Pinned Loading

1. decoder-only-transformer-from-scratch decoder-only-transformer-from-scratch Public

   A decoder-only Transformer implemented from scratch in PyTorch for autoregressive next-token prediction, with inspectable intermediate states for architectural analysis.

   Jupyter Notebook

2. llm-instruction-finetuning-lora llm-instruction-finetuning-lora Public

   Instruction-tuning a GPT-2 model with LoRA to generate short, clear, and accurate one-sentence answers to user queries.

   Python

3. Grounded-LLM-with-RAG Grounded-LLM-with-RAG Public

   An end-to-end RAG pipeline that turns documents into searchable embeddings and retrieves relevant context for accurate question answering.

   Python

4. Inside-Transformers Inside-Transformers Public

   This repository is a systematic exploration of Transformer architectures, focusing on how and why they work. It includes internal mechanics and data flow analysis, architecture-level breakdowns, co…

   Jupyter Notebook