This repository provides a ONNX converted and quantized version of meta-llama/Llama-Prompt-Guard-2-22M - Meta LLaMA – Foundation model powering the classifier - Hugging Face Transformers – Model and tokenizer loading - ONNX – Model export and runtime format - ONNX Runtime – Efficient inference backend We use jackhhao/jailbreak-classification for the evaluation (train+test) You can find the full source code, CLI tools, and evaluation scripts in the official GitHub repository.
SAVRN Model Hub · Models by License
Open-Weight Models Under llama4
1 open-weight models released under llama4 in the SAVRN Model Hub, with AthithyaSakthivel8 publishing the most.
1Models
1Publishers
71M to 71MParameter range
1Licenses
Most Downloaded
| Model | Publisher | Parameters | License | Monthly downloads | Cheapest GPUs at 16-bit |
|---|---|---|---|---|---|
| Llama-Prompt-Guard-2-22M-onnx | AthithyaSakthivel8 | 71M | llama4 | — | 1x MI300X, $1.85/hr |
Who Publishes Them
| Publisher | Models |
|---|---|
| AthithyaSakthivel8 | 1 |
All 1 Models
Questions
Which llama4 models are most downloaded?
By monthly downloads reported by the Hugging Face Hub: .
Other Licenses
- apache-2.0 3031
- mit 1221
- cc-by-nc-4.0 184
- cc-by-4.0 147
- bsd-3-clause 98
- gemma 59
- cc-by-nc-sa-4.0 49
- llama3.2 34
- agpl-3.0 32
- llama3.1 27
- unknown 26
- cc-by-sa-4.0 18