Pinned Loading

1. Reasoning_fine-tuning Reasoning_fine-tuning Public

   Learning how to fine-tune pre-trained models to reason in specific domains like maths

2. Connect4_RLproject Connect4_RLproject Public

   Gaining a deep understanding of the history and development of reinforcement learning through creating a sophisticated Connect4 agent using techniques built upon over the years discussed by the 'Ar…

   Jupyter Notebook

3. Sanji_Agent Sanji_Agent Public

   Training an agent to follow a recipe sequence using Reinforcement Learning

   Jupyter Notebook

4. Creating-an-LLM Creating-an-LLM Public

   Learning about LLM's by attempting to create one from scratch and train it on the openwebtextcorbus data.

   Jupyter Notebook

5. Computer-Vision Computer-Vision Public

   Learning computer vision with various computer vision projects

   Jupyter Notebook