Stars
🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
openpilot is an operating system for robotics. Currently, it upgrades the driver assistance system in 275+ supported cars.
OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamically to do so.
🤗 The largest hub of ready-to-use datasets for ML models with fast, easy-to-use and efficient data manipulation tools
Fast and memory-efficient exact attention
RWKV is an RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best of RNN and transformer - great performance, fast inference,…
An open source implementation of CLIP.
Implementation / replication of DALL-E, OpenAI's Text to Image Transformer, in Pytorch
Differentiable ODE solvers with full GPU support and O(1)-memory backpropagation.
A highly efficient implementation of Gaussian Processes in PyTorch
Full description can be found here: https://discuss.huggingface.co/t/pretrain-gpt-neo-for-open-source-github-copilot-model/7678?u=ncoop57
On the Variance of the Adaptive Learning Rate and Beyond
Multi-LoRA inference server that scales to 1000s of fine-tuned LLMs
Reference implementation for DPO (Direct Preference Optimization)
Differentiable convex optimization layers
Pytorch library for fast transformer implementations
A framework for Privacy Preserving Machine Learning
A library for mechanistic interpretability of GPT-style language models
An implementation of Performer, a linear attention-based transformer, in Pytorch
PyTorch Extension Library of Optimized Autograd Sparse Matrix Operations
Open-source codebase for EfficientZero, from "Mastering Atari Games with Limited Data" at NeurIPS 2021.
Implementation of RETRO, Deepmind's Retrieval based Attention net, in Pytorch
NL-Augmenter 🦎 → 🐍 A Collaborative Repository of Natural Language Transformations
LibKGE - A knowledge graph embedding library for reproducible research