Downloads · 30 days
5
1% of all-time downloads
nichal/pegasus_QR
pegasus_QR is a machine learning model from nichal. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for transformers.
PEGASUS model fine-tuned for the conversational question rewriting task.
Downloads · 30 days
5
1% of all-time downloads
All-time downloads
468
Public
Repo size
4.6 GB
Likes
0
Public
Click a slice to open those files.
.bin2.3 GB · 100%
From the Hugging Face model README
PEGASUS model fine-tuned for the conversational question rewriting task.
Used to rewrite questions using previous conversation turns into self-contained questions (i.e. questions that can be understood outside the conversation context)
>>> from transformers import PegasusForConditionalGeneration, PegasusTokenizer
>>> tokenizer = PegasusTokenizer.from_pretrained('nichal/pegasus_QR')
>>> model = PegasusForConditionalGeneration.from_pretrained('nichal/pegasus_QR')
Initialized with pre-trained model PEGASUS-large, fine-tuned using cross-entropy and self-critical sequence training.