metadata

base_model: meta-llama/Llama-3.1-8B-Instruct
library_name: peft
license: mit
datasets:
  - imnim/multiclass-email-classification
language:
  - en
tags:
  - Email-classifier
  - Email-labelling
  - Fine-tuning
  - peft
  - lora

Model Card for Model ID

Model is finetuned for the task of email labelling. It labels the given email into one or more than one categories based on email subject and email body.

Model Details

Model Description

The model classifies emails into the following 10 categories: "Business", "Personal", "Promotions", "Customer Support", "Job Application", "Finance & Bills", "Events & Invitations", "Travel & Bookings", "Reminders", "Newsletters"

I have prepared a synthetic but realistic dataset of 2,105 labeled emails. Each email includes a subject, body, and one or more categories.

Developed by: imnim
Model type: text-to-text
Language(s) (NLP): English
Finetuned from model: Llama-3.1-8B-Instruct

Model Sources

Repository: https://github.com/contributerMe/multi-label-email-classifier
Demo: https://huggingface.co/spaces/imnim/Multi-labelEmailClassifier

Technical Specifications

Model Architecture and Objective

Auto-regressive language model that uses an optimized transformer architecture.

Compute Infrastructure

Kaggle Notebook

Hardware

Trained on Kaggle's P100 GPU

Framework versions

PEFT 0.15.2