# Few-shot Fine-tuning

A LoRA adapter based on the FLUX.1-dev model, specifically designed for generating logos, icons, and emojis, supporting various 3D rendering effects including Microsoft FluentUI style.

This is a sentence-transformers model fine-tuned from BAAI/bge-base-en-v1.5, which maps sentences and paragraphs to a 768-dimensional dense vector space.

A video understanding model fine-tuned based on MCG-NJU/videomae-base, with average performance on the evaluation set (accuracy 50%)

A video understanding model fine-tuned based on MCG-NJU/videomae-base, trained on an unknown dataset

A sentiment analysis model fine-tuned based on distilbert-base-uncased, achieving 87.67% accuracy on the evaluation set

A reasoning-enhanced model optimized from Google Gemma-3-1B, improving logical reasoning capabilities through GRPO algorithm and high-quality datasets

A DistilBERT-based text classification model for distinguishing between food and non-food texts

Hardhat detection model fine-tuned based on DETR-ResNet50 architecture, designed for industrial scenarios

A sentiment analysis model fine-tuned based on distilbert-base-uncased, achieving an accuracy of 85.67% on the evaluation set

A diffusion model based on the DDPM architecture for generating cartoon-style character avatars

A version fine-tuned for 1 day using the Docmatix dataset (5% data volume) based on Microsoft's Florence-2 model, suitable for image-text understanding tasks

This model is a fine-tuned version of google/paligemma-3b-pt-224 on a subset of the VQAv2 dataset, specializing in visual question answering tasks.

A clothing classification model fine-tuned based on Google's ViT model, supporting image classification for 7 clothing categories

A Flan-T5-Base fine-tuned intent classification model for categorizing customer queries into predefined categories

MetaVoice-1B is a 1.2 billion parameter text-to-speech (TTS) foundation model trained on 100,000 hours of speech data, specializing in generating emotional English speech with support for voice cloning and long-form synthesis.

This model is a fine-tuned version of Salesforce's BLIP image captioning base model on the SageMaker platform, primarily used for image caption generation tasks.

Document image understanding model fine-tuned based on naver-clova-ix/donut-base-finetuned-cord-v2

A model fine-tuned on an image folder dataset based on naver-clova-ix/donut-base, with no specific use case explicitly stated

This model is a vision classification model fine-tuned on the THFOOD-50 Thai food dataset based on the Swin Transformer V2 architecture, specifically designed for Thai food image recognition.

A model fine-tuned based on philschmid/donut-base-sroie, suitable for image processing tasks

This is an image classification model fine-tuned on a bean dataset based on Google's ViT model, achieving a high accuracy of 99.25% on the validation set.

A fine-tuned model based on the Swin Transformer architecture, specifically designed for skin cancer image classification tasks

A fine-tuned model based on Swin Transformer architecture for garbage classification tasks, achieving 88.27% accuracy

A small model based on the Swin Transformer architecture, fine-tuned on the CIFAR-100 dataset for image classification tasks

A model fine-tuned on the image folder dataset based on naver-clova-ix/donut-base, suitable for document understanding tasks

ConvNeXt-Tiny model fine-tuned on an image folder dataset, suitable for image classification tasks

A fine-tuned test version of Google Vision Transformer (ViT) base model on CIFAR-10 dataset

Audio classification model based on AST architecture, pre-trained on the AudioSet dataset and fine-tuned on the ESC-50 dataset

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

A fine-tuned version based on the naver-clova-ix/donut-base model on an image folder dataset, suitable for document understanding tasks.

Model fine-tuned based on naver-clova-ix/donut-base for processing image data

Invoice recognition model based on Donut architecture, fine-tuned on a dataset of 200 invoices

Image classification model fine-tuned on image folder dataset based on Google's ViT model, achieving 95.02% accuracy

A meme classification model fine-tuned from facebook/deit-base-patch16-224, achieving 84.85% accuracy on the imagefolder dataset

Model fine-tuned based on distilroberta-base, specific purpose not clearly stated

This model is a fine-tuned version of facebook/bart-base on the SQuAD dataset, suitable for question-answering tasks.

A question-answering model fine-tuned on the SQuAD dataset based on facebook/bart-base

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

A speech recognition model fine-tuned using the uob_singlish dataset based on the facebook/wav2vec2-xls-r-300m pre-trained model

This model is a fine-tuned version of wav2vec2-xls-r-300m-mixed based on the uob_singlish dataset, specializing in Singapore English speech recognition.