| { | |
| "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.images.front": { | |
| "type": "VISUAL", | |
| "shape": [ | |
| 3, | |
| 480, | |
| 640 | |
| ] | |
| } | |
| }, | |
| "output_features": { | |
| "action": { | |
| "type": "ACTION", | |
| "shape": [ | |
| 6 | |
| ] | |
| } | |
| }, | |
| "device": "cuda", | |
| "use_amp": false, | |
| "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": 10.0, | |
| "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, | |
| "add_image_special_tokens": false, | |
| "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, | |
| "min_period": 0.004, | |
| "max_period": 4.0 | |
| } |