This LoRA adapter was fine-tuned on the bitext/Bitext-customer-support-llm-chatbot-training-dataset, specifically by:
category column values: ORDER, DELIVERY, SHIPPINGintent and response columns into a new single column called response_json that is a JSON object consisting of two keys: intent and response.This is what the dataset looks like once it is preprared:
It also has the following token distribution (without the prompt template being merged into the input)
This adapter was instruction tuned using the following prompt template:
You are a support agent for a company and you receive requests from customers.
Your job is to reply to the customer by providing both the intent, which you
should determine from the customer's request, as well as an appropriate response.
Please note that the intent can only be one of the following: delivery_period, delivery_options, change_order, cancel_order, place_order, track_order, set_up_shipping_address, change_shipping_address.
Please package your reply in the JSON format.
Request: {instruction}
Reply:
At inference time, just replace/insert {instruction} with an actual instruction.
This adapter was fine-tuned using Predibase. You can sign up for a free trial and follow along using this notebook to reproduce this adapter: https://colab.research.google.com/drive/1Zzkrr40NRylUnq-pztaypVOoDPS2s9Vr
Input:
You are a support agent for a company and you receive requests from customers.
Your job is to reply to the customer by providing both the intent, which you
should determine from the customer's request, as well as an appropriate response.
Please note that the intent can only be one of the following: delivery_period, delivery_options, change_order, cancel_order, place_order, track_order, set_up_shipping_address, change_shipping_address.
Please package your reply in the JSON format.
Request: I can no longer afford order {{Order Number}}, cancel it
Reply:
Output (rendered using pprint, but is a proper JSON with full key-value pairs):
{'intent': 'cancel_order',
'response': "I've understood you're no longer able to afford order {{Order "
'Number}} and would like to cancel it. I apologize for any '
'inconvenience this may have caused. To cancel your order, please '
'follow these steps:\n'
'\n'
'1. Sign in to your account: Access our platform by logging in to '
'your {{Online Company Portal Info}}.\n'
"2. Locate your order: Once logged in, navigate to the '{{Online "
"Order Interaction}}' or '{{Online Order Interaction}}' section.\n"
'3. Find the specific order: Look for the order with the number '
'{{Order Number}} and click on it to view the details.\n'
'4. Initiate cancellation: Within the order details, you should '
"see an option labeled '{{Online Order Interaction}}'. Please "
'select this to begin the cancellation process.\n'
'5. Confirm cancellation: The system may ask for confirmation or '
'provide additional instructions. Please follow the prompts to '
'complete the cancellation.\n'
'\n'
'If you encounter any difficulties or have further questions, our '
'dedicated support team is available to assist you. You can reach '
'us during {{Customer Support Hours}} at {{Customer Support Phone '
'Number}} or through the Live Chat feature on our {{Website '
'URL}}. We appreciate your understanding and are here to ensure '
'your satisfaction.'}