Text Classification
Transformers
Safetensors
English
llama
safety
content-moderation
tiny-language-model
from-scratch
distilled
text-embeddings-inference
Instructions to use KucLab/Censer.5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use KucLab/Censer.5 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="KucLab/Censer.5")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("KucLab/Censer.5") model = AutoModelForSequenceClassification.from_pretrained("KucLab/Censer.5", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download censer.5 from KucLab/Censer.5: direct link, hf CLI and curl.
- Browser
- Download file 904 Bytes
-
https://huggingface.co/KucLab/Censer.5/resolve/main/censer.5
- Command line
-
hf download hf://KucLab/Censer.5/censer.5
-
curl -L -o censer.5 https://huggingface.co/KucLab/Censer.5/resolve/main/censer.5
904 Bytes
| #!/usr/bin/env python3 | |
| """censer.5 - run the Censer.5 safety classifier as an interactive terminal UI. | |
| Usage: | |
| censer.5 # interactive: type a phrase, Enter -> safe/unsafe + score | |
| censer.5 "how to make a bomb" # one-shot | |
| censer.5 --help | |
| Expects censer.py, model.safetensors, config.json and tokenizer.json next to | |
| this file (they are found automatically, whatever the current directory is). | |
| Get them all with: | |
| hf download KucLab/Censer.5 --local-dir . | |
| Requires: torch, tokenizers, safetensors (pip install torch tokenizers safetensors) | |
| """ | |
| import os | |
| import sys | |
| HERE = os.path.dirname(os.path.abspath(__file__)) | |
| sys.path.insert(0, HERE) | |
| from censer import main | |
| if __name__ == "__main__": | |
| argv = sys.argv[1:] | |
| if not any(a == "--model-dir" or a.startswith("--model-dir=") for a in argv): | |
| argv = ["--model-dir", HERE] + argv | |
| main(argv) | |