A project structure aware autonomous software engineer aiming for autonomous program improvement. Resolved 37.3% tasks (pass@1) in SWE-bench lite and 46.2% tasks (pass@1) in SWE-bench verified with each task costs less than $0.7.
Repository Index
142,273 visible repositories in the index
121–144 of 918 · Most stars
Largest multi-label image database; ResNet-101 model; 80.73% top-1 acc on ImageNet
PyTorch implementation of TabNet paper : https://arxiv.org/pdf/1908.07442.pdf
- pytorch
- deep-neural-networks
- machine-learning-library
- tabular-data
🔥🔥🔥 专注于YOLO11,YOLOv8、TYOLOv12、YOLOv10、RT-DETR、YOLOv7、YOLOv5改进模型,Support to improve backbone, neck, head, loss, IoU, NMS and other modules🚀
- yolov5
- backbone
- pytorch
- transformer
J-Space Cognition Suite — a model-agnostic inference-time control suite for deep reasoning, long-horizon work, verification, and recovery. Based on Anthropic's J-space global workspace research.
Unleash Next-Level AI! 🚀 💻 Code Generation: DeepSeek r1 + Claude 3.7 Sonnet - Unparalleled Performance! 📝 Content Creation: DeepSeek r1 + Gemini 2.5 Pro - Superior Quality! 🔌 OpenAI-Compatible. 🌊 Streaming & Non-Streaming Support. ✨ Experience the Future of AI – Today! Click to Try Now! ✨
An XCode project template to build universal frameworks (arm7, arm7s, and simulator) for iOS / iPhone.
owllook-小说搜索引擎
A Web UI for easy subtitle using whisper model.
- ai
- open-source
- python
- web-ui
Serve large Qwen models fast on the GPUs you actually own. Qwen3.8-27B on a single 24 GB card with vLLM: 127 tok/s single-user (381 when the answer quotes the prompt), ~1,035 tok/s at 64 concurrent, 150k-262k context. vLLM patches, requant pipeline, benchmarks.
- kv-cache
- llm-inference
- local-llm
- quantization
An offical implementation of PatchTST: "A Time Series is Worth 64 Words: Long-term Forecasting with Transformers." (ICLR 2023) https://arxiv.org/abs/2211.14730
The fastest way to run Qwen 3.8 Flash Next, Qwen 3.8 27B and Ternary Bonsai 2 27B on a Mac: 125 tok/s in OpenCode on an M5 Max, and a 27B model on 16 GB Macs. Native MTP speculative decoding on Apple Silicon, exact at any temperature. OpenAI and Anthropic compatible local server.
- apple-silicon
- local-ai
- mlx
- mtp
ASC is a super FAST and lightweight Android decompiler designed for Agents/Mobile Researchers.
- android
- decompilation
- decompile
- decompiler
PyTorch version of the paper 'Enhanced Deep Residual Networks for Single Image Super-Resolution' (CVPRW 2017)
An agent capable of self-evolving and dynamically hardening security
- agent
- hermes
- open-claw
Run the full 2.78-trillion-parameter Kimi K3 model, DeepSeek V4.1 Flash or GLM-5.3-Flash beyond available RAM by streaming activated weights directly from NVMe. A dependency-free, embeddable C inference engine.
PyTorch implementation of JiT https://arxiv.org/abs/2511.13720
快速提取音视频内容,整理成一份结构化的markdown笔记
2026年稳定高速VPN推荐:40款性价比翻墙梯子完全指南,每周核查跑路与价格。翻墙梯子/科学上网/机场测评,解锁 YouTube、Netflix、TikTok、ChatGPT,适用 Clash、V2ray、小火箭、sing-box,支持 Windows、Mac、iOS、安卓、路由器
- clash
- shadowsocks
- ssr
- trojan
Community recipes for serving LLMs on RTX 3090/4090/5090 CUDA gpus. Multi-engine (vLLM, sglang, llama.cpp and other custom engines) and model-agnostic. Currently shipping Qwen3.8-27B Qwen3.6 35B Gemma 4 26B Gemma 4 31B configs for 1×/2×/4x/8x cards.
兜哥出品 <一本开源的NLP入门书籍>
Members of the United States Congress, 1789-Present, in YAML/JSON/CSV, as well as committees, presidents, and vice presidents.
A Keras implementation of CapsNet in NIPS2017 paper "Dynamic Routing Between Capsules". Now test error = 0.34%.
- keras
- capsnet
- capsule
- capsnet-keras
High Fidelity Detection Mechanism for RSC/Next.js RCE (CVE-2025-55182 & CVE-2025-66478)