CatalogWantedMirrorsLedgerOperating StatementDocsStudio statusCard system
alt.freeweights.vision / modernbert-ai-detection-raid-mage
From: GeorgeDrayson <huggingface.co/GeorgeDrayson>Newsgroups: alt.freeweights.visionSubject:

modernbert-ai-detection-raid-mage

Date: 2026-11-15Commit: e047d9cSigned: 2DC28CC7B26A283B ✓

Text classification model with 150M parameters. Safetensors weights, 602 MB in all. Published by GeorgeDrayson under Apache-2.0.

150M params602MBmodernbert-ai-detection-raid-magesafetensorspermissive
FactsParams150MSize602 MBFormatssafetensorsTasktext classificationLicenseApache-2.0From sourcepermissive
$ fw get GeorgeDrayson/modernbert-ai-detection-raid-mage
# manifest sha256 04647a3e5612… · 602 MB · 7 files
$ fw verify ./modernbert-ai-detection-raid-mage GeorgeDrayson/modernbert-ai-detection-raid-mage
From sourceHosted (signed)GeorgeDrayson/modernbert-ai-detection-raid-mageLast check: 2026-11-15 03:29 UTC
Run at homeGet help

Get help: custom fine-tune or private deploy. We review your setup before we quote.

Fine-tune of ModernBERT-base.

Works with

Run8Fine-tune7Convert8Scan2

Runs with

Ranked by fit to this model (safetensors), then by GitHub stars.

TransformersLocalAItinygradTriton Inference ServerBentoMLCTranslate2ExLlamaV2LitServe
OverviewModel cardFilesUse itLicenseProvenanceModel tree

Overview

Size
602 MB
Weights
598 MB (safetensors)
Parameters
150M
Formats
safetensors
Task
text classification
License
Apache-2.0 (permissive)
Files
7, each with a sha256
Publisher
GeorgeDrayson
Added
2026-11-15
Section
alt.freeweights.vision
Lineage

Original release from the publisher.

Base model: answerdotai/ModernBERT-base

Where these bytes come from
Publisher at the pinned commit→You

Sources are tried in order. A file counts only when its size and sha256 match the manifest. Sources are checked when you ask for them, not on a timer.

Sources
BadgeHostLast checkResult
From sourcehuggingface.co2026-11-15 03:29 UTCpassed

Model card

From the publisher at commit e047d9c. Shown as plain text with links; images open at the publisher.

Machine-generated text detection prevents language model collapse#

This model is part of the research presented in the paper Machine-generated text detection prevents language model collapse, which proposes an approach to prevent model collapse based on importance sampling from a machine-generated text detector. The official implementation and training scripts are available in the GitHub repository: GeorgeDrayson/model_collapse

The model is trained on the MAGE and RAID datasets.

Usage#

To use the model for detecting machine-generated text:

from transformers import AutoTokenizer, AutoModelForSequenceClassification
import torch

tokenizer = AutoTokenizer.from_pretrained("GeorgeDrayson/modernbert-raid-mage")
model = AutoModelForSequenceClassification.from_pretrained("GeorgeDrayson/modernbert-raid-mage")

text = "Your input text here."
inputs = tokenizer(text, return_tensors="pt")
outputs = model(**inputs)
probabilities = torch.nn.functional.softmax(outputs.logits, dim=-1)
print(f"Probability of machine-generated text: {probabilities[0][1].item():.4f}")

Citation#

If you use this model or find the research helpful, please cite:

@article{drayson2025machine,
  title={Machine-generated text detection prevents language model collapse},
  author={Drayson, George and Yilmaz, Emine and Lampos, Vasileios},
  journal={arXiv preprint arXiv:2502.15654},
  year={2025}
}

Files

7 files · 602 MBWeights 598 MB (safetensors). Sizes and sha256 from the signed manifest.
Hide all 7 files with their sha256
FileSizesha256
.gitattributes1.52 KB11ad7efa24975ee4b0c3c3a38ed18737f0658a5f75a0a96787b576a78a023361
README.md1.77 KB328d6508b1a135e8d1559e25efdf0cb7dc9f00ba78663fc6904003ff0ab73891
config.json1.29 KBa6225f6c55e0fb92ccb6a53832714993a5eeceff0a4ac89e90f803de8e06a742
model.safetensors598 MB2ae8059c621795fc490353bbd920bc3672e6eaf8ad66ddb7c015b4ecb0129218
special_tokens_map.json694 Bea97ecdbcc73713039d8d64dbb05e3689495c96657fbd9a18f5bed381be81049
tokenizer.json3.58 MB6c8aaa9a542084f2457eab775d4eeb51f92a70c0fd9de28d5edb0ddec3c08d30
tokenizer_config.json20.8 KBc16f1b07f93d05be753ec0acf8cb511d895a8bdb09669f6b156df81e3f96c2eb
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
e047d9c56f pinned now2026-11-15 03:29 UTC7 files · 602 MB

Use it

$ fw get GeorgeDrayson/modernbert-ai-detection-raid-mage
# manifest sha256 04647a3e5612… · 602 MB · 7 files
$ fw verify ./modernbert-ai-detection-raid-mage GeorgeDrayson/modernbert-ai-detection-raid-mage
fw.pyChecks the signature and every sha256, tries each source in order, resumes.
$ python3 fw.py get https://freeweights.allternit.com/manifests/GeorgeDrayson/modernbert-ai-detection-raid-mage.json --dir ./modernbert-ai-detection-raid-mage $ python3 fw.py verify ./modernbert-ai-detection-raid-mage ./GeorgeDrayson__modernbert-ai-detection-raid-mage.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download GeorgeDrayson/modernbert-ai-detection-raid-mage --revision e047d9c56f51a7e5c5ef5b0dd556f519bb9dd624 --local-dir ./modernbert-ai-detection-raid-mage
Run at home

License

Name
Apache License 2.0
Id
Apache-2.0
Class
Permissive
Redistribution
yes
Listing
Hosted (signed)
Decided
License as declared by the publisher. No person read it. 2026-11-15
Text in
README.md
Text sha256
328d6508b1a135e8d1559e25efdf0cb7dc9f00ba78663fc6904003ff0ab73891
Terms gate
No extra terms beyond the license.

Read the license text

Licenses are checked against the license table. A custom license passes only after a person reads it.

Provenance

From: GeorgeDrayson <huggingface.co/GeorgeDrayson>Newsgroups: alt.freeweights.visionSubject: modernbert-ai-detection-raid-mageDate: 2026-11-15Commit: e047d9cSigned: 2DC28CC7B26A283B ✓
Upstream
GeorgeDrayson/modernbert-ai-detection-raid-mage
Pinned commit
e047d9c56f51a7e5c5ef5b0dd556f519bb9dd624
Manifest
modernbert-ai-detection-raid-mage.json · .minisig
Manifest sha256
04647a3e5612051c3e49be280298443ef3b1ddd587cdc95396e6a7f4978faa5a
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-15 03:29 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/GeorgeDrayson/modernbert-ai-detection-raid-mage.json $ curl -O https://freeweights.allternit.com/manifests/GeorgeDrayson/modernbert-ai-detection-raid-mage.json.minisig $ minisign -Vm modernbert-ai-detection-raid-mage.json -P RWQ7KGqyx4zCLXtUFOqvfv8L3g+8fpKJ1FsuxPyOYMF+4KufbUxKq1Oq $ shasum -a 256 <file> # compare with the Files tab

A manifest whose signature fails must be rejected. A file whose size or sha256 does not match must be discarded. Verify a download

Model tree

Parent

answerdotai/ModernBERT-base · this model is a finetune of it

1 model in the catalog name this one as their parent.

Quantizations
1
Quantizations 1
Get it
Download
$ HF_ENDPOINT=https://freeweights.allternit.com hf download GeorgeDrayson/modernbert-ai-detection-raid-mage
Open in Freeweights Studio

Pull, verify and run it in the Allternit app on Desktop, web or phone.

Signed manifest
minisign, key 2DC28CC7B26A283B. modernbert-ai-detection-raid-mage.json. Provenance. Takedown history: none.
Source
huggingface.co/GeorgeDrayson/modernbert-ai-detection-raid-mage

Variants

1 quantized or adapter build of modernbert-ai-detection-raid-mage. Each has its own license check and page.

SubjectSizeParamsLicenseDate
modernbert-ai-detection-raid-mage-ONNXHosted (signed) From: onnx-community in alt.freeweights.vision1.94 GB—Permissive2026-11-15

Related models

All of alt.freeweights.vision →
From: dima806 <huggingface.co/dima806>Subject: ai_vs_real_image_detection
From: legekka <huggingface.co/legekka>Subject: AI-Anime-Image-Detector-ViT
From: onnx-community <huggingface.co/onnx-community>Subject: AI-Anime-Image-Detector-ViT-ONNX
From: AICodexLab <huggingface.co/AICodexLab>Subject: answerdotai-ModernBERT-base-ai-detector
From: onnx-community <huggingface.co/onnx-community>Subject: answerdotai-ModernBERT-base-ai-detector-ONNX
From: onnx-community <huggingface.co/onnx-community>Subject: bart-large-cnn-ONNX