Zero-Shot Classification
Transformers
PyTorch
Safetensors
deberta-v2
text-classification
mdeberta-v3-base
nli
natural-language-inference
multitask
multi-task
pipeline
extreme-multi-task
extreme-mtl
tasksource
zero-shot
rlhf
Instructions to use sileod/mdeberta-v3-base-tasksource-nli with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use sileod/mdeberta-v3-base-tasksource-nli with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("zero-shot-classification", model="sileod/mdeberta-v3-base-tasksource-nli")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("sileod/mdeberta-v3-base-tasksource-nli") model = AutoModelForSequenceClassification.from_pretrained("sileod/mdeberta-v3-base-tasksource-nli", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download special_tokens_map.json from sileod/mdeberta-v3-base-tasksource-nli: direct link, hf CLI and curl.
- Browser
- Download file 173 Bytes
-
https://huggingface.co/sileod/mdeberta-v3-base-tasksource-nli/resolve/refs%2Fpr%2F1/special_tokens_map.json
- Command line
-
hf download hf://sileod/mdeberta-v3-base-tasksource-nli@refs/pr/1/special_tokens_map.json
-
curl -L -o special_tokens_map.json https://huggingface.co/sileod/mdeberta-v3-base-tasksource-nli/resolve/refs%2Fpr%2F1/special_tokens_map.json
173 Bytes
| { | |
| "bos_token": "[CLS]", | |
| "cls_token": "[CLS]", | |
| "eos_token": "[SEP]", | |
| "mask_token": "[MASK]", | |
| "pad_token": "[PAD]", | |
| "sep_token": "[SEP]", | |
| "unk_token": "[UNK]" | |
| } | |