Pinned Repositories
nanotron
Minimalistic large language model 3D-parallelism training
ai-notebooks
AI notebooks
fastgoose
A PyTorch implementation of Model Parallelism and ZeRO Optimizer
instructGOOSE
Implementation of Reinforcement Learning from Human Feedback (RLHF)
pipegoose
Large scale 4D parallelism pre-training for 🤗 transformers in Mixture of Experts *(still work in progress)*
prodgpt
A production-ready training, evaluation and data pipeline
progen
Generating new proteins using language models
reinforcement-learning
stable-diffusion-from-scratch
Implementation of Stable Diffusion from scratch [WORK IN PROGRESS]
toolformer
Implementation of Toolformer: Language Models Can Teach Themselves to Use Tools