Downloads · 30 days
9
12% of all-time downloads
parsbert_keyphrase
hesamheidari/parsbert_keyphrase
parsbert_keyphrase is a token classification model from hesamheidari. Use it when you need labels on individual words, such as names. It is set up for transformers. The card lists the license as apache-2.0.
should probably proofread and complete it, then remove this comment. --
All-time downloads
75
Public
Parameters
122M
2.4 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors489 MB · 99%
At a glance
- Task
- Token Classification
- Library
- transformers
- License
- apache-2.0
- Model type
- bert
- Access
- Public
- Created
- Aug 12, 2025
- Updated
- Aug 24, 2025
- SHA
- c7a65584
Try a prompt
Base models
Model card
From the Hugging Face model README
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
parsbert_keyphrase
This model is a fine-tuned version of PartAI/TookaBERT-Base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1877
- Precision: 0.4982
- Recall: 0.4979
- F1: 0.4980
- Accuracy: 0.9390
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: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.1362 | 1.0 | 2107 | 0.1609 | 0.4950 | 0.4504 | 0.4717 | 0.9408 |
| 0.1231 | 2.0 | 4214 | 0.1589 | 0.5069 | 0.4569 | 0.4806 | 0.9420 |
| 0.1097 | 3.0 | 6321 | 0.1671 | 0.4976 | 0.4902 | 0.4939 | 0.9406 |
| 0.0961 | 4.0 | 8428 | 0.1752 | 0.5032 | 0.4885 | 0.4958 | 0.9398 |
| 0.0861 | 5.0 | 10535 | 0.1877 | 0.4982 | 0.4979 | 0.4980 | 0.9390 |
Framework versions
- Transformers 4.48.3
- Pytorch 2.6.0+cu124
- Datasets 3.4.0
- Tokenizers 0.21.1
- Task
- Token Classification
- Library
- transformers
- Type
- bert
- License
- apache-2.0
- Created
- Aug 12, 2025
- Updated
- Aug 24, 2025