|
|
--- |
|
|
license: llama3.2 |
|
|
base_model: |
|
|
- meta-llama/Llama-3.1-8B |
|
|
tags: |
|
|
- intent-classification |
|
|
- knowledge-distillation |
|
|
- customer-service |
|
|
--- |
|
|
# Model Card for Distil-CustomerServiceIntent-Llama3B |
|
|
|
|
|
<!-- Provide a quick summary of what the model is/does. --> |
|
|
|
|
|
This model is a highly efficient **Small Language Model (SLM)** fine-tuned for **customer service intent classification**. It is designed to quickly and accurately route incoming customer service chatbot requests into three distinct, high-volume categories, enabling automated responses and efficient routing. |
|
|
|
|
|
The model was created using using the [distil labs](https://www.distillabs.ai/) platform. |
|
|
|
|
|
## Model Details |
|
|
|
|
|
### Model Description |
|
|
|
|
|
<!-- Provide a longer summary of what this model is. --> |
|
|
|
|
|
- **Developed by:** Mary Newhauser with Distil Labs GmbH |
|
|
- **License:** Llama 3.2 Community License Agreement |
|
|
- **Finetuned from model:** meta-llama/Llama-3.1-8B |
|
|
|
|
|
## Task: Text Classification (Intent Recognition) |
|
|
|
|
|
The model classifies user input into one of **three** distinct, mutually exclusive categories: |
|
|
|
|
|
| ID | Class Name | Description | |
|
|
| :--- | :--- | :--- | |
|
|
| **0** | **order_status** | Questions regarding the status of an existing order (processing, in fulfillment, delivered, etc.). **Excludes courier-specific inquiries.** | |
|
|
| **1** | **delivery_inquiry** | All questions specifically related to the physical delivery or courier actions. Includes questions about package location, expected delivery date, or rescheduling requests. | |
|
|
| **2** | **return_inquiry** | All questions related to the company's specific return policy, the return process, or confirmation of a returned item receipt. | |
|
|
|
|
|
## How to Get Started with the Model |
|
|
|
|
|
Use the code below to get started with the model. |
|
|
|
|
|
## Model Card Contact |
|
|
|
|
|
Contact: contact@distillabs.ai |
