config.json

{
    "architectures": [
        "Mistral3ForConditionalGeneration"
    ],
    "image_token_index": 10,
    "model_type": "mistral3",
    "multimodal_projector_bias": false,
    "projector_hidden_act": "gelu",
    "quantization": {
        "group_size": 64,
        "bits": 8
    },
    "quantization_config": {
        "group_size": 64,
        "bits": 8
    },
    "spatial_merge_size": 2,
    "text_config": {
        "attention_dropout": 0.0,
        "head_dim": 128,
        "hidden_act": "silu",
        "hidden_size": 5120,
        "initializer_range": 0.02,
        "intermediate_size": 32768,
        "max_position_embeddings": 131072,
        "model_type": "mistral",
        "num_attention_heads": 32,
        "num_hidden_layers": 40,
        "num_key_value_heads": 8,
        "rms_norm_eps": 1e-05,
        "rope_theta": 1000000000.0,
        "sliding_window": null,
        "use_cache": true,
        "vocab_size": 131072,
        "tie_word_embeddings": false
    },
    "torch_dtype": "bfloat16",
    "transformers_version": "4.52.4",
    "vision_feature_layer": -1
}