Tag: Python
All the articles with the tag "Python".
Projects
BERT Fine-tuning
Improving a Japanese Text-Generation Model through Fine-Tuning BERT.
Reinforcement Learning with OpenAI Gym
Implementation of Reinforcement Learning Algorithms with OpenAI Gym.
Build a GPT-like LLM from scratch
An attempt to build a GPT-style LLM from scratch with PyTorch. Covers the full architecture, pre-training loop, decoding strategies, and loading OpenAI GPT-2 weights.
Build Large Reasoning Model (LRM) from scratch
Build a Large Reasoning Model from scratch and turn non-reasoning LLMs into reasoning LLMs.
Mike 3.0: RAG Powered LLM Model for Chatbot Backend
RAG backend chatbot service built with FastAPI and pgvector. It features real-time document ingestion and LLM-powered responses.
Pong (Reinforcement Learning) with WebSocket Backend
Training PPO agents to master Atari Pong using PyTorch and PettingZoo, served to browser via WebSockets.
RAG vs LoRA: LLM Fine-Tuning Comparison for Mike 3.0
An experimental comparison between RAG and LoRA for building a personal portfolio chatbot.
Rehabilitation Platform Backend
A multi-tenant B2B2C rehabilitation platform built with FastAPI and Python, implementing Clean Architecture.
