Text Classification
Transformers
Safetensors
PyTorch
English
roberta
question-answering
text-embeddings-inference
Instructions to use whitedevil0089devil/roberta_base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use whitedevil0089devil/roberta_base with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="whitedevil0089devil/roberta_base")# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("whitedevil0089devil/roberta_base") model = AutoModelForSequenceClassification.from_pretrained("whitedevil0089devil/roberta_base") - Notebooks
- Google Colab
- Kaggle
roberta_base
This is a fine-tuned RoBERTa model for question-answering classification tasks.
Model Details
- Base Model: roberta-base
- Model Type: Sequence Classification
- Language: English
- License: Apache 2.0
Model Information
- Number of Classes: 5
- Classification Type: grouped_classification
- Class Names: Empty, Word, Short, Medium, Long
Usage
from transformers import AutoTokenizer, AutoModelForSequenceClassification
import torch
# Load model and tokenizer
tokenizer = AutoTokenizer.from_pretrained('whitedevil0089devil/roberta_base')
model = AutoModelForSequenceClassification.from_pretrained('whitedevil0089devil/roberta_base')
# Example usage
question = "Your question here"
inputs = tokenizer(question, return_tensors="pt", truncation=True, padding=True, max_length=384)
with torch.no_grad():
outputs = model(**inputs)
predictions = torch.nn.functional.softmax(outputs.logits, dim=-1)
predicted_class = torch.argmax(outputs.logits, dim=-1).item()
confidence = predictions[0][predicted_class].item()
print(f"Predicted class: {predicted_class}")
print(f"Confidence: {confidence:.4f}")
Training Details
This model was fine-tuned using:
- Framework: PyTorch + Transformers
- Optimization: AdamW with learning rate scheduling
- Training Strategy: Early stopping with validation monitoring
- Hardware: Trained on Google Colab (T4 GPU)
Intended Use
This model is designed for question-answering classification tasks. It can be used to:
- Classify questions into predefined categories
- Provide automated responses based on question classification
- Support Q&A systems and chatbots
Limitations
- Model performance depends on the similarity between training data and inference data
- May not generalize well to domains significantly different from training data
- Classification accuracy may vary based on question complexity and length
Citation
If you use this model, please cite:
@misc{roberta-qa-model,
title={Fine-tuned RoBERTa for Question-Answer Classification},
author={Your Name},
year={2024},
url={https://huggingface.co/whitedevil0089devil/roberta_base}
}
- Downloads last month
- 3
Model tree for whitedevil0089devil/roberta_base
Base model
FacebookAI/roberta-base