pattoncarter/NLP-Prompt-Firewall
Project showcasing the performance of a lightweight, efficient, fine-tuned NLP model (DistilBERT) on narrow text classification tasks (corporate DLP) versus multi-billion parameter, LLM-based content safety classification model (Llama-Guard-3-8b).
Stars
1
Forks
—
Language
Python
License
—
Category
Last pushed
Nov 30, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/pattoncarter/NLP-Prompt-Firewall"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
AMontgomerie/CEFR-English-Level-Predictor
NLP system for predicting the reading difficulty level of a text in terms of its CEFR level.
vene/marseille
Mining Argument Structures with Expressive Inference (Linear and LSTM Engines)
public-law/readability
How readable is your text? Provide a text input and get its grade level. Validated against the...
Erprabhat8423/hindi-readability
The first Python package for measuring readability of Hindi text. Uses Devanagari-aware formulas...
openderocknlp/vocabulary-level-grader
Analyzes the given text and determine what's the vocabulary level based on CEFR levels