- All languages
- Assembly
- AutoHotkey
- B4X
- C
- C#
- C++
- CMake
- CSS
- Cuda
- Dart
- Dockerfile
- Fancy
- Go
- HTML
- Haskell
- Java
- JavaScript
- Jinja
- Jupyter Notebook
- Kotlin
- Lua
- MATLAB
- Makefile
- Markdown
- Mustache
- Nunjucks
- Objective-C
- PHP
- Perl
- Python
- Rich Text Format
- Roff
- Ruby
- Rust
- SCSS
- Scala
- Shell
- Svelte
- Swift
- TeX
- TypeScript
- Visual Basic 6.0
- Vue
- XSLT
- Zig
Starred repositories
aha model inference library, now supports Qwen(2.5VL/3/3VL/3.5/ASR), MiniCPM4, VoxCPM/1.5, DeepSeek-OCR/2, Hunyuan-OCR, PaddleOCR-VL/1.5, RMBG2.0, GLM(ASR-Nano-2512/OCR), Fun-ASR-Nano-2512, LFM(2/2.5)
A Rust-native claw you can trust. One binary — sandboxed, secure, auditable. Voice, memory, MCP tools, and multi-channel access built-in.
A user-friendly & efficient knowledge distillation framework for LLMs, supporting off-policy, on-policy (OPD), cross-tokenizer, multimodal, and on-policy self-distillation.
LiYing is an automated photo processing program designed for automating the post-processing workflow of ID photos in general photo studios. | LiYing 是一套适用于自动化 完成一般照相馆后期证件照处理流程的照片自动处理的程序。
megemini / llama.cpp
Forked from ggml-org/llama.cppLLM inference in C/C++
Twinkle✨: Training workbench to make your model glow.
谷歌新书Agent设计模式(agentic design patterns)最佳中文版,持续优化。附:在线阅读、pdf和epub电子书下载。
Design an MLP model to achieve the classification task on MNIST. Show the training process and classification results.
Multilingual Document Layout Parsing in a Single Vision-Language Model
CowAgent是基于大模型的超级AI助理,能主动思考和任务规划、访问操作系统和外部资源、创造和执行Skills、拥有长期记忆并不断成长,比OpenClaw更轻量和便捷。同时支持微信、飞书、钉钉、企微、QQ、公众号、网页等接入,可选择OpenAI/Claude/Gemini/DeepSeek/ Qwen/GLM/Kimi/LinkAI,能处理文本、语音、图片和文件,可快速搭建个人AI助理和企…
大模型算法岗面试题(含答案):常见问题和概念解析 "大模型面试题"、"算法岗面试"、"面试常见问题"、"大模型算法面试"、"大模型应用基础"
https://adongwanai.github.io/AgentGuide | AI Agent开发指南 | LangGraph实战 | 高级RAG | 转行大模型 | 大模型面试 | 算法工程师 | 面试题库 | 强化学习|数据合成
data engineering book
Local AI assistant, dreaming explorable worlds.
OCR model that handles complex tables, forms, handwriting with full layout.
Production ready toolkit to run AI locally
C++ OCR 练手项目(WIP) — 学习 ONNXRuntime / OpenVINO 推理与前后处理
y-trainerY-Trainer 是一个LLM模型微调训练框架。 📊 核心优势: 📉 精准对抗过拟合: 专门优化,有效解决SFT中的过拟合难题。 🧩 突破遗忘瓶颈: 无需依赖通用语料,即可卓越地保留模型的泛化能力,守住核心竞争力的同时实现专项提升!🏆
Cross Platform Lite Procedure Call - Support Linux, macOS, Windows, iOS, Android, Web Assembly, Flutter, Kotlin, Python and More