This is a CLIP model that uses a ConvNeXt base visual backbone trained on the LAION-2B dataset. It produces aligned image and text embeddings suitable for zero-shot image classification, retrieval, and multimodal tasks. The model is provided by LAION on Hugging Face.
In the Embeddings & retrieval space, CLIP Convnext Base W laion2B s13B b82K takes a focused approach. It focuses on creating joint image-text embeddings for zero-shot classification and retrieval using a ConvNeXt-based CLIP model. CLIP Convnext Base W laion2B s13B b82K is an open-source project aimed at developers. CLIP Convnext Base W laion2B s13B b82K is open source under the Open Source license. It ships for the web and API.
LAION builds and maintains CLIP Convnext Base W laion2B s13B b82K, and it first shipped in 2021. Development happens publicly on GitHub with 14k stars and 115 commits in the last 90 days.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do