Instructions to use microsoft/ssr-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use microsoft/ssr-base 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="microsoft/ssr-base")# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("microsoft/ssr-base") model = AutoModelForSeq2SeqLM.from_pretrained("microsoft/ssr-base", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| language: | |
| - en | |
| datasets: | |
| - c4 | |
| tags: | |
| - summarization | |
| - text2text-generation | |
| # SSR-base | |
| SSR-base model as in EMNLP 2021 paper [Improving Sequence-to-Sequence Pre-training via Sequence Span Rewriting](https://arxiv.org/abs/2101.00416). | |