Tiny Model, Big Logic: Diversity-Driven Optimization Elicits Large-Model Reasoning Ability in VibeThinker-1.5B
- ai
- huggingface
- language-model
- transformer
111,820 visible repositories in the index
913–936 of 1,948 · Most stars
Tiny Model, Big Logic: Diversity-Driven Optimization Elicits Large-Model Reasoning Ability in VibeThinker-1.5B
Distributed, MVCC SQLite that runs on FoundationDB.
UCCL is an efficient communication library for GPUs, covering collectives, P2P (e.g., KV cache transfer, RL weight transfer), and EP (e.g., GPU-driven)
Spring,SpringBoot 2.0,SpringMVC,Mybatis,mybatis-plus,motan/dubbo分布式,Redis缓存,Shiro权限管理,Spring-Session单点登录,Quartz分布式集群调度,Restful服务,QQ/微信登录,App token登录,微信/支付宝支付;日期转换、数据类型转换、序列化、汉字转拼音、身份证号码验证、数字转人民币、发送短信、发送邮件、加密解密、图片处理、excel导入导出、FTP/SFTP/fastDFS上传下载、二维码、XML读写、高精度计算、系统配置工具类等等。
Kubernetes History Visualization
The repository host gives no description.
solo-learn: a library of self-supervised methods for visual representation learning powered by Pytorch Lightning
A cross platform way to express data transformation, relational algebra, standardized record expression and plans.
Bundler Structure from Motion Toolkit
This repository includes all the interview preparation questions for Amazon SDE role
Open-source ETL/ELT you deploy on your own servers or cloud. Built on DuckDB: no-code/low-code visual pipelines or SQL, 427 components, dbt, CDC, data quality, reverse ETL, lineage, MCP for AI agents. No vendor cloud, no per-row billing.
[CVPR 2023] Official implementation of the paper "Mask DINO: Towards A Unified Transformer-based Framework for Object Detection and Segmentation"
Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization
[ICLR'23 Spotlight & ECCV'24 & IJCV'24] MapTR: Structured Modeling and Learning for Online Vectorized HD Map Construction
"Retinexformer: One-stage Retinex-based Transformer for Low-light Image Enhancement" (ICCV 2023 Top-10 Cited 🏆) & (NTIRE 2024 Runner-Up 🏆) & (NTIRE 2025 Winner 🏆) & (NTIRE 2026 Winner 🏆)
VRT: A Video Restoration Transformer (official repository)
a fast and user-friendly runtime for transformer inference (Bert, Albert, GPT2, Decoders, etc) on CPU and GPU.
Open-source Higgsfield on ComfyUI: 120 image, video, VFX and audio apps, every model open weights; runs on Modal or your own GPU
Query processing and transformation of array-backed data tables.
Implementation of SoundStorm, Efficient Parallel Audio Generation from Google Deepmind, in Pytorch
MLeap: Deploy ML Pipelines to Production
Photogrammetry Guide. Photogrammetry is widely used for Aerial surveying, Agriculture, Architecture, 3D Games, Robotics, Archaeology, Construction, Emergency management, and Medical.
Develop input methods for Windows easily with Python and node.js
Super fast sftp/ftp extension for VS Code