| | --- |
| | license: mit |
| | datasets: |
| | - stanfordnlp/sst2 |
| | language: |
| | - en |
| | base_model: |
| | - distilbert/distilbert-base-uncased |
| | pipeline_tag: text-classification |
| | tags: |
| | - legal |
| | - PyTorch |
| | - text-classification |
| | - sentiment-analysis |
| | --- |
| | |
| | # Simple Text Classifier |
| |
|
| | This is a fine-tuned model for text classification based on `distilbert-base-uncased`. |
| |
|
| | ## Model Details |
| |
|
| | - Model Type: Text Classification |
| | - Number of Classes: 2 |
| | - Hidden Size: 768 |
| |
|
| | ## Usage |
| |
|
| | ```python |
| | from transformers import AutoTokenizer |
| | from huggingface_text_classifier.model import SimpleTextClassifier |
| | |
| | # Load model and tokenizer |
| | tokenizer = AutoTokenizer.from_pretrained("ajinathgh/sentiment_analysis") |
| | model = SimpleTextClassifier.from_pretrained("ajinathgh/sentiment_analysis") |
| | |
| | # Prepare input |
| | inputs = tokenizer("Example text to classify", return_tensors="pt") |
| | |
| | # Get predictions |
| | outputs = model(**inputs) |
| | predicted_class = outputs.argmax(-1).item() |
| | ``` |
