Pinned Repositories
Advanced-Machine-Learning-Specialization
Materials and notes for the coursera specialization "Advanced Machine Learning Specialization" containing 7 courses.
Authorship-Attribution-using-Transfer-Learning
Transfer learning for authorship attribution with unsupervised training of a language model that teaches a model the working and structure of Bangla language, followed by authorship attribution specific fine-tuning and classification. Effects of various tokenization methods are analyzed as well.
Competitive-Programming
Contains my codes for various programming competitions and practices including learning Data Structure and Algorithms.
GPT3-Reliability-Check
Systematic analysis of the responses of GPT-3 to different categories of statements and the potential vulnerabilities to simple prompting changes. We analyze what confuses GPT-3: how the model responds to certain sensitive topics and what affects the prompt wording has on the model response.
GroupStudy
A social networking Web App aiming to make group interaction easier and more organized. Features include posting, commenting, files upload and file/folder organizing system along with a group shared whiteboard API for group sharing experiences, all within one or more groups as organized by the members of a group.
KG-LM-Integration
A research project to combine information from Knowledge Graphs (KG) into Large Languge Models (LLM) to improve LLM factual accuracy while retaining fluency. The intention is to de-bias and prevent LLMs misinformation generation in a simple and cheap way.
llm-reliability-and-consistency-evaluation
Evaluating LLMs' factual accuracy, consistency, and robustness to prompt variations using diverse response and question formats.
ML-Workshop
Workshop on Introductory Machine Learning from python and libraries to basic ML algorithms.
TruthEval
A curated collection of challenging statements on sensitive topics for LLM benchmarking. Designed to distinguish LLMs' abilities from their stochastic nature.
Wikidata-WDQS-Analysis
Analysis on Wikidata and Wikidata Query Service to help figure out ways to scale the service. Repository contains analysis code, written articles on the findings and visualizations.
tanny411's Repositories
tanny411/GPT3-Reliability-Check
Systematic analysis of the responses of GPT-3 to different categories of statements and the potential vulnerabilities to simple prompting changes. We analyze what confuses GPT-3: how the model responds to certain sensitive topics and what affects the prompt wording has on the model response.
tanny411/KG-LM-Integration
A research project to combine information from Knowledge Graphs (KG) into Large Languge Models (LLM) to improve LLM factual accuracy while retaining fluency. The intention is to de-bias and prevent LLMs misinformation generation in a simple and cheap way.
tanny411/TruthEval
A curated collection of challenging statements on sensitive topics for LLM benchmarking. Designed to distinguish LLMs' abilities from their stochastic nature.
tanny411/Competitive-Programming
Contains my codes for various programming competitions and practices including learning Data Structure and Algorithms.
tanny411/Advanced-Machine-Learning-Specialization
Materials and notes for the coursera specialization "Advanced Machine Learning Specialization" containing 7 courses.
tanny411/Authorship-Attribution-using-Transfer-Learning
Transfer learning for authorship attribution with unsupervised training of a language model that teaches a model the working and structure of Bangla language, followed by authorship attribution specific fine-tuning and classification. Effects of various tokenization methods are analyzed as well.
tanny411/GroupStudy
A social networking Web App aiming to make group interaction easier and more organized. Features include posting, commenting, files upload and file/folder organizing system along with a group shared whiteboard API for group sharing experiences, all within one or more groups as organized by the members of a group.
tanny411/llm-reliability-and-consistency-evaluation
Evaluating LLMs' factual accuracy, consistency, and robustness to prompt variations using diverse response and question formats.
tanny411/Wikidata-WDQS-Analysis
Analysis on Wikidata and Wikidata Query Service to help figure out ways to scale the service. Repository contains analysis code, written articles on the findings and visualizations.
tanny411/wmf-inspiration-week
During inspiration week in WMF, I joined a ML collab project. I took up the part to collect and analyze nsfw data. Mainly to collect a list of all possible nsfw topics in Wikidata and then collect all images in commons related to those selected topics. This allowed us to train a nsfw detector model, host it in WMF Cloud, and run inferences with it. The next steps are to improve the model ofcourse, and incorporate it in various wikimedia projects to detect and warn users of nsfw content where applicable.
tanny411/Machine-Learning-Projects
This repository contains some collection of my machine learning, deep learning and AI projects. This includes Kaggle, Courses and Personal projects.
tanny411/personal-tracker
A MERN web app to track our lives! From food, health, todos to habit tracking and much more. Even add customizable activities to track and display your desired dashboards.
tanny411/astminer
A library for mining of path-based representations of code (and more)
tanny411/COVID-19-trend-app
tanny411/geographic-gaps-in-CS-research
This is a research project to analyze the geographic gaps in CS research. We research citation, collaboration, paper publications, and effect of venues in a few CS subfields. The subfields are those that are listed in CSRAnkings.
tanny411/mental-math
A small python project to practice mental math.
tanny411/Neural-Audio-Mashups
A WMF DSE (data science and engineering) hackathon project. https://phabricator.wikimedia.org/T292306
tanny411/quran.com-frontend-v2
tanny411/Research-Collaboration-Visualization
Visualization project showing scientific collaboration. https://tanny411.github.io/Research-Collaboration-Visualization/
tanny411/SafeKids
A chrome extension to auto block harmful sites and replace bad words for a safer web experience for children. Provision for manual addition/deletion of sites to block. Used Javascript, HTML/CSS as backend and frontend technologies respectively
tanny411/tanny411.github.io
My personal website.
tanny411/Text-Label-Explorer
Interactive Dashboard for Text Label Exploration
tanny411/toolforge-db-test
A repo to test VC with toolforge
tanny411/web-development
Web development training.
tanny411/wikimedia-discovery-discovery-parent-pom
tanny411/wikimedia-microtask
This repo contains solution for the wikimedia microtask for outreachy applicants.
tanny411/Wikimedia-NSFW-Classifier-Reports
tanny411/wikipedia-page-protection
tanny411/wmfdata-python
Tools for working with Wikimedia data on the restricted SWAP platform
tanny411/yale-lily.github.io