arpytanshu Goto Github PK
Name: Arpitanshu
Type: User
Bio: Machine Learning Engineer 2 @ Quantive
Location: India
Name: Arpitanshu
Type: User
Bio: Machine Learning Engineer 2 @ Quantive
Location: India
Encode sentences to fix length vectors using pre-trained bert from huggingface-transformers
Bash Script for setting up Apache Cloudstack's Management & Client nodes.
Minimal implementation of DDPM w/ CFG from scratch and trained on English typefaces dataset
Discrete Particles simulation on GPUs using OpenCL and OpenGL.
Comparing Direct Preference Optimization (DPO) vs Supervised FineTuning (SFT) for finetuning LMs on MMLU type datasets.
Implementation of Graph Muti-Attention Network with PyTorch
Discrete Graph Structure Learning for Forecasting Multiple Time Series, ICLR 2021.
PyTorch Implementation of HUSE: Hierarchical Universal Semantic Embeddings ( https://arxiv.org/pdf/1911.05978.pdf )
This Latent Semantic Indexing [ LSI ] model collects, parses, and stores documents to facilitate fast and accurate information retrieval through queries.
re-implementaion of "A watermark for Large Language Models" ( https://arxiv.org/abs/2301.10226 )
backyard projects
Multivariatee time-series forecasting stuff
Parspec Classification Assignment
Learning to trace rays in a weekend.
The GitHub repository for the paper: “Time Series is a Special Sequence: Forecasting with Sample Convolution and Interaction“.
llama finetuned to create SQL queries from table schema.
Implements a Single Shot MultiBox Detector to detect products in shelf images. - https://arxiv.org/abs/1512.02325
Just some code snippets to look back at.
🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
Time Series Tokenizer inspired by Symbolic Aggregate approXimation (SAX) for seamlessly training LLMs with time-series data.
Vision Transformer Implementation ( https://arxiv.org/abs/2010.11929 ) with multi-label classification on CelebA dataset.
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.