Zero-Shot Classification
Transformers
PyTorch
Safetensors
English
deberta-v2
text-classification
deberta-v3-large
nli
natural-language-inference
multitask
multi-task
pipeline
extreme-multi-task
extreme-mtl
tasksource
zero-shot
rlhf
Instructions to use sileod/deberta-v3-large-tasksource-nli with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use sileod/deberta-v3-large-tasksource-nli with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("zero-shot-classification", model="sileod/deberta-v3-large-tasksource-nli")# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("sileod/deberta-v3-large-tasksource-nli") model = AutoModelForSequenceClassification.from_pretrained("sileod/deberta-v3-large-tasksource-nli") - Notebooks
- Google Colab
- Kaggle
Why is this model significantly bigger than microsoft/deberta-v3-large
#3
by cyenjoylife - opened
The original pytorch_model.bin under microsoft/deberta-v3-large is 874MB, but the pytorch_model.bin file here is 1.7GB. I'm wondering why this model is much bigger. Is this model saved in full precision? Very much appreciate your reply!