Finetune Llama 3.3, DeepSeek-R1, Reasoning, Phi-4 & Gemma 2 LLMs 2x faster with 70% less memory

A generative speech model for daily dialogue.

veRL: Volcano Engine Reinforcement Learning for LLM

Puzzles for learning Triton

A multi-level tensor algebra superoptimizer

Dify is an open-source LLM app development platform. Dify's intuitive interface combines AI workflow, RAG pipeline, agent capabilities, model management, observability features and more, letting yo…

LXMF client for Android, Linux and macOS allowing you to communicate with people or LXMF-compatible systems over Reticulum networks using LoRa, Packet Radio, WiFi, I2P, or anything else Reticulum s…

Unofficial implementation for the paper "Mixture-of-Depths: Dynamically allocating compute in transformer-based language models"

leaked prompts of GPTs

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

3D Visualization of an GPT-style LLM

Enable Next-Gen Large Language Model Applications. Join our Discord: https://discord.gg/pAbnFJrkgZ

The official Python library for the OpenAI API

The official sources for the RDKit library

Protection against Model Serialization Attacks

ACE (Autonomous Cognitive Entities) - 100% local and open source autonomous agents

Examples and recipes for Llama 2 model

The Startup CTO's Handbook, a book covering leadership, management and technical topics for leaders of software engineering teams

Infinite Photorealistic Worlds using Procedural Generation

Audiocraft is a library for audio processing and generation with deep learning. It features the state-of-the-art EnCodec audio compressor / tokenizer, along with MusicGen, a simple and controllable…

Solve puzzles. Learn CUDA.

MiniGPT-4: Enhancing Vision-language Understanding with Advanced Large Language Models

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

The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

Making large AI models cheaper, faster and more accessible

Alpaca dataset from Stanford, cleaned and curated