cogvlm

GPT4V-level open-source multi-modal model based on Llama3-8B

Tag manager and captioner for image datasets

Famous Vision Language Models and Their Architectures

Python scripts to use for captioning images with VLMs

Tiny-scale experiment showing that CLIP models trained using detailed captions generated by multimodal models (CogVLM and LLaVA 1.5) outperform models trained using the original alt-texts on a range of classification and retrieval tasks.

A comparitive study between the two of the best performing open source Vision Language Models - Google Gemini Vision and CogVLM