[EMNLP'23, ACL'24] To speed up LLMs' inference and enhance LLM's perceive of key information, compress the prompt and KV-Cache, which achieves up to 20x compression with minimal performance loss.

Home of CodeT5: Open Code LLMs for Code Understanding and Generation

Interact with your documents using the power of GPT, 100% privately, no data leaks

Automate code optimization, refactoring, and readability improvements with CodeGenie AI.

[In progress] Budgeting app built with Flask and Nordigen API

A set of curated exercises and questions one can practice before going for graduate interviews and tech tests

A set of curated exercises to help prepare you for the Certified Kubernetes Administrator Exam by the Cloud Native Computing Foundation

Useful notes for the KCNA - Kubernetes and Cloud Native Associate

Basic application implementing android sensors (gyroscope and accelorometer)

A portfolio of all my java related work in MSc

An online shop using ASP.NET Core 2.1 with Vue.js

A simple blog using ASP.NET Core 2.1