Instructions to use PassbyGrocer/resume_ner_herb with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use PassbyGrocer/resume_ner_herb with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("token-classification", model="PassbyGrocer/resume_ner_herb")# Load model directly from transformers import AutoTokenizer, BertLstmCRF tokenizer = AutoTokenizer.from_pretrained("PassbyGrocer/resume_ner_herb") model = BertLstmCRF.from_pretrained("PassbyGrocer/resume_ner_herb", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| library_name: transformers | |
| license: mit | |
| datasets: | |
| - PassbyGrocer/resume-ner | |
| language: | |
| - zh | |
| metrics: | |
| - precision | |
| - recall | |
| - f1 | |
| base_model: | |
| - hfl/chinese-roberta-wwm-ext | |
| pipeline_tag: token-classification | |
| eval_p = 0.9822171390155553 | |
| eval_r = 0.9790383704405495 | |
| eval_f1 = 0.9806131065277388 | |
| train result | |
| | Epoch | Training Loss | Validation Loss | Precision | Recall | F1 | | |
| |-------|---------------|-----------------|-----------|----------|----------| | |
| | 1 | No log | 223.361084 | 0.980017 | 0.937134 | 0.957643 | | |
| | 2 | No log | 61.423782 | 0.973549 | 0.959132 | 0.965962 | | |
| | 3 | 2994.676800 | 72.477470 | 0.976213 | 0.962664 | 0.969052 | | |
| | 4 | 2994.676800 | 103.387581 | 0.971125 | 0.962664 | 0.966845 | | |
| | 5 | 33.797800 | 156.035553 | 0.975023 | 0.964581 | 0.969666 | | |
| | 6 | 33.797800 | 265.293549 | 0.971879 | 0.969324 | 0.970583 | | |
| | 7 | 20.226000 | 766.043457 | 0.974243 | 0.965187 | 0.969429 | | |
| | 8 | 20.226000 | 1143.557495 | 0.974143 | 0.965691 | 0.969722 | | |
| | 9 | 23.267200 | 996.235901 | 0.974592 | 0.968517 | 0.971405 | | |
| | 10 | 23.267200 | 959.597229 | 0.974522 | 0.966398 | 0.970242 | | |
| eval result | |
| | Label | Precision | Recall | F1-Score | Support | | |
| |-------------|-----------|--------|----------|---------| | |
| | B-CONT | 1.00 | 1.00 | 1.00 | 33 | | |
| | B-EDU | 1.00 | 1.00 | 1.00 | 106 | | |
| | B-LOC | 1.00 | 1.00 | 1.00 | 2 | | |
| | B-NAME | 1.00 | 1.00 | 1.00 | 110 | | |
| | B-ORG | 0.99 | 0.98 | 0.98 | 523 | | |
| | B-PRO | 0.95 | 1.00 | 0.97 | 18 | | |
| | B-RACE | 1.00 | 1.00 | 1.00 | 15 | | |
| | B-TITLE | 0.96 | 0.96 | 0.96 | 690 | | |
| | I-CONT | 1.00 | 1.00 | 1.00 | 97 | | |
| | I-EDU | 1.00 | 1.00 | 1.00 | 283 | | |
| | I-LOC | 1.00 | 1.00 | 1.00 | 8 | | |
| | I-NAME | 1.00 | 1.00 | 1.00 | 177 | | |
| | I-ORG | 0.99 | 0.98 | 0.99 | 4146 | | |
| | I-PRO | 0.93 | 1.00 | 0.96 | 51 | | |
| | I-RACE | 1.00 | 1.00 | 1.00 | 14 | | |
| | I-TITLE | 0.97 | 0.97 | 0.97 | 2171 | | |
| | O | 0.00 | 0.00 | 0.00 | 0 | | |
| {'eval_loss': 684.596923828125, 'eval_precision': 0.9822171390155553, 'eval_recall': 0.9790383704405495, 'eval_f1': 0.9806131065277388, 'eval_runtime': 5.8637, 'eval_samples_per_second': 78.96, 'eval_steps_per_second': 4.946, 'epoch': 10.0} | |