Instructions to use tweettemposhift/ner-ner_random2_seed2-bertweet-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use tweettemposhift/ner-ner_random2_seed2-bertweet-base with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("token-classification", model="tweettemposhift/ner-ner_random2_seed2-bertweet-base")# Load model directly from transformers import AutoTokenizer, AutoModelForTokenClassification tokenizer = AutoTokenizer.from_pretrained("tweettemposhift/ner-ner_random2_seed2-bertweet-base") model = AutoModelForTokenClassification.from_pretrained("tweettemposhift/ner-ner_random2_seed2-bertweet-base") - Notebooks
- Google Colab
- Kaggle
| {"test/eval_loss": 0.37003591656684875, "test/eval_corporation": {"precision": 0.5218934911242603, "recall": 0.5632183908045977, "f1": 0.5417690417690417, "number": 783}, "test/eval_creative_work": {"precision": 0.43526170798898073, "recall": 0.38164251207729466, "f1": 0.40669240669240664, "number": 414}, "test/eval_event": {"precision": 0.5463743676222597, "recall": 0.5094339622641509, "f1": 0.5272579332790888, "number": 636}, "test/eval_group": {"precision": 0.6984126984126984, "recall": 0.6586826347305389, "f1": 0.6779661016949153, "number": 1002}, "test/eval_location": {"precision": 0.6013513513513513, "recall": 0.6716981132075471, "f1": 0.6345811051693405, "number": 265}, "test/eval_person": {"precision": 0.8745198463508322, "recall": 0.8760153911928175, "f1": 0.8752669799231098, "number": 2339}, "test/eval_product": {"precision": 0.7122692725298588, "recall": 0.7248618784530386, "f1": 0.7185104052573932, "number": 905}, "test/eval_overall_precision": 0.7082143989850935, "test/eval_overall_recall": 0.7039722572509458, "test/eval_overall_f1": 0.706086956521739, "test/eval_overall_accuracy": 0.8982538064388832, "test/eval_runtime": 3.9856, "test/eval_samples_per_second": 175.884, "test/eval_steps_per_second": 22.08} |