Instructions to use DAMO-NLP-SG/roberta-time_identification with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use DAMO-NLP-SG/roberta-time_identification with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("token-classification", model="DAMO-NLP-SG/roberta-time_identification")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForTokenClassification tokenizer = AutoTokenizer.from_pretrained("DAMO-NLP-SG/roberta-time_identification") model = AutoModelForTokenClassification.from_pretrained("DAMO-NLP-SG/roberta-time_identification", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download predict_results.json from DAMO-NLP-SG/roberta-time_identification: direct link, hf CLI and curl.
- Browser
- Download file 279 Bytes
-
https://huggingface.co/DAMO-NLP-SG/roberta-time_identification/resolve/main/predict_results.json
- Command line
-
hf download hf://DAMO-NLP-SG/roberta-time_identification/predict_results.json
-
curl -L -o predict_results.json https://huggingface.co/DAMO-NLP-SG/roberta-time_identification/resolve/main/predict_results.json
279 Bytes
| { | |
| "predict_accuracy": 0.9436280563102001, | |
| "predict_f1": 0.0, | |
| "predict_loss": 0.3772517442703247, | |
| "predict_precision": 0.0, | |
| "predict_recall": 0.0, | |
| "predict_runtime": 14.6577, | |
| "predict_samples_per_second": 47.415, | |
| "predict_steps_per_second": 0.205 | |
| } |