Instructions to use yhavinga/mt5-base-cnn-nl with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use yhavinga/mt5-base-cnn-nl 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/mt5-base-cnn-nl")# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("yhavinga/mt5-base-cnn-nl") model = AutoModelForSeq2SeqLM.from_pretrained("yhavinga/mt5-base-cnn-nl", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "test_gen_len": 108.5, | |
| "test_loss": 1.6764, | |
| "test_n_objs": -1, | |
| "test_rouge1": 31.1766, | |
| "test_rouge2": 8.4538, | |
| "test_rougeL": 17.8674, | |
| "test_rougeLsum": 25.7783, | |
| "test_runtime": 18914.1138, | |
| "test_samples_per_second": 0.607 | |
| } |