File size: 2,038 Bytes
			
			c09a564 e74c04c c09a564  | 
								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  | 
								{
    "type": "smolvla",
    "n_obs_steps": 1,
    "normalization_mapping": {
        "VISUAL": "IDENTITY",
        "STATE": "MEAN_STD",
        "ACTION": "MEAN_STD"
    },
    "input_features": {
        "observation.state": {
            "type": "STATE",
            "shape": [
                6
            ]
        },
        "observation.image2": {
            "type": "VISUAL",
            "shape": [
                3,
                256,
                256
            ]
        },
        "observation.image": {
            "type": "VISUAL",
            "shape": [
                3,
                256,
                256
            ]
        },
        "observation.image3": {
            "type": "VISUAL",
            "shape": [
                3,
                256,
                256
            ]
        }
    },
    "output_features": {
        "action": {
            "type": "ACTION",
            "shape": [
                6
            ]
        }
    },
    "chunk_size": 50,
    "n_action_steps": 50,
    "max_state_dim": 32,
    "max_action_dim": 32,
    "resize_imgs_with_padding": [
        512,
        512
    ],
    "empty_cameras": 0,
    "adapt_to_pi_aloha": false,
    "use_delta_joint_actions_aloha": false,
    "tokenizer_max_length": 48,
    "num_steps": 10,
    "use_cache": true,
    "freeze_vision_encoder": true,
    "train_expert_only": true,
    "train_state_proj": true,
    "optimizer_lr": 0.0001,
    "optimizer_betas": [
        0.9,
        0.95
    ],
    "optimizer_eps": 1e-08,
    "optimizer_weight_decay": 1e-10,
    "optimizer_grad_clip_norm": 10,
    "scheduler_warmup_steps": 1000,
    "scheduler_decay_steps": 30000,
    "scheduler_decay_lr": 2.5e-06,
    "vlm_model_name": "HuggingFaceTB/SmolVLM2-500M-Video-Instruct",
    "load_vlm_weights": true,
    "attention_mode": "cross_attn",
    "prefix_length": 0,
    "pad_language_to": "max_length",
    "num_expert_layers": 0,
    "num_vlm_layers": 16,
    "self_attn_every_n_layers": 2,
    "expert_width_multiplier": 0.75
}
 |