This model is a fine-tuned version of xlm-roberta-base on the Language Identification dataset. This model is an XLM-RoBERTa transformer model with a classification head on top (i.e. a linear layer on top of the pooled output). For additional information please refer to the xlm-roberta-base model card or to the paper Unsupervised Cross-lingual Representation Learning at Scale by Conneau et al. You can directly use this model as a language detector, i.e. for sequence classification tasks. Currently, it supports the following 20 languages: arabic (ar), bulgarian (bg), german (de), modern greek (el), english (en), spanish (es), french (fr), hindi (hi), italian (it), japanese (ja), dutch (nl)…
LLM-powered applications are susceptible to prompt attacks, which are prompts intentionally designed to subvert the developer’s intended behavior of the LLM.
Parameters279M
Context—
Weights1.1 GB
Licensellama3.1
AccessAccess requested at publisher
Monthly Downloads4.5M
Runs On
What it takes to serve Prompt-Guard-86M (279M 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 | 0.6 GB | 0.7 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 8-bit | 0.3 GB | 0.3 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 4-bit | 0.1 GB | 0.2 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 Sep 18, 2026.
SAVRN's Notes on Prompt-Guard-86M
Nothing here generates a reply. It sits in front of the model that does and flags the two attack types Meta names, prompt injection and jailbreaks. Loaded at 16-bit it wants 0.7 GB of memory for 0.6 GB of weights, under half a percent of the cheapest Index setup, a single MI300X with 192 GB at $1.85 an hour on-demand. Co-locate it with the model it protects and the memory is noise.
Read the license closely. The Llama 3.1 Community License allows commercial use, but a licensee whose products had more than 700 million monthly active users on the release date must request a license from Meta, attribution is required, and Meta's Acceptable Use Policy applies. Access is gated; plan for the wait. The name says 86M while the file counts 279 million parameters, and no evaluations are reported, so you measure it on your own traffic before trusting it.
Model Card
LLM-powered applications are susceptible to prompt attacks, which are prompts intentionally designed to subvert the developer’s intended behavior of the LLM. Categories of prompt attacks include prompt injection and jailbreaking: - Prompt Injections are inputs that exploit the concatenation of untrusted data from third parties and users into the context window of a model to get a model to execute unintended instructions. - Jailbreaks are malicious instructions designed to override the safety and security features built into a model. Prompt Guard is a classifier model trained on a large corpus of attacks, capable of detecting both explicitly malicious prompts as well as data that contains…
Excerpt from the card by Meta Llama, licensed llama3.1.
Identity and Version
- Repository
- meta-llama/Prompt-Guard-86M
- Publisher
- Meta Llama
- Task
- Text classification
- Modality
- Text
- Library
- transformers
- Parameters
- 279M parameters
- Languages
- en
- Revision
- 1209add6ca7d9c1d815171b8e5571587fe3e7b03
- First published
- 2024-07-21
- Last updated
- 2025-11-12
Files and Weights
11 files, 1.1 GB in total. The weights are 1 file totalling 1.1 GB in safetensors.
Weights1 file · 1.1 GB
Configuration2 files · 1.3 KB
Tokenizer2 files · 16.3 MB
Documentation3 files · 43.3 KB
Other2 files · 1.0 MB
Repository1 file · 1.6 KB
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| model.safetensors | Weights | 1.1 GB | — |
| config.json | Configuration | 1.0 KB | — |
| special_tokens_map.json | Configuration | 286 B | — |
| LICENSE | Documentation | 7.6 KB | — |
| README.md | Documentation | 31.0 KB | — |
| USE_POLICY.md | Documentation | 4.7 KB | — |
| Prompt-Guard-20240715180000.md5 | Other | 256 B | — |
| prompt_guard_visual.png | Other | 1.0 MB | — |
| .gitattributes | Repository | 1.6 KB | — |
| tokenizer.json | Tokenizer | 16.3 MB | — |
| tokenizer_config.json | Tokenizer | 1.3 KB | — |
License and Download
- License
- llama3.1
- Access
- Access requested at publisher
- Download size
- 1.1 GB
Download from Meta Llama
Released by Meta Llama through Meta's Llama downloads.
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 1.1 GB |
| 16-bit | 0.6 GB |
| 8-bit | 0.3 GB |
| 4-bit | 0.1 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Compare Prompt-Guard-86M
Questions About Prompt-Guard-86M
How much GPU memory does Prompt-Guard-86M need?
About 0.7 GB at 16-bit and 0.2 GB at 4-bit: the weights (279M parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run Prompt-Guard-86M 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.
Can I use Prompt-Guard-86M commercially?
Yes, with conditions. Prompt-Guard-86M is released under Meta Llama 3.1 Community License. The Llama 3.1 Community License permits commercial use, except that a licensee whose products had more than 700 million monthly active users on the release date must request a license from Meta. It requires attribution as the license specifies and compliance with Meta's Acceptable Use Policy.
Similar Models
This model is a fine-tuned version of xlm-roberta-base on the None dataset. It achieves the following results on the evaluation set: The following hyperparameters were used during training: - learningrate: 3e-05 - trainbatchsize: 16 - evalbatchsize: 16 - lrschedulertype: linear - trainingsteps: 1800 - mixedprecisiontraining: Native AMP - Transformers 4.37.2 - Pytorch 2.1.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2
This repository contains a fine-tuned XLM-RoBERTa Base model for 3-class sentiment classification in Sindhi. The model predicts one of the following labels: - positive - neutral - negative This model is intended for research, experimentation, and lightweight production prototyping on Sindhi-language sentiment analysis tasks. It may be useful for short-text classification such as reviews, feedback, and social-media snippets. It should not be used as the only basis for high-stakes decisions. Performance can vary by domain, dialect, and writing style, and human review is recommended when errors could affect people or organizations. The saved model artifacts in this repository report the…
We have updated the new reranker, supporting larger lengths, more languages, and achieving better performance. More details please refer to our Github: FlagEmbedding. FlagEmbedding focuses on retrieval-augmented LLMs, consisting of the following projects currently: - 3/18/2024: Release new rerankers, built upon powerful M3 and LLM (GEMMA and MiniCPM, not so large actually) backbones, supporitng multi-lingual processing and larger inputs, massive improvements of ranking performances on BEIR, C-MTEB/Retrieval, MIRACL, LlamaIndex Evaluation. - 3/18/2024: Release Visualized-BGE, equipping BGE with visual capabilities. Visualized-BGE can be utilized to generate embeddings for hybrid image-text…
Paper: SciFive: a text-to-text transformer model for biomedical literature Authors: Long N. Phan, James T. Anibal, Hieu Tran, Shaurya Chanana, Erol Bahadroglu, Alec Peltekian, Grégoire Altan-Bonnet For more details, do check out our Github repo.
roberta-large-mnli is the RoBERTa large model fine-tuned on the Multi-Genre Natural Language Inference (MNLI) corpus. The model is a pretrained model on English language text using a masked language modeling (MLM) objective. Use the code below to get started with the model. The model can be loaded with the zero-shot-classification pipeline like so: You can then use this pipeline to classify sequences into any of the class names you specify. For example: This fine-tuned model can be used for zero-shot classification tasks, including zero-shot sentence-pair classification (see the GitHub repo for examples) and zero-shot sequence classification. The model should not be used to intentionally…