Summarization
Transformers
PyTorch
TensorFlow
JAX
English
pegasus
text2text-generation
Eval Results (legacy)
Instructions to use google/pegasus-xsum with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use google/pegasus-xsum 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="google/pegasus-xsum")# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("google/pegasus-xsum") model = AutoModelForSeq2SeqLM.from_pretrained("google/pegasus-xsum", device_map="auto") - Inference
- Notebooks
- Google Colab
- Kaggle
Download special_tokens_map.json from google/pegasus-xsum: direct link, hf CLI and curl.
- Browser
- Download file 65 Bytes
-
https://huggingface.co/google/pegasus-xsum/resolve/refs%2Fpr%2F9/special_tokens_map.json
- Command line
-
hf download hf://google/pegasus-xsum@refs/pr/9/special_tokens_map.json
-
curl -L -o special_tokens_map.json https://huggingface.co/google/pegasus-xsum/resolve/refs%2Fpr%2F9/special_tokens_map.json
65 Bytes
| {"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>"} |