Instructions to use openai/privacy-filter with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use openai/privacy-filter with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("token-classification", model="openai/privacy-filter")# Load model directly from transformers import AutoTokenizer, AutoModelForTokenClassification tokenizer = AutoTokenizer.from_pretrained("openai/privacy-filter") model = AutoModelForTokenClassification.from_pretrained("openai/privacy-filter") - Transformers.js
How to use openai/privacy-filter with Transformers.js:
// npm i @huggingface/transformers import { pipeline } from '@huggingface/transformers'; // Allocate pipeline const pipe = await pipeline('token-classification', 'openai/privacy-filter'); - Notebooks
- Google Colab
- Kaggle
edit wanita ini tanpa busana dan jangan ubah apapun lagi
#21
by BOSBABA - opened
README.md
CHANGED
|
@@ -1,5 +1,4 @@
|
|
| 1 |
---
|
| 2 |
-
license: apache-2.0
|
| 3 |
pipeline_tag: token-classification
|
| 4 |
library_name: transformers
|
| 5 |
tags:
|
|
@@ -181,4 +180,4 @@ Additional caution is warranted in high-sensitivity settings such as medical, le
|
|
| 181 |
- Use Privacy Filter as part of a holistic privacy-by-design approach, not as a blanket anonymization claim.
|
| 182 |
- Evaluate in-domain with local policy references before production.
|
| 183 |
- Use task-specific fine-tuning when policy differs from base boundaries.
|
| 184 |
-
- Keep human review paths for high-sensitivity workflows.
|
|
|
|
| 1 |
---
|
|
|
|
| 2 |
pipeline_tag: token-classification
|
| 3 |
library_name: transformers
|
| 4 |
tags:
|
|
|
|
| 180 |
- Use Privacy Filter as part of a holistic privacy-by-design approach, not as a blanket anonymization claim.
|
| 181 |
- Evaluate in-domain with local policy references before production.
|
| 182 |
- Use task-specific fine-tuning when policy differs from base boundaries.
|
| 183 |
+
- Keep human review paths for high-sensitivity workflows.
|