ShareGPT version of gretelai/synthetic_text_to_sql using the following code: from datasets import load_dataset, DatasetDict

dataset = load_dataset('gretelai/synthetic_text_to_sql', split='all')

def format_sample(sample): conversations = [ { "from": "human", "value": f"{sample['sql_context']}\n\n{sample['sql_prompt']}" }, { "from": "gpt", "value":… See the full description on the dataset page: https://huggingface.co/datasets/mlabonne/synthetic_text_to_sql-ShareGPT.