Aman Sanger's Projects
Directed Graph of Arxiv Papers
DeepSpeed is a deep learning optimization library that makes distributed training easy, efficient, and effective.
DeleteEmptyComponents sample script installed with Fusion
Flood-Filling Networks for instance segmentation in 3d volumes.
An implementation of model parallel autoregressive transformers on GPUs, based on the DeepSpeed library.
Code for the paper "Evaluating Large Language Models Trained on Code"
Pytorch implementation of JointBERT: "BERT for Joint Intent Classification and Slot Filling"
Inference code for LLaMA models
MSKCC analysis
NNUE (Chess evaluation) trainer in Pytorch
Top-level domain name registry service on Google App Engine
Using NLP to classify how patients have responded to cancer treatment based on scan reports
Config files for my GitHub profile.
Siamese and triplet networks with online pair/triplet mining in PyTorch
PHP library of Snapchat’s private API
Text classification models. Used a submodule for other projects.
🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.