Overview

RADAR Vicuna 7B is a specialized text-classification model based on the Vicuna architecture, optimized for high-accuracy labeling and categorization tasks. Unlike general-purpose LLMs that require complex few-shot prompting for classification, this model is tuned to output structured labels efficiently, making it an ideal choice for developers building automated moderation pipelines, sentiment analysis engines, or intent recognition systems. It balances a compact 7B parameter footprint with the reasoning capabilities of the Llama-derived lineage, allowing for low-latency deployment on consumer-grade GPUs or edge servers. Integration is straightforward for those familiar with the Hugging Face ecosystem, providing a performant alternative to larger models when task-specific precision and inference speed are the primary constraints.

Highlights

Optimized for high-precision text classification and labeling
Compact 7B parameter size for low-latency inference
Apache-2.0 license allows flexible commercial integration
Ideal for sentiment analysis and intent recognition
Efficient deployment on consumer-grade GPU hardware

Usage

Install

# Install Hugging Face transformers
pip install transformers torch

SDK Usage

# Load model with transformers
from transformers import AutoModel, AutoTokenizer

model = AutoModel.from_pretrained("TrustSafeAI/RADAR-Vicuna-7B")
tokenizer = AutoTokenizer.from_pretrained("TrustSafeAI/RADAR-Vicuna-7B")

Hugging Face Download

We recommend downloading the model via the Hugging Face CLI or Hub SDK.

Guidance：Before downloading, install huggingface_hub with:

Guidance

pip install -U huggingface_hub

CLI Download

Download the full repository

huggingface-cli download TrustSafeAI/RADAR-Vicuna-7B

Download a single file to a local folder (e.g. config.json into ./dir)

huggingface-cli download TrustSafeAI/RADAR-Vicuna-7B config.json --local-dir ./dir

See the official docs for more CLI options

SDK Download

# 模型下载
from huggingface_hub import snapshot_download
model_dir = snapshot_download('TrustSafeAI/RADAR-Vicuna-7B')

Git Download

Make sure git-lfs is installed first

Git Download

git lfs install
git clone https://huggingface.co/TrustSafeAI/RADAR-Vicuna-7B

To skip LFS large-file downloads, use:

Skip LFS

GIT_LFS_SKIP_SMUDGE=1 git clone https://huggingface.co/TrustSafeAI/RADAR-Vicuna-7B

Model files are hosted on the Hugging Face Hub — download directly via HF CLI / SDK / Git, not through this site.

PyTorch / Transformers Usage

Install Transformers

pip install -U transformers torch

Load the model and run inference

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained('TrustSafeAI/RADAR-Vicuna-7B')
tokenizer = AutoTokenizer.from_pretrained('TrustSafeAI/RADAR-Vicuna-7B')

Full Documentation

来源: HuggingFace

---
pipeline_tag: text-classification
---

<br>

RADAR Model Card

Model Details

RADAR-Vicuna-7B is an AI-text detector trained via adversarial learning between the detector and a paraphraser on human-text corpus (OpenWebText) and AI-text corpus generated
based on OpenWebText.

Developed by: TrustSafeAI

Model type: An encoder-only language model based on the transformer architecture (RoBERTa).

License: Non-commercial license (inherited from Vicuna-7B-v1.1)

Trained from model: RoBERTa

Model Sources

Project Page: https://radar.vizhub.ai/

Paper: https://arxiv.org/abs/2307.03838

IBM Blog Post: https://research.ibm.com/blog/AI-forensics-attribution

Uses

Users could use this detector to assist them in detecting text generated by large language models. Please note that this detector is trained on AI-text generated by Vicuna-7B-v1.1. As the model only supports non-commercial use, the intended users are not allowed to involve this detector into commercial activities.

Get Started with the Model

Please refer to the following guidelines to see how to locally run the downloaded model or use our API service hosted on Huggingface Space.

Google Colab Demo: https://colab.research.google.com/drive/1r7mLEfVynChUUgIfw1r4WZyh9b0QBQdo?usp=sharing

Huggingface API Documentation: https://trustsafeai-radar-ai-text-detector.hf.space/?view=api

Training Pipeline

We propose adversarial learning between a paraphraser and our detector. The paraphraser's goal is to make the AI-generated text more like human-writen and the detector's goal is to
promote it's ability to identify the AI-text.

(Step 1) Training Data preparation: Before training, we use Vicuna-7B to generate AI-text by performing text completion based on the prefix span of human-text in OpenWebText.

(Step 2) Update the paraphraser During training, the paraphraser will do paraphrasing on the AI-text generated in Step 1. And then collect the reward returned by the detector to update the paraphraser using Proxy Proximal Optimization loss.

(Step 3) Update the detector The detector is optimized using the logistic loss on the human-text, AI-text and paraphrased AI-text.

See more details in Sections 3 and 4 of this paper.

Ethical Considerations

We suggest users use our tool to assist with identifying AI-written content at scale and with discretion. If the detection result is to be used as evidence, further validation steps are necessary as RADAR cannot always make correct predictions.