Summarization
Transformers
TensorBoard
Safetensors
pegasus
text2text-generation
Trained with AutoTrain
Instructions to use chris-santiago/pegasus-samsum with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use chris-santiago/pegasus-samsum 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="chris-santiago/pegasus-samsum")# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("chris-santiago/pegasus-samsum") model = AutoModelForSeq2SeqLM.from_pretrained("chris-santiago/pegasus-samsum", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Model Trained Using AutoTrain
This model is a fine-tuned version of google/pegasus-cnn_dailymail on the samsum dataset.
- Problem type: Seq2Seq
Validation Metrics
loss: 1.4270155429840088
rouge1: 46.4301
rouge2: 23.4668
rougeL: 37.0224
rougeLsum: 42.8893
gen_len: 35.9694
runtime: 467.0921
samples_per_second: 1.751
steps_per_second: 0.439
: 1.0
- Downloads last month
- 24