techandy42
🎓 CS @ U of Waterloo | 🤖 ML Researcher @ WAT.ai x hamming.ai | 🏆 4x Hackathon Winner | LLM Enjoyer
Toronto, Ontario, Canada
Pinned Repositories
awesome-llm-metrics
An open-source framework that makes evaluating LLMs & prompt engineering x10 easier!
Bing_AI_Clone
A clone project of the Bing AI with Google Custom Search Engine and GPT-3.5/4.
bug_in_the_code_stack
A new benchmark for measuring LLM's capability to detect bugs in large codebase.
calculator
This is a calculator app that supports basic artihmetics and brackets. The app is designed to prevent the user from making any logical errors by checking the validity of their inputs.
CrafterGPT
Leveraging Language Model to Play Procedurally-Generated Survival Games.
ExchangeAgent
Training a stock exchange agent with Reinforcement Learning algorithms and Decision Transformer.
FinancialBERT
Stock price prediction model built using BERT and regression model trained on textual financial news data.
GreenTechGuardians
A Circular Economy business idea evaluator tool built using Gen-AI.
OpenAI_Gym_Atari_Space_Invaders_RL
Space Invaders agent trained using DQN/A2C models on OpenAI Gym Atari Environment.
personal-portfolio-website
This is a personal portfolio website made using Bootstrap.
techandy42's Repositories
techandy42/FinancialBERT
Stock price prediction model built using BERT and regression model trained on textual financial news data.
techandy42/awesome-llm-metrics
An open-source framework that makes evaluating LLMs & prompt engineering x10 easier!
techandy42/bug_in_the_code_stack
A new benchmark for measuring LLM's capability to detect bugs in large codebase.
techandy42/CrafterGPT
Leveraging Language Model to Play Procedurally-Generated Survival Games.
techandy42/GreenTechGuardians
A Circular Economy business idea evaluator tool built using Gen-AI.
techandy42/OpenAI_Gym_Atari_Space_Invaders_RL
Space Invaders agent trained using DQN/A2C models on OpenAI Gym Atari Environment.
techandy42/ExchangeAgent
Training a stock exchange agent with Reinforcement Learning algorithms and Decision Transformer.
techandy42/LLM_Reward_Model
Developing a LLM response ranking reward model using HFRL except it's GPT-3.5 instead of human.
techandy42/OpenAI_Gym_Atari_Pong_RL
Pong agent trained on trained using DQN model on OpenAI Gym Atari Environment.
techandy42/Satellite_Image_Classification_Project
Satellite image classification model built using PyTorch.
techandy42/techandy42
README.md for my GitHub page.
techandy42/Algo_Schedule_Manager
This is open-source repository of Algo AI, an automated schedule manager platform built using heuristic decision-making algorithms & GPT-4.
techandy42/anserini
Anserini is a Lucene toolkit for reproducible information retrieval research
techandy42/babilong
BABILong is a benchmark for LLM evaluation using the needle-in-a-haystack approach.
techandy42/bug_in_the_code_stack_v2
Can LLMs find bugs that compilers can't?: A benchmark for measuring LLMs' capabilities in debugging large source code.
techandy42/crafter
Benchmarking the Spectrum of Agent Capabilities
techandy42/decision-making-heuristic-algorithms
Basic decision-making problems solved using heuristic algorithms implemented in Java and Python.
techandy42/eccc-hail-forecasting-project
Open-source ECCC repository for notebooks and documentations for the Hail Forecasting project by Hokyung (Andy) Lee.
techandy42/eccc-webcam-project
Open-source ECCC repository for notebooks and documentations for the Webcam project by Hokyung (Andy) Lee.
techandy42/LVEval
Repository of LV-Eval Benchmark
techandy42/Monte_Carlo_Go_Agent
A Go agent built using Monte Carlo Search Tree algorithm.
techandy42/OpenAI_Gym_Bipedal_Walker_RL
Bipedal Walker agent trained using SAC model on OpenAI Gym Environment.
techandy42/OpenAI_Gym_Lunar_Lander_RL
Lunar Lander agent trained using DQN model on OpenAI Gym Environment.
techandy42/OpenAI_Gym_RL_Algorithms_Database
A database of various RL algorithms implemented in PyTorch for the OpenAI Gym Environments with code and explanations.
techandy42/pyserini
Pyserini is a Python toolkit for reproducible information retrieval research with sparse and dense representations.
techandy42/racecar_gym
A gym environment for a miniature racecar using the pybullet physics engine.
techandy42/RagTagTeam
Startup co-founder matching platform built using Cohere for the WAT.AI RAG Challenge hackathon.
techandy42/rank_llm
Repository for prompt-decoding using LLMs (GPT3.5, GPT4, and Vicuna)
techandy42/torchgym
A PyTorch library that provides major RL algorithms and functionalities for training OpenAI Gym agents.
techandy42/Transformer_Seq2Seq_Ko_En_Bidirectional_Translator
A bidirectional (joint model) transformer seq2seq translator model for Korean-to-English translation.