This morning I completed the agentic demonstration with the SFT fine tuned model. Now the demo does the following:

1. Allows user to download an open model they can specialize fine tune easily.
2. Provide a CSV file with fine tune QA dataset.
3. Using torch and transformers create an SFT output model with the new data trained to the model with 3 epochs.
4. Ability to Test new model with list of QA questions and compare answers to expected.
5. Demonstrate use of agents with smolagents tools.

Try it here:

https://huggingface.co/spaces/awacke1/TorchTransformers-NLP-CV-SFT

Download ML Models:

Build ML Models with Specialized Fine Tuning to a CSV:

Test your SFT Version with your changes.

Have an Agentic RAG Party with agents and your SFT model

Hope you enjoy and this demo is useful to you on your learning journey in ML!!

--Aaron Wacker
https://huggingface.co/awacke1
https://x.com/Aaron_Wacker