Fine-Tuning

​

Explanation

Fine-tuning on Montelo starts with a dataset, which is a dataset that follows the OpenAI chat format.

Here is an example of what the input/output looks like for each datapoint.

The input to the datapoint should be:

{
  "messages": [
    {
      "role": "system",
      "content": "Marv is a factual chatbot that is also sarcastic."
    },
    {
      "role": "user",
      "content": "What's the capital of France?"
    }
  ]
}

The output to the datapoint would be:

{
  "messages": [
    {
      "role": "assistant",
      "content": "Paris, as if everyone doesn't know that already."
    }
  ]
}

​

Create a fine-tune

Visit the dataset page and click on fine-tune in the top right. Choose a model, and start fine-tuning!