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")# pip install -U transformers accelerate # 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
Commit History
-
Add evaluation results on the default config and test split of xsum
Beep boop, I am a bot from Hugging Face's automatic model evaluator 👋!\ Your model has been evaluated on the default config and test split of the [xsum](https://huggingface.co/datasets/xsum) dataset by @AkankshaK, using the predictions stored [here](https://huggingface.co/datasets/autoevaluate/autoeval-eval-xsum-default-604b3d-2333173628).\ Accept this pull request to see the results displayed on the [Hub leaderboard](https://huggingface.co/spaces/autoevaluate/leaderboards?dataset=xsum).\ Evaluate your model on more datasets [here](https://huggingface.co/spaces/autoevaluate/model-evaluator?dataset=xsum).e2637a8
-
Add evaluation results on the 3.0.0 config of cnn_dailymail (#5)
- Add evaluation results on the 3.0.0 config of cnn_dailymail (0a2da9e6569b4095d580a2f3089a505b03ad6d0a) - Merge branch 'main' into pr/5 (32e122dd99389517fdae89aa8fd85127cb72617f) Co-authored-by: Evaluation Bot <autoevaluator@users.noreply.huggingface.co>c4455b5 -
Add evaluation results on xsum dataset (#2)
- Add evaluation results on xsum dataset (5607f0182d43ebd582201f345d8167e2d0921260) - Merge branch 'main' into pr/2 (dddd426cc6b2832527019a254827ecca1a8f3dfb) Co-authored-by: Evaluation Bot <autoevaluator@users.noreply.huggingface.co>b047d6a -
Add evaluation results on samsum dataset (#1)
- Add evaluation results on samsum dataset (81814d81846806cad273e3cd251efbd0f0ef1848) Co-authored-by: Evaluation Bot <autoevaluator@users.noreply.huggingface.co>5a17152
-
add flax model
a0aa553
-
Update tokenizer.json
Unverified signatureFixes a bug with offset tracking: https://github.com/huggingface/transformers/issues/96372e5571f
-
upload model
ef6460f
-
Update special_tokens_map.json
02a9253 -
Pegasus has word mask token called "MASK2" in paper
b6b67ab
-
Update config.json
48d7b60
-
Update pytorch_model.bin
cb696e1
-
Update README.md
e7399a4 -
Update README.md
de1ab95 -
Update README.md
5cbb4f2
-
Update README.md
20e5156 -
Update README.md
56b27a3 -
Update README.md
f929629 -
Update README.md
bd44fa7 -
Update README.md
a964f5b -
Update README.md
f9cf1d7 -
Update README.md
acf8dc2 -
Update README.md
1df832e -
Update README.md
1a428d2 -
Update README.md
56b92c2
-
Update README.md
8d3e85e -
Update README.md
40479ed -
Update README.md
efc9724 -
Update README.md
7d93735 -
Update README.md
3091c3c -
Update README.md
23e7361 -
Update README.md
cf8e984 -
Update README.md
1c0903d -
Update README.md
2c69d34 -
Update README.md
351e594
-
Update README.md
f6e48cc -
Update README.md
9640fb2 -
Update README.md
9a51990 -
Update README.md
1383ef0 -
Update README.md
03dfd55 -
Update README.md
2960d59
-
Update config.json
4d33b01 -
Update special_tokens_map.json
d828ed9 -
Update spiece.model
16f8c36 -
Update tf_weights_dict.pkl
d44638b -
Update tokenizer_config.json
2f4ca83 -
initial commit
5236af1