---
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:
1. Grouping the data on the following `category` column values: `ACCOUNT`, `CANCEL`, `SUBSCRIPTION`
2. 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:

![Accounts Dataset](https://github.com/arnavgarg1/shareable_artifacts_for_talks/blob/main/MLOps%20World%202024/accounts_dataset.png)

# How To Use This Model

## Prompt Template

This adapter was instruction tuned using the following prompt template:

```text
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):
```python
{'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