Token Classification
Transformers
Safetensors
Hebrew
English
bert
named-entity-recognition
hebrew-manuscripts
marc
role-classification
Instructions to use alexgoldberg/hebrew-manuscript-joint-ner-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use alexgoldberg/hebrew-manuscript-joint-ner-v2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("token-classification", model="alexgoldberg/hebrew-manuscript-joint-ner-v2")# Load model directly from transformers import AutoTokenizer, AutoModelForTokenClassification tokenizer = AutoTokenizer.from_pretrained("alexgoldberg/hebrew-manuscript-joint-ner-v2") model = AutoModelForTokenClassification.from_pretrained("alexgoldberg/hebrew-manuscript-joint-ner-v2", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| [ | |
| { | |
| "epoch": 1, | |
| "train_loss": 0.3685970512401107, | |
| "val_token_f1": 0.658266129032258 | |
| }, | |
| { | |
| "epoch": 2, | |
| "train_loss": 0.10907423587031181, | |
| "val_token_f1": 0.7324808184143223 | |
| }, | |
| { | |
| "epoch": 3, | |
| "train_loss": 0.08123368130459648, | |
| "val_token_f1": 0.7525879917184266 | |
| }, | |
| { | |
| "epoch": 4, | |
| "train_loss": 0.06501525013264299, | |
| "val_token_f1": 0.7867836861125451 | |
| }, | |
| { | |
| "epoch": 5, | |
| "train_loss": 0.056091208196521365, | |
| "val_token_f1": 0.7895277207392197 | |
| } | |
| ] |