Text Classification
Transformers
Safetensors
English
lfm2_vl
feature-extraction
decision-model
typed-decisions
system-one
shell
guardrail
command-risk
lfm2
liquid
lora
custom_code
Eval Results (legacy)
Instructions to use yannelli/d1-3b-cli-command-risk with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use yannelli/d1-3b-cli-command-risk with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="yannelli/d1-3b-cli-command-risk", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModel processor = AutoProcessor.from_pretrained("yannelli/d1-3b-cli-command-risk", trust_remote_code=True) model = AutoModel.from_pretrained("yannelli/d1-3b-cli-command-risk", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download eval/guardrail.json from yannelli/d1-3b-cli-command-risk: direct link, hf CLI and curl.
- Browser
- Download file 902 Bytes
-
https://huggingface.co/yannelli/d1-3b-cli-command-risk/resolve/main/eval/guardrail.json
- Command line
-
hf download hf://yannelli/d1-3b-cli-command-risk/eval/guardrail.json
-
curl -L -o guardrail.json https://huggingface.co/yannelli/d1-3b-cli-command-risk/resolve/main/eval/guardrail.json
902 Bytes
| { | |
| "cases": 12689, | |
| "families": 97, | |
| "level_macro_f1": 0.669, | |
| "level_interval": [ | |
| 0.484, | |
| 0.781 | |
| ], | |
| "level_accuracy": 0.756, | |
| "f1_by_level": { | |
| "safe": 0.989, | |
| "low": 0.257, | |
| "moderate": 0.86, | |
| "high": 0.508, | |
| "critical": 0.733 | |
| }, | |
| "category_macro_f1": 0.929, | |
| "category_interval": [ | |
| 0.724, | |
| 0.978 | |
| ], | |
| "f1_by_category": { | |
| "data_destruction": 0.876, | |
| "device_overwrite": 0.994, | |
| "overbroad_permissions": 0.998, | |
| "privilege_escalation": 1.0, | |
| "remote_code_execution": 1.0, | |
| "unsafe_download_exec": 1.0, | |
| "resource_exhaustion": 1.0, | |
| "credential_exposure": 1.0, | |
| "irreversible_config": 0.693, | |
| "history_log_tampering": 0.812, | |
| "network_disruption": 1.0, | |
| "signal_kill": 1.0, | |
| "shell_footgun": 0.704 | |
| }, | |
| "risky_f1": 0.997, | |
| "reversible_f1": 0.859, | |
| "requires_root_f1": 0.911, | |
| "cutoff_at_1pct_validation_fpr": 0.714, | |
| "test_safe_fpr": 0.0168, | |
| "recall_high_critical": 0.999 | |
| } | |