huggingface/nanotron

Nanotron: minimalistic library for pretraining transformer models with simple API and scalable parallelism

View on index · View in 3D Map

Related repos

• transformers library for working with machine learning models
• Extension of Transformers for optimizing and running models on specific hardware
• library for post-training and fine-tuning transformer models with SFT, PPO, DPO, and more
• run Hugging Face Transformers models in your browser with JavaScript
• open source app to run, train, and tune large language models on your computer
• GPU-optimized library for training massive transformer models at scale
• energy-based transformers for scalable reasoning and generalization
• open-source robotics platform with pretrained models, datasets, and tools for real-world robot learning
• Collection of PyTorch image models, training scripts, and utilities
• diffusion models for generating images, audio, and 3D with easy pipelines