Hugging Face's logo

OPTML-Group
/
ResWAM-RoboDojo

Robotics
PyTorch
vision-language-action
world-action-model
flow-matching
robodojo
bimanual-manipulation
Model card Files
xet
 Community
ResWAM-RoboDojo
File size: 4,004 Bytes
e586b8b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
{
  "action": {
    "dimension": 14,
    "execute_horizon": 10,
    "horizon": 32,
    "padding": "end_of_episode_clamp_to_last_frame_supervised",
    "representation": "14-D absolute joint/qpos"
  },
  "benchmark": "robodojo",
  "data": {
    "camera_keys": {
      "head": "observation.images.cam_high",
      "left_wrist": "observation.images.cam_left_wrist",
      "right_wrist": "observation.images.cam_right_wrist"
    },
    "camera_order": [
      "head",
      "left_wrist",
      "right_wrist"
    ],
    "codec": {
      "decode_clip": false,
      "encode_clamp_sigma": 12.0,
      "grippers": "2x-1",
      "joints": "zscore_mean_std_all_clean_frames",
      "statistics": "codec_statistics.json",
      "version": "reswam-robodojo-absolute-qpos-zscore-joints-affine-grippers-14d-v1"
    },
    "metadata_frequency_hz": 25,
    "preprocess_to_256": "direct_bicubic_antialias_no_crop",
    "vlm_camera_order": [
      "head",
      "left_wrist",
      "right_wrist"
    ]
  },
  "dataset": {
    "action_dimension": 14,
    "action_representation": "14-D absolute joint/qpos",
    "camera_order": [
      "head",
      "left_wrist",
      "right_wrist"
    ],
    "cleaning_variant": "all-frames",
    "control_hz": 25,
    "episodes": 3500,
    "frames": 1856102,
    "gripper_semantics": "larger_is_more_open",
    "hf_repo": "RoboDojo-Benchmark/RoboDojo",
    "joint_order": [
      "left_joint_0",
      "left_joint_1",
      "left_joint_2",
      "left_joint_3",
      "left_joint_4",
      "left_joint_5",
      "left_joint_6",
      "right_joint_0",
      "right_joint_1",
      "right_joint_2",
      "right_joint_3",
      "right_joint_4",
      "right_joint_5",
      "right_joint_6"
    ],
    "sampler": "uniform_concat_every_clean_frame_end_clamped_supervised",
    "state_dimension": 14,
    "state_representation": "14-D current qpos",
    "tasks": 35
  },
  "evaluation": {
    "action_type": "joint",
    "benchmark": "RoboDojo sim (Isaac Sim 5.1 / Isaac Lab 2.3), official XPolicyLab websocket client",
    "control_hz": 25,
    "env_cfg": "arx_x5",
    "execute_horizon": 10,
    "num_configs": 54,
    "num_tasks": 42,
    "prediction_horizon": 32,
    "seeds": [
      0
    ],
    "total_episodes": 2100
  },
  "flow": {
    "action_noise": "independent_gaussian",
    "action_scheduler_shift": 1,
    "action_tau": "independent_uniform_shifted",
    "inference_rounds": 10,
    "synchronous_commit": true,
    "world_noise": "independent_gaussian",
    "world_scheduler_shift": 5,
    "world_tau": "independent_uniform_shifted"
  },
  "model": {
    "dino": {
      "architecture": "DINOv3-B/16",
      "combine": "arithmetic_mean",
      "frozen": true,
      "model_id": "facebook/dinov3-vitb16-pretrain-lvd1689m",
      "remove_prefix_tokens": true,
      "selected_blocks": [
        8,
        10
      ],
      "spatial_pooling": "2x2",
      "target_token_ln": true,
      "tokens": 64
    },
    "expert": {
      "depth": 12,
      "expert_parameter_count": 493608462,
      "ffn_dim": 4096,
      "heads": 16,
      "hidden_dim": 1024,
      "state_dropout_prob": 0.0,
      "use_state_null_tokens": false
    },
    "rynnbrain": {
      "backbone_parameter_count": 1755487104,
      "repo": "Alibaba-DAMO-Academy/RynnBrain1.1-2B",
      "text_hidden_size": 2048,
      "text_layers": 16,
      "vision_layers": 24
    }
  },
  "optimizer": {
    "betas": [
      0.9,
      0.95
    ],
    "clip_grad_norm": 1.0,
    "expert_min_lr": 1e-05,
    "expert_peak_lr": 0.0001,
    "name": "AdamW",
    "precision": "bfloat16",
    "vlm_min_lr": 1e-06,
    "vlm_peak_lr": 1e-05,
    "weight_decay": 1e-08
  },
  "schema_version": "reswam-robodojo-config-v1",
  "training": {
    "fsdp": "FULL_SHARD",
    "global_batch": 256,
    "gradient_accumulation": 2,
    "microbatch": 32,
    "seed": 20260907,
    "world_size": 4
  },
  "world": {
    "camera": "head",
    "loss_weight": 0.1,
    "objective": "endpoint_only_extra_LN_delta",
    "target_offset": 32
  }
}