# Vision-Language Pretraining

BLIP is a unified vision-language pretraining framework, excelling in vision-language tasks such as image caption generation

A vision-language model fine-tuned from openai/clip-vit-large-patch14, trained for 10 epochs

Vision Transformer model based on SigLIP architecture, containing only the image encoder part, utilizing raw attention pooling mechanism

Vision Transformer model based on SigLIP architecture, containing only the image encoder part, using original attention pooling mechanism

MiniVLA is a more compact yet higher-performing vision-language-action model, compatible with the Prismatic VLMs project codebase.

BiomedCLIP is a biomedical vision-language processing model developed by Microsoft, based on PubMedBERT and ViT architecture, specifically designed for the biomedical domain.

BLIP is a unified vision-language pretraining framework, excelling in tasks like image caption generation, supporting both conditional and unconditional text generation

Vision-language model based on ViLT architecture, fine-tuned for specific tasks

LLaVA is an open-source multimodal chatbot, fine-tuned based on LLaMA/Vicuna and trained with GPT-generated multimodal instruction-following data.

BLIP is an advanced vision-language pretraining model, excelling in image captioning tasks by effectively utilizing web data through guided annotation strategies

OTTER-MPT7B-Init is a set of weights for initializing Otter model training, converted directly from Openflamingo.

Image caption generation model fine-tuned based on Salesforce/blip-image-captioning-base

Pix2Struct is an image encoder-text decoder model trained on image-text pairs, suitable for various vision-language tasks

A vision-language model pre-trained on COCO and fine-tuned on a football dataset, proficient in generating image captions