Bidirectional LSTM-CRF for Sequence Labeling. Easy-to-use and state-of-the-art performance.
An implementation of BWT in python
CUDA Library Samples
Adapting SparseGPT to work with LLaMa and PyTorch semi-structured sparsity
FBPCS (Facebook Private Computation Solutions) leverages secure multi-party computation (MPC) to output aggregated data without making unencrypted, readable data available to the other party or any third parties. Facebook provides impression & opportunity data, and the advertiser provides conversion / outcome data. Both parties have dedicated cloud computing instances living on separate Virtual Private Clouds (VPCs) that are connected to allow network communication. The FBPMP products that have been implemented are Private Lift and Private Attribution. It’s expected that more products will be implemented and added to the Private Measurement suite.
Multi-user server for Jupyter notebooks
LearnPsdd implemented in Python
This program is an automated trading bot that uses TDAmeritrades Thinkorswim trading platform's scanners and alerts systems to place trades dynamically using the TDAmeritrade API.
Tensors and Dynamic neural networks in Python with strong GPU acceleration
ICLR 2018 Quick-Thought vectors
Sentence Embeddings with BERT & XLNet
PyTorch Implementation of "Generating Sentences from a Continuous Space" by Bowman et al 2015 https://arxiv.org/abs/1511.06349
Simulated Annealing Demo
A distributed approximate nearest neighborhood search (ANN) library which provides a high quality vector index build, search and distributed online serving toolkits for large scale vector search scenario.
startup data analysis
Implementation of https://arxiv.org/pdf/1511.06349.pdf