# Zero-shot Classification

A vision-language model fine-tuned based on the CLIP architecture, specifically designed for zero-shot classification of plant diseases

This model is converted from BAAI/bge-reranker-v2-m3 into GGUF format using llama.cpp via ggml.ai's GGUF-my-repo space, primarily for text classification tasks.

Marqo-FashionSigLIP is a multimodal embedding model optimized for fashion product search, achieving a 57% improvement in MRR and recall rate compared to FashionCLIP.

A zero-shot classification model fine-tuned on XNLI and ANLI datasets based on facebook/drama-large, supporting natural language inference tasks in 15 languages.

This is a pre-trained backdoor-injected model for studying backdoor sample detection in contrastive language-image pretraining.

This model is a fine-tuned version of Alibaba-NLP/gte-multilingual-base on the XNLI and ANLI datasets, supporting multilingual natural language inference tasks.

This model is a fine-tuned version of Alibaba-NLP/gte-multilingual-base on the XNLI dataset, supporting multilingual natural language inference tasks.

A CLIP-based fine-tuned model for LEGO brick image-text matching, specifically designed to recognize LEGO bricks and their descriptions.

ConceptCLIP is a large-scale vision-language pre-training model enhanced with medical concepts, suitable for various medical imaging modalities, capable of achieving robust performance across multiple medical imaging tasks.

Vision Transformer model based on CLIP architecture, specialized in image feature extraction

GIT is a Transformer-based generative image-to-text model capable of converting visual content into textual descriptions.

AIMv2 is a series of vision models pretrained with multimodal autoregressive objectives, demonstrating outstanding performance across multiple multimodal understanding benchmarks.

LLM2CLIP is an innovative approach that enhances CLIP's cross-modal capabilities through large language models, significantly improving the discriminative power of visual and text representations.

A multilingual vision-language pre-trained model for the remote sensing field, supporting image-text cross-modal tasks in 10 languages.

A fine-tuned fashion multimodal retrieval model based on ViT-B-16-SigLIP, specializing in fashion product search

Marqo-FashionCLIP is a fashion-domain multimodal retrieval model based on the CLIP architecture, achieving state-of-the-art performance in fashion product search tasks through generalized contrastive learning.

A large-scale vision-language model based on Vision Transformer architecture, supporting cross-modal understanding between images and text

A CLIP model trained on the Recap-DataComp-1B dataset using LLaMA-3 generated captions, suitable for zero-shot image classification tasks

ONNX ported version based on CLIP ViT-B/32 architecture, suitable for image classification and similarity search tasks.

A Japanese natural language inference cross-encoder trained on tohoku-nlp/bert-base-japanese-v3, supporting entailment, neutral, and contradiction judgments

A Japanese CLIP model developed by LY Corporation, trained on approximately 1 billion web-collected image-text pairs, suitable for various vision tasks.

BERTurk-Legal is a Transformer-based language model specifically designed for prior case retrieval tasks in the Turkish legal domain.

A Japanese natural language inference model based on BERT architecture, trained on the JSNLI dataset, used to determine logical relationships (entailment/neutral/contradiction) between sentence pairs

A zero-shot classification model based on the RoBERTa architecture, designed for text classification tasks without requiring training data, supports both GPU and CPU operation, and is trained using fully business-friendly data.

A DeBERTa-v3-large model specifically designed for efficient zero-shot classification, trained on fully commercially friendly synthetic data and NLI datasets, supporting GPU/CPU inference

A Korean natural language inference model based on the DeBERTa architecture, trained on the kor-nli and klue-nli datasets, supporting zero-shot classification tasks.

TeCoA is a vision-language model initialized from OpenAI CLIP, enhanced with supervised adversarial fine-tuning for improved robustness

CONCH is a vision-language foundation model for histopathology, pre-trained on 1.17 million pathology image-text pairs, demonstrating state-of-the-art performance in 14 computational pathology tasks.

A Japanese version of the CLIP model that maps Japanese text and images into the same embedding space, suitable for zero-shot image classification, text-image retrieval, and other tasks.

TinyCLIP is an innovative cross-modal distillation approach for large-scale language-image pre-trained models, achieving the optimal balance between speed and accuracy through affinity mimicking and weight inheritance techniques.

This is the ONNX format conversion of the fmops/distilbert-prompt-injection model, designed for detecting prompt injection attacks.

This model is a natural language inference model based on the RoBERTa architecture, specifically fine-tuned for depression detection tasks.

GIT is a Transformer-based image-to-text generation model capable of generating descriptive text from input images.

OpenAI's open-source CLIP model, based on Vision Transformer (ViT) architecture, supporting joint understanding of images and text.

A zero-shot image classification model based on OpenCLIP

A fine-tuned xlm-roberta-large model based on multilingual training data for zero-shot text classification, using the Manifesto Project coding scheme.

This is a vision-language model based on the CLIP architecture, specifically post-trained on 80 million face images.

A large CLIP model trained on the LAION-2B dataset, using ViT-bigG-14 architecture, supporting cross-modal understanding between images and text

PubMedCLIP is a version of the CLIP model fine-tuned for the medical field, specifically designed to handle medical images and related text.

GIT is a Transformer-based generative image-to-text model capable of converting visual content into descriptive text.