Summarization
Transformers
PyTorch
JAX
TensorBoard
Dutch
t5
text2text-generation
seq2seq
Eval Results (legacy)
text-generation-inference
Instructions to use yhavinga/t5-v1.1-large-dutch-cnn-test with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use yhavinga/t5-v1.1-large-dutch-cnn-test with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "summarization" 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("summarization", model="yhavinga/t5-v1.1-large-dutch-cnn-test")# Load model directly from transformers import AutoTokenizer, AutoModelForMultimodalLM tokenizer = AutoTokenizer.from_pretrained("yhavinga/t5-v1.1-large-dutch-cnn-test") model = AutoModelForMultimodalLM.from_pretrained("yhavinga/t5-v1.1-large-dutch-cnn-test") - Notebooks
- Google Colab
- Kaggle
| python run_summarization_flax.py \ | |
| --output_dir . \ | |
| --model_name_or_path yhavinga/t5-v1.1-large-dutch-cased-2 \ | |
| --tokenizer_name yhavinga/t5-v1.1-large-dutch-cased-2 \ | |
| --dataset_name="ml6team/cnn_dailymail_nl" \ | |
| --text_column article \ | |
| --summary_column highlights \ | |
| --do_train --do_eval --do_predict --predict_with_generate \ | |
| --num_train_epochs 5 \ | |
| --learning_rate 5e-5 --warmup_steps 0 \ | |
| --per_device_train_batch_size 2 \ | |
| --per_device_eval_batch_size 2 \ | |
| --overwrite_output_dir \ | |
| --adafactor \ | |
| --max_source_length 1024 --max_target_length 96 \ | |
| --save_steps="20000" \ | |
| --eval_steps="5000" \ | |
| # --push_to_hub |