metadata

library_name: peft
base_model: mistralai/Mistral-7B-v0.1
license: apache-2.0
datasets:
  - bitext/Bitext-customer-support-llm-chatbot-training-dataset
language:
  - en
tags:
  - text-generation-inference

Description

This LoRA adapter was fine-tuned on the bitext/Bitext-customer-support-llm-chatbot-training-dataset, specifically by:

Grouping the data on the following category column values: ACCOUNT, CANCEL, SUBSCRIPTION
Merging intent and response columns into a new single column called response_json that is a JSON object consistint of two keys: intent and response.

This is what the dataset looks like once it is preprared:

How To Use This Model

Prompt Template

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: registration_problems, newsletter_subscription, recover_password, check_cancellation_fee, create_account, switch_account, edit_account, delete_account.

Please package your reply in the JSON format.

Request: {instruction}

Reply:

At inference time, just replace/insert {instruction} with an actual instruction.

Example Input and Output

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: registration_problems, newsletter_subscription, recover_password, check_cancellation_fee, create_account, switch_account, edit_account, delete_account.

Please package your reply in the JSON format.

Request: where can I get information about opening {{Account Category}} accounts?

Reply:

Output (rendered using pprint, but is a proper JSON with full key-value pairs):

{'intent': 'create_account',
 'response': "I'm glad you asked! You can find all the information you need "
             'about opening {{Account Category}} accounts on our website. '
             'Simply visit our homepage and navigate to the account section. '
             "There, you'll find detailed information about the benefits, "
             'features, and requirements for opening a {{Account Category}} '
             'account. If you have any specific questions or need further '
             'assistance, feel free to reach out to our customer support team '
             "who will be more than happy to help you. We're here to make the "
             'process as smooth as possible for you!'}

Framework versions

PEFT 0.8.2
Ludwig 0.10.2