Instructions to use tweettemposhift/ner-ner_random3_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_random3_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_random3_seed2-roberta-base")# Load model directly from transformers import AutoTokenizer, AutoModelForTokenClassification tokenizer = AutoTokenizer.from_pretrained("tweettemposhift/ner-ner_random3_seed2-roberta-base") model = AutoModelForTokenClassification.from_pretrained("tweettemposhift/ner-ner_random3_seed2-roberta-base") - Notebooks
- Google Colab
- Kaggle
| {"test/eval_loss": 0.36488401889801025, "test/eval_corporation": {"precision": 0.4616519174041298, "recall": 0.4556040756914119, "f1": 0.4586080586080586, "number": 687}, "test/eval_creative_work": {"precision": 0.3839541547277937, "recall": 0.36813186813186816, "f1": 0.3758765778401122, "number": 364}, "test/eval_event": {"precision": 0.4809917355371901, "recall": 0.4298375184638109, "f1": 0.4539781591263651, "number": 677}, "test/eval_group": {"precision": 0.7509191176470589, "recall": 0.7018900343642611, "f1": 0.7255772646536411, "number": 1164}, "test/eval_location": {"precision": 0.5909090909090909, "recall": 0.5889967637540453, "f1": 0.5899513776337115, "number": 309}, "test/eval_person": {"precision": 0.8866459627329193, "recall": 0.9059896866322887, "f1": 0.8962134588973907, "number": 2521}, "test/eval_product": {"precision": 0.6906820365033621, "recall": 0.752092050209205, "f1": 0.7200801201802703, "number": 956}, "test/eval_overall_precision": 0.7133182844243793, "test/eval_overall_recall": 0.7097933513027853, "test/eval_overall_f1": 0.7115514523755911, "test/eval_overall_accuracy": 0.8960939003271118, "test/eval_runtime": 4.0034, "test/eval_samples_per_second": 175.852, "test/eval_steps_per_second": 21.982} |