Instructions to use ARTeLab/it5-summarization-fanpage-64 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ARTeLab/it5-summarization-fanpage-64 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-fanpage-64")# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("ARTeLab/it5-summarization-fanpage-64") model = AutoModelForSeq2SeqLM.from_pretrained("ARTeLab/it5-summarization-fanpage-64", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download train_results.json from ARTeLab/it5-summarization-fanpage-64: direct link, hf CLI and curl.
- Browser
- Download file 193 Bytes
-
https://huggingface.co/ARTeLab/it5-summarization-fanpage-64/resolve/main/train_results.json
- Command line
-
hf download hf://ARTeLab/it5-summarization-fanpage-64/train_results.json
-
curl -L -o train_results.json https://huggingface.co/ARTeLab/it5-summarization-fanpage-64/resolve/main/train_results.json
193 Bytes
| { | |
| "epoch": 4.0, | |
| "train_loss": 1.610106024723899, | |
| "train_runtime": 44159.403, | |
| "train_samples": 67492, | |
| "train_samples_per_second": 6.113, | |
| "train_steps_per_second": 1.019 | |
| } |