Engineering Blog
Building an Unbeatable Tic-Tac-Toe Agent
2024-03-15How I used Reinforcement Learning to create an agent that never loses.
#RL#Python#Game Theory
Democratizing Legal Aid with RAG
2024-02-28Exploring the architecture of a RAG pipeline for Pakistani traffic laws.
#RAG#LLM#Legal Tech
Fine-Tuning FLAN-T5 for Specific Tasks
2024-01-10A deep dive into the process of fine-tuning a small LLM for instruction following.
#Fine-tuning#HuggingFace