{ "architectures": [ "SpatialMLLMForConditionalGeneration" ], "attention_dropout": 0.0, "bos_token_id": 151643, "connector_config": { "connector_type": "mlp_add", "spatial_embeds_layer_idx": -1 }, "eos_token_id": 151645, "hidden_act": "silu", "hidden_size": 2048, "image_token_id": 151655, "initializer_range": 0.02, "intermediate_size": 11008, "max_position_embeddings": 128000, "max_window_layers": 70, "model_type": "spatial-mllm", "num_attention_heads": 16, "num_hidden_layers": 36, "num_key_value_heads": 2, "rms_norm_eps": 1e-06, "rope_scaling": { "mrope_section": [ 16, 24, 24 ], "rope_type": "default", "type": "default" }, "rope_theta": 1000000.0, "sliding_window": 32768, "spatial_config": { "_attn_implementation_autoset": true, "embed_dim": 1024, "img_size": 518, "model_type": "vggt_spatial_encoder", "patch_size": 14, "torch_dtype": "bfloat16" }, "tie_word_embeddings": true, "torch_dtype": "bfloat16", "transformers_version": "4.51.3", "use_cache": false, "use_sliding_window": false, "video_token_id": 151656, "vision_config": { "depth": 32, "fullatt_block_indexes": [ 7, 15, 23, 31 ], "hidden_act": "silu", "hidden_size": 1280, "in_channels": 3, "in_chans": 3, "intermediate_size": 3420, "model_type": "qwen2_5_vl", "num_heads": 16, "out_hidden_size": 2048, "patch_size": 14, "spatial_merge_size": 2, "spatial_patch_size": 14, "temporal_patch_size": 2, "tokens_per_second": 2, "torch_dtype": "bfloat16", "window_size": 112 }, "vision_end_token_id": 151653, "vision_start_token_id": 151652, "vision_token_id": 151654, "vocab_size": 151936 }