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.

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

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

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！

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.

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。

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

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

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.

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

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

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.

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.

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

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.

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

Python SDK for Llama Stack

A CLI tool for generating commit messages using Google Generative AI

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

Use LLMs and LLM Vision to handle paperless-ngx

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.

For loading and running Pixtral models