| license: apache-2.0 | |
| library_name: rwkv-clip | |
| pipeline_tag: zero-shot-image-classification | |
| datasets: | |
| - Kaichengalex/YFCC15M | |
| tags: | |
| - clip | |
| This repository contains the RWKV-CLIP-B32-YFCC15M model presented in [RWKV-CLIP: A Robust Vision-Language Representation Learner](https://huggingface.co/papers/2406.06973). | |