SecInt is a SmolLM2-360M model fine-tuned for real-time nginx security log classification, aiming to automatically detect security threats, errors, and normal traffic patterns in web server logs with an accuracy of over 99%, enabling real-time detection on the CPU.

Natural Language ProcessingTransformersMultiple Languages

This is the GGUF format version of the GPT-OSS 20B model based on WeOpenML, which first implements the innovative MoE CPU expert offloading technology. This technology achieves a 99.9% reduction in video memory while maintaining the full generation quality, and only requires 2MB of video memory to run a 20 billion parameter mixture of experts model.

Natural Language ProcessingSafetensorsMultiple Languages

This is an audio detection model based on the AST architecture, specifically fine-tuned for the drone audio recognition task. It achieved an accuracy of 99.6% and an F1 value of 99.74% on the evaluation set, showing excellent performance.

Audio ProcessingTransformers

A Vision Transformer-based binary classification model specifically designed for detecting deepfake images, with an accuracy rate of 99.2%

Computer VisionTransformers

This model is a fine-tuned version based on microsoft/deberta-v3-base, achieving an outstanding accuracy of 99.87% on the evaluation set.

Natural Language ProcessingTransformers

FP8 quantized version of QwQ-32B, reducing storage and memory requirements by 50% through dynamic quantization while maintaining 99.75% of the original model accuracy

Natural Language ProcessingTransformers

FP8 quantized version of QwQ-32B, reducing storage and memory requirements by 50% through dynamic quantization while maintaining 99.75% of the original model accuracy

Natural Language ProcessingTransformers

DistilBERT fine-tuned fake news classification model with approximately 99% accuracy

Natural Language ProcessingTransformersEnglish

This is a Turkish language model fine-tuned from ModernBERT-base-Turkish-uncased-mlm using PyLate, designed for sentence similarity calculation and document reranking.

Natural Language ProcessingSafetensorsOther

A deepfake audio detection model fine-tuned based on wav2vec2-base, achieving 99.66% accuracy

Audio ProcessingTransformers

A fine-tuned speech processing model based on facebook/wav2vec2-base, achieving 99.48% accuracy on the evaluation set

Audio ProcessingTransformers

Model fine-tuned based on bert-base-multilingual-cased, achieving 99.93% accuracy on the evaluation set

Natural Language ProcessingTransformers

A liveness detection model based on the DINOv2 architecture, designed to distinguish real faces from spoofing attacks, achieving 99.32% accuracy on the evaluation dataset.

Computer VisionTransformers

This is a BERT model fine-tuned for spam detection with a validation accuracy of approximately 99%

Natural Language ProcessingSafetensorsMultiple Languages

A ResNet-50 fine-tuned tomato leaf disease image classification model with 99.56% accuracy

Computer VisionTransformers

A fine-tuned tomato leaf disease classification model based on Google Vision Transformer (ViT) architecture, achieving 99.67% accuracy on the evaluation set

Computer VisionTransformers

This model is a text classification model fine-tuned on an unknown dataset based on PhoBERT-base-v2. It achieved an accuracy of 99.67% and an F1 score of 99.32% on the evaluation set.

Natural Language ProcessingTransformers

A speech processing model fine-tuned based on microsoft/wavLM-base, achieving 99.62% accuracy on the evaluation set

Audio ProcessingTransformers

A Deepfake audio detection model fine-tuned on audio folder datasets, achieving 99.73% accuracy

Audio ProcessingTransformers

A Deepfake audio detection model fine-tuned on audio folder datasets, capable of efficiently identifying synthetic speech with an evaluation accuracy of 99.64%

Audio ProcessingTransformers