Downloads · 30 days
10
13% of all-time downloads
cws-coarse
tjspross/cws-coarse
cws-coarse is a token classification model from tjspross. 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
79
Public
Parameters
324M
2.6 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors1.3 GB · 100%
At a glance
- Task
- Token Classification
- Library
- transformers
- License
- apache-2.0
- Model type
- bert
- Access
- Public
- Created
- Jan 20, 2026
- Updated
- Mar 27, 2026
- SHA
- 53123c3b
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. -->
cws-coarse
This model is a fine-tuned version of hfl/chinese-roberta-wwm-ext-large on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.2171
- Precision: 0.9426
- Recall: 0.9408
- F1: 0.9417
- Accuracy: 0.9429
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 OptimizerNames.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: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 96 | 0.2096 | 0.9369 | 0.9355 | 0.9362 | 0.9351 |
| No log | 2.0 | 192 | 0.2062 | 0.9435 | 0.9393 | 0.9414 | 0.9427 |
| No log | 3.0 | 288 | 0.2171 | 0.9426 | 0.9408 | 0.9417 | 0.9429 |
Framework versions
- Transformers 4.49.0
- Pytorch 2.7.1+cu126
- Datasets 3.6.0
- Tokenizers 0.21.1
- Task
- Token Classification
- Library
- transformers
- Type
- bert
- License
- apache-2.0
- Created
- Jan 20, 2026
- Updated
- Mar 27, 2026