Fine-Tuning with LLMs

A notebook that I had worked on to understand fine-tuning in LLMs and their hyperparameter tuning.

If you are here reading this, go take a look at my portfolio at Streamlit

References:

Google's lora_tuning colab notebook : https://colab.research.google.com/github/google/generative-ai-docs/blob/main/site/en/gemma/docs/lora_tuning.ipynb

LLM-evaluation using DeepEval

A notebook going through all the deepeval metrics and how it is using the LLM to evaluate the results. Have given some samples and produced a summary table which is very easy to understand and also easy to know when to use what metric.

References:

DeepEval Docs : https://docs.confident-ai.com/docs/metrics-llm-evals