Search public pages, research tools, and SAVRN solutions.
ai-text-detector is an open-weight model for text classification from Bill Fisk, released under Apache License 2.0. It has 512-token context. Its published files total 1.7 GB.
This repository contains the merged FP32 ONNX model used by @clueso/ai-text-detector, a local AI-text detector for Node.js. It is a LoRA fine-tune of wasitaigeneratedcom/ai-text-detector-small.
By Bill Fisk, published under apache-2.0, revision 451cd562a29f.
This repository contains the merged FP32 ONNX model used by @clueso/ai-text-detector, a local AI-text detector for Node.js. It is a LoRA fine-tune of wasitaigeneratedcom/ai-text-detector-small. The original four output classes and mask-aware mean-pooling architecture are preserved: The ONNX graph contains the DeBERTa encoder, mask-aware mean pooling, and four-class classifier. No remote code is required. Only the published MAGE training split was used for gradient updates. The accepted training sample contained 4,000 human and 4,000 AI documents, balanced across sources. Rank-8 LoRA adapters were trained on all 24 layers' query and value projections together with the classifier. This made…
This repository contains the merged FP32 ONNX model used by @clueso/ai-text-detector, a local AI-text detector for Node.js.
It is a LoRA fine-tune of wasitaigeneratedcom/ai-text-detector-small. The original four output classes and mask-aware mean-pooling architecture are preserved:
DeBERTa-v3-large
↓
mask-aware mean pooling
↓
Linear(1024 → 4)
├── human
├── ai
├── ai_edited
└── humanized
The headline AI score is:
AI score = 1 - P(human)
0.9974874649196864The ONNX graph contains the DeBERTa encoder, mask-aware mean pooling, and four-class classifier. No remote code is required.
Only the published MAGE training split was used for gradient updates. The accepted training sample contained 4,000 human and 4,000 AI documents, balanced across sources.
Rank-8 LoRA adapters were trained on all 24 layers' query and value projections together with the classifier. This made 790,532 of 434,802,692 parameters trainable. Training ran for one epoch on Apple MPS with an effective batch size of 16 and learning rate 1e-4.
MAGE provides binary labels while this detector has four output classes. The training objective therefore compared the human logit with the combined nonhuman logit:
human_logit = logits[0]
nonhuman_logit = logsumexp(logits[1], logits[2], logits[3])
A KL-divergence preservation term discouraged collapse of the conditional distribution among ai, ai_edited, and humanized.
Training, validation, calibration, development, and sealed evaluation data were separated by published split and source group. Cross-boundary exact normalized-text matches and identical normalized 50-word prefixes were excluded.
See FINE_TUNING.md for the complete methodology and limitations.
On the untouched 1,997-document MAGE validation partition, ROC-AUC improved from 0.7820 to 0.9712.
The package-native threshold was selected on a separate 1,999-document MAGE calibration partition, targeting no more than 0.5% human false positives. At the selected threshold, calibration produced 54.6% AI recall, 0.40% human FPR, and 0.9659 ROC-AUC.
A fresh sealed package-native comparison used 4,000 documents from previously unused HC3 and RAID source groups:
| Model | ROC-AUC | AI recall | Human FPR | Balanced accuracy |
|---|---|---|---|---|
| Original, calibrated | 0.9672 | 66.70% | 0.10% | 83.30% |
| MAGE LoRA v1, calibrated | 0.9866 | 83.55% | 0.55% | 91.50% |
Dataset-level results:
| Dataset | Original recall | Fine-tuned recall | Original FPR | Fine-tuned FPR |
|---|---|---|---|---|
| HC3 | 91.9% | 92.6% | 0.0% | 0.7% |
| RAID | 41.5% | 74.5% | 0.2% | 0.4% |
File: onnx/model.onnx
Bytes: 1,737,980,451
SHA-256: 8b0d4d219bb87c645578b9bf590168635d5a5d0d2c7b7cb92a550fef2179d26f
The maximum absolute logit difference between PyTorch and ONNX across three reference inputs, including a 768-token input, was 0.000020682811737060547.
AI-text detection is probabilistic evidence, not proof of authorship. This model should not be the sole basis for disciplinary, employment, academic-integrity, legal, or other high-impact decisions.
Performance can vary with domain, language, generator, editing level, document length, and author population. The original model's undisclosed training corpus may overlap with public benchmarks. A false-positive rate measured on these samples does not guarantee the same rate in deployment.
Apache License 2.0. See LICENSE and NOTICE.
Base model: wasitaigeneratedcom/ai-text-detector-small.
10 files, 1.7 GB in total. The weights are 1 file totalling 1.7 GB in onnx.
| File | Type | Size | SHA-256 |
|---|---|---|---|
| onnx/model.onnx | Weights | 1.7 GB | 8b0d4d219bb8 |
| config.json | Configuration | 1.1 KB | — |
| serving_head.json | Configuration | 579 B | — |
| FINE_TUNING.md | Documentation | 10.7 KB | — |
| LICENSE | Documentation | 11.4 KB | — |
| NOTICE | Documentation | 401 B | — |
| README.md | Documentation | 4.4 KB | — |
| .gitattributes | Repository | 1.5 KB | — |
| tokenizer.json | Tokenizer | 8.3 MB | — |
| tokenizer_config.json | Tokenizer | 504 B | — |
Released by Bill Fisk through its official repository on Hugging Face. Read the license.
| Precision | Weights in memory |
|---|---|
| As published | 1.7 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Yes. ai-text-detector is released under Apache License 2.0. The Apache License 2.0 is a permissive open-source license. It permits commercial use, modification and redistribution. It requires keeping the license and copyright notices and any NOTICE file, stating significant changes, and it includes an express patent grant from contributors.
512 tokens, from the maximum position embeddings in its published configuration.
This is a RoBERTa-base model trained on ~124M tweets from January 2018 to December 2021, and finetuned for sentiment analysis with the TweetEval benchmark. The original Twitter-based RoBERTa model can be found here and the original reference paper is TweetEval. This model is suitable for English. 0 -> Negative; 1 -> Neutral; 2 -> Positive This sentiment analysis model has been integrated into TweetNLP. You can access the demo here.
FinBERT is a BERT model pre-trained on financial communication text. The purpose is to enhance financial NLP research and practice. It is trained on the following three financial communication corpus. The total corpora size is 4.9B tokens. More technical details on FinBERT: Click Link This released finbert-tone model is the FinBERT model fine-tuned on 10,000 manually annotated (positive, negative, neutral) sentences from analyst reports. This model achieves superior performance on financial tone analysis task. If you are simply interested in using FinBERT for financial tone analysis, give it a try. If you use the model in your academic work, please cite the following paper: Huang, Allen H.…
https://huggingface.co/cross-encoder/ms-marco-MiniLM-L-6-v2 with ONNX weights to be compatible with Transformers.js. If you haven't already, you can install the Transformers.js JavaScript library from NPM using: Note: Having a separate repo for ONNX weights is intended to be a temporary solution until WebML gains more traction. If you would like to make your models web-ready, we recommend converting to ONNX using Optimum and structuring your repo like this one (with ONNX weights located in a subfolder named onnx).
This is a multilingual XLM-roBERTa-base model trained on ~198M tweets and finetuned for sentiment analysis. The sentiment fine-tuning was done on 8 languages (Ar, En, Fr, De, Hi, It, Sp, Pt) but it can be used for more languages (see paper for details). This model has been integrated into the TweetNLP library.
The huggingface models currently give different results to the detoxify library (see issue here). For the most up to date models we recommend using the models from https://github.com/unitaryai/detoxify Trained models & code to predict toxic comments on 3 Jigsaw challenges: Toxic comment classification, Unintended Bias in Toxic comments, Multilingual toxic comment classification. Built by Laura Hanu at Unitary, where we are working to stop harmful content online by interpreting visual content in context. Score not directly comparable since it is obtained on the validation set provided and not on the test set. To update when the test labels are made available. It is also noteworthy to mention…
With this model, you can classify emotions in English text data. The model was trained on 6 diverse datasets (see Appendix below) and predicts Ekman's 6 basic emotions, plus a neutral class: 1) anger 2) disgust 3) fear 4) joy 5) neutral 6) sadness 7) surprise The model is a fine-tuned checkpoint of DistilRoBERTa-base. For a 'non-distilled' emotion model, please refer to the model card of the RoBERTa-large version. a) Run emotion model with 3 lines of code on single text example using Hugging Face's pipeline command on Google Colab: b) Run emotion model on multiple examples and full datasets (e.g.,.csv files) on Google Colab: Please reach out to [email protected] if you have any…