Arch-Guard
katanemo/Arch-Guard
Tracked by OpenModelStats since September 8, 2026View on Hugging Face ↗
- Downloads 30DRolling recent-window download count as reported by the source platform.
- 342
- Total downloadsCumulative all-time download counter reported by the source platform.
- 34.7K
- Gained 7DIncrease in cumulative total downloads between OpenModelStats' own observations seven days apart.
- +66(increase)
- 0.2%(up) vs baseline
- Gained 30DIncrease in cumulative total downloads between OpenModelStats' own observations roughly thirty days apart.
- —
- LikesCommunity likes reported by the source platform.
- 19
- +0 in 7D
- Rank · tracked modelsPosition among all eligible models tracked by OpenModelStats, ordered by recent downloads. #1195 among tracked Text Classification models.
- #48,851
- 1639(down 1639 places)this week
- Parameters
- 279M
- Last source update
- May 6, 2025
- MomentumOpenModelStats' composite rising-model signal (0–100): a percentile blend of absolute 7-day download gains, capped percentage growth, and likes gained. See Methodology.
- 27.4
- Arch-Guard gained 66 downloads during the last seven tracked days.
- It moved from #1163 to #1195 among tracked Text Classification models this week.
Downloads over time
Cumulative total downloads observed by OpenModelStatsLikes over time
Rank among tracked models
Lower is betterOverview
Arch-Guard is a text classification model published by katanemo. OpenModelStats has tracked the model since Sep 8, 2026, most recently observing it 9h ago.
- Published
- Aug 20, 2024
- Last updated
- May 6, 2025
- Library
- —
- License
- mit
- Task
- Text Classification
- Parameters
- 278,811,651
- Spaces
- —
- Derivative models
- —
- Velocity 7D/day
- 9
safetensorsdeberta-v2text-classificationendataset:SohamGhadge/casual-conversationdataset:tau/commonsense_qadataset:AIR-Bench/qa_finance_endataset:JailbreakBench/JBB-Behaviorsdataset:rubend18/ChatGPT-Jailbreak-Promptsdataset:cstnz/Disaster-tweet-jailbreakingdataset:JailbreakV-28K/JailBreakV-28kdataset:Amod/mental_health_counseling_conversations
Publisher
katanemoView publisher statistics →Derived from meta-llama/Prompt-Guard-86M (reported by the source; parent not yet tracked).
Similar models
| Model | DL 30D |
|---|---|
| Prompt-Guard-86Mmeta-llama | 3M |
| Ara-Prompt-Guard_V0NAMAA-Space | 2,461 |
| formality-classifier-mdeberta-v3-baseLenDigLearn | 307 |
| Llama-Prompt-Guard-2-86Mmeta-llama | 122.4K |
| Llama-Prompt-Guard-2-86M-onnxgravitee-io | 10K |
| mdeberta-v3-base-prompt-injectionproventra | 3,657 |