Upload folder using huggingface_hub
Browse files
checkpoint-1000/config.json
ADDED
|
@@ -0,0 +1,64 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"action_dim": 32,
|
| 3 |
+
"action_head_cfg": {
|
| 4 |
+
"action_dim": 32,
|
| 5 |
+
"action_horizon": 16,
|
| 6 |
+
"add_pos_embed": true,
|
| 7 |
+
"backbone_embedding_dim": 2048,
|
| 8 |
+
"diffusion_model_cfg": {
|
| 9 |
+
"attention_head_dim": 48,
|
| 10 |
+
"cross_attention_dim": 2048,
|
| 11 |
+
"dropout": 0.2,
|
| 12 |
+
"final_dropout": true,
|
| 13 |
+
"interleave_self_attention": true,
|
| 14 |
+
"norm_type": "ada_norm",
|
| 15 |
+
"num_attention_heads": 32,
|
| 16 |
+
"num_layers": 16,
|
| 17 |
+
"output_dim": 1024,
|
| 18 |
+
"positional_embeddings": null
|
| 19 |
+
},
|
| 20 |
+
"hidden_size": 1024,
|
| 21 |
+
"input_embedding_dim": 1536,
|
| 22 |
+
"max_action_dim": 32,
|
| 23 |
+
"max_state_dim": 64,
|
| 24 |
+
"model_dtype": "float32",
|
| 25 |
+
"noise_beta_alpha": 1.5,
|
| 26 |
+
"noise_beta_beta": 1.0,
|
| 27 |
+
"noise_s": 0.999,
|
| 28 |
+
"num_inference_timesteps": 4,
|
| 29 |
+
"num_target_vision_tokens": 32,
|
| 30 |
+
"num_timestep_buckets": 1000,
|
| 31 |
+
"tune_diffusion_model": true,
|
| 32 |
+
"tune_projector": true,
|
| 33 |
+
"use_vlln": true,
|
| 34 |
+
"vl_self_attention_cfg": {
|
| 35 |
+
"attention_head_dim": 64,
|
| 36 |
+
"dropout": 0.2,
|
| 37 |
+
"final_dropout": true,
|
| 38 |
+
"num_attention_heads": 32,
|
| 39 |
+
"num_layers": 4,
|
| 40 |
+
"positional_embeddings": null
|
| 41 |
+
}
|
| 42 |
+
},
|
| 43 |
+
"action_horizon": 16,
|
| 44 |
+
"architectures": [
|
| 45 |
+
"GR00T_N1_5"
|
| 46 |
+
],
|
| 47 |
+
"attn_implementation": null,
|
| 48 |
+
"backbone_cfg": {
|
| 49 |
+
"eagle_path": "NVEagle/eagle_er-qwen3_1_7B-Siglip2_400M_stage1_5_128gpu_er_v7_1mlp_nops",
|
| 50 |
+
"load_bf16": false,
|
| 51 |
+
"project_to_dim": null,
|
| 52 |
+
"reproject_vision": false,
|
| 53 |
+
"select_layer": 12,
|
| 54 |
+
"tune_llm": false,
|
| 55 |
+
"tune_visual": true,
|
| 56 |
+
"use_flash_attention": true
|
| 57 |
+
},
|
| 58 |
+
"compute_dtype": "bfloat16",
|
| 59 |
+
"hidden_size": 2048,
|
| 60 |
+
"model_dtype": "float32",
|
| 61 |
+
"model_type": "gr00t_n1_5",
|
| 62 |
+
"torch_dtype": "bfloat16",
|
| 63 |
+
"transformers_version": "4.51.3"
|
| 64 |
+
}
|
checkpoint-1000/model-00001-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:acc3a805d4a6999b1e2a6f05a21ef6b4cad16219ab05b4e981de802fb1f85aac
|
| 3 |
+
size 4999367032
|
checkpoint-1000/model-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:04e3200e06fa393b4629263d685bc15df35e54f46470595e03667085fe25ee7a
|
| 3 |
+
size 1348059136
|
experiment_cfg/metadata.json
ADDED
|
@@ -0,0 +1,355 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"new_embodiment": {
|
| 3 |
+
"statistics": {
|
| 4 |
+
"state": {
|
| 5 |
+
"left_arm": {
|
| 6 |
+
"max": [
|
| 7 |
+
34.16289520263672,
|
| 8 |
+
61.91222381591797,
|
| 9 |
+
99.38703918457031,
|
| 10 |
+
75.7874755859375,
|
| 11 |
+
46.27594757080078
|
| 12 |
+
],
|
| 13 |
+
"min": [
|
| 14 |
+
-27.90346908569336,
|
| 15 |
+
-99.60814666748047,
|
| 16 |
+
-33.27495574951172,
|
| 17 |
+
-88.31119537353516,
|
| 18 |
+
-66.83760833740234
|
| 19 |
+
],
|
| 20 |
+
"mean": [
|
| 21 |
+
-1.3637042045593262,
|
| 22 |
+
-70.07746124267578,
|
| 23 |
+
81.53594970703125,
|
| 24 |
+
46.74204635620117,
|
| 25 |
+
-32.77935791015625
|
| 26 |
+
],
|
| 27 |
+
"std": [
|
| 28 |
+
10.373152732849121,
|
| 29 |
+
52.60585021972656,
|
| 30 |
+
34.18480682373047,
|
| 31 |
+
48.48912811279297,
|
| 32 |
+
37.322959899902344
|
| 33 |
+
],
|
| 34 |
+
"q01": [
|
| 35 |
+
-22.021116256713867,
|
| 36 |
+
-99.52977752685547,
|
| 37 |
+
-18.82662010192871,
|
| 38 |
+
-66.29981231689453,
|
| 39 |
+
-58.38827896118164
|
| 40 |
+
],
|
| 41 |
+
"q99": [
|
| 42 |
+
26.69683265686035,
|
| 43 |
+
51.0971794128418,
|
| 44 |
+
98.94921112060547,
|
| 45 |
+
74.72486114501953,
|
| 46 |
+
45.88522720336914
|
| 47 |
+
]
|
| 48 |
+
},
|
| 49 |
+
"gripper1": {
|
| 50 |
+
"max": [
|
| 51 |
+
71.77835083007812
|
| 52 |
+
],
|
| 53 |
+
"min": [
|
| 54 |
+
0.0
|
| 55 |
+
],
|
| 56 |
+
"mean": [
|
| 57 |
+
10.566564559936523
|
| 58 |
+
],
|
| 59 |
+
"std": [
|
| 60 |
+
10.46413803100586
|
| 61 |
+
],
|
| 62 |
+
"q01": [
|
| 63 |
+
0.4510309398174286
|
| 64 |
+
],
|
| 65 |
+
"q99": [
|
| 66 |
+
56.572166442871094
|
| 67 |
+
]
|
| 68 |
+
},
|
| 69 |
+
"right_arm": {
|
| 70 |
+
"max": [
|
| 71 |
+
31.229597091674805,
|
| 72 |
+
73.70741271972656,
|
| 73 |
+
98.10017395019531,
|
| 74 |
+
84.24878692626953,
|
| 75 |
+
41.3212776184082
|
| 76 |
+
],
|
| 77 |
+
"min": [
|
| 78 |
+
-27.022125244140625,
|
| 79 |
+
-97.75550842285156,
|
| 80 |
+
-63.21243667602539,
|
| 81 |
+
-96.60742950439453,
|
| 82 |
+
-65.18462371826172
|
| 83 |
+
],
|
| 84 |
+
"mean": [
|
| 85 |
+
-1.5135765075683594,
|
| 86 |
+
-25.33967399597168,
|
| 87 |
+
61.376529693603516,
|
| 88 |
+
0.33546876907348633,
|
| 89 |
+
-41.29887390136719
|
| 90 |
+
],
|
| 91 |
+
"std": [
|
| 92 |
+
12.458887100219727,
|
| 93 |
+
60.93878936767578,
|
| 94 |
+
35.7954216003418,
|
| 95 |
+
60.31285858154297,
|
| 96 |
+
23.256187438964844
|
| 97 |
+
],
|
| 98 |
+
"q01": [
|
| 99 |
+
-22.887195587158203,
|
| 100 |
+
-97.51502990722656,
|
| 101 |
+
-18.134714126586914,
|
| 102 |
+
-95.5573501586914,
|
| 103 |
+
-57.9000244140625
|
| 104 |
+
],
|
| 105 |
+
"q99": [
|
| 106 |
+
28.61806297302246,
|
| 107 |
+
63.446895599365234,
|
| 108 |
+
97.84110260009766,
|
| 109 |
+
73.2633285522461,
|
| 110 |
+
29.41472053527832
|
| 111 |
+
]
|
| 112 |
+
},
|
| 113 |
+
"gripper2": {
|
| 114 |
+
"max": [
|
| 115 |
+
75.05668640136719
|
| 116 |
+
],
|
| 117 |
+
"min": [
|
| 118 |
+
2.324263095855713
|
| 119 |
+
],
|
| 120 |
+
"mean": [
|
| 121 |
+
23.147193908691406
|
| 122 |
+
],
|
| 123 |
+
"std": [
|
| 124 |
+
13.153349876403809
|
| 125 |
+
],
|
| 126 |
+
"q01": [
|
| 127 |
+
2.551020383834839
|
| 128 |
+
],
|
| 129 |
+
"q99": [
|
| 130 |
+
61.621315002441406
|
| 131 |
+
]
|
| 132 |
+
}
|
| 133 |
+
},
|
| 134 |
+
"action": {
|
| 135 |
+
"left_arm": {
|
| 136 |
+
"max": [
|
| 137 |
+
35.92695617675781,
|
| 138 |
+
62.01413345336914,
|
| 139 |
+
100.0,
|
| 140 |
+
76.97608184814453,
|
| 141 |
+
46.617828369140625
|
| 142 |
+
],
|
| 143 |
+
"min": [
|
| 144 |
+
-28.066692352294922,
|
| 145 |
+
-100.0,
|
| 146 |
+
-35.07326126098633,
|
| 147 |
+
-89.78516387939453,
|
| 148 |
+
-67.17948913574219
|
| 149 |
+
],
|
| 150 |
+
"mean": [
|
| 151 |
+
-1.1567177772521973,
|
| 152 |
+
-70.6091537475586,
|
| 153 |
+
82.1029281616211,
|
| 154 |
+
47.767425537109375,
|
| 155 |
+
-32.80006408691406
|
| 156 |
+
],
|
| 157 |
+
"std": [
|
| 158 |
+
10.52210521697998,
|
| 159 |
+
52.541717529296875,
|
| 160 |
+
35.224395751953125,
|
| 161 |
+
49.508544921875,
|
| 162 |
+
37.26472473144531
|
| 163 |
+
],
|
| 164 |
+
"q01": [
|
| 165 |
+
-21.873760223388672,
|
| 166 |
+
-100.0,
|
| 167 |
+
-20.238094329833984,
|
| 168 |
+
-66.76124572753906,
|
| 169 |
+
-58.43711853027344
|
| 170 |
+
],
|
| 171 |
+
"q99": [
|
| 172 |
+
27.669710159301758,
|
| 173 |
+
50.230565567016654,
|
| 174 |
+
100.0,
|
| 175 |
+
76.97608184814453,
|
| 176 |
+
45.738704681396484
|
| 177 |
+
]
|
| 178 |
+
},
|
| 179 |
+
"gripper1": {
|
| 180 |
+
"max": [
|
| 181 |
+
74.2166519165039
|
| 182 |
+
],
|
| 183 |
+
"min": [
|
| 184 |
+
0.0
|
| 185 |
+
],
|
| 186 |
+
"mean": [
|
| 187 |
+
10.451210021972656
|
| 188 |
+
],
|
| 189 |
+
"std": [
|
| 190 |
+
10.781113624572754
|
| 191 |
+
],
|
| 192 |
+
"q01": [
|
| 193 |
+
0.08952551335096359
|
| 194 |
+
],
|
| 195 |
+
"q99": [
|
| 196 |
+
56.938228607177734
|
| 197 |
+
]
|
| 198 |
+
},
|
| 199 |
+
"right_arm": {
|
| 200 |
+
"max": [
|
| 201 |
+
31.447315216064453,
|
| 202 |
+
72.47631072998047,
|
| 203 |
+
99.20035552978516,
|
| 204 |
+
85.42713928222656,
|
| 205 |
+
42.69340896606445
|
| 206 |
+
],
|
| 207 |
+
"min": [
|
| 208 |
+
-27.511274337768555,
|
| 209 |
+
-99.25834655761719,
|
| 210 |
+
-67.30342102050781,
|
| 211 |
+
-98.40870666503906,
|
| 212 |
+
-66.81427764892578
|
| 213 |
+
],
|
| 214 |
+
"mean": [
|
| 215 |
+
-1.471267580986023,
|
| 216 |
+
-26.692821502685547,
|
| 217 |
+
60.74913787841797,
|
| 218 |
+
0.23357370495796204,
|
| 219 |
+
-41.19910430908203
|
| 220 |
+
],
|
| 221 |
+
"std": [
|
| 222 |
+
12.504396438598633,
|
| 223 |
+
60.0944709777832,
|
| 224 |
+
36.86882400512695,
|
| 225 |
+
60.7491340637207,
|
| 226 |
+
23.23846435546875
|
| 227 |
+
],
|
| 228 |
+
"q01": [
|
| 229 |
+
-23.001230239868164,
|
| 230 |
+
-97.692626953125,
|
| 231 |
+
-19.68014144897461,
|
| 232 |
+
-96.31491088867188,
|
| 233 |
+
-57.749412536621094
|
| 234 |
+
],
|
| 235 |
+
"q99": [
|
| 236 |
+
28.823287963867188,
|
| 237 |
+
62.34033966064453,
|
| 238 |
+
98.57840728759766,
|
| 239 |
+
74.03684997558594,
|
| 240 |
+
29.721281051635742
|
| 241 |
+
]
|
| 242 |
+
},
|
| 243 |
+
"gripper2": {
|
| 244 |
+
"max": [
|
| 245 |
+
77.73826599121094
|
| 246 |
+
],
|
| 247 |
+
"min": [
|
| 248 |
+
0.4267425239086151
|
| 249 |
+
],
|
| 250 |
+
"mean": [
|
| 251 |
+
21.515247344970703
|
| 252 |
+
],
|
| 253 |
+
"std": [
|
| 254 |
+
14.212292671203613
|
| 255 |
+
],
|
| 256 |
+
"q01": [
|
| 257 |
+
1.8492176532745361
|
| 258 |
+
],
|
| 259 |
+
"q99": [
|
| 260 |
+
61.87766647338867
|
| 261 |
+
]
|
| 262 |
+
}
|
| 263 |
+
}
|
| 264 |
+
},
|
| 265 |
+
"modalities": {
|
| 266 |
+
"video": {
|
| 267 |
+
"right": {
|
| 268 |
+
"resolution": [
|
| 269 |
+
640,
|
| 270 |
+
480
|
| 271 |
+
],
|
| 272 |
+
"channels": 3,
|
| 273 |
+
"fps": 30.0
|
| 274 |
+
},
|
| 275 |
+
"top_rgb": {
|
| 276 |
+
"resolution": [
|
| 277 |
+
640,
|
| 278 |
+
480
|
| 279 |
+
],
|
| 280 |
+
"channels": 3,
|
| 281 |
+
"fps": 30.0
|
| 282 |
+
}
|
| 283 |
+
},
|
| 284 |
+
"state": {
|
| 285 |
+
"left_arm": {
|
| 286 |
+
"absolute": true,
|
| 287 |
+
"rotation_type": null,
|
| 288 |
+
"shape": [
|
| 289 |
+
5
|
| 290 |
+
],
|
| 291 |
+
"continuous": true
|
| 292 |
+
},
|
| 293 |
+
"gripper1": {
|
| 294 |
+
"absolute": true,
|
| 295 |
+
"rotation_type": null,
|
| 296 |
+
"shape": [
|
| 297 |
+
1
|
| 298 |
+
],
|
| 299 |
+
"continuous": true
|
| 300 |
+
},
|
| 301 |
+
"right_arm": {
|
| 302 |
+
"absolute": true,
|
| 303 |
+
"rotation_type": null,
|
| 304 |
+
"shape": [
|
| 305 |
+
5
|
| 306 |
+
],
|
| 307 |
+
"continuous": true
|
| 308 |
+
},
|
| 309 |
+
"gripper2": {
|
| 310 |
+
"absolute": true,
|
| 311 |
+
"rotation_type": null,
|
| 312 |
+
"shape": [
|
| 313 |
+
1
|
| 314 |
+
],
|
| 315 |
+
"continuous": true
|
| 316 |
+
}
|
| 317 |
+
},
|
| 318 |
+
"action": {
|
| 319 |
+
"left_arm": {
|
| 320 |
+
"absolute": true,
|
| 321 |
+
"rotation_type": null,
|
| 322 |
+
"shape": [
|
| 323 |
+
5
|
| 324 |
+
],
|
| 325 |
+
"continuous": true
|
| 326 |
+
},
|
| 327 |
+
"gripper1": {
|
| 328 |
+
"absolute": true,
|
| 329 |
+
"rotation_type": null,
|
| 330 |
+
"shape": [
|
| 331 |
+
1
|
| 332 |
+
],
|
| 333 |
+
"continuous": true
|
| 334 |
+
},
|
| 335 |
+
"right_arm": {
|
| 336 |
+
"absolute": true,
|
| 337 |
+
"rotation_type": null,
|
| 338 |
+
"shape": [
|
| 339 |
+
5
|
| 340 |
+
],
|
| 341 |
+
"continuous": true
|
| 342 |
+
},
|
| 343 |
+
"gripper2": {
|
| 344 |
+
"absolute": true,
|
| 345 |
+
"rotation_type": null,
|
| 346 |
+
"shape": [
|
| 347 |
+
1
|
| 348 |
+
],
|
| 349 |
+
"continuous": true
|
| 350 |
+
}
|
| 351 |
+
}
|
| 352 |
+
},
|
| 353 |
+
"embodiment_tag": "new_embodiment"
|
| 354 |
+
}
|
| 355 |
+
}
|