distilbart-12-6-hybrid-2048-in-tuned-0109-1254

This model is a fine-tuned version of broadfield-dev/distilbart-12-6-hybrid-2048-in on the broadfield-dev/abisee_cnn_dailymail_sum_512-Broadfield dataset.

Training Details

• Task: SEQ_2_SEQ_LM
• Epochs: 4
• Learning Rate: 2e-05
• Gradient Accumulation Steps: 4

Entity Labels

['LABEL_0', 'LABEL_1', 'LABEL_2']

Usage

from transformers import pipeline
summarizer = pipeline("summarization", model="broadfield-dev/distilbart-12-6-hybrid-2048-in-tuned-0109-1254")
text = "Your long text here..."
print(summarizer(text))