| --- |
| license: apache-2.0 |
| tags: |
| - text-classification |
| - fine-tuning |
| - resume classification |
| library_name: transformers |
| --- |
| # DistilBERT Resume Classification Model |
|
|
| This repository contains a fine-tuned DistilBERT model for classifying resume sentences into predefined categories. The model is trained on a dataset of resumes and can classify sentences into categories such as Personal Information, Experience, Summary, Education, Qualifications & Certificates, Skills, and Objectives. |
|
|
| ## Model Details |
|
|
| - **Model:** DistilBERT (base-uncased) |
| - **Fine-tuned on:** Custom resume dataset (ganchengguang/resume_seven_class) |
| - **Number of classes:** 7 |
|
|
| ## Categories |
|
|
| The model can classify sentences into the following categories: |
| - Personal Information |
| - Experience |
| - Summary |
| - Education |
| - Qualifications & Certificates |
| - Skills |
| - Objectives |
|
|
| ## Usage |
|
|
| ### Load the Model and Tokenizer |
|
|
| To use the model and tokenizer, you can load them from the Hugging Face Hub as follows: |
|
|
| ```python |
| from transformers import DistilBertTokenizerFast, DistilBertForSequenceClassification |
| |
| # Load the model and tokenizer |
| model_name = "oussama120/Resume_Sentence_Classification" |
| tokenizer = DistilBertTokenizerFast.from_pretrained(model_name) |
| model = DistilBertForSequenceClassification.from_pretrained(model_name) |
