Upload folder using huggingface_hub

README.md

@@ -0,0 +1,9 @@
+---
+tags:
+- model_hub_mixin
+- pytorch_model_hub_mixin
+---
+
+This model has been pushed to the Hub using the [PytorchModelHubMixin](https://huggingface.co/docs/huggingface_hub/package_reference/mixins#huggingface_hub.PyTorchModelHubMixin) integration:
+- Library: https://huggingface.co/robotics-diffusion-transformer/rdt-1b
+- Docs: [More Information Needed]

checkpoint-100/README.md

@@ -0,0 +1,9 @@
+---
+tags:
+- model_hub_mixin
+- pytorch_model_hub_mixin
+---
+
+This model has been pushed to the Hub using the [PytorchModelHubMixin](https://huggingface.co/docs/huggingface_hub/package_reference/mixins#huggingface_hub.PyTorchModelHubMixin) integration:
+- Library: https://huggingface.co/robotics-diffusion-transformer/rdt-1b
+- Docs: [More Information Needed]

checkpoint-100/config.json

@@ -0,0 +1,49 @@
+{
+  "action_dim": 128,
+  "ema": {
+    "inv_gamma": 1.0,
+    "max_value": 0.9999,
+    "min_value": 0.0,
+    "power": 0.75,
+    "update_after_step": 0
+  },
+  "img_adaptor": "mlp2x_gelu",
+  "img_cond_len": 4374,
+  "img_pos_embed_config": [
+    [
+      "image",
+      [
+        2,
+        3,
+        -729
+      ]
+    ]
+  ],
+  "img_token_dim": 1152,
+  "lang_adaptor": "mlp2x_gelu",
+  "lang_pos_embed_config": [
+    [
+      "lang",
+      -1024
+    ]
+  ],
+  "lang_token_dim": 4096,
+  "max_lang_cond_len": 1024,
+  "noise_scheduler": {
+    "beta_schedule": "squaredcos_cap_v2",
+    "clip_sample": false,
+    "num_inference_timesteps": 5,
+    "num_train_timesteps": 1000,
+    "prediction_type": "sample",
+    "type": "ddpm"
+  },
+  "pred_horizon": 64,
+  "rdt": {
+    "cond_pos_embed_type": "multimodal",
+    "depth": 28,
+    "hidden_size": 2048,
+    "num_heads": 32
+  },
+  "state_adaptor": "mlp3x_gelu",
+  "state_token_dim": 128
+}

checkpoint-100/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d1fc7d36a1e9696cb003879baa3f6b98aec063a440eca406c2cde6ca52f263f
+size 2512832968

checkpoint-100/optimizer.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a02e4e45cc23d6110d919712036826c139685e98d7200e31ad57f336f7de6237
+size 5026055309

checkpoint-100/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc97fc23d09fdf6376ccf26fd65f57710d7b675a96c3c35ecbc31e4ea5a72f9f
+size 2513008267

checkpoint-100/random_states_0.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9acc0c01d36765357863588613423d5a48fcfc8dbdbb5521b32c8e04fe486505
+size 16513

checkpoint-100/random_states_1.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d86066f1f6262a935176342587055a2d9ba50a676ce5bf19aacf5afab43a8154
+size 16449

checkpoint-100/random_states_2.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7ad37ffe3f56c37d1f4b8a988b1c86848a159be35969c287ed34f5de3af4205
+size 16513

checkpoint-100/random_states_3.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ccb54702b1a118dbfa147b8156bff5f6a2152f7d725dcc09f86b7b275d15885f
+size 16513

checkpoint-100/random_states_4.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32fc4d606a43952410a86cd9fba2b9f92a0c16547e39e9b81b006090060709a5
+size 16513

checkpoint-100/random_states_5.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5794f947108456ae5199b48ab6042f4b8664dbe52f0123a36aae40be967e630
+size 16513

checkpoint-100/random_states_6.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f18981771fe0f852dff0004f22bc7c2d462af0c5b2ccdf0e486b8e6c84f33b3d
+size 16449

checkpoint-100/random_states_7.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf1b2d2f825c634258dbf7082f5495988a7ebfd72a20161962cf365c07b240ea
+size 16513

checkpoint-100/scheduler.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4475372fbf2e3da6d4807a0dff26b2fa33c10c5343d8d1571e5c893836d6c7ca
+size 1401

config.json

@@ -0,0 +1,49 @@
+{
+  "action_dim": 128,
+  "ema": {
+    "inv_gamma": 1.0,
+    "max_value": 0.9999,
+    "min_value": 0.0,
+    "power": 0.75,
+    "update_after_step": 0
+  },
+  "img_adaptor": "mlp2x_gelu",
+  "img_cond_len": 4374,
+  "img_pos_embed_config": [
+    [
+      "image",
+      [
+        2,
+        3,
+        -729
+      ]
+    ]
+  ],
+  "img_token_dim": 1152,
+  "lang_adaptor": "mlp2x_gelu",
+  "lang_pos_embed_config": [
+    [
+      "lang",
+      -1024
+    ]
+  ],
+  "lang_token_dim": 4096,
+  "max_lang_cond_len": 1024,
+  "noise_scheduler": {
+    "beta_schedule": "squaredcos_cap_v2",
+    "clip_sample": false,
+    "num_inference_timesteps": 5,
+    "num_train_timesteps": 1000,
+    "prediction_type": "sample",
+    "type": "ddpm"
+  },
+  "pred_horizon": 64,
+  "rdt": {
+    "cond_pos_embed_type": "multimodal",
+    "depth": 28,
+    "hidden_size": 2048,
+    "num_heads": 32
+  },
+  "state_adaptor": "mlp3x_gelu",
+  "state_token_dim": 128
+}

logs/roboticDiffusionTransformer/1761750657.8426015/events.out.tfevents.1761750657.14002ff7b0c2.229585.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45f9d3df8e6f8c5f6f5ff5f8f5f7a2e134a7b11ba0ec9e50bfaf4dcac1e33391
+size 2767

logs/roboticDiffusionTransformer/1761750657.8457227/hparams.yml

@@ -0,0 +1,49 @@
+adam_beta1: 0.9
+adam_beta2: 0.999
+adam_epsilon: 1.0e-08
+adam_weight_decay: 0.01
+allow_tf32: false
+alpha: 0.9
+cam_ext_mask_prob: -1.0
+checkpointing_period: 10
+checkpoints_total_limit: 4
+cond_mask_prob: 0.1
+config_path: configs/base.yaml
+dataloader_num_workers: 8
+dataset_type: finetune
+deepspeed: null
+gradient_accumulation_steps: 1
+gradient_checkpointing: false
+hub_model_id: null
+hub_token: null
+image_aug: true
+learning_rate: 0.0001
+load_from_hdf5: true
+local_rank: 0
+logging_dir: logs
+lr_num_cycles: 1
+lr_power: 1.0
+lr_scheduler: constant
+lr_warmup_steps: 500
+max_grad_norm: 1.0
+max_train_steps: 100
+mixed_precision: bf16
+num_sample_batches: 2
+num_train_epochs: 1
+output_dir: checkpoints/20251029150953
+precomp_lang_embed: false
+pretrained_model_name_or_path: /work/bmb/hf_models/OpenDriveLab-org/rdt-iros-manipulation-challenge-baseline/awb-pretrained/
+pretrained_text_encoder_name_or_path: /work/bmb/hf_models/google/t5-v1_1-xxl
+pretrained_vision_encoder_name_or_path: /work/bmb/hf_models/google/siglip-so400m-patch14-384
+push_to_hub: false
+recipe: 10task
+report_to: all
+resume_from_checkpoint: null
+sample_batch_size: 32
+sample_period: 5
+scale_lr: false
+seed: null
+set_grads_to_none: false
+state_noise_snr: 40.0
+train_batch_size: 16
+use_8bit_adam: false

logs/roboticDiffusionTransformer/events.out.tfevents.1761750655.14002ff7b0c2.229585.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4aa2a59eaf2cbba1571320d4f0338c0327dc148d82e7831f2602c5202dcb2db0
+size 12968

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc97fc23d09fdf6376ccf26fd65f57710d7b675a96c3c35ecbc31e4ea5a72f9f
+size 2513008267