Summarization
Transformers
PyTorch
TensorBoard
English
pegasus
text2text-generation
Generated from Trainer
Instructions to use ChaniM/tst-summarization with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ChaniM/tst-summarization 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="ChaniM/tst-summarization")# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("ChaniM/tst-summarization") model = AutoModelForSeq2SeqLM.from_pretrained("ChaniM/tst-summarization", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "predict_gen_len": 27.536553524804177, | |
| "predict_loss": 2.717167854309082, | |
| "predict_rouge1": 25.5341, | |
| "predict_rouge2": 8.9514, | |
| "predict_rougeL": 17.6839, | |
| "predict_rougeLsum": 22.0931, | |
| "predict_runtime": 5533.2858, | |
| "predict_samples": 11490, | |
| "predict_samples_per_second": 2.077, | |
| "predict_steps_per_second": 1.038 | |
| } |