update_config

checkpoint.json

@@ -12,7 +12,7 @@
     "chunk_size": 2,
     "conditioning": {
       "action_tokens_per_frame": 4,
-      "contract_sha256": "bb69c3678ea0a17e0685933606b44d5b9fe946d1f657fa945d7b4dce321723df",
+      "contract_sha256": "118860602b7d1017ca6333ad1cfe4324d500f526b45efc478429d20ffd062492",
       "default_embodiment": "agibotworld",
       "embodiments": {
         "abc_yam": {
@@ -111,7 +111,7 @@
           "artifact_path": "cosmos3_nano_sim_bimanual_action_sources/ae695e2c643a5626b3c3564f00705aa3a83ab0da7640549c7340db71172594b0.json",
           "path": "projects/cosmos3/cosmos3/datasets/action/normalizers/global_asinh_v1_backward_anchored_gripper_metric.json",
           "pose_convention_authority": "resolved_canonical_lance_training_config",
-          "repository_revision": "970970f3a3024563973d4114e7c60cfda62c3af0",
+          "repository_revision": "2076f215a33b4fe164bf2faca4c01a28cda71f79",
           "sha256": "ae695e2c643a5626b3c3564f00705aa3a83ab0da7640549c7340db71172594b0"
         }
       },
@@ -195,6 +195,15 @@
             "target": "projects.cosmos3.cosmos3.datasets.action.canonical_lance_action_datasets.CanonicalLanceYAMDataset",
             "translation_scale": 1.0
           },
+          {
+            "camera_mask": false,
+            "embodiment": "hand_pose",
+            "name": "mecka_all",
+            "pose_convention": "backward_chunk_anchored_16f",
+            "rotation_format": "rot6d",
+            "target": "projects.cosmos3.cosmos3.datasets.action.canonical_lance_action_datasets.CanonicalLanceMeckaDataset",
+            "translation_scale": 1.0
+          },
           {
             "camera_mask": true,
             "embodiment": "behavior1k_lerobot",
@@ -237,12 +246,12 @@
       "temporal_modality_margin": 15000
     },
     "schema_version": 1,
-    "sink_frames": 0,
+    "sink_frames": 8,
     "temporal_compression_factor": 4,
-    "text_cache_max_len": 512,
+    "text_cache_max_len": 1024,
     "vae_spatial_compression_factor": 16,
     "video_temporal_causal": true,
-    "window_frames": null
+    "window_frames": 64
   },
   "source_weights": "ema",
   "student_only": true

config.json

@@ -25,14 +25,14 @@
     },
     "latent_patch_size": 2,
     "schema_version": 1,
-    "sink_frames": 0,
+    "sink_frames": 8,
     "temporal_compression_factor": 4,
     "temporal_modality_margin": 15000,
     "text_cache_max_len": 1024,
     "unified_3d_mrope_reset_spatial_ids": true,
     "vae_spatial_compression_factor": 16,
     "video_temporal_causal": true,
-    "window_frames": null
+    "window_frames": 64
   },
   "image_token_id": 151655,
   "model": {
@@ -61,9 +61,9 @@
         ]
       },
       "ar_distilled_sample_type": null,
-      "ar_static_und_cache_max_len": 512,
+      "ar_static_und_cache_max_len": 1024,
       "attention_io_layout": "sequence_sharded",
-      "attention_sink_size": 0,
+      "attention_sink_size": 8,
       "causal_training_strategy": "none",
       "clamp_empty_varlen_kv": true,
       "compile": {
@@ -121,22 +121,29 @@
       "flex_attention": {
         "_type": "causal_flex_attention_config",
         "backend": "auto",
-        "deduplicate_cross_view": false,
         "geometry_position_encoding": "baseline",
         "mask": {
           "_type": "causal_flex_attention_mask_config",
           "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,
+          "cross_view_temporal_window": {
+            "_type": "cross_view_temporal_window_config",
+            "bounds": null,
+            "includes_first_frame": false
+          },
           "lidar_attends_captions": true,
           "radar_attends_captions": true,
-          "sensor_to_control_window": null,
-          "sensor_to_sensor_window": null
+          "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": "all_views",
+        "maskless_cross_view_action_attends_action": false,
+        "maskless_cross_view_attends_action": false,
+        "maskless_cross_view_band_keys": "other_views",
         "maskless_cross_view_band_radius": 0,
         "maskless_cross_view_include_frame_zero": false,
         "prope_intrinsics": false,
@@ -159,7 +166,7 @@
       "input_video_key": "video",
       "joint_attn_implementation": "three_way",
       "kv_cache_dtype": null,
-      "kv_cache_inference_size": null,
+      "kv_cache_inference_size": 64,
       "kv_cache_kernel_impl": "triton",
       "latent_downsample_factor": 16,
       "lbl": {
@@ -184,22 +191,29 @@
       "multiview_attention": {
         "_type": "flex_attention_config",
         "backend": "auto",
-        "deduplicate_cross_view": false,
         "geometry_position_encoding": "baseline",
         "mask": {
           "_type": "flex_attention_mask_config",
           "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,
+          "cross_view_temporal_window": {
+            "_type": "cross_view_temporal_window_config",
+            "bounds": null,
+            "includes_first_frame": false
+          },
           "lidar_attends_captions": true,
           "radar_attends_captions": true,
-          "sensor_to_control_window": null,
-          "sensor_to_sensor_window": null
+          "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": "all_views",
+        "maskless_cross_view_action_attends_action": false,
+        "maskless_cross_view_attends_action": false,
+        "maskless_cross_view_band_keys": "other_views",
         "maskless_cross_view_band_radius": 0,
         "maskless_cross_view_include_frame_zero": false,
         "prope_intrinsics": false,
@@ -282,7 +296,7 @@
       "rolling_prompt_context_after": 0,
       "rolling_prompt_context_before": 0,
       "rolling_prompt_policy": null,
-      "rolling_static_caption_max_tokens": 576,
+      "rolling_static_caption_max_tokens": 1024,
       "rolling_text_position_mode": "fixed",
       "rolling_text_sink_tokens": 4,
       "sigma_diffusion_forcing": 0.02,

cosmos3_nano_sim_bimanual_action_sources/action_schema.json

@@ -1,6 +1,6 @@
 {
   "action_tokens_per_frame": 4,
-  "contract_sha256": "bb69c3678ea0a17e0685933606b44d5b9fe946d1f657fa945d7b4dce321723df",
+  "contract_sha256": "118860602b7d1017ca6333ad1cfe4324d500f526b45efc478429d20ffd062492",
   "default_embodiment": "agibotworld",
   "embodiments": {
     "abc_yam": {
@@ -98,7 +98,7 @@
       "artifact_path": "cosmos3_nano_sim_bimanual_action_sources/ae695e2c643a5626b3c3564f00705aa3a83ab0da7640549c7340db71172594b0.json",
       "path": "projects/cosmos3/cosmos3/datasets/action/normalizers/global_asinh_v1_backward_anchored_gripper_metric.json",
       "pose_convention_authority": "resolved_canonical_lance_training_config",
-      "repository_revision": "970970f3a3024563973d4114e7c60cfda62c3af0",
+      "repository_revision": "2076f215a33b4fe164bf2faca4c01a28cda71f79",
       "sha256": "ae695e2c643a5626b3c3564f00705aa3a83ab0da7640549c7340db71172594b0"
     }
   },
@@ -182,6 +182,15 @@
         "target": "projects.cosmos3.cosmos3.datasets.action.canonical_lance_action_datasets.CanonicalLanceYAMDataset",
         "translation_scale": 1.0
       },
+      {
+        "camera_mask": false,
+        "embodiment": "hand_pose",
+        "name": "mecka_all",
+        "pose_convention": "backward_chunk_anchored_16f",
+        "rotation_format": "rot6d",
+        "target": "projects.cosmos3.cosmos3.datasets.action.canonical_lance_action_datasets.CanonicalLanceMeckaDataset",
+        "translation_scale": 1.0
+      },
       {
         "camera_mask": true,
         "embodiment": "behavior1k_lerobot",

cosmos3_nano_sim_bimanual_action_sources/resolved_action_config.json

@@ -72,6 +72,15 @@
       "target": "projects.cosmos3.cosmos3.datasets.action.canonical_lance_action_datasets.CanonicalLanceYAMDataset",
       "translation_scale": 1.0
     },
+    {
+      "camera_mask": false,
+      "embodiment": "hand_pose",
+      "name": "mecka_all",
+      "pose_convention": "backward_chunk_anchored_16f",
+      "rotation_format": "rot6d",
+      "target": "projects.cosmos3.cosmos3.datasets.action.canonical_lance_action_datasets.CanonicalLanceMeckaDataset",
+      "translation_scale": 1.0
+    },
     {
       "camera_mask": true,
       "embodiment": "behavior1k_lerobot",

cosmos3_nano_sim_bimanual_artifact.json

@@ -5370,10 +5370,10 @@
     }
   },
   "files": {
-    "cosmos3_nano_sim_bimanual_action_sources/action_schema.json": "886ac3e20c452b5c866a03ab522ab3417b42cc9de05c1cbff4c9cd6e89d4c0ea",
+    "cosmos3_nano_sim_bimanual_action_sources/action_schema.json": "0cc23fe344b611c7be1e5cf659250c339963c63d789495810f9afdc137bd2a59",
     "cosmos3_nano_sim_bimanual_action_sources/ae695e2c643a5626b3c3564f00705aa3a83ab0da7640549c7340db71172594b0.json": "ae695e2c643a5626b3c3564f00705aa3a83ab0da7640549c7340db71172594b0",
     "cosmos3_nano_sim_bimanual_action_sources/cosmos3_nano_sim_bimanual_action_schema.schema.json": "09000a99ffe41434ad0212e23e23bf9a35cb6542f8f3e51e114250d382be86ad",
-    "cosmos3_nano_sim_bimanual_action_sources/resolved_action_config.json": "b59669bcb1caa34905f3dd79a1a7bd5436e7d13d3adc57d3f5eec6983ceb22a6",
+    "cosmos3_nano_sim_bimanual_action_sources/resolved_action_config.json": "7d1e9e5463f33aab70fda2bca70d8f26988d67a1b427111303bcd0c1f06bf85c",
     "diffusion_pytorch_model-00001-of-00006.safetensors": "e58d7e3b6a8c0e19afdf022ab344c185758beca392c3dbc11d14593aab9cb872",
     "diffusion_pytorch_model-00002-of-00006.safetensors": "3b947ed6053667352c22e559115b5a38afe36004dc227a2e5b3bc42967378643",
     "diffusion_pytorch_model-00003-of-00006.safetensors": "135a906487336252d32f110c92e75ab498f31488b1a4871576d470880edbfbc6",
@@ -5393,7 +5393,7 @@
     "chunk_size": 2,
     "conditioning": {
       "action_tokens_per_frame": 4,
-      "contract_sha256": "bb69c3678ea0a17e0685933606b44d5b9fe946d1f657fa945d7b4dce321723df",
+      "contract_sha256": "118860602b7d1017ca6333ad1cfe4324d500f526b45efc478429d20ffd062492",
       "default_embodiment": "agibotworld",
       "embodiments": {
         "abc_yam": {
@@ -5492,7 +5492,7 @@
           "artifact_path": "cosmos3_nano_sim_bimanual_action_sources/ae695e2c643a5626b3c3564f00705aa3a83ab0da7640549c7340db71172594b0.json",
           "path": "projects/cosmos3/cosmos3/datasets/action/normalizers/global_asinh_v1_backward_anchored_gripper_metric.json",
           "pose_convention_authority": "resolved_canonical_lance_training_config",
-          "repository_revision": "970970f3a3024563973d4114e7c60cfda62c3af0",
+          "repository_revision": "2076f215a33b4fe164bf2faca4c01a28cda71f79",
           "sha256": "ae695e2c643a5626b3c3564f00705aa3a83ab0da7640549c7340db71172594b0"
         }
       },
@@ -5576,6 +5576,15 @@
             "target": "projects.cosmos3.cosmos3.datasets.action.canonical_lance_action_datasets.CanonicalLanceYAMDataset",
             "translation_scale": 1.0
           },
+          {
+            "camera_mask": false,
+            "embodiment": "hand_pose",
+            "name": "mecka_all",
+            "pose_convention": "backward_chunk_anchored_16f",
+            "rotation_format": "rot6d",
+            "target": "projects.cosmos3.cosmos3.datasets.action.canonical_lance_action_datasets.CanonicalLanceMeckaDataset",
+            "translation_scale": 1.0
+          },
           {
             "camera_mask": true,
             "embodiment": "behavior1k_lerobot",
@@ -5618,14 +5627,14 @@
       "temporal_modality_margin": 15000
     },
     "schema_version": 1,
-    "sink_frames": 0,
+    "sink_frames": 8,
     "temporal_compression_factor": 4,
-    "text_cache_max_len": 512,
+    "text_cache_max_len": 1024,
     "vae_spatial_compression_factor": 16,
     "video_temporal_causal": true,
-    "window_frames": null
+    "window_frames": 64
   },
-  "manifest_sha256": "12a54e6f7252db57fec46552eb60624880a544f6ae9fa77aa6d5c39849950c81",
+  "manifest_sha256": "5314c68fcb654570385b5419f98fe6240370cea8da69de0a3a79c7764d003d8a",
   "tensor_inventory": {
     "action_modality_embed": {
       "dtype": "BF16",

cosmos_dreams_action_sources/4d38b6321a92741c93e8cf1e96cba18979399ddb5c037708d3aaeffd666faa10.json

@@ -1,41 +0,0 @@
-{
-  "metadata": {
-    "embodiment_type":    "agibot",
-    "pose_convention":    "backward_framewise",
-    "rotation_format":    "rot6d",
-    "action_dim":         29,
-    "skip_rotation_dims": [3, 4, 5, 6, 7, 8, 12, 13, 14, 15, 16, 17, 22, 23, 24, 25, 26, 27],
-    "chunk_length":       16,
-    "sample_stride":      16,
-    "dataset_name":       "agibot_shared_gripper_beta",
-    "dataset_class":      "AgibotGEARGripperDataset+AgibotGEARGripperExtDataset+AgiBotWorldBetaDataset",
-    "dataset_root":       "AgiBotWorld-GEAR + AgiBotWorld-Beta",
-    "split":              "train",
-    "num_samples_stats":  200000,
-    "reservoir_size":     200000,
-    "max_samples":        200000,
-    "sampling_seed":      42,
-    "dataset_lengths":    {
-      "agibot_gear_gripper": 10723406,
-      "agibot_gear_gripper_ext": 209875,
-      "agibotworld_beta": 16688991
-    },
-    "normalizer_note":    "Shared AgiBot 29D FK-pose normalizer for GEAR gripper/ext and AgiBotWorld-Beta. Intended for action_normalization=asinh_rot to compress valid heavy-tailed base motion without clamping."
-  },
-  "global": {
-    "mean": [ 0.000007, -0.000028,  0.000017,  0.000000,  0.000000,  0.000000,  0.000000,  0.000000,  0.000000,  0.000054,  0.000055, -0.000004,  0.000000,  0.000000,  0.000000,  0.000000,  0.000000,  0.000000,  0.461416, -0.000065,  0.000066,  0.000026,  0.000000,  0.000000,  0.000000,  0.000000,  0.000000,  0.000000,  0.511525],
-    "std":  [ 0.001146,  0.003775,  0.006236,  1.000000,  1.000000,  1.000000,  1.000000,  1.000000,  1.000000,  0.005170,  0.005957,  0.005775,  1.000000,  1.000000,  1.000000,  1.000000,  1.000000,  1.000000,  0.365715,  0.004577,  0.006320,  0.004809,  1.000000,  1.000000,  1.000000,  1.000000,  1.000000,  1.000000,  0.368419],
-    "min":  [-0.332076, -0.461419, -1.287811, -1.000000, -1.000000, -1.000000, -1.000000, -1.000000, -1.000000, -1.181742, -1.008569, -0.964748, -1.000000, -1.000000, -1.000000, -1.000000, -1.000000, -1.000000,  0.000000, -1.086141, -1.194795, -0.704462, -1.000000, -1.000000, -1.000000, -1.000000, -1.000000, -1.000000,  0.000000],
-    "max":  [ 0.332075,  0.461429,  1.287816,  1.000000,  1.000000,  1.000000,  1.000000,  1.000000,  1.000000,  1.181742,  1.008569,  0.968047,  1.000000,  1.000000,  1.000000,  1.000000,  1.000000,  1.000000,  1.000000,  1.077497,  1.194157,  0.696745,  1.000000,  1.000000,  1.000000,  1.000000,  1.000000,  1.000000,  1.000000],
-    "q01":  [-0.000474, -0.004285, -0.006603, -1.000000, -1.000000, -1.000000, -1.000000, -1.000000, -1.000000, -0.011330, -0.012649, -0.014966, -1.000000, -1.000000, -1.000000, -1.000000, -1.000000, -1.000000,  0.000000, -0.010683, -0.011185, -0.012754, -1.000000, -1.000000, -1.000000, -1.000000, -1.000000, -1.000000,  0.000000],
-    "q99":  [ 0.000472,  0.003180,  0.007315,  1.000000,  1.000000,  1.000000,  1.000000,  1.000000,  1.000000,  0.011657,  0.012629,  0.013074,  1.000000,  1.000000,  1.000000,  1.000000,  1.000000,  1.000000,  1.000000,  0.010122,  0.011385,  0.011604,  1.000000,  1.000000,  1.000000,  1.000000,  1.000000,  1.000000,  1.000000]
-  },
-  "global_raw": {
-    "mean": [ 0.000007, -0.000028,  0.000017,  0.999997,  0.000012, -0.000011, -0.000013,  0.999992,  0.000013,  0.000054,  0.000055, -0.000004,  0.999755,  0.000162, -0.000206, -0.000163,  0.999770, -0.000068,  0.461416, -0.000065,  0.000066,  0.000026,  0.999821, -0.000156,  0.000218,  0.000156,  0.999840, -0.000065,  0.511525],
-    "std":  [ 0.001146,  0.003775,  0.006236,  0.000050,  0.001322,  0.001990,  0.001321,  0.000091,  0.003722,  0.005170,  0.005957,  0.005775,  0.001184,  0.016934,  0.014178,  0.016919,  0.001112,  0.013136,  0.365715,  0.004577,  0.006320,  0.004809,  0.001140,  0.014271,  0.012406,  0.014263,  0.000987,  0.010745,  0.368419],
-    "min":  [-0.332076, -0.461419, -1.287811,  0.992475, -0.047897, -0.115986, -0.048200,  0.986519, -0.163639, -1.181742, -1.008569, -0.964748,  0.834839, -0.535909, -0.508249, -0.417918,  0.835656, -0.360748,  0.000000, -1.086141, -1.194795, -0.704462,  0.885655, -0.422226, -0.392999, -0.404670,  0.847586, -0.267267,  0.000000],
-    "max":  [ 0.332075,  0.461429,  1.287816,  1.000000,  0.048245,  0.111197,  0.047794,  1.000000,  0.130982,  1.181742,  1.008569,  0.968047,  1.000000,  0.413419,  0.506131,  0.545759,  1.000000,  0.405109,  1.000000,  1.077497,  1.194157,  0.696745,  1.000000,  0.405554,  0.460652,  0.428101,  1.000000,  0.423156,  1.000000],
-    "q01":  [-0.000474, -0.004285, -0.006603,  0.999969, -0.000524, -0.000606, -0.000540,  0.999801, -0.000404, -0.011330, -0.012649, -0.014966,  0.995746, -0.055268, -0.044579, -0.057030,  0.995879, -0.041778,  0.000000, -0.010683, -0.011185, -0.012754,  0.996474, -0.048846, -0.038892, -0.044784,  0.996874, -0.034269,  0.000000],
-    "q99":  [ 0.000472,  0.003180,  0.007315,  1.000000,  0.000532,  0.000603,  0.000514,  1.000000,  0.000454,  0.011657,  0.012629,  0.013074,  1.000000,  0.057221,  0.045662,  0.055355,  1.000000,  0.042508,  1.000000,  0.010122,  0.011385,  0.011604,  1.000000,  0.044671,  0.039433,  0.048886,  1.000000,  0.036261,  1.000000]
-  }
-}

cosmos_dreams_action_sources/action_schema.json

@@ -1,95 +0,0 @@
-{
-  "action_tokens_per_frame": 4,
-  "contract_sha256": "2c75f43813f507ab5d382d5d64c41955b3871ee164c093fa098c8429cb8547db",
-  "default_embodiment": "camera_pose",
-  "embodiments": {
-    "camera_pose": {
-      "domain_id": 2,
-      "layout": {
-        "delta_equation": "T_i^-1 @ T_{i+1}",
-        "fields": [
-          {
-            "name": "camera_translation",
-            "offset": 0,
-            "size": 3,
-            "unit": "meter"
-          },
-          {
-            "name": "camera_rotation",
-            "offset": 3,
-            "representation": "rot6d_columns",
-            "size": 6,
-            "unit": "dimensionless"
-          }
-        ],
-        "id": "camera_pose_backward_framewise_rot6d_v1",
-        "pose_convention": "backward_framewise",
-        "rotation_representation": "rot6d_columns"
-      },
-      "normalizer": {
-        "derivation": {
-          "rotation_scale": 1.0,
-          "translation_scale": 10.0
-        },
-        "method": "pose_scale",
-        "schema_version": 1,
-        "training_config": {
-          "experiment": "causal_8b_sf_dmd_max_4step_cam_chunk4_480p_961f",
-          "repository_revision": "483375f79279832b52d9e5c3598345a86f7137d5",
-          "resolved_sha256": "0e7b2be45c82b13c6f1454cdafd7e75d1941a6565e3b72b15a03a99d65177f29"
-        },
-        "transform": {
-          "forward_clamp": false,
-          "offset": [
-            0.0,
-            0.0,
-            0.0,
-            0.0,
-            0.0,
-            0.0,
-            0.0,
-            0.0,
-            0.0
-          ],
-          "scale": [
-            0.10000000149011612,
-            0.10000000149011612,
-            0.10000000149011612,
-            1.0,
-            1.0,
-            1.0,
-            1.0,
-            1.0,
-            1.0
-          ],
-          "type": "affine"
-        },
-        "transform_sha256": "bb8102c686b4813c1cdcc82b78cb174225fa35f8bfafd07d36b81a767bb6e698"
-      },
-      "raw_action_dim": 9
-    }
-  },
-  "model_action_dim": 64,
-  "num_embodiment_domains": 32,
-  "padding": {
-    "stage": "after_normalization",
-    "value": 0.0
-  },
-  "schema_version": 3,
-  "training_config_excerpt": {
-    "datasets": [
-      {
-        "apply_forward_clamp": false,
-        "dataset_class": "CameraDatasetSharded",
-        "embodiment": "camera_pose",
-        "method": "pose_scale",
-        "mode": "forward_dynamics",
-        "pose_convention": "backward_framewise",
-        "rotation_format": "rot6d",
-        "rotation_scale": 1.0,
-        "translation_scale": 10.0
-      }
-    ],
-    "experiment": "causal_8b_sf_dmd_max_4step_cam_chunk4_480p_961f"
-  }
-}

cosmos_dreams_action_sources/cosmos_dreams_action_schema.schema.json

@@ -1,201 +0,0 @@
-{
-  "$schema": "https://json-schema.org/draft/2020-12/schema",
-  "$id": "https://developer.nvidia.com/cosmos-dreams/action-schema-v3.schema.json",
-  "title": "Cosmos-Dreams Per-Embodiment Action Schema v3",
-  "type": "object",
-  "additionalProperties": false,
-  "required": ["schema_version", "action_tokens_per_frame", "model_action_dim", "num_embodiment_domains", "default_embodiment", "embodiments", "padding", "training_config_excerpt", "contract_sha256"],
-  "properties": {
-    "schema_version": {"const": 3},
-    "action_tokens_per_frame": {"const": 4},
-    "model_action_dim": {"const": 64},
-    "num_embodiment_domains": {"const": 32},
-    "default_embodiment": {"enum": ["abc_yam", "agibotworld", "agibot_gear_gripper", "agibot_gear_gripper_ext", "camera_pose", "molmoact2_yam", "xdof_yam"]},
-    "embodiments": {
-      "type": "object",
-      "minProperties": 1,
-      "additionalProperties": false,
-      "properties": {
-        "abc_yam": {"$ref": "#/$defs/yam_embodiment"},
-        "agibotworld": {"$ref": "#/$defs/agibot_embodiment"},
-        "agibot_gear_gripper": {"$ref": "#/$defs/agibot_embodiment"},
-        "agibot_gear_gripper_ext": {"$ref": "#/$defs/agibot_embodiment"},
-        "camera_pose": {"$ref": "#/$defs/camera_embodiment"},
-        "molmoact2_yam": {"$ref": "#/$defs/yam_embodiment"},
-        "xdof_yam": {"$ref": "#/$defs/yam_embodiment"}
-      }
-    },
-    "padding": {"const": {"stage": "after_normalization", "value": 0.0}},
-    "training_config_excerpt": {
-      "type": "object",
-      "additionalProperties": false,
-      "required": ["datasets", "experiment"],
-      "properties": {
-        "datasets": {"type": "array", "minItems": 1, "items": {"oneOf": [{"$ref": "#/$defs/agibot_dataset_descriptor"}, {"$ref": "#/$defs/yam_dataset_descriptor"}, {"$ref": "#/$defs/camera_dataset_descriptor"}]}},
-        "experiment": {"type": "string", "minLength": 1}
-      }
-    },
-    "contract_sha256": {"$ref": "#/$defs/sha256"}
-  },
-  "$defs": {
-    "sha256": {"type": "string", "pattern": "^[0-9a-f]{64}$"},
-    "repository_revision": {"type": "string", "pattern": "^[0-9a-f]{40}$"},
-    "training_config": {
-      "type": "object",
-      "additionalProperties": false,
-      "required": ["experiment", "resolved_sha256", "repository_revision"],
-      "properties": {
-        "experiment": {"type": "string", "minLength": 1},
-        "resolved_sha256": {"$ref": "#/$defs/sha256"},
-        "repository_revision": {"$ref": "#/$defs/repository_revision"}
-      }
-    },
-    "agibot_layout": {
-      "const": {"id": "agibot_backward_framewise_rot6d_v1", "pose_convention": "backward_framewise", "delta_equation": "T_i^-1 @ T_{i+1}", "rotation_representation": "rot6d_columns", "fields": [{"name": "head_translation", "offset": 0, "size": 3, "unit": "meter"}, {"name": "head_rotation", "offset": 3, "size": 6, "unit": "dimensionless", "representation": "rot6d_columns"}, {"name": "right_translation", "offset": 9, "size": 3, "unit": "meter"}, {"name": "right_rotation", "offset": 12, "size": 6, "unit": "dimensionless", "representation": "rot6d_columns"}, {"name": "right_gripper", "offset": 18, "size": 1, "unit": "open_fraction", "closed_value": 0.0, "open_value": 1.0}, {"name": "left_translation", "offset": 19, "size": 3, "unit": "meter"}, {"name": "left_rotation", "offset": 22, "size": 6, "unit": "dimensionless", "representation": "rot6d_columns"}, {"name": "left_gripper", "offset": 28, "size": 1, "unit": "open_fraction", "closed_value": 0.0, "open_value": 1.0}]}
-    },
-    "yam_layout": {
-      "const": {"id": "legacy_yam_fk_backward_framewise_rot6d_v1", "pose_convention": "backward_framewise", "delta_equation": "T_i^-1 @ T_{i+1}", "rotation_representation": "rot6d_columns", "fields": [{"name": "left_translation", "offset": 0, "size": 3, "unit": "meter"}, {"name": "left_rotation", "offset": 3, "size": 6, "unit": "dimensionless", "representation": "rot6d_columns"}, {"name": "left_gripper", "offset": 9, "size": 1, "unit": "open_fraction", "closed_value": 0.0, "open_value": 1.0}, {"name": "right_translation", "offset": 10, "size": 3, "unit": "meter"}, {"name": "right_rotation", "offset": 13, "size": 6, "unit": "dimensionless", "representation": "rot6d_columns"}, {"name": "right_gripper", "offset": 19, "size": 1, "unit": "open_fraction", "closed_value": 0.0, "open_value": 1.0}]}
-    },
-    "camera_layout": {
-      "const": {"id": "camera_pose_backward_framewise_rot6d_v1", "pose_convention": "backward_framewise", "delta_equation": "T_i^-1 @ T_{i+1}", "rotation_representation": "rot6d_columns", "fields": [{"name": "camera_translation", "offset": 0, "size": 3, "unit": "meter"}, {"name": "camera_rotation", "offset": 3, "size": 6, "unit": "dimensionless", "representation": "rot6d_columns"}]}
-    },
-    "agibot_embodiment": {
-      "type": "object",
-      "additionalProperties": false,
-      "required": ["domain_id", "raw_action_dim", "layout", "normalizer"],
-      "properties": {"domain_id": {"const": 15}, "raw_action_dim": {"const": 29}, "layout": {"$ref": "#/$defs/agibot_layout"}, "normalizer": {"$ref": "#/$defs/quantile_rot"}}
-    },
-    "yam_embodiment": {
-      "type": "object",
-      "additionalProperties": false,
-      "required": ["domain_id", "raw_action_dim", "layout", "normalizer"],
-      "properties": {"domain_id": {"const": 16}, "raw_action_dim": {"const": 20}, "layout": {"$ref": "#/$defs/yam_layout"}, "normalizer": {"$ref": "#/$defs/yam_quantile_rot"}}
-    },
-    "camera_embodiment": {
-      "type": "object",
-      "additionalProperties": false,
-      "required": ["domain_id", "raw_action_dim", "layout", "normalizer"],
-      "properties": {"domain_id": {"const": 2}, "raw_action_dim": {"const": 9}, "layout": {"$ref": "#/$defs/camera_layout"}, "normalizer": {"$ref": "#/$defs/pose_scale"}}
-    },
-    "agibot_dataset_descriptor": {
-      "type": "object",
-      "additionalProperties": false,
-      "required": ["dataset_class", "embodiment", "method", "apply_forward_clamp", "pose_convention", "rotation_format", "stats_filename"],
-      "properties": {
-        "dataset_class": {"enum": ["AgiBotWorldBetaDataset", "AgibotGEARGripperDataset", "AgibotGEARGripperExtDataset"]},
-        "embodiment": {"enum": ["agibotworld", "agibot_gear_gripper", "agibot_gear_gripper_ext"]},
-        "method": {"const": "quantile_rot"},
-        "apply_forward_clamp": {"const": false},
-        "pose_convention": {"const": "backward_framewise"},
-        "rotation_format": {"const": "rot6d"},
-        "stats_filename": {"enum": ["agibot_backward_framewise_rot6d.json", "agibot_gear_gripper_backward_framewise_rot6d.json"]}
-      },
-      "allOf": [
-        {"if": {"properties": {"dataset_class": {"const": "AgiBotWorldBetaDataset"}}}, "then": {"properties": {"embodiment": {"const": "agibotworld"}, "stats_filename": {"const": "agibot_backward_framewise_rot6d.json"}}}},
-        {"if": {"properties": {"dataset_class": {"const": "AgibotGEARGripperDataset"}}}, "then": {"properties": {"embodiment": {"const": "agibot_gear_gripper"}}}},
-        {"if": {"properties": {"dataset_class": {"const": "AgibotGEARGripperExtDataset"}}}, "then": {"properties": {"embodiment": {"const": "agibot_gear_gripper_ext"}}}}
-      ]
-    },
-    "yam_dataset_descriptor": {
-      "type": "object",
-      "additionalProperties": false,
-      "required": ["dataset_class", "embodiment", "method", "apply_forward_clamp", "pose_convention", "rotation_format", "stats_filename"],
-      "properties": {
-        "dataset_class": {"enum": ["ABCYAMLeRobotDataset", "MolmoAct2YAMDataset", "XDOFYAMDataset"]},
-        "embodiment": {"enum": ["abc_yam", "molmoact2_yam", "xdof_yam"]},
-        "method": {"const": "quantile_rot"},
-        "apply_forward_clamp": {"const": false},
-        "pose_convention": {"const": "backward_framewise"},
-        "rotation_format": {"const": "rot6d"},
-        "stats_filename": {"enum": ["abc_yam_backward_framewise_rot6d.json", "molmoact2_yam_backward_framewise_rot6d.json", "xdof_yam_backward_framewise_rot6d.json"]}
-      },
-      "allOf": [
-        {"if": {"properties": {"dataset_class": {"const": "ABCYAMLeRobotDataset"}}}, "then": {"properties": {"embodiment": {"const": "abc_yam"}, "stats_filename": {"const": "abc_yam_backward_framewise_rot6d.json"}}}},
-        {"if": {"properties": {"dataset_class": {"const": "MolmoAct2YAMDataset"}}}, "then": {"properties": {"embodiment": {"const": "molmoact2_yam"}, "stats_filename": {"const": "molmoact2_yam_backward_framewise_rot6d.json"}}}},
-        {"if": {"properties": {"dataset_class": {"const": "XDOFYAMDataset"}}}, "then": {"properties": {"embodiment": {"const": "xdof_yam"}, "stats_filename": {"const": "xdof_yam_backward_framewise_rot6d.json"}}}}
-      ]
-    },
-    "camera_dataset_descriptor": {
-      "type": "object",
-      "additionalProperties": false,
-      "required": ["dataset_class", "embodiment", "method", "apply_forward_clamp", "mode", "pose_convention", "rotation_format", "translation_scale", "rotation_scale"],
-      "properties": {
-        "dataset_class": {"const": "CameraDatasetSharded"},
-        "embodiment": {"const": "camera_pose"},
-        "method": {"const": "pose_scale"},
-        "apply_forward_clamp": {"const": false},
-        "mode": {"const": "forward_dynamics"},
-        "pose_convention": {"const": "backward_framewise"},
-        "rotation_format": {"const": "rot6d"},
-        "translation_scale": {"type": "number", "exclusiveMinimum": 0},
-        "rotation_scale": {"type": "number", "exclusiveMinimum": 0}
-      }
-    },
-    "quantile_rot": {
-      "type": "object",
-      "additionalProperties": false,
-      "required": ["schema_version", "method", "transform", "derivation", "source", "training_config", "transform_sha256"],
-      "properties": {
-        "schema_version": {"const": 1},
-        "method": {"const": "quantile_rot"},
-        "transform": {
-          "type": "object",
-          "additionalProperties": false,
-          "required": ["type", "offset", "scale", "forward_clamp"],
-          "properties": {"type": {"const": "affine"}, "offset": {"type": "array", "minItems": 29, "maxItems": 29, "items": {"type": "number"}}, "scale": {"type": "array", "minItems": 29, "maxItems": 29, "items": {"type": "number", "exclusiveMinimum": 0}}, "forward_clamp": {"const": false}}
-        },
-        "derivation": {"type": "object", "additionalProperties": false, "required": ["statistics_block", "low_key", "high_key", "range_floor"], "properties": {"statistics_block": {"const": "global_raw"}, "low_key": {"const": "q01"}, "high_key": {"const": "q99"}, "range_floor": {"const": 9.99999993922529e-9}}},
-        "source": {
-          "type": "object",
-          "additionalProperties": false,
-          "required": ["path", "artifact_path", "sha256", "repository_revision"],
-          "properties": {"path": {"enum": ["projects/cosmos3/cosmos3/datasets/action/normalizers/agibot_backward_framewise_rot6d.json", "projects/cosmos3/cosmos3/datasets/action/normalizers/agibot_gear_gripper_backward_framewise_rot6d.json"]}, "artifact_path": {"type": "string", "pattern": "^cosmos_dreams_action_sources/[0-9a-f]{64}\\.json$"}, "sha256": {"$ref": "#/$defs/sha256"}, "repository_revision": {"$ref": "#/$defs/repository_revision"}}
-        },
-        "training_config": {"$ref": "#/$defs/training_config"},
-        "transform_sha256": {"$ref": "#/$defs/sha256"}
-      }
-    },
-    "yam_quantile_rot": {
-      "type": "object",
-      "additionalProperties": false,
-      "required": ["schema_version", "method", "transform", "derivation", "source", "training_config", "transform_sha256"],
-      "properties": {
-        "schema_version": {"const": 1},
-        "method": {"const": "quantile_rot"},
-        "transform": {
-          "type": "object",
-          "additionalProperties": false,
-          "required": ["type", "offset", "scale", "forward_clamp"],
-          "properties": {"type": {"const": "affine"}, "offset": {"type": "array", "minItems": 20, "maxItems": 20, "items": {"type": "number"}}, "scale": {"type": "array", "minItems": 20, "maxItems": 20, "items": {"type": "number", "exclusiveMinimum": 0}}, "forward_clamp": {"const": false}}
-        },
-        "derivation": {"type": "object", "additionalProperties": false, "required": ["statistics_block", "low_key", "high_key", "range_floor"], "properties": {"statistics_block": {"const": "global_raw"}, "low_key": {"const": "q01"}, "high_key": {"const": "q99"}, "range_floor": {"const": 9.99999993922529e-9}}},
-        "source": {
-          "type": "object",
-          "additionalProperties": false,
-          "required": ["path", "artifact_path", "sha256", "repository_revision"],
-          "properties": {"path": {"enum": ["projects/cosmos3/cosmos3/datasets/action/legacy/normalizers/abc_yam_backward_framewise_rot6d.json", "projects/cosmos3/cosmos3/datasets/action/legacy/normalizers/molmoact2_yam_backward_framewise_rot6d.json", "projects/cosmos3/cosmos3/datasets/action/legacy/normalizers/xdof_yam_backward_framewise_rot6d.json"]}, "artifact_path": {"type": "string", "pattern": "^cosmos_dreams_action_sources/[0-9a-f]{64}\\.json$"}, "sha256": {"$ref": "#/$defs/sha256"}, "repository_revision": {"$ref": "#/$defs/repository_revision"}}
-        },
-        "training_config": {"$ref": "#/$defs/training_config"},
-        "transform_sha256": {"$ref": "#/$defs/sha256"}
-      }
-    },
-    "pose_scale": {
-      "type": "object",
-      "additionalProperties": false,
-      "required": ["schema_version", "method", "transform", "derivation", "training_config", "transform_sha256"],
-      "properties": {
-        "schema_version": {"const": 1},
-        "method": {"const": "pose_scale"},
-        "transform": {
-          "type": "object",
-          "additionalProperties": false,
-          "required": ["type", "offset", "scale", "forward_clamp"],
-          "properties": {"type": {"const": "affine"}, "offset": {"type": "array", "minItems": 9, "maxItems": 9, "items": {"const": 0.0}}, "scale": {"type": "array", "minItems": 9, "maxItems": 9, "items": {"type": "number", "exclusiveMinimum": 0}}, "forward_clamp": {"const": false}}
-        },
-        "derivation": {"type": "object", "additionalProperties": false, "required": ["translation_scale", "rotation_scale"], "properties": {"translation_scale": {"type": "number", "exclusiveMinimum": 0}, "rotation_scale": {"type": "number", "exclusiveMinimum": 0}}},
-        "training_config": {"$ref": "#/$defs/training_config"},
-        "transform_sha256": {"$ref": "#/$defs/sha256"}
-      }
-    }
-  }
-}

cosmos_dreams_action_sources/resolved_action_config.json

@@ -1,16 +0,0 @@
-{
-  "datasets": [
-    {
-      "apply_forward_clamp": false,
-      "dataset_class": "CameraDatasetSharded",
-      "embodiment": "camera_pose",
-      "method": "pose_scale",
-      "mode": "forward_dynamics",
-      "pose_convention": "backward_framewise",
-      "rotation_format": "rot6d",
-      "rotation_scale": 1.0,
-      "translation_scale": 10.0
-    }
-  ],
-  "experiment": "causal_8b_sf_dmd_max_4step_cam_chunk4_480p_961f"
-}

cosmos_dreams_manifest.json

@@ -1,131 +0,0 @@
-{
-  "attention_mode": "three_way",
-  "checkpoint_hash": "9540afba2ac43d36b213a847f227b8011f5419feb670be722b518debdc22f63e",
-  "checkpoint_id": "causal_8b_sf_dmd_max_4step_cam_chunk4_480p_961f@iter_000002000",
-  "checkpoint_iteration": 2000,
-  "chunk_partition": [
-    1,
-    4
-  ],
-  "chunk_size": 4,
-  "conditioning": {
-    "action_tokens_per_frame": 4,
-    "contract_sha256": "2c75f43813f507ab5d382d5d64c41955b3871ee164c093fa098c8429cb8547db",
-    "default_embodiment": "camera_pose",
-    "embodiments": {
-      "camera_pose": {
-        "domain_id": 2,
-        "layout": {
-          "delta_equation": "T_i^-1 @ T_{i+1}",
-          "fields": [
-            {
-              "name": "camera_translation",
-              "offset": 0,
-              "size": 3,
-              "unit": "meter"
-            },
-            {
-              "name": "camera_rotation",
-              "offset": 3,
-              "representation": "rot6d_columns",
-              "size": 6,
-              "unit": "dimensionless"
-            }
-          ],
-          "id": "camera_pose_backward_framewise_rot6d_v1",
-          "pose_convention": "backward_framewise",
-          "rotation_representation": "rot6d_columns"
-        },
-        "normalizer": {
-          "derivation": {
-            "rotation_scale": 1.0,
-            "translation_scale": 10.0
-          },
-          "method": "pose_scale",
-          "schema_version": 1,
-          "training_config": {
-            "experiment": "causal_8b_sf_dmd_max_4step_cam_chunk4_480p_961f",
-            "repository_revision": "483375f79279832b52d9e5c3598345a86f7137d5",
-            "resolved_sha256": "0e7b2be45c82b13c6f1454cdafd7e75d1941a6565e3b72b15a03a99d65177f29"
-          },
-          "transform": {
-            "forward_clamp": false,
-            "offset": [
-              0.0,
-              0.0,
-              0.0,
-              0.0,
-              0.0,
-              0.0,
-              0.0,
-              0.0,
-              0.0
-            ],
-            "scale": [
-              0.10000000149011612,
-              0.10000000149011612,
-              0.10000000149011612,
-              1.0,
-              1.0,
-              1.0,
-              1.0,
-              1.0,
-              1.0
-            ],
-            "type": "affine"
-          },
-          "transform_sha256": "bb8102c686b4813c1cdcc82b78cb174225fa35f8bfafd07d36b81a767bb6e698"
-        },
-        "raw_action_dim": 9
-      }
-    },
-    "mode": "action",
-    "model_action_dim": 64,
-    "num_embodiment_domains": 32,
-    "padding": {
-      "stage": "after_normalization",
-      "value": 0.0
-    },
-    "schema_version": 3,
-    "training_config_excerpt": {
-      "datasets": [
-        {
-          "apply_forward_clamp": false,
-          "dataset_class": "CameraDatasetSharded",
-          "embodiment": "camera_pose",
-          "method": "pose_scale",
-          "mode": "forward_dynamics",
-          "pose_convention": "backward_framewise",
-          "rotation_format": "rot6d",
-          "rotation_scale": 1.0,
-          "translation_scale": 10.0
-        }
-      ],
-      "experiment": "causal_8b_sf_dmd_max_4step_cam_chunk4_480p_961f"
-    }
-  },
-  "fixed_step_sampler_config": {
-    "num_train_timesteps": 1000,
-    "sample_type": "sde",
-    "t_list": [
-      1.0,
-      0.9375,
-      0.8333333333333334,
-      0.625
-    ]
-  },
-  "latent_patch_size": 2,
-  "mrope": {
-    "base_fps": 24.0,
-    "enable_fps_modulation": true,
-    "reset_spatial_ids": true,
-    "temporal_modality_margin": 15000
-  },
-  "schema_version": 1,
-  "sink_frames": 0,
-  "temporal_compression_factor": 4,
-  "text_cache_max_len": 512,
-  "vae_spatial_compression_factor": 16,
-  "video_temporal_causal": true,
-  "window_frames": 96
-}

model_index.json

@@ -20,17 +20,17 @@
     },
     "latent_patch_size": 2,
     "schema_version": 1,
-    "sink_frames": 0,
+    "sink_frames": 8,
     "temporal_compression_factor": 4,
     "temporal_modality_margin": 15000,
-    "text_cache_max_len": 512,
+    "text_cache_max_len": 1024,
     "unified_3d_mrope_reset_spatial_ids": true,
     "vae_spatial_compression_factor": 16,
     "video_temporal_causal": true,
-    "window_frames": null
+    "window_frames": 64
   },
-  "_diffusers_version": "0.39.0",
-  "default_use_system_prompt": true,
+  "_diffusers_version": "0.40.0",
+  "default_use_system_prompt": false,
   "enable_safety_checker": false,
   "safety_checker": [
     null,
@@ -46,7 +46,7 @@
   ],
   "text_tokenizer": [
     "transformers",
-    "Qwen2TokenizerFast"
+    "Qwen2Tokenizer"
   ],
   "transformer": [
     "diffusers",

modular_model_index.json

@@ -21,28 +21,30 @@
     },
     "latent_patch_size": 2,
     "schema_version": 1,
-    "sink_frames": 0,
+    "sink_frames": 8,
     "temporal_compression_factor": 4,
     "temporal_modality_margin": 15000,
-    "text_cache_max_len": 512,
+    "text_cache_max_len": 1024,
     "unified_3d_mrope_reset_spatial_ids": true,
     "vae_spatial_compression_factor": 16,
     "video_temporal_causal": true,
-    "window_frames": null
+    "window_frames": 64
   },
-  "_diffusers_version": "0.39.0",
+  "_diffusers_version": "0.40.0",
+  "default_use_system_prompt": false,
   "distilled_sigmas": [
     1.0,
     0.9375,
     0.8333333333333334,
     0.625
   ],
+  "enable_safety_checker": false,
   "is_distilled": true,
   "scheduler": [
     "diffusers",
     "FlowMatchEulerDiscreteScheduler",
     {
-      "pretrained_model_name_or_path": "diffusers_format",
+      "pretrained_model_name_or_path": "diffusers_format7",
       "subfolder": "scheduler",
       "type_hint": [
         "diffusers",
@@ -53,13 +55,13 @@
   ],
   "text_tokenizer": [
     "transformers",
-    "Qwen2TokenizerFast",
+    "Qwen2Tokenizer",
     {
-      "pretrained_model_name_or_path": "diffusers_format",
+      "pretrained_model_name_or_path": "diffusers_format7",
       "subfolder": "text_tokenizer",
       "type_hint": [
         "transformers",
-        "Qwen2TokenizerFast"
+        "Qwen2Tokenizer"
       ],
       "variant": null
     }
@@ -68,7 +70,7 @@
     "diffusers",
     "Cosmos3OmniTransformer",
     {
-      "pretrained_model_name_or_path": "diffusers_format",
+      "pretrained_model_name_or_path": "diffusers_format7",
       "subfolder": "transformer",
       "type_hint": [
         "diffusers",
@@ -77,11 +79,12 @@
       "variant": null
     }
   ],
+  "use_native_flow_schedule": false,
   "vae": [
     "diffusers",
     "AutoencoderKLWan",
     {
-      "pretrained_model_name_or_path": "diffusers_format",
+      "pretrained_model_name_or_path": "diffusers_format7",
       "subfolder": "vae",
       "type_hint": [
         "diffusers",

scheduler/scheduler_config.json

@@ -1,6 +1,6 @@
 {
   "_class_name": "FlowMatchEulerDiscreteScheduler",
-  "_diffusers_version": "0.39.0",
+  "_diffusers_version": "0.40.0",
   "base_image_seq_len": 256,
   "base_shift": 0.5,
   "fixed_step_requires_explicit_sigmas": true,

text_tokenizer/tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
-size 11422654
+oid sha256:be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506
+size 11422650

text_tokenizer/tokenizer_config.json

@@ -1,217 +1,11 @@
 {
-  "add_bos_token": false,
   "add_prefix_space": false,
-  "added_tokens_decoder": {
-    "151643": {
-      "content": "<|endoftext|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151644": {
-      "content": "<|im_start|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151645": {
-      "content": "<|im_end|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151646": {
-      "content": "<|object_ref_start|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151647": {
-      "content": "<|object_ref_end|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151648": {
-      "content": "<|box_start|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151649": {
-      "content": "<|box_end|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151650": {
-      "content": "<|quad_start|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151651": {
-      "content": "<|quad_end|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151652": {
-      "content": "<|vision_start|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151653": {
-      "content": "<|vision_end|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151654": {
-      "content": "<|vision_pad|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151655": {
-      "content": "<|image_pad|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151656": {
-      "content": "<|video_pad|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151657": {
-      "content": "<tool_call>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151658": {
-      "content": "</tool_call>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151659": {
-      "content": "<|fim_prefix|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151660": {
-      "content": "<|fim_middle|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151661": {
-      "content": "<|fim_suffix|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151662": {
-      "content": "<|fim_pad|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151663": {
-      "content": "<|repo_name|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151664": {
-      "content": "<|file_sep|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151665": {
-      "content": "<tool_response>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151666": {
-      "content": "</tool_response>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151667": {
-      "content": "<think>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151668": {
-      "content": "</think>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    }
-  },
-  "additional_special_tokens": [
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": [
     "<|im_start|>",
     "<|im_end|>",
     "<|object_ref_start|>",
@@ -226,11 +20,8 @@
     "<|image_pad|>",
     "<|video_pad|>"
   ],
-  "bos_token": null,
-  "clean_up_tokenization_spaces": false,
-  "eos_token": "<|im_end|>",
-  "errors": "replace",
-  "extra_special_tokens": {},
+  "is_local": false,
+  "local_files_only": false,
   "model_max_length": 262144,
   "pad_token": "<|endoftext|>",
   "split_special_tokens": false,

transformer/config.json

@@ -1,6 +1,6 @@
 {
   "_class_name": "Cosmos3OmniTransformer",
-  "_diffusers_version": "0.39.0",
+  "_diffusers_version": "0.40.0",
   "action_dim": 64,
   "action_gen": true,
   "attention_bias": false,
@@ -15,7 +15,7 @@
     "chunk_size": 2,
     "conditioning": {
       "action_tokens_per_frame": 4,
-      "contract_sha256": "bb69c3678ea0a17e0685933606b44d5b9fe946d1f657fa945d7b4dce321723df",
+      "contract_sha256": "118860602b7d1017ca6333ad1cfe4324d500f526b45efc478429d20ffd062492",
       "default_embodiment": "agibotworld",
       "embodiments": {
         "abc_yam": {
@@ -114,7 +114,7 @@
           "artifact_path": "cosmos3_nano_sim_bimanual_action_sources/ae695e2c643a5626b3c3564f00705aa3a83ab0da7640549c7340db71172594b0.json",
           "path": "projects/cosmos3/cosmos3/datasets/action/normalizers/global_asinh_v1_backward_anchored_gripper_metric.json",
           "pose_convention_authority": "resolved_canonical_lance_training_config",
-          "repository_revision": "970970f3a3024563973d4114e7c60cfda62c3af0",
+          "repository_revision": "2076f215a33b4fe164bf2faca4c01a28cda71f79",
           "sha256": "ae695e2c643a5626b3c3564f00705aa3a83ab0da7640549c7340db71172594b0"
         }
       },
@@ -198,6 +198,15 @@
             "target": "projects.cosmos3.cosmos3.datasets.action.canonical_lance_action_datasets.CanonicalLanceYAMDataset",
             "translation_scale": 1.0
           },
+          {
+            "camera_mask": false,
+            "embodiment": "hand_pose",
+            "name": "mecka_all",
+            "pose_convention": "backward_chunk_anchored_16f",
+            "rotation_format": "rot6d",
+            "target": "projects.cosmos3.cosmos3.datasets.action.canonical_lance_action_datasets.CanonicalLanceMeckaDataset",
+            "translation_scale": 1.0
+          },
           {
             "camera_mask": true,
             "embodiment": "behavior1k_lerobot",
@@ -235,14 +244,14 @@
     },
     "latent_patch_size": 2,
     "schema_version": 1,
-    "sink_frames": 0,
+    "sink_frames": 8,
     "temporal_compression_factor": 4,
     "temporal_modality_margin": 15000,
     "text_cache_max_len": 1024,
     "unified_3d_mrope_reset_spatial_ids": true,
     "vae_spatial_compression_factor": 16,
     "video_temporal_causal": true,
-    "window_frames": null
+    "window_frames": 64
   },
   "enable_fps_modulation": true,
   "head_dim": 128,
@@ -271,6 +280,7 @@
       20,
       20
     ],
+    "rope_theta": 5000000,
     "rope_type": "default"
   },
   "rope_theta": 5000000,

vae/config.json

@@ -1,6 +1,6 @@
 {
   "_class_name": "AutoencoderKLWan",
-  "_diffusers_version": "0.39.0",
+  "_diffusers_version": "0.40.0",
   "_name_or_path": "Wan-AI/Wan2.2-TI2V-5B-Diffusers",
   "attn_scales": [],
   "base_dim": 160,