Instructions to use stanford-nlpxed/question-detection with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use stanford-nlpxed/question-detection with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("stanford-nlpxed/question-detection") model = AutoModel.from_pretrained("stanford-nlpxed/question-detection", device_map="auto") - Notebooks
- Google Colab
- Kaggle
File size: 464 Bytes
e03df0d | 1 | {"dataset_path": "data/switchboard_question_detection.json", "model_name": "bert-base-uncased", "checkpoint": "bert-base-uncased", "max_history": 0, "train_batch_size": 32, "valid_batch_size": 16, "gradient_accumulation_steps": 1, "max_length": 300, "lr": 6.25e-05, "max_norm": 1.0, "n_epochs": 3, "eval_before_start": true, "min_prev_length": 0, "final_speaker": -1, "fp16": "O2", "local_rank": -1, "head_attr": {"is_question": {"size": 2}}, "distributed": false} |