# Transfer Learning Optimization

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

This model predicts users' tendencies in the Big Five personality traits (OCEAN) by analyzing their responses to 20 questions, achieving 97% accuracy

This model is a fine-tuned version of facebook/convnextv2-large-22k-224 on a dog breed classification dataset, achieving an accuracy of 91.39% on the evaluation set.

Image classification model fine-tuned based on google/vit-base-patch16-224-in21k, suitable for plant classification tasks

A plant image classification model based on the ViT architecture, achieving 99.95% validation accuracy after fine-tuning on an unknown dataset

A pre-trained image classification model based on the BEiT architecture, supporting Vietnamese labels, suitable for vision tasks

A bird image classification model based on Swin Transformer architecture, fine-tuned on bird datasets with an accuracy of 82.15%

An image classification model fine-tuned on the image folder dataset based on microsoft/beit-base-patch16-224-pt22k-ft22k

A Vision Transformer-based image classification model for identifying vegetation in street view images, achieving an accuracy of 92.9%.

Vision model based on Swin Transformer Tiny architecture, fine-tuned for 10 epochs on image classification tasks

A fine-tuned image classification model based on Swin Transformer Tiny architecture, trained on image folder datasets

A fine-tuned image classification model based on ConvNeXt-Tiny architecture, achieving 98.15% accuracy on the EuroSAT dataset

An image classification model fine-tuned based on Google's Vision Transformer (ViT), trained on custom image datasets

A melanoma image classification model fine-tuned based on Google's ViT-Large model, achieving 82.73% accuracy on the evaluation set

This model is a fine-tuned version of Google's ViT model on an unknown dataset, primarily used for image classification tasks.

An image classification model fine-tuned on the sudo-s/herbier_mesuem1 dataset based on google/vit-base-patch16-224-in21k, achieving 91.29% accuracy

This model is a fine-tuned version based on the Swin Transformer architecture, specifically designed for MRI image classification tasks, achieving an accuracy of 98.07% on the evaluation set.

An Indonesian emotion classifier trained on the Indo-roberta model, fine-tuned on the IndoNLU EmoT dataset for sentiment analysis tasks.

This is a streamlined 3-layer version of the Microsoft MiniLM-L12-H384-uncased model, retaining only layers [3,7,11] from the original model.

A compressed BERT model achieved through progressive module replacement, reducing model complexity while maintaining performance

FinBERT is a Finnish pre-trained language model based on Google's BERT architecture, trained on over 3 billion Finnish word tokens and suitable for various Finnish NLP tasks.

BERT-based Portuguese model trained on clinical records and biomedical literature

MiniLMv2 is a lightweight pre-trained language model introduced by Microsoft, achieving efficient inference through knowledge distillation technology.

GerPT2 is a large German language model based on the GPT2 architecture, trained on the CC-100 and German Wikipedia datasets, outperforming similar German GPT2 models.

This is a sentence transformer model based on XLM-Roberta-base, specifically designed for semantic text similarity tasks in Greek and English.

This is a BERT-based Turkish named entity recognition model, suitable for entity recognition tasks in Turkish texts.

This model is a sparse pre-trained model achieving 90% sparsity through weight pruning techniques, suitable for fine-tuning on various language tasks.

Pre-trained model based on the t5-large architecture, specializing in Python code summarization tasks

This is a sparsely pretrained BERT-Base model achieving 90% weight sparsity through one-shot pruning, suitable for fine-tuning on various language tasks.

This is a pretrained language model for Tagalog, trained on multi-source data, aimed at improving the performance of Tagalog natural language processing tasks.