Question Answering
Transformers
PyTorch
Safetensors
English
deberta-v2
deberta
deberta-v3
deberta-v3-large
Eval Results (legacy)
Instructions to use deepset/deberta-v3-large-squad2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use deepset/deberta-v3-large-squad2 with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "question-answering" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # pip install "transformers<5.0.0" from transformers import pipeline pipe = pipeline("question-answering", model="deepset/deberta-v3-large-squad2")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForQuestionAnswering tokenizer = AutoTokenizer.from_pretrained("deepset/deberta-v3-large-squad2") model = AutoModelForQuestionAnswering.from_pretrained("deepset/deberta-v3-large-squad2", device_map="auto") - Inference
- Notebooks
- Google Colab
- Kaggle
Commit History
-
Adding `safetensors` variant of this model
ca0bbbb
-
Adding model_max_length to the tokenizer config
Sebastian5b66c60
-
Add verifyToken field to verify evaluation results are produced by Hugging Face's automatic model evaluator (#8)
Sebastian +1: autoevaluator - Add verifyToken field to verify evaluation results are produced by Hugging Face's automatic model evaluator (f15e2df316f03bf05de5724308ab38d2174120fb) Co-authored-by: Evaluation Bot <autoevaluator@users.noreply.huggingface.co>cf83ca2
-
Update README.md
d88b80d
-
Add evaluation results on the plain_text config of squad (#4)
- Add evaluation results on the plain_text config of squad (9618ae2bf7cd8a72f85d6857cc12d38bc330f192) Co-authored-by: Evaluation Bot <autoevaluator@users.noreply.huggingface.co>a11a5ad
-
Update README.md (#2)
- Update README.md (95f00f71f5d8243c2524ce1c7c961ced7054cd8d)54d10aa -
Add evaluation results on the squad_v2 config of squad_v2 (#1)
- Add evaluation results on the squad_v2 config of squad_v2 (c8b7584fd31df58d9e4ead7bd17cfe15c8608dee) Co-authored-by: Evaluation Bot <autoevaluator@users.noreply.huggingface.co>f030715 -
Update README.md
a02020b -
Create README.md
de73c83 -
Add new model to Hugging Face.
7620389 -
initial commit
5a91a1a