#
Starred repositories
401
results
for source starred repositories
Clear filter
《How to Scale Your Model》中文翻译项目 - 智能技术文档翻译工具。专为大语言模型扩展技术书籍设计，突破长文档翻译瓶颈，完美保留数学公式、代码块格式。采用占位符机制+分层翻译策略，基于Gemini API提供高质量翻译。Python+crawl4ai技术栈，支持批量处理和增量更新。
《Build a Large Language Model (From Scratch)》是一本深入探讨大语言模型原理与实现的电子书，适合希望深入了解 GPT 等大模型架构、训练过程及应用开发的学习者。为了让更多中文读者能够接触到这本极具价值的教材，我决定将其翻译成中文，并通过 GitHub 进行开源共享。
中文古籍刻本風格直排電子書製作工具 Chinese Ancient eBooks Generator
Integrate the DeepSeek API into popular softwares
Large-scale 3D graph vis software written in Rust.
A fork of https://github.com/kamichikoichi/kage-engine, used in https://github.com/ge9/NazonoMincho. This does *not* function as an well-formed JavaScript library by itself. Use https://github.com/…
Real time interactive streaming digital human
ChatPilot: Chat Agent Web UI，实现Chat对话前端，支持Google搜索、文件网址对话（RAG）、代码解释器功能，复现了Kimi Chat(文件，拖进来；网址，发出来)。
A Chinese serif font derived from IPAmj Mincho. 一款衍生于「IPAmj明朝」的中文宋体字型。
Pic Smaller – Compress JPEG, PNG, WEBP, AVIF, SVG and GIF images intelligently
A @ClickHouse fork that supports high-performance vector search and full-text search.
A simple command-line utility for Linux, for extracting text from EPUB documents.
Booktype is a free, open source platform that produces beautiful, engaging books formatted for print, Amazon, iBooks and almost any ereader within minutes.
Curated tutorials and resources for Large Language Models, AI Painting, and more.
Netease Youdao's open-source embedding and reranker models for RAG products.
A tool for automatic phoneme transcription
Tools related to mispronunciation diagnosis detection (MDD) systems.
A local chatbot fine-tuned by bilibili user comments.
Using FCN to segment the book's content and background, then dewarping the pages,
CRAFT(Baek et al., 2019) model training code
[CVPR 2024] Official implementation of "ViTamin: Designing Scalable Vision Models in the Vision-language Era"
High-speed Large Language Model Serving for Local Deployment
Implementation of Band Split Roformer, SOTA Attention network for music source separation out of ByteDance AI Labs
InstantID: Zero-shot Identity-Preserving Generation in Seconds 🔥