|
|
--- |
|
|
title: Next Word Prediction |
|
|
emoji: 🔮 |
|
|
colorFrom: blue |
|
|
colorTo: purple |
|
|
sdk: docker |
|
|
app_file: Dockerfile |
|
|
pinned: false |
|
|
--- |
|
|
|
|
|
# Next Word Prediction Demo |
|
|
|
|
|
This is a demo app for next word prediction using a trained model with a .pkl tokenizer file. |
|
|
|
|
|
## How to Use |
|
|
1. Enter some text in the input box |
|
|
2. Select how many words you want to predict (1-10) |
|
|
3. Adjust the temperature (controls creativity vs predictability) |
|
|
4. Click "Predict Next Words" to see the prediction |
|
|
|
|
|
## Model Details |
|
|
- Built with TensorFlow/Keras |
|
|
- Uses .pkl format tokenizer |
|
|
- Trained on [mention your dataset here] |
|
|
|
|
|
## Files |
|
|
- `model.h5`: Trained Keras model |
|
|
- `tokenizer.pkl`: Tokenizer for text processing (.pkl format) |
|
|
- `app.py`: Streamlit application |
|
|
- `Dockerfile`: Container configuration |
