Summarization
Transformers
PyTorch
TensorBoard
Safetensors
Italian
t5
text2text-generation
text-generation-inference
Instructions to use ARTeLab/it5-summarization-ilpost with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ARTeLab/it5-summarization-ilpost 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-ilpost")# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("ARTeLab/it5-summarization-ilpost") model = AutoModelForSeq2SeqLM.from_pretrained("ARTeLab/it5-summarization-ilpost", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "epoch": 4.0, | |
| "eval_gen_len": 45.3175, | |
| "eval_loss": 1.6020476818084717, | |
| "eval_rouge1": 33.7802, | |
| "eval_rouge2": 16.2953, | |
| "eval_rougeL": 27.4797, | |
| "eval_rougeLsum": 30.2273, | |
| "eval_runtime": 846.7357, | |
| "eval_samples": 4400, | |
| "eval_samples_per_second": 5.196, | |
| "eval_steps_per_second": 0.867, | |
| "predict_gen_len": 45.3175, | |
| "predict_loss": 1.6020476818084717, | |
| "predict_rouge1": 33.7802, | |
| "predict_rouge2": 16.2953, | |
| "predict_rougeL": 27.4797, | |
| "predict_rougeLsum": 30.2273, | |
| "predict_runtime": 846.3322, | |
| "predict_samples": 4400, | |
| "predict_samples_per_second": 5.199, | |
| "predict_steps_per_second": 0.867, | |
| "train_loss": 1.7515089764228484, | |
| "train_runtime": 22215.4472, | |
| "train_samples": 35201, | |
| "train_samples_per_second": 6.338, | |
| "train_steps_per_second": 1.056 | |
| } |