# Transfer learning optimization

Haitian Creole speech recognition model fine-tuned based on OpenAI Whisper-medium, focusing on high-accuracy transcription

An image classification model based on Google Vision Transformer (ViT) architecture, specifically fine-tuned for the beans dataset

An image classification model built based on the timm library, with zoobot-encoder-convnext_nano as the base model, capable of image classification.

Vision Transformer model based on OpenCLIP framework, fine-tuned for zero-shot image classification tasks

An image segmentation model based on the SegFormer-B5 architecture, fine-tuned on larger-sized image datasets, excels at distinguishing between background and branch regions

Lightweight image classification model based on DeiT-tiny architecture, achieving 98.56% validation accuracy after fine-tuning on a custom image dataset

A computer vision model based on ConvNeXt-Tiny architecture, fine-tuned on specific datasets for image classification tasks

A fine-tuned image classification model based on the Swin Transformer architecture, achieving 99.17% validation accuracy on the image folder dataset

Vision Transformer model fine-tuned on flower image dataset based on Google's ViT model

A lightweight image classification model based on the DeiT-tiny architecture, achieving 94.8% accuracy after fine-tuning on a custom image dataset

A lightweight image classification model based on SwinV2 architecture, fine-tuned on an image folder dataset with 97.83% accuracy

This is a vision model based on the Swin Transformer architecture, which performs excellently in image classification tasks after fine-tuning.

This model is a fine-tuned image classification model based on the Swin Transformer V2 Tiny architecture, achieving 96.35% accuracy on the evaluation set.

This model is a fine-tuned version based on microsoft/beit-base-patch16-224-pt22k-ft22k, with specific usage and training data not explicitly stated.

A vision model based on the Swin Transformer Tiny architecture, fine-tuned on an unknown dataset for image classification tasks

Image classification model fine-tuned based on google/vit-base-patch16-224-in21k, achieving 91% accuracy on the test set

Fine-tuned model based on Swin Transformer Tiny architecture for image classification tasks

A fine-tuned model based on Google Vision Transformer (ViT) architecture, suitable for image classification tasks

This model is an image classification model based on the Swin Transformer architecture, achieving 98.9% accuracy after fine-tuning on the CIFAR-10 dataset.

A multilingual QA model fine-tuned on the SQuAD v2 dataset based on bert-base-multilingual-cased

An image classification model based on the BEiT architecture, fine-tuned on an image folder dataset with an accuracy rate of 98.7%

Vision Transformer model based on BEiT architecture, fine-tuned on MNIST handwritten digit dataset, achieving 99.35% accuracy

An image classification model fine-tuned on the image folder dataset based on microsoft/cvt-13-384-22k, achieving an accuracy of 83.46% on the evaluation set

This model is a fine-tuned version based on facebook/convnext-tiny-224, primarily used for image classification tasks, demonstrating excellent performance on the evaluation set.

High-precision image classification model fine-tuned based on Google's ViT-base model, achieving 91.81% accuracy on the evaluation set

GPTuz is an advanced Uzbek language model based on the GPT-2 small model, trained through transfer learning and fine-tuning techniques.

An image classification model fine-tuned on the Cifar100 dataset based on Google's ViT base model, achieving an accuracy of 89.85%

This model is a fine-tuned BEiT base version on the CIFAR-10 dataset, focusing on image classification tasks, achieving 99.18% accuracy on the evaluation set.

A fine-tuned version of Google's ViT model on an image folder dataset for image classification tasks, achieving an accuracy of 90.72%.

An image classification model fine-tuned on an image folder dataset based on Visual-Attention-Network/van-base, achieving an accuracy of 98.85%

This model is an image classification model fine-tuned on the CIFAR-10 dataset based on the Swin Transformer Tiny architecture, achieving an accuracy of 97.89%.

This model is a fine-tuned version of distilbert-base-uncased on an unspecified dataset, primarily used for text-related tasks.

A T5 (Text-to-Text Transfer Transformer) model pretrained on Japanese corpus, suitable for various text generation tasks.

Indonesian natural language inference classifier based on the Indo-roberta model, trained using the IndoNLI dataset

Image classification model based on ConvNeXt architecture, fine-tuned on image folder dataset

Spanish language model based on GPT-2 small architecture, fine-tuned on Spanish Wikipedia through transfer learning

This model is a transfer learning-based Arabic speech recognition system specifically designed to identify Quran recitations and locate corresponding chapters.

T5-3B is a 3-billion-parameter text-to-text transfer Transformer model developed by Google, employing a unified text-to-text framework to handle various NLP tasks.

A SQL code summarization model based on the T5-large architecture, optimized through transfer learning and fine-tuning, specifically designed for generating functional descriptions of SQL code

A Dutch-specific model developed based on OpenAI's small GPT-2 model, optimized for Dutch language processing by retraining the word embedding layer and fine-tuning