Text Classification
Transformers
Safetensors
English
deberta-v2
agent-governance
policy-checking
ai-agents
guardrails
hummbl
text-embeddings-inference
Instructions to use hummbl-hf/decision-0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use hummbl-hf/decision-0 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="hummbl-hf/decision-0")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("hummbl-hf/decision-0") model = AutoModelForSequenceClassification.from_pretrained("hummbl-hf/decision-0", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Card: disclose known self-approval gap (discussion #1)
#2
by sum-guy-429 - opened
For Reuben's review; do not merge without his approval.
Adds a visible 'Known gap: self-approval is not detected' warning, using the exact probe numbers from discussion #1 (https://huggingface.co/hummbl-hf/decision-0/discussions/1). Model card only: warning under the advisory note plus two Limitations bullets (self-approval; empty-evidence over-escalation). SHA256SUMS updated for README.md only, so the published checksum list still verifies. Weights, decide.py and all other files unchanged.