|
|
--- |
|
|
license: mit |
|
|
--- |
|
|
Imagine you have a BERT model – the superhero of natural language understanding – but this one speaks German! We took the powerful "bert-base-german-cased" model and gave it a special mission: classify German text. After intense training, it's ready to help you tackle tasks like sentiment analysis, content categorization, or even semantic search in the German language. |
|
|
It is trained on 160K article summaries performs well on semantic search and text classification. I plan on to further fine tune this model with a much larger dataset approximately going to 511K article summaries. |
|
|
|
|
|
How to Use It: |
|
|
Let's see how you can unleash this German-speaking superhero on your data: |
|
|
|
|
|
Install Hugging Face Transformers: |
|
|
First, make sure you have the Hugging Face Transformers library installed. You can do this with pip: |
|
|
|
|
|
bash |
|
|
Copy code |
|
|
pip install transformers |
|
|
Load the Fine-Tuned Model: |
|
|
To use this fine-tuned BERT model, load it with the Transformers library: |
|
|
|
|
|
python |
|
|
Copy code |
|
|
from transformers import TFBertForSequenceClassification, BertTokenizer |
|
|
|
|
|
# Load the model and tokenizer |
|
|
model = TFBertForSequenceClassification.from_pretrained("path/to/your/model/directory") |
|
|
tokenizer = BertTokenizer.from_pretrained("bert-base-german-cased") |
|
|
Prepare Your Text: |
|
|
You can perform text classification with this model. Tokenize your text using the tokenizer: |
|
|
|
|
|
# Enter Text Input |
|
|
text = "Deine Textnachricht hier" # Your German text |
|
|
|
|
|
Get Predictions: |
|
|
Predict the label or class for your text: |
|
|
inputs = tokenizer(text, padding='max_length', truncation=True, max_length=128, return_tensors='tf', return_attention_mask=True) |
|
|
|
|
|
# Make a prediction |
|
|
with tf.device('/GPU:0'): # Specify the GPU device |
|
|
outputs = model(inputs) |
|
|
The predicted_class will give you the predicted label for your text. |
|
|
|
|
|
Semantic Search: |
|
|
For semantic search, you can create embeddings for a list of text and calculate the similarity between your query text and the documents, as discussed earlier. The model can help you find similar content with ease. |
|
|
|
|
|
That's it! Your fine-tuned BERT model is now your ally for handling various text-based tasks in the German language. Whether it's text classification or semantic search, this model is ready to assist you on your NLP adventures. |
|
|
|
|
|
|
|
|
|
|
|
Feel free to reach out if you have questions or need assistance in using this model to accomplish your German language processing tasks. Viel Erfolg! (Good luck!) |
