-
The Bigram model.ipynb implements a Bigram Language Model using PyTorch, designed to learn and generate text from character-level sequences. The model uses embeddings to represent each character as a learnable vector, and it generates new text by predicting the next character in a sequence.
-
The chatbot.py contains a PyTorch implementation of a GPT-based language model (gpt-v1.ipynb) that can generate text based on input prompts. The model is trained using transformer architecture and includes self-attention and feedforward layers to process text data.