Instructions to use descentis/distilbert-cuad with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use descentis/distilbert-cuad with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("question-answering", model="descentis/distilbert-cuad")# Load model directly from transformers import AutoTokenizer, AutoModelForQuestionAnswering tokenizer = AutoTokenizer.from_pretrained("descentis/distilbert-cuad") model = AutoModelForQuestionAnswering.from_pretrained("descentis/distilbert-cuad", device_map="auto") - Notebooks
- Google Colab
- Kaggle
File size: 700 Bytes
cc9a049 | 1 | {"baskets": [], "data_dir": "data", "dev_filename": "dev-v2.0.json", "dev_split": 0, "doc_stride": 128, "max_answers": 6, "max_query_length": 64, "max_seq_len": 256, "multithreading_rust": true, "ph_output_type": "per_token_squad", "proxies": null, "sp_toks_end": 1, "sp_toks_mid": 1, "sp_toks_start": 1, "tasks": {"question_answering": {"label_list": ["start_token", "end_token"], "metric": "squad", "label_tensor_name": "question_answering_label_ids", "label_name": "question_answering_label", "label_column_name": null, "text_column_name": null, "task_type": null}}, "test_filename": null, "train_filename": "train-v2.0.json", "tokenizer": "DistilBertTokenizerFast", "processor": "SquadProcessor"} |