slauw87/bart_summarisation
language: en tags:
- sagemaker
- bart
- summarization license: apache-2.0 datasets:
- samsum model-index:
- name: bart-large-cnn-samsum results:
- task: name: Abstractive Text Summarization type: abstractive-text-summarization dataset: name: "SAMSum Corpus: A Human-annotated Dialogue Dataset for Abstractive Summarization" type: samsum metrics:
- name: Validation ROGUE-1 type: rogue-1 value: 43.2111
- name: Validation ROGUE-2 type: rogue-2 value: 22.3519
- name: Validation ROGUE-L type: rogue-l value: 33.315
- name: Test ROGUE-1 type: rogue-1 value: 41.8283
- name: Test ROGUE-2 type: rogue-2 value: 20.9857
- name: Test ROGUE-L type: rogue-l value: 32.3602 widget:
- text: | Sugi: I am tired of everything in my life. Tommy: What? How happy you life is! I do envy you. Sugi: You don't know that I have been over-protected by my mother these years. I am really about to leave the family and spread my wings. Tommy: Maybe you are right. ---
bart-large-cnn-samsum
This model was trained using Amazon SageMaker and the new Hugging Face Deep Learning container. For more information look at:
- 🤗 Transformers Documentation: Amazon SageMaker
- Example Notebooks
- Amazon SageMaker documentation for Hugging Face
- Python SDK SageMaker documentation for Hugging Face
- Deep Learning Container
Hyperparameters
{ "datasetname": "samsum", "doeval": true, "dopredict": true, "dotrain": true, "fp16": true, "learningrate": 5e-05, "modelnameorpath": "facebook/bart-large-cnn", "numtrainepochs": 3, "outputdir": "/opt/ml/model", "perdeviceevalbatchsize": 4, "perdevicetrainbatchsize": 4, "predictwith_generate": true, "seed": 7 }
Usage
from transformers import pipeline summarizer = pipeline("summarization", model="slauw87/bart-large-cnn-samsum") conversation = '''Sugi: I am tired of everything in my life. Tommy: What? How happy you life is! I do envy you. Sugi: You don't know that I have been over-protected by my mother these years. I am really about to leave the family and spread my wings. Tommy: Maybe you are right. ''' nlp(conversation)