🔄 In a Training Loop

Horizon Labs

Horizon-Labs

AI & ML interests

None yet

Recent Activity

updated a Space 1 day ago

Horizon-Labs/prompt-injection-leaderboard

updated a model 1 day ago

Horizon-Labs/prompt-injection-guard-large

updated a model 1 day ago

Horizon-Labs/prompt-injection-guard-base

View all activity

Organizations

None yet

Horizon-Labs 's Spaces 18

Phishing & Scam Detector

🎣

Detect phishing, scams and spam in many languages

Punctuation Restoration

✒

Restore punctuation in 88 languages, in your browser

Multilingual Toxicity

🧹

Detoxify-style toxicity scores in 34 languages, in-browser

Multilingual Embedding

🧭

Multilingual semantic search with bge-m3-compatible vectors

Multilingual Reranker

🔎

Rerank passages for a query in 40+ languages, in-browser

Multilingual Emotions

🎭

28 GoEmotions labels for text in many languages, in-browser

Multilingual Sentiment

💬

Positive, neutral or negative in many languages, in-browser

Language Detection

🌍

Detect the language of text in 183 languages, in-browser

Content Safety Guard

🛡

Flag unsafe prompts and LLM responses, in your browser

Multilingual Zero-Shot Classifier

🏷

Classify text in 30+ languages into any labels, in-browser

Hallucination Guard

🔎

Is an AI answer supported by its source? In-browser

PII Redactor

🕶

Multilingual PII & secrets redaction in your browser

Prompt Injection Guard

🛡

Detect prompt injection in your browser (transformers.js)

Prompt Injection Detector Leaderboard

📊

Open prompt-injection classifiers on 12 public eval sets

README

🛡

Multilingual Reranking & Retrieval Leaderboard

🔎

Open rerankers and embedding models on 41 multilingual sets

Multilingual Zero-Shot Classification Leaderboard

🏷

Open zero-shot classifiers on intents/topics in 16 languages

Content Safety Classifier Leaderboard

🧭

Open moderation models on 9 safety benchmarks, 17 languages