Updated 10 months ago

rwkv-lm • Rank 11.2 • Science 67%

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 RNN and transformer - great performance, linear time, constant space (no kv-cache), fast training, infinite ctx_len, and free sentence embedding.

Updated 10 months ago

https://github.com/timeseriesai/tsai • Rank 21.4 • Science 46%

Time series Timeseries Deep Learning Machine Learning Python Pytorch fastai | State-of-the-art Deep Learning library for Time Series and Sequences in Pytorch / fastai

Updated 10 months ago

https://github.com/blinkdl/chatrwkv • Rank 21.3 • Science 46%

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

Updated 10 months ago

load_forecasting • Rank 7.8 • Science 36%

Forecasting electric power load of Delhi using ARIMA, RNN, LSTM, and GRU models

Updated 10 months ago

https://github.com/cedrickchee/awd-lstm-lm • Science 10%

LSTM and QRNN Language Model Toolkit for PyTorch (adapted to fast.ai version)

Updated 10 months ago

https://github.com/cn-tu/adversarial-recurrent-ids • Science 10%

Contact: Alexander Hartl, Maximilian Bachl, Fares Meghdouri. Explainability methods and Adversarial Robustness metrics for RNNs for Intrusion Detection Systems. Also contains code for "SparseIDS: Learning Packet Sampling with Reinforcement Learning" (branch "rl").

Updated 10 months ago

rwkv-depth-recurrence • Science 67%

A implementation of RWKV models with depth recurrence (crosslayer-param sharing)

Updated 10 months ago

https://github.com/atharvapathak/twitter_sentiment_analysis_project • Science 23%

Twitter sentiment analysis is the process of analyzing tweets posted on the Twitter platform to determine the overall sentiment expressed within them. It involves using natural language processing (NLP) and machine learning techniques to classify tweets.

Updated 10 months ago

https://github.com/alcantarar/recurrent_grf_prediction • Science 10%

Repository supporting "Predicting continuous ground reaction forces from accelerometers during uphill and downhill running: A recurrent neural network solution"