A modular graph-based Retrieval-Augmented Generation (RAG) system

Using GPT to parse PDF

GLM-4 series: Open Multilingual Multimodal Chat LMs | 开源多语言多模态对话模型

An all-in-one LLMs Chat UI for Apple Silicon Mac using MLX Framework.

An alternative, self-hosted solution that allows you to continue using Snap Camera with all Snapchat filters after its shutdown on January 25, 2023.

[CVPR2023] Referring Multi-Object Tracking

Agent driven automation starting with the web. Discord: https://discord.gg/wgNfmFuqJF

The official repo of Qwen-Audio (通义千问-Audio) chat & pretrained large audio language model proposed by Alibaba Cloud.

Qwen2 is the large language model series developed by Qwen team, Alibaba Cloud.

Vanna AI Streamlit App

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

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

🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production

AI Native Data App Development framework with AWEL(Agentic Workflow Expression Language) and Agents

CoreNLP: A Java suite of core NLP tools for tokenization, sentence segmentation, NER, parsing, coreference, sentiment analysis, etc.

A generative speech model for daily dialogue.

An Extensible Deep Learning Library

AI chat for every model.

save what you love

A secure authentication module to validate user credentials in a Streamlit application.

ChatOpenLLM is an open-source Python package that provides ChatOpenAI()-like functionality for various open-source models. Built upon the powerful Langchain library, OpenLLM makes it easy to implem…

Accelerate local LLM inference and finetuning (LLaMA, Mistral, ChatGLM, Qwen, Baichuan, Mixtral, Gemma, Phi, etc.) on Intel CPU and GPU (e.g., local PC with iGPU, discrete GPU such as Arc, Flex and…

A high-throughput and memory-efficient inference and serving engine for LLMs

Generate music based on natural language prompts using LLMs running locally

Created and enhanced a local LLM training system on Apple Silicon with MLX and Metal API, overcoming the absence of CUDA support. Fine-tuned the Llama3 model on 16 GPUs for streamlined solution of …

ExcelChat - Chat w/ your excel file

Hackable and optimized Transformers building blocks, supporting a composable construction.

Build AI Assistants with memory, knowledge and tools.

A minimal GPU design in Verilog to learn how GPUs work from the ground up

AI Infra主要是指AI的基础建设，包括AI芯片、AI编译器、AI推理和训练框架等AI全栈底层技术。