Downloads · 30 days
4
6% of all-time downloads
LongFormer-Paper-Citaion-Classifier
REEM-ALRASHIDI/LongFormer-Paper-Citaion-Classifier
LongFormer-Paper-Citaion-Classifier is a text classification model from REEM-ALRASHIDI. Use it when you need a label for a piece of text. It is set up for transformers.
The LongFormer Paper Classification model developed by Reem, is designed to classify research papers into four citation categories (Level 1, Level 2, Level 3, and Level 4) based on their citation counts.
All-time downloads
70
Public
Parameters
149M
595 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors595 MB · 100%
At a glance
- Task
- Text Classification
- Library
- transformers
- Model type
- longformer
- Access
- Public
- Created
- Apr 21, 2024
- Updated
- Apr 21, 2024
- SHA
- 4af5c126
Try a prompt
Model card
From the Hugging Face model README
Model Card for Model ID
Model Details
Model Description
The LongFormer Paper Classification model developed by Reem, is designed to classify research papers into four citation categories (Level 1, Level 2, Level 3, and Level 4) based on their citation counts.
Uses
The model is intended for researchers, academics, and institutions to analyze the impact and visibility of research papers based on their citation counts
Bias and Limitations
Users should be cautious of potential biases in the training data and publication practices, and validate predictions with domain expertise.
Training Details
Training Data
The model is trained on a dataset of labeled research papers with citation categories. Fine-tuning hyperparameters are used during training.
Evaluation
Evaluation metrics include accuracy, precision, recall, and F1 score across citation categories.
- Task
- Text Classification
- Library
- transformers
- Type
- longformer
- Created
- Apr 21, 2024
- Updated
- Apr 21, 2024