Al-aminI

kotaemon

An open-source RAG-based tool for chatting with your documents.

llama_index

LlamaIndex is a data framework for your LLM applications

L1B3RT45

JAILBREAK PROMPTS FOR ALL MAJOR AI MODELS

llm-datasets

High-quality datasets, tools, and concepts for LLM fine-tuning.

MiniCPM-V

MiniCPM-V 2.6: A GPT-4V Level MLLM for Single Image, Multi Image and Video on Your Phone

typesense

Open Source alternative to Algolia + Pinecone and an Easier-to-Use alternative to ElasticSearch ⚡ 🔍 ✨ Fast, typo tolerant, in-memory fuzzy Search Engine for building delightful search experiences

LLMs-from-scratch

Implementing a ChatGPT-like LLM in PyTorch from scratch, step by step

LongRoPE

LongRoPE is a novel method that can extends the context window of pre-trained LLMs to an impressive 2048k tokens.

Perplexica

Perplexica is an AI-powered search engine. It is an Open source alternative to Perplexity AI

awesome-audio-plaza

Daily tracking of awesome audio papers, including music generation, zero-shot tts, asr, audio generation

Desktop_BUD-E

BUD-E (Buddy) is an open-source voice assistant framework that facilitates seamless interaction with AI models and APIs, enabling the creation and integration of diverse skills for educational and research applications.

Voice-farmer-assistant

HippoRAG

HippoRAG is a novel RAG framework inspired by human long-term memory that enables LLMs to continuously integrate knowledge across external documents. RAG + Knowledge Graphs + Personalized PageRank.

jepa

PyTorch code and models for V-JEPA self-supervised learning from video.

ml-4m

4M: Massively Multimodal Masked Modeling

LLM101n

LLM101n: Let's build a Storyteller

ws

HippoRAG-API

HippoRAG implementation using APIs

python-whatsapp-bot

Build AI WhatsApp Bots with Pure Python

gemini-api-quickstart

Get up and running in under 5 minutes with the Google AI Gemini API (in Python)

sing-Lang-AI

assistant-api

this is the backend of the RGT assistant API

assistant-frontend

the frontend of the AI assistant

Skywork

Skywork series models are pre-trained on 3.2TB of high-quality multilingual (mainly Chinese and English) and code data. We have open-sourced the model, training data, evaluation data, evaluation methods, etc. 天工系列模型在3.2TB高质量多语言和代码数据上进行预训练。我们开源了模型参数，训练数据，评估数据，评估方法。

emailengine

Headless email client

cropcraft

A Procedural World Generator for Robotics Simulation of Agricultural Tasks

nmfb-collection

LLM-Prompt-Engineering-Simplified-Book

LLM Prompting Engineering Simplified Book

Gemini

The open source implementation of Gemini, the model that will "eclipse ChatGPT" by Google

Diamonds-backend