Accessible large language models via k-bit quantization for PyTorch.
- llm
- machine-learning
- pytorch
- qlora
60,621 visible repositories in the index
169–192 of 798 · Most stars
Accessible large language models via k-bit quantization for PyTorch.
TranslatedA Trojan proxy written in Go. An unidentifiable mechanism that helps you bypass GFW. Supports multiplexing, routing, CDN relay, and Shadowsocks obfuscation plugins; multi-platform, no dependencies. https://p4gefau1t.github.io/trojan-go/
The plugin manager for zsh.
The open-source, privacy-friendly CAPTCHA you host yourself. Bots and AI agents out, people in.
Semantic cache for LLMs. Fully integrated with LangChain and llama_index.
Package Management for Golang
Disque is a distributed message broker
:trophy: Automate versioning and CHANGELOG generation, with semver.org and conventionalcommits.org
Semantic Versioning Specification
Portfolio analytics for quants, written in Python
Fly through your shell history. Great Scott!
ODS V3 Pre-Release: Public testing and refinement ahead of the official V3 launch. Turn your PC, Mac, or Linux box into a private AI server.
A debugging and profiling tool that can trace and visualize python code execution
The QuantLib C++ library
Semantic Image Synthesis with SPADE
A shell for wayland compositors
A Collection of Variational Autoencoders (VAE) in PyTorch.
TranslatedTSP: a self-hosted, zero-maintenance quantitative workbench for A-shares covering "custom strategies + monitoring + backtesting" | LLM capabilities drive strategy customization + individual stock analysis + post-trade review | Freely connect third-party data sources and personalized extended data | Personal open-source project
ClamAV - Documentation is here: https://docs.clamav.net
Collection of notebooks about quantitative finance, with interactive python code.
A minimal programming example for a chat server
BleachBit system cleaner for Windows and Linux
Desktop Telegram client with good customization and Ghost mode.
TranslatedMore and more websites have anti-crawler features: some hide key data in images, and some use inhuman CAPTCHAs. This is a repository of anti-anti-crawler code, built to improve skills by contending with websites of different characteristics (with no malicious intent). (Submissions of websites that are hard to scrape are welcome.) (The project is paused due to work reasons.)