Instructions to use MattBoraske/BART-En-2-De-Translation with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use MattBoraske/BART-En-2-De-Translation with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "translation" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # 'pip install "transformers<5.0.0' from transformers import pipeline pipe = pipeline("translation", model="MattBoraske/BART-En-2-De-Translation")# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("MattBoraske/BART-En-2-De-Translation") model = AutoModelForSeq2SeqLM.from_pretrained("MattBoraske/BART-En-2-De-Translation") - Notebooks
- Google Colab
- Kaggle
This is a base BART model fine-tuned for English to German translation.
Usage
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
# Load model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("MattBoraske/BART_De-En_Translation")
model = AutoModelForSeq2SeqLM.from_pretrained("MattBoraske/BART_De-En_Translation")
# Sample English sentence
sentence = "Good morning! How are you?"
# Translate English to Deutsch (German)
inputs = tokenizer.encode(sentence, return_tensors="pt")
outputs = model.generate(inputs, max_length=40, num_beams=4, early_stopping=True)
translated_sentence = tokenizer.decode(outputs[0], skip_special_tokens=True)
print(translated_sentence)
- Downloads last month
- 10