# llm-semantic-router/toolcall-sentinel

Model from Hugging Face for text classification: llm-semantic-router/toolcall-sentinel · transformers

## Facts

- Type: LLM
- Task: text-classification
- Framework: transformers
- License: apache-2.0 — Permissive open license: commercial use, modification, and redistribution are permitted. (https://spdx.org/licenses/Apache-2.0.html)
- Source: https://huggingface.co/llm-semantic-router/toolcall-sentinel
- Hosting: hosted (9 files)
- Files: 9 hosted of 10 listed
- File counts: "listed" is every file in the source repository; only hosted files download from Hugging Bay, and the download plan lists the files it selects for one download, so its count can differ.
- Hosted here: 9 files, 602.1 MB
- Full repo upstream: 602.1 MB
- Recommended file: 598.4 MB · model.safetensors
- Download: https://huggingbay.xyz/artifact/hf-model-llm-semantic-router-toolcall-sentinel/files (download plan: https://huggingbay.xyz/api/artifacts/hf-model-llm-semantic-router-toolcall-sentinel/download-plan)
- Per-file SHA-256: available for 9 of 9 hosted files via https://huggingbay.xyz/api/artifacts/hf-model-llm-semantic-router-toolcall-sentinel/files?limit=100
- Run-ready: no (Hugging Bay has not certified a run path for this model; hosted bytes are downloadable and hash-checkable only)
- Peer-assisted fallbacks: 0 verified, 0 pending review
- Downloads: 22
- Stars: 1
- Card completeness: 96%

## Description

External Hugging Face catalog record for llm-semantic-router/toolcall-sentinel. Task: text classification. Library: transformers. Languages: en. Datasets referenced by card metadata: allenai/wildjailbreak, hackaprompt/hackaprompt-dataset, TrustAIRLab/in-the-wild-jailbreak-prompts, tatsu-lab/alpaca, databricks/databricks-dolly-15k. Base model: answerdotai/ModernBERT-base. Includes 5 model-card evaluation signals. Popularity signal at import: 23 downloads and 1 likes.

## Model Card Facts

- Declared license: apache-2.0
- Pipeline: text-classification
- Library: transformers
- Base model: answerdotai/ModernBERT-base
- Task categories: text-classification
- Languages: en
- Referenced datasets: allenai/wildjailbreak, hackaprompt/hackaprompt-dataset, TrustAIRLab/in-the-wild-jailbreak-prompts, tatsu-lab/alpaca, databricks/databricks-dolly-15k
- Model-index entries: toolcall-sentinel
- Evaluation signals: 5 model-card eval results
- File hints: 10 upstream file samples

## Evaluation Signals

- toolcall-sentinel: INJECTION_RISK F1 = 0.9596 (Prompt Injection Detection)
- toolcall-sentinel: INJECTION_RISK Precision = 0.9715 (Prompt Injection Detection)
- toolcall-sentinel: INJECTION_RISK Recall = 0.9481 (Prompt Injection Detection)
- toolcall-sentinel: Accuracy = 0.96 (Prompt Injection Detection)
- toolcall-sentinel: ROC-AUC = 0.9928 (Prompt Injection Detection)

## Referenced Data

- Dataset: allenai/wildjailbreak
- Dataset: hackaprompt/hackaprompt-dataset
- Dataset: TrustAIRLab/in-the-wild-jailbreak-prompts
- Dataset: tatsu-lab/alpaca
- Dataset: databricks/databricks-dolly-15k

## File Hints

- .gitattributes (1.5 KB)
- README.md (4.2 KB)
- best_metrics.json (985 B)
- config.json (1.3 KB)
- final_report.json (227 B)
- model.safetensors (571 MB) LFS
- special_tokens_map.json (694 B)
- tokenizer.json (3.4 MB)
- tokenizer_config.json (20 KB)
- training_config.json (376 B)

## Quality Checklist

- Summary: passed
- Description: passed
- Model card metadata: passed
- License: passed
- Provenance: passed
- File inventory: passed
- Hosted bytes: passed
- Scan result: passed
- Manifest signature: passed

## Safety Notes

- External catalog metadata imported from Hugging Face public API on 2026-09-03T19:03:43.948Z.
- Open license detected as apache-2.0.
- Model-index metadata found for toolcall-sentinel.
- Model card references dataset context: allenai/wildjailbreak, hackaprompt/hackaprompt-dataset, TrustAIRLab/in-the-wild-jailbreak-prompts, tatsu-lab/alpaca.
- Not a run kit: hosted, hash-checked bytes only; run readiness is not certified for this model yet.

## Actions

- Web: https://huggingbay.xyz/artifact/hf-model-llm-semantic-router-toolcall-sentinel
- Files API: https://huggingbay.xyz/api/artifacts/hf-model-llm-semantic-router-toolcall-sentinel/files?limit=100
- Metadata: https://huggingbay.xyz/api/artifacts/hf-model-llm-semantic-router-toolcall-sentinel/metadata.json
- Distribution: https://huggingbay.xyz/api/artifacts/hf-model-llm-semantic-router-toolcall-sentinel/distribution
- Manifest: https://huggingbay.xyz/api/manifests/hf-model-llm-semantic-router-toolcall-sentinel
- Download plan (per-file SHA-256 + signed download URLs): https://huggingbay.xyz/api/artifacts/hf-model-llm-semantic-router-toolcall-sentinel/download-plan
- Hosted download rows: https://huggingbay.xyz/api/downloadable-files?artifactId=hf-model-llm-semantic-router-toolcall-sentinel&limit=100
- Request mirror: not applicable.
- Submit peer fallback for review: POST https://huggingbay.xyz/api/artifacts/hf-model-llm-semantic-router-toolcall-sentinel/decentralized-fallbacks