Pinned Repositories
jcaip.github.io
personal blog
lightning-sam
Fine-tune Segment-Anything Model with Lightning Fabric.
Ocular
OCR done in Python
quickthoughts
pytorch reimplementation of qt paper
twitter_sentiment_analysis
Sentiment Analysis LSTM Model written in tensorflow
ao
PyTorch native quantization and sparsity for training and inference
pytorch
Tensors and Dynamic neural networks in Python with strong GPU acceleration
distbelief
Implementing Google's DistBelief paper
jcaip's Repositories
jcaip/quickthoughts
pytorch reimplementation of qt paper
jcaip/jcaip.github.io
personal blog
jcaip/lightning-sam
Fine-tune Segment-Anything Model with Lightning Fabric.
jcaip/builder
Continuous builder and binary build scripts for pytorch
jcaip/Burrows-Wheeler-Compression
An implementation of BWT in python
jcaip/configs
my i3 config, conkyrc, vimrc, and other config files
jcaip/contrast
Jekyll Theme
jcaip/CUDALibrarySamples
CUDA Library Samples
jcaip/fast-sparse-llama
Adapting SparseGPT to work with LLaMa and PyTorch semi-structured sparsity
jcaip/fbpcs
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.
jcaip/gpt-fast
add 2:4 sparsity to gpt-fast
jcaip/int8-cusparselt
jcaip/Labelbox
The most versatile data labeling platform for training expert AI.
jcaip/lectures
Material for cuda-mode lectures
jcaip/math-vis
jcaip/MATH131
math 131
jcaip/MATH164
optimization
jcaip/orbital-branching
wip
jcaip/Py-Psdd
LearnPsdd implemented in Python
jcaip/python-trading-bot-with-thinkorswim
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.
jcaip/pytorch
Tensors and Dynamic neural networks in Python with strong GPU acceleration
jcaip/pytorch-playground
Trying to learn more pytorch
jcaip/S2V
ICLR 2018 Quick-Thought vectors
jcaip/SDNet
SDNet
jcaip/sentence-transformers
Sentence Embeddings with BERT & XLNet
jcaip/Sentence-VAE
PyTorch Implementation of "Generating Sentences from a Continuous Space" by Bowman et al 2015 https://arxiv.org/abs/1511.06349
jcaip/simulated_annealing
Simulated Annealing Demo
jcaip/SPTAG
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.
jcaip/startup
startup data analysis
jcaip/text-vae
Implementation of https://arxiv.org/pdf/1511.06349.pdf