| { | |
| "type": "pi", | |
| "n_obs_steps": 1, | |
| "normalization_mapping": { | |
| "VISUAL": "IDENTITY", | |
| "STATE": "MEAN_STD", | |
| "ACTION": "MEAN_STD" | |
| }, | |
| "input_features": { | |
| "observation.images.image": { | |
| "type": "VISUAL", | |
| "shape": [ | |
| 3, | |
| 256, | |
| 320 | |
| ] | |
| }, | |
| "observation.state": { | |
| "type": "STATE", | |
| "shape": [ | |
| 8 | |
| ] | |
| } | |
| }, | |
| "output_features": { | |
| "action": { | |
| "type": "ACTION", | |
| "shape": [ | |
| 7 | |
| ] | |
| } | |
| }, | |
| "device": "cpu", | |
| "use_amp": false, | |
| "chunk_size": 4, | |
| "n_action_steps": 4, | |
| "max_state_dim": 32, | |
| "max_action_dim": 32, | |
| "resize_imgs_with_padding": [ | |
| 224, | |
| 224 | |
| ], | |
| "empty_cameras": 0, | |
| "adapt_to_pi_aloha": false, | |
| "use_delta_joint_actions_aloha": false, | |
| "tokenizer_max_length": 48, | |
| "proj_width": 1024, | |
| "num_steps": 10, | |
| "use_cache": true, | |
| "attention_implementation": "eager", | |
| "freeze_vision_encoder": true, | |
| "train_expert_only": false, | |
| "train_state_proj": true, | |
| "optimizer_lr": 5e-05, | |
| "optimizer_betas": [ | |
| 0.9, | |
| 0.95 | |
| ], | |
| "optimizer_eps": 1e-08, | |
| "optimizer_weight_decay": 1e-10, | |
| "scheduler_warmup_steps": 1000, | |
| "scheduler_decay_steps": 3200000, | |
| "scheduler_decay_lr": 2.5e-06, | |
| "paligemma_config": { | |
| "bos_token_id": 2, | |
| "eos_token_id": 1, | |
| "hidden_size": 2048, | |
| "ignore_index": -100, | |
| "image_token_index": 257152, | |
| "model_type": "paligemma", | |
| "pad_token_id": 0, | |
| "projection_dim": 2048, | |
| "text_config": { | |
| "hidden_activation": "gelu_pytorch_tanh", | |
| "hidden_size": 2048, | |
| "intermediate_size": 16384, | |
| "model_type": "gemma", | |
| "num_attention_heads": 8, | |
| "num_hidden_layers": 18, | |
| "num_image_tokens": 256, | |
| "num_key_value_heads": 1, | |
| "torch_dtype": "float32", | |
| "vocab_size": 257152 | |
| }, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.48.1", | |
| "vision_config": { | |
| "hidden_size": 1152, | |
| "intermediate_size": 4304, | |
| "model_type": "siglip_vision_model", | |
| "num_attention_heads": 16, | |
| "num_hidden_layers": 27, | |
| "num_image_tokens": 256, | |
| "patch_size": 14, | |
| "projection_dim": 2048, | |
| "projector_hidden_act": "gelu_fast", | |
| "vision_use_head": false | |
| }, | |
| "vocab_size": 257152 | |
| }, | |
| "gemma_expert_config": { | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 2, | |
| "eos_token_id": 1, | |
| "head_dim": 256, | |
| "hidden_act": "gelu_pytorch_tanh", | |
| "hidden_activation": "gelu_pytorch_tanh", | |
| "hidden_size": 1024, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 4096, | |
| "max_position_embeddings": 8192, | |
| "model_type": "gemma", | |
| "num_attention_heads": 8, | |
| "num_hidden_layers": 18, | |
| "num_key_value_heads": 1, | |
| "pad_token_id": 0, | |
| "rms_norm_eps": 1e-06, | |
| "rope_theta": 10000.0, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.48.1", | |
| "use_cache": true, | |
| "vocab_size": 257152 | |
| } | |
| } |