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

A terminal workspace with batteries included

VILA - a multi-image visual language model with training, inference and evaluation recipe, deployable from cloud to edge (Jetson Orin and laptops)

DSPy: The framework for programming—not prompting—foundation models

AppAgent: Multimodal Agents as Smartphone Users, an LLM-based multimodal agent framework designed to operate smartphone apps.

Fast and flexible image augmentation library. Paper about the library: https://www.mdpi.com/2078-2489/11/2/125

High-speed Large Language Model Serving on PCs with Consumer-grade GPUs

NeuroSurgeon is a package that enables researchers to uncover and manipulate subnetworks within models in Huggingface Transformers

A collection of GPT system prompts and various prompt injection/leaking knowledge.

Argilla is a collaboration tool for AI engineers and domain experts to build high-quality datasets

InsTag: A Tool for Data Analysis in LLM Supervised Fine-tuning

YaRN: Efficient Context Window Extension of Large Language Models

Inference code for Llama models

ripgrep recursively searches directories for a regex pattern while respecting your gitignore

NeoVim dark colorscheme inspired by the colors of the famous painting by Katsushika Hokusai.

Fast inference engine for Transformer models

Sync your Kindle notes and highlights directly into your Obsidian vault

Reverse Instructions to generate instruction tuning data with corpus examples

A collection of open-source dataset to train instruction-following LLMs (ChatGPT,LLaMA,Alpaca)

Using Whisper API to transcribe Youtube videos.

C++ implementation for BLOOM

AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.

LLM as a Chatbot Service

Basaran is an open-source alternative to the OpenAI text completion API. It provides a compatible streaming API for your Hugging Face Transformers-based text generation models.

無料で使える中品質なテキスト読み上げソフトウェア、VOICEVOXのコア

Databricks’ Dolly, a large language model trained on the Databricks Machine Learning Platform

法務省登記所備付地図データ（地図XML）をGeoJSONに変換するコンバータ