open_clip/model_configs/convnext_xlarge.json

{
    "embed_dim": 1024,
    "vision_cfg": {
        "timm_model_name": "convnext_xlarge",
        "timm_model_pretrained": false,
        "timm_pool": "",
        "timm_proj": "linear",
        "timm_drop": 0.0,
        "timm_drop_path": 0.1,
        "image_size": 256
    },
    "text_cfg": {
        "context_length": 77,
        "vocab_size": 49408,
        "width": 1024,
        "heads": 16,
        "layers": 20
    }
}