ojus1 Goto Github PK
Name: Surya Kant Sahu
Type: User
Company: Observe.ai
Bio: I play music, and write dirty PyTorch code. ML Researcher. Collaboratoring w/ MIT. Ex- R&D IITB
Twitter: SuryaOju
Location: India
Name: Surya Kant Sahu
Type: User
Company: Observe.ai
Bio: I play music, and write dirty PyTorch code. ML Researcher. Collaboratoring w/ MIT. Ex- R&D IITB
Twitter: SuryaOju
Location: India
Implementation of unregularized univariate Linear regression on C++
A python module to record ML model's statistics and plot them.
Ludwig is a toolbox built on top of TensorFlow that allows to train and test deep learning models without the need to write code.
Matrix header for matrix operations and writing/reading to/from files to matrix.
A Knowledge Distillation Toolbox. The official implementation of https://arxiv.org/abs/2203.08679
RLHF + MusicTransformer = Generate the music YOU love
Federated Learning on Non-IID Data Silos: An Experimental Study
Chess but with a Twist.
Me tinkerering around Numerical solvers/optimizers and comparing their performances using Machine Learned solvers
Nothing much to add here, just go to https://ojus1.github.io
🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
A simple Commandline Tool to pass Asynchronous jobs to a Local/Remote Workstation. Meant for ML Tasks.
List of Proxies for internal use at Appyhigh LLP
Random Feature Extraction with Numpy
Lecture notebooks and coding assignments for the quantum machine learning MOOC created by Peter Wittek on EdX in the Spring 2019
Reproducing papers by M Tzelepi
RWKV-2 is a RNN with transformer-level performance. It can be directly trained like a GPT transformer (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.
An Implementation of Smoothed Gradient Descent-Ascent (NeurIPS 2020) and a variant of the algorithm.
Neural Style transfer using a small autoencoder
Reproducing the paper: "Time2Vec: Learning a Vector Representation of Time" - https://arxiv.org/pdf/1907.05321.pdf
Triplet Loss Utility for Pytorch Library.
A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)
Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch
A high-throughput and memory-efficient inference and serving engine for LLMs
Guessing the word given an incomplete word and its description
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.