{ "action_space_specs": [ { "action_dim": 138, "blocks": [ { "end": 3, "name": "left_wrist_pos", "start": 0 }, { "end": 9, "name": "left_wrist_rot6d", "start": 3 }, { "end": 69, "name": "left_finger_geometry", "start": 9 }, { "end": 72, "name": "right_wrist_pos", "start": 69 }, { "end": 78, "name": "right_wrist_rot6d", "start": 72 }, { "end": 138, "name": "right_finger_geometry", "start": 78 } ], "id": 0, "name": "human_hand_geometry", "proprio_dim": 138 }, { "action_dim": 184, "blocks": [ { "end": 64, "name": "sonic_motion", "start": 0 }, { "end": 124, "name": "left_finger_geometry", "start": 64 }, { "end": 184, "name": "right_finger_geometry", "start": 124 } ], "id": 1, "name": "human_fullbody_sonic_geometry", "proprio_dim": 120 }, { "action_dim": 76, "blocks": [ { "end": 64, "name": "sonic_motion", "start": 0 }, { "end": 70, "name": "left_revo2", "start": 64 }, { "end": 76, "name": "right_revo2", "start": 70 } ], "id": 2, "name": "robot_sonic_revo2", "proprio_dim": 44 }, { "action_dim": 36, "blocks": [ { "end": 7, "name": "left_hand", "start": 0 }, { "end": 14, "name": "right_hand", "start": 7 }, { "end": 21, "name": "left_arm", "start": 14 }, { "end": 28, "name": "right_arm", "start": 21 }, { "end": 32, "name": "torso_pose", "start": 28 }, { "end": 36, "name": "torso_navigation", "start": 32 } ], "id": 3, "name": "robot_g1_simple_sim", "proprio_dim": 32 }, { "action_dim": 184, "blocks": [ { "end": 64, "name": "sonic_motion", "start": 0 }, { "end": 124, "name": "left_finger_geometry", "start": 64 }, { "end": 184, "name": "right_finger_geometry", "start": 124 } ], "id": 4, "name": "human_fullbody_sonic_hand_state", "proprio_dim": 138 } ], "architectures": [ "Lambda0" ], "base_model_name_or_path": "Qwen/Qwen3.5-2B", "dim_time": 32, "dtype": "bfloat16", "expert_dropout": 0.0, "expert_hidden_size": 768, "expert_mlp_ratio": 4.0, "expert_num_heads": 12, "expert_num_layers": 24, "model_type": "lambda0", "num_actions": 50, "num_domains": 30, "prediction_type": "velocity", "qwen_config": { "_name_or_path": "", "architectures": [ "Qwen3_5ForConditionalGeneration" ], "chunk_size_feed_forward": 0, "dtype": null, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "image_token_id": 248056, "is_encoder_decoder": false, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "model_type": "qwen3_5", "output_attentions": false, "output_hidden_states": false, "problem_type": null, "return_dict": true, "text_config": { "_name_or_path": "", "architectures": null, "attention_bias": false, "attention_dropout": 0.0, "attn_output_gate": true, "bos_token_id": null, "chunk_size_feed_forward": 0, "dtype": "bfloat16", "eos_token_id": 248044, "full_attention_interval": 4, "head_dim": 256, "hidden_act": "silu", "hidden_size": 2048, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "initializer_range": 0.02, "intermediate_size": 6144, "is_encoder_decoder": false, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "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_conv_kernel_dim": 4, "linear_key_head_dim": 128, "linear_num_key_heads": 16, "linear_num_value_heads": 16, "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": 8, "num_hidden_layers": 24, "num_key_value_heads": 2, "output_attentions": false, "output_hidden_states": false, "pad_token_id": null, "partial_rotary_factor": 0.25, "problem_type": null, "return_dict": true, "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": true, "vocab_size": 248320 }, "tie_word_embeddings": true, "transformers_version": "5.14.1", "video_token_id": 248057, "vision_config": { "_name_or_path": "", "architectures": null, "chunk_size_feed_forward": 0, "deepstack_visual_indexes": [], "depth": 24, "dtype": null, "hidden_act": "gelu_pytorch_tanh", "hidden_size": 1024, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "in_channels": 3, "initializer_range": 0.02, "intermediate_size": 4096, "is_encoder_decoder": false, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "model_type": "qwen3_5_vision", "num_heads": 16, "num_position_embeddings": 2304, "out_hidden_size": 2048, "output_attentions": false, "output_hidden_states": false, "patch_size": 16, "problem_type": null, "return_dict": true, "spatial_merge_size": 2, "temporal_patch_size": 2 }, "vision_end_token_id": 248054, "vision_start_token_id": 248053 }, "soft_prompt_length": 32, "state_conditioning_mode": "discrete_vlm", "state_discrete_bins": 256, "training_contract": "lambda0_velocity_v1", "transformers_version": "5.14.1", "use_proprio": true, "variant": "2b", "vlm_hidden_size": 2048 }