Building an LLM/Chatbot from Scratch: Movie Script Language Model

In this pioneering research project completed in September 2022 (pre-ChatGPT), I took on the challenge of building a language model from the ground up. Working under the Inspirit AI research mentorship program, I trained an LLM using a large corpus of movie transcripts, diving deep into the fundamental architecture of AI language models.
The project involved:
-Collecting and preprocessing a massive dataset of movie scripts
-Understanding and implementing transformer architecture
-Training a custom language model from scratch
-Fine-tuning the model's parameters for optimal performance