AI agents running research on single-GPU nanochat training automatically

A lightweight, low-dependency, unified API to use all common reranking and cross-encoder models.

Rust bindings for the Python interpreter

Semi-automated research assistant for academic research and software development. Supports Claude Code, Codex CLI, Kimi Code CLI, and OpenCode across ideation, coding, experiments, writing, and pub…

Multiple Optimized Specialists for AI-Driven Chemical Predictions

Breakthrough Method for Agile Ai Driven Development

A plug-and-play library for parameter-efficient-tuning (Delta Tuning)

RWKV (pronounced RwaKuv) is an RNN with great LLM performance, which can also be directly trained like a GPT transformer (parallelizable). We are at RWKV-7 "Goose". So it's combining the best of RN…

ChatRWKV is like ChatGPT but powered by RWKV (100% RNN) language model, and open source.

Graph Neural Network Library for PyTorch

Must-read papers on prompt-based tuning for pre-trained language models.

Implementation of SATA Tree-LSTM (Dynamic Compositionality in Recursive Neural Networks with Structure-aware Tag Representations, AAAI 2019)

Automatic Korean Hanja tagging tool powered by Hanjaro (hanjaro.juntong.or.kr)

A collection of AWESOME things about domain adaptation

Probabilistic reasoning and statistical analysis in TensorFlow

Implementations of various VAE-based semi-supervised and generative models in PyTorch

Enhancing Sentence Embedding with Generalized Pooling

Code for ICML 2018 paper on "Fast and Scalable Bayesian Deep Learning by Weight-Perturbation in Adam" by Khan, Nielsen, Tangkaratt, Lin, Gal, and Srivastava

Deconvolutional Latent-Variable Model for Text Sequence Matching

Word Pair Encoding (WPE) for semi-automatic meaningful-keywords generation.

Basic Utilities for PyTorch Natural Language Processing (NLP)

PyTorch implementation of the NIPS-17 paper "Poincaré Embeddings for Learning Hierarchical Representations"

tensorboard for pytorch (and chainer, mxnet, numpy, ...)

Models, data loaders and abstractions for language processing, powered by PyTorch

Tensors and Dynamic neural networks in Python with strong GPU acceleration

Theano was a Python library that allows you to define, optimize, and evaluate mathematical expressions involving multi-dimensional arrays efficiently. It is being continued as PyTensor: www.github.…

An Open Source Machine Learning Framework for Everyone

A flexible framework of neural networks for deep learning