Hugging Face's logo

InternRobotics
/
InternVLA-A1.5-DOMINO

Robotics
Safetensors
vision-language-action-model
world-model
manipulation
domino
Model card Files
xet
 Community
1
InternVLA-A1.5-DOMINO
File size: 2,254 Bytes
804a639
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
{
  "type": "internvla_a1_5",
  "n_obs_steps": 1,
  "input_features": {
    "observation.state": {
      "type": "STATE",
      "shape": [
        32
      ]
    }
  },
  "output_features": {
    "action": {
      "type": "ACTION",
      "shape": [
        32
      ]
    }
  },
  "device": "cuda:0",
  "use_amp": false,
  "push_to_hub": false,
  "repo_id": null,
  "private": null,
  "tags": null,
  "license": null,
  "pretrained_path": null,
  "vlm_model_name_or_path": "Qwen/Qwen3.5-2B",
  "action_expert_hidden_size": 1024,
  "action_expert_intermediate_size": 3072,
  "dtype": "bfloat16",
  "chunk_size": 50,
  "n_action_steps": 50,
  "max_state_dim": 32,
  "max_action_dim": 32,
  "num_inference_steps": 10,
  "time_sampling_beta_alpha": 1.5,
  "time_sampling_beta_beta": 1.0,
  "time_sampling_scale": 0.999,
  "time_sampling_offset": 0.001,
  "min_period": 0.004,
  "max_period": 4.0,
  "image_resolution": [
    224,
    224
  ],
  "empty_cameras": 0,
  "normalization_mapping": {
    "VISUAL": "IDENTITY",
    "STATE": "IDENTITY",
    "ACTION": "IDENTITY"
  },
  "gradient_checkpointing": false,
  "compile_model": false,
  "compile_mode": "max-autotune",
  "optimizer_lr": 5e-05,
  "optimizer_betas": [
    0.9,
    0.95
  ],
  "optimizer_eps": 1e-08,
  "optimizer_weight_decay": 0.01,
  "optimizer_grad_clip_norm": 1.0,
  "scheduler_warmup_steps": 2000,
  "scheduler_decay_steps": 100000,
  "scheduler_decay_lr": 5e-06,
  "tokenizer_max_length": 48,
  "freeze_vision_encoder": false,
  "train_expert_only": false,
  "enable_vqa_loss": true,
  "lambda_vqa": 1.0,
  "tokenize_state": true,
  "action_token_min": 248077,
  "action_token_max": 250124,
  "knowledge_insulation": false,
  "block_action_attend_fast_tokens": true,
  "inference_action_type": "fm",
  "use_sdpa": false,
  "num_learnable_tokens": 50,
  "wan_checkpoint_path": "Wan-AI/Wan2.2-TI2V-5B",
  "wan_config_path": "Wan-AI/Wan2.2-TI2V-5B",
  "vae_path": "Wan-AI/Wan2.2-TI2V-5B/Wan2.2_VAE.pth",
  "video_precision": "bfloat16",
  "freeze_wan_dit": true,
  "num_video_frames": 4,
  "video_height": 224,
  "video_width": 224,
  "video_loss_weight": 1.0,
  "video_loss_only": false,
  "action_loss_only": true,
  "freeze_learnable_tokens": true,
  "inference_backend": "standard"
}