CoolFace
19 results

llm-guard

inallmodelsdatasetsappsagentspeopleprojects

Models

All models matching “llm-guard”
fastino /gliguard-LLMGuardrails-300Mtext-classificationgliner2en88 likes4.5k downloads2d agoHugging Facellm-semantic-router /Vela-1.0-Encoder-307M-Guardtext-classificationtransformers1 likes2.1k downloads6d agoHugging FaceVigilGuard /vigil-llm-guardgatedtext-classificationtransformersen3 likes44 downloads5mo agoHugging Faceehd0309 /ko-guardrail-llm-v1text-generationpeftko0 likes28 downloads4mo agoHugging FaceNeeraj-Ch0udhary /llmguard-input-guardtext-classificationtransformers0 likes10 downloads4mo agoHugging FaceHemg /LLMGUARD-roberta-11text-classificationtransformers0 likes4 downloads2y agoHugging FaceTuathe /llmguard-injection-model0 likes2 downloads1y agoHugging Facegreenscale-nandesh /llm-guardrailstext-generationtransformers0 likes2y agoHugging Face

Datasets

All datasets matching “llm-guard”
open-llm-leaderboard-old /details_guardrail__llama-2-7b-guanaco-instruct-sharded Dataset Card for Evaluation run of guardrail/llama-2-7b-guanaco-instruct-sharded Dataset Summary Dataset automatically created during the evaluation run of model guardrail/llama-2-7b-guanaco-instruct-sharded on the Open LLM Leaderboard. The dataset is composed of 64 configuration, each one coresponding to one of the evaluated task. The dataset has been created from 2 run(s). Each run can be found as a specific split in each configuration, the split being named using the… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard-old/details_guardrail__llama-2-7b-guanaco-instruct-sharded.0 likes35 downloads3y agoHugging Faceshanemhamilton /llm-prompt-guard-tuning-corpus llm-prompt-guard tuning corpus Prompt-injection detection corpus used to tune the llm-prompt-guard pattern set. Two JSONL files: attacks.jsonl — 198 rows, label: 1. Injection payloads grouped by attack category (instruction override, role hijacking, jailbreak, unicode/homoglyph/tag-block smuggling, encoding bypass, and more). benign.jsonl — 1,310 rows, label: 0. Ordinary user input across seven domains, including phrasing that superficially resembles an attack ("ignore the… See the full description on the dataset page: https://huggingface.co/datasets/shanemhamilton/llm-prompt-guard-tuning-corpus.text-classification1K<n<10K0 likes35 downloads10d agoHugging Facecgoosen /llm_guard_datasettabular10K<n<100K0 likes22 downloads2y agoHugging FaceYUGOROU /Counseling-LLM-guardrailtextn<1K1 likes14 downloads1y agoHugging FaceDormamu-Labs /Dormamu_GVD-1_Guardrail_Vulnerability_Dataset_for_LLM_Alignment Dormamu GVD-1: Alignment Benchmark Dataset Introduction Dormamu is an advanced AI alignment framework developed to enhance the safety and ethical robustness of large language models (LLMs). It extends the OWASP LLM Top 10 vulnerabilities with proprietary categories, such as DormamuX1 for existential risk simulations and DormamuX2 for cultural alignment testing. The Guardrail Vulnerability Dataset version 1 (GVD-1) is a comprehensive collection of test cases designed to benchmark LLM… See the full description on the dataset page: https://huggingface.co/datasets/Dormamu-Labs/Dormamu_GVD-1_Guardrail_Vulnerability_Dataset_for_LLM_Alignment.0 likes11 downloads11mo agoHugging Face

Apps

All apps matching “llm-guard”
protectai /llm-guard-playgrounddocker44 likes1y agoHugging FaceSSK-14 /LLM-Guarddocker0 likes2y agoHugging FaceGPT-Wizards /LLM-Guarddocker0 likes2y agoHugging Facegreenscale-nandesh /greenscale-nandesh-llm-guardrailsgradio0 likes2y agoHugging Faceretereum /student-llm-guardgradio0 likes2y agoHugging Faceuetuluk /student-llm-guardgradio0 likes2y agoHugging Face