Token Classification
Transformers
Safetensors
openai_privacy_filter
pii
ner
privacy
redaction
multilingual
openmed
openai-privacy-filter
Instructions to use OpenMed/privacy-filter-multilingual-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use OpenMed/privacy-filter-multilingual-v2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("token-classification", model="OpenMed/privacy-filter-multilingual-v2")# Load model directly from transformers import AutoTokenizer, AutoModelForTokenClassification tokenizer = AutoTokenizer.from_pretrained("OpenMed/privacy-filter-multilingual-v2") model = AutoModelForTokenClassification.from_pretrained("OpenMed/privacy-filter-multilingual-v2") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -135,6 +135,7 @@ already produces clean spans).
|
|
| 135 |
The output space is `O` plus `B-`, `I-`, `E-`, `S-` for each of the 54 categories
|
| 136 |
(4 ร 54 + 1 = 217). The `id2label` mapping is shipped with the model.
|
| 137 |
|
|
|
|
| 138 |
## Limitations & intended use
|
| 139 |
|
| 140 |
- **Multilingual but uneven.** Strongest on languages with rich PII training
|
|
|
|
| 135 |
The output space is `O` plus `B-`, `I-`, `E-`, `S-` for each of the 54 categories
|
| 136 |
(4 ร 54 + 1 = 217). The `id2label` mapping is shipped with the model.
|
| 137 |
|
| 138 |
+
|
| 139 |
## Limitations & intended use
|
| 140 |
|
| 141 |
- **Multilingual but uneven.** Strongest on languages with rich PII training
|