| { |
| "allow_patterns_overrides": [ |
| "*/*.safetensors" |
| ], |
| "architectures": [ |
| "Cosmos3ForConditionalGeneration" |
| ], |
| "backbone_type": "cosmos3_multiview", |
| "cosmos3_nano_sim_auto": { |
| "checkpoint_hash": "1c13c34424f1a040f9a7b4a73c469059a4347b50de730e7a7b7bbe8657577b49", |
| "checkpoint_id": "sim_auto_joint_stage3_sfdmd_mads_all@iter_000001800", |
| "checkpoint_iteration": 1800, |
| "schema_version": 1 |
| }, |
| "image_token_id": 151655, |
| "model": { |
| "_recursive_": false, |
| "_target": "omni_mot_causal_model", |
| "config": { |
| "_type": "omni_mot_causal_model_config", |
| "action_gen": false, |
| "action_global_asinh": false, |
| "action_io_projector_type": "domain_aware", |
| "action_metric_gripper": false, |
| "action_schema": "native", |
| "activation_checkpointing": { |
| "_type": "activation_checkpointing_config", |
| "determinism_check": "default", |
| "min_cgroup_memory_free_fraction": 0.1, |
| "mode": "full", |
| "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" |
| ] |
| }, |
| "ar_distilled_sample_type": null, |
| "ar_static_und_cache_max_len": 512, |
| "attention_io_layout": "sequence_sharded", |
| "attention_sink_size": 0, |
| "causal_training_strategy": "teacher_forcing", |
| "clamp_empty_varlen_kv": true, |
| "compile": { |
| "_type": "compile_config", |
| "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": true, |
| "diffusion_expert_config": { |
| "_type": "diffusion_expert_config", |
| "base_fps": 30, |
| "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": 1, |
| "load_weights_from_pretrained": false, |
| "max_vae_latent_side_after_patchify": 52, |
| "num_view_embeddings": 12, |
| "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": { |
| "_type": "ema_config", |
| "enabled": false, |
| "iteration_shift": 0, |
| "rate": 0.1 |
| }, |
| "enable_input_bias": true, |
| "enable_moba": false, |
| "exclude_reasoner_weights_from_checkpoint": false, |
| "fixed_step_sampler_config": { |
| "_type": "fixed_step_sampler_config", |
| "sample_type": "sde", |
| "t_list": [ |
| 1.0, |
| 0.9375, |
| 0.8333333333333334, |
| 0.625 |
| ] |
| }, |
| "flex_attention": { |
| "_type": "causal_flex_attention_config", |
| "backend": "auto", |
| "geometry_position_encoding": "baseline", |
| "mask": { |
| "_type": "causal_flex_attention_mask_config", |
| "attention_scope": "all_views", |
| "control_attends_sensor": false, |
| "cross_view_temporal_window": { |
| "_type": "cross_view_temporal_window_config", |
| "bounds": null, |
| "includes_first_frame": false |
| }, |
| "lidar_attends_captions": true, |
| "radar_attends_captions": true, |
| "same_view_temporal_window": { |
| "_type": "same_view_temporal_window_config", |
| "control_to_control_bounds": null, |
| "control_to_sensor_bounds": null, |
| "sensor_to_control_bounds": null, |
| "sensor_to_sensor_bounds": null |
| } |
| }, |
| "maskless_cross_view_band_keys": "other_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 |
| }, |
| "grad_clip": true, |
| "input_caption_key": "ai_caption", |
| "input_image_key": "images", |
| "input_video_key": "video", |
| "joint_attn_implementation": "multiview", |
| "kv_cache_dtype": null, |
| "kv_cache_inference_size": null, |
| "kv_cache_kernel_impl": "triton", |
| "latent_downsample_factor": 16, |
| "lbl": { |
| "_type": "lbl_config", |
| "coeff_gen": null, |
| "coeff_und": null, |
| "method": "local" |
| }, |
| "lidar_fps": 10.0, |
| "lidar_state_ch": 128, |
| "lidar_tokenizer": { |
| "_target": "lidar_tokenizer_v1_interface", |
| "apply_validity_mask": true, |
| "bucket_name": "bucket", |
| "device": "cuda", |
| "dtype": "float32", |
| "load_checkpoint": true, |
| "network_config": { |
| "base_channels": 128, |
| "bottleneck_3d": true, |
| "bottleneck_3d_causal_time": true, |
| "bottleneck_3d_max_t": 32, |
| "bottleneck_3d_rope": true, |
| "depths": [ |
| 3, |
| 3, |
| 3, |
| 3 |
| ], |
| "dilation": [ |
| 1, |
| 1, |
| 1, |
| 1 |
| ], |
| "formulation": "VAE", |
| "in_channels": 3, |
| "mapping_depth": 2, |
| "mask_as_input": false, |
| "mlp_ratio": 3.0, |
| "num_heads": [ |
| 4, |
| 4, |
| 8, |
| 8 |
| ], |
| "out_channels": 3, |
| "patch_size": [ |
| 2, |
| 2 |
| ], |
| "positional_embedding": "learnable_embedding", |
| "resolution": [ |
| 128, |
| 1808 |
| ], |
| "temporal_downsample": [ |
| false, |
| false, |
| false |
| ], |
| "temporal_upsample": [ |
| false, |
| false, |
| false |
| ], |
| "window_size": [ |
| 5, |
| 45 |
| ], |
| "z_dim": 128 |
| }, |
| "object_store_credential_path_pretrained": null, |
| "range_projection": { |
| "_target": "lidar_range_projection_config", |
| "azimuth_end_degrees": -180.0, |
| "azimuth_endpoint": false, |
| "azimuth_start_degrees": 180.0, |
| "coordinate_system": "x_forward_y_left_z_up", |
| "intensity_encoding": "unit", |
| "invalid_range_m": 0.0, |
| "max_range_m": 100.0, |
| "min_range_m": 5.0, |
| "model_width": 1808, |
| "model_width_transform": "circular_pad", |
| "native_height": 128, |
| "native_width": 3600, |
| "return_selection": "nearest", |
| "semantic_height": 128, |
| "semantic_width": 1800, |
| "sensor": "pandar128", |
| "validity_threshold": 0.5 |
| }, |
| "sample_posterior": false, |
| "spatial_compression": [ |
| 16, |
| 16 |
| ], |
| "spatial_compression_factor": 16, |
| "streaming_chunk_frames": 20, |
| "streaming_context_frames": 21, |
| "temporal_compression_factor": 1, |
| "vae_path": "pretrained/tokenizers/lidar/diffusion_pytorch_model.safetensors" |
| }, |
| "load_vision_tokenizer": true, |
| "lora_alpha": 32, |
| "lora_enabled": false, |
| "lora_rank": 16, |
| "lora_target_modules": "q_proj_moe_gen,k_proj_moe_gen,v_proj_moe_gen,o_proj_moe_gen", |
| "max_action_dim": 32, |
| "max_num_tokens_after_packing": 1400000, |
| "moba_bidirectional_steps": 1, |
| "moba_causal_steps": 1, |
| "multiview_action_conditioning": null, |
| "multiview_attention": { |
| "_type": "flex_attention_config", |
| "backend": "maskless", |
| "geometry_position_encoding": "baseline", |
| "mask": { |
| "_type": "flex_attention_mask_config", |
| "attention_scope": "decomposed", |
| "control_attends_sensor": true, |
| "cross_view_temporal_window": { |
| "_type": "cross_view_temporal_window_config", |
| "bounds": [ |
| -0.4, |
| 0.0 |
| ], |
| "includes_first_frame": false |
| }, |
| "lidar_attends_captions": true, |
| "radar_attends_captions": true, |
| "same_view_temporal_window": { |
| "_type": "same_view_temporal_window_config", |
| "control_to_control_bounds": null, |
| "control_to_sensor_bounds": null, |
| "sensor_to_control_bounds": null, |
| "sensor_to_sensor_bounds": null |
| } |
| }, |
| "maskless_cross_view_band_keys": "other_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, |
| "nvfp4_linears": null, |
| "parallelism": { |
| "_type": "parallelism_config", |
| "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", |
| "radar_fps": null, |
| "radar_state_ch": null, |
| "radar_tokenizer": null, |
| "rectified_flow_inference_config": { |
| "_type": "rectified_flow_inference_config", |
| "num_train_timesteps": 1000, |
| "scheduler_type": "unipc", |
| "shift": 1, |
| "use_dynamic_shifting": false |
| }, |
| "rectified_flow_training_config": { |
| "_type": "rectified_flow_training_config", |
| "action_loss_weight": 10.0, |
| "exclude_fully_conditioned_items": false, |
| "image_loss_scale": null, |
| "independent_action_schedule": false, |
| "independent_sound_schedule": false, |
| "lidar_loss_scale": 200.0, |
| "loss_reduction_mode": "local_item_mean", |
| "loss_scale": 100.0, |
| "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": "uniform", |
| "train_time_weight": "uniform", |
| "use_discrete_rf": false, |
| "use_dynamic_shift": false |
| }, |
| "release_cp_raw_batch_after_preprocessing": false, |
| "resolution": "720", |
| "rolling_kv_cache_chunks": 2, |
| "rolling_kv_sink_chunks": 1, |
| "rolling_media_rope_scale": 1.0, |
| "rolling_media_sink_age_cap_seconds": null, |
| "rolling_media_text_extent": null, |
| "rolling_prompt_context_after": 0, |
| "rolling_prompt_context_before": 0, |
| "rolling_prompt_policy": "segmented", |
| "rolling_static_caption_max_tokens": 1024, |
| "rolling_text_position_mode": "fixed", |
| "rolling_text_sink_tokens": 4, |
| "sigma_diffusion_forcing": 0.02, |
| "sound_dim": null, |
| "sound_gen": false, |
| "sound_latent_fps": 25, |
| "sound_tokenizer": { |
| "_target": "avae_interface", |
| "audio_channels": 2, |
| "avae_config_path": "", |
| "avae_path": "pretrained/tokenizers/audio/avae/avae_48k_noncausal_25hz_64ch.ckpt", |
| "bucket_name": "bucket", |
| "hop_size": 1920, |
| "io_channels": 64, |
| "latent_mean": null, |
| "latent_std": null, |
| "normalization_type": "none", |
| "normalize_latents": true, |
| "object_store_credential_path_pretrained": null, |
| "sample_rate": 48000, |
| "tanh_clamp": 0.995, |
| "tanh_input_scale": 1.5, |
| "tanh_output_scale": 3.5 |
| }, |
| "sr_latent_condition_noise": null, |
| "state_ch": 48, |
| "state_t": 300, |
| "teacher_forcing_detach_clean_kv": false, |
| "teacher_forcing_frames_per_chunk": 3, |
| "teacher_forcing_kv_implementation": "multiview_maskless_kv", |
| "teacher_forcing_replay_policy": { |
| "_type": "teacher_forcing_replay_policy_config", |
| "clean_pass_causality": "chunk", |
| "control_visibility": "causal", |
| "controls_read_strict_past_clean_rgb": true, |
| "decomposed_temporal_window_seconds": 0.4, |
| "deduplicate_cross_view": true, |
| "multiview_attention_scope": "decomposed" |
| }, |
| "teacher_forcing_target_only_no_text_pass2": false, |
| "teacher_forcing_transfer_control_dropout_rate": 0.0, |
| "timestep_embedding_chunk_size": 128000, |
| "tokenizer": { |
| "_target": "wan2pt2_vae_interface", |
| "bucket_name": "bucket", |
| "causal": true, |
| "chunk_duration": 93, |
| "encode_bucket_multiple": null, |
| "encode_chunk_frames": { |
| "256": 68, |
| "480": 24, |
| "720": 8 |
| }, |
| "encode_exact_durations": [ |
| 17, |
| 61, |
| 73 |
| ], |
| "keep_decoder_cache": false, |
| "object_store_credential_path_pretrained": null, |
| "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": true, |
| "vision_gen": true, |
| "vlm_config": { |
| "_type": "vlm_config", |
| "layer_module": null, |
| "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" |
| }, |
| "qk_norm_for_text": true |
| } |
| }, |
| "model_name": "nvidia/Cosmos3-Nano-Reasoner", |
| "pretrained_weights": { |
| "_type": "pretrained_weights_config", |
| "backbone_path": "", |
| "checkpoint_format": null, |
| "credentials_path": "", |
| "enable_gcs_patch_in_boto3": false, |
| "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", |
| "per_view_caption_task": "av_joint_camera_lidar_transfer", |
| "per_view_captions": true, |
| "text_config": { |
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "bos_token_id": 151643, |
| "dtype": "bfloat16", |
| "eos_token_id": 151645, |
| "head_dim": 128, |
| "hidden_act": "silu", |
| "hidden_size": 4096, |
| "initializer_range": 0.02, |
| "intermediate_size": 12288, |
| "max_position_embeddings": 262144, |
| "model_type": "qwen3_vl_text", |
| "num_attention_heads": 32, |
| "num_hidden_layers": 36, |
| "num_key_value_heads": 8, |
| "rms_norm_eps": 1e-06, |
| "rope_scaling": { |
| "mrope_interleaved": true, |
| "mrope_section": [ |
| 24, |
| 20, |
| 20 |
| ], |
| "rope_type": "default" |
| }, |
| "rope_theta": 5000000, |
| "use_cache": true, |
| "vocab_size": 151936 |
| }, |
| "tie_word_embeddings": false, |
| "transformers_version": "4.57.0.dev0", |
| "video_token_id": 151656, |
| "vision_config": { |
| "deepstack_visual_indexes": [ |
| 8, |
| 16, |
| 24 |
| ], |
| "depth": 27, |
| "hidden_act": "gelu_pytorch_tanh", |
| "hidden_size": 1152, |
| "in_channels": 3, |
| "initializer_range": 0.02, |
| "intermediate_size": 4304, |
| "model_type": "qwen3_vl", |
| "num_heads": 16, |
| "num_position_embeddings": 2304, |
| "out_hidden_size": 4096, |
| "patch_size": 16, |
| "spatial_merge_size": 2, |
| "temporal_patch_size": 2 |
| }, |
| "vision_end_token_id": 151653, |
| "vision_start_token_id": 151652 |
| } |
|
|
