Filip Cornell's starred repositories
RWKV-LM
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, saves VRAM, fast training, "infinite" ctx_len, and free sentence embedding.
Chatbot-Long-Short-Term-Memory
GPT-3 Chatbot with Long and Short Term Memory and advanced logic built in javascript with openai API - short and long memory, KYC, embeddings, openai, database, flexible, gpt-3.5-turbo, react
hyp_metric
Hyperbolic Vision Transformers: Combining Improvements in Metric Learning | Official repository
tmu
Implements the Tsetlin Machine, Coalesced Tsetlin Machine, Convolutional Tsetlin Machine, Regression Tsetlin Machine, and Weighted Tsetlin Machine, with support for continuous features, drop clause, Type III Feedback, focused negative sampling, multi-task classifier, autoencoder, literal budget, and one-vs-one multi-class classifier. TMU is written in Python with wrappers for C and CUDA-based clause evaluation and updating.
Open-World-TaxoKG-CoLearning
Data and code of AKBC'22 paper "Open-World Taxonomy and Knowledge Graph Co-Learning".
Prompt-Engineering-Guide
🐙 Guides, papers, lecture, notebooks and resources for prompt engineering
Differentiable-Frechet-Mean
[ICML 2020] Differentiating through the Fréchet Mean (https://arxiv.org/abs/2003.00335).
PoincareKMeans
K-Means algorithm in the Poincare Disk Model
htsprophet
Hierarchical Time Series Forecasting using Prophet
AdaptiveXGBoostClassifier
Implementation of the Adaptive XGBoost classifier for evolving data streams
Awesome-Hyperbolic-Representation-and-Deep-Learning
Paper list about hyperbolic embedding, hyperbolic models,hyperbolic applications