Fine-Tuning Chat Model with Domain-Specific Data for custom dataset

[anantgupta129]

I have domain-specific data that I've preprocessed from PDFs into a c4_demo.json format, where each entry looks like [{"text": "<data from file1.pdf"}]. Now, I want to fine-tune my model for chat-based interactions to generate structured chat outputs. My dataset is currently in the following format: [{"role": "system", "content": ""}, {"role": "user", "content": ""}, {"role": "assistant", "content": ""}, ...]. Which fine-tuning method should I use for this?