🔗 Notebooks

Here is a list of the notebooks available in this repository:

1. Reinforcement Learning

• Training an LLM with RL: Training Gemma 1B to play Connect-Four using Deepseeks GRPO algorithm.

2. LLMs

• Fake News Detection: Detecting fake news with Bidirectional Encoder (BERT) + LSTM model
• Falcon Finetune: Old repo of how to train Falcon
• [Custom LLM options](Customising Large Language Models.ipynb): Options for customising LLMs