config.json

{
    "embed_dim": 512,
    "image_cfg": {
        "image_size": 224,
        "model_name": "vit_b16"
    },
    "text_cfg": {
        "context_length": 77,
        "vocab_size": 49408,
        "dim": 512,
        "ffn_multiplier_per_layer": 4.0,
        "n_heads_per_layer": 8,
        "n_transformer_layers": 12,
        "norm_layer": "layer_norm_fp32",
        "causal_masking": true,
        "model_name": "base"
    }
}