# Fine-tuning Optimization

An image segmentation model fine-tuned on the Dnq2025/Mask2former_Pretrain dataset, based on the facebook/mask2former-swin-base-IN21k-ade-semantic model

A text ranking model fine-tuned based on Qwen2.5-0.5B-Instruct, suitable for information retrieval and relevance ranking tasks

A Chinese speech recognition model fine-tuned based on whisper-large-v3-turbo, showing significant performance improvements in multiple Chinese speech recognition benchmarks

A Hausa-to-Chinese translation model fine-tuned based on T5-small, achieving a BLEU score of 30.0183 on the evaluation set.

An image caption generation model based on the ViT-GPT2 architecture, capable of converting input images into descriptive text

This is a text classification model fine-tuned on DistilBERT-base-uncased for distinguishing between food and non-food text content.

xFinder-llama38it is a fine-tuned key answer extraction model based on Llama3-8B-Instruct, designed to improve the accuracy and robustness of key answer extraction from large language model outputs.

A speech processing model further fine-tuned based on wav2vec2-base-finetuned, achieving 98.82% accuracy on the evaluation set

A fine-tuned speech processing model based on wav2vec2-base-finetuned, achieving 98.82% accuracy on the evaluation set

PaliGemma is a lightweight and versatile vision-language model built on the SigLIP vision model and Gemma language model, supporting multilingual image-text interaction tasks.

A fine-tuned essay scoring model based on TinyLlama-1.1B

A T5-small fine-tuned NL2SQL model for converting natural language to SQL queries

A Chinese speech recognition model fine-tuned based on distilwhisper-large-v2, with a speed 5.8 times faster than whisper-large-v2 and 51% fewer parameters

A document QA model fine-tuned based on microsoft/layoutlmv2-base-uncased, suitable for document layout understanding and QA tasks

Turkish speech recognition model fine-tuned based on OpenAI Whisper-small, with a word error rate of 26.34%

Fine-tuned image-to-text model based on microsoft/git-base

This model is a fine-tuned version of DistilHuBERT on the GTZAN music classification dataset, primarily used for music genre classification tasks.

A Korean-English translation model fine-tuned based on Helsinki-NLP's opus-mt-ko-en model

A vision-language model fine-tuned on image folder datasets based on microsoft/git-base, primarily used for image caption generation tasks

An image segmentation model fine-tuned on the bilal01/stamp-verification-test dataset based on nvidia/mit-b0

A vision model fine-tuned based on microsoft/swin-tiny-patch4-window7-224, achieving 100% accuracy on the evaluation set

Object detection model fine-tuned on the cppe-5 dataset based on facebook/detr-resnet-50

A video understanding model fine-tuned on an unknown dataset based on the VideoMAE base model, achieving 86.41% accuracy on the evaluation set

This model is a fine-tuned version of microsoft/xtremedistil-l6-h384-uncased on the SQuAD dataset, primarily used for question answering tasks.

This model is an image classification model fine-tuned on the CIFAR-100 dataset based on the Swin Transformer architecture, achieving an accuracy of 92.01%.

Japanese speech recognition model fine-tuned on the common_voice_11_0 dataset based on openai/whisper-medium

Urdu sentiment classification model based on xlm-roberta-base architecture, capable of binary sentiment classification for Urdu sentences

An image segmentation model fine-tuned on the imadd/water_dataset dataset based on nvidia/mit-b0, designed for water segmentation tasks

An image classification model fine-tuned based on microsoft/resnet-50, demonstrating medium accuracy on an unknown dataset

A text classification model fine-tuned on the becasv2 dataset based on distilbert-base-uncased

A question-answering model based on DistilBERT, fine-tuned on the SQuAD dataset for extractive question answering tasks.

A QA model fine-tuned on the adversarial_qa dataset based on microsoft/deberta-base

This model is an image classification model fine-tuned on the beans dataset based on the ConvNeXt-Tiny architecture, achieving an accuracy of 96.09%.

This model is a fine-tuned version of microsoft/xtremedistil-l12-h384-uncased on the wikitext dataset, primarily used for text generation tasks.

A speech recognition model fine-tuned on the common_voice dataset based on facebook/wav2vec2-base

A speech recognition model fine-tuned on the common_voice dataset based on facebook/wav2vec2-xls-r-300m

This model is a fine-tuned audio classification model based on distilhubert trained on a common language dataset, primarily used for language recognition tasks.

A text processing model fine-tuned based on the distilroberta-base model, suitable for general NLP tasks

A text sentiment classification model based on DistilBERT, fine-tuned on the emotion dataset with an accuracy of 92.9%

A lightweight Russian named entity recognition model based on BERT architecture, supporting the identification of three types of entities: person, location, and organization.