A formatted version of the mlabonne/FineTome-100k dataset from Hugging Face for conversations. We are taking the first prompt and response to create a simple dataset for fine-tuning.

Demo of fine-tuning PixArt

Demo repo of supervised fine tuning and grpo in the same repo

This is an example repo to help you get started on the features available in Oxen.ai

Here lies all the data 🐉

Testing rag+gemini