CatalogWantedMirrorsLedgerOperating StatementDocsStudio statusCard system
alt.freeweights.vision / answerdotai-ModernBERT-base-ai-detector
From: AICodexLab <huggingface.co/AICodexLab>Newsgroups: alt.freeweights.visionSubject:

answerdotai-ModernBERT-base-ai-detector

Date: 2026-11-15Commit: 7839e63Signed: 2DC28CC7B26A283B ✓

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

150M params602MBanswerdotai-ModernBERT-base-ai-detectorsafetensorspermissive
FactsParams150MSize602 MBFormatssafetensorsTasktext classificationLicenseApache-2.0From sourcepermissive
$ fw get AICodexLab/answerdotai-ModernBERT-base-ai-detector
# manifest sha256 305c150a6db6… · 602 MB · 8 files
$ fw verify ./answerdotai-ModernBERT-base-ai-detector AICodexLab/answerdotai-ModernBERT-base-ai-detector
From sourceHosted (signed)AICodexLab/answerdotai-ModernBERT-base-ai-detectorLast check: 2026-11-15 02:46 UTC
Fine-tune in StudioGet help

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

Fine-tune of ModernBERT-base.

Runs withBentoMLCTranslate2ExLlamaV2LitServeLocalAItinygradTransformersTriton Inference ServerFine-tune withAccelerateDeepSpeedJAXKerasPyTorch Lightningsd-scriptsSimpleTunerConvert withCore ML ToolsExecuTorchOliveONNXOptimum QuantoOptimumsafetensorstorchaoScan withModelScanpicklescan
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
8, each with a sha256
Publisher
AICodexLab
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 commitโ†’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 02:46 UTCpassed

Model card

From the publisher at commit 7839e63. Shown as plain text with links; images open at the publisher.

answerdotai-ModernBERT-base-ai-detector#

This model is a fine-tuned version of answerdotai/ModernBERT-base on the AI vs Human Text Classification dataset, DAIGT V2 Train Dataset.

It achieves the following results on the evaluation set:

  • Validation Loss: 0.0036

๐Ÿ“ Model Description#

This model is based on ModernBERT-base, a lightweight and efficient BERT-based model. It has been fine-tuned for AI-generated vs Human-written text classification, allowing it to distinguish between texts written by AI models (ChatGPT, DeepSeek, Claude, etc.) and human authors.

๐ŸŽฏ Intended Uses & Limitations#

โœ… Intended Uses#
  • AI-generated content detection (e.g., ChatGPT, Claude, DeepSeek).
  • Text classification for distinguishing human vs AI-generated content.
  • Educational & Research applications for AI-content detection.
โš ๏ธ Limitations#
  • Not 100% accurate โ†’ Some AI texts may resemble human writing and vice versa.
  • Limited to trained dataset scope โ†’ May struggle with out-of-domain text.
  • Bias risks โ†’ If the dataset contains bias, the model may inherit it.

๐Ÿ“Š Training and Evaluation Data#

  • The model was fine-tuned on 35,894 training samples and 8,974 test samples.
  • The dataset consists of AI-generated text samples (ChatGPT, Claude, DeepSeek, etc.) and human-written samples (Wikipedia, books, articles).
  • Labels:
    • 1 โ†’ AI-generated text
    • 0 โ†’ Human-written text

โš™๏ธ Training Procedure#

Training Hyperparameters#

The following hyperparameters were used during training:

HyperparameterValue
Learning Rate2e-5
Train Batch Size16
Eval Batch Size16
OptimizerAdamW (ฮฒ1=0.9, ฮฒ2=0.999, ฮต=1e-08)
LR SchedulerLinear
Epochs3
Mixed PrecisionNative AMP (fp16)

๐Ÿ“ˆ Training Results#

Training LossEpochStepValidation Loss
0.05050.225000.0214
0.01140.4410000.0110
0.00880.6615000.0032
0.00.8920000.0048
0.00681.1125000.0035
0.01.3330000.0040
0.01.5535000.0097
0.00531.7840000.0101
0.02.0045000.0053
0.02.2250000.0039
0.00172.4555000.0046
0.02.6760000.0043
0.02.8965000.0036

๐Ÿ›  Framework Versions#

LibraryVersion
Transformers4.48.3
PyTorch2.5.1+cu124
Datasets3.3.2
Tokenizers0.21.0

๐Ÿ“ค Model Usage#

To load and use the model for text classification:

from transformers import AutoModelForSequenceClassification, AutoTokenizer, pipeline

model_name = "answerdotai/ModernBERT-base-ai-detector"

# Load model and tokenizer
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForSequenceClassification.from_pretrained(model_name)

# Create text classification pipeline
classifier = pipeline("text-classification", model=model, tokenizer=tokenizer)

# Run classification
text = "This text was written by an AI model like ChatGPT."
result = classifier(text)

print(result)

Files

8 files ยท 602 MBWeights 598 MB (safetensors). Sizes and sha256 from the signed manifest.
Hide all 8 files with their sha256
FileSizesha256
.gitattributes1.52 KB11ad7efa24975ee4b0c3c3a38ed18737f0658a5f75a0a96787b576a78a023361
README.md4.13 KB2cac60baea3a08c26a38b97e08e9396ccbe11a405c77baab48e802cf02ea4976
config.json1.36 KBf844eca0d1d8131fd6d904ac997aab3cb6150cb0df81bd4085fd183870ec2058
model.safetensors598 MB110318cc81b582af21738b7dce62a7a312d6ec338ee2f996acd595ba3e041f9f
special_tokens_map.json694 Bea97ecdbcc73713039d8d64dbb05e3689495c96657fbd9a18f5bed381be81049
tokenizer.json3.58 MB6c8aaa9a542084f2457eab775d4eeb51f92a70c0fd9de28d5edb0ddec3c08d30
tokenizer_config.json20.8 KB2966a59b9e9cf122279aec1249e22e5bc7ad8430c754e95031b13fd128d4e560
training_args.bin5.30 KBaff3e7fa490e603305ba4ecbb63b75192b51e11637c2d1584e82ccb5afab7535
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
7839e63277 pinned now2026-11-15 02:46 UTC8 files ยท 602 MB

Use it

$ fw get AICodexLab/answerdotai-ModernBERT-base-ai-detector
# manifest sha256 305c150a6db6… · 602 MB · 8 files
$ fw verify ./answerdotai-ModernBERT-base-ai-detector AICodexLab/answerdotai-ModernBERT-base-ai-detector
fw.pyChecks the signature and every sha256, tries each source in order, resumes.
$ python3 fw.py get https://freeweights.allternit.com/manifests/AICodexLab/answerdotai-ModernBERT-base-ai-detector.json --dir ./answerdotai-ModernBERT-base-ai-detector $ python3 fw.py verify ./answerdotai-ModernBERT-base-ai-detector ./AICodexLab__answerdotai-ModernBERT-base-ai-detector.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download AICodexLab/answerdotai-ModernBERT-base-ai-detector --revision 7839e63277a262579bc98932bbe804b11ee63810 --local-dir ./answerdotai-ModernBERT-base-ai-detector
Fine-tune in Studio

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
2cac60baea3a08c26a38b97e08e9396ccbe11a405c77baab48e802cf02ea4976
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: AICodexLab <huggingface.co/AICodexLab>Newsgroups: alt.freeweights.visionSubject: answerdotai-ModernBERT-base-ai-detectorDate: 2026-11-15Commit: 7839e63Signed: 2DC28CC7B26A283B ✓
Upstream
AICodexLab/answerdotai-ModernBERT-base-ai-detector
Pinned commit
7839e63277a262579bc98932bbe804b11ee63810
Manifest
answerdotai-ModernBERT-base-ai-detector.json ยท .minisig
Manifest sha256
305c150a6db69824c187a879615222ea60d2688f7ae395dcc7073f8e5a576d72
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-15 02:46 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/AICodexLab/answerdotai-ModernBERT-base-ai-detector.json $ curl -O https://freeweights.allternit.com/manifests/AICodexLab/answerdotai-ModernBERT-base-ai-detector.json.minisig $ minisign -Vm answerdotai-ModernBERT-base-ai-detector.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 ยท 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 AICodexLab/answerdotai-ModernBERT-base-ai-detector
Open in Freeweights Studio

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

Signed manifest
minisign, key 2DC28CC7B26A283B. answerdotai-ModernBERT-base-ai-detector.json. Provenance. Takedown history: none.
Source
huggingface.co/AICodexLab/answerdotai-ModernBERT-base-ai-detector

Variants

1 quantized or adapter build of answerdotai-ModernBERT-base-ai-detector. Each has its own license check and page.

SubjectSizeParamsLicenseDate
answerdotai-ModernBERT-base-ai-detector-ONNXHosted (signed) From: onnx-community in alt.freeweights.vision1.94 GBโ€”Permissive2026-11-15

Related models

All of alt.freeweights.vision โ†’
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: 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
From: timm <huggingface.co/timm>Subject: beit_base_patch16_224.in22k_ft_in22k_in1k