dataset_adapters/WizardLMWizardLM_evol_instruct_V2_196k.py

import random

def transform_data(data):
    transformed_data = {}
    transformed_data['id'] = random.randint(1, 1000000) # generates a random integer as ID
    transformed_data['conversations'] = []

    conversations = data.get('conversations', [])
    for conversation in conversations:
        from_val = conversation.get('from', '')
        value = conversation.get('value', '')
        if from_val.lower() in ['human', 'gpt', 'system']:
            transformed_conversation = {'from': from_val, 'value': value}
            transformed_data['conversations'].append(transformed_conversation)

    return transformed_data