{
    "_commit_hash": null,
    "architectures": [
        "LlavaForConditionalGeneration"
    ],
    "ignore_index": -100,
    "image_seq_length": 1,
    "image_token_index": 10,
    "model_type": "pixtral",
    "projector_hidden_act": "gelu",
    "quantization": {
        "group_size": 64,
        "bits": 8
    },
    "text_config": {
        "hidden_size": 5120,
        "head_dim": 128,
        "intermediate_size": 14336,
        "is_composition": true,
        "max_position_embeddings": 1024000,
        "model_type": "mistral",
        "num_hidden_layers": 40,
        "num_key_value_heads": 8,
        "rms_norm_eps": 1e-05,
        "rope_theta": 1000000000.0,
        "sliding_window": null,
        "vocab_size": 131072
    },
    "torch_dtype": "bfloat16",
    "transformers_version": null,
    "vision_config": {
        "head_dim": 64,
        "hidden_act": "gelu",
        "image_size": 1024,
        "is_composition": true,
        "model_type": "pixtral",
        "patch_size": 16,
        "rope_theta": 10000.0,
        "tie_word_embeddings": false,
        "intermediate_size": 4096
    },
    "vision_feature_layer": -1,
    "vision_feature_select_strategy": "full"
}