Summarization
Transformers
PyTorch
Safetensors
Italian
t5
text2text-generation
text-generation-inference
Instructions to use ARTeLab/it5-summarization-mlsum with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ARTeLab/it5-summarization-mlsum 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="ARTeLab/it5-summarization-mlsum")# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("ARTeLab/it5-summarization-mlsum") model = AutoModelForSeq2SeqLM.from_pretrained("ARTeLab/it5-summarization-mlsum", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download predict_results.json from ARTeLab/it5-summarization-mlsum: direct link, hf CLI and curl.
- Browser
- Download file 341 Bytes
-
https://huggingface.co/ARTeLab/it5-summarization-mlsum/resolve/main/predict_results.json
- Command line
-
hf download hf://ARTeLab/it5-summarization-mlsum/predict_results.json
-
curl -L -o predict_results.json https://huggingface.co/ARTeLab/it5-summarization-mlsum/resolve/main/predict_results.json
341 Bytes
| { | |
| "predict_gen_len": 32.5268, | |
| "predict_loss": 1.9996718168258667, | |
| "predict_rouge1": 19.3739, | |
| "predict_rouge2": 5.9753, | |
| "predict_rougeL": 16.691, | |
| "predict_rougeLsum": 16.7862, | |
| "predict_runtime": 650.8156, | |
| "predict_samples": 4000, | |
| "predict_samples_per_second": 6.146, | |
| "predict_steps_per_second": 1.025 | |
| } |