Model Card for r831/finetuned-distilbert-sentiment
A binary sentiment classifier based on distilbert-base-uncased, fine-tuned on the IMDB dataset using the 🤗 Transformers Trainer API and Hugging Face Datasets. This model can classify movie reviews as either positive or negative.
Model Details
Model Description
This model is a fine-tuned version of distilbert-base-uncased, a lightweight transformer model developed by Hugging Face, designed for sequence classification tasks.
- Developed by:
r831 - Model type: Transformer-based binary classifier
- Language(s): English
- License: Apache 2.0 (inherited from DistilBERT)
- Finetuned from model:
distilbert-base-uncased
Model Sources
- Repository: https://huggingface.co/r831/finetuned-distilbert-sentiment
- Paper (DistilBERT): https://arxiv.org/abs/1910.01108
Uses
Direct Use
You can directly use this model to classify movie reviews or other short English texts into positive or negative sentiment using Hugging Face Pipelines or Transformers.
Downstream Use
Can be embedded in apps for:
- Review moderation
- Opinion mining
- User feedback classification
Out-of-Scope Use
- Multilingual sentiment analysis
- Domain-specific sentiment tasks without re-finetuning
Bias, Risks, and Limitations
The model was trained on the IMDB movie review dataset and may not generalize well to other domains (e.g., financial reviews, product reviews). It may reflect biases present in the IMDB dataset.
Recommendations
Avoid deploying this model in sensitive domains without further fine-tuning and evaluation. For critical applications, human review is recommended.
How to Get Started with the Model
from transformers import pipeline
classifier = pipeline("text-classification", model="r831/finetuned-distilbert-sentiment")
result = classifier("The movie was absolutely fantastic!")
print(result)
- Downloads last month
- 1