smolvla / config.json
gribok201's picture
Upload folder using huggingface_hub
2f14779 verified
{
"architectures": [
"LerobotSmolVLAWrappedModel"
],
"auto_map": {
"AutoModel": "modeling_lerobot_policy.LerobotSmolVLAWrappedModel"
},
"adapt_to_pi_aloha": false,
"add_image_special_tokens": false,
"attention_mode": "cross_attn",
"chunk_size": 50,
"device": "cuda",
"empty_cameras": 0,
"expert_width_multiplier": 0.75,
"freeze_vision_encoder": true,
"input_features": {
"observation.image": {
"shape": [
3,
256,
256
],
"type": "VISUAL"
},
"observation.image2": {
"shape": [
3,
256,
256
],
"type": "VISUAL"
},
"observation.image3": {
"shape": [
3,
256,
256
],
"type": "VISUAL"
},
"observation.state": {
"shape": [
6
],
"type": "STATE"
}
},
"load_vlm_weights": true,
"max_action_dim": 32,
"max_period": 4,
"max_state_dim": 32,
"min_period": 0.004,
"n_action_steps": 50,
"n_obs_steps": 1,
"normalization_mapping": {
"ACTION": "MEAN_STD",
"STATE": "MEAN_STD",
"VISUAL": "IDENTITY"
},
"num_expert_layers": 0,
"num_steps": 10,
"num_vlm_layers": 16,
"optimizer_betas": [
0.9,
0.95
],
"optimizer_eps": "1e-08",
"optimizer_grad_clip_norm": 10,
"optimizer_lr": 0.0001,
"optimizer_weight_decay": "1e-10",
"output_features": {
"action": {
"shape": [
6
],
"type": "ACTION"
}
},
"pad_language_to": "max_length",
"prefix_length": 0,
"resize_imgs_with_padding": [
512,
512
],
"scheduler_decay_lr": 2.5e-06,
"scheduler_decay_steps": 30000,
"scheduler_warmup_steps": 1000,
"self_attn_every_n_layers": 2,
"tokenizer_max_length": 48,
"train_expert_only": true,
"train_state_proj": true,
"type": "smolvla",
"use_amp": false,
"use_cache": true,
"use_delta_joint_actions_aloha": false,
"vlm_model_name": "HuggingFaceTB/SmolVLM2-500M-Video-Instruct"
}