# Load model directly
from transformers import AutoTokenizer, AutoModelForTokenClassification
tokenizer = AutoTokenizer.from_pretrained("philschmid/gbert-base-germaner")
model = AutoModelForTokenClassification.from_pretrained("philschmid/gbert-base-germaner")Quick Links
gbert-base-germaner
This model is a fine-tuned version of deepset/gbert-base on the germaner dataset. It achieves the following results on the evaluation set:
- precision: 0.8521
- recall: 0.8754
- f1: 0.8636
- accuracy: 0.9761
If you want to learn how to fine-tune BERT yourself using Keras and Tensorflow check out this blog post:
https://www.philschmid.de/huggingface-transformers-keras-tf
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- num_train_epochs: 5
- train_batch_size: 16
- eval_batch_size: 32
- learning_rate: 2e-05
- weight_decay_rate: 0.01
- num_warmup_steps: 0
- fp16: True
Framework versions
- Transformers 4.14.1
- Datasets 1.16.1
- Tokenizers 0.10.3
- Downloads last month
- 15
Dataset used to train philschmid/gbert-base-germaner
Evaluation results
- precision on germanerself-reported0.852
- recall on germanerself-reported0.875
- f1 on germanerself-reported0.864
- accuracy on germanerself-reported0.976
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("token-classification", model="philschmid/gbert-base-germaner")