config.json

{
    "_vocab_size": 257152,
    "architectures": [
        "PaliGemmaForConditionalGeneration"
    ],
    "bos_token_id": 2,
    "eos_token_id": 1,
    "image_token_index": 257152,
    "model_type": "paligemma",
    "num_hidden_layers": 42,
    "pad_token_id": 0,
    "projection_dim": 3584,
    "text_config": {
        "architectures": [
            "Gemma2ForCausalLM"
        ],
        "attn_logit_softcapping": 50.0,
        "cache_implementation": "hybrid",
        "eos_token_id": [
            1,
            107
        ],
        "final_logit_softcapping": 30.0,
        "hidden_act": "gelu_pytorch_tanh",
        "hidden_activation": "gelu_pytorch_tanh",
        "hidden_size": 3584,
        "intermediate_size": 14336,
        "model_type": "gemma2",
        "num_attention_heads": 16,
        "num_hidden_layers": 42,
        "num_image_tokens": 1024,
        "num_key_value_heads": 8,
        "query_pre_attn_scalar": 256,
        "sliding_window": 4096,
        "torch_dtype": "bfloat16",
        "vocab_size": 257216
    },
    "torch_dtype": "bfloat16",
    "transformers_version": "4.47.0.dev0",
    "vision_config": {
        "hidden_size": 1152,
        "image_size": 448,
        "intermediate_size": 4304,
        "model_type": "siglip_vision_model",
        "num_attention_heads": 16,
        "num_hidden_layers": 27,
        "num_image_tokens": 1024,
        "num_positions": 1024,
        "patch_size": 14,
        "projection_dim": 3584,
        "torch_dtype": "bfloat16",
        "vision_use_head": false
    }
}