datasets:
- stanfordnlp/imdb
language:
- en
base_model:
- distilbert/distilbert-base-uncased
tags:
- torch
- code
library_name: transformers
pipeline_tag: text-classification
metrics:
- accuracy
DistilBERT Fine-Tuned on IMDB Sentiment Analysis
This model is a fine-tuned version of DistilBERT for sentiment analysis on the IMDB movie reviews dataset. It classifies movie reviews into two categories: positive and negative sentiments.
Model Details
Model Description
This model has been fine-tuned on the IMDB dataset, which contains movie reviews labeled with sentiments: positive or negative. The model is based on the DistilBERT architecture, which is a lighter, more efficient variant of BERT, offering faster inference without significantly sacrificing accuracy.
- Developed by: Leonuraht/Scilineo
- Model type: Transformer-based model for text classification (sentiment analysis)
- Language(s) (NLP): English
- Finetuned from model : distilbert-base-uncased
Uses
Direct Use
This model is directly usable for sentiment analysis tasks. It predicts the sentiment of text by classifying it as either "positive" or "negative".
Downstream Use [optional]
This model can be further fine-tuned for other text classification tasks or integrated into larger applications where sentiment analysis is required.
Out-of-Scope Use
This model is not intended for multilingual sentiment analysis or for handling text outside of movie reviews. It may not perform well on domains with vastly different vocabularies or sentiment expression styles.
Bias, Risks, and Limitations
The model has been trained on the IMDB movie reviews dataset, and as such, it may exhibit biases inherent in the data (e.g., biases in sentiment based on genre, culture, or language). It is important to be mindful of these limitations when using the model in real-world applications.
Recommendations
Users should be aware of the model's biases and limitations. It is recommended to further fine-tune the model with a diverse dataset if it is to be used in domains beyond movie reviews.
How to Get Started with the Model
To use the model for sentiment analysis, you can load it via the Hugging Face transformers library. Here's an example:
from transformers import pipeline
# Load the fine-tuned model from Hugging Face
model = "Leonuraht/IMDBert"
classifier = pipeline("sentiment-analysis", model=model)
# Test the model with a sample text
result = classifier("This movie was amazing!")
print(result) # Outputs: [{'label': 'POSITIVE' }]