{
    "architectures": [
        "StepVLForConditionalGeneration"
    ],
    "auto_map": {
        "AutoConfig": "configuration_step_vl.StepRoboticsConfig",
        "AutoModelForCausalLM": "modeling_step_vl.Step3VL10BForCausalLM"
    },
    "model_type": "step_robotics",
    "im_end_token": "<im_end>",
    "im_patch_token": "<im_patch>",
    "im_start_token": "<im_start>",
    "image_token_len": 169,
    "patch_token_len": 81,
    "image_token_id": 151679,
    "understand_projector_stride": 2,
    "use_im_start_end": "true",
    "vision_select_layer": -1,
    "projector_bias": false,
    "vision_config": {
        "image_size": 728,
        "patch_size": 14,
        "width": 1536,
        "layers": 47,
        "heads": 16,
        "pool_type": "none",
        "output_dim": null,
        "use_cls_token": false,
        "ls_init_value": 0.1,
        "use_ln_post": false,
        "hidden_act": "quick_gelu"
    },
    "text_config": {
        "architectures": [
            "Qwen3ForCausalLM"
        ],
        "attention_bias": false,
        "attention_dropout": 0.0,
        "bos_token_id": 151643,
        "eos_token_id": [
            151643,
            151679
        ],
        "head_dim": 128,
        "hidden_act": "silu",
        "hidden_size": 4096,
        "initializer_range": 0.02,
        "intermediate_size": 12288,
        "max_position_embeddings": 65536,
        "max_window_layers": 36,
        "model_type": "qwen3",
        "num_attention_heads": 32,
        "num_hidden_layers": 36,
        "num_key_value_heads": 8,
        "rms_norm_eps": 1e-06,
        "rope_scaling": null,
        "rope_theta": 1000000,
        "sliding_window": null,
        "tie_word_embeddings": false,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.51.0",
        "use_cache": true,
        "use_sliding_window": false,
        "vocab_size": 151936
    }
}