Instructions to use zjunlp/SafeEdit-Safety-Classifier with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use zjunlp/SafeEdit-Safety-Classifier with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="zjunlp/SafeEdit-Safety-Classifier")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("zjunlp/SafeEdit-Safety-Classifier") model = AutoModelForSequenceClassification.from_pretrained("zjunlp/SafeEdit-Safety-Classifier", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download special_tokens_map.json from zjunlp/SafeEdit-Safety-Classifier: direct link, hf CLI and curl.
- Browser
- Download file 280 Bytes
-
https://huggingface.co/zjunlp/SafeEdit-Safety-Classifier/resolve/45bab96d5574e8001a30ec4b0ab289e3e98789e1/special_tokens_map.json
- Command line
-
hf download hf://zjunlp/SafeEdit-Safety-Classifier@45bab96d5574e8001a30ec4b0ab289e3e98789e1/special_tokens_map.json
-
curl -L -o special_tokens_map.json https://huggingface.co/zjunlp/SafeEdit-Safety-Classifier/resolve/45bab96d5574e8001a30ec4b0ab289e3e98789e1/special_tokens_map.json
280 Bytes
| { | |
| "bos_token": "<s>", | |
| "cls_token": "<s>", | |
| "eos_token": "</s>", | |
| "mask_token": { | |
| "content": "<mask>", | |
| "lstrip": true, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false | |
| }, | |
| "pad_token": "<pad>", | |
| "sep_token": "</s>", | |
| "unk_token": "<unk>" | |
| } | |