Instructions to use tweettemposhift/ner-ner_random0_seed2-roberta-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use tweettemposhift/ner-ner_random0_seed2-roberta-base with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("token-classification", model="tweettemposhift/ner-ner_random0_seed2-roberta-base")# Load model directly from transformers import AutoTokenizer, AutoModelForTokenClassification tokenizer = AutoTokenizer.from_pretrained("tweettemposhift/ner-ner_random0_seed2-roberta-base") model = AutoModelForTokenClassification.from_pretrained("tweettemposhift/ner-ner_random0_seed2-roberta-base") - Notebooks
- Google Colab
- Kaggle
| {"test/eval_loss": 0.37680888175964355, "test/eval_corporation": {"precision": 0.5780089153046062, "recall": 0.5172872340425532, "f1": 0.5459649122807018, "number": 752}, "test/eval_creative_work": {"precision": 0.3625, "recall": 0.4447852760736196, "f1": 0.3994490358126722, "number": 326}, "test/eval_event": {"precision": 0.48484848484848486, "recall": 0.4514991181657848, "f1": 0.46757990867579907, "number": 567}, "test/eval_group": {"precision": 0.7237209302325581, "recall": 0.6140489344909235, "f1": 0.6643894107600342, "number": 1267}, "test/eval_location": {"precision": 0.44021739130434784, "recall": 0.6558704453441295, "f1": 0.526829268292683, "number": 247}, "test/eval_person": {"precision": 0.8254185172531602, "recall": 0.9123867069486404, "f1": 0.8667264573991031, "number": 2648}, "test/eval_product": {"precision": 0.6397379912663755, "recall": 0.6576879910213244, "f1": 0.6485888212506917, "number": 891}, "test/eval_overall_precision": 0.6870916218963264, "test/eval_overall_recall": 0.7064795461331741, "test/eval_overall_f1": 0.6966507177033493, "test/eval_overall_accuracy": 0.8906750331532813, "test/eval_runtime": 3.9525, "test/eval_samples_per_second": 177.358, "test/eval_steps_per_second": 22.265} |