Models
DeepSeek LLM: Let there be answers
DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models
《神经网络与深度学习》 邱锡鹏著 Neural Network and Deep Learning
中文自然语言处理工具包 Toolkit for Chinese natural language processing
fastNLP: A Modularized and Extensible NLP Framework. Currently still in incubation.
[NeurIPS 2025] YOLOv12: Attention-Centric Real-Time Object Detectors
YOLOv10: Real-Time End-to-End Object Detection [NeurIPS 2024]
YOLOv3 in PyTorch > ONNX > CoreML > TFLite
FlashMLA: Efficient Multi-head Latent Attention Kernels