Giter VIP home page Giter VIP logo
Rabiraj Bandyopadhyay photo

rabirajb Goto Github PK

followers: 2.0 following: 7.0 repos: 44.0 gists: 0.0

Name: Rabiraj Bandyopadhyay

Type: User

Company: Coursera

Bio: PhD student at GESIS working on NLP. Prev: Sr. Data Scientist at Coursera, MS Student + Visiting Researcher at University at Buffalo Dept. of Computer Science

Twitter: RabirajB

Location: Seattle, Washington, USA

  • šŸ‘‹ Hi, Iā€™m Rabiraj
  • šŸ‘€ Iā€™m interested in Deep Learning and Natural Language Processing
  • šŸŒ± Iā€™m currently learning and doing research on Hate Speech
  • šŸ’žļø Iā€™m looking to collaborate on interesting projects on synthetic text generation, instruction tuning and data efficient methods for Hate Speech Detection
  • šŸ“« How to reach me? LinkedIn and Twitter

Rabiraj Bandyopadhyay's Projects

congenbench icon congenbench

A one stop shop for anyone interested in researching controllable generation and constrained decoding

datainf icon datainf

DataInf: Efficiently Estimating Data Influence in LoRA-tuned LLMs and Diffusion Models (ICLR 2024)

dataset_difficulty icon dataset_difficulty

"Understanding Dataset Difficulty with V-Usable Information" (ICML 2022, outstanding paper)

fewgen icon fewgen

[ICML 2023] Tuning Language Models as Training Data Generators for Augmentation-Enhanced Few-Shot Learning

hare-hate-speech icon hare-hate-speech

Official repository of "HARE: Explainable Hate Speech Detection with Step-by-Step Reasoning", Findings of EMNLP 2023

ilm-1 icon ilm-1

Easily fine tune GPT-2 to fill in missing text

label-words-are-anchors icon label-words-are-anchors

Repository for Label Words are Anchors: An Information Flow Perspective for Understanding In-Context Learning

less icon less

Preprint: Less: Selecting Influential Data for Targeted Instruction Tuning

litgpt icon litgpt

Pretrain, finetune, deploy 20+ LLMs on your own data. Uses state-of-the-art techniques: flash attention, FSDP, 4-bit, LoRA, and more.

luar icon luar

Transformer-based model for learning authorship representations.

misinfocorrect icon misinfocorrect

Code and Data for WWW'23 paper Reinforcement Learning-based Counter-Misinformation Response Generation: A Case Study of COVID-19 Vaccine Misinformation

mistral-src icon mistral-src

Reference implementation of Mistral AI 7B v0.1 model.

Recommend Projects

  • React photo React

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

  • Vue.js photo Vue.js

    šŸ–– 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. šŸ“ŠšŸ“ˆšŸŽ‰

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 ā¤ļø Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.