| { |
| "architectures": [ |
| "Qwen3_5ForConditionalGenerationWithSpatialForcing" |
| ], |
| "depth_gradient_scales": [ |
| 1, |
| 2, |
| 4, |
| 8 |
| ], |
| "depth_loss_type": "geo_depth", |
| "depth_loss_weight": 0.05, |
| "depth_outlier_keep_ratio": 0.98, |
| "depth_student_layers": [ |
| 7, |
| 16, |
| 24, |
| 32 |
| ], |
| "depth_supervision_enabled": false, |
| "depth_use_teacher_confidence": false, |
| "dtype": "bfloat16", |
| "eos_token_id": 248046, |
| "heading_loss_weight": 0.1, |
| "heading_projection_dim": 512, |
| "heading_supervision_enabled": true, |
| "heading_turn_angle_deg": 15.0, |
| "image_token_id": 248056, |
| "model_type": "qwen3_5", |
| "pad_token_id": 248044, |
| "progress_loss_type": "bce_logits", |
| "progress_loss_weight": 0.1, |
| "progress_projection_dim": 512, |
| "progress_supervision_enabled": true, |
| "progress_target_convention": "completed_before_current", |
| "progress_target_type": "expert_forward_fraction", |
| "sf_layer_weights": [ |
| 0.3333333333333333, |
| 0.3333333333333333, |
| 0.3333333333333333 |
| ], |
| "sf_loss_weight": 0.3, |
| "sf_multiframe_teacher": false, |
| "sf_multilayer_enabled": true, |
| "sf_projector_hidden_dim": 4096, |
| "sf_student_layer": 24, |
| "sf_student_layers": [ |
| 8, |
| 16, |
| 24 |
| ], |
| "sf_teacher_dim": 2048, |
| "sf_teacher_layer": 23, |
| "sf_teacher_layers": [ |
| 11, |
| 17, |
| 23 |
| ], |
| "sf_use_vggt_pe": true, |
| "sf_verify_invariants": true, |
| "spatial_forcing_enabled": true, |
| "spatial_teacher_model_path": "facebook/VGGT-1B", |
| "text_config": { |
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "attn_output_gate": true, |
| "bos_token_id": null, |
| "dtype": "bfloat16", |
| "eos_token_id": 248044, |
| "full_attention_interval": 4, |
| "head_dim": 256, |
| "hidden_act": "silu", |
| "hidden_size": 2560, |
| "initializer_range": 0.02, |
| "intermediate_size": 9216, |
| "layer_types": [ |
| "linear_attention", |
| "linear_attention", |
| "linear_attention", |
| "full_attention", |
| "linear_attention", |
| "linear_attention", |
| "linear_attention", |
| "full_attention", |
| "linear_attention", |
| "linear_attention", |
| "linear_attention", |
| "full_attention", |
| "linear_attention", |
| "linear_attention", |
| "linear_attention", |
| "full_attention", |
| "linear_attention", |
| "linear_attention", |
| "linear_attention", |
| "full_attention", |
| "linear_attention", |
| "linear_attention", |
| "linear_attention", |
| "full_attention", |
| "linear_attention", |
| "linear_attention", |
| "linear_attention", |
| "full_attention", |
| "linear_attention", |
| "linear_attention", |
| "linear_attention", |
| "full_attention" |
| ], |
| "linear_conv_kernel_dim": 4, |
| "linear_key_head_dim": 128, |
| "linear_num_key_heads": 16, |
| "linear_num_value_heads": 32, |
| "linear_value_head_dim": 128, |
| "mamba_ssm_dtype": "float32", |
| "max_position_embeddings": 262144, |
| "mlp_only_layers": [], |
| "model_type": "qwen3_5_text", |
| "mtp_num_hidden_layers": 1, |
| "mtp_use_dedicated_embeddings": false, |
| "num_attention_heads": 16, |
| "num_hidden_layers": 32, |
| "num_key_value_heads": 4, |
| "pad_token_id": null, |
| "partial_rotary_factor": 0.25, |
| "rms_norm_eps": 1e-06, |
| "rope_parameters": { |
| "mrope_interleaved": true, |
| "mrope_section": [ |
| 11, |
| 11, |
| 10 |
| ], |
| "partial_rotary_factor": 0.25, |
| "rope_theta": 10000000, |
| "rope_type": "default" |
| }, |
| "tie_word_embeddings": true, |
| "use_cache": false, |
| "vocab_size": 248320 |
| }, |
| "tie_word_embeddings": true, |
| "transformers_version": "5.3.0", |
| "use_cache": true, |
| "use_geometry_encoder": false, |
| "use_geometry_fusion": false, |
| "video_token_id": 248057, |
| "vision_config": { |
| "deepstack_visual_indexes": [], |
| "depth": 24, |
| "dtype": "bfloat16", |
| "hidden_act": "gelu_pytorch_tanh", |
| "hidden_size": 1024, |
| "in_channels": 3, |
| "initializer_range": 0.02, |
| "intermediate_size": 4096, |
| "model_type": "qwen3_5", |
| "num_heads": 16, |
| "num_position_embeddings": 2304, |
| "out_hidden_size": 2560, |
| "patch_size": 16, |
| "spatial_merge_size": 2, |
| "temporal_patch_size": 2 |
| }, |
| "vision_end_token_id": 248054, |
| "vision_start_token_id": 248053 |
| } |
|
|
