Giter Site home page Giter Site logo

Hi there πŸ‘‹

  • πŸ˜„ I'm Sumanth, a software engineer at Anyscale. My primary interests are broadly in machine learning and systems engineering.
  • πŸš€ I'm trying to understand generative models, and have worked on finetuning and in-context learning for language models. Addicted to compute πŸ€–
  • πŸ’» I've made open-source contributions to πŸ€— PEFT and Accelerate.
  • 🌱 I'm trying to learn what it takes to build machine learning systems in practice.
  • ✨ I have a blog: https://sumanthrh.com
  • πŸ’¬ Some samples of my work:
  • πŸ“« You can reach out to me at [email protected]
  • ⚑ Fun fact: Give me any song with a moderate tempo and I can whistle it 🎢
  • Other GitHub accounts: c3-sumanthrh

Sumanth R Hegde's Projects

accelerate icon accelerate

πŸš€ A simple way to train and use PyTorch models with multi-GPU, TPU, mixed-precision

adapnet-pp icon adapnet-pp

Code for the EE6132 Course Project, Fall 2019. Code forked from https://github.com/DeepSceneSeg/AdapNet-pp with project-specific changes

cleverhans icon cleverhans

An adversarial example library for constructing attacks, building defenses, and benchmarking both

cs6790_gpcv icon cs6790_gpcv

Assignments of the course "Geometry and Photometry for Computer Vision" , Spring 2020.

ecco icon ecco

Explain, analyze, and visualize NLP language models. Ecco creates interactive visualizations directly in Jupyter notebooks explaining the behavior of Transformer-based language models (like GPT2, BERT, RoBERTA, T5, and T0).

ee5111_estimation_theory icon ee5111_estimation_theory

A repository of mini projects and projects carried out as part of the EE5111 Estimation Theory couse, Spring 2020.

ee5120_linear_algebra icon ee5120_linear_algebra

This is repository of assignments and explorations done as part of the EE5120 Applied Linear Algebra course (July-Nov 2019)

fastchat icon fastchat

Fork of FastChat, an open platform for training, serving, and evaluating large language models. Release repo for Vicuna and FastChat-T5.

handout icon handout

Turn Python scripts into handouts with Markdown and figures

ia_3_test icon ia_3_test

Fork of Chao's test with peftt ia^3. Trying to get to the bottom of IA3 training errors.

icl_support_example icon icl_support_example

The official implementation of the paper "Finding Support Examples for In-Context Learning".

iitm-netaccess-cmd icon iitm-netaccess-cmd

Command line application for approving/revoking your machine's internet access at IIT Madras

interiit_2018 icon interiit_2018

Our submission for the " Eye in the Sky " problem statement of Inter IIT Tech Meet 2018 conducted by IIT Bombay

llmperf icon llmperf

LLMPerf is a library for validating and benchmarking LLMs

nanotron icon nanotron

Minimalistic large language model 3D-parallelism training

peft icon peft

Fork of πŸ€— PEFT: State-of-the-art Parameter-Efficient Fine-Tuning. Our implementation for IA3, a new fine-tuning method is now a part of the official Huggingface library!

pygloo icon pygloo

Pygloo provides Python bindings for Gloo.

ray icon ray

Ray is a unified framework for scaling AI and Python applications. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.

sbi-stockroom-ps icon sbi-stockroom-ps

A project aimed at creating a facial recognition module and handwiting matching module for automatic customer identification in banks

starter-hugo-academic icon starter-hugo-academic

πŸŽ“ Hugo Academic Theme εˆ›ε»ΊδΈ€δΈͺε­¦ζœ―η½‘η«™. Easily create a beautiful academic rΓ©sumΓ© or educational website using Hugo, GitHub, and Netlify.

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    πŸ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. πŸ“ŠπŸ“ˆπŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❀️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.