- Copenhagen
Stars
Kronos: A Foundation Model for the Language of Financial Markets
Lockfree, atomic, multi producer, multi consumer, C++, in process and inter-process queue
TorchCFM: a Conditional Flow Matching library
A PyTorch library for implementing flow matching algorithms, featuring continuous and discrete flow matching implementations. It includes practical examples for both text and image modalities.
An easy to customize, strong type library with built in support for unit-like behavior
C++ DataFrame for statistical, financial, and ML analysis in modern C++
official implementation for our paper Cal-QL: Calibrated Offline RL Pre-Training for Efficient Online Fine-Tuning (NeurIPS 2023)
High-quality single-file implementations of SOTA Offline and Offline-to-Online RL algorithms: AWAC, BC, CQL, DT, EDAC, IQL, SAC-N, TD3+BC, LB-SAC, SPOT, Cal-QL, ReBRAC
An offline deep reinforcement learning library
The seq library is a collection of original C++17 STL-like containers and related tools
Aim 💫 — An easy-to-use & supercharged open-source experiment tracker.
Immutable and statically-typeable DataFrames with runtime type and data validation
A repository used to provide an introduction to dataviz in Python
Development repository for the Triton language and compiler
Implementation of the Transformer variant proposed in "Transformer Quality in Linear Time"
Official Pytorch Implementation for "Continual Transformers: Redundancy-Free Attention for Online Inference" [ICLR 2023]
Transmute-free Rust library to work with the Arrow format
Serialization library written in C++17 - Pack C++ structs into a compact byte-array without any macros or boilerplate code
Fast and memory-efficient exact attention
Basic Development Environment - a set of foundational C++ libraries used at Bloomberg.
C++17 library for comfortable and efficient dynamic polymorphism
A fast & densely stored hashmap and hashset based on robin-hood backward shift deletion
Compile Time Regular Expression in C++
The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (V…
Hackable and optimized Transformers building blocks, supporting a composable construction.