A collection of LLM papers, blogs, and projects, with a focus on OpenAI o1 and reasoning techniques.

g1: Using Llama-3.1 70b on Groq to create o1-like reasoning chains

LLaMA-Omni is a low-latency and high-quality end-to-end speech interaction model built upon Llama-3.1-8B-Instruct, aiming to achieve speech capabilities at the GPT-4o level.

An AI-powered file management tool that ensures privacy by organizing local texts, images. Using Llama3.2 3B and Llava v1.6 models with the Nexa SDK, it intuitively scans, restructures, and organizes files for quick, seamless access and easy retrieval.

An Open Source Python alternative to NotebookLM's podcast feature: Transforming Multimodal Content into Captivating Multilingual Audio Conversations with GenAI

Browser automation system that uses AI-driven planning to navigate web pages and perform goals.

BaseAI — The Web AI Framework. The easiest way to build serverless autonomous AI agents with memory. Start building local-first, agentic pipes, tools, and memory. Deploy serverless with one command.

Kodu is an autonomous coding agent that lives in your IDE. It is a VSCode extension that can help you build your dream project step by step by leveraging the latest technologies in automated coding agents

Hexabot is an open-source AI chatbot / agent builder. It allows you to create and manage multi-channel and multilingual chatbots / agents with ease.

Dynamiq is an orchestration framework for agentic AI and LLM applications

AI-powered assistant to help you with your daily tasks, powered by Llama 3.2. It can recognize your voice, process natural language, and perform various actions based on your commands: summarizing text, rephasing sentences, answering questions, writing emails, and more.

「大模型」3小时从0训练27M参数的视觉多模态VLM，个人显卡即可推理训练！

Go library for embedded vector search and semantic embeddings using llama.cpp

A Python-based web-assisted large language model (LLM) search assistant using Llama.cpp

High-quality and streaming Speech-to-Speech interactive agent in a single file. 只用一个文件实现的流式全双工语音交互原型智能体！

A paper list of some recent works about Token Compress for Vit and VLM

这是一份入门AI/LLM大模型的逐步指南，包含教程和演示代码，带你从API走进本地大模型部署和微调，代码文件会提供Kaggle或Colab在线版本，即便没有显卡也可以进行学习。项目中还开设了一个小型的代码游乐场🎡，你可以尝试在里面实验一些有意思的AI脚本。同时，包含李宏毅 (HUNG-YI LEE）2024生成式人工智能导论课程的完整中文镜像作业。

OD-FinLLM is a refined model derived from the LLaMA series, with specific enhancements for Chinese financial knowledge. This model is built by fine-tuning LLaMA using a specialized instruction dataset created from publicly available Chinese financial Q&A data and additional web-scraped financial information.

The official repository of our survey paper: "Towards a Unified View of Preference Learning for Large Language Models: A Survey"

Add AI capabilities to your file system using Ollama, Groq, OpenAi and other's api

Building open version of OpenAI o1 via reasoning traces (Groq, ollama, Anthropic, Gemini, OpenAI, Azure supported) Demo: https://huggingface.co/spaces/pseudotensor/open-strawberry

The official GitHub page for the survey paper "Towards Next-Generation LLM-based Recommender Systems: A Survey and Beyond". And this paper is under review.

TapeAgents is a framework that facilitates all stages of the LLM Agent development lifecycle

The Dawn of Video Generation: Preliminary Explorations with SORA-like Models

4th Place Solution for the Kaggle Competition: LMSYS - Chatbot Arena Human Preference Predictions

Unified management of projects with large model APIs, unified conversion to OpenAI format, calling multiple backend services, OpenAI, Anthropic, Gemini, Vertex, Cloudflare, DeepBricks, OpenRouter, etc.

Simple UI for Llama-3.2-11B-Vision & Molmo-7B-D

The repository of TrafficLLM, a universal LLM adaptation framework to learn robust traffic representation for all open-sourced LLM in real-world scenarios and enhance the generalization across diverse traffic analysis tasks.

Desk-Emoji is a truly open-source AI desktop robot featuring an emoji screen, a two-axis console, and LLM capabilities for voice chat.

VLM driven tool that processes surveillance videos, extracts frames, and generates insightful annotations using a fine-tuned Florence-2 Vision-Language Model. Includes a Gradio-based interface for querying and analyzing video footage.

Solutions for all LeetCode questions in all available languages [Currently 3328/3328 questions. Continue Updating]

Effective LLM Alignment Toolkit

Flock is a workflow-based low-code platform for rapidly building chatbots, RAG, and coordinating multi-agent teams.（Flock 是一个基于workflow工作流的低代码平台，用于快速构建聊天机器人、RAG、Agent和Muti-Agent应用。）

An open-source implementaion for fine-tuning Llama3.2-Vision series by Meta.

🗜️ Codebase-digest is your AI-friendly codebase packer and analyzer. Features 60+ coding prompts and generates structured overviews with metrics. Ideal for feeding projects to LLMs like GPT-4, Claude, PaLM, and Gemini for code analysis and understanding.

Use LLMs and LLM Vision to handle paperless-ngx

A survey on harmful fine-tuning attack for large language model

A prompt for jailbreaking ChatGPT 4o. Tried last at the 4th of September 2024

open-o1: Using GPT-4o with CoT to Create o1-like Reasoning Chains

Python SDK for Llama Stack

A CLI tool for generating commit messages using Google Generative AI

AskTube - An AI-powered YouTube video summarizer and QA assistant powered by Retrieval Augmented Generation (RAG) 🤖. Run it entirely on your local machine with Ollama, or cloud-based models like Claude, OpenAI, Gemini, Mistral, and more.

LangFair is a Python library for conducting use-case level LLM bias and fairness assessments

For loading and running Pixtral models

Nomi enable people to use computer more simply.

A proxy sidecar to access Gemini models via OpenAI and Ollama APIs

A python package for serving LLM on OpenAI-compatible API endpoints with prompt caching using MLX.

LLM notes, including model inference, transformer model structure, and lightllm framework code analysis notes

Code for evaluating with Flow-Judge-v0.1 - an open-source, lightweight (3.8B) language model optimized for LLM system evaluations. Crafted for accuracy, speed, and customization.

GPT-SoVITS-V2模型，合并了官方的一些PR，包含但不限于:参考音频自动填充，字幕同步，SillyTavern酒馆接入等功能

🔥 Aurora Series: A more efficient multimodal large language model series for video.

an Easy-to-use Tool for Comprehensive Response Evaluation of LLMs

A website where you can compare every AI Model ✨

Your own GPT Telegram Bot on Vercel

[Preprint] TRACE: Temporal Grounding Video LLM via Casual Event Modeling

Awesome Large Language Models for Vulnerability Detection

Official Implementation for EMNLP 2024 (main) "AgentReview: Exploring Academic Peer Review with LLM Agent."

Local LLMs in your DAW!

Gotcha GPT ensures the integrity of academic writing in universities and publishing houses due to advances in Artificial Intelligence (AI). It discriminates AI- and human-generated manuscripts (English and Portuguese).

multi-agents banking assistant with Java and Semantic Kernel

最新ChatGPT Plus开通攻略：如何使用国内支付宝充值购买ChatGPT Plus帐号？本文将会手把手地教大家如何在中国大陆使用支付宝充值ChatGPT Plus会员，而且本教程亲测真实有效，我们已经稳定使用ChatGPT Plus一年多，没有遇到任何问题。此外，ChatGPT Plus开通的整个流程也仅需十分钟！

WechatBot with ASR & LLM 集成Dify 大语言模型API接口和微软ASR服务，华尔街见闻、币安、东方财富等金融数据，可识别语音的微信机器人

Terraform configuration for deploying Dify on Google Cloud with scalability, high availability, and production-level readiness.

LLaMa 3.2 Multimodal Web UI is a user-friendly interface for interacting with the Ollama platform.

PrimeDepth: Efficient Monocular Depth Estimation with a Stable Diffusion Preimage

A Python base cli tool for caption images with WD series, Joy-caption-pre-alpha,meta Llama 3.2 Vision Instruct and Qwen2 VL Instruct models.

EventHallusion: Diagnosing Event Hallucinations in Video LLMs

An LLM library for Ruby

Flipper Zero application to interact with Gemini-esp32 and have an AI on your Flipper

Enable shell access on chatgpt.com

A Free OpenAI-compatible API designed to interact with models like GPT-4o, Claude 3 Haiku, Mixtral 8x7b & Llama 3 70b through DuckDuckGo's AI Chat.

Dolomite Engine is a library for pretraining/finetuning LLMs

4bit bitsandbytes quants of the best 7B vlms

AutoGpt 智能推理SDK，利用AI本身的能力进行多次对话推理，回复效果更加理想，更智能。

Free tool to create viral videos from YouTube, generating clips optimized for TikTok and Instagram with automatic transcription and 9:16 editing.

Simulate human behavior with mass LLMs

Raspberry Pi Voice Chatbot backed by local or cloud LLM, with Robot Arm gestures

The OllaLab-Lean project is designed to help both novice and experienced developers rapidly set up and begin working on LLM-based projects.

Building an AI agent with Llama 3.1 via Groq to match the reasoning capabilities of OpenAI's o1 model

goat the GOAT LLM CLI

"Simplicity Prevails: Rethinking Negative Preference Optimization for LLM Unlearning" by Chongyu Fan*, Jiancheng Liu*, Licong Lin*, Jinghan Jia, Ruiqi Zhang, Song Mei, Sijia Liu

Experiments with llama3

Library for managing LLM interactions

Local GLM-4 Prompt Enhancer and Inference for ComfyUI

Python tool for translating subtitles using Google Gemini AI

Bridge between LLMs and various Skyrim Mods

Easily turn large English text datasets into Japanese text datasets using open LLMs.

WorldCuisines is an extensive multilingual and multicultural benchmark that spans 30 languages, covering a wide array of global cuisines.

DashHub is an open-source AI platform designed to help teams of all sizes securely integrate and manage AI solutions (LLMs, GenAI). Its flexible, vendor-neutral architecture enables seamless and cost-effective AI adoption, fostering collaboration and innovation across teams.

Building blocks for rapid development of GenAI applications

The LlamaPress Web App