This is the model card of a transformers model that has been pushed on the Hub. Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. Use the code below to get started with the model. Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).
Open-weight model · Text classification
Llama-Prompt-Guard-2-22M-onnx
by AthithyaSakthivel8 Athithya117/Llama-Prompt-Guard-2-22M-onnx
Llama-Prompt-Guard-2-22M-onnx is an open-weight model for text classification from AthithyaSakthivel8, released under llama4. It has 71M parameters and a 512-token context. At 16-bit it needs about 0.2 GB of GPU memory, which fits on 1x MI300X from $1.85 an hour, at the lowest prices in the SAVRN Index.
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 …
Parameters71M
Context512
Weights640.1 MB
Licensellama4
AccessOpen weights
Monthly Downloads—
Runs On
What it takes to serve Llama-Prompt-Guard-2-22M-onnx (71M parameters): the memory its weights need at each precision, and the cheapest way to rent enough data-center GPUs to hold them.
| Precision | Weights | Memory needed | Cheapest setup | Per hour | Also fits |
|---|---|---|---|---|---|
| 16-bit | 0.1 GB | 0.2 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 8-bit | 0.1 GB | 0.1 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 4-bit | 0.0 GB | 0.0 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
Memory is the weights at that precision plus 20% for the runtime and a short context; a long context needs more. Prices are the lowest on-demand hourly rates in the SAVRN Index, read Oct 18, 2026.
Llama-Prompt-Guard-2-22M-onnx on every accelerator the SAVRN Index prices, at every precision
Model Card
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.
Excerpt from the card by AthithyaSakthivel8, licensed llama4.
Configuration
- Architecture
- DebertaV2ForSequenceClassification
- Context length (tokens)
- 512
- Layers
- 12
- Hidden size
- 384
- Feed-forward size
- 1,536
- Attention heads
- 6
- Vocabulary size
- 128,100
- Stored precision
- float32
- Model type
- deberta-v2
Identity and Version
- Repository
- Athithya117/Llama-Prompt-Guard-2-22M-onnx
- Publisher
- AthithyaSakthivel8
- Task
- Text classification
- Modality
- Text
- Library
- Not stated by the source
- Parameters
- 71M parameters
- Languages
- en, fr, de, hi, it, pt, es, th
- Revision
- 28be611a5e773bcc2bfc2cc7477be06b90302fa5
- First published
- 2026-10-17
- Last updated
- 2026-10-17
Files and Weights
11 files, 648.8 MB in total. The weights are 3 files totalling 640.1 MB in onnx, safetensors.
Weights3 files · 640.1 MB
Configuration2 files · 2.0 KB
Tokenizer2 files · 8.7 MB
Documentation3 files · 10.2 KB
Repository1 file · 1.5 KB
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| model.onnx | Weights | 284.2 MB | c6f4d2ebf59b |
| model.quant.onnx | Weights | 72.5 MB | 38c3f03e30a4 |
| model.safetensors | Weights | 283.3 MB | 5120e30bcd53 |
| config.json | Configuration | 1.0 KB | — |
| special_tokens_map.json | Configuration | 970 B | — |
| LICENSE | Documentation | 7.6 KB | — |
| NOTICE | Documentation | 111 B | — |
| README.md | Documentation | 2.5 KB | — |
| .gitattributes | Repository | 1.5 KB | — |
| tokenizer.json | Tokenizer | 8.6 MB | — |
| tokenizer_config.json | Tokenizer | 1.5 KB | — |
License and Download
- License
- llama4
- Access
- Open weights, no gate
- Download size
- 640.1 MB
Download from AthithyaSakthivel8
Released by AthithyaSakthivel8 through its official repository on Hugging Face.
Built From
- Derived from meta-llama/Llama-Prompt-Guard-2-22M
- Quantized from meta-llama/Llama-Prompt-Guard-2-22M
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 640.1 MB |
| 16-bit | 0.1 GB |
| 8-bit | 0.1 GB |
| 4-bit | 0.0 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About Llama-Prompt-Guard-2-22M-onnx
How much GPU memory does Llama-Prompt-Guard-2-22M-onnx need?
About 0.2 GB at 16-bit and 0 GB at 4-bit: the weights (71M parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run Llama-Prompt-Guard-2-22M-onnx on?
At 16-bit, 1x MI300X from $1.85 an hour; at 4-bit, 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists.
What license is Llama-Prompt-Guard-2-22M-onnx released under?
llama4, as its publisher declares it. Read the license text before commercial use.
What is Llama-Prompt-Guard-2-22M-onnx's context length?
512 tokens, from the maximum position embeddings in its published configuration.
Similar Models
This is the model card of a transformers model that has been pushed on the Hub. Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. Use the code below to get started with the model. Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).
This model is a fine-tuned version of distilbert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set: The following hyperparameters were used during training: - learningrate: 2e-05 - trainbatchsize: 64 - evalbatchsize: 64 - lrschedulertype: linear - numepochs: 2 - Transformers 5.18.0 - Pytorch 2.11.0+cu130 - Datasets 4.8.5 - Tokenizers 0.23.2
This is the model card of a transformers model that has been pushed on the Hub. Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. Use the code below to get started with the model. Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).
This model is based on DistilBERT and has been fine-tuned for multilabel classification of Emails and URLs as safe or potentially phishing. - Base Architecture: DistilBERT - Task: Multilabel Classification - Fine-tuning Framework: Hugging Face Trainer API - Training Duration: 3 epochs - Accuracy: 99.58 - F1-score: 99.579 - Precision: 99.583 - Recall: 99.58 The model was trained on a custom dataset of Emails and URLs labeled as legitimate or phishing. The dataset is available at cybersectony/PhishingEmailDetectionv2.0 on the Hugging Face Hub.
This model is a fine-tune checkpoint of DistilBERT-base-uncased, fine-tuned on SST-2. This model reaches an accuracy of 91.3 on the dev set (for comparison, Bert bert-base-uncased version reaches an accuracy of 92.7). This model can be used for topic classification. You can use the raw model for either masked language modeling or next sentence prediction, but it's mostly intended to be fine-tuned on a downstream task. See the model hub to look for fine-tuned versions on a task that interests you. The model should not be used to intentionally create hostile or alienating environments for people. In addition, the model was not trained to be factual or true representations of people or events…