{ "architectures": [ "Cosmos3OmniModel" ], "auto_map": { "AutoConfig": "cosmos3.model.Cosmos3OmniConfig", "AutoModel": "cosmos3.model.Cosmos3OmniModel" }, "dtype": "bfloat16", "model": { "_recursive_": false, "_target": "omni_mot_model", "config": { "_type": "omni_mot_model_config", "action_gen": true, "action_global_asinh": false, "action_io_projector_type": "domain_aware", "action_metric_gripper": false, "action_schema": "native", "activation_checkpointing": { "determinism_check": "default", "min_cgroup_memory_free_fraction": 0.1, "mode": "selective", "offload_to_cpu": false, "preserve_rng_state": true, "save_only_marked_ops": false, "save_ops_regex": [ "fmha_forward", "_flash_attn_varlen_forward", "_flash_attn_forward", "fmha_fwd" ] }, "attention_io_layout": "sequence_sharded", "causal_training_strategy": "none", "compile": { "ar_post_saturation_mode": "default", "compile_dynamic": true, "compiled_region": "language", "coordinate_descent_tuning": false, "cuda_graph_scope": "block", "enabled": false, "mark_unbacked": false, "max_autotune_pointwise": false, "use_cuda_graphs": false }, "correct_cp_gradients": false, "diffusion_expert_config": { "base_fps": 24, "enable_action_modality_embedding": true, "enable_fps_modulation": true, "enable_media_modality_embedding": false, "enable_sound_modality_embedding": true, "enable_vision_modality_embeddings": false, "lidar_patch_spatial_hw": null, "load_weights_from_pretrained": false, "max_vae_latent_side_after_patchify": 20, "num_view_embeddings": 0, "patch_spatial": 2, "radar_patch_spatial_hw": null, "sound_base_temporal_compression_factor": null, "timestep_range": 1.0, "unified_3d_mrope_reset_spatial_ids": true, "unified_3d_mrope_temporal_modality_margin": 15000, "vision_temporal_position_mode": "latent_index" }, "ema": { "enabled": false, "iteration_shift": 0, "rate": 0.1 }, "enable_input_bias": true, "exclude_reasoner_weights_from_checkpoint": false, "fixed_step_sampler_config": null, "input_caption_key": "ai_caption", "input_image_key": "images", "input_video_key": "video", "joint_attn_implementation": "two_way", "latent_downsample_factor": 16, "lbl": { "coeff_gen": null, "coeff_und": null, "method": "local" }, "lidar_fps": null, "lidar_state_ch": null, "lidar_tokenizer": null, "load_vision_tokenizer": true, "lora_alpha": 64, "lora_enabled": true, "lora_rank": 32, "lora_target_modules": "q_proj_moe_gen,k_proj_moe_gen,v_proj_moe_gen,o_proj_moe_gen,mlp_moe_gen.gate_proj,mlp_moe_gen.up_proj,mlp_moe_gen.down_proj", "max_action_dim": 64, "max_num_tokens_after_packing": 45056, "multiview_action_conditioning": null, "multiview_attention": { "backend": "auto", "deduplicate_cross_view": false, "geometry_position_encoding": "baseline", "mask": { "attention_scope": "all_views", "control_attends_sensor": false, "control_to_control_window": null, "control_to_sensor_window": null, "decomposed_temporal_window_includes_first_frame": false, "decomposed_temporal_window_seconds": null, "lidar_attends_captions": true, "radar_attends_captions": true, "sensor_to_control_window": null, "sensor_to_sensor_window": null }, "maskless_cross_view_band_keys": "all_views", "maskless_cross_view_band_radius": 0, "maskless_cross_view_include_frame_zero": false, "prope_intrinsics": false, "rigrope_canonical_frame": false, "rigrope_channels": "all", "rigrope_head_fraction": 1.0, "rigrope_include_time": false, "rigrope_max_freq_exponent": 3.0, "rigrope_min_freq_exponent": 0.0, "rigrope_missing_geometry": "error", "rigrope_moment_normalization": "fixed", "rigrope_moment_scale_floor_m": 0.05, "rigrope_moment_scale_m": 25.0, "rigrope_pose_world_frame": "scene", "rigrope_time_scale_s": 1.0 }, "natten_parameter_list": null, "net": null, "num_embodiment_domains": 32, "parallelism": { "cfg_parallel_shard_degree": 1, "context_parallel_shard_degree": 1, "data_parallel_replicate_degree": 1, "data_parallel_shard_degree": -1, "enable_inference_mode": false, "fsdp_cpu_offload": false, "fsdp_master_dtype": "float32", "fsdp_reduce_dtype": "bfloat16", "vae_load_balance_group_size": 1 }, "precision": "bfloat16", "quantization": { "exclude_regex": [], "fp8_granularity": "per_row", "include_regex": [], "method": null, "mixed_precision_first_steps": 0, "mixed_precision_last_steps": 0, "mixed_precision_reasoner_policy": "high_precision", "mixed_precision_w8a16_cache": "none", "modelopt_fp8_checkpoint_path": null, "modelopt_fp8_target_fqns": [] }, "radar_fps": null, "radar_state_ch": null, "radar_tokenizer": null, "rectified_flow_inference_config": { "num_train_timesteps": 1000, "scheduler_type": "unipc", "shift": 1, "use_dynamic_shifting": false }, "rectified_flow_training_config": { "action_loss_weight": 10.0, "exclude_fully_conditioned_items": null, "image_loss_scale": 1.0, "independent_action_schedule": false, "independent_sound_schedule": false, "lidar_loss_scale": null, "loss_reduction_mode": "local_item_mean", "loss_scale": 1.0, "normalize_loss_by_active": false, "radar_loss_scale": null, "shift": { "256": 3, "480": 5, "720": 10 }, "shift_action": null, "shift_image": null, "shift_lidar": null, "shift_sound": null, "sound_loss_scale": null, "train_time_action_distribution": "logitnormal", "train_time_image_distribution": "logitnormal", "train_time_sound_distribution": "logitnormal", "train_time_video_distribution": "waver", "train_time_weight": "uniform", "use_discrete_rf": false, "use_dynamic_shift": false }, "release_cp_raw_batch_after_preprocessing": false, "resolution": "720", "sound_dim": null, "sound_gen": false, "sound_latent_fps": 25, "sound_tokenizer": null, "sr_latent_condition_noise": null, "state_ch": 48, "state_t": 300, "tokenizer": { "_target": "wan2pt2_vae_interface", "bucket_name": "", "causal": true, "chunk_duration": 93, "encode_bucket_multiple": null, "encode_chunk_frames": { "256": 68, "480": 24, "720": 8, "768": 8 }, "encode_exact_durations": null, "keep_decoder_cache": false, "object_store_credential_path_pretrained": "", "spatial_compression_factor": 16, "temporal_compression_factor": 4, "temporal_window": null, "use_streaming_encode": false, "vae_path": "pretrained/tokenizers/video/wan2pt2/Wan2.2_VAE.pth" }, "video_temporal_causal": false, "vision_gen": true, "vlm_config": { "layer_module": "Qwen2MoTDecoderLayer", "model_instance": { "_target": "qwen3_vl_text_for_causal_lm", "config": { "_target": "create_vlm_config", "base_config": { "_target": "qwen3_vl_mot_config_from_json_file", "json_file": "cosmos3://vfm/models/vlm/qwen3_vl/configs/Qwen3-VL-8B-Instruct.json" }, "freeze_und": false, "include_visual": false, "layer_module": "MoTDecoderLayer", "qk_norm_for_text": true, "tie_word_embeddings": true } }, "model_name": "Qwen/Qwen3-VL-8B-Instruct", "pretrained_weights": { "backbone_path": "s3://bucket0/cosmos3/pretrained/huggingface/Qwen/Qwen3-VL-8B-Instruct/", "checkpoint_format": null, "credentials_path": "", "enable_gcs_patch_in_boto3": true, "enabled": false }, "qk_norm": false, "safetensors_path": "", "tie_word_embeddings": false, "tokenizer": { "_target": "create_qwen2_tokenizer_with_download", "config_variant": "hf", "pretrained_model_name": "Qwen/Qwen3-VL-8B-Instruct" }, "use_system_prompt": false } } }, "model_type": "cosmos3_omni", "transformers_version": "4.57.6" }