Text Classification
Transformers
ONNX
Safetensors
modernbert
prompt-injection
jailbreak-detection
llm-security
ai-agents
guardrails
text-embeddings-inference
Instructions to use usezn/Galvanize-2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use usezn/Galvanize-2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="usezn/Galvanize-2")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("usezn/Galvanize-2") model = AutoModelForSequenceClassification.from_pretrained("usezn/Galvanize-2", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download thresholds.json from usezn/Galvanize-2: direct link, hf CLI and curl.
- Browser
- Download file 378 Bytes
-
https://huggingface.co/usezn/Galvanize-2/resolve/main/thresholds.json
- Command line
-
hf download hf://usezn/Galvanize-2/thresholds.json
-
curl -L -o thresholds.json https://huggingface.co/usezn/Galvanize-2/resolve/main/thresholds.json
378 Bytes
| { | |
| "probability_threshold": 0.661988004118821, | |
| "margin_threshold": 0.6721660494804383, | |
| "recall_first_probability_threshold": 0.5, | |
| "rule": "flag as prompt injection if probability >= probability_threshold (equivalently margin >= margin_threshold)", | |
| "input_protocol": "flatten whitespace, tokenize with tokenizer.json (keeps its normalizer), keep the first 512 tokens" | |
| } | |