Instructions to use deepset/bert-base-cased-squad2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use deepset/bert-base-cased-squad2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("question-answering", model="deepset/bert-base-cased-squad2")# Load model directly from transformers import AutoTokenizer, AutoModelForQuestionAnswering tokenizer = AutoTokenizer.from_pretrained("deepset/bert-base-cased-squad2") model = AutoModelForQuestionAnswering.from_pretrained("deepset/bert-base-cased-squad2") - Inference
- Notebooks
- Google Colab
- Kaggle
| { | |
| "architectures": [ | |
| "BertForQuestionAnswering" | |
| ], | |
| "attention_probs_dropout_prob": 0.1, | |
| "hidden_act": "gelu", | |
| "hidden_dropout_prob": 0.1, | |
| "hidden_size": 768, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 3072, | |
| "language": "english", | |
| "layer_norm_eps": 1e-12, | |
| "max_position_embeddings": 512, | |
| "model_type": "bert", | |
| "name": "Bert", | |
| "num_attention_heads": 12, | |
| "num_hidden_layers": 12, | |
| "output_past": true, | |
| "pad_token_id": 0, | |
| "type_vocab_size": 2, | |
| "vocab_size": 28996 | |
| } | |