|
|
---
|
|
|
tags:
|
|
|
- text-generation
|
|
|
- lstm
|
|
|
- tensorflow
|
|
|
library_name: tensorflow
|
|
|
pipeline_tag: text-generation
|
|
|
---
|
|
|
|
|
|
# LSTM Text Generation Model
|
|
|
|
|
|
This model was trained using TensorFlow/Keras for financial article generation tasks.
|
|
|
|
|
|
## Model Details
|
|
|
|
|
|
- **Model Type**: LSTM
|
|
|
- **Framework**: TensorFlow/Keras
|
|
|
- **Task**: Text Generation
|
|
|
- **Vocabulary Size**: 41376
|
|
|
- **Architecture**: Long Short-Term Memory (LSTM)
|
|
|
|
|
|
## Usage
|
|
|
|
|
|
```python
|
|
|
from huggingface_hub import snapshot_download
|
|
|
import tensorflow as tf
|
|
|
import json
|
|
|
import pickle
|
|
|
import numpy as np
|
|
|
|
|
|
# Download model files
|
|
|
model_path = snapshot_download(repo_id="firobeid/L4_LSTM_financial_article_generator")
|
|
|
|
|
|
# Load the LSTM model
|
|
|
model = tf.keras.models.load_model(f"{model_path}/lstm_model")
|
|
|
|
|
|
# Load tokenizer
|
|
|
try:
|
|
|
# Try JSON format first
|
|
|
with open(f"{model_path}/tokenizer.json", 'r', encoding='utf-8') as f:
|
|
|
tokenizer_json = f.read()
|
|
|
tokenizer = tf.keras.preprocessing.text.tokenizer_from_json(tokenizer_json)
|
|
|
except FileNotFoundError:
|
|
|
# Fallback to pickle format
|
|
|
with open(f"{model_path}/tokenizer.pkl", 'rb') as f:
|
|
|
tokenizer = pickle.load(f)
|
|
|
|
|
|
# Text generation function
|
|
|
def generate_text(input_text, num_words=10):
|
|
|
# Preprocess input
|
|
|
X = np.array(tokenizer.texts_to_sequences([input_text])) - 1
|
|
|
|
|
|
# Generate predictions
|
|
|
output_text = []
|
|
|
for i in range(num_words):
|
|
|
y_proba = model.predict(X, verbose=0)[0]
|
|
|
pred_word_ind = np.argmax(y_proba, axis=-1) + 1
|
|
|
pred_word = tokenizer.index_word[pred_word_ind[-1]]
|
|
|
|
|
|
input_text += ' ' + pred_word
|
|
|
output_text.append(pred_word)
|
|
|
X = np.array(tokenizer.texts_to_sequences([input_text])) - 1
|
|
|
|
|
|
return ' '.join(output_text)
|
|
|
|
|
|
# Example usage
|
|
|
# Start with these tags: <business>, <entertainment>, <politics>, <sport>, <tech>
|
|
|
result = generate_text("<tech> The future of artificial intelligence", num_words=15)
|
|
|
print(result)
|
|
|
```
|
|
|
|
|
|
## Training
|
|
|
|
|
|
This model was trained on text data using LSTM architecture for next-word prediction.
|
|
|
|
|
|
## Limitations
|
|
|
|
|
|
- Model performance depends on training data quality and size
|
|
|
- Generated text may not always be coherent for longer sequences
|
|
|
- Model architecture is optimized for the specific vocabulary it was trained on
|
|
|
|
