| { |
| "action_chunk_size": 30, |
| "action_dim": 81, |
| "action_head_type": "expert", |
| "architectures": [ |
| "Qwen3VLForConditionalGeneration" |
| ], |
| "depth_aux_num_heads": 8, |
| "depth_aux_num_layers": 2, |
| "depth_grid_size": 16, |
| "depth_loss_weight": 1.0, |
| "dtype": "bfloat16", |
| "eos_token_id": 151645, |
| "expert_backbone": "qwen3_vl", |
| "expert_foresight_visibility": "first", |
| "expert_hidden_size": 768, |
| "expert_intermediate_size": 2752, |
| "expert_num_attention_heads": null, |
| "expert_num_foresight_tokens": 0, |
| "expert_per_layer_adanorm": true, |
| "expert_qk_norm": false, |
| "expert_time_concat": true, |
| "expert_train_repeat": 1, |
| "history_token_id": -1, |
| "image_token_id": 151655, |
| "knowledge_insulation": false, |
| "latent_action_chunk_size": 6, |
| "latent_action_dim": 608, |
| "latent_action_stride": 5, |
| "lb_align_layer": null, |
| "lb_align_loss": "cosine", |
| "lb_align_weight": 0.5, |
| "lb_num_queries": 256, |
| "lb_num_task_tokens": 8, |
| "lb_query_init_std": 1.0, |
| "lb_resampler_dim_head": 32, |
| "lb_resampler_ff_mult": 1, |
| "lb_resampler_heads": 4, |
| "lb_resampler_layers": 1, |
| "model_type": "rynn_brain_vla", |
| "num_ee_types": 8, |
| "num_view_slots": 6, |
| "pad_token_id": 151643, |
| "predict_future_depth": true, |
| "sf_align_layer": null, |
| "sf_align_weight": 0.5, |
| "sf_teacher_code": null, |
| "sf_teacher_dim": 1024, |
| "sf_teacher_layer": -1, |
| "sf_teacher_path": null, |
| "sf_use_vlm_norm": true, |
| "state_token_id": 151669, |
| "text_config": { |
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "bos_token_id": 151643, |
| "dtype": "bfloat16", |
| "eos_token_id": 151645, |
| "head_dim": 128, |
| "hidden_act": "silu", |
| "hidden_size": 2048, |
| "initializer_range": 0.02, |
| "intermediate_size": 6144, |
| "knowledge_insulation": false, |
| "max_position_embeddings": 262144, |
| "model_type": "qwen3_vl_text", |
| "num_attention_heads": 16, |
| "num_hidden_layers": 28, |
| "num_key_value_heads": 8, |
| "pad_token_id": null, |
| "rms_norm_eps": 1e-06, |
| "rope_parameters": { |
| "mrope_interleaved": true, |
| "mrope_section": [ |
| 24, |
| 20, |
| 20 |
| ], |
| "rope_theta": 5000000, |
| "rope_type": "default" |
| }, |
| "tie_word_embeddings": true, |
| "use_cache": true, |
| "vocab_size": 151936 |
| }, |
| "tie_word_embeddings": true, |
| "time_conditioning": "adaln", |
| "transformers_version": "5.2.0", |
| "use_depth_aux": false, |
| "use_ee_embedding": false, |
| "use_history_cond": false, |
| "use_latent_actions": true, |
| "use_latent_head_readout": false, |
| "use_lb_align": false, |
| "use_sf_align": false, |
| "use_view_cond_slots": true, |
| "use_view_role_embedding": false, |
| "video_token_id": 151656, |
| "vision_config": { |
| "deepstack_visual_indexes": [ |
| 5, |
| 11, |
| 17 |
| ], |
| "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_vl", |
| "num_heads": 16, |
| "num_position_embeddings": 2304, |
| "out_hidden_size": 2048, |
| "patch_size": 16, |
| "spatial_merge_size": 2, |
| "temporal_patch_size": 2 |
| }, |
| "vision_end_token_id": 151653, |
| "vision_start_token_id": 151652 |
| } |
|
|
