Instructions to use ra1nbowdash/mountain-ner-bert with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ra1nbowdash/mountain-ner-bert with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("token-classification", model="ra1nbowdash/mountain-ner-bert")# Load model directly from transformers import AutoTokenizer, AutoModelForTokenClassification tokenizer = AutoTokenizer.from_pretrained("ra1nbowdash/mountain-ner-bert") model = AutoModelForTokenClassification.from_pretrained("ra1nbowdash/mountain-ner-bert", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "best_epoch": 2.0, | |
| "best_dev_f1": 0.9401595744680851, | |
| "best_path": "/Users/nickol/My Fucking Stuff/machine learning/code/data-science-test-nlp-cv/ds-internship-assessment/Task_1_NLP/artifacts/models/bert_ner", | |
| "backbone": "dslim/bert-base-NER", | |
| "patience": 3, | |
| "history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_f1": 0.9242119382964454, | |
| "eval_precision": 0.9248322147651007, | |
| "eval_recall": 0.9235924932975871, | |
| "eval_loss": 0.02194095030426979 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_f1": 0.9401595744680851, | |
| "eval_precision": 0.9327176781002638, | |
| "eval_recall": 0.9477211796246648, | |
| "eval_loss": 0.017569638788700104 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_f1": 0.9386138613861386, | |
| "eval_precision": 0.9245773732119635, | |
| "eval_recall": 0.953083109919571, | |
| "eval_loss": 0.01644252985715866 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_f1": 0.9355263157894737, | |
| "eval_precision": 0.9186046511627907, | |
| "eval_recall": 0.953083109919571, | |
| "eval_loss": 0.02181176282465458 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_f1": 0.9381578947368421, | |
| "eval_precision": 0.9211886304909561, | |
| "eval_recall": 0.9557640750670241, | |
| "eval_loss": 0.02115728333592415 | |
| } | |
| ] | |
| } |