{ "type": "cosmos3_edge", "n_obs_steps": 1, "input_features": {}, "output_features": {}, "device": "cuda", "dtype": "float32", "use_amp": false, "use_peft": false, "push_to_hub": false, "repo_id": null, "private": null, "tags": null, "license": null, "pretrained_path": null, "pretrained_revision": null, "chunk_size": 32, "n_action_steps": 32, "max_action_dim": 64, "normalization_mapping": { "VISUAL": "IDENTITY", "STATE": "IDENTITY", "ACTION": "IDENTITY" }, "mot_backbone": { "transformers_version": "5.5.4", "architectures": null, "output_hidden_states": false, "return_dict": true, "dtype": null, "chunk_size_feed_forward": 0, "is_encoder_decoder": false, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "problem_type": null, "text_config": { "architectures": null, "output_hidden_states": false, "return_dict": true, "dtype": null, "chunk_size_feed_forward": 0, "is_encoder_decoder": false, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "problem_type": null, "vocab_size": 131072, "hidden_size": 2048, "intermediate_size": 9216, "num_hidden_layers": 28, "num_attention_heads": 16, "num_key_value_heads": 8, "head_dim": 128, "hidden_act": "relu2", "mlp_bias": false, "attention_bias": false, "attention_dropout": 0.0, "max_position_embeddings": 131072, "initializer_range": 0.02, "rms_norm_eps": 1e-05, "use_cache": true, "rope_parameters": { "mrope_section": [ 24, 20, 20 ], "rope_theta": 100000000, "rope_type": "default" }, "pad_token_id": 0, "joint_attn_implementation": "two_way", "_name_or_path": "", "eos_token_id": 11, "model_type": "nemotron_3_dense_vl_text", "output_attentions": false }, "vision_config": { "architectures": null, "output_hidden_states": false, "return_dict": true, "dtype": null, "chunk_size_feed_forward": 0, "is_encoder_decoder": false, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "problem_type": null, "hidden_size": 1152, "intermediate_size": 4304, "num_hidden_layers": 27, "num_attention_heads": 16, "num_channels": 3, "patch_size": 16, "hidden_act": "gelu_pytorch_tanh", "layer_norm_eps": 1e-06, "attention_dropout": 0.0, "num_patches": 256, "spatial_merge_size": 2, "_name_or_path": "", "model_type": "nemotron_3_dense_vl_vision", "output_attentions": false }, "projector_config": { "architectures": null, "output_hidden_states": false, "return_dict": true, "dtype": null, "chunk_size_feed_forward": 0, "is_encoder_decoder": false, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "problem_type": null, "input_hidden_size": 1152, "merger_intermediate_size": 11520, "out_hidden_size": 2048, "spatial_merge_size": 2, "use_postshuffle_norm": false, "_name_or_path": "", "model_type": "nemotron_3_dense_vl_projector", "output_attentions": false }, "image_token_id": 19, "video_token_id": 18, "vision_start_token_id": 20, "vision_end_token_id": 21, "tie_word_embeddings": false, "_name_or_path": "", "model_type": "nemotron_3_dense_vl", "output_attentions": false }, "tokenizer_name": "nvidia/Cosmos3-Edge", "vae": { "base_dim": 160, "decoder_base_dim": 256, "z_dim": 48, "dim_mult": [ 1, 2, 4, 4 ], "num_res_blocks": 2, "attn_scales": [], "temperal_downsample": [ false, true, true ], "dropout": 0.0, "latents_mean": [ -0.2289, -0.0052, -0.1323, -0.2339, -0.2799, 0.0174, 0.1838, 0.1557, -0.1382, 0.0542, 0.2813, 0.0891, 0.157, -0.0098, 0.0375, -0.1825, -0.2246, -0.1207, -0.0698, 0.5109, 0.2665, -0.2108, -0.2158, 0.2502, -0.2055, -0.0322, 0.1109, 0.1567, -0.0729, 0.0899, -0.2799, -0.123, -0.0313, -0.1649, 0.0117, 0.0723, -0.2839, -0.2083, -0.052, 0.3748, 0.0152, 0.1957, 0.1433, -0.2944, 0.3573, -0.0548, -0.1681, -0.0667 ], "latents_std": [ 0.4765, 1.0364, 0.4514, 1.1677, 0.5313, 0.499, 0.4818, 0.5013, 0.8158, 1.0344, 0.5894, 1.0901, 0.6885, 0.6165, 0.8454, 0.4978, 0.5759, 0.3523, 0.7135, 0.6804, 0.5833, 1.4146, 0.8986, 0.5659, 0.7069, 0.5338, 0.4889, 0.4917, 0.4069, 0.4999, 0.6866, 0.4093, 0.5709, 0.6065, 0.6415, 0.4944, 0.5726, 1.2042, 0.5458, 1.6887, 0.3971, 1.06, 0.3943, 0.5537, 0.5444, 0.4089, 0.7468, 0.7744 ], "is_residual": true, "in_channels": 12, "out_channels": 12, "patch_size": 2, "scale_factor_temporal": 4, "scale_factor_spatial": 16 }, "latent_patch_size": 2, "timestep_scale": 0.001, "timestep_embedding_dim": 256, "num_embodiment_domains": 32, "base_fps": 24.0, "temporal_modality_margin": 15000, "video_temporal_causal": false, "train_gen_stream_only": true, "freeze_vision_encoder": true, "load_action_modules": true, "gradient_checkpointing": false, "compile_model": false, "compile_mode": "default", "attn_implementation": "sdpa", "num_train_timesteps": 1000, "video_time_distribution": "waver", "training_shift": { "256": 3.0, "480": 5.0, "720": 10.0 }, "independent_action_schedule": false, "action_time_distribution": "logitnormal", "action_training_shift": null, "video_loss_weight": 10.0, "action_loss_weight": 10.0, "num_inference_steps": 4, "guidance_scale": 3.0, "guidance_interval": null, "sampling_shift": 5.0, "sampler": "unipc", "save_predicted_video": false, "mode": "wam", "use_state": true, "domain_id": 8, "fps": null, "view_size": null, "view_description": "The top row is from the wrist-mounted camera. The bottom row contains two horizontally concatenated third-person perspective views of the scene from opposite sides, with the robot visible.", "idle_state": true, "action_feature_names": null, "cfg_dropout_rate": 0.1, "optimizer_lr": 8e-05, "optimizer_betas": [ 0.9, 0.99 ], "optimizer_eps": 1e-08, "optimizer_weight_decay": 0.05, "optimizer_grad_clip_norm": 1.0, "optimizer_action_lr_multiplier": 5.0, "scheduler_warmup_steps": 0, "scheduler_decay_steps": 100000 }