Sign in

Repository Index

111,820 visible repositories in the index

Tags: All Tags
Tags

A repository shows when it has any selected Tag.

Filters (1)

Filters

Clear all filters

1–24 of 204 · Most stars

RWKV (pronounced RwaKuv) is an RNN with great LLM performance, which can also be directly trained like a GPT transformer (parallelizable). We are at RWKV-7 "Goose". So it's combining the best of RNN and transformer - great performance, linear time, constant space (no kv-cache), fast training, infinite ctx_len, and free sentence embedding.

Plumb a PDF for detailed information about each char, rectangle, line, et cetera — and easily extract text and tables.

  • pdf
  • pdf-parsing
  • table-extraction

JiuwenSwarm is an intelligent AI Agent built on openJiuwen. It extends the powerful capabilities of large language models directly to your fingertips through various communication apps you use daily.

Fast, correct Python JSON library supporting dataclasses, datetimes, and numpy

  • json
  • python
  • rust
  • serialization

Translatedpycorrector is a toolkit for text error correction. Text error correction, implementing applications of models such as Kenlm, T5, MacBERT, ChatGLM3, and Qwen2.5 in error correction scenarios, ready to use out of the box.

  • spelling-errors
  • error-correction
  • pycorrector
  • kenlm

ACI.dev is the open source tool-calling platform that hooks up 600+ tools into any agentic IDE or custom AI agent through direct function calling or a unified MCP server. The birthplace of VibeOps.

Official Repository: Telegram bot which can download direct links, torrents, nzb, google drive, telegram document, any file/folder from rclone supported clouds, all yt-dlp supported sites and jdownloader supported sites, then upload them to google drive, telegram cloud or to one of rclone supported clouds

  • mirror
  • leech
  • clone
  • mega

[ICML 2024] Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model

CnOCR: Awesome Chinese/English OCR Python toolkits based on PyTorch. It comes with 20+ well-trained models for different application scenarios and can be used directly after installation. 【基于 PyTorch/MXNet 的中文/英文 OCR Python 包。】

  • ocr
  • ocr-python
  • pytorch
  • chinese-character-recognition

FireRed-OpenStoryline is an AI video editing agent that transforms manual editing into intention-driven directing through natural language interaction, LLM-powered planning, and precise tool orchestration. It facilitates transparent, human-in-the-loop creation with reusable Style Skills for consistent, professional storytelling.