Downloads · 30 days
3
10% of all-time downloads
bozhidara-pesheva/distilbert-base-uncased-no-perturb
distilbert-base-uncased-no-perturb is a token classification model from bozhidara-pesheva. 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. --
Downloads · 30 days
3
10% of all-time downloads
All-time downloads
30
Public
Parameters
66.4M
265 MB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors265 MB · 100%
From the Hugging Face model README
This model is a fine-tuned version of distilbert/distilbert-base-uncased on the None dataset. It achieves the following results on the evaluation set:
More information needed
More information needed
More information needed
The following hyperparameters were used during training:
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 103 | 0.1871 | 0.1940 | 0.1238 | 0.1512 | 0.9499 |
| No log | 2.0 | 206 | 0.1603 | 0.2885 | 0.3476 | 0.3153 | 0.9540 |
| No log | 3.0 | 309 | 0.1545 | 0.3826 | 0.3778 | 0.3802 | 0.9597 |