Training Large Language Model to Reason in a Continuous Latent Space

🚀 Efficient implementations of state-of-the-art linear attention models in Pytorch and Triton

Official codebase used to develop Vision Transformer, SigLIP, MLP-Mixer, LiT and more.

SimPO: Simple Preference Optimization with a Reference-Free Reward

Next-Token Prediction is All You Need

Implementation of Imagen, Google's Text-to-Image Neural Network, in Pytorch

Implementation of Denoising Diffusion Probabilistic Model in Pytorch

PyTorch original implementation of Cross-lingual Language Model Pretraining.

Scripts for fine-tuning Meta Llama3 with composable FSDP & PEFT methods to cover single/multi-node GPUs. Supports default & custom datasets for applications such as summarization and Q&A. Supportin…

A tool for learning vector representations of words and entities from Wikipedia

State-of-the-art LLM-based translation models.

Code for 'LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders'

PyTorch implementation of MAE https//arxiv.org/abs/2111.06377

Implementation of Muse: Text-to-Image Generation via Masked Generative Transformers, in Pytorch

Official repository for ORPO

JAX implementation of the Mistral 7b v0.2 model