Inference and training library for high-quality TTS models.

Speech To Speech: an effort for an open-sourced and modular GPT4-o

Umami is a simple, fast, privacy-focused alternative to Google Analytics.

aka "Bayesian Methods for Hackers": An introduction to Bayesian methods probabilistic programming with a computation/understanding-first, mathematics-second point of view. All in pure Python ;)

Statsmodels: statistical modeling and econometrics in Python

VIP cheatsheets for Stanford's CS 229 Machine Learning

Python-based research interface for blackbox and hyperparameter optimization, based on the internal Google Vizier Service.

Nmap - the Network Mapper. Github mirror of official SVN repository.

An awesome & curated list of best LLMOps tools for developers

Official inference repo for FLUX.1 models

🚀 KIMI AI 长文本大模型逆向API白嫖测试【特长：长文本解读整理】，支持高速流式输出、智能体对话、联网搜索、长文档解读、图像OCR、多轮对话，零配置部署，多路token支持，自动清理会话痕迹。

Build resilient language agents as graphs.

整理开源的中文大语言模型，以规模较小、可私有化部署、训练成本较低的模型为主，包括底座模型，垂直领域微调及应用，数据集与教程等。

Microsoft's GraphRAG AutoGen Ollama Chainlit = Fully Local & Free Multi-Agent RAG Superbot

Chat with your database (SQL, CSV, pandas, polars, mongodb, noSQL, etc). PandasAI makes data analysis conversational using LLMs (GPT 3.5 / 4, Anthropic, VertexAI) and RAG.

🤖 Chat with your SQL database 📊. Accurate Text-to-SQL Generation via LLMs using RAG 🔄.

Python library and CLI tool to interface with Google Translate's text-to-speech API

本系统是集工单统计、任务钩子、权限管理、灵活配置流程与模版等等于一身的开源工单系统，当然也可以称之为工作流引擎。 致力于减少跨部门之间的沟通，自动任务的执行，提升工作效率与工作质量，减少不必要的工作量与人为出错率。

Alpaca dataset from Stanford, cleaned and curated

Instruction Tuning with GPT-4

A powerful obfuscator for JavaScript and Node.js

QLoRA: Efficient Finetuning of Quantized LLMs

Fast and memory-efficient exact attention

A chat app that transcribes audio in real-time, streams back a response from a language model, and synthesizes this response as natural-sounding speech.

Go ahead and axolotl questions

Guide for fine-tuning Llama/Mistral/CodeLlama models and more

🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

LLM Finetuning with peft

#1 Locally hosted web application that allows you to perform various operations on PDF files

Real time interactive streaming digital human