config.json

{
    "architectures": [
        "Llama4ForConditionalGeneration"
    ],
    "boi_token_index": 200080,
    "eoi_token_index": 200081,
    "image_token_index": 200092,
    "model_type": "llama4",
    "quantization": {
        "group_size": 64,
        "bits": 6
    },
    "quantization_config": {
        "group_size": 64,
        "bits": 6
    },
    "text_config": {
        "_attn_implementation_autoset": true,
        "attention_bias": false,
        "attention_chunk_size": 8192,
        "attention_dropout": 0.0,
        "bos_token_id": 200000,
        "eos_token_id": [
            200001,
            200007,
            200008
        ],
        "for_llm_compressor": false,
        "head_dim": 128,
        "hidden_act": "silu",
        "hidden_size": 5120,
        "initializer_range": 0.02,
        "interleave_moe_layer_step": 2,
        "intermediate_size": 8192,
        "intermediate_size_mlp": 16384,
        "max_position_embeddings": 1048576,
        "model_type": "llama4_text",
        "num_attention_heads": 40,
        "num_experts_per_tok": 1,
        "num_hidden_layers": 48,
        "num_key_value_heads": 8,
        "num_local_experts": 128,
        "output_router_logits": false,
        "pad_token_id": 200018,
        "rms_norm_eps": 1e-05,
        "rope_scaling": null,
        "rope_theta": 500000.0,
        "router_aux_loss_coef": 0.001,
        "router_jitter_noise": 0.0,
        "torch_dtype": "bfloat16",
        "use_cache": true,
        "use_qk_norm": false,
        "vocab_size": 202048
    },
    "torch_dtype": "bfloat16",
    "transformers_version": "4.51.0.dev0",
    "vision_config": {
        "_attn_implementation_autoset": true,
        "attention_dropout": 0.0,
        "hidden_act": "gelu",
        "hidden_size": 1408,
        "image_size": 336,
        "initializer_range": 0.02,
        "intermediate_size": 5632,
        "model_type": "llama4_vision_model",
        "multi_modal_projector_bias": false,
        "norm_eps": 1e-05,
        "num_attention_heads": 16,
        "num_channels": 3,
        "num_hidden_layers": 34,
        "patch_size": 14,
        "pixel_shuffle_ratio": 0.5,
        "projector_dropout": 0.0,
        "projector_input_dim": 4096,
        "projector_output_dim": 4096,
        "rope_theta": 10000,
        "vision_feature_layer": -1,
        "vision_feature_select_strategy": "default",
        "vision_output_dim": 4096
    }
}