Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+trainer_state.json filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,80 @@
+{
+  "_name_or_path": "/mnt/amlfs-01/home/seonghyeony/checkpoints/groot_s_gr1_idm_real_global_stats",
+  "action_dim": 32,
+  "action_head_cfg": {
+    "_convert_": "object",
+    "_target_": "gr00t.model.action_head.flow_matching_action_head_idm.FlowMatchingActionHeadIDM",
+    "config": {
+      "_recursive_": false,
+      "_target_": "gr00t.model.action_head.flow_matching_action_head_idm.FlowMatchingActionHeadIDMConfig",
+      "action_dim": 32,
+      "action_horizon": 16,
+      "add_pos_embed": true,
+      "add_seperator_token": true,
+      "add_view_embed": true,
+      "backbone_features_projector_cfg": null,
+      "diffusion_model_cfg": {
+        "_target_": "gr00t.model.action_head.cross_attention_dit.DiT",
+        "attention_head_dim": 64,
+        "dropout": 0.2,
+        "final_dropout": true,
+        "interleave_self_attention": true,
+        "norm_type": "ada_norm",
+        "num_attention_heads": 16,
+        "num_layers": 8,
+        "output_dim": 1024,
+        "positional_embeddings": null
+      },
+      "hidden_size": 1024,
+      "max_action_dim": 32,
+      "max_num_views": 3,
+      "max_state_dim": 44,
+      "mm_projector_cfg": {
+        "_convert_": "object",
+        "_target_": "gr00t.model.action_head.multimodal_projector.MultimodalProjector",
+        "config": {
+          "_target_": "gr00t.model.action_head.multimodal_projector.MultimodalProjectorConfig",
+          "hidden_size": 1024,
+          "mm_hidden_size": 1024,
+          "mm_projector_type": "mlp_doubledownsample"
+        }
+      },
+      "mm_vision_select_layer": -2,
+      "model_dtype": "float32",
+      "noise_beta_alpha": 1.5,
+      "noise_beta_beta": 1.0,
+      "noise_s": 0.999,
+      "num_inference_timesteps": 16,
+      "num_timestep_buckets": 1000,
+      "siglip_hidden_size": 1024,
+      "siglip_model_cfg": {
+        "_convert_": "object",
+        "_target_": "gr00t.model.action_head.siglip.SiglipModel.from_pretrained",
+        "pretrained_model_name_or_path": "google/siglip2-large-patch16-256"
+      },
+      "tune_vision_tower": true,
+      "vl_self_attention_cfg": {
+        "_target_": "gr00t.model.action_head.cross_attention_dit.SelfAttentionTransformer",
+        "attention_head_dim": 64,
+        "dropout": 0.2,
+        "final_dropout": true,
+        "num_attention_heads": 16,
+        "num_layers": 4,
+        "positional_embeddings": null
+      }
+    }
+  },
+  "action_horizon": 16,
+  "architectures": [
+    "IDM"
+  ],
+  "backbone_cfg": {
+    "_target_": "gr00t.model.backbone.IdentityBackbone"
+  },
+  "hidden_size": 0,
+  "model_dtype": "float32",
+  "model_type": "dual_brain",
+  "resume_path": "/mnt/amlfs-01/home/seonghyeony/checkpoints/groot_s_gr1_idm_real_global_stats",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.48.0"
+}

experiment_cfg/metadata.json

@@ -0,0 +1,934 @@
+{
+    "gr1_unified": {
+        "dataset_name": "gr1_unified:FullSet, gr1_unified:FullSet",
+        "dataset_statistics": {
+            "state": {
+                "left_arm": {
+                    "max": [
+                        1.3570959568023682,
+                        1.5781080722808838,
+                        1.7425614595413208,
+                        0.04977008327841759,
+                        2.521491289138794,
+                        1.5104753971099854,
+                        1.3451268672943115
+                    ],
+                    "min": [
+                        -1.7593636512756348,
+                        -0.08899051696062088,
+                        -1.6571800708770752,
+                        -2.516343355178833,
+                        -2.307133436203003,
+                        -1.4132264852523804,
+                        -1.4408576488494873
+                    ],
+                    "mean": [
+                        -0.1721954196691513,
+                        0.18329788744449615,
+                        -0.13603615760803223,
+                        -1.0807313919067383,
+                        0.14450088143348694,
+                        0.1319544017314911,
+                        -0.08306947350502014
+                    ],
+                    "std": [
+                        0.40682145953178406,
+                        0.18259239196777344,
+                        0.25132784247398376,
+                        0.5786943435668945,
+                        0.33050763607025146,
+                        0.28609949350357056,
+                        0.30134323239326477
+                    ],
+                    "q01": [
+                        -1.601158422231674,
+                        -0.0004831812286283818,
+                        -0.9488833963871002,
+                        -2.43623423576355,
+                        -0.940359205007553,
+                        -0.648951044678688,
+                        -0.9641011685132981
+                    ],
+                    "q99": [
+                        0.6305126994848265,
+                        0.7966297268867493,
+                        0.3873166218400003,
+                        -0.07399308793246723,
+                        1.0455405175685888,
+                        0.8574009954929354,
+                        0.48388660699129127
+                    ]
+                },
+                "left_hand": {
+                    "max": [
+                        2.8765757083892822,
+                        2.6975045204162598,
+                        3.3291828632354736,
+                        2.7148845195770264,
+                        3.664421558380127,
+                        3.5466625690460205
+                    ],
+                    "min": [
+                        -3.262805700302124,
+                        -2.7771592140197754,
+                        -3.4712820053100586,
+                        -2.7828404903411865,
+                        -2.197380781173706,
+                        -2.636387825012207
+                    ],
+                    "mean": [
+                        0.21940384805202484,
+                        0.21819256246089935,
+                        0.20426052808761597,
+                        0.22833923995494843,
+                        0.06841608136892319,
+                        0.9091449975967407
+                    ],
+                    "std": [
+                        0.42784574627876276,
+                        0.41304099559783936,
+                        0.3710329830646515,
+                        0.42297253012657166,
+                        0.18603332340717316,
+                        0.7297042012214661
+                    ],
+                    "q01": [
+                        -0.17130047902464868,
+                        -0.002568027237430215,
+                        -0.0029985445667989547,
+                        -0.0024907408631406726,
+                        -0.14894675761461257,
+                        -0.0002731013679294847
+                    ],
+                    "q99": [
+                        1.5014824867248535,
+                        1.5016536712646484,
+                        1.404326802492144,
+                        1.5127789616584781,
+                        0.7817099303007136,
+                        1.872669064998627
+                    ]
+                },
+                "left_leg": {
+                    "max": [
+                        0.0,
+                        0.0,
+                        0.0,
+                        0.0,
+                        5.186659473110922e-05,
+                        0.0
+                    ],
+                    "min": [
+                        0.0,
+                        0.0,
+                        0.0,
+                        0.0,
+                        -2.446335656713927e-06,
+                        -1.6033794963732362e-05
+                    ],
+                    "mean": [
+                        0.0,
+                        0.0,
+                        0.0,
+                        0.0,
+                        7.68979953136295e-06,
+                        -2.6351963242632337e-06
+                    ],
+                    "std": [
+                        0.0,
+                        0.0,
+                        0.0,
+                        0.0,
+                        1.7361962818540633e-05,
+                        5.2996829253970645e-06
+                    ],
+                    "q01": [
+                        0.0,
+                        0.0,
+                        0.0,
+                        0.0,
+                        -2.446335656713927e-06,
+                        -1.6033794963732362e-05
+                    ],
+                    "q99": [
+                        0.0,
+                        0.0,
+                        0.0,
+                        0.0,
+                        5.186659473110922e-05,
+                        0.0
+                    ]
+                },
+                "neck": {
+                    "max": [
+                        0.01535311620682478,
+                        0.05556071177124977,
+                        0.008969387039542198
+                    ],
+                    "min": [
+                        -0.23586410284042358,
+                        -0.03865945711731911,
+                        -0.06754876673221588
+                    ],
+                    "mean": [
+                        -0.0008622645400464535,
+                        5.3951262088958174e-05,
+                        -0.00013521323853638023
+                    ],
+                    "std": [
+                        0.01196372415870428,
+                        0.0034790514037013054,
+                        0.0031053286511451006
+                    ],
+                    "q01": [
+                        -0.00492388429120183,
+                        -0.0027977502904832363,
+                        0.0
+                    ],
+                    "q99": [
+                        2.9924885893706232e-06,
+                        0.0002969176275655627,
+                        0.0
+                    ]
+                },
+                "right_arm": {
+                    "max": [
+                        1.7399436235427856,
+                        0.07876992970705032,
+                        2.5426626205444336,
+                        0.048908114433288574,
+                        3.000918388366699,
+                        1.4513440132141113,
+                        1.5000383853912354
+                    ],
+                    "min": [
+                        -2.2743337154388428,
+                        -2.999122142791748,
+                        -1.7424250841140747,
+                        -2.536545753479004,
+                        -2.6034910678863525,
+                        -1.5032434463500977,
+                        -1.4913568496704102
+                    ],
+                    "mean": [
+                        -0.1590277999639511,
+                        -0.2511773109436035,
+                        0.08599518239498138,
+                        -1.1420482397079468,
+                        0.21259814500808716,
+                        0.04237671568989754,
+                        0.03427042067050934
+                    ],
+                    "std": [
+                        0.563156247138977,
+                        0.24450603127479553,
+                        0.32825493812561035,
+                        0.7310536503791809,
+                        0.4813914895057678,
+                        0.35611921548843384,
+                        0.509053111076355
+                    ],
+                    "q01": [
+                        -1.423364037275314,
+                        -1.0436977982521056,
+                        -0.7169023394584656,
+                        -2.4936094284057613,
+                        -0.7377233326435089,
+                        -0.803617289662361,
+                        -0.9991738587617873
+                    ],
+                    "q99": [
+                        1.1677674055099487,
+                        0.0006303858070168663,
+                        0.8771779745817194,
+                        -0.0582109544426202,
+                        1.4707317113876357,
+                        0.8474899172782919,
+                        1.2271583080291748
+                    ]
+                },
+                "right_hand": {
+                    "max": [
+                        2.397510290145874,
+                        2.4422738552093506,
+                        3.0158462524414062,
+                        2.457378625869751,
+                        1.4605257511138916,
+                        2.168534278869629
+                    ],
+                    "min": [
+                        -1.7595213651657104,
+                        -1.8982670307159424,
+                        -1.8622381687164307,
+                        -1.8314869403839111,
+                        -1.0045679807662964,
+                        -0.31411829590797424
+                    ],
+                    "mean": [
+                        0.3499335348606109,
+                        0.3412855267524719,
+                        0.3271332383155823,
+                        0.357576698064804,
+                        0.09723818302154541,
+                        1.0641368627548218
+                    ],
+                    "std": [
+                        0.49147421121597296,
+                        0.4654525816440582,
+                        0.4451630115509033,
+                        0.48662698268890386,
+                        0.1814946085214615,
+                        0.5735033154487608
+                    ],
+                    "q01": [
+                        -0.004218762856908143,
+                        -0.004575904295779765,
+                        -0.005576773989014327,
+                        -0.004707079078070819,
+                        -0.18967307358980176,
+                        0.03200087323784828
+                    ],
+                    "q99": [
+                        1.4994217157363892,
+                        1.5029035806655884,
+                        1.661455136537552,
+                        1.5188306391239168,
+                        0.6953653633594525,
+                        1.8182492077350618
+                    ]
+                },
+                "right_leg": {
+                    "max": [
+                        0.0,
+                        0.0,
+                        0.0,
+                        0.0,
+                        5.369959126255708e-06,
+                        0.0
+                    ],
+                    "min": [
+                        0.0,
+                        0.0,
+                        0.0,
+                        0.0,
+                        -2.446335656713927e-06,
+                        -5.166131450096145e-05
+                    ],
+                    "mean": [
+                        0.0,
+                        0.0,
+                        0.0,
+                        0.0,
+                        8.152188684107387e-07,
+                        -7.940252544358373e-06
+                    ],
+                    "std": [
+                        0.0,
+                        0.0,
+                        0.0,
+                        0.0,
+                        1.92081461136695e-06,
+                        1.7361962818540633e-05
+                    ],
+                    "q01": [
+                        0.0,
+                        0.0,
+                        0.0,
+                        0.0,
+                        -2.446335656713927e-06,
+                        -5.1661314500961446e-05
+                    ],
+                    "q99": [
+                        0.0,
+                        0.0,
+                        0.0,
+                        0.0,
+                        5.369959126255708e-06,
+                        0.0
+                    ]
+                },
+                "waist": {
+                    "max": [
+                        1.0323854684829712,
+                        0.7102982997894287,
+                        0.43762317299842834
+                    ],
+                    "min": [
+                        -0.8131351470947266,
+                        -0.4901888370513916,
+                        -0.7304351925849915
+                    ],
+                    "mean": [
+                        0.014510802924633026,
+                        0.014398206025362015,
+                        -0.00020241182937752455
+                    ],
+                    "std": [
+                        0.12270263582468033,
+                        0.032448362559080124,
+                        0.00728295324370265
+                    ],
+                    "q01": [
+                        -0.33650725632905953,
+                        -0.0290498711168766,
+                        -0.026060330495238305
+                    ],
+                    "q99": [
+                        0.48663658648729347,
+                        0.12612193301320096,
+                        0.02228020317852497
+                    ]
+                }
+            },
+            "action": {
+                "left_arm": {
+                    "max": [
+                        1.4113223552703857,
+                        1.8901419639587402,
+                        1.7754145860671997,
+                        7.309383363462985e-05,
+                        2.563594102859497,
+                        1.5000243186950684,
+                        1.4908421039581299
+                    ],
+                    "min": [
+                        -2.291214942932129,
+                        -0.001746351015754044,
+                        -2.4999990463256836,
+                        -2.814260482788086,
+                        -2.3611011505126953,
+                        -1.4937989711761475,
+                        -1.4969758987426758
+                    ],
+                    "mean": [
+                        -0.17771673202514648,
+                        0.18351773917675016,
+                        -0.1372099369764328,
+                        -1.0842658281326294,
+                        0.14675945043563843,
+                        0.1292145699262619,
+                        -0.09504522383213042
+                    ],
+                    "std": [
+                        0.4174487590789795,
+                        0.18478454649448398,
+                        0.25687918066978455,
+                        0.5807053446769714,
+                        0.3365735411643982,
+                        0.2984270751476288,
+                        0.3153652846813202
+                    ],
+                    "q01": [
+                        -1.6055770933628082,
+                        -7.429541994952153e-07,
+                        -0.9837155520915983,
+                        -2.480029511451721,
+                        -0.9457575023174285,
+                        -0.7192997813224793,
+                        -1.008323037624359
+                    ],
+                    "q99": [
+                        0.6335921049118056,
+                        0.8018405169248584,
+                        0.39303458780050327,
+                        -0.0636610623449087,
+                        1.0508334636688232,
+                        0.8918659299612055,
+                        0.5138001590967183
+                    ]
+                },
+                "left_hand": {
+                    "max": [
+                        1.5707963705062866,
+                        1.646651268005371,
+                        1.709236979484558,
+                        2.0620639324188232,
+                        3.0,
+                        3.0
+                    ],
+                    "min": [
+                        -1.9597030878067017,
+                        -1.8635213375091553,
+                        -1.9709523916244507,
+                        -1.5,
+                        -3.0,
+                        0.0
+                    ],
+                    "mean": [
+                        -0.22721463441848755,
+                        -0.21956320106983185,
+                        -0.2144497036933899,
+                        -0.21446840465068817,
+                        -0.48631641268730164,
+                        1.6838233470916748
+                    ],
+                    "std": [
+                        1.0050891637802124,
+                        1.012416124343872,
+                        1.0138051509857178,
+                        1.020043969154358,
+                        2.066762685775757,
+                        1.4588384628295898
+                    ],
+                    "q01": [
+                        -1.5,
+                        -1.5,
+                        -1.5,
+                        -1.5,
+                        -3.0,
+                        0.0
+                    ],
+                    "q99": [
+                        1.5,
+                        1.5,
+                        1.5,
+                        1.5,
+                        3.0,
+                        3.0
+                    ]
+                },
+                "left_leg": {
+                    "max": [
+                        0.0,
+                        0.0,
+                        0.0,
+                        0.0,
+                        0.0,
+                        0.0
+                    ],
+                    "min": [
+                        0.0,
+                        0.0,
+                        0.0,
+                        0.0,
+                        0.0,
+                        0.0
+                    ],
+                    "mean": [
+                        0.0,
+                        0.0,
+                        0.0,
+                        0.0,
+                        0.0,
+                        0.0
+                    ],
+                    "std": [
+                        0.0,
+                        0.0,
+                        0.0,
+                        0.0,
+                        0.0,
+                        0.0
+                    ],
+                    "q01": [
+                        0.0,
+                        0.0,
+                        0.0,
+                        0.0,
+                        0.0,
+                        0.0
+                    ],
+                    "q99": [
+                        0.0,
+                        0.0,
+                        0.0,
+                        0.0,
+                        0.0,
+                        0.0
+                    ]
+                },
+                "neck": {
+                    "max": [
+                        0.0,
+                        0.0,
+                        0.0
+                    ],
+                    "min": [
+                        0.0,
+                        0.0,
+                        0.0
+                    ],
+                    "mean": [
+                        0.0,
+                        0.0,
+                        0.0
+                    ],
+                    "std": [
+                        0.0,
+                        0.0,
+                        0.0
+                    ],
+                    "q01": [
+                        0.0,
+                        0.0,
+                        0.0
+                    ],
+                    "q99": [
+                        0.0,
+                        0.0,
+                        0.0
+                    ]
+                },
+                "right_arm": {
+                    "max": [
+                        1.7834906578063965,
+                        0.0002448999439366162,
+                        2.549729585647583,
+                        7.45560391806066e-05,
+                        3.0000460147857666,
+                        1.4975632429122925,
+                        1.4998434782028198
+                    ],
+                    "min": [
+                        -2.318650960922241,
+                        -2.9999561309814453,
+                        -1.9257696866989136,
+                        -2.8759055137634277,
+                        -2.620600461959839,
+                        -1.5001521110534668,
+                        -1.4994292259216309
+                    ],
+                    "mean": [
+                        -0.16953834891319275,
+                        -0.2535267770290375,
+                        0.08221600204706192,
+                        -1.1492931842803955,
+                        0.21761417388916016,
+                        0.0431099571287632,
+                        0.041337188333272934
+                    ],
+                    "std": [
+                        0.5752111673355103,
+                        0.2584686279296875,
+                        0.341155469417572,
+                        0.7394758462905884,
+                        0.48707106709480286,
+                        0.3721199631690979,
+                        0.5423213839530945
+                    ],
+                    "q01": [
+                        -1.4375487387180328,
+                        -1.0682010412216187,
+                        -0.7535711079835892,
+                        -2.6383612155914307,
+                        -0.7471688866615296,
+                        -0.8604200631380081,
+                        -1.090039813518524
+                    ],
+                    "q99": [
+                        1.1753968834877018,
+                        -9.999999974752427e-07,
+                        0.8976036489009873,
+                        -0.05795218236744387,
+                        1.4876463234424593,
+                        0.877433916926385,
+                        1.464138692617417
+                    ]
+                },
+                "right_hand": {
+                    "max": [
+                        1.5707963705062866,
+                        1.7183797359466553,
+                        3.979951858520508,
+                        3.9879753589630127,
+                        3.0,
+                        3.0
+                    ],
+                    "min": [
+                        -1.5,
+                        -1.5,
+                        -1.5,
+                        -1.5,
+                        -3.0,
+                        4.470348358154297e-08
+                    ],
+                    "mean": [
+                        -0.5435706377029419,
+                        -0.5304322242736816,
+                        -0.5179098844528198,
+                        -0.4968528747558594,
+                        -1.1343770027160645,
+                        2.1282095909118652
+                    ],
+                    "std": [
+                        1.1248024702072144,
+                        1.1392076015472412,
+                        1.1426663398742676,
+                        1.3018625974655151,
+                        2.1998753547668457,
+                        0.9186902642250061
+                    ],
+                    "q01": [
+                        -1.5,
+                        -1.5,
+                        -1.5,
+                        -1.5,
+                        -3.0,
+                        0.0433624254539609
+                    ],
+                    "q99": [
+                        1.5,
+                        1.5,
+                        1.5,
+                        1.5,
+                        3.0,
+                        3.0
+                    ]
+                },
+                "right_leg": {
+                    "max": [
+                        0.0,
+                        0.0,
+                        0.0,
+                        0.0,
+                        0.0,
+                        0.0
+                    ],
+                    "min": [
+                        0.0,
+                        0.0,
+                        0.0,
+                        0.0,
+                        0.0,
+                        0.0
+                    ],
+                    "mean": [
+                        0.0,
+                        0.0,
+                        0.0,
+                        0.0,
+                        0.0,
+                        0.0
+                    ],
+                    "std": [
+                        0.0,
+                        0.0,
+                        0.0,
+                        0.0,
+                        0.0,
+                        0.0
+                    ],
+                    "q01": [
+                        0.0,
+                        0.0,
+                        0.0,
+                        0.0,
+                        0.0,
+                        0.0
+                    ],
+                    "q99": [
+                        0.0,
+                        0.0,
+                        0.0,
+                        0.0,
+                        0.0,
+                        0.0
+                    ]
+                },
+                "waist": {
+                    "max": [
+                        1.049119234085083,
+                        0.6198405623435974,
+                        0.45177245140075684
+                    ],
+                    "min": [
+                        -0.8292319774627686,
+                        -0.5185094475746155,
+                        -0.37811079621315
+                    ],
+                    "mean": [
+                        0.014836843125522135,
+                        0.01042813528329134,
+                        -0.00014937532250769436
+                    ],
+                    "std": [
+                        0.12568794190883636,
+                        0.030695030465722084,
+                        0.004574332851916552
+                    ],
+                    "q01": [
+                        -0.3402548208832741,
+                        -0.025130789913237094,
+                        -0.016220059804618357
+                    ],
+                    "q99": [
+                        0.4959896907210364,
+                        0.12137954644858845,
+                        0.010726323025301111
+                    ]
+                }
+            },
+            "total_trajectory_length": 63066032,
+            "num_trajectories": 226554
+        },
+        "modalities": {
+            "video": {
+                "ego_view": {
+                    "resolution": [
+                        256,
+                        256
+                    ],
+                    "channels": 3,
+                    "fps": 20.0
+                }
+            },
+            "state": {
+                "left_arm": {
+                    "absolute": true,
+                    "rotation_type": null,
+                    "shape": [
+                        7
+                    ],
+                    "continuous": true
+                },
+                "left_hand": {
+                    "absolute": true,
+                    "rotation_type": null,
+                    "shape": [
+                        6
+                    ],
+                    "continuous": true
+                },
+                "left_leg": {
+                    "absolute": true,
+                    "rotation_type": null,
+                    "shape": [
+                        6
+                    ],
+                    "continuous": true
+                },
+                "neck": {
+                    "absolute": true,
+                    "rotation_type": null,
+                    "shape": [
+                        3
+                    ],
+                    "continuous": true
+                },
+                "right_arm": {
+                    "absolute": true,
+                    "rotation_type": null,
+                    "shape": [
+                        7
+                    ],
+                    "continuous": true
+                },
+                "right_hand": {
+                    "absolute": true,
+                    "rotation_type": null,
+                    "shape": [
+                        6
+                    ],
+                    "continuous": true
+                },
+                "right_leg": {
+                    "absolute": true,
+                    "rotation_type": null,
+                    "shape": [
+                        6
+                    ],
+                    "continuous": true
+                },
+                "waist": {
+                    "absolute": true,
+                    "rotation_type": null,
+                    "shape": [
+                        3
+                    ],
+                    "continuous": true
+                }
+            },
+            "action": {
+                "left_arm": {
+                    "absolute": true,
+                    "rotation_type": null,
+                    "shape": [
+                        7
+                    ],
+                    "continuous": true
+                },
+                "left_hand": {
+                    "absolute": true,
+                    "rotation_type": null,
+                    "shape": [
+                        6
+                    ],
+                    "continuous": true
+                },
+                "left_leg": {
+                    "absolute": true,
+                    "rotation_type": null,
+                    "shape": [
+                        6
+                    ],
+                    "continuous": true
+                },
+                "neck": {
+                    "absolute": true,
+                    "rotation_type": null,
+                    "shape": [
+                        3
+                    ],
+                    "continuous": true
+                },
+                "right_arm": {
+                    "absolute": true,
+                    "rotation_type": null,
+                    "shape": [
+                        7
+                    ],
+                    "continuous": true
+                },
+                "right_hand": {
+                    "absolute": true,
+                    "rotation_type": null,
+                    "shape": [
+                        6
+                    ],
+                    "continuous": true
+                },
+                "right_leg": {
+                    "absolute": true,
+                    "rotation_type": null,
+                    "shape": [
+                        6
+                    ],
+                    "continuous": true
+                },
+                "waist": {
+                    "absolute": true,
+                    "rotation_type": null,
+                    "shape": [
+                        3
+                    ],
+                    "continuous": true
+                }
+            },
+            "annotation": {
+                "human": [
+                    "action.verb",
+                    "action.object",
+                    "action.start_location",
+                    "action.end_location",
+                    "action.hand",
+                    "action.rating",
+                    "action.failure_code",
+                    "action.remarks",
+                    "coarse_action",
+                    "fine_action",
+                    "validity"
+                ]
+            }
+        },
+        "embodiment": {
+            "robot_name": "gr00t004, gr00t001, gr00t003, gr00t005, gr00t006, gr00t007",
+            "robot_type": "GR1T2, GR1T1, GR1T2, GR1T2, GR1T2, GR1T2",
+            "record_frequency": 20.0,
+            "body_controller_frequency": 120.0,
+            "hand_controller_frequency": 40.0,
+            "embodiment_tag": "gr1_unified"
+        },
+        "processing": null,
+        "version": null
+    }
+}

global_step60000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6498a18f5a01c89992c29d24d03e7aa72fe5354193604ee91ae3e5fa54fed53
+size 918308912

global_step60000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f6c2692203262082568739dbfe1eb921f1e8430f8fdc57a2d6685e249016fdd
+size 918308592

global_step60000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b571564bc648751daa672016900ee8c4f5bbf5960fded0a4c38cd389140c8735
+size 918308976

global_step60000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b83dbbdcd9eca607e147f0c9fc6ea248693b95e5e441f23a84226649c2272b4
+size 918308592

global_step60000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c6b1b4a4d5176bf748dc25c3b8a4329c61415b49685736e8b1c7b630f26e980
+size 918308144

global_step60000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5fda8acc1148643c7df260a2360ebe9f357266ba421558d6defef379ead74eb1
+size 918307184

global_step60000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:343eccd3a900e86095d99b3251ce7ba72737aca749e64275f0a37786652d47a2
+size 918303664

global_step60000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e44e6313aca11f286d65a5ff8a8beb3405aa12528830907c52057e3321c73c8a
+size 918304048

global_step60000/mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5275e187ae20f381d3f6a18cbaf518cfd2eda8c3ef1d3a6da873d970087a8e33
+size 1325387042

latest

@@ -0,0 +1 @@
+global_step60000

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:575aba6acf8b14462410688cddd9e4f023f096d0c97a768b1ec16368aa92f298
+size 1274863076

rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eafc2a4bb1f9d7dba9475ca28e61e1105bd48e4459b071d3ed0d1b76aa1c261a
+size 15984

rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:821ac307cd326308bdbf3bf8c0b0e3fd1f12261d3d391b719e82107f7e0e3f77
+size 15984

rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9906bf1ffc05c9593c09f68867cd9688c751a91b4ea3b87ec32ccc6ec5e45c6c
+size 15984

rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d570d2f204a2b93b4562bbe0bb40b0dbaad7ef740ac66c70d32bfdf4b0b589b
+size 15984

rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6955b3cceacd7bb106d6567a2744ea608765afc4b447e9b8a2fb08fd33a18b0c
+size 15984

rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df6c0417c7e490e0a662efd9d65c50a17fce6d4bab92da3f2bfc83d156d4b82c
+size 15984

rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13191fd984b806d00370ac2e2290a08d7d0acd6e7efd224395a06260642dc9e0
+size 15984

rng_state_7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7865bc20171325a58c9418fbdce6222a60c3af36414cc9383cde59312fa2c3f9
+size 15984

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb677b69d5815e7e1f5f341ea75c4bd0f7789a7a85a36e672ade3f744edffa5f
+size 1064

trainer_state.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01ed6037a3d44bff78f5206941cb323b77a67cb7d2a69395c61abb9b801275e0
+size 14954652

zero_to_fp32.py

@@ -0,0 +1,604 @@
+#!/usr/bin/env python
+
+# Copyright (c) Microsoft Corporation.
+# SPDX-License-Identifier: Apache-2.0
+
+# DeepSpeed Team
+
+# This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets
+# copied into the top level checkpoint dir, so the user can easily do the conversion at any point in
+# the future. Once extracted, the weights don't require DeepSpeed and can be used in any
+# application.
+#
+# example: python zero_to_fp32.py . pytorch_model.bin
+
+import argparse
+import torch
+import glob
+import math
+import os
+import re
+from collections import OrderedDict
+from dataclasses import dataclass
+
+# while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
+# DeepSpeed data structures it has to be available in the current python environment.
+from deepspeed.utils import logger
+from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
+                                            FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
+                                            FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
+
+
+@dataclass
+class zero_model_state:
+    buffers: dict()
+    param_shapes: dict()
+    shared_params: list
+    ds_version: int
+    frozen_param_shapes: dict()
+    frozen_param_fragments: dict()
+
+
+debug = 0
+
+# load to cpu
+device = torch.device('cpu')
+
+
+def atoi(text):
+    return int(text) if text.isdigit() else text
+
+
+def natural_keys(text):
+    '''
+    alist.sort(key=natural_keys) sorts in human order
+    http://nedbatchelder.com/blog/200712/human_sorting.html
+    (See Toothy's implementation in the comments)
+    '''
+    return [atoi(c) for c in re.split(r'(\d+)', text)]
+
+
+def get_model_state_file(checkpoint_dir, zero_stage):
+    if not os.path.isdir(checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
+
+    # there should be only one file
+    if zero_stage <= 2:
+        file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
+    elif zero_stage == 3:
+        file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
+
+    if not os.path.exists(file):
+        raise FileNotFoundError(f"can't find model states file at '{file}'")
+
+    return file
+
+
+def get_checkpoint_files(checkpoint_dir, glob_pattern):
+    # XXX: need to test that this simple glob rule works for multi-node setup too
+    ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
+
+    if len(ckpt_files) == 0:
+        raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
+
+    return ckpt_files
+
+
+def get_optim_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
+
+
+def get_model_state_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
+
+
+def parse_model_states(files):
+    zero_model_states = []
+    for file in files:
+        state_dict = torch.load(file, map_location=device)
+
+        if BUFFER_NAMES not in state_dict:
+            raise ValueError(f"{file} is not a model state checkpoint")
+        buffer_names = state_dict[BUFFER_NAMES]
+        if debug:
+            print("Found buffers:", buffer_names)
+
+        # recover just the buffers while restoring them to fp32 if they were saved in fp16
+        buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
+        param_shapes = state_dict[PARAM_SHAPES]
+
+        # collect parameters that are included in param_shapes
+        param_names = []
+        for s in param_shapes:
+            for name in s.keys():
+                param_names.append(name)
+
+        # update with frozen parameters
+        frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
+        if frozen_param_shapes is not None:
+            if debug:
+                print(f"Found frozen_param_shapes: {frozen_param_shapes}")
+            param_names += list(frozen_param_shapes.keys())
+
+        # handle shared params
+        shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
+
+        ds_version = state_dict.get(DS_VERSION, None)
+
+        frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
+
+        z_model_state = zero_model_state(buffers=buffers,
+                                         param_shapes=param_shapes,
+                                         shared_params=shared_params,
+                                         ds_version=ds_version,
+                                         frozen_param_shapes=frozen_param_shapes,
+                                         frozen_param_fragments=frozen_param_fragments)
+        zero_model_states.append(z_model_state)
+
+    return zero_model_states
+
+
+def parse_optim_states(files, ds_checkpoint_dir):
+
+    total_files = len(files)
+    state_dicts = []
+    for f in files:
+        state_dict = torch.load(f, map_location=device)
+        # immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights
+        # and also handle the case where it was already removed by another helper script
+        state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None)
+        state_dicts.append(state_dict)
+
+    if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]:
+        raise ValueError(f"{files[0]} is not a zero checkpoint")
+    zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
+    world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
+
+    # For ZeRO-2 each param group can have different partition_count as data parallelism for expert
+    # parameters can be different from data parallelism for non-expert parameters. So we can just
+    # use the max of the partition_count to get the dp world_size.
+
+    if type(world_size) is list:
+        world_size = max(world_size)
+
+    if world_size != total_files:
+        raise ValueError(
+            f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
+            "Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
+        )
+
+    # the groups are named differently in each stage
+    if zero_stage <= 2:
+        fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
+    elif zero_stage == 3:
+        fp32_groups_key = FP32_FLAT_GROUPS
+    else:
+        raise ValueError(f"unknown zero stage {zero_stage}")
+
+    if zero_stage <= 2:
+        fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
+    elif zero_stage == 3:
+        # if there is more than one param group, there will be multiple flattened tensors - one
+        # flattened tensor per group - for simplicity merge them into a single tensor
+        #
+        # XXX: could make the script more memory efficient for when there are multiple groups - it
+        # will require matching the sub-lists of param_shapes for each param group flattened tensor
+
+        fp32_flat_groups = [
+            torch.cat(state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key], 0) for i in range(len(state_dicts))
+        ]
+
+    return zero_stage, world_size, fp32_flat_groups
+
+
+def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters):
+    """
+    Returns fp32 state_dict reconstructed from ds checkpoint
+
+    Args:
+        - ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
+
+    """
+    print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
+
+    optim_files = get_optim_files(ds_checkpoint_dir)
+    zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
+    print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
+
+    model_files = get_model_state_files(ds_checkpoint_dir)
+
+    zero_model_states = parse_model_states(model_files)
+    print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
+
+    if zero_stage <= 2:
+        return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                                          exclude_frozen_parameters)
+    elif zero_stage == 3:
+        return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                                          exclude_frozen_parameters)
+
+
+def _zero2_merge_frozen_params(state_dict, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+    frozen_param_fragments = zero_model_states[0].frozen_param_fragments
+
+    if debug:
+        num_elem = sum(s.numel() for s in frozen_param_shapes.values())
+        print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        state_dict[name] = frozen_param_fragments[name]
+
+        if debug:
+            print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _has_callable(obj, fn):
+    attr = getattr(obj, fn, None)
+    return callable(attr)
+
+
+def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+
+    # Reconstruction protocol:
+    #
+    # XXX: document this
+
+    if debug:
+        for i in range(world_size):
+            for j in range(len(fp32_flat_groups[0])):
+                print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
+
+    # XXX: memory usage doubles here (zero2)
+    num_param_groups = len(fp32_flat_groups[0])
+    merged_single_partition_of_fp32_groups = []
+    for i in range(num_param_groups):
+        merged_partitions = [sd[i] for sd in fp32_flat_groups]
+        full_single_fp32_vector = torch.cat(merged_partitions, 0)
+        merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
+    avail_numel = sum(
+        [full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
+
+    if debug:
+        wanted_params = sum([len(shapes) for shapes in param_shapes])
+        wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
+        # not asserting if there is a mismatch due to possible padding
+        print(f"Have {avail_numel} numels to process.")
+        print(f"Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    total_numel = 0
+    total_params = 0
+    for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
+        offset = 0
+        avail_numel = full_single_fp32_vector.numel()
+        for name, shape in shapes.items():
+
+            unpartitioned_numel = shape.numel() if _has_callable(shape, 'numel') else math.prod(shape)
+            total_numel += unpartitioned_numel
+            total_params += 1
+
+            if debug:
+                print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+            state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
+            offset += unpartitioned_numel
+
+        # Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
+        # avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
+        # paddings performed in the code it's almost impossible to predict the exact numbers w/o the
+        # live optimizer object, so we are checking that the numbers are within the right range
+        align_to = 2 * world_size
+
+        def zero2_align(x):
+            return align_to * math.ceil(x / align_to)
+
+        if debug:
+            print(f"original offset={offset}, avail_numel={avail_numel}")
+
+        offset = zero2_align(offset)
+        avail_numel = zero2_align(avail_numel)
+
+        if debug:
+            print(f"aligned  offset={offset}, avail_numel={avail_numel}")
+
+        # Sanity check
+        if offset != avail_numel:
+            raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                               exclude_frozen_parameters):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    if not exclude_frozen_parameters:
+        _zero2_merge_frozen_params(state_dict, zero_model_states)
+
+    _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def zero3_partitioned_param_info(unpartitioned_numel, world_size):
+    remainder = unpartitioned_numel % world_size
+    padding_numel = (world_size - remainder) if remainder else 0
+    partitioned_numel = math.ceil(unpartitioned_numel / world_size)
+    return partitioned_numel, padding_numel
+
+
+def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    if debug:
+        for i in range(world_size):
+            num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
+            print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in zero_model_states[0].frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
+        state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
+
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+    avail_numel = fp32_flat_groups[0].numel() * world_size
+    # Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
+    # param, re-consolidating each param, while dealing with padding if any
+
+    # merge list of dicts, preserving order
+    param_shapes = {k: v for d in param_shapes for k, v in d.items()}
+
+    if debug:
+        for i in range(world_size):
+            print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
+
+        wanted_params = len(param_shapes)
+        wanted_numel = sum(shape.numel() for shape in param_shapes.values())
+        # not asserting if there is a mismatch due to possible padding
+        avail_numel = fp32_flat_groups[0].numel() * world_size
+        print(f"Trainable params: Have {avail_numel} numels to process.")
+        print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    offset = 0
+    total_numel = 0
+    total_params = 0
+    for name, shape in param_shapes.items():
+
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+        total_params += 1
+
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+        # XXX: memory usage doubles here
+        state_dict[name] = torch.cat(
+            tuple(fp32_flat_groups[i].narrow(0, offset, partitioned_numel) for i in range(world_size)),
+            0).narrow(0, 0, unpartitioned_numel).view(shape)
+        offset += partitioned_numel
+
+    offset *= world_size
+
+    # Sanity check
+    if offset != avail_numel:
+        raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                               exclude_frozen_parameters):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    if not exclude_frozen_parameters:
+        _zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
+
+    _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag=None, exclude_frozen_parameters=False):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
+    ``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
+    via a model hub.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14``
+        - ``exclude_frozen_parameters``: exclude frozen parameters
+
+    Returns:
+        - pytorch ``state_dict``
+
+    Note: this approach may not work if your application doesn't have sufficient free CPU memory and
+    you may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
+    the checkpoint.
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
+        # do the training and checkpoint saving
+        state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
+        model = model.cpu() # move to cpu
+        model.load_state_dict(state_dict)
+        # submit to model hub or save the model to share with others
+
+    In this example the ``model`` will no longer be usable in the deepspeed context of the same
+    application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
+
+    """
+    if tag is None:
+        latest_path = os.path.join(checkpoint_dir, 'latest')
+        if os.path.isfile(latest_path):
+            with open(latest_path, 'r') as fd:
+                tag = fd.read().strip()
+        else:
+            raise ValueError(f"Unable to find 'latest' file at {latest_path}")
+
+    ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
+
+    if not os.path.isdir(ds_checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
+
+    return _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters)
+
+
+def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir, output_file, tag=None, exclude_frozen_parameters=False):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
+    loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``output_file``: path to the pytorch fp32 state_dict output file (e.g. path/pytorch_model.bin)
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+        - ``exclude_frozen_parameters``: exclude frozen parameters
+    """
+
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag, exclude_frozen_parameters)
+    print(f"Saving fp32 state dict to {output_file}")
+    torch.save(state_dict, output_file)
+
+
+def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
+    """
+    1. Put the provided model to cpu
+    2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
+    3. Load it into the provided model
+
+    Args:
+        - ``model``: the model object to update
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+
+    Returns:
+        - ``model`: modified model
+
+    Make sure you have plenty of CPU memory available before you call this function. If you don't
+    have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
+    conveniently placed for you in the checkpoint folder.
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
+        model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
+        # submit to model hub or save the model to share with others
+
+    Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
+    of the same application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    """
+    logger.info(f"Extracting fp32 weights")
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
+
+    logger.info(f"Overwriting model with fp32 weights")
+    model = model.cpu()
+    model.load_state_dict(state_dict, strict=False)
+
+    return model
+
+
+if __name__ == "__main__":
+
+    parser = argparse.ArgumentParser()
+    parser.add_argument("checkpoint_dir",
+                        type=str,
+                        help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
+    parser.add_argument(
+        "output_file",
+        type=str,
+        help="path to the pytorch fp32 state_dict output file (e.g. path/checkpoint-12/pytorch_model.bin)")
+    parser.add_argument("-t",
+                        "--tag",
+                        type=str,
+                        default=None,
+                        help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1")
+    parser.add_argument("--exclude_frozen_parameters", action='store_true', help="exclude frozen parameters")
+    parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
+    args = parser.parse_args()
+
+    debug = args.debug
+
+    convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir,
+                                               args.output_file,
+                                               tag=args.tag,
+                                               exclude_frozen_parameters=args.exclude_frozen_parameters)