Question Answering
Transformers
PyTorch
Safetensors
English
deberta-v2
deberta
deberta-v3
Eval Results (legacy)
Instructions to use deepset/deberta-v3-base-squad2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use deepset/deberta-v3-base-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-base-squad2")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForQuestionAnswering tokenizer = AutoTokenizer.from_pretrained("deepset/deberta-v3-base-squad2") model = AutoModelForQuestionAnswering.from_pretrained("deepset/deberta-v3-base-squad2", device_map="auto") - Inference
- Notebooks
- Google Colab
- Kaggle
Commit History
-
Adding `safetensors` variant of this model
5fcc6cb
-
Adding model_max_length to the tokenizer config
Sebastian9258f36
-
Add verifyToken field to verify evaluation results are produced by Hugging Face's automatic model evaluator (#5)
Sebastian +1: autoevaluator - Add verifyToken field to verify evaluation results are produced by Hugging Face's automatic model evaluator (9bf0ac54995654b82e7631f74a63f312fe071e41) Co-authored-by: Evaluation Bot <autoevaluator@users.noreply.huggingface.co>ba6be5b
-
Update README.md
3528ea1
-
Add evaluation results on the plain_text config of squad (#3)
- Add evaluation results on the plain_text config of squad (7f39e06e840a955dc8f6d7b383f1a6c760b3bc5e) Co-authored-by: Evaluation Bot <autoevaluator@users.noreply.huggingface.co>09fb13f
-
Update README.md
2795a73
-
Update README.md
5540fdf -
Add evaluation results on the squad_v2 config of squad_v2 (#1)
- Add evaluation results on the squad_v2 config of squad_v2 (94f9c873fccd1b85f3ce6fc89cdf6029e3a988a1) Co-authored-by: Evaluation Bot <autoevaluator@users.noreply.huggingface.co>5bcc058 -
Update README.md
b360ddf
-
Update README.md
fe4e3d2 -
Update README.md
a602180 -
Update README.md
4a0e5e6 -
Create README.md
c8b512d -
Update tokenizer_config.json
fddfce4 -
Update config.json
1c4ed4b -
Add new model to Hugging Face.
48d0b9a -
initial commit
cb1878a