aflah02

BackTranslation-Based-Data-Augmentation

Distributed-KV-Store-Using-RAFT-with-Leader-Lease

This project presents a Distributed Key-Value Store implemented using the Raft Consensus Algorithm with Leader Lease. Leveraging the reliability and fault tolerance offered by Raft, the system ensures consistent data replication and fault recovery across a distributed network of nodes.

Easy-Data-Augmentation-Implementation

My Implementation for the paper EDA: Easy Data Augmentation Techniques for Boosting Performance on Text Classification Tasks using Tensorflow

GSOC_Report

A report for the work I did during my Google Summer of Code 2022 Project with TensorFlow

Online_Retail_System

A Cross Platform Online Retail System App Built Using Python and Flutter for our Fundamentals of Database Management System (CSE202) Course at IIITD

SemWiseResourcesIIIT

Semester Wise Resource Collection for Various Courses at IIIT Delhi

The_Will_Hero_Game

The Will Hero Game - Adaptation of the popular game Will Hero by ZPlay for our Advanced Programming Course (CSE201) using JavaFX and OOPS Concepts alongside curating UML/Usecase Diagrams

TokenSmith

A comprehensive toolkit for streamlining data editing, search, and inspection for large-scale language model training and interpretability.

pythia

The hub for EleutherAI's work on interpretability and learning dynamics

keras-hub

Pretrained model hub for Keras 3.

aflah02/SemWiseResourcesIIIT

Semester Wise Resource Collection for Various Courses at IIIT Delhi

aflah02/TokenSmith

A comprehensive toolkit for streamlining data editing, search, and inspection for large-scale language model training and interpretability.

aflah02/ChatGPU

aflah02/Cluster-Insights

aflah02/LLM-Latent-Source-Preferences

Code for the paper "In Agents We Trust, but Who Do Agents Trust? Latent Source Preferences Steer LLM Generations"

aflah02/QUENCH

Code for "QUENCH: Measuring the gap between Indic and Non-Indic Contextual General Reasoning in LLMs" (accepted at COLING 2025)

aflah02/FSDP_Experiments

aflah02/HopeEDI-Fix

aflah02/Perplexity-vs-Evaluation

aflah02/aflah02

aflah02/aflah02.github.io

Personal Website

aflah02/al-folio

A beautiful, simple, clean, and responsive Jekyll theme for academics

aflah02/apex

A PyTorch Extension: Tools for easy mixed precision and distributed training in Pytorch

aflah02/bitsandbytes

Accessible large language models via k-bit quantization for PyTorch.

aflah02/generative_agents

Generative Agents: Interactive Simulacra of Human Behavior

aflah02/gpt-neox

An implementation of model parallel autoregressive transformers on GPUs, based on the Megatron and DeepSpeed libraries

aflah02/Hubble

aflah02/litgpt

20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.

aflah02/mimir

Python package for measuring memorization in LLMs.

aflah02/OLMo-core

PyTorch building blocks for the OLMo ecosystem

aflah02/open-unlearning

The one-stop repository for large language model (LLM) unlearning. Supports TOFU, MUSE, WMDP, and many unlearning methods. All features: benchmarks, methods, evaluations, models etc. are easily extensible.

aflah02/prime-environments

Training-Ready RL Environments + Evals

aflah02/python-package-template

A template repo for Python packages

aflah02/sglang

SGLang is a fast serving framework for large language models and vision language models.

aflah02/Streamlit-Chatbot-Templates

aflah02/vLLM-Serving-POC

aflah02/website-wip

aflah02/Wesbite-WIP

aflah02/wip-website

Minimal Jekyll blog styled to resemble the look and layout of Edward Tufte's books

aflah02/wip_website