ParsBERT: Transformer-based Model for Persian Language Understanding
Paper • 2005.12515 • Published
# Load model directly
from transformers import AutoTokenizer, AutoModelForQuestionAnswering
tokenizer = AutoTokenizer.from_pretrained("ForutanRad/bert-fa-QA-v1")
model = AutoModelForQuestionAnswering.from_pretrained("ForutanRad/bert-fa-QA-v1")Quick Links
bert-fa-QA-v1
Persian Question and answer Model Based on Bert Model
This model is a fine-tuned version of ParsBERT on PersianQA dataset. It achieves the following results on the evaluation set:
- Loss: 1.7297
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:
- learning_rate: 3e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.2563 | 1.0 | 1126 | 1.7222 |
| 1.3372 | 2.0 | 2252 | 1.7297 |
Framework versions
- Transformers 4.9.0
- Pytorch 1.9.0+cu102
- Tokenizers 0.10.3
- Downloads last month
- 5
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("question-answering", model="ForutanRad/bert-fa-QA-v1")