Stars
Mixed precision training from scratch with Tensors and CUDA
🌐 Make websites accessible for AI agents. Automate tasks online with ease.
A PyTorch native platform for training generative AI models
This project aim to reproduce Sora (Open AI T2V model), we wish the open source community contribute to this project.
Distilabel is a framework for synthetic data and AI feedback for engineers who need fast, reliable and scalable pipelines based on verified research papers.
LLM training code for Databricks foundation models
(ECCV 2024) Code for V-IRL: Grounding Virtual Intelligence in Real Life
1 min voice data can also be used to train a good TTS model! (few shot voice cloning)
Build and share delightful machine learning apps, all in Python. 🌟 Star to support our work!
A Unified Library for Parameter-Efficient and Modular Transfer Learning
Official code for ReLoRA from the paper Stack More Layers Differently: High-Rank Training Through Low-Rank Updates
NAACL '24 (Best Demo Paper RunnerUp) / MlSys @ NeurIPS '23 - RedCoast: A Lightweight Tool to Automate Distributed Training and Inference
Package for extracting and mapping the results of every single tensor operation in a PyTorch model in one line of code.
Open-sourced codes for MiniGPT-4 and MiniGPT-v2 (https://minigpt-4.github.io, https://minigpt-v2.github.io/)
Edit anything in images powered by segment-anything, ControlNet, StableDiffusion, etc. (ACM MM)
Grounded SAM: Marrying Grounding DINO with Segment Anything & Stable Diffusion & Recognize Anything - Automatically Detect , Segment and Generate Anything
An LLM playground you can run on your laptop
Accessible large language models via k-bit quantization for PyTorch.
Instruct-tune LLaMA on consumer hardware
Making large AI models cheaper, faster and more accessible
Implementation of RLHF (Reinforcement Learning with Human Feedback) on top of the PaLM architecture. Basically ChatGPT but with PaLM