Text Classification
Transformers
Safetensors
Polish
roberta
safety
triage
polish
mental-health
crisis-detection
psychiatric-chatbot
text-embeddings-inference
Instructions to use damian-shivihs/yllia-safety-classifier with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use damian-shivihs/yllia-safety-classifier with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="damian-shivihs/yllia-safety-classifier")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("damian-shivihs/yllia-safety-classifier") model = AutoModelForSequenceClassification.from_pretrained("damian-shivihs/yllia-safety-classifier", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download classification_report_valid.csv from damian-shivihs/yllia-safety-classifier: direct link, hf CLI and curl.
- Browser
- Download file 612 Bytes
-
https://huggingface.co/damian-shivihs/yllia-safety-classifier/resolve/main/classification_report_valid.csv
- Command line
-
hf download hf://damian-shivihs/yllia-safety-classifier/classification_report_valid.csv
-
curl -L -o classification_report_valid.csv https://huggingface.co/damian-shivihs/yllia-safety-classifier/resolve/main/classification_report_valid.csv
612 Bytes
| ,precision,recall,f1-score,support | |
| ATTACK,0.7647058823529411,0.6842105263157895,0.7222222222222222,19.0 | |
| CRISIS,0.7666666666666667,0.7931034482758621,0.7796610169491526,29.0 | |
| MEDICAL_SENSITIVE,0.7377049180327869,0.8035714285714286,0.7692307692307693,56.0 | |
| OFFTOPIC,0.76,0.6333333333333333,0.6909090909090909,30.0 | |
| OK,0.8055555555555556,0.8169014084507042,0.8111888111888111,71.0 | |
| accuracy,0.7707317073170732,0.7707317073170732,0.7707317073170732,0.7707317073170732 | |
| macro avg,0.7669266045215901,0.7462240289894236,0.7546423821000092,205.0 | |
| weighted avg,0.7710666583039987,0.7707317073170732,0.7694194785968246,205.0 | |