win4r

openai-realtime-console

React app for inspecting, building and debugging with the Realtime API

ultravox

A fast multimodal LLM for real-time voice

pocketpal-ai

An app that brings language models directly to your phone.

InternVL

[CVPR 2024 Oral] InternVL Family: A Pioneering Open-Source Alternative to GPT-4o. 接近GPT-4o表现的开源多模态对话模型

LongWriter

LongWriter: Unleashing 10,000+ Word Generation from Long Context LLMs

koboldcpp

Run GGUF models easily with a KoboldAI UI. One File. Zero Install.

TensorRT-LLM

TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and build TensorRT engines that contain state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT-LLM also contains components to create Python and C++ runtimes that execute those TensorRT engines.

web-llm

High-performance In-browser LLM Inference Engine

lmdeploy

LMDeploy is a toolkit for compressing, deploying, and serving LLMs.

mistral.rs

Blazingly fast LLM inference.

Vision-language-models-VLM

vision language models finetuning notebooks & use cases (paligemma - florence .....)

DB-GPT-Hub

A repository that contains models, datasets, and fine-tuning techniques for DB-GPT, with the purpose of enhancing model performance in Text-to-SQL

notebooks

Collection of notebook guides created by the Brev.dev team!

VARAG

Vision-Augmented Retrieval and Generation (VARAG) - Vision first RAG Engine

onnx

Open standard for machine learning interoperability

copa

CoPa: LLM Prompting Templating

dataloader

DataLoader is a generic utility to be used as part of your application's data fetching layer to provide a consistent API over various backends and reduce requests to those backends via batching and caching.

datasetGPT

A command-line interface to generate textual and conversational datasets with LLMs.

NotionNext

使用 NextJS + Notion API 实现的，支持多种部署方案的静态博客，无需服务器、零门槛搭建网站，为Notion和所有创作者设计。 (A static blog built with NextJS and Notion API, supporting multiple deployment options. No server required, zero threshold to set up a website. Designed for Notion and all creators.)

llama-stack

Composable building blocks to build Llama Apps

harbor

Effortlessly run LLM backends, APIs, frontends, and services with one command.

agenta

The all-in-one LLM developer platform: prompt management, evaluation, human feedback, and deployment all in one place.

FlashRAG

⚡FlashRAG: A Python Toolkit for Efficient RAG Research

moshi

GRIN-MoE

GRadient-INformed MoE

Qwen2.5

Qwen2.5 is the large language model series developed by Qwen team, Alibaba Cloud.

Controllable-RAG-Agent

This repository provides an advanced Retrieval-Augmented Generation (RAG) solution for complex question answering. It uses sophisticated graph based algorithm to handle the tasks.

GenAI_Agents

This repository provides tutorials and implementations for various Generative AI Agent techniques, from basic to advanced. It serves as a comprehensive guide for building intelligent, interactive AI systems.

auto-cot

Official implementation for "Automatic Chain of Thought Prompting in Large Language Models" (stay tuned & more will be updated)

tree-of-thoughts

Plug in and Play Implementation of Tree of Thoughts: Deliberate Problem Solving with Large Language Models that Elevates Model Reasoning by atleast 70%