GPT2 for Multiple Languages, including pretrained models. GPT2 多语言支持, 15亿参数中文预训练模型
- gpt-2
- tpu
- bert
- pretrained-models
89,572 visible repositories in the index
409–432 of 840 · Most stars
GPT2 for Multiple Languages, including pretrained models. GPT2 多语言支持, 15亿参数中文预训练模型
TranslatedMicroduck replica: the full robot built with Feetech HD-1910 servos has been verified on real hardware (standing, walking, front roll and getting up). Includes an image, a Studio web control center, CAD/BOM, assembly tutorials, circuit design files and a training platform | Microduck robot replica with real hardware demos.
Official Repo For Pixel-LLM Codebase: Sa2VA (T-PAMI-26), SAMTok (CVPR-26), VRT (Arxiv-25), SaSaSa2VA (1-st solution for LSVOS)
crypto-trading-open
[CVPR 2025] Learning Flow Fields in Attention for Controllable Person Image Generation
一个面向workbuddy / Codex 等agent 的跨境电商和国内电商通用视觉创作 Skill。我精选25个高质量案例,涵盖纯色底产品主图、场景化生活图、平铺图、电商详情图、真实场景等等,全部配完整提示词,都可以利用 GPT-Image-2 、Seedream 5.5 API生成最终效果。一键生成电商相关图片!输入产品图片和需求描述,自动生成完整的电商主图、详情页图片、社媒推广图、直播间场景图等全套视觉素材。 与众不同之处是:**Campaign Style Lock** 机制 和 **强推广** 和 **重视转化效果**。
Python GUI for uninstalling the default Windows 10 apps.
This repository contains the official implementation of the research papers, "MobileCLIP" CVPR 2024 and "MobileCLIP2" TMLR August 2025
Completely free and open-source human-like Instagram bot. Powered by UIAutomator2 and compatible with basically any Android device 5.0+ that can run Instagram - real or emulated.
🔗 Don't know what type of hash it is? Name That Hash will name that hash type! 🤖 Identify MD5, SHA256 and 300+ other hashes ☄ Comes with a neat web app 🔥
【ICML 2025 Spotlight】 Official Repo for Paper ‘’HealthGPT : A Medical Large Vision-Language Model for Unifying Comprehension and Generation via Heterogeneous Knowledge Adaptation‘’
[ICLR 2025] Automated Design of Agentic Systems
2025年全网最全即插即用模块,免费分享!CVPR2025,AAAI2025,ICLR2025,TNNLS2025,arXiv2025......包含人工智能全领域(机器学习、深度学习等),适用于图像分类、目标检测、实例分割、语义分割、全景分割、姿态识别、医学图像分割、视频目标分割、图像抠图、图像编辑、单目标跟踪、多目标跟踪、行人重识别、RGBT、图像去噪、去雨、去雾、去阴影、去模糊、超分辨率、去反光、去摩尔纹、图像恢复、图像修复、高光谱图像恢复、图像融合、图像上色、高动态范围成像、视频与图像压缩、3D点云、3D目标检测、3D语义分割、3D姿态识别等各类计算机视觉和图像处理任务,以及自然语言处理、大语言模型、多模态等其他各类人工智能相关任务。持续更新中......
[CVPR 2025] DEIM: DETR with Improved Matching for Fast Convergence
[SIGGRAPH Asia 2025] DreamO: A Unified Framework for Image Customization
A curated list of awesome resources, tools, and other shiny things for LLM prompt engineering.
看海量化回测平台 khQuant 开源版 V2.2:免费开源的 A 股量化回测桌面软件。不用开户、不用装 QMT,BaoStock / Tushare 下载数据到本地 DuckDB,Python 写策略,一键出回测报告。
[CVPR 2025] MatAnyone: Stable Video Matting with Consistent Memory Propagation
Local Laya typed decisions on Apple Core ML and Neural Engine. Validated ports, ~5 ms short decisions on M3 Max, reproducible speed and energy benchmarks.
[ACM MM 2025] FantasyTalking: Realistic Talking Portrait Generation via Coherent Motion Synthesis
[CVPR 2025] StreamingT2V: Consistent, Dynamic, and Extendable Long Video Generation from Text
HY-World 1.5: A Systematic Framework for Interactive World Modeling with Real-Time Latency and Geometric Consistency
AI 写作伙伴,点亮你的创作灵感
[EMNLP 2025 Oral] MemoryOS is designed to provide a memory operating system for personalized AI agents.