thakur-nandan
Ph.D. Student working on NLP and IR at the University of Waterloo.
University of WaterlooWaterloo, Ontario
Pinned Repositories
beir
A Heterogeneous Benchmark for Information Retrieval. Easy to use, evaluate your models across 15+ diverse IR datasets.
pyserini
Pyserini is a Python toolkit for reproducible information retrieval research with sparse and dense representations.
beir-ColBERT
Evaluation of BEIR Datasets using ColBERT retrieval model
compute-canada
CC Information provided to easy run slurm scripts on CC Wiki
DeepLearningWithKeras
How to use the Keras Deep Learning library
income
INCOME: An Easy Repository for Training and Evaluation of Index Compression Methods in Dense Retrieval. Includes BPR and JPQ.
SocieteGenerale
Societe Generale BrainWaves 2017-2018 Competition Solution Code
sprint
SPRINT Toolkit helps you evaluate diverse neural sparse models easily using a single click on any IR dataset.
topic-modeling
This repository contains as intuitive example on topic-modeling using regular LDA, and how GuidedLDA is better than regular LDA
sentence-transformers
State-of-the-Art Text Embeddings
thakur-nandan's Repositories
thakur-nandan/sprint
SPRINT Toolkit helps you evaluate diverse neural sparse models easily using a single click on any IR dataset.
thakur-nandan/income
INCOME: An Easy Repository for Training and Evaluation of Index Compression Methods in Dense Retrieval. Includes BPR and JPQ.
thakur-nandan/beir-ColBERT
Evaluation of BEIR Datasets using ColBERT retrieval model
thakur-nandan/topic-modeling
This repository contains as intuitive example on topic-modeling using regular LDA, and how GuidedLDA is better than regular LDA
thakur-nandan/beir-JPQ
CIKM'21: JPQ substantially improves the efficiency of Dense Retrieval with 30x compression ratio, 10x CPU speedup and 2x GPU speedup.
thakur-nandan/citadel-repro
A reproduction of CITADEL and CITADEL+ checkpoints using dpr-scale repository
thakur-nandan/Imagesearch
CS 679 Project Repository: Learning Efficient Autoencoders for Image Search
thakur-nandan/jekyll-instagram
thakur-nandan/personal-website
Personal Website | Nandan Thakur | Copyright © nandan-thakur.com, 2021
thakur-nandan/poison-texts
CS 886 Project on Adversarial Attacks on NLP models
thakur-nandan/compute-canada
CC Information provided to easy run slurm scripts on CC Wiki
thakur-nandan/anserini
A Lucene toolkit for replicable information retrieval research
thakur-nandan/BatteryDEV
Our Official Code Repositorty for QS-EIS-Challenge BatteryDEV 2022
thakur-nandan/beir-leaderboard
BEIR Leaderboard
thakur-nandan/CQADupStack
A Benchmark Data Set for Community Question-Answering Research
thakur-nandan/datasets
🤗 The largest hub of ready-to-use NLP datasets for ML models with fast, easy-to-use and efficient data manipulation tools
thakur-nandan/Deep-Learning
thakur-nandan/DeepCT
DeepCT and HDCT uses BERT to generate novel, context-aware bag-of-words term weights for documents and queries.
thakur-nandan/hf-upload
Sample scripts used for uploading bulk datasets and models to HF
thakur-nandan/mGTRR
Easy to use Multi-GPU Training of Retriever and Reranker
thakur-nandan/mteb
MTEB: Massive Text Embedding Benchmark
thakur-nandan/orpo
Official repository for ORPO
thakur-nandan/peft
🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
thakur-nandan/qra_code
Question similarity with domain adaptation.
thakur-nandan/sentence-transformers
Sentence Embeddings with BERT & XLNet
thakur-nandan/tevatron
Tevatron - A flexible toolkit for neural retrieval research and development.
thakur-nandan/thakur-nandan.github.io
Github Pages template for academic personal websites, forked from mmistakes/minimal-mistakes
thakur-nandan/video-insights
video insights created and using open-sourced packages
thakur-nandan/words
thakur-nandan/words-urvashi