Upload folder using huggingface_hub

checkpoint-15000/config.json

@@ -0,0 +1,77 @@
+{
+  "action_horizon": 40,
+  "architectures": [
+    "AlinVLAv0"
+  ],
+  "attn_implementation": null,
+  "backbone_model_type": "contextvla_qwen3_vl_legacy",
+  "backbone_trainable_params_fp32": true,
+  "color_jitter_params": {
+    "brightness": 0.3,
+    "contrast": 0.4,
+    "hue": 0.08,
+    "saturation": 0.5
+  },
+  "diffusion_model_cfg": {
+    "action_head_max_seq_len": 512,
+    "attention_head_dim": 64,
+    "depth_multi_stream": 4,
+    "depth_single_stream": 8,
+    "dropout": 0.2,
+    "final_dropout": true,
+    "num_attention_heads": 24,
+    "output_dim": 1024,
+    "positional_embeddings": "rope_sa_only",
+    "pre_norm": "layer_norm",
+    "qk_norm": "rms_norm",
+    "rope_theta": 10000.0,
+    "sa_dim": 1536,
+    "set_triple_stream_for_mq": false,
+    "set_triple_stream_for_state": false,
+    "temb_type": "input_token",
+    "use_swiglu": true,
+    "vl_dim": 4096
+  },
+  "dtype": "bfloat16",
+  "load_bf16": true,
+  "memory_cfg": {
+    "hidden_size": 4096,
+    "intermediate_size": 16384,
+    "max_position_embeddings": 32,
+    "num_attention_heads": 16,
+    "num_hidden_layers": 2,
+    "num_key_value_heads": 16,
+    "rms_norm_eps": 1e-05,
+    "use_causal_attn": true,
+    "use_rope": true
+  },
+  "memory_length": 4,
+  "memory_meta_queries_mode": "meta_only",
+  "memory_video_delta_indices": [
+    -48,
+    -32,
+    -16,
+    0
+  ],
+  "model_name": "huiwon/alinvlm_v1_3",
+  "model_type": "AlinVLAv0",
+  "n_meta_queries": 64,
+  "new_embodiment_train_ratio": 0,
+  "qwen3_collator": true,
+  "random_rotation_angle": null,
+  "reproject_vision": false,
+  "state_dropout_prob": 0.0,
+  "transformers_version": "4.57.0",
+  "tune_diffusion_model": true,
+  "tune_llm": false,
+  "tune_projector": true,
+  "tune_top_llm_layers": 4,
+  "tune_visual": false,
+  "tune_vlln": true,
+  "use_memory": false,
+  "use_mmditv0": false,
+  "use_mmditv1": true,
+  "use_relative_action": true,
+  "use_video": true,
+  "video_length": 4
+}

checkpoint-15000/embodiment_id.json

@@ -0,0 +1,38 @@
+{
+  "new_embodiment": 0,
+  "fractal20220817_data": 1,
+  "kuka": 2,
+  "bridge_orig": 3,
+  "taco_play": 4,
+  "jaco_play": 5,
+  "berkeley_cable_routing": 6,
+  "roboturk": 7,
+  "viola": 8,
+  "berkeley_autolab_ur5": 9,
+  "toto": 10,
+  "language_table": 11,
+  "stanford_hydra_dataset_converted_externally_to_rlds": 12,
+  "austin_buds_dataset_converted_externally_to_rlds": 13,
+  "nyu_franka_play_dataset_converted_externally_to_rlds": 14,
+  "furniture_bench_dataset_converted_externally_to_rlds": 15,
+  "ucsd_kitchen_dataset_converted_externally_to_rlds": 16,
+  "austin_sailor_dataset_converted_externally_to_rlds": 17,
+  "austin_sirius_dataset_converted_externally_to_rlds": 18,
+  "dlr_edan_shared_control_converted_externally_to_rlds": 19,
+  "iamlab_cmu_pickup_insert_converted_externally_to_rlds": 20,
+  "utaustin_mutex": 21,
+  "berkeley_fanuc_manipulation": 22,
+  "cmu_stretch": 23,
+  "bc_z": 24,
+  "fmb_dataset": 25,
+  "dobbe": 26,
+  "droid": 27,
+  "agibot_dexhand": 28,
+  "agibot_gripper": 29,
+  "galaxea": 30,
+  "humanoid_everyday_g1": 31,
+  "humanoid_everyday_h1": 32,
+  "action_net": 33,
+  "neural_gr1": 34,
+  "simulation_gr1": 35
+}

checkpoint-15000/experiment_cfg/conf.yaml

@@ -0,0 +1,308 @@
+data:
+  datasets:
+  - dataset_paths:
+    - /rlwrld2/home/nayoung_oh/workspace/datasets/0330/openarm_usb_teleop_0
+    embodiment_tag: new_embodiment
+    mix_ratio: 0.67
+    dataset_type: physical_embodiment
+    val_dataset_path: null
+  - dataset_paths:
+    - /rlwrld2/home/nayoung_oh/workspace/datasets/0330/openarm_usb_teleop_1
+    embodiment_tag: new_embodiment
+    mix_ratio: 0.33
+    dataset_type: physical_embodiment
+    val_dataset_path: null
+  modality_configs:
+    new_embodiment:
+      video:
+        delta_indices:
+        - -9
+        - -7
+        - -5
+        - -3
+        - -8
+        - -6
+        - -4
+        - -2
+        - -7
+        - -5
+        - -3
+        - -1
+        - -6
+        - -4
+        - -2
+        - 0
+        modality_keys:
+        - camera_ego_left
+        - camera_ego_right
+        sin_cos_embedding_keys: null
+        mean_std_embedding_keys: null
+        action_configs: null
+      state:
+        delta_indices:
+        - -3
+        - -2
+        - -1
+        - 0
+        modality_keys:
+        - right_arm_joints
+        - left_arm_joints
+        - right_hand_joints
+        - left_hand_joints
+        - neck_joints
+        sin_cos_embedding_keys: null
+        mean_std_embedding_keys: null
+        action_configs: null
+      action:
+        delta_indices:
+        - 0
+        - 1
+        - 2
+        - 3
+        - 4
+        - 5
+        - 6
+        - 7
+        - 8
+        - 9
+        - 10
+        - 11
+        - 12
+        - 13
+        - 14
+        - 15
+        - 16
+        - 17
+        - 18
+        - 19
+        - 20
+        - 21
+        - 22
+        - 23
+        - 24
+        - 25
+        - 26
+        - 27
+        - 28
+        - 29
+        - 30
+        - 31
+        - 32
+        - 33
+        - 34
+        - 35
+        - 36
+        - 37
+        - 38
+        - 39
+        modality_keys:
+        - right_arm_joints
+        - left_arm_joints
+        - right_hand_joints
+        - left_hand_joints
+        - neck_joints
+        sin_cos_embedding_keys: null
+        mean_std_embedding_keys: null
+        action_configs:
+        - rep: ABSOLUTE
+          type: NON_EEF
+          format: DEFAULT
+          state_key: null
+        - rep: ABSOLUTE
+          type: NON_EEF
+          format: DEFAULT
+          state_key: null
+        - rep: ABSOLUTE
+          type: NON_EEF
+          format: DEFAULT
+          state_key: null
+        - rep: ABSOLUTE
+          type: NON_EEF
+          format: DEFAULT
+          state_key: null
+        - rep: ABSOLUTE
+          type: NON_EEF
+          format: DEFAULT
+          state_key: null
+      language:
+        delta_indices:
+        - 0
+        modality_keys:
+        - annotation.human.task_description
+        sin_cos_embedding_keys: null
+        mean_std_embedding_keys: null
+        action_configs: null
+  dataset_mode: sharded
+  download_cache: false
+  shard_size: 1024
+  episode_sampling_rate: 0.1
+  num_shards_per_epoch: 100000
+  override_pretraining_statistics: false
+  mode: single_turn
+  random_chop: 0.0
+  mock_dataset_mode: false
+  shuffle: true
+  seed: 42
+  multiprocessing_context: fork
+  allow_padding: true
+  subsample_ratio: 1.0
+  image_crop_size:
+  - 244
+  - 244
+  image_target_size:
+  - 224
+  - 224
+  video_backend: torchcodec
+load_config_path: null
+model:
+  model_type: AlinVLAv0
+  model_dtype: bfloat16
+  model_name: huiwon/alinvlm_v1_3
+  backbone_model_type: contextvla_qwen3_vl_legacy
+  model_revision: null
+  tune_top_llm_layers: 4
+  backbone_embedding_dim: 4096
+  tune_llm: false
+  tune_visual: false
+  select_layer: 18
+  reproject_vision: false
+  use_flash_attention: true
+  load_bf16: true
+  collator_overwrite_image_inputs: false
+  qwen3_collator: true
+  backbone_trainable_params_fp32: true
+  image_crop_size: null
+  image_target_size: null
+  shortest_image_edge: 256
+  crop_fraction: 0.95
+  random_rotation_angle: null
+  color_jitter_params:
+    brightness: 0.3
+    contrast: 0.4
+    hue: 0.08
+    saturation: 0.5
+  max_area: 65536
+  resize_m: 32
+  use_albumentations_transforms: true
+  formalize_language: true
+  apply_sincos_state_encoding: false
+  use_relative_action: true
+  use_percentiles: true
+  conversation_image_first: false
+  max_state_dim: 64
+  max_action_dim: 64
+  action_horizon: 40
+  hidden_size: 1024
+  input_embedding_dim: 1536
+  new_embodiment_train_ratio: 0.0
+  add_pos_embed: true
+  attn_dropout: 0.2
+  use_vlln: false
+  max_seq_len: 1024
+  use_mmditv0: false
+  n_meta_queries: 64
+  diffusion_model_cfg:
+    action_head_max_seq_len: 512
+    attention_head_dim: 64
+    depth_multi_stream: 4
+    depth_single_stream: 8
+    dropout: 0.2
+    final_dropout: true
+    num_attention_heads: 24
+    output_dim: 1024
+    positional_embeddings: rope_sa_only
+    pre_norm: layer_norm
+    qk_norm: rms_norm
+    rope_theta: 10000.0
+    set_triple_stream_for_mq: false
+    set_triple_stream_for_state: false
+    temb_type: input_token
+    use_swiglu: true
+  use_mmditv1: true
+  num_inference_timesteps: 4
+  noise_beta_alpha: 1.5
+  noise_beta_beta: 1.0
+  noise_s: 0.999
+  num_timestep_buckets: 1000
+  tune_projector: true
+  tune_diffusion_model: true
+  tune_vlln: true
+  state_dropout_prob: 0.0
+  state_additive_noise_scale: 0.0
+  use_memory: false
+  memory_length: 4
+  memory_meta_queries_mode: meta_only
+  memory_cfg:
+    hidden_size: 4096
+    intermediate_size: 16384
+    max_position_embeddings: 32
+    num_attention_heads: 16
+    num_hidden_layers: 2
+    num_key_value_heads: 16
+    rms_norm_eps: 1.0e-05
+    use_causal_attn: true
+    use_rope: true
+  training_rtc_max_overlap: -1
+  inference_rtc_overlap_steps: null
+  inference_rtc_frozen_steps: null
+  rtc_ramp_rate: 10.0
+  use_video: true
+  video_length: 4
+  max_num_embodiments: 36
+training:
+  output_dir: ./ckpt/output
+  experiment_name: big_usb_40
+  max_steps: 30000
+  global_batch_size: 64
+  batch_size: null
+  gradient_accumulation_steps: 1
+  learning_rate: 0.0001
+  lr_scheduler_type: cosine
+  weight_decay: 1.0e-05
+  warmup_ratio: 0.05
+  warmup_steps: 0
+  max_grad_norm: 1.0
+  optim: adamw_torch
+  start_from_checkpoint: /rlwrld2/home/nayoung_oh/workspace/RLDX/models/alinvla_v1d4_video_mq64_mixv4_pt100k
+  tf32: true
+  fp16: false
+  bf16: true
+  eval_bf16: true
+  logging_steps: 10
+  save_steps: 5000
+  save_total_limit: 5
+  save_vl_model: false
+  upload_checkpoints: false
+  upload_every: 1000
+  upload_last_n_checkpoints: 5
+  max_concurrent_uploads: 2
+  eval_strategy: 'no'
+  eval_steps: 500
+  eval_set_split_ratio: 0.1
+  eval_batch_size: 2
+  save_best_eval_metric_name: ''
+  save_best_eval_metric_greater_is_better: true
+  deepspeed_stage: 2
+  gradient_checkpointing: false
+  transformers_trust_remote_code: true
+  transformers_local_files_only: false
+  transformers_cache_dir: null
+  transformers_access_token: null
+  use_ddp: false
+  ddp_bucket_cap_mb: 100
+  num_gpus: 4
+  dataloader_num_workers: 4
+  remove_unused_columns: false
+  use_wandb: true
+  wandb_project: n1d6_finetune
+  enable_profiling: false
+  max_retries: 3
+  assert_loss_less_than: null
+  add_rl_callback: false
+  enable_open_loop_eval: false
+  open_loop_eval_traj_ids:
+  - 0
+  open_loop_eval_steps_per_traj: 100
+  open_loop_eval_plot_indices: null
+max_steps: 30000
+save_steps: 5000

checkpoint-15000/experiment_cfg/config.yaml

@@ -0,0 +1,327 @@
+!!python/object:gr00t.configs.base_config.Config
+data: !!python/object:gr00t.configs.data.data_config.DataConfig
+  allow_padding: true
+  dataset_mode: sharded
+  datasets:
+  - !!python/object:gr00t.configs.data.data_config.SingleDatasetConfig
+    dataset_paths:
+    - /rlwrld2/home/nayoung_oh/workspace/datasets/0330/openarm_usb_teleop_0
+    dataset_type: physical_embodiment
+    embodiment_tag: new_embodiment
+    mix_ratio: 0.67
+    val_dataset_path: null
+  - !!python/object:gr00t.configs.data.data_config.SingleDatasetConfig
+    dataset_paths:
+    - /rlwrld2/home/nayoung_oh/workspace/datasets/0330/openarm_usb_teleop_1
+    dataset_type: physical_embodiment
+    embodiment_tag: new_embodiment
+    mix_ratio: 0.33
+    val_dataset_path: null
+  download_cache: false
+  episode_sampling_rate: 0.1
+  image_crop_size:
+  - 244
+  - 244
+  image_target_size:
+  - 224
+  - 224
+  mock_dataset_mode: false
+  modality_configs:
+    new_embodiment:
+      action: !!python/object:gr00t.data.types.ModalityConfig
+        action_configs:
+        - &id001 !!python/object:gr00t.data.types.ActionConfig
+          format: !!python/object/apply:gr00t.data.types.ActionFormat
+          - default
+          rep: !!python/object/apply:gr00t.data.types.ActionRepresentation
+          - absolute
+          state_key: null
+          type: !!python/object/apply:gr00t.data.types.ActionType
+          - non_eef
+        - *id001
+        - *id001
+        - *id001
+        - *id001
+        delta_indices:
+        - 0
+        - 1
+        - 2
+        - 3
+        - 4
+        - 5
+        - 6
+        - 7
+        - 8
+        - 9
+        - 10
+        - 11
+        - 12
+        - 13
+        - 14
+        - 15
+        - 16
+        - 17
+        - 18
+        - 19
+        - 20
+        - 21
+        - 22
+        - 23
+        - 24
+        - 25
+        - 26
+        - 27
+        - 28
+        - 29
+        - 30
+        - 31
+        - 32
+        - 33
+        - 34
+        - 35
+        - 36
+        - 37
+        - 38
+        - 39
+        mean_std_embedding_keys: null
+        modality_keys:
+        - right_arm_joints
+        - left_arm_joints
+        - right_hand_joints
+        - left_hand_joints
+        - neck_joints
+        sin_cos_embedding_keys: null
+      language: !!python/object:gr00t.data.types.ModalityConfig
+        action_configs: null
+        delta_indices:
+        - 0
+        mean_std_embedding_keys: null
+        modality_keys:
+        - annotation.human.task_description
+        sin_cos_embedding_keys: null
+      state: !!python/object:gr00t.data.types.ModalityConfig
+        action_configs: null
+        delta_indices:
+        - -3
+        - -2
+        - -1
+        - 0
+        mean_std_embedding_keys: null
+        modality_keys:
+        - right_arm_joints
+        - left_arm_joints
+        - right_hand_joints
+        - left_hand_joints
+        - neck_joints
+        sin_cos_embedding_keys: null
+      video: !!python/object:gr00t.data.types.ModalityConfig
+        action_configs: null
+        delta_indices:
+        - -9
+        - -7
+        - -5
+        - -3
+        - -8
+        - -6
+        - -4
+        - -2
+        - -7
+        - -5
+        - -3
+        - -1
+        - -6
+        - -4
+        - -2
+        - 0
+        mean_std_embedding_keys: null
+        modality_keys:
+        - camera_ego_left
+        - camera_ego_right
+        sin_cos_embedding_keys: null
+  mode: single_turn
+  multiprocessing_context: fork
+  num_shards_per_epoch: 100000
+  override_pretraining_statistics: false
+  random_chop: 0.0
+  seed: 42
+  shard_size: 1024
+  shuffle: true
+  subsample_ratio: 1.0
+  video_backend: torchcodec
+load_config_path: null
+model: !!python/object:gr00t.configs.model.alinvla_v0.AlinVLAv0Config
+  _attn_implementation_internal: null
+  _commit_hash: null
+  _name_or_path: ''
+  _output_attentions: false
+  add_cross_attention: false
+  architectures: null
+  backbone_model_type: contextvla_qwen3_vl_legacy
+  backbone_trainable_params_fp32: true
+  bad_words_ids: null
+  begin_suppress_tokens: null
+  bos_token_id: null
+  chunk_size_feed_forward: 0
+  color_jitter_params:
+    brightness: 0.3
+    contrast: 0.4
+    hue: 0.08
+    saturation: 0.5
+  conversation_image_first: false
+  cross_attention_hidden_size: null
+  decoder_start_token_id: null
+  diffusion_model_cfg:
+    action_head_max_seq_len: 512
+    attention_head_dim: 64
+    depth_multi_stream: 4
+    depth_single_stream: 8
+    dropout: 0.2
+    final_dropout: true
+    num_attention_heads: 24
+    output_dim: 1024
+    positional_embeddings: rope_sa_only
+    pre_norm: layer_norm
+    qk_norm: rms_norm
+    rope_theta: 10000.0
+    set_triple_stream_for_mq: false
+    set_triple_stream_for_state: false
+    temb_type: input_token
+    use_swiglu: true
+  diversity_penalty: 0.0
+  do_sample: false
+  dtype: null
+  early_stopping: false
+  encoder_no_repeat_ngram_size: 0
+  eos_token_id: null
+  exponential_decay_length_penalty: null
+  finetuning_task: null
+  forced_bos_token_id: null
+  forced_eos_token_id: null
+  id2label:
+    0: LABEL_0
+    1: LABEL_1
+  is_decoder: false
+  is_encoder_decoder: false
+  label2id:
+    LABEL_0: 0
+    LABEL_1: 1
+  length_penalty: 1.0
+  load_bf16: true
+  max_length: 20
+  memory_cfg:
+    hidden_size: 4096
+    intermediate_size: 16384
+    max_position_embeddings: 32
+    num_attention_heads: 16
+    num_hidden_layers: 2
+    num_key_value_heads: 16
+    rms_norm_eps: 1.0e-05
+    use_causal_attn: true
+    use_rope: true
+  memory_video_delta_indices:
+  - -48
+  - -32
+  - -16
+  - 0
+  min_length: 0
+  model_name: huiwon/alinvlm_v1_3
+  model_type: AlinVLAv0
+  n_meta_queries: 64
+  new_embodiment_train_ratio: 0
+  no_repeat_ngram_size: 0
+  num_beam_groups: 1
+  num_beams: 1
+  num_return_sequences: 1
+  output_hidden_states: false
+  output_scores: false
+  pad_token_id: null
+  prefix: null
+  problem_type: null
+  pruned_heads: {}
+  qwen3_collator: true
+  random_rotation_angle: null
+  remove_invalid_values: false
+  repetition_penalty: 1.0
+  reproject_vision: false
+  return_dict: true
+  return_dict_in_generate: false
+  sep_token_id: null
+  state_dropout_prob: 0.0
+  suppress_tokens: null
+  task_specific_params: null
+  temperature: 1.0
+  tf_legacy_loss: false
+  tie_encoder_decoder: false
+  tie_word_embeddings: true
+  tokenizer_class: null
+  top_k: 50
+  top_p: 1.0
+  torchscript: false
+  transformers_version: null
+  tune_diffusion_model: true
+  tune_llm: false
+  tune_projector: true
+  tune_top_llm_layers: 4
+  tune_visual: false
+  typical_p: 1.0
+  use_bfloat16: false
+  use_mmditv0: false
+  use_mmditv1: true
+  use_relative_action: true
+  use_video: true
+  video_length: 4
+training: !!python/object:gr00t.configs.training.training_config.TrainingConfig
+  add_rl_callback: false
+  assert_loss_less_than: null
+  batch_size: null
+  bf16: true
+  dataloader_num_workers: 4
+  ddp_bucket_cap_mb: 100
+  deepspeed_stage: 2
+  enable_open_loop_eval: false
+  enable_profiling: false
+  eval_batch_size: 2
+  eval_bf16: true
+  eval_set_split_ratio: 0.1
+  eval_steps: 500
+  eval_strategy: 'no'
+  experiment_name: big_usb_40
+  fp16: false
+  global_batch_size: 64
+  gradient_accumulation_steps: 1
+  gradient_checkpointing: false
+  learning_rate: 0.0001
+  logging_steps: 10
+  lr_scheduler_type: cosine
+  max_concurrent_uploads: 2
+  max_grad_norm: 1.0
+  max_retries: 3
+  max_steps: 30000
+  num_gpus: 4
+  open_loop_eval_plot_indices: null
+  open_loop_eval_steps_per_traj: 100
+  open_loop_eval_traj_ids:
+  - 0
+  optim: adamw_torch
+  output_dir: ./ckpt/output
+  remove_unused_columns: false
+  save_best_eval_metric_greater_is_better: true
+  save_best_eval_metric_name: ''
+  save_steps: 5000
+  save_total_limit: 5
+  save_vl_model: false
+  start_from_checkpoint: /rlwrld2/home/nayoung_oh/workspace/RLDX/models/alinvla_v1d4_video_mq64_mixv4_pt100k
+  tf32: true
+  transformers_access_token: null
+  transformers_cache_dir: null
+  transformers_local_files_only: false
+  transformers_trust_remote_code: true
+  upload_checkpoints: false
+  upload_every: 1000
+  upload_last_n_checkpoints: 5
+  use_ddp: false
+  use_wandb: true
+  wandb_project: n1d6_finetune
+  warmup_ratio: 0.05
+  warmup_steps: 0
+  weight_decay: 1.0e-05

checkpoint-15000/experiment_cfg/dataset_statistics.json

@@ -0,0 +1,629 @@
+{
+  "new_embodiment": {
+    "state": {
+      "right_arm_joints": {
+        "min": [
+          -0.20847637951374054,
+          -0.17223620414733887,
+          -0.8260852694511414,
+          0.006294346414506435,
+          -1.5836957693099976,
+          -0.5304417610168457,
+          -0.6185625791549683
+        ],
+        "max": [
+          1.4608606100082397,
+          0.7867932915687561,
+          0.7280460596084595,
+          2.026970386505127,
+          0.32101166248321533,
+          0.7837415337562561,
+          0.5834668278694153
+        ],
+        "mean": [
+          0.5230762350115545,
+          0.031938130726095276,
+          0.07735111293069932,
+          1.0961320673796087,
+          -1.1073419616170415,
+          0.11922063120033552,
+          0.05158661119532133
+        ],
+        "std": [
+          0.457679354789903,
+          0.15803064005676729,
+          0.26611296499301296,
+          0.5450642539383688,
+          0.44136857118707146,
+          0.21900165579974118,
+          0.15309557379165087
+        ],
+        "q01": [
+          -0.045479488308008235,
+          -0.15748688659880955,
+          -0.2324001598639563,
+          0.23192057110022266,
+          -1.5726320718878462,
+          -0.26164717355209116,
+          -0.15236894632345038
+        ],
+        "q99": [
+          1.1783605899921912,
+          0.29508311892070715,
+          0.4700866512723284,
+          1.7546243470988008,
+          -0.40475618449400974,
+          0.5152354760941318,
+          0.29988374789735234
+        ]
+      },
+      "left_arm_joints": {
+        "min": [
+          -1.4444571733474731,
+          -1.0122454166412354,
+          -1.0866330862045288,
+          0.10738536715507507,
+          -1.2121385335922241,
+          -0.7833600640296936,
+          -0.9882124066352844
+        ],
+        "max": [
+          0.2615014910697937,
+          0.17109178006649017,
+          1.5047303438186646,
+          2.0948729515075684,
+          1.5684367418289185,
+          0.7448310256004333,
+          1.344510555267334
+        ],
+        "mean": [
+          -0.04986175698282235,
+          -0.19392163572815393,
+          0.17408178791213455,
+          1.6268207280624323,
+          0.943715995203565,
+          -0.1656372827567857,
+          0.08572700017970818
+        ],
+        "std": [
+          0.13127968307410454,
+          0.21879874111138958,
+          0.18787674653153308,
+          0.13760933470652406,
+          0.7142651273520758,
+          0.3682533803815269,
+          0.21210845544579085
+        ],
+        "q01": [
+          -0.27506257213997515,
+          -0.6895779073341636,
+          -0.0784322185224472,
+          1.355194293867866,
+          -0.3763468656182127,
+          -0.769349612863381,
+          -0.4407769059315693
+        ],
+        "q99": [
+          0.08620987205422512,
+          0.08083185656331611,
+          0.5328141061374334,
+          1.7955220293853555,
+          1.5638651034392295,
+          0.2517314710440321,
+          0.5060496525470584
+        ]
+      },
+      "right_hand_joints": {
+        "min": [
+          0.02471296489238739,
+          -0.008722222410142422,
+          0.020351851359009743,
+          -0.14192885160446167,
+          0.01162963081151247,
+          -0.008722222410142422,
+          -0.01162963081151247,
+          -0.08576852083206177,
+          0.01162963081151247,
+          0.02180555649101734,
+          0.010175925679504871,
+          0.005814815405756235
+        ],
+        "max": [
+          1.5714536905288696,
+          1.0873703956604004,
+          1.2007594108581543,
+          -0.06382732838392258,
+          1.6339629888534546,
+          1.190583348274231,
+          1.7836945056915283,
+          1.8084073066711426,
+          1.8491111993789673,
+          1.7880555391311646,
+          1.844749927520752,
+          1.2807129621505737
+        ],
+        "mean": [
+          0.5850972631377792,
+          0.42659694968022016,
+          0.6479643724551789,
+          -0.08767521811430576,
+          0.425969056384194,
+          0.39579498645896927,
+          0.4627784831631483,
+          0.5736243939751159,
+          0.4692227715888908,
+          0.49072391727075826,
+          0.4756991051017129,
+          0.4021215243171613
+        ],
+        "std": [
+          0.4659352716590282,
+          0.26326663460608324,
+          0.1903730892891041,
+          0.021649972511879785,
+          0.3177542874289095,
+          0.12852050776384696,
+          0.35465225689414787,
+          0.2813339579162597,
+          0.5321364975758696,
+          0.39219871994450173,
+          0.5316887540787808,
+          0.2635455642348228
+        ],
+        "q01": [
+          0.04709112252429289,
+          0.05362940602356817,
+          0.03094588222703274,
+          -0.12354047151182598,
+          0.02500137889803208,
+          0.015720412845067713,
+          0.05507507756448419,
+          0.06626581013963564,
+          0.020781336379338825,
+          0.03831492052703827,
+          0.016980372181013663,
+          0.014013878352033101
+        ],
+        "q99": [
+          1.2835387079641307,
+          0.9926928857163729,
+          0.9508772217850779,
+          -0.06821455715077998,
+          0.9838547316175984,
+          0.6369301133140961,
+          1.1447815406442614,
+          1.08181754207393,
+          1.5359646890495815,
+          1.2619330054281663,
+          1.450155472114204,
+          0.9488189728109094
+        ]
+      },
+      "left_hand_joints": {
+        "min": [
+          0.01453703735023737,
+          -0.02180555649101734,
+          0.05087963119149208,
+          -0.11556173861026764,
+          -0.0,
+          0.005814815405756235,
+          0.02907407470047474,
+          0.004361111205071211,
+          0.01162963081151247,
+          0.008722222410142422,
+          0.01162963081151247,
+          0.0029074077028781176
+        ],
+        "max": [
+          1.5511019229888916,
+          1.1644166707992554,
+          0.9318241477012634,
+          -0.053776565939188004,
+          1.1586018800735474,
+          1.2981574535369873,
+          1.7110095024108887,
+          1.2981574535369873,
+          1.7371760606765747,
+          0.7428426146507263,
+          1.3635740280151367,
+          0.5146111249923706
+        ],
+        "mean": [
+          0.32985505008751104,
+          0.6881588844618378,
+          0.6488113999748686,
+          -0.06972486540469508,
+          0.3926318089439047,
+          0.5482275542810864,
+          0.47254444520168226,
+          0.41040236509504985,
+          0.3783655666627965,
+          0.5194880139656365,
+          0.3418363023788917,
+          0.47916842368371915
+        ],
+        "std": [
+          0.14452058747164218,
+          0.15373799437316096,
+          0.11791576866346334,
+          0.01307136103551452,
+          0.10481756163917923,
+          0.12678199391146713,
+          0.12084425493478433,
+          0.1635095111154085,
+          0.19093731519085877,
+          0.11041810061836821,
+          0.37641207261413745,
+          0.0887305578820552
+        ],
+        "q01": [
+          0.060338779066490496,
+          0.5119375301750233,
+          0.057951124183853064,
+          -0.08574211243768456,
+          0.02229960322668788,
+          0.0197731460882619,
+          0.037480855866511335,
+          0.014501567945081463,
+          0.019313894965212467,
+          0.015534716928085666,
+          0.01924718063100328,
+          0.014888906043983111
+        ],
+        "q99": [
+          0.4228504704116889,
+          0.9837010790668748,
+          0.7180913469770518,
+          -0.05784016806244579,
+          0.514612030705292,
+          0.6783910810682822,
+          0.6035341481979898,
+          0.6762715916941239,
+          0.7075596448178942,
+          0.6270238740126298,
+          0.9857991865153608,
+          0.5125562485176647
+        ]
+      },
+      "neck_joints": {
+        "min": [
+          0.7009612917900085,
+          -0.0032425422687083483
+        ],
+        "max": [
+          0.7112611532211304,
+          0.0036240178160369396
+        ],
+        "mean": [
+          0.7044533545035223,
+          0.0010014864396475569
+        ],
+        "std": [
+          0.0019810688647565705,
+          0.0027107617865090093
+        ],
+        "q01": [
+          0.7039417799490104,
+          -0.0028693337709507255
+        ],
+        "q99": [
+          0.7081959350937106,
+          0.003242540992498085
+        ]
+      }
+    },
+    "action": {
+      "right_arm_joints": {
+        "min": [
+          -0.19921624660491943,
+          -0.17453299462795258,
+          -0.8291807174682617,
+          0.0,
+          -1.5707999467849731,
+          -0.5814089179039001,
+          -0.623637855052948
+        ],
+        "max": [
+          1.486642599105835,
+          0.7893767356872559,
+          0.7344165444374084,
+          2.0441505908966064,
+          0.38465243577957153,
+          0.785398006439209,
+          0.6433967351913452
+        ],
+        "mean": [
+          0.5430090535721166,
+          0.033566931036718685,
+          0.07625336950521511,
+          1.1092998512043604,
+          -1.0892971230997093,
+          0.09155957572632356,
+          0.073395238163872
+        ],
+        "std": [
+          0.4596794105521279,
+          0.1621918706557556,
+          0.2679870922781361,
+          0.5501861114444726,
+          0.44758367140485505,
+          0.22767518069131656,
+          0.16769684972295845
+        ],
+        "q01": [
+          -0.03456410663712079,
+          -0.16184220019671516,
+          -0.23216804975752398,
+          0.23341644017039692,
+          -1.5707028190120937,
+          -0.309905468247712,
+          -0.15133796950514602
+        ],
+        "q99": [
+          1.200440279459216,
+          0.29559855399130414,
+          0.47206481063425404,
+          1.7754976640909697,
+          -0.37575176490588347,
+          0.5010074686091875,
+          0.3440673376461279
+        ]
+      },
+      "left_arm_joints": {
+        "min": [
+          -1.5065116882324219,
+          -1.0190038681030273,
+          -1.0935002565383911,
+          0.014847817830741405,
+          -1.2871253490447998,
+          -0.785398006439209,
+          -0.98295658826828
+        ],
+        "max": [
+          0.25296857953071594,
+          0.17453299462795258,
+          1.501496434211731,
+          2.1152310371398926,
+          1.5707999467849731,
+          0.785398006439209,
+          1.3924580812454224
+        ],
+        "mean": [
+          -0.06444040306770334,
+          -0.2012424200521196,
+          0.17902124138928244,
+          1.6448206240709824,
+          0.9245709606725199,
+          -0.13036384597608147,
+          0.07370097759832434
+        ],
+        "std": [
+          0.13388403640089191,
+          0.22584157217233736,
+          0.19047329506273125,
+          0.14005725802758057,
+          0.7307305254518663,
+          0.3894608804758103,
+          0.22220778127217836
+        ],
+        "q01": [
+          -0.28973830174308024,
+          -0.6940539310712703,
+          -0.07905846509907914,
+          1.3640073856782455,
+          -0.4320198988812157,
+          -0.7719500454666719,
+          -0.48853233881168573
+        ],
+        "q99": [
+          0.07653752761821989,
+          0.08863872731021356,
+          0.5342535898797907,
+          1.8158065448750924,
+          1.570770554242114,
+          0.3071050589200862,
+          0.505248945544354
+        ]
+      },
+      "right_hand_joints": {
+        "min": [
+          0.026661602780222893,
+          0.0,
+          0.02366132102906704,
+          -0.17000000178813934,
+          0.01246256660670042,
+          0.0,
+          0.0,
+          0.0011867061257362366,
+          0.013637464493513107,
+          0.024103114381432533,
+          0.012091287411749363,
+          0.00664250273257494
+        ],
+        "max": [
+          1.7780132293701172,
+          1.3474156856536865,
+          1.4250937700271606,
+          -0.025157466530799866,
+          1.7364939451217651,
+          1.1551449298858643,
+          1.7935020923614502,
+          1.6204304695129395,
+          1.8591424226760864,
+          1.689421534538269,
+          1.8520755767822266,
+          1.1890243291854858
+        ],
+        "mean": [
+          0.6239154227631595,
+          0.4734269487818846,
+          0.7052524192097098,
+          -0.0994350955853528,
+          0.445617227524724,
+          0.4120455103231284,
+          0.5305768463764756,
+          0.5999651932137665,
+          0.5549466424355907,
+          0.5411834015984729,
+          0.48569650618147897,
+          0.4039426324710887
+        ],
+        "std": [
+          0.5605042020116761,
+          0.33643817537672954,
+          0.19982472888235422,
+          0.04681108942644247,
+          0.36050933420191983,
+          0.13796386090211465,
+          0.4911472584136365,
+          0.31706520184474446,
+          0.6512271464068475,
+          0.45676763934549547,
+          0.5481346251398389,
+          0.2617218955348148
+        ],
+        "q01": [
+          0.049512094295544706,
+          0.04391928536156868,
+          0.06661649222801683,
+          -0.1691424089310887,
+          0.03366654186732824,
+          0.03491670466944912,
+          0.045978101791642315,
+          0.07975563647047126,
+          0.027088694712146515,
+          0.050041808570090995,
+          0.025063916005994703,
+          0.027789555362793733
+        ],
+        "q99": [
+          1.5096395081324445,
+          1.0117019110491778,
+          0.9871990005581402,
+          -0.04557066642478349,
+          1.129917783318187,
+          0.6697547134449693,
+          1.4636922683123665,
+          1.1542747309416463,
+          1.704446982988189,
+          1.3244573535339408,
+          1.4724930172015087,
+          0.9484881772754448
+        ]
+      },
+      "left_hand_joints": {
+        "min": [
+          0.019045373424887657,
+          0.0,
+          0.05370108410716057,
+          -0.16869805753231049,
+          0.0012344357091933489,
+          0.008150840178132057,
+          0.03300570324063301,
+          0.006950031500309706,
+          0.012305227108299732,
+          0.010256324894726276,
+          0.011016922071576118,
+          0.007798284757882357
+        ],
+        "max": [
+          1.6031163930892944,
+          1.1825103759765625,
+          1.0342681407928467,
+          0.005556285381317139,
+          1.1919951438903809,
+          1.2375268936157227,
+          1.7269041538238525,
+          1.3056350946426392,
+          1.7406609058380127,
+          0.7451879382133484,
+          1.3663225173950195,
+          0.5
+        ],
+        "mean": [
+          0.3274554329878354,
+          0.6816605953002266,
+          0.665040378275847,
+          -0.08246567780487488,
+          0.3863661692061652,
+          0.5535841803974353,
+          0.46503769937507694,
+          0.4109603218945199,
+          0.3769462572830021,
+          0.5226880008575805,
+          0.33666394538840627,
+          0.48215487205665214
+        ],
+        "std": [
+          0.14631145376302618,
+          0.1512041150457038,
+          0.10564640145168502,
+          0.0387129805935982,
+          0.10139465603207952,
+          0.11700147021444009,
+          0.12220344020893094,
+          0.15816582331596807,
+          0.19094290279570064,
+          0.10102949256192277,
+          0.38079709737611284,
+          0.07690963441476438
+        ],
+        "q01": [
+          0.07869434876053279,
+          0.5046172398762443,
+          0.09302006264326931,
+          -0.1423123249924626,
+          0.0406597002223288,
+          0.04727644260624045,
+          0.05873163730448438,
+          0.031363568981418746,
+          0.03321028503469109,
+          0.044394902811118096,
+          0.02024680250758706,
+          0.04200780881531574
+        ],
+        "q99": [
+          0.4284983198796039,
+          0.966640028222133,
+          0.7364649212501883,
+          -0.030307355938947973,
+          0.5190797485182326,
+          0.684899658535276,
+          0.6059135765155187,
+          0.6885722217989116,
+          0.7126064420225153,
+          0.6312143412139029,
+          0.9916327871268753,
+          0.49999892561907305
+        ]
+      },
+      "neck_joints": {
+        "min": [
+          0.6980000138282776,
+          -0.002854566555470228
+        ],
+        "max": [
+          0.7066459059715271,
+          0.0032304299529641867
+        ],
+        "mean": [
+          0.6982365136311492,
+          2.895988731653634e-05
+        ],
+        "std": [
+          0.001417052313910553,
+          0.00046692749679010055
+        ],
+        "q01": [
+          0.6980000137282772,
+          -0.0026975402881033667
+        ],
+        "q99": [
+          0.7040469144690047,
+          0.002611027152444705
+        ]
+      }
+    },
+    "relative_action": {}
+  }
+}

checkpoint-15000/experiment_cfg/final_model_config.json

@@ -0,0 +1,86 @@
+{
+  "model_type": "AlinVLAv0",
+  "model_dtype": "bfloat16",
+  "model_name": "huiwon/alinvlm_v1_3",
+  "backbone_model_type": "contextvla_qwen3_vl_legacy",
+  "model_revision": null,
+  "tune_top_llm_layers": 4,
+  "backbone_embedding_dim": 4096,
+  "tune_llm": false,
+  "tune_visual": false,
+  "select_layer": 18,
+  "reproject_vision": false,
+  "use_flash_attention": true,
+  "load_bf16": true,
+  "collator_overwrite_image_inputs": false,
+  "qwen3_collator": true,
+  "backbone_trainable_params_fp32": true,
+  "apply_sincos_state_encoding": false,
+  "use_relative_action": true,
+  "use_percentiles": true,
+  "conversation_image_first": false,
+  "max_state_dim": 64,
+  "max_action_dim": 64,
+  "action_horizon": 40,
+  "hidden_size": 1024,
+  "input_embedding_dim": 1536,
+  "new_embodiment_train_ratio": 0,
+  "add_pos_embed": true,
+  "attn_dropout": 0.2,
+  "use_vlln": false,
+  "max_seq_len": 1024,
+  "use_mmditv0": false,
+  "n_meta_queries": 64,
+  "diffusion_model_cfg": {
+    "action_head_max_seq_len": 512,
+    "attention_head_dim": 64,
+    "depth_multi_stream": 4,
+    "depth_single_stream": 8,
+    "dropout": 0.2,
+    "final_dropout": true,
+    "num_attention_heads": 24,
+    "output_dim": 1024,
+    "positional_embeddings": "rope_sa_only",
+    "pre_norm": "layer_norm",
+    "qk_norm": "rms_norm",
+    "rope_theta": 10000.0,
+    "sa_dim": 1536,
+    "set_triple_stream_for_mq": false,
+    "set_triple_stream_for_state": false,
+    "temb_type": "input_token",
+    "use_swiglu": true,
+    "vl_dim": 4096
+  },
+  "use_mmditv1": true,
+  "num_inference_timesteps": 4,
+  "noise_beta_alpha": 1.5,
+  "noise_beta_beta": 1.0,
+  "noise_s": 0.999,
+  "num_timestep_buckets": 1000,
+  "tune_projector": true,
+  "tune_diffusion_model": true,
+  "tune_vlln": true,
+  "state_dropout_prob": 0.0,
+  "state_additive_noise_scale": 0.0,
+  "use_memory": false,
+  "memory_length": 4,
+  "memory_meta_queries_mode": "meta_only",
+  "memory_cfg": {
+    "hidden_size": 4096,
+    "intermediate_size": 16384,
+    "max_position_embeddings": 32,
+    "num_attention_heads": 16,
+    "num_hidden_layers": 2,
+    "num_key_value_heads": 16,
+    "rms_norm_eps": 1e-05,
+    "use_causal_attn": true,
+    "use_rope": true
+  },
+  "training_rtc_max_overlap": -1,
+  "inference_rtc_overlap_steps": null,
+  "inference_rtc_frozen_steps": null,
+  "rtc_ramp_rate": 10.0,
+  "use_video": true,
+  "video_length": 4,
+  "max_num_embodiments": 36
+}

checkpoint-15000/global_step15000/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:c17bea15836a31b9c8c9d7c1f40408ea5b4d1a614ee6401ccbe24ada54900712
+size 7127945825

checkpoint-15000/global_step15000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:028b641fa93a99eda5149c8e75eb0f9791a957cc5843700b181b062eda46dc04
+size 7127945121

checkpoint-15000/global_step15000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e49f5a459075b8df2a46ed147d169412293e5ffbd1bd74ff0f5220b46771957
+size 7127944737

checkpoint-15000/global_step15000/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:a4c25f045812b4f3c2f7b437eadd7f411d1df686fd9c1d7ce1c65bbb074cbad1
+size 7127944417

checkpoint-15000/global_step15000/mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c720a90e7fb8fcc477affe376b95217e41dc0fdd20c43b5bf1c4ad0956d6dd2
+size 22900273523

checkpoint-15000/latest

@@ -0,0 +1 @@
+global_step15000

checkpoint-15000/model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad118a81beb168fd2af42ee4dd34d2e5b1455cea97af4545ebfe8ad960a62025
+size 4912540968

checkpoint-15000/model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62763887a51db9d72c7ecbdfc3c6d4fb2f13a3cf1e7959ca593cba3b3ca2efd5
+size 4446192352

checkpoint-15000/model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:628791f8184f0eeca17639f21c212538d96be2fb77ed8858ab12c4b9ef78e10f
+size 4467286696

checkpoint-15000/model.safetensors.index.json

@@ -0,0 +1,732 @@
+{
+  "metadata": {
+    "total_parameters": 6912894784,
+    "total_size": 13825920640
+  },
+  "weight_map": {
+    "action_head.action_decoder.layer1.W": "model-00003-of-00003.safetensors",
+    "action_head.action_decoder.layer1.b": "model-00003-of-00003.safetensors",
+    "action_head.action_decoder.layer2.W": "model-00003-of-00003.safetensors",
+    "action_head.action_decoder.layer2.b": "model-00003-of-00003.safetensors",
+    "action_head.action_encoder.W1.W": "model-00003-of-00003.safetensors",
+    "action_head.action_encoder.W1.b": "model-00003-of-00003.safetensors",
+    "action_head.action_encoder.W2.W": "model-00003-of-00003.safetensors",
+    "action_head.action_encoder.W2.b": "model-00003-of-00003.safetensors",
+    "action_head.action_encoder.W3.W": "model-00003-of-00003.safetensors",
+    "action_head.action_encoder.W3.b": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.0.k_norm_sa.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.0.k_norm_vl.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.0.q_norm_sa.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.0.q_norm_vl.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.0.sa_mlp.w12.bias": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.0.sa_mlp.w12.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.0.sa_mlp.w3.bias": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.0.sa_mlp.w3.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.0.sa_proj.bias": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.0.sa_proj.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.0.sa_qkv.bias": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.0.sa_qkv.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.0.vl_mlp.w12.bias": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.0.vl_mlp.w12.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.0.vl_mlp.w3.bias": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.0.vl_mlp.w3.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.0.vl_proj.bias": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.0.vl_proj.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.0.vl_qkv.bias": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.0.vl_qkv.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.1.k_norm_sa.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.1.k_norm_vl.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.1.q_norm_sa.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.1.q_norm_vl.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.1.sa_mlp.w12.bias": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.1.sa_mlp.w12.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.1.sa_mlp.w3.bias": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.1.sa_mlp.w3.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.1.sa_proj.bias": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.1.sa_proj.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.1.sa_qkv.bias": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.1.sa_qkv.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.1.vl_mlp.w12.bias": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.1.vl_mlp.w12.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.1.vl_mlp.w3.bias": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.1.vl_mlp.w3.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.1.vl_proj.bias": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.1.vl_proj.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.1.vl_qkv.bias": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.1.vl_qkv.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.2.k_norm_sa.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.2.k_norm_vl.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.2.q_norm_sa.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.2.q_norm_vl.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.2.sa_mlp.w12.bias": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.2.sa_mlp.w12.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.2.sa_mlp.w3.bias": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.2.sa_mlp.w3.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.2.sa_proj.bias": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.2.sa_proj.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.2.sa_qkv.bias": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.2.sa_qkv.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.2.vl_mlp.w12.bias": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.2.vl_mlp.w12.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.2.vl_mlp.w3.bias": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.2.vl_mlp.w3.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.2.vl_proj.bias": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.2.vl_proj.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.2.vl_qkv.bias": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.2.vl_qkv.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.3.k_norm_sa.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.3.k_norm_vl.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.3.q_norm_sa.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.3.q_norm_vl.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.3.sa_mlp.w12.bias": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.3.sa_mlp.w12.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.3.sa_mlp.w3.bias": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.3.sa_mlp.w3.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.3.sa_proj.bias": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.3.sa_proj.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.3.sa_qkv.bias": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.3.sa_qkv.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.3.vl_mlp.w12.bias": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.3.vl_mlp.w12.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.3.vl_mlp.w3.bias": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.3.vl_mlp.w3.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.3.vl_proj.bias": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.3.vl_proj.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.3.vl_qkv.bias": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.3.vl_qkv.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.proj_out_1.bias": "model-00003-of-00003.safetensors",
+    "action_head.model.proj_out_1.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.proj_out_2.bias": "model-00003-of-00003.safetensors",
+    "action_head.model.proj_out_2.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.rope_embedder.freqs_cis_0": "model-00003-of-00003.safetensors",
+    "action_head.model.rope_embedder.freqs_cis_1": "model-00003-of-00003.safetensors",
+    "action_head.model.single_blocks.0.k_norm.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.single_blocks.0.linear1.bias": "model-00003-of-00003.safetensors",
+    "action_head.model.single_blocks.0.linear1.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.single_blocks.0.linear2.bias": "model-00003-of-00003.safetensors",
+    "action_head.model.single_blocks.0.linear2.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.single_blocks.0.mlp_proj.bias": "model-00003-of-00003.safetensors",
+    "action_head.model.single_blocks.0.mlp_proj.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.single_blocks.0.q_norm.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.single_blocks.1.k_norm.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.single_blocks.1.linear1.bias": "model-00003-of-00003.safetensors",
+    "action_head.model.single_blocks.1.linear1.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.single_blocks.1.linear2.bias": "model-00003-of-00003.safetensors",
+    "action_head.model.single_blocks.1.linear2.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.single_blocks.1.mlp_proj.bias": "model-00003-of-00003.safetensors",
+    "action_head.model.single_blocks.1.mlp_proj.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.single_blocks.1.q_norm.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.single_blocks.2.k_norm.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.single_blocks.2.linear1.bias": "model-00003-of-00003.safetensors",
+    "action_head.model.single_blocks.2.linear1.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.single_blocks.2.linear2.bias": "model-00003-of-00003.safetensors",
+    "action_head.model.single_blocks.2.linear2.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.single_blocks.2.mlp_proj.bias": "model-00003-of-00003.safetensors",
+    "action_head.model.single_blocks.2.mlp_proj.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.single_blocks.2.q_norm.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.single_blocks.3.k_norm.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.single_blocks.3.linear1.bias": "model-00003-of-00003.safetensors",
+    "action_head.model.single_blocks.3.linear1.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.single_blocks.3.linear2.bias": "model-00003-of-00003.safetensors",
+    "action_head.model.single_blocks.3.linear2.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.single_blocks.3.mlp_proj.bias": "model-00003-of-00003.safetensors",
+    "action_head.model.single_blocks.3.mlp_proj.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.single_blocks.3.q_norm.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.single_blocks.4.k_norm.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.single_blocks.4.linear1.bias": "model-00003-of-00003.safetensors",
+    "action_head.model.single_blocks.4.linear1.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.single_blocks.4.linear2.bias": "model-00003-of-00003.safetensors",
+    "action_head.model.single_blocks.4.linear2.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.single_blocks.4.mlp_proj.bias": "model-00003-of-00003.safetensors",
+    "action_head.model.single_blocks.4.mlp_proj.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.single_blocks.4.q_norm.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.single_blocks.5.k_norm.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.single_blocks.5.linear1.bias": "model-00003-of-00003.safetensors",
+    "action_head.model.single_blocks.5.linear1.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.single_blocks.5.linear2.bias": "model-00003-of-00003.safetensors",
+    "action_head.model.single_blocks.5.linear2.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.single_blocks.5.mlp_proj.bias": "model-00003-of-00003.safetensors",
+    "action_head.model.single_blocks.5.mlp_proj.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.single_blocks.5.q_norm.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.single_blocks.6.k_norm.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.single_blocks.6.linear1.bias": "model-00003-of-00003.safetensors",
+    "action_head.model.single_blocks.6.linear1.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.single_blocks.6.linear2.bias": "model-00003-of-00003.safetensors",
+    "action_head.model.single_blocks.6.linear2.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.single_blocks.6.mlp_proj.bias": "model-00003-of-00003.safetensors",
+    "action_head.model.single_blocks.6.mlp_proj.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.single_blocks.6.q_norm.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.single_blocks.7.k_norm.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.single_blocks.7.linear1.bias": "model-00003-of-00003.safetensors",
+    "action_head.model.single_blocks.7.linear1.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.single_blocks.7.linear2.bias": "model-00003-of-00003.safetensors",
+    "action_head.model.single_blocks.7.linear2.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.single_blocks.7.mlp_proj.bias": "model-00003-of-00003.safetensors",
+    "action_head.model.single_blocks.7.mlp_proj.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.single_blocks.7.q_norm.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.timestep_encoder.timestep_embedder.linear_1.bias": "model-00003-of-00003.safetensors",
+    "action_head.model.timestep_encoder.timestep_embedder.linear_1.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.timestep_encoder.timestep_embedder.linear_2.bias": "model-00003-of-00003.safetensors",
+    "action_head.model.timestep_encoder.timestep_embedder.linear_2.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.vl_proj_to_sa.bias": "model-00003-of-00003.safetensors",
+    "action_head.model.vl_proj_to_sa.weight": "model-00003-of-00003.safetensors",
+    "action_head.position_embedding.weight": "model-00003-of-00003.safetensors",
+    "action_head.state_encoder.layer1.W": "model-00003-of-00003.safetensors",
+    "action_head.state_encoder.layer1.b": "model-00003-of-00003.safetensors",
+    "action_head.state_encoder.layer2.W": "model-00003-of-00003.safetensors",
+    "action_head.state_encoder.layer2.b": "model-00003-of-00003.safetensors",
+    "backbone.meta_emb": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.lm_head.weight": "model-00003-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.embed_tokens.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.0.layer.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.0.layer.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.0.layer.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.0.layer.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.0.layer.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.0.layer.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.0.layer.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.0.layer.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.0.layer.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.0.layer.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.0.layer.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.1.layer.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.1.layer.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.1.layer.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.1.layer.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.1.layer.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.1.layer.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.1.layer.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.1.layer.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.1.layer.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.1.layer.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.1.layer.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.10.layer.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.10.layer.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.10.layer.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.10.layer.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.10.layer.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.10.layer.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.10.layer.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.10.layer.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.10.layer.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.10.layer.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.10.layer.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.11.layer.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.11.layer.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.11.layer.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.11.layer.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.11.layer.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.11.layer.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.11.layer.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.11.layer.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.11.layer.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.11.layer.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.11.layer.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.12.layer.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.12.layer.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.12.layer.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.12.layer.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.12.layer.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.12.layer.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.12.layer.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.12.layer.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.12.layer.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.12.layer.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.12.layer.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.13.layer.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.13.layer.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.13.layer.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.13.layer.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.13.layer.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.13.layer.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.13.layer.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.13.layer.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.13.layer.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.13.layer.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.13.layer.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.14.layer.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.14.layer.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.14.layer.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.14.layer.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.14.layer.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.14.layer.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.14.layer.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.14.layer.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.14.layer.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.14.layer.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.14.layer.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.15.layer.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.15.layer.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.15.layer.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.15.layer.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.15.layer.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.15.layer.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.15.layer.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.15.layer.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.15.layer.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.15.layer.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.15.layer.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.16.layer.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.16.layer.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.16.layer.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.16.layer.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.16.layer.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.16.layer.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.16.layer.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.16.layer.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.16.layer.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.16.layer.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.16.layer.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.17.layer.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.17.layer.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.17.layer.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.17.layer.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.17.layer.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.17.layer.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.17.layer.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.17.layer.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.17.layer.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.17.layer.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.17.layer.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.2.layer.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.2.layer.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.2.layer.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.2.layer.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.2.layer.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.2.layer.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.2.layer.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.2.layer.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.2.layer.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.2.layer.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.2.layer.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.3.layer.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.3.layer.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.3.layer.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.3.layer.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.3.layer.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.3.layer.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.3.layer.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.3.layer.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.3.layer.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.3.layer.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.3.layer.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.4.layer.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.4.layer.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.4.layer.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.4.layer.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.4.layer.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.4.layer.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.4.layer.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.4.layer.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.4.layer.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.4.layer.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.4.layer.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.5.layer.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.5.layer.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.5.layer.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.5.layer.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.5.layer.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.5.layer.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.5.layer.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.5.layer.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.5.layer.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.5.layer.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.5.layer.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.6.layer.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.6.layer.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.6.layer.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.6.layer.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.6.layer.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.6.layer.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.6.layer.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.6.layer.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.6.layer.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.6.layer.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.6.layer.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.7.layer.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.7.layer.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.7.layer.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.7.layer.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.7.layer.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.7.layer.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.7.layer.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.7.layer.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.7.layer.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.7.layer.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.7.layer.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.8.layer.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.8.layer.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.8.layer.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.8.layer.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.8.layer.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.8.layer.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.8.layer.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.8.layer.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.8.layer.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.8.layer.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.8.layer.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.9.layer.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.9.layer.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.9.layer.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.9.layer.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.9.layer.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.9.layer.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.9.layer.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.9.layer.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.9.layer.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.9.layer.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.9.layer.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.norm.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.0.attn.proj.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.0.attn.proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.0.attn.qkv.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.0.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.0.mlp.linear_fc1.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.0.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.0.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.0.mlp.linear_fc2.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.0.norm1.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.0.norm1.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.0.norm2.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.0.norm2.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.1.attn.proj.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.1.attn.proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.1.attn.qkv.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.1.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.1.mlp.linear_fc1.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.1.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.1.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.1.mlp.linear_fc2.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.1.norm1.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.1.norm1.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.1.norm2.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.1.norm2.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.10.attn.proj.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.10.attn.proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.10.attn.qkv.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.10.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.10.mlp.linear_fc1.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.10.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.10.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.10.mlp.linear_fc2.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.10.norm1.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.10.norm1.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.10.norm2.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.10.norm2.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.11.attn.proj.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.11.attn.proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.11.attn.qkv.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.11.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.11.mlp.linear_fc1.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.11.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.11.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.11.mlp.linear_fc2.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.11.norm1.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.11.norm1.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.11.norm2.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.11.norm2.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.12.attn.proj.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.12.attn.proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.12.attn.qkv.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.12.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.12.mlp.linear_fc1.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.12.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.12.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.12.mlp.linear_fc2.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.12.norm1.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.12.norm1.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.12.norm2.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.12.norm2.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.13.attn.proj.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.13.attn.proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.13.attn.qkv.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.13.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.13.mlp.linear_fc1.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.13.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.13.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.13.mlp.linear_fc2.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.13.norm1.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.13.norm1.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.13.norm2.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.13.norm2.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.14.attn.proj.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.14.attn.proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.14.attn.qkv.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.14.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.14.mlp.linear_fc1.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.14.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.14.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.14.mlp.linear_fc2.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.14.norm1.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.14.norm1.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.14.norm2.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.14.norm2.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.15.attn.proj.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.15.attn.proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.15.attn.qkv.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.15.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.15.mlp.linear_fc1.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.15.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.15.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.15.mlp.linear_fc2.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.15.norm1.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.15.norm1.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.15.norm2.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.15.norm2.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.16.attn.proj.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.16.attn.proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.16.attn.qkv.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.16.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.16.mlp.linear_fc1.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.16.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.16.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.16.mlp.linear_fc2.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.16.norm1.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.16.norm1.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.16.norm2.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.16.norm2.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.17.attn.proj.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.17.attn.proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.17.attn.qkv.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.17.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.17.mlp.linear_fc1.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.17.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.17.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.17.mlp.linear_fc2.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.17.norm1.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.17.norm1.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.17.norm2.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.17.norm2.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.18.attn.proj.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.18.attn.proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.18.attn.qkv.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.18.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.18.mlp.linear_fc1.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.18.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.18.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.18.mlp.linear_fc2.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.18.norm1.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.18.norm1.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.18.norm2.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.18.norm2.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.19.attn.proj.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.19.attn.proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.19.attn.qkv.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.19.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.19.mlp.linear_fc1.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.19.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.19.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.19.mlp.linear_fc2.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.19.norm1.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.19.norm1.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.19.norm2.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.19.norm2.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.2.attn.proj.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.2.attn.proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.2.attn.qkv.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.2.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.2.mlp.linear_fc1.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.2.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.2.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.2.mlp.linear_fc2.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.2.norm1.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.2.norm1.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.2.norm2.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.2.norm2.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.20.attn.proj.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.20.attn.proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.20.attn.qkv.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.20.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.20.mlp.linear_fc1.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.20.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.20.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.20.mlp.linear_fc2.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.20.norm1.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.20.norm1.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.20.norm2.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.20.norm2.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.21.attn.proj.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.21.attn.proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.21.attn.qkv.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.21.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.21.mlp.linear_fc1.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.21.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.21.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.21.mlp.linear_fc2.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.21.norm1.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.21.norm1.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.21.norm2.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.21.norm2.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.22.attn.proj.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.22.attn.proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.22.attn.qkv.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.22.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.22.mlp.linear_fc1.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.22.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.22.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.22.mlp.linear_fc2.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.22.norm1.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.22.norm1.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.22.norm2.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.22.norm2.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.23.attn.proj.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.23.attn.proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.23.attn.qkv.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.23.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.23.mlp.linear_fc1.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.23.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.23.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.23.mlp.linear_fc2.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.23.norm1.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.23.norm1.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.23.norm2.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.23.norm2.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.24.attn.proj.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.24.attn.proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.24.attn.qkv.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.24.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.24.mlp.linear_fc1.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.24.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.24.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.24.mlp.linear_fc2.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.24.norm1.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.24.norm1.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.24.norm2.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.24.norm2.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.25.attn.proj.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.25.attn.proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.25.attn.qkv.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.25.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.25.mlp.linear_fc1.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.25.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.25.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.25.mlp.linear_fc2.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.25.norm1.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.25.norm1.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.25.norm2.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.25.norm2.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.26.attn.proj.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.26.attn.proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.26.attn.qkv.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.26.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.26.mlp.linear_fc1.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.26.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.26.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.26.mlp.linear_fc2.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.26.norm1.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.26.norm1.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.26.norm2.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.26.norm2.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.3.attn.proj.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.3.attn.proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.3.attn.qkv.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.3.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.3.mlp.linear_fc1.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.3.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.3.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.3.mlp.linear_fc2.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.3.norm1.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.3.norm1.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.3.norm2.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.3.norm2.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.4.attn.proj.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.4.attn.proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.4.attn.qkv.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.4.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.4.mlp.linear_fc1.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.4.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.4.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.4.mlp.linear_fc2.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.4.norm1.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.4.norm1.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.4.norm2.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.4.norm2.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.5.attn.proj.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.5.attn.proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.5.attn.qkv.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.5.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.5.mlp.linear_fc1.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.5.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.5.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.5.mlp.linear_fc2.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.5.norm1.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.5.norm1.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.5.norm2.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.5.norm2.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.6.attn.proj.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.6.attn.proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.6.attn.qkv.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.6.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.6.mlp.linear_fc1.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.6.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.6.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.6.mlp.linear_fc2.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.6.norm1.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.6.norm1.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.6.norm2.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.6.norm2.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.7.attn.proj.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.7.attn.proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.7.attn.qkv.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.7.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.7.mlp.linear_fc1.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.7.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.7.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.7.mlp.linear_fc2.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.7.norm1.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.7.norm1.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.7.norm2.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.7.norm2.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.8.attn.proj.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.8.attn.proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.8.attn.qkv.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.8.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.8.mlp.linear_fc1.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.8.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.8.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.8.mlp.linear_fc2.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.8.norm1.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.8.norm1.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.8.norm2.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.8.norm2.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.9.attn.proj.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.9.attn.proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.9.attn.qkv.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.9.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.9.mlp.linear_fc1.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.9.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.9.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.9.mlp.linear_fc2.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.9.norm1.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.9.norm1.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.9.norm2.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.9.norm2.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.deepstack_merger_list.0.linear_fc1.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.deepstack_merger_list.0.linear_fc1.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.deepstack_merger_list.0.linear_fc2.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.deepstack_merger_list.0.linear_fc2.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.deepstack_merger_list.0.norm.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.deepstack_merger_list.0.norm.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.deepstack_merger_list.1.linear_fc1.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.deepstack_merger_list.1.linear_fc1.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.deepstack_merger_list.1.linear_fc2.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.deepstack_merger_list.1.linear_fc2.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.deepstack_merger_list.1.norm.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.deepstack_merger_list.1.norm.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.deepstack_merger_list.2.linear_fc1.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.deepstack_merger_list.2.linear_fc1.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.deepstack_merger_list.2.linear_fc2.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.deepstack_merger_list.2.linear_fc2.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.deepstack_merger_list.2.norm.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.deepstack_merger_list.2.norm.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.merger.linear_fc1.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.merger.linear_fc1.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.merger.linear_fc2.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.merger.linear_fc2.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.merger.norm.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.merger.norm.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.patch_embed.proj.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.patch_embed.proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.pos_embed.weight": "model-00001-of-00003.safetensors"
+  }
+}

checkpoint-15000/processor_config.json

@@ -0,0 +1,3250 @@
+{
+  "processor_class": "AlinVLAv0Processor",
+  "processor_kwargs": {
+    "modality_configs": {
+      "humanoid_everyday_g1": {
+        "video": {
+          "delta_indices": [
+            -6,
+            -4,
+            -2,
+            0
+          ],
+          "modality_keys": [
+            "egocentric_resized"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "state": {
+          "delta_indices": [
+            0
+          ],
+          "modality_keys": [
+            "left_arm",
+            "left_hand",
+            "right_arm",
+            "right_hand"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "action": {
+          "delta_indices": [
+            0,
+            1,
+            2,
+            3,
+            4,
+            5,
+            6,
+            7,
+            8,
+            9,
+            10,
+            11,
+            12,
+            13,
+            14,
+            15
+          ],
+          "modality_keys": [
+            "left_arm",
+            "left_hand",
+            "right_arm",
+            "right_hand"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": [
+            {
+              "rep": "ABSOLUTE",
+              "type": "NON_EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "ABSOLUTE",
+              "type": "NON_EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "ABSOLUTE",
+              "type": "NON_EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "ABSOLUTE",
+              "type": "NON_EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            }
+          ]
+        },
+        "language": {
+          "delta_indices": [
+            0
+          ],
+          "modality_keys": [
+            "annotation.human.action.task_description"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        }
+      },
+      "kuka": {
+        "video": {
+          "delta_indices": [
+            -6,
+            -4,
+            -2,
+            0
+          ],
+          "modality_keys": [
+            "primary"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "state": {
+          "delta_indices": [
+            0
+          ],
+          "modality_keys": [
+            "end_effector_position",
+            "end_effector_rotation",
+            "gripper_position"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "action": {
+          "delta_indices": [
+            0,
+            1,
+            2,
+            3,
+            4,
+            5,
+            6,
+            7,
+            8,
+            9,
+            10,
+            11,
+            12,
+            13,
+            14,
+            15
+          ],
+          "modality_keys": [
+            "end_effector_position",
+            "end_effector_rotation",
+            "gripper_close"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": [
+            {
+              "rep": "DELTA",
+              "type": "EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "DELTA",
+              "type": "EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "ABSOLUTE",
+              "type": "NON_EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            }
+          ]
+        },
+        "language": {
+          "delta_indices": [
+            0
+          ],
+          "modality_keys": [
+            "annotation.human.action.task_description"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        }
+      },
+      "cmu_stretch": {
+        "video": {
+          "delta_indices": [
+            -6,
+            -4,
+            -2,
+            0
+          ],
+          "modality_keys": [
+            "primary"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "state": {
+          "delta_indices": [
+            0
+          ],
+          "modality_keys": [
+            "end_effector_position",
+            "end_effector_rotation",
+            "gripper_position"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "action": {
+          "delta_indices": [
+            0,
+            1,
+            2,
+            3,
+            4,
+            5,
+            6,
+            7,
+            8,
+            9,
+            10,
+            11,
+            12,
+            13,
+            14,
+            15
+          ],
+          "modality_keys": [
+            "end_effector_position",
+            "end_effector_rotation",
+            "gripper_close"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": [
+            {
+              "rep": "DELTA",
+              "type": "EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "DELTA",
+              "type": "EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "ABSOLUTE",
+              "type": "NON_EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            }
+          ]
+        },
+        "language": {
+          "delta_indices": [
+            0
+          ],
+          "modality_keys": [
+            "annotation.human.action.task_description"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        }
+      },
+      "stanford_hydra_dataset_converted_externally_to_rlds": {
+        "video": {
+          "delta_indices": [
+            -6,
+            -4,
+            -2,
+            0
+          ],
+          "modality_keys": [
+            "primary",
+            "wrist"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "state": {
+          "delta_indices": [
+            0
+          ],
+          "modality_keys": [
+            "end_effector_position",
+            "end_effector_rotation",
+            "gripper_position"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "action": {
+          "delta_indices": [
+            0,
+            1,
+            2,
+            3,
+            4,
+            5,
+            6,
+            7,
+            8,
+            9,
+            10,
+            11,
+            12,
+            13,
+            14,
+            15
+          ],
+          "modality_keys": [
+            "end_effector_position",
+            "end_effector_rotation",
+            "gripper_close"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": [
+            {
+              "rep": "DELTA",
+              "type": "EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "DELTA",
+              "type": "EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "ABSOLUTE",
+              "type": "NON_EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            }
+          ]
+        },
+        "language": {
+          "delta_indices": [
+            0
+          ],
+          "modality_keys": [
+            "annotation.human.action.task_description"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        }
+      },
+      "iamlab_cmu_pickup_insert_converted_externally_to_rlds": {
+        "video": {
+          "delta_indices": [
+            -6,
+            -4,
+            -2,
+            0
+          ],
+          "modality_keys": [
+            "primary",
+            "wrist"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "state": {
+          "delta_indices": [
+            0
+          ],
+          "modality_keys": [
+            "end_effector_position",
+            "end_effector_rotation",
+            "gripper_position"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "action": {
+          "delta_indices": [
+            0,
+            1,
+            2,
+            3,
+            4,
+            5,
+            6,
+            7,
+            8,
+            9,
+            10,
+            11,
+            12,
+            13,
+            14,
+            15
+          ],
+          "modality_keys": [
+            "end_effector_position",
+            "end_effector_rotation",
+            "gripper_close"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": [
+            {
+              "rep": "DELTA",
+              "type": "EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "DELTA",
+              "type": "EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "ABSOLUTE",
+              "type": "NON_EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            }
+          ]
+        },
+        "language": {
+          "delta_indices": [
+            0
+          ],
+          "modality_keys": [
+            "annotation.human.action.task_description"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        }
+      },
+      "berkeley_fanuc_manipulation": {
+        "video": {
+          "delta_indices": [
+            -6,
+            -4,
+            -2,
+            0
+          ],
+          "modality_keys": [
+            "primary",
+            "wrist"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "state": {
+          "delta_indices": [
+            0
+          ],
+          "modality_keys": [
+            "joint_position",
+            "gripper_position"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "action": {
+          "delta_indices": [
+            0,
+            1,
+            2,
+            3,
+            4,
+            5,
+            6,
+            7,
+            8,
+            9,
+            10,
+            11,
+            12,
+            13,
+            14,
+            15
+          ],
+          "modality_keys": [
+            "end_effector_position",
+            "end_effector_rotation",
+            "gripper_close"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": [
+            {
+              "rep": "DELTA",
+              "type": "EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "DELTA",
+              "type": "EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "ABSOLUTE",
+              "type": "NON_EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            }
+          ]
+        },
+        "language": {
+          "delta_indices": [
+            0
+          ],
+          "modality_keys": [
+            "annotation.human.action.task_description"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        }
+      },
+      "viola": {
+        "video": {
+          "delta_indices": [
+            -6,
+            -4,
+            -2,
+            0
+          ],
+          "modality_keys": [
+            "primary",
+            "wrist"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "state": {
+          "delta_indices": [
+            0
+          ],
+          "modality_keys": [
+            "joint_position",
+            "gripper_position"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "action": {
+          "delta_indices": [
+            0,
+            1,
+            2,
+            3,
+            4,
+            5,
+            6,
+            7,
+            8,
+            9,
+            10,
+            11,
+            12,
+            13,
+            14,
+            15
+          ],
+          "modality_keys": [
+            "end_effector_position",
+            "end_effector_rotation",
+            "gripper_close"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": [
+            {
+              "rep": "DELTA",
+              "type": "EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "DELTA",
+              "type": "EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "ABSOLUTE",
+              "type": "NON_EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            }
+          ]
+        },
+        "language": {
+          "delta_indices": [
+            0
+          ],
+          "modality_keys": [
+            "annotation.human.action.task_description"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        }
+      },
+      "galaxea": {
+        "video": {
+          "delta_indices": [
+            -6,
+            -4,
+            -2,
+            0
+          ],
+          "modality_keys": [
+            "primary",
+            "wrist_left",
+            "wrist_right"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "state": {
+          "delta_indices": [
+            0
+          ],
+          "modality_keys": [
+            "state"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "action": {
+          "delta_indices": [
+            0,
+            1,
+            2,
+            3,
+            4,
+            5,
+            6,
+            7,
+            8,
+            9,
+            10,
+            11,
+            12,
+            13,
+            14,
+            15
+          ],
+          "modality_keys": [
+            "action"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": [
+            {
+              "rep": "ABSOLUTE",
+              "type": "NON_EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            }
+          ]
+        },
+        "language": {
+          "delta_indices": [
+            0
+          ],
+          "modality_keys": [
+            "annotation.human.action.task_description"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        }
+      },
+      "utaustin_mutex": {
+        "video": {
+          "delta_indices": [
+            -6,
+            -4,
+            -2,
+            0
+          ],
+          "modality_keys": [
+            "primary",
+            "wrist"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "state": {
+          "delta_indices": [
+            0
+          ],
+          "modality_keys": [
+            "joint_position",
+            "gripper_position"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "action": {
+          "delta_indices": [
+            0,
+            1,
+            2,
+            3,
+            4,
+            5,
+            6,
+            7,
+            8,
+            9,
+            10,
+            11,
+            12,
+            13,
+            14,
+            15
+          ],
+          "modality_keys": [
+            "end_effector_position",
+            "end_effector_rotation",
+            "gripper_close"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": [
+            {
+              "rep": "DELTA",
+              "type": "EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "DELTA",
+              "type": "EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "ABSOLUTE",
+              "type": "NON_EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            }
+          ]
+        },
+        "language": {
+          "delta_indices": [
+            0
+          ],
+          "modality_keys": [
+            "annotation.human.action.task_description"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        }
+      },
+      "dobbe": {
+        "video": {
+          "delta_indices": [
+            -6,
+            -4,
+            -2,
+            0
+          ],
+          "modality_keys": [
+            "wrist"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "state": {
+          "delta_indices": [
+            0
+          ],
+          "modality_keys": [
+            "end_effector_position",
+            "end_effector_rotation",
+            "gripper_position"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "action": {
+          "delta_indices": [
+            0,
+            1,
+            2,
+            3,
+            4,
+            5,
+            6,
+            7,
+            8,
+            9,
+            10,
+            11,
+            12,
+            13,
+            14,
+            15
+          ],
+          "modality_keys": [
+            "end_effector_position",
+            "end_effector_rotation",
+            "gripper_close"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": [
+            {
+              "rep": "DELTA",
+              "type": "EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "DELTA",
+              "type": "EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "ABSOLUTE",
+              "type": "NON_EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            }
+          ]
+        },
+        "language": {
+          "delta_indices": [
+            0
+          ],
+          "modality_keys": [
+            "annotation.human.action.task_description"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        }
+      },
+      "taco_play": {
+        "video": {
+          "delta_indices": [
+            -6,
+            -4,
+            -2,
+            0
+          ],
+          "modality_keys": [
+            "primary",
+            "wrist"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "state": {
+          "delta_indices": [
+            0
+          ],
+          "modality_keys": [
+            "end_effector_position",
+            "end_effector_rotation",
+            "gripper_position"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "action": {
+          "delta_indices": [
+            0,
+            1,
+            2,
+            3,
+            4,
+            5,
+            6,
+            7,
+            8,
+            9,
+            10,
+            11,
+            12,
+            13,
+            14,
+            15
+          ],
+          "modality_keys": [
+            "end_effector_position",
+            "end_effector_rotation",
+            "gripper_close"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": [
+            {
+              "rep": "DELTA",
+              "type": "EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "DELTA",
+              "type": "EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "ABSOLUTE",
+              "type": "NON_EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            }
+          ]
+        },
+        "language": {
+          "delta_indices": [
+            0
+          ],
+          "modality_keys": [
+            "annotation.human.action.task_description"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        }
+      },
+      "humanoid_everyday_h1": {
+        "video": {
+          "delta_indices": [
+            -6,
+            -4,
+            -2,
+            0
+          ],
+          "modality_keys": [
+            "egocentric_resized"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "state": {
+          "delta_indices": [
+            0
+          ],
+          "modality_keys": [
+            "left_arm",
+            "left_hand",
+            "right_arm",
+            "right_hand"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "action": {
+          "delta_indices": [
+            0,
+            1,
+            2,
+            3,
+            4,
+            5,
+            6,
+            7,
+            8,
+            9,
+            10,
+            11,
+            12,
+            13,
+            14,
+            15
+          ],
+          "modality_keys": [
+            "left_arm",
+            "left_hand",
+            "right_arm",
+            "right_hand"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": [
+            {
+              "rep": "ABSOLUTE",
+              "type": "NON_EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "ABSOLUTE",
+              "type": "NON_EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "ABSOLUTE",
+              "type": "NON_EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "ABSOLUTE",
+              "type": "NON_EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            }
+          ]
+        },
+        "language": {
+          "delta_indices": [
+            0
+          ],
+          "modality_keys": [
+            "annotation.human.action.task_description"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        }
+      },
+      "berkeley_autolab_ur5": {
+        "video": {
+          "delta_indices": [
+            -6,
+            -4,
+            -2,
+            0
+          ],
+          "modality_keys": [
+            "primary",
+            "wrist"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "state": {
+          "delta_indices": [
+            0
+          ],
+          "modality_keys": [
+            "end_effector_position",
+            "end_effector_rotation",
+            "gripper_position"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "action": {
+          "delta_indices": [
+            0,
+            1,
+            2,
+            3,
+            4,
+            5,
+            6,
+            7,
+            8,
+            9,
+            10,
+            11,
+            12,
+            13,
+            14,
+            15
+          ],
+          "modality_keys": [
+            "end_effector_position",
+            "end_effector_rotation",
+            "gripper_close"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": [
+            {
+              "rep": "DELTA",
+              "type": "EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "DELTA",
+              "type": "EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "ABSOLUTE",
+              "type": "NON_EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            }
+          ]
+        },
+        "language": {
+          "delta_indices": [
+            0
+          ],
+          "modality_keys": [
+            "annotation.human.action.task_description"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        }
+      },
+      "jaco_play": {
+        "video": {
+          "delta_indices": [
+            -6,
+            -4,
+            -2,
+            0
+          ],
+          "modality_keys": [
+            "primary",
+            "wrist"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "state": {
+          "delta_indices": [
+            0
+          ],
+          "modality_keys": [
+            "end_effector_position",
+            "end_effector_rotation",
+            "gripper_position"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "action": {
+          "delta_indices": [
+            0,
+            1,
+            2,
+            3,
+            4,
+            5,
+            6,
+            7,
+            8,
+            9,
+            10,
+            11,
+            12,
+            13,
+            14,
+            15
+          ],
+          "modality_keys": [
+            "end_effector_position",
+            "end_effector_rotation",
+            "gripper_close"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": [
+            {
+              "rep": "DELTA",
+              "type": "EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "DELTA",
+              "type": "EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "ABSOLUTE",
+              "type": "NON_EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            }
+          ]
+        },
+        "language": {
+          "delta_indices": [
+            0
+          ],
+          "modality_keys": [
+            "annotation.human.action.task_description"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        }
+      },
+      "furniture_bench_dataset_converted_externally_to_rlds": {
+        "video": {
+          "delta_indices": [
+            -6,
+            -4,
+            -2,
+            0
+          ],
+          "modality_keys": [
+            "primary",
+            "wrist"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "state": {
+          "delta_indices": [
+            0
+          ],
+          "modality_keys": [
+            "end_effector_position",
+            "end_effector_rotation",
+            "gripper_position"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "action": {
+          "delta_indices": [
+            0,
+            1,
+            2,
+            3,
+            4,
+            5,
+            6,
+            7,
+            8,
+            9,
+            10,
+            11,
+            12,
+            13,
+            14,
+            15
+          ],
+          "modality_keys": [
+            "end_effector_position",
+            "end_effector_rotation",
+            "gripper_close"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": [
+            {
+              "rep": "DELTA",
+              "type": "EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "DELTA",
+              "type": "EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "ABSOLUTE",
+              "type": "NON_EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            }
+          ]
+        },
+        "language": {
+          "delta_indices": [
+            0
+          ],
+          "modality_keys": [
+            "annotation.human.action.task_description"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        }
+      },
+      "berkeley_cable_routing": {
+        "video": {
+          "delta_indices": [
+            -6,
+            -4,
+            -2,
+            0
+          ],
+          "modality_keys": [
+            "primary",
+            "secondary",
+            "wrist"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "state": {
+          "delta_indices": [
+            0
+          ],
+          "modality_keys": [
+            "joint_position"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "action": {
+          "delta_indices": [
+            0,
+            1,
+            2,
+            3,
+            4,
+            5,
+            6,
+            7,
+            8,
+            9,
+            10,
+            11,
+            12,
+            13,
+            14,
+            15
+          ],
+          "modality_keys": [
+            "end_effector_position",
+            "end_effector_rotation",
+            "gripper_close"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": [
+            {
+              "rep": "DELTA",
+              "type": "EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "DELTA",
+              "type": "EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "ABSOLUTE",
+              "type": "NON_EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            }
+          ]
+        },
+        "language": {
+          "delta_indices": [
+            0
+          ],
+          "modality_keys": [
+            "annotation.human.action.task_description"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        }
+      },
+      "nyu_franka_play_dataset_converted_externally_to_rlds": {
+        "video": {
+          "delta_indices": [
+            -6,
+            -4,
+            -2,
+            0
+          ],
+          "modality_keys": [
+            "primary",
+            "secondary"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "state": {
+          "delta_indices": [
+            0
+          ],
+          "modality_keys": [
+            "end_effector_position",
+            "end_effector_rotation",
+            "gripper_position"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "action": {
+          "delta_indices": [
+            0,
+            1,
+            2,
+            3,
+            4,
+            5,
+            6,
+            7,
+            8,
+            9,
+            10,
+            11,
+            12,
+            13,
+            14,
+            15
+          ],
+          "modality_keys": [
+            "end_effector_position",
+            "end_effector_rotation",
+            "gripper_close"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": [
+            {
+              "rep": "DELTA",
+              "type": "EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "DELTA",
+              "type": "EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "ABSOLUTE",
+              "type": "NON_EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            }
+          ]
+        },
+        "language": {
+          "delta_indices": [
+            0
+          ],
+          "modality_keys": [
+            "annotation.human.action.task_description"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        }
+      },
+      "bridge_orig": {
+        "video": {
+          "delta_indices": [
+            -6,
+            -4,
+            -2,
+            0
+          ],
+          "modality_keys": [
+            "primary",
+            "secondary"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "state": {
+          "delta_indices": [
+            0
+          ],
+          "modality_keys": [
+            "end_effector_position",
+            "end_effector_rotation",
+            "gripper_position"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "action": {
+          "delta_indices": [
+            0,
+            1,
+            2,
+            3,
+            4,
+            5,
+            6,
+            7,
+            8,
+            9,
+            10,
+            11,
+            12,
+            13,
+            14,
+            15
+          ],
+          "modality_keys": [
+            "end_effector_position",
+            "end_effector_rotation",
+            "gripper_close"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": [
+            {
+              "rep": "DELTA",
+              "type": "EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "DELTA",
+              "type": "EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "ABSOLUTE",
+              "type": "NON_EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            }
+          ]
+        },
+        "language": {
+          "delta_indices": [
+            0
+          ],
+          "modality_keys": [
+            "annotation.human.action.task_description"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        }
+      },
+      "droid": {
+        "video": {
+          "delta_indices": [
+            -6,
+            -4,
+            -2,
+            0
+          ],
+          "modality_keys": [
+            "primary",
+            "secondary",
+            "wrist"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "state": {
+          "delta_indices": [
+            0
+          ],
+          "modality_keys": [
+            "end_effector_position",
+            "end_effector_rotation",
+            "gripper_position"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "action": {
+          "delta_indices": [
+            0,
+            1,
+            2,
+            3,
+            4,
+            5,
+            6,
+            7,
+            8,
+            9,
+            10,
+            11,
+            12,
+            13,
+            14,
+            15
+          ],
+          "modality_keys": [
+            "end_effector_position",
+            "end_effector_rotation",
+            "gripper_close"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": [
+            {
+              "rep": "DELTA",
+              "type": "EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "DELTA",
+              "type": "EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "ABSOLUTE",
+              "type": "NON_EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            }
+          ]
+        },
+        "language": {
+          "delta_indices": [
+            0
+          ],
+          "modality_keys": [
+            "annotation.human.action.task_description"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        }
+      },
+      "agibot_gripper": {
+        "video": {
+          "delta_indices": [
+            -6,
+            -4,
+            -2,
+            0
+          ],
+          "modality_keys": [
+            "primary",
+            "wrist_left",
+            "wrist_right"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "state": {
+          "delta_indices": [
+            0
+          ],
+          "modality_keys": [
+            "state"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "action": {
+          "delta_indices": [
+            0,
+            1,
+            2,
+            3,
+            4,
+            5,
+            6,
+            7,
+            8,
+            9,
+            10,
+            11,
+            12,
+            13,
+            14,
+            15
+          ],
+          "modality_keys": [
+            "action"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": [
+            {
+              "rep": "ABSOLUTE",
+              "type": "NON_EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            }
+          ]
+        },
+        "language": {
+          "delta_indices": [
+            0
+          ],
+          "modality_keys": [
+            "annotation.human.action.task_description"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        }
+      },
+      "simulation_gr1": {
+        "video": {
+          "delta_indices": [
+            -6,
+            -4,
+            -2,
+            0
+          ],
+          "modality_keys": [
+            "ego_view"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "state": {
+          "delta_indices": [
+            0
+          ],
+          "modality_keys": [
+            "left_arm",
+            "left_hand",
+            "left_leg",
+            "neck",
+            "right_arm",
+            "right_hand",
+            "right_leg",
+            "waist"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "action": {
+          "delta_indices": [
+            0,
+            1,
+            2,
+            3,
+            4,
+            5,
+            6,
+            7,
+            8,
+            9,
+            10,
+            11,
+            12,
+            13,
+            14,
+            15
+          ],
+          "modality_keys": [
+            "left_arm",
+            "left_hand",
+            "left_leg",
+            "neck",
+            "right_arm",
+            "right_hand",
+            "right_leg",
+            "waist"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": [
+            {
+              "rep": "ABSOLUTE",
+              "type": "NON_EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "ABSOLUTE",
+              "type": "NON_EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "ABSOLUTE",
+              "type": "NON_EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "ABSOLUTE",
+              "type": "NON_EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "ABSOLUTE",
+              "type": "NON_EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "ABSOLUTE",
+              "type": "NON_EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "ABSOLUTE",
+              "type": "NON_EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "ABSOLUTE",
+              "type": "NON_EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            }
+          ]
+        },
+        "language": {
+          "delta_indices": [
+            0
+          ],
+          "modality_keys": [
+            "annotation.human.action.task_description"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        }
+      },
+      "austin_sirius_dataset_converted_externally_to_rlds": {
+        "video": {
+          "delta_indices": [
+            -6,
+            -4,
+            -2,
+            0
+          ],
+          "modality_keys": [
+            "primary",
+            "wrist"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "state": {
+          "delta_indices": [
+            0
+          ],
+          "modality_keys": [
+            "end_effector_position",
+            "end_effector_rotation",
+            "gripper_position"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "action": {
+          "delta_indices": [
+            0,
+            1,
+            2,
+            3,
+            4,
+            5,
+            6,
+            7,
+            8,
+            9,
+            10,
+            11,
+            12,
+            13,
+            14,
+            15
+          ],
+          "modality_keys": [
+            "end_effector_position",
+            "end_effector_rotation",
+            "gripper_close"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": [
+            {
+              "rep": "DELTA",
+              "type": "EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "DELTA",
+              "type": "EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "ABSOLUTE",
+              "type": "NON_EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            }
+          ]
+        },
+        "language": {
+          "delta_indices": [
+            0
+          ],
+          "modality_keys": [
+            "annotation.human.action.task_description"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        }
+      },
+      "austin_sailor_dataset_converted_externally_to_rlds": {
+        "video": {
+          "delta_indices": [
+            -6,
+            -4,
+            -2,
+            0
+          ],
+          "modality_keys": [
+            "primary",
+            "wrist"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "state": {
+          "delta_indices": [
+            0
+          ],
+          "modality_keys": [
+            "end_effector_position",
+            "end_effector_rotation",
+            "gripper_position"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "action": {
+          "delta_indices": [
+            0,
+            1,
+            2,
+            3,
+            4,
+            5,
+            6,
+            7,
+            8,
+            9,
+            10,
+            11,
+            12,
+            13,
+            14,
+            15
+          ],
+          "modality_keys": [
+            "end_effector_position",
+            "end_effector_rotation",
+            "gripper_close"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": [
+            {
+              "rep": "DELTA",
+              "type": "EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "DELTA",
+              "type": "EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "ABSOLUTE",
+              "type": "NON_EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            }
+          ]
+        },
+        "language": {
+          "delta_indices": [
+            0
+          ],
+          "modality_keys": [
+            "annotation.human.action.task_description"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        }
+      },
+      "language_table": {
+        "video": {
+          "delta_indices": [
+            -6,
+            -4,
+            -2,
+            0
+          ],
+          "modality_keys": [
+            "primary"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "state": {
+          "delta_indices": [
+            0
+          ],
+          "modality_keys": [
+            "end_effector_position"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "action": {
+          "delta_indices": [
+            0,
+            1,
+            2,
+            3,
+            4,
+            5,
+            6,
+            7,
+            8,
+            9,
+            10,
+            11,
+            12,
+            13,
+            14,
+            15
+          ],
+          "modality_keys": [
+            "end_effector_position"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": [
+            {
+              "rep": "DELTA",
+              "type": "EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            }
+          ]
+        },
+        "language": {
+          "delta_indices": [
+            0
+          ],
+          "modality_keys": [
+            "annotation.human.action.task_description"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        }
+      },
+      "ucsd_kitchen_dataset_converted_externally_to_rlds": {
+        "video": {
+          "delta_indices": [
+            -6,
+            -4,
+            -2,
+            0
+          ],
+          "modality_keys": [
+            "primary"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "state": {
+          "delta_indices": [
+            0
+          ],
+          "modality_keys": [
+            "joint_position"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "action": {
+          "delta_indices": [
+            0,
+            1,
+            2,
+            3,
+            4,
+            5,
+            6,
+            7,
+            8,
+            9,
+            10,
+            11,
+            12,
+            13,
+            14,
+            15
+          ],
+          "modality_keys": [
+            "end_effector_position",
+            "end_effector_rotation",
+            "gripper_close"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": [
+            {
+              "rep": "DELTA",
+              "type": "EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "DELTA",
+              "type": "EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "ABSOLUTE",
+              "type": "NON_EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            }
+          ]
+        },
+        "language": {
+          "delta_indices": [
+            0
+          ],
+          "modality_keys": [
+            "annotation.human.action.task_description"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        }
+      },
+      "dlr_edan_shared_control_converted_externally_to_rlds": {
+        "video": {
+          "delta_indices": [
+            -6,
+            -4,
+            -2,
+            0
+          ],
+          "modality_keys": [
+            "primary"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "state": {
+          "delta_indices": [
+            0
+          ],
+          "modality_keys": [
+            "end_effector_position",
+            "end_effector_rotation",
+            "gripper_position"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "action": {
+          "delta_indices": [
+            0,
+            1,
+            2,
+            3,
+            4,
+            5,
+            6,
+            7,
+            8,
+            9,
+            10,
+            11,
+            12,
+            13,
+            14,
+            15
+          ],
+          "modality_keys": [
+            "end_effector_position",
+            "end_effector_rotation",
+            "gripper_close"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": [
+            {
+              "rep": "DELTA",
+              "type": "EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "DELTA",
+              "type": "EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "ABSOLUTE",
+              "type": "NON_EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            }
+          ]
+        },
+        "language": {
+          "delta_indices": [
+            0
+          ],
+          "modality_keys": [
+            "annotation.human.action.task_description"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        }
+      },
+      "bc_z": {
+        "video": {
+          "delta_indices": [
+            -6,
+            -4,
+            -2,
+            0
+          ],
+          "modality_keys": [
+            "primary"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "state": {
+          "delta_indices": [
+            0
+          ],
+          "modality_keys": [
+            "end_effector_position",
+            "end_effector_rotation",
+            "gripper_position"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "action": {
+          "delta_indices": [
+            0,
+            1,
+            2,
+            3,
+            4,
+            5,
+            6,
+            7,
+            8,
+            9,
+            10,
+            11,
+            12,
+            13,
+            14,
+            15
+          ],
+          "modality_keys": [
+            "end_effector_position",
+            "end_effector_rotation",
+            "gripper_close"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": [
+            {
+              "rep": "DELTA",
+              "type": "EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "DELTA",
+              "type": "EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "ABSOLUTE",
+              "type": "NON_EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            }
+          ]
+        },
+        "language": {
+          "delta_indices": [
+            0
+          ],
+          "modality_keys": [
+            "annotation.human.action.task_description"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        }
+      },
+      "austin_buds_dataset_converted_externally_to_rlds": {
+        "video": {
+          "delta_indices": [
+            -6,
+            -4,
+            -2,
+            0
+          ],
+          "modality_keys": [
+            "primary",
+            "wrist"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "state": {
+          "delta_indices": [
+            0
+          ],
+          "modality_keys": [
+            "joint_position",
+            "gripper_position"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "action": {
+          "delta_indices": [
+            0,
+            1,
+            2,
+            3,
+            4,
+            5,
+            6,
+            7,
+            8,
+            9,
+            10,
+            11,
+            12,
+            13,
+            14,
+            15
+          ],
+          "modality_keys": [
+            "end_effector_position",
+            "end_effector_rotation",
+            "gripper_close"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": [
+            {
+              "rep": "DELTA",
+              "type": "EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "DELTA",
+              "type": "EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "ABSOLUTE",
+              "type": "NON_EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            }
+          ]
+        },
+        "language": {
+          "delta_indices": [
+            0
+          ],
+          "modality_keys": [
+            "annotation.human.action.task_description"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        }
+      },
+      "agibot_dexhand": {
+        "video": {
+          "delta_indices": [
+            -6,
+            -4,
+            -2,
+            0
+          ],
+          "modality_keys": [
+            "primary"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "state": {
+          "delta_indices": [
+            0
+          ],
+          "modality_keys": [
+            "state"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "action": {
+          "delta_indices": [
+            0,
+            1,
+            2,
+            3,
+            4,
+            5,
+            6,
+            7,
+            8,
+            9,
+            10,
+            11,
+            12,
+            13,
+            14,
+            15
+          ],
+          "modality_keys": [
+            "action"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": [
+            {
+              "rep": "ABSOLUTE",
+              "type": "NON_EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            }
+          ]
+        },
+        "language": {
+          "delta_indices": [
+            0
+          ],
+          "modality_keys": [
+            "annotation.human.action.task_description"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        }
+      },
+      "fractal20220817_data": {
+        "video": {
+          "delta_indices": [
+            -6,
+            -4,
+            -2,
+            0
+          ],
+          "modality_keys": [
+            "primary"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "state": {
+          "delta_indices": [
+            0
+          ],
+          "modality_keys": [
+            "end_effector_position",
+            "end_effector_rotation",
+            "gripper_position"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "action": {
+          "delta_indices": [
+            0,
+            1,
+            2,
+            3,
+            4,
+            5,
+            6,
+            7,
+            8,
+            9,
+            10,
+            11,
+            12,
+            13,
+            14,
+            15
+          ],
+          "modality_keys": [
+            "end_effector_position",
+            "end_effector_rotation",
+            "gripper_close"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": [
+            {
+              "rep": "DELTA",
+              "type": "EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "DELTA",
+              "type": "EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "ABSOLUTE",
+              "type": "NON_EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            }
+          ]
+        },
+        "language": {
+          "delta_indices": [
+            0
+          ],
+          "modality_keys": [
+            "annotation.human.action.task_description"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        }
+      },
+      "neural_gr1": {
+        "video": {
+          "delta_indices": [
+            -6,
+            -4,
+            -2,
+            0
+          ],
+          "modality_keys": [
+            "ego_view"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "state": {
+          "delta_indices": [
+            0
+          ],
+          "modality_keys": [
+            "left_arm",
+            "left_hand",
+            "left_leg",
+            "neck",
+            "right_arm",
+            "right_hand",
+            "right_leg",
+            "waist"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "action": {
+          "delta_indices": [
+            0,
+            1,
+            2,
+            3,
+            4,
+            5,
+            6,
+            7,
+            8,
+            9,
+            10,
+            11,
+            12,
+            13,
+            14,
+            15
+          ],
+          "modality_keys": [
+            "left_arm",
+            "left_hand",
+            "left_leg",
+            "neck",
+            "right_arm",
+            "right_hand",
+            "right_leg",
+            "waist"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": [
+            {
+              "rep": "ABSOLUTE",
+              "type": "NON_EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "ABSOLUTE",
+              "type": "NON_EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "ABSOLUTE",
+              "type": "NON_EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "ABSOLUTE",
+              "type": "NON_EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "ABSOLUTE",
+              "type": "NON_EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "ABSOLUTE",
+              "type": "NON_EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "ABSOLUTE",
+              "type": "NON_EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "ABSOLUTE",
+              "type": "NON_EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            }
+          ]
+        },
+        "language": {
+          "delta_indices": [
+            0
+          ],
+          "modality_keys": [
+            "annotation.human.action.task_description"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        }
+      },
+      "roboturk": {
+        "video": {
+          "delta_indices": [
+            -6,
+            -4,
+            -2,
+            0
+          ],
+          "modality_keys": [
+            "primary"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "state": {
+          "delta_indices": [
+            0
+          ],
+          "modality_keys": [
+            "none"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "action": {
+          "delta_indices": [
+            0,
+            1,
+            2,
+            3,
+            4,
+            5,
+            6,
+            7,
+            8,
+            9,
+            10,
+            11,
+            12,
+            13,
+            14,
+            15
+          ],
+          "modality_keys": [
+            "end_effector_position",
+            "end_effector_rotation",
+            "gripper_close"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": [
+            {
+              "rep": "DELTA",
+              "type": "EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "DELTA",
+              "type": "EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "ABSOLUTE",
+              "type": "NON_EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            }
+          ]
+        },
+        "language": {
+          "delta_indices": [
+            0
+          ],
+          "modality_keys": [
+            "annotation.human.action.task_description"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        }
+      },
+      "fmb_dataset": {
+        "video": {
+          "delta_indices": [
+            -6,
+            -4,
+            -2,
+            0
+          ],
+          "modality_keys": [
+            "primary",
+            "secondary",
+            "wrist"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "state": {
+          "delta_indices": [
+            0
+          ],
+          "modality_keys": [
+            "end_effector_position",
+            "end_effector_rotation",
+            "gripper_position"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "action": {
+          "delta_indices": [
+            0,
+            1,
+            2,
+            3,
+            4,
+            5,
+            6,
+            7,
+            8,
+            9,
+            10,
+            11,
+            12,
+            13,
+            14,
+            15
+          ],
+          "modality_keys": [
+            "end_effector_position",
+            "end_effector_rotation",
+            "gripper_close"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": [
+            {
+              "rep": "DELTA",
+              "type": "EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "DELTA",
+              "type": "EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "ABSOLUTE",
+              "type": "NON_EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            }
+          ]
+        },
+        "language": {
+          "delta_indices": [
+            0
+          ],
+          "modality_keys": [
+            "annotation.human.action.task_description"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        }
+      },
+      "toto": {
+        "video": {
+          "delta_indices": [
+            -6,
+            -4,
+            -2,
+            0
+          ],
+          "modality_keys": [
+            "primary"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "state": {
+          "delta_indices": [
+            0
+          ],
+          "modality_keys": [
+            "joint_position",
+            "gripper_position"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "action": {
+          "delta_indices": [
+            0,
+            1,
+            2,
+            3,
+            4,
+            5,
+            6,
+            7,
+            8,
+            9,
+            10,
+            11,
+            12,
+            13,
+            14,
+            15
+          ],
+          "modality_keys": [
+            "end_effector_position",
+            "end_effector_rotation",
+            "gripper_close"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": [
+            {
+              "rep": "DELTA",
+              "type": "EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "DELTA",
+              "type": "EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "ABSOLUTE",
+              "type": "NON_EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            }
+          ]
+        },
+        "language": {
+          "delta_indices": [
+            0
+          ],
+          "modality_keys": [
+            "annotation.human.action.task_description"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        }
+      },
+      "action_net": {
+        "video": {
+          "delta_indices": [
+            -6,
+            -4,
+            -2,
+            0
+          ],
+          "modality_keys": [
+            "primary"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "state": {
+          "delta_indices": [
+            0
+          ],
+          "modality_keys": [
+            "state"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "action": {
+          "delta_indices": [
+            0,
+            1,
+            2,
+            3,
+            4,
+            5,
+            6,
+            7,
+            8,
+            9,
+            10,
+            11,
+            12,
+            13,
+            14,
+            15
+          ],
+          "modality_keys": [
+            "action"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": [
+            {
+              "rep": "ABSOLUTE",
+              "type": "NON_EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            }
+          ]
+        },
+        "language": {
+          "delta_indices": [
+            0
+          ],
+          "modality_keys": [
+            "annotation.human.action.task_description"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        }
+      },
+      "new_embodiment": {
+        "video": {
+          "delta_indices": [
+            -9,
+            -7,
+            -5,
+            -3,
+            -8,
+            -6,
+            -4,
+            -2,
+            -7,
+            -5,
+            -3,
+            -1,
+            -6,
+            -4,
+            -2,
+            0
+          ],
+          "modality_keys": [
+            "camera_ego_left",
+            "camera_ego_right"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "state": {
+          "delta_indices": [
+            -3,
+            -2,
+            -1,
+            0
+          ],
+          "modality_keys": [
+            "right_arm_joints",
+            "left_arm_joints",
+            "right_hand_joints",
+            "left_hand_joints",
+            "neck_joints"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "action": {
+          "delta_indices": [
+            0,
+            1,
+            2,
+            3,
+            4,
+            5,
+            6,
+            7,
+            8,
+            9,
+            10,
+            11,
+            12,
+            13,
+            14,
+            15,
+            16,
+            17,
+            18,
+            19,
+            20,
+            21,
+            22,
+            23,
+            24,
+            25,
+            26,
+            27,
+            28,
+            29,
+            30,
+            31,
+            32,
+            33,
+            34,
+            35,
+            36,
+            37,
+            38,
+            39
+          ],
+          "modality_keys": [
+            "right_arm_joints",
+            "left_arm_joints",
+            "right_hand_joints",
+            "left_hand_joints",
+            "neck_joints"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": [
+            {
+              "rep": "ABSOLUTE",
+              "type": "NON_EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "ABSOLUTE",
+              "type": "NON_EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "ABSOLUTE",
+              "type": "NON_EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "ABSOLUTE",
+              "type": "NON_EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "ABSOLUTE",
+              "type": "NON_EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            }
+          ]
+        },
+        "language": {
+          "delta_indices": [
+            0
+          ],
+          "modality_keys": [
+            "annotation.human.task_description"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        }
+      }
+    },
+    "image_crop_size": null,
+    "image_target_size": null,
+    "use_albumentations": true,
+    "random_rotation_angle": null,
+    "color_jitter_params": {
+      "brightness": 0.3,
+      "contrast": 0.4,
+      "hue": 0.08,
+      "saturation": 0.5
+    },
+    "shortest_image_edge": null,
+    "crop_fraction": 0.95,
+    "max_area": 65536,
+    "resize_m": 32,
+    "model_name": "huiwon/alinvlm_v1_3",
+    "model_type": "contextvla_qwen3_vl_legacy",
+    "formalize_language": true,
+    "max_state_dim": 64,
+    "max_action_dim": 64,
+    "max_action_horizon": 40,
+    "use_percentiles": true,
+    "clip_outliers": true,
+    "apply_sincos_state_encoding": false,
+    "use_relative_action": true,
+    "memory_length": 1,
+    "new_embodiment_train_ratio": 0
+  }
+}

checkpoint-15000/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d4b4fee480358bc2617d2e4e000c179bf08e6b3ca065c78d405e5e3fa044751
+size 15429

checkpoint-15000/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ffe0150a788908f40c71e56102f3e34d5ee3e26afb9f5c77a2280c1598e04448
+size 15429

checkpoint-15000/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:104ab0b064f29fb73ee56852dbac81228ad5bd535e55de2436a46461f82ef34d
+size 15429

checkpoint-15000/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70b3f45b53b004d2d6b1e90645e6484e445f38ae2b9fae3ca71460ac51f2192b
+size 15429

checkpoint-15000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:037b2ed242ecad60951513a5d540a61893b2e95e49094b8f92f474ad42ba86e2
+size 1465

checkpoint-15000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51e8c83c3d2526bb2353636310d7563bb07463309240b4e519d75acfd132f52f
+size 7761

checkpoint-15000/wandb_config.json

@@ -0,0 +1 @@
+{"project": "n1d6_finetune", "run_id": "big_usb_40"}

checkpoint-15000/zero_to_fp32.py

@@ -0,0 +1,760 @@
+#!/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 . output_dir/
+#   or
+#   python zero_to_fp32.py . output_dir/ --safe_serialization
+
+import argparse
+import torch
+import glob
+import math
+import os
+import re
+import gc
+import json
+import numpy as np
+from tqdm import tqdm
+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, weights_only=False)
+
+        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 tqdm(files, desc='Loading checkpoint shards'):
+        state_dict = torch.load(f, map_location=device, mmap=True, weights_only=False)
+        # 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 ZERO_STAGE not 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}")
+
+    fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] 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")
+
+
+class GatheredTensor:
+    """
+    A pseudo tensor that collects partitioned weights.
+    It is more memory efficient when there are multiple groups.
+    """
+
+    def __init__(self, flat_groups, flat_groups_offset, offset, partitioned_numel, shape):
+        self.flat_groups = flat_groups
+        self.flat_groups_offset = flat_groups_offset
+        self.offset = offset
+        self.partitioned_numel = partitioned_numel
+        self.shape = shape
+        self.dtype = self.flat_groups[0][0].dtype
+
+    def contiguous(self):
+        """
+        Merge partitioned weights from flat_groups into a single tensor.
+        """
+        end_idx = self.offset + self.partitioned_numel
+        world_size = len(self.flat_groups)
+        pad_flat_param_chunks = []
+
+        for rank_i in range(world_size):
+            # for each rank, we need to collect weights from related group/groups
+            flat_groups_at_rank_i = self.flat_groups[rank_i]
+            start_group_id = None
+            end_group_id = None
+            for group_id in range(len(self.flat_groups_offset)):
+                if self.flat_groups_offset[group_id] <= self.offset < self.flat_groups_offset[group_id + 1]:
+                    start_group_id = group_id
+                if self.flat_groups_offset[group_id] < end_idx <= self.flat_groups_offset[group_id + 1]:
+                    end_group_id = group_id
+                    break
+            # collect weights from related group/groups
+            for group_id in range(start_group_id, end_group_id + 1):
+                flat_tensor = flat_groups_at_rank_i[group_id]
+                start_offset = self.offset - self.flat_groups_offset[group_id]
+                end_offset = min(end_idx, self.flat_groups_offset[group_id + 1]) - self.flat_groups_offset[group_id]
+                pad_flat_param_chunks.append(flat_tensor[start_offset:end_offset])
+
+        # collect weights from all ranks
+        pad_flat_param = torch.cat(pad_flat_param_chunks, dim=0)
+        param = pad_flat_param[:self.shape.numel()].view(self.shape).contiguous()
+        return param
+
+
+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 = sum([flat_group.numel() for flat_group in fp32_flat_groups[0]]) * 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
+    flat_groups_offset = [0] + list(np.cumsum([flat_tensor.numel() for flat_tensor in fp32_flat_groups[0]]))
+    for name, shape in tqdm(param_shapes.items(), desc='Gathering sharded weights'):
+        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}"
+            )
+
+        # memory efficient tensor
+        tensor = GatheredTensor(fp32_flat_groups, flat_groups_offset, offset, partitioned_numel, shape)
+        state_dict[name] = tensor
+        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 to_torch_tensor(state_dict, return_empty_tensor=False):
+    """
+    Convert state_dict of GatheredTensor to torch tensor
+    """
+    torch_state_dict = {}
+    converted_tensors = {}
+    for name, tensor in state_dict.items():
+        tensor_id = id(tensor)
+        if tensor_id in converted_tensors:  # shared tensors
+            shared_tensor = torch_state_dict[converted_tensors[tensor_id]]
+            torch_state_dict[name] = shared_tensor
+        else:
+            converted_tensors[tensor_id] = name
+            if return_empty_tensor:
+                torch_state_dict[name] = torch.empty(tensor.shape, dtype=tensor.dtype)
+            else:
+                torch_state_dict[name] = tensor.contiguous()
+    return torch_state_dict
+
+
+def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir,
+                                             tag=None,
+                                             exclude_frozen_parameters=False,
+                                             lazy_mode=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
+        - ``lazy_mode``: get state_dict in lazy mode. It returns a dict of pesduo tensor instead of torch tensor, which is more memory efficient.
+          Convert the pesduo tensor to torch tensor by ``.contiguous()``
+
+    Returns:
+        - pytorch ``state_dict``
+
+    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.
+
+    Note: the above usage may not work if your application doesn't have sufficient free CPU memory.
+    You may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
+    the checkpoint. Or you can load state_dict in lazy mode ::
+
+        from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
+        state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, lazy_mode=True) # not on cpu
+        for name, lazy_tensor in state_dict.item():
+            tensor = lazy_tensor.contiguous()  # to cpu
+            print(name, tensor)
+            # del tensor to release memory if it no longer in use
+    """
+    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")
+
+    state_dict = _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters)
+    if lazy_mode:
+        return state_dict
+    else:
+        return to_torch_tensor(state_dict)
+
+
+def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir,
+                                               output_dir,
+                                               max_shard_size="5GB",
+                                               safe_serialization=False,
+                                               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_dir``: directory to the pytorch fp32 state_dict output files
+        - ``max_shard_size``: the maximum size for a checkpoint before being sharded, default value is 5GB
+        - ``safe_serialization``:  whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).
+        - ``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
+    """
+
+    # Dependency pre-check
+    if safe_serialization:
+        try:
+            from safetensors.torch import save_file
+        except ImportError:
+            print('If you want to use `safe_serialization`, please `pip install safetensors`')
+            raise
+    if max_shard_size is not None:
+        try:
+            from huggingface_hub import split_torch_state_dict_into_shards
+        except ImportError:
+            print('If you want to use `max_shard_size`, please `pip install huggingface_hub`')
+            raise
+
+    # Convert zero checkpoint to state_dict
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir,
+                                                          tag,
+                                                          exclude_frozen_parameters,
+                                                          lazy_mode=True)
+
+    # Shard the model if it is too big.
+    weights_name = "model.safetensors" if safe_serialization else "pytorch_model.bin"
+    if max_shard_size is not None:
+        filename_pattern = weights_name.replace(".bin", "{suffix}.bin").replace(".safetensors", "{suffix}.safetensors")
+        # an memory-efficient approach for sharding
+        empty_state_dict = to_torch_tensor(state_dict, return_empty_tensor=True)
+        state_dict_split = split_torch_state_dict_into_shards(empty_state_dict,
+                                                              filename_pattern=filename_pattern,
+                                                              max_shard_size=max_shard_size)
+    else:
+        from collections import namedtuple
+        StateDictSplit = namedtuple("StateDictSplit", ["is_sharded", "filename_to_tensors"])
+        state_dict_split = StateDictSplit(is_sharded=False,
+                                          filename_to_tensors={weights_name: list(state_dict.keys())})
+
+    # Save the model by shard
+    os.makedirs(output_dir, exist_ok=True)
+    filename_to_tensors = state_dict_split.filename_to_tensors.items()
+    for shard_file, tensors in tqdm(filename_to_tensors, desc="Saving checkpoint shards"):
+        shard_state_dict = {tensor_name: state_dict[tensor_name] for tensor_name in tensors}
+        shard_state_dict = to_torch_tensor(shard_state_dict)
+        output_path = os.path.join(output_dir, shard_file)
+        if safe_serialization:
+            save_file(shard_state_dict, output_path, metadata={"format": "pt"})
+        else:
+            torch.save(shard_state_dict, output_path)
+        # release the memory of current shard
+        for tensor_name in list(shard_state_dict.keys()):
+            del state_dict[tensor_name]
+            del shard_state_dict[tensor_name]
+        del shard_state_dict
+        gc.collect()
+
+    # Save index if sharded
+    if state_dict_split.is_sharded:
+        index = {
+            "metadata": state_dict_split.metadata,
+            "weight_map": state_dict_split.tensor_to_filename,
+        }
+        save_index_file = "model.safetensors.index.json" if safe_serialization else "pytorch_model.bin.index.json"
+        save_index_file = os.path.join(output_dir, save_index_file)
+        with open(save_index_file, "w", encoding="utf-8") as f:
+            content = json.dumps(index, indent=2, sort_keys=True) + "\n"
+            f.write(content)
+
+
+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("Extracting fp32 weights")
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
+
+    logger.info("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_dir",
+                        type=str,
+                        help="directory to the pytorch fp32 state_dict output files"
+                        "(e.g. path/checkpoint-12-output/)")
+    parser.add_argument(
+        "--max_shard_size",
+        type=str,
+        default="5GB",
+        help="The maximum size for a checkpoint before being sharded. Checkpoints shard will then be each of size"
+        "lower than this size. If expressed as a string, needs to be digits followed by a unit (like `5MB`"
+        "We default it to 5GB in order for models to be able to run easily on free-tier google colab instances"
+        "without CPU OOM issues.")
+    parser.add_argument(
+        "--safe_serialization",
+        default=False,
+        action='store_true',
+        help="Whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).")
+    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_dir,
+                                               max_shard_size=args.max_shard_size,
+                                               safe_serialization=args.safe_serialization,
+                                               tag=args.tag,
+                                               exclude_frozen_parameters=args.exclude_frozen_parameters)

checkpoint-25000/config.json

@@ -0,0 +1,77 @@
+{
+  "action_horizon": 40,
+  "architectures": [
+    "AlinVLAv0"
+  ],
+  "attn_implementation": null,
+  "backbone_model_type": "contextvla_qwen3_vl_legacy",
+  "backbone_trainable_params_fp32": true,
+  "color_jitter_params": {
+    "brightness": 0.3,
+    "contrast": 0.4,
+    "hue": 0.08,
+    "saturation": 0.5
+  },
+  "diffusion_model_cfg": {
+    "action_head_max_seq_len": 512,
+    "attention_head_dim": 64,
+    "depth_multi_stream": 4,
+    "depth_single_stream": 8,
+    "dropout": 0.2,
+    "final_dropout": true,
+    "num_attention_heads": 24,
+    "output_dim": 1024,
+    "positional_embeddings": "rope_sa_only",
+    "pre_norm": "layer_norm",
+    "qk_norm": "rms_norm",
+    "rope_theta": 10000.0,
+    "sa_dim": 1536,
+    "set_triple_stream_for_mq": false,
+    "set_triple_stream_for_state": false,
+    "temb_type": "input_token",
+    "use_swiglu": true,
+    "vl_dim": 4096
+  },
+  "dtype": "bfloat16",
+  "load_bf16": true,
+  "memory_cfg": {
+    "hidden_size": 4096,
+    "intermediate_size": 16384,
+    "max_position_embeddings": 32,
+    "num_attention_heads": 16,
+    "num_hidden_layers": 2,
+    "num_key_value_heads": 16,
+    "rms_norm_eps": 1e-05,
+    "use_causal_attn": true,
+    "use_rope": true
+  },
+  "memory_length": 4,
+  "memory_meta_queries_mode": "meta_only",
+  "memory_video_delta_indices": [
+    -48,
+    -32,
+    -16,
+    0
+  ],
+  "model_name": "huiwon/alinvlm_v1_3",
+  "model_type": "AlinVLAv0",
+  "n_meta_queries": 64,
+  "new_embodiment_train_ratio": 0,
+  "qwen3_collator": true,
+  "random_rotation_angle": null,
+  "reproject_vision": false,
+  "state_dropout_prob": 0.0,
+  "transformers_version": "4.57.0",
+  "tune_diffusion_model": true,
+  "tune_llm": false,
+  "tune_projector": true,
+  "tune_top_llm_layers": 4,
+  "tune_visual": false,
+  "tune_vlln": true,
+  "use_memory": false,
+  "use_mmditv0": false,
+  "use_mmditv1": true,
+  "use_relative_action": true,
+  "use_video": true,
+  "video_length": 4
+}

checkpoint-25000/embodiment_id.json

@@ -0,0 +1,38 @@
+{
+  "new_embodiment": 0,
+  "fractal20220817_data": 1,
+  "kuka": 2,
+  "bridge_orig": 3,
+  "taco_play": 4,
+  "jaco_play": 5,
+  "berkeley_cable_routing": 6,
+  "roboturk": 7,
+  "viola": 8,
+  "berkeley_autolab_ur5": 9,
+  "toto": 10,
+  "language_table": 11,
+  "stanford_hydra_dataset_converted_externally_to_rlds": 12,
+  "austin_buds_dataset_converted_externally_to_rlds": 13,
+  "nyu_franka_play_dataset_converted_externally_to_rlds": 14,
+  "furniture_bench_dataset_converted_externally_to_rlds": 15,
+  "ucsd_kitchen_dataset_converted_externally_to_rlds": 16,
+  "austin_sailor_dataset_converted_externally_to_rlds": 17,
+  "austin_sirius_dataset_converted_externally_to_rlds": 18,
+  "dlr_edan_shared_control_converted_externally_to_rlds": 19,
+  "iamlab_cmu_pickup_insert_converted_externally_to_rlds": 20,
+  "utaustin_mutex": 21,
+  "berkeley_fanuc_manipulation": 22,
+  "cmu_stretch": 23,
+  "bc_z": 24,
+  "fmb_dataset": 25,
+  "dobbe": 26,
+  "droid": 27,
+  "agibot_dexhand": 28,
+  "agibot_gripper": 29,
+  "galaxea": 30,
+  "humanoid_everyday_g1": 31,
+  "humanoid_everyday_h1": 32,
+  "action_net": 33,
+  "neural_gr1": 34,
+  "simulation_gr1": 35
+}

checkpoint-25000/experiment_cfg/conf.yaml

@@ -0,0 +1,308 @@
+data:
+  datasets:
+  - dataset_paths:
+    - /rlwrld2/home/nayoung_oh/workspace/datasets/0330/openarm_usb_teleop_0
+    embodiment_tag: new_embodiment
+    mix_ratio: 0.67
+    dataset_type: physical_embodiment
+    val_dataset_path: null
+  - dataset_paths:
+    - /rlwrld2/home/nayoung_oh/workspace/datasets/0330/openarm_usb_teleop_1
+    embodiment_tag: new_embodiment
+    mix_ratio: 0.33
+    dataset_type: physical_embodiment
+    val_dataset_path: null
+  modality_configs:
+    new_embodiment:
+      video:
+        delta_indices:
+        - -9
+        - -7
+        - -5
+        - -3
+        - -8
+        - -6
+        - -4
+        - -2
+        - -7
+        - -5
+        - -3
+        - -1
+        - -6
+        - -4
+        - -2
+        - 0
+        modality_keys:
+        - camera_ego_left
+        - camera_ego_right
+        sin_cos_embedding_keys: null
+        mean_std_embedding_keys: null
+        action_configs: null
+      state:
+        delta_indices:
+        - -3
+        - -2
+        - -1
+        - 0
+        modality_keys:
+        - right_arm_joints
+        - left_arm_joints
+        - right_hand_joints
+        - left_hand_joints
+        - neck_joints
+        sin_cos_embedding_keys: null
+        mean_std_embedding_keys: null
+        action_configs: null
+      action:
+        delta_indices:
+        - 0
+        - 1
+        - 2
+        - 3
+        - 4
+        - 5
+        - 6
+        - 7
+        - 8
+        - 9
+        - 10
+        - 11
+        - 12
+        - 13
+        - 14
+        - 15
+        - 16
+        - 17
+        - 18
+        - 19
+        - 20
+        - 21
+        - 22
+        - 23
+        - 24
+        - 25
+        - 26
+        - 27
+        - 28
+        - 29
+        - 30
+        - 31
+        - 32
+        - 33
+        - 34
+        - 35
+        - 36
+        - 37
+        - 38
+        - 39
+        modality_keys:
+        - right_arm_joints
+        - left_arm_joints
+        - right_hand_joints
+        - left_hand_joints
+        - neck_joints
+        sin_cos_embedding_keys: null
+        mean_std_embedding_keys: null
+        action_configs:
+        - rep: ABSOLUTE
+          type: NON_EEF
+          format: DEFAULT
+          state_key: null
+        - rep: ABSOLUTE
+          type: NON_EEF
+          format: DEFAULT
+          state_key: null
+        - rep: ABSOLUTE
+          type: NON_EEF
+          format: DEFAULT
+          state_key: null
+        - rep: ABSOLUTE
+          type: NON_EEF
+          format: DEFAULT
+          state_key: null
+        - rep: ABSOLUTE
+          type: NON_EEF
+          format: DEFAULT
+          state_key: null
+      language:
+        delta_indices:
+        - 0
+        modality_keys:
+        - annotation.human.task_description
+        sin_cos_embedding_keys: null
+        mean_std_embedding_keys: null
+        action_configs: null
+  dataset_mode: sharded
+  download_cache: false
+  shard_size: 1024
+  episode_sampling_rate: 0.1
+  num_shards_per_epoch: 100000
+  override_pretraining_statistics: false
+  mode: single_turn
+  random_chop: 0.0
+  mock_dataset_mode: false
+  shuffle: true
+  seed: 42
+  multiprocessing_context: fork
+  allow_padding: true
+  subsample_ratio: 1.0
+  image_crop_size:
+  - 244
+  - 244
+  image_target_size:
+  - 224
+  - 224
+  video_backend: torchcodec
+load_config_path: null
+model:
+  model_type: AlinVLAv0
+  model_dtype: bfloat16
+  model_name: huiwon/alinvlm_v1_3
+  backbone_model_type: contextvla_qwen3_vl_legacy
+  model_revision: null
+  tune_top_llm_layers: 4
+  backbone_embedding_dim: 4096
+  tune_llm: false
+  tune_visual: false
+  select_layer: 18
+  reproject_vision: false
+  use_flash_attention: true
+  load_bf16: true
+  collator_overwrite_image_inputs: false
+  qwen3_collator: true
+  backbone_trainable_params_fp32: true
+  image_crop_size: null
+  image_target_size: null
+  shortest_image_edge: 256
+  crop_fraction: 0.95
+  random_rotation_angle: null
+  color_jitter_params:
+    brightness: 0.3
+    contrast: 0.4
+    hue: 0.08
+    saturation: 0.5
+  max_area: 65536
+  resize_m: 32
+  use_albumentations_transforms: true
+  formalize_language: true
+  apply_sincos_state_encoding: false
+  use_relative_action: true
+  use_percentiles: true
+  conversation_image_first: false
+  max_state_dim: 64
+  max_action_dim: 64
+  action_horizon: 40
+  hidden_size: 1024
+  input_embedding_dim: 1536
+  new_embodiment_train_ratio: 0.0
+  add_pos_embed: true
+  attn_dropout: 0.2
+  use_vlln: false
+  max_seq_len: 1024
+  use_mmditv0: false
+  n_meta_queries: 64
+  diffusion_model_cfg:
+    action_head_max_seq_len: 512
+    attention_head_dim: 64
+    depth_multi_stream: 4
+    depth_single_stream: 8
+    dropout: 0.2
+    final_dropout: true
+    num_attention_heads: 24
+    output_dim: 1024
+    positional_embeddings: rope_sa_only
+    pre_norm: layer_norm
+    qk_norm: rms_norm
+    rope_theta: 10000.0
+    set_triple_stream_for_mq: false
+    set_triple_stream_for_state: false
+    temb_type: input_token
+    use_swiglu: true
+  use_mmditv1: true
+  num_inference_timesteps: 4
+  noise_beta_alpha: 1.5
+  noise_beta_beta: 1.0
+  noise_s: 0.999
+  num_timestep_buckets: 1000
+  tune_projector: true
+  tune_diffusion_model: true
+  tune_vlln: true
+  state_dropout_prob: 0.0
+  state_additive_noise_scale: 0.0
+  use_memory: false
+  memory_length: 4
+  memory_meta_queries_mode: meta_only
+  memory_cfg:
+    hidden_size: 4096
+    intermediate_size: 16384
+    max_position_embeddings: 32
+    num_attention_heads: 16
+    num_hidden_layers: 2
+    num_key_value_heads: 16
+    rms_norm_eps: 1.0e-05
+    use_causal_attn: true
+    use_rope: true
+  training_rtc_max_overlap: -1
+  inference_rtc_overlap_steps: null
+  inference_rtc_frozen_steps: null
+  rtc_ramp_rate: 10.0
+  use_video: true
+  video_length: 4
+  max_num_embodiments: 36
+training:
+  output_dir: ./ckpt/output
+  experiment_name: big_usb_40
+  max_steps: 30000
+  global_batch_size: 64
+  batch_size: null
+  gradient_accumulation_steps: 1
+  learning_rate: 0.0001
+  lr_scheduler_type: cosine
+  weight_decay: 1.0e-05
+  warmup_ratio: 0.05
+  warmup_steps: 0
+  max_grad_norm: 1.0
+  optim: adamw_torch
+  start_from_checkpoint: /rlwrld2/home/nayoung_oh/workspace/RLDX/models/alinvla_v1d4_video_mq64_mixv4_pt100k
+  tf32: true
+  fp16: false
+  bf16: true
+  eval_bf16: true
+  logging_steps: 10
+  save_steps: 5000
+  save_total_limit: 5
+  save_vl_model: false
+  upload_checkpoints: false
+  upload_every: 1000
+  upload_last_n_checkpoints: 5
+  max_concurrent_uploads: 2
+  eval_strategy: 'no'
+  eval_steps: 500
+  eval_set_split_ratio: 0.1
+  eval_batch_size: 2
+  save_best_eval_metric_name: ''
+  save_best_eval_metric_greater_is_better: true
+  deepspeed_stage: 2
+  gradient_checkpointing: false
+  transformers_trust_remote_code: true
+  transformers_local_files_only: false
+  transformers_cache_dir: null
+  transformers_access_token: null
+  use_ddp: false
+  ddp_bucket_cap_mb: 100
+  num_gpus: 4
+  dataloader_num_workers: 4
+  remove_unused_columns: false
+  use_wandb: true
+  wandb_project: n1d6_finetune
+  enable_profiling: false
+  max_retries: 3
+  assert_loss_less_than: null
+  add_rl_callback: false
+  enable_open_loop_eval: false
+  open_loop_eval_traj_ids:
+  - 0
+  open_loop_eval_steps_per_traj: 100
+  open_loop_eval_plot_indices: null
+max_steps: 30000
+save_steps: 5000

checkpoint-25000/experiment_cfg/config.yaml

@@ -0,0 +1,327 @@
+!!python/object:gr00t.configs.base_config.Config
+data: !!python/object:gr00t.configs.data.data_config.DataConfig
+  allow_padding: true
+  dataset_mode: sharded
+  datasets:
+  - !!python/object:gr00t.configs.data.data_config.SingleDatasetConfig
+    dataset_paths:
+    - /rlwrld2/home/nayoung_oh/workspace/datasets/0330/openarm_usb_teleop_0
+    dataset_type: physical_embodiment
+    embodiment_tag: new_embodiment
+    mix_ratio: 0.67
+    val_dataset_path: null
+  - !!python/object:gr00t.configs.data.data_config.SingleDatasetConfig
+    dataset_paths:
+    - /rlwrld2/home/nayoung_oh/workspace/datasets/0330/openarm_usb_teleop_1
+    dataset_type: physical_embodiment
+    embodiment_tag: new_embodiment
+    mix_ratio: 0.33
+    val_dataset_path: null
+  download_cache: false
+  episode_sampling_rate: 0.1
+  image_crop_size:
+  - 244
+  - 244
+  image_target_size:
+  - 224
+  - 224
+  mock_dataset_mode: false
+  modality_configs:
+    new_embodiment:
+      action: !!python/object:gr00t.data.types.ModalityConfig
+        action_configs:
+        - &id001 !!python/object:gr00t.data.types.ActionConfig
+          format: !!python/object/apply:gr00t.data.types.ActionFormat
+          - default
+          rep: !!python/object/apply:gr00t.data.types.ActionRepresentation
+          - absolute
+          state_key: null
+          type: !!python/object/apply:gr00t.data.types.ActionType
+          - non_eef
+        - *id001
+        - *id001
+        - *id001
+        - *id001
+        delta_indices:
+        - 0
+        - 1
+        - 2
+        - 3
+        - 4
+        - 5
+        - 6
+        - 7
+        - 8
+        - 9
+        - 10
+        - 11
+        - 12
+        - 13
+        - 14
+        - 15
+        - 16
+        - 17
+        - 18
+        - 19
+        - 20
+        - 21
+        - 22
+        - 23
+        - 24
+        - 25
+        - 26
+        - 27
+        - 28
+        - 29
+        - 30
+        - 31
+        - 32
+        - 33
+        - 34
+        - 35
+        - 36
+        - 37
+        - 38
+        - 39
+        mean_std_embedding_keys: null
+        modality_keys:
+        - right_arm_joints
+        - left_arm_joints
+        - right_hand_joints
+        - left_hand_joints
+        - neck_joints
+        sin_cos_embedding_keys: null
+      language: !!python/object:gr00t.data.types.ModalityConfig
+        action_configs: null
+        delta_indices:
+        - 0
+        mean_std_embedding_keys: null
+        modality_keys:
+        - annotation.human.task_description
+        sin_cos_embedding_keys: null
+      state: !!python/object:gr00t.data.types.ModalityConfig
+        action_configs: null
+        delta_indices:
+        - -3
+        - -2
+        - -1
+        - 0
+        mean_std_embedding_keys: null
+        modality_keys:
+        - right_arm_joints
+        - left_arm_joints
+        - right_hand_joints
+        - left_hand_joints
+        - neck_joints
+        sin_cos_embedding_keys: null
+      video: !!python/object:gr00t.data.types.ModalityConfig
+        action_configs: null
+        delta_indices:
+        - -9
+        - -7
+        - -5
+        - -3
+        - -8
+        - -6
+        - -4
+        - -2
+        - -7
+        - -5
+        - -3
+        - -1
+        - -6
+        - -4
+        - -2
+        - 0
+        mean_std_embedding_keys: null
+        modality_keys:
+        - camera_ego_left
+        - camera_ego_right
+        sin_cos_embedding_keys: null
+  mode: single_turn
+  multiprocessing_context: fork
+  num_shards_per_epoch: 100000
+  override_pretraining_statistics: false
+  random_chop: 0.0
+  seed: 42
+  shard_size: 1024
+  shuffle: true
+  subsample_ratio: 1.0
+  video_backend: torchcodec
+load_config_path: null
+model: !!python/object:gr00t.configs.model.alinvla_v0.AlinVLAv0Config
+  _attn_implementation_internal: null
+  _commit_hash: null
+  _name_or_path: ''
+  _output_attentions: false
+  add_cross_attention: false
+  architectures: null
+  backbone_model_type: contextvla_qwen3_vl_legacy
+  backbone_trainable_params_fp32: true
+  bad_words_ids: null
+  begin_suppress_tokens: null
+  bos_token_id: null
+  chunk_size_feed_forward: 0
+  color_jitter_params:
+    brightness: 0.3
+    contrast: 0.4
+    hue: 0.08
+    saturation: 0.5
+  conversation_image_first: false
+  cross_attention_hidden_size: null
+  decoder_start_token_id: null
+  diffusion_model_cfg:
+    action_head_max_seq_len: 512
+    attention_head_dim: 64
+    depth_multi_stream: 4
+    depth_single_stream: 8
+    dropout: 0.2
+    final_dropout: true
+    num_attention_heads: 24
+    output_dim: 1024
+    positional_embeddings: rope_sa_only
+    pre_norm: layer_norm
+    qk_norm: rms_norm
+    rope_theta: 10000.0
+    set_triple_stream_for_mq: false
+    set_triple_stream_for_state: false
+    temb_type: input_token
+    use_swiglu: true
+  diversity_penalty: 0.0
+  do_sample: false
+  dtype: null
+  early_stopping: false
+  encoder_no_repeat_ngram_size: 0
+  eos_token_id: null
+  exponential_decay_length_penalty: null
+  finetuning_task: null
+  forced_bos_token_id: null
+  forced_eos_token_id: null
+  id2label:
+    0: LABEL_0
+    1: LABEL_1
+  is_decoder: false
+  is_encoder_decoder: false
+  label2id:
+    LABEL_0: 0
+    LABEL_1: 1
+  length_penalty: 1.0
+  load_bf16: true
+  max_length: 20
+  memory_cfg:
+    hidden_size: 4096
+    intermediate_size: 16384
+    max_position_embeddings: 32
+    num_attention_heads: 16
+    num_hidden_layers: 2
+    num_key_value_heads: 16
+    rms_norm_eps: 1.0e-05
+    use_causal_attn: true
+    use_rope: true
+  memory_video_delta_indices:
+  - -48
+  - -32
+  - -16
+  - 0
+  min_length: 0
+  model_name: huiwon/alinvlm_v1_3
+  model_type: AlinVLAv0
+  n_meta_queries: 64
+  new_embodiment_train_ratio: 0
+  no_repeat_ngram_size: 0
+  num_beam_groups: 1
+  num_beams: 1
+  num_return_sequences: 1
+  output_hidden_states: false
+  output_scores: false
+  pad_token_id: null
+  prefix: null
+  problem_type: null
+  pruned_heads: {}
+  qwen3_collator: true
+  random_rotation_angle: null
+  remove_invalid_values: false
+  repetition_penalty: 1.0
+  reproject_vision: false
+  return_dict: true
+  return_dict_in_generate: false
+  sep_token_id: null
+  state_dropout_prob: 0.0
+  suppress_tokens: null
+  task_specific_params: null
+  temperature: 1.0
+  tf_legacy_loss: false
+  tie_encoder_decoder: false
+  tie_word_embeddings: true
+  tokenizer_class: null
+  top_k: 50
+  top_p: 1.0
+  torchscript: false
+  transformers_version: null
+  tune_diffusion_model: true
+  tune_llm: false
+  tune_projector: true
+  tune_top_llm_layers: 4
+  tune_visual: false
+  typical_p: 1.0
+  use_bfloat16: false
+  use_mmditv0: false
+  use_mmditv1: true
+  use_relative_action: true
+  use_video: true
+  video_length: 4
+training: !!python/object:gr00t.configs.training.training_config.TrainingConfig
+  add_rl_callback: false
+  assert_loss_less_than: null
+  batch_size: null
+  bf16: true
+  dataloader_num_workers: 4
+  ddp_bucket_cap_mb: 100
+  deepspeed_stage: 2
+  enable_open_loop_eval: false
+  enable_profiling: false
+  eval_batch_size: 2
+  eval_bf16: true
+  eval_set_split_ratio: 0.1
+  eval_steps: 500
+  eval_strategy: 'no'
+  experiment_name: big_usb_40
+  fp16: false
+  global_batch_size: 64
+  gradient_accumulation_steps: 1
+  gradient_checkpointing: false
+  learning_rate: 0.0001
+  logging_steps: 10
+  lr_scheduler_type: cosine
+  max_concurrent_uploads: 2
+  max_grad_norm: 1.0
+  max_retries: 3
+  max_steps: 30000
+  num_gpus: 4
+  open_loop_eval_plot_indices: null
+  open_loop_eval_steps_per_traj: 100
+  open_loop_eval_traj_ids:
+  - 0
+  optim: adamw_torch
+  output_dir: ./ckpt/output
+  remove_unused_columns: false
+  save_best_eval_metric_greater_is_better: true
+  save_best_eval_metric_name: ''
+  save_steps: 5000
+  save_total_limit: 5
+  save_vl_model: false
+  start_from_checkpoint: /rlwrld2/home/nayoung_oh/workspace/RLDX/models/alinvla_v1d4_video_mq64_mixv4_pt100k
+  tf32: true
+  transformers_access_token: null
+  transformers_cache_dir: null
+  transformers_local_files_only: false
+  transformers_trust_remote_code: true
+  upload_checkpoints: false
+  upload_every: 1000
+  upload_last_n_checkpoints: 5
+  use_ddp: false
+  use_wandb: true
+  wandb_project: n1d6_finetune
+  warmup_ratio: 0.05
+  warmup_steps: 0
+  weight_decay: 1.0e-05

checkpoint-25000/experiment_cfg/dataset_statistics.json

@@ -0,0 +1,629 @@
+{
+  "new_embodiment": {
+    "state": {
+      "right_arm_joints": {
+        "min": [
+          -0.20847637951374054,
+          -0.17223620414733887,
+          -0.8260852694511414,
+          0.006294346414506435,
+          -1.5836957693099976,
+          -0.5304417610168457,
+          -0.6185625791549683
+        ],
+        "max": [
+          1.4608606100082397,
+          0.7867932915687561,
+          0.7280460596084595,
+          2.026970386505127,
+          0.32101166248321533,
+          0.7837415337562561,
+          0.5834668278694153
+        ],
+        "mean": [
+          0.5230762350115545,
+          0.031938130726095276,
+          0.07735111293069932,
+          1.0961320673796087,
+          -1.1073419616170415,
+          0.11922063120033552,
+          0.05158661119532133
+        ],
+        "std": [
+          0.457679354789903,
+          0.15803064005676729,
+          0.26611296499301296,
+          0.5450642539383688,
+          0.44136857118707146,
+          0.21900165579974118,
+          0.15309557379165087
+        ],
+        "q01": [
+          -0.045479488308008235,
+          -0.15748688659880955,
+          -0.2324001598639563,
+          0.23192057110022266,
+          -1.5726320718878462,
+          -0.26164717355209116,
+          -0.15236894632345038
+        ],
+        "q99": [
+          1.1783605899921912,
+          0.29508311892070715,
+          0.4700866512723284,
+          1.7546243470988008,
+          -0.40475618449400974,
+          0.5152354760941318,
+          0.29988374789735234
+        ]
+      },
+      "left_arm_joints": {
+        "min": [
+          -1.4444571733474731,
+          -1.0122454166412354,
+          -1.0866330862045288,
+          0.10738536715507507,
+          -1.2121385335922241,
+          -0.7833600640296936,
+          -0.9882124066352844
+        ],
+        "max": [
+          0.2615014910697937,
+          0.17109178006649017,
+          1.5047303438186646,
+          2.0948729515075684,
+          1.5684367418289185,
+          0.7448310256004333,
+          1.344510555267334
+        ],
+        "mean": [
+          -0.04986175698282235,
+          -0.19392163572815393,
+          0.17408178791213455,
+          1.6268207280624323,
+          0.943715995203565,
+          -0.1656372827567857,
+          0.08572700017970818
+        ],
+        "std": [
+          0.13127968307410454,
+          0.21879874111138958,
+          0.18787674653153308,
+          0.13760933470652406,
+          0.7142651273520758,
+          0.3682533803815269,
+          0.21210845544579085
+        ],
+        "q01": [
+          -0.27506257213997515,
+          -0.6895779073341636,
+          -0.0784322185224472,
+          1.355194293867866,
+          -0.3763468656182127,
+          -0.769349612863381,
+          -0.4407769059315693
+        ],
+        "q99": [
+          0.08620987205422512,
+          0.08083185656331611,
+          0.5328141061374334,
+          1.7955220293853555,
+          1.5638651034392295,
+          0.2517314710440321,
+          0.5060496525470584
+        ]
+      },
+      "right_hand_joints": {
+        "min": [
+          0.02471296489238739,
+          -0.008722222410142422,
+          0.020351851359009743,
+          -0.14192885160446167,
+          0.01162963081151247,
+          -0.008722222410142422,
+          -0.01162963081151247,
+          -0.08576852083206177,
+          0.01162963081151247,
+          0.02180555649101734,
+          0.010175925679504871,
+          0.005814815405756235
+        ],
+        "max": [
+          1.5714536905288696,
+          1.0873703956604004,
+          1.2007594108581543,
+          -0.06382732838392258,
+          1.6339629888534546,
+          1.190583348274231,
+          1.7836945056915283,
+          1.8084073066711426,
+          1.8491111993789673,
+          1.7880555391311646,
+          1.844749927520752,
+          1.2807129621505737
+        ],
+        "mean": [
+          0.5850972631377792,
+          0.42659694968022016,
+          0.6479643724551789,
+          -0.08767521811430576,
+          0.425969056384194,
+          0.39579498645896927,
+          0.4627784831631483,
+          0.5736243939751159,
+          0.4692227715888908,
+          0.49072391727075826,
+          0.4756991051017129,
+          0.4021215243171613
+        ],
+        "std": [
+          0.4659352716590282,
+          0.26326663460608324,
+          0.1903730892891041,
+          0.021649972511879785,
+          0.3177542874289095,
+          0.12852050776384696,
+          0.35465225689414787,
+          0.2813339579162597,
+          0.5321364975758696,
+          0.39219871994450173,
+          0.5316887540787808,
+          0.2635455642348228
+        ],
+        "q01": [
+          0.04709112252429289,
+          0.05362940602356817,
+          0.03094588222703274,
+          -0.12354047151182598,
+          0.02500137889803208,
+          0.015720412845067713,
+          0.05507507756448419,
+          0.06626581013963564,
+          0.020781336379338825,
+          0.03831492052703827,
+          0.016980372181013663,
+          0.014013878352033101
+        ],
+        "q99": [
+          1.2835387079641307,
+          0.9926928857163729,
+          0.9508772217850779,
+          -0.06821455715077998,
+          0.9838547316175984,
+          0.6369301133140961,
+          1.1447815406442614,
+          1.08181754207393,
+          1.5359646890495815,
+          1.2619330054281663,
+          1.450155472114204,
+          0.9488189728109094
+        ]
+      },
+      "left_hand_joints": {
+        "min": [
+          0.01453703735023737,
+          -0.02180555649101734,
+          0.05087963119149208,
+          -0.11556173861026764,
+          -0.0,
+          0.005814815405756235,
+          0.02907407470047474,
+          0.004361111205071211,
+          0.01162963081151247,
+          0.008722222410142422,
+          0.01162963081151247,
+          0.0029074077028781176
+        ],
+        "max": [
+          1.5511019229888916,
+          1.1644166707992554,
+          0.9318241477012634,
+          -0.053776565939188004,
+          1.1586018800735474,
+          1.2981574535369873,
+          1.7110095024108887,
+          1.2981574535369873,
+          1.7371760606765747,
+          0.7428426146507263,
+          1.3635740280151367,
+          0.5146111249923706
+        ],
+        "mean": [
+          0.32985505008751104,
+          0.6881588844618378,
+          0.6488113999748686,
+          -0.06972486540469508,
+          0.3926318089439047,
+          0.5482275542810864,
+          0.47254444520168226,
+          0.41040236509504985,
+          0.3783655666627965,
+          0.5194880139656365,
+          0.3418363023788917,
+          0.47916842368371915
+        ],
+        "std": [
+          0.14452058747164218,
+          0.15373799437316096,
+          0.11791576866346334,
+          0.01307136103551452,
+          0.10481756163917923,
+          0.12678199391146713,
+          0.12084425493478433,
+          0.1635095111154085,
+          0.19093731519085877,
+          0.11041810061836821,
+          0.37641207261413745,
+          0.0887305578820552
+        ],
+        "q01": [
+          0.060338779066490496,
+          0.5119375301750233,
+          0.057951124183853064,
+          -0.08574211243768456,
+          0.02229960322668788,
+          0.0197731460882619,
+          0.037480855866511335,
+          0.014501567945081463,
+          0.019313894965212467,
+          0.015534716928085666,
+          0.01924718063100328,
+          0.014888906043983111
+        ],
+        "q99": [
+          0.4228504704116889,
+          0.9837010790668748,
+          0.7180913469770518,
+          -0.05784016806244579,
+          0.514612030705292,
+          0.6783910810682822,
+          0.6035341481979898,
+          0.6762715916941239,
+          0.7075596448178942,
+          0.6270238740126298,
+          0.9857991865153608,
+          0.5125562485176647
+        ]
+      },
+      "neck_joints": {
+        "min": [
+          0.7009612917900085,
+          -0.0032425422687083483
+        ],
+        "max": [
+          0.7112611532211304,
+          0.0036240178160369396
+        ],
+        "mean": [
+          0.7044533545035223,
+          0.0010014864396475569
+        ],
+        "std": [
+          0.0019810688647565705,
+          0.0027107617865090093
+        ],
+        "q01": [
+          0.7039417799490104,
+          -0.0028693337709507255
+        ],
+        "q99": [
+          0.7081959350937106,
+          0.003242540992498085
+        ]
+      }
+    },
+    "action": {
+      "right_arm_joints": {
+        "min": [
+          -0.19921624660491943,
+          -0.17453299462795258,
+          -0.8291807174682617,
+          0.0,
+          -1.5707999467849731,
+          -0.5814089179039001,
+          -0.623637855052948
+        ],
+        "max": [
+          1.486642599105835,
+          0.7893767356872559,
+          0.7344165444374084,
+          2.0441505908966064,
+          0.38465243577957153,
+          0.785398006439209,
+          0.6433967351913452
+        ],
+        "mean": [
+          0.5430090535721166,
+          0.033566931036718685,
+          0.07625336950521511,
+          1.1092998512043604,
+          -1.0892971230997093,
+          0.09155957572632356,
+          0.073395238163872
+        ],
+        "std": [
+          0.4596794105521279,
+          0.1621918706557556,
+          0.2679870922781361,
+          0.5501861114444726,
+          0.44758367140485505,
+          0.22767518069131656,
+          0.16769684972295845
+        ],
+        "q01": [
+          -0.03456410663712079,
+          -0.16184220019671516,
+          -0.23216804975752398,
+          0.23341644017039692,
+          -1.5707028190120937,
+          -0.309905468247712,
+          -0.15133796950514602
+        ],
+        "q99": [
+          1.200440279459216,
+          0.29559855399130414,
+          0.47206481063425404,
+          1.7754976640909697,
+          -0.37575176490588347,
+          0.5010074686091875,
+          0.3440673376461279
+        ]
+      },
+      "left_arm_joints": {
+        "min": [
+          -1.5065116882324219,
+          -1.0190038681030273,
+          -1.0935002565383911,
+          0.014847817830741405,
+          -1.2871253490447998,
+          -0.785398006439209,
+          -0.98295658826828
+        ],
+        "max": [
+          0.25296857953071594,
+          0.17453299462795258,
+          1.501496434211731,
+          2.1152310371398926,
+          1.5707999467849731,
+          0.785398006439209,
+          1.3924580812454224
+        ],
+        "mean": [
+          -0.06444040306770334,
+          -0.2012424200521196,
+          0.17902124138928244,
+          1.6448206240709824,
+          0.9245709606725199,
+          -0.13036384597608147,
+          0.07370097759832434
+        ],
+        "std": [
+          0.13388403640089191,
+          0.22584157217233736,
+          0.19047329506273125,
+          0.14005725802758057,
+          0.7307305254518663,
+          0.3894608804758103,
+          0.22220778127217836
+        ],
+        "q01": [
+          -0.28973830174308024,
+          -0.6940539310712703,
+          -0.07905846509907914,
+          1.3640073856782455,
+          -0.4320198988812157,
+          -0.7719500454666719,
+          -0.48853233881168573
+        ],
+        "q99": [
+          0.07653752761821989,
+          0.08863872731021356,
+          0.5342535898797907,
+          1.8158065448750924,
+          1.570770554242114,
+          0.3071050589200862,
+          0.505248945544354
+        ]
+      },
+      "right_hand_joints": {
+        "min": [
+          0.026661602780222893,
+          0.0,
+          0.02366132102906704,
+          -0.17000000178813934,
+          0.01246256660670042,
+          0.0,
+          0.0,
+          0.0011867061257362366,
+          0.013637464493513107,
+          0.024103114381432533,
+          0.012091287411749363,
+          0.00664250273257494
+        ],
+        "max": [
+          1.7780132293701172,
+          1.3474156856536865,
+          1.4250937700271606,
+          -0.025157466530799866,
+          1.7364939451217651,
+          1.1551449298858643,
+          1.7935020923614502,
+          1.6204304695129395,
+          1.8591424226760864,
+          1.689421534538269,
+          1.8520755767822266,
+          1.1890243291854858
+        ],
+        "mean": [
+          0.6239154227631595,
+          0.4734269487818846,
+          0.7052524192097098,
+          -0.0994350955853528,
+          0.445617227524724,
+          0.4120455103231284,
+          0.5305768463764756,
+          0.5999651932137665,
+          0.5549466424355907,
+          0.5411834015984729,
+          0.48569650618147897,
+          0.4039426324710887
+        ],
+        "std": [
+          0.5605042020116761,
+          0.33643817537672954,
+          0.19982472888235422,
+          0.04681108942644247,
+          0.36050933420191983,
+          0.13796386090211465,
+          0.4911472584136365,
+          0.31706520184474446,
+          0.6512271464068475,
+          0.45676763934549547,
+          0.5481346251398389,
+          0.2617218955348148
+        ],
+        "q01": [
+          0.049512094295544706,
+          0.04391928536156868,
+          0.06661649222801683,
+          -0.1691424089310887,
+          0.03366654186732824,
+          0.03491670466944912,
+          0.045978101791642315,
+          0.07975563647047126,
+          0.027088694712146515,
+          0.050041808570090995,
+          0.025063916005994703,
+          0.027789555362793733
+        ],
+        "q99": [
+          1.5096395081324445,
+          1.0117019110491778,
+          0.9871990005581402,
+          -0.04557066642478349,
+          1.129917783318187,
+          0.6697547134449693,
+          1.4636922683123665,
+          1.1542747309416463,
+          1.704446982988189,
+          1.3244573535339408,
+          1.4724930172015087,
+          0.9484881772754448
+        ]
+      },
+      "left_hand_joints": {
+        "min": [
+          0.019045373424887657,
+          0.0,
+          0.05370108410716057,
+          -0.16869805753231049,
+          0.0012344357091933489,
+          0.008150840178132057,
+          0.03300570324063301,
+          0.006950031500309706,
+          0.012305227108299732,
+          0.010256324894726276,
+          0.011016922071576118,
+          0.007798284757882357
+        ],
+        "max": [
+          1.6031163930892944,
+          1.1825103759765625,
+          1.0342681407928467,
+          0.005556285381317139,
+          1.1919951438903809,
+          1.2375268936157227,
+          1.7269041538238525,
+          1.3056350946426392,
+          1.7406609058380127,
+          0.7451879382133484,
+          1.3663225173950195,
+          0.5
+        ],
+        "mean": [
+          0.3274554329878354,
+          0.6816605953002266,
+          0.665040378275847,
+          -0.08246567780487488,
+          0.3863661692061652,
+          0.5535841803974353,
+          0.46503769937507694,
+          0.4109603218945199,
+          0.3769462572830021,
+          0.5226880008575805,
+          0.33666394538840627,
+          0.48215487205665214
+        ],
+        "std": [
+          0.14631145376302618,
+          0.1512041150457038,
+          0.10564640145168502,
+          0.0387129805935982,
+          0.10139465603207952,
+          0.11700147021444009,
+          0.12220344020893094,
+          0.15816582331596807,
+          0.19094290279570064,
+          0.10102949256192277,
+          0.38079709737611284,
+          0.07690963441476438
+        ],
+        "q01": [
+          0.07869434876053279,
+          0.5046172398762443,
+          0.09302006264326931,
+          -0.1423123249924626,
+          0.0406597002223288,
+          0.04727644260624045,
+          0.05873163730448438,
+          0.031363568981418746,
+          0.03321028503469109,
+          0.044394902811118096,
+          0.02024680250758706,
+          0.04200780881531574
+        ],
+        "q99": [
+          0.4284983198796039,
+          0.966640028222133,
+          0.7364649212501883,
+          -0.030307355938947973,
+          0.5190797485182326,
+          0.684899658535276,
+          0.6059135765155187,
+          0.6885722217989116,
+          0.7126064420225153,
+          0.6312143412139029,
+          0.9916327871268753,
+          0.49999892561907305
+        ]
+      },
+      "neck_joints": {
+        "min": [
+          0.6980000138282776,
+          -0.002854566555470228
+        ],
+        "max": [
+          0.7066459059715271,
+          0.0032304299529641867
+        ],
+        "mean": [
+          0.6982365136311492,
+          2.895988731653634e-05
+        ],
+        "std": [
+          0.001417052313910553,
+          0.00046692749679010055
+        ],
+        "q01": [
+          0.6980000137282772,
+          -0.0026975402881033667
+        ],
+        "q99": [
+          0.7040469144690047,
+          0.002611027152444705
+        ]
+      }
+    },
+    "relative_action": {}
+  }
+}

checkpoint-25000/experiment_cfg/final_model_config.json

@@ -0,0 +1,86 @@
+{
+  "model_type": "AlinVLAv0",
+  "model_dtype": "bfloat16",
+  "model_name": "huiwon/alinvlm_v1_3",
+  "backbone_model_type": "contextvla_qwen3_vl_legacy",
+  "model_revision": null,
+  "tune_top_llm_layers": 4,
+  "backbone_embedding_dim": 4096,
+  "tune_llm": false,
+  "tune_visual": false,
+  "select_layer": 18,
+  "reproject_vision": false,
+  "use_flash_attention": true,
+  "load_bf16": true,
+  "collator_overwrite_image_inputs": false,
+  "qwen3_collator": true,
+  "backbone_trainable_params_fp32": true,
+  "apply_sincos_state_encoding": false,
+  "use_relative_action": true,
+  "use_percentiles": true,
+  "conversation_image_first": false,
+  "max_state_dim": 64,
+  "max_action_dim": 64,
+  "action_horizon": 40,
+  "hidden_size": 1024,
+  "input_embedding_dim": 1536,
+  "new_embodiment_train_ratio": 0,
+  "add_pos_embed": true,
+  "attn_dropout": 0.2,
+  "use_vlln": false,
+  "max_seq_len": 1024,
+  "use_mmditv0": false,
+  "n_meta_queries": 64,
+  "diffusion_model_cfg": {
+    "action_head_max_seq_len": 512,
+    "attention_head_dim": 64,
+    "depth_multi_stream": 4,
+    "depth_single_stream": 8,
+    "dropout": 0.2,
+    "final_dropout": true,
+    "num_attention_heads": 24,
+    "output_dim": 1024,
+    "positional_embeddings": "rope_sa_only",
+    "pre_norm": "layer_norm",
+    "qk_norm": "rms_norm",
+    "rope_theta": 10000.0,
+    "sa_dim": 1536,
+    "set_triple_stream_for_mq": false,
+    "set_triple_stream_for_state": false,
+    "temb_type": "input_token",
+    "use_swiglu": true,
+    "vl_dim": 4096
+  },
+  "use_mmditv1": true,
+  "num_inference_timesteps": 4,
+  "noise_beta_alpha": 1.5,
+  "noise_beta_beta": 1.0,
+  "noise_s": 0.999,
+  "num_timestep_buckets": 1000,
+  "tune_projector": true,
+  "tune_diffusion_model": true,
+  "tune_vlln": true,
+  "state_dropout_prob": 0.0,
+  "state_additive_noise_scale": 0.0,
+  "use_memory": false,
+  "memory_length": 4,
+  "memory_meta_queries_mode": "meta_only",
+  "memory_cfg": {
+    "hidden_size": 4096,
+    "intermediate_size": 16384,
+    "max_position_embeddings": 32,
+    "num_attention_heads": 16,
+    "num_hidden_layers": 2,
+    "num_key_value_heads": 16,
+    "rms_norm_eps": 1e-05,
+    "use_causal_attn": true,
+    "use_rope": true
+  },
+  "training_rtc_max_overlap": -1,
+  "inference_rtc_overlap_steps": null,
+  "inference_rtc_frozen_steps": null,
+  "rtc_ramp_rate": 10.0,
+  "use_video": true,
+  "video_length": 4,
+  "max_num_embodiments": 36
+}

checkpoint-25000/global_step25000/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:af2d9927aca9f18b4848bd9d72bf60b060d9c076910ea6f5da51c21226571599
+size 7127945825

checkpoint-25000/global_step25000/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:cf89b4910c29c3c30d86914a6b9a3703073aa8adb433c0b731b2b8aa7a7626e1
+size 7127945121

checkpoint-25000/global_step25000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12e0f2c38cc9cf288df5c0debe98bbc4cafe8cb702c9e8d07412165083063ff5
+size 7127944737

checkpoint-25000/global_step25000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d2186a0390ebaf2dce2da7667368a892bbf72008b72c5c56f38729bc34f6bea
+size 7127944417

checkpoint-25000/global_step25000/mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a5331a308f977760f90fd31f3be180cc03837b55023389f08eb7ce814f1d980
+size 22900273523

checkpoint-25000/latest

@@ -0,0 +1 @@
+global_step25000

checkpoint-25000/model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52ae3ddbc0fc9a28c55b1e176e06af221dd6df3c6d28897d61c0456e9e279e24
+size 4912540968

checkpoint-25000/model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dfd12ece9a6c9be16442ba07b75bc104cd29577bd097b9c184e218f685871f64
+size 4446192352

checkpoint-25000/model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fda8500387d3f1d2368c803965195866047e302a5fe4ac1bae280b5653889d6a
+size 4467286696

checkpoint-25000/model.safetensors.index.json

@@ -0,0 +1,732 @@
+{
+  "metadata": {
+    "total_parameters": 6912894784,
+    "total_size": 13825920640
+  },
+  "weight_map": {
+    "action_head.action_decoder.layer1.W": "model-00003-of-00003.safetensors",
+    "action_head.action_decoder.layer1.b": "model-00003-of-00003.safetensors",
+    "action_head.action_decoder.layer2.W": "model-00003-of-00003.safetensors",
+    "action_head.action_decoder.layer2.b": "model-00003-of-00003.safetensors",
+    "action_head.action_encoder.W1.W": "model-00003-of-00003.safetensors",
+    "action_head.action_encoder.W1.b": "model-00003-of-00003.safetensors",
+    "action_head.action_encoder.W2.W": "model-00003-of-00003.safetensors",
+    "action_head.action_encoder.W2.b": "model-00003-of-00003.safetensors",
+    "action_head.action_encoder.W3.W": "model-00003-of-00003.safetensors",
+    "action_head.action_encoder.W3.b": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.0.k_norm_sa.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.0.k_norm_vl.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.0.q_norm_sa.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.0.q_norm_vl.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.0.sa_mlp.w12.bias": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.0.sa_mlp.w12.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.0.sa_mlp.w3.bias": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.0.sa_mlp.w3.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.0.sa_proj.bias": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.0.sa_proj.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.0.sa_qkv.bias": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.0.sa_qkv.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.0.vl_mlp.w12.bias": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.0.vl_mlp.w12.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.0.vl_mlp.w3.bias": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.0.vl_mlp.w3.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.0.vl_proj.bias": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.0.vl_proj.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.0.vl_qkv.bias": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.0.vl_qkv.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.1.k_norm_sa.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.1.k_norm_vl.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.1.q_norm_sa.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.1.q_norm_vl.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.1.sa_mlp.w12.bias": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.1.sa_mlp.w12.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.1.sa_mlp.w3.bias": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.1.sa_mlp.w3.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.1.sa_proj.bias": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.1.sa_proj.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.1.sa_qkv.bias": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.1.sa_qkv.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.1.vl_mlp.w12.bias": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.1.vl_mlp.w12.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.1.vl_mlp.w3.bias": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.1.vl_mlp.w3.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.1.vl_proj.bias": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.1.vl_proj.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.1.vl_qkv.bias": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.1.vl_qkv.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.2.k_norm_sa.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.2.k_norm_vl.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.2.q_norm_sa.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.2.q_norm_vl.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.2.sa_mlp.w12.bias": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.2.sa_mlp.w12.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.2.sa_mlp.w3.bias": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.2.sa_mlp.w3.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.2.sa_proj.bias": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.2.sa_proj.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.2.sa_qkv.bias": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.2.sa_qkv.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.2.vl_mlp.w12.bias": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.2.vl_mlp.w12.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.2.vl_mlp.w3.bias": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.2.vl_mlp.w3.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.2.vl_proj.bias": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.2.vl_proj.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.2.vl_qkv.bias": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.2.vl_qkv.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.3.k_norm_sa.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.3.k_norm_vl.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.3.q_norm_sa.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.3.q_norm_vl.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.3.sa_mlp.w12.bias": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.3.sa_mlp.w12.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.3.sa_mlp.w3.bias": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.3.sa_mlp.w3.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.3.sa_proj.bias": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.3.sa_proj.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.3.sa_qkv.bias": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.3.sa_qkv.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.3.vl_mlp.w12.bias": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.3.vl_mlp.w12.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.3.vl_mlp.w3.bias": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.3.vl_mlp.w3.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.3.vl_proj.bias": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.3.vl_proj.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.3.vl_qkv.bias": "model-00003-of-00003.safetensors",
+    "action_head.model.double_blocks.3.vl_qkv.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.proj_out_1.bias": "model-00003-of-00003.safetensors",
+    "action_head.model.proj_out_1.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.proj_out_2.bias": "model-00003-of-00003.safetensors",
+    "action_head.model.proj_out_2.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.rope_embedder.freqs_cis_0": "model-00003-of-00003.safetensors",
+    "action_head.model.rope_embedder.freqs_cis_1": "model-00003-of-00003.safetensors",
+    "action_head.model.single_blocks.0.k_norm.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.single_blocks.0.linear1.bias": "model-00003-of-00003.safetensors",
+    "action_head.model.single_blocks.0.linear1.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.single_blocks.0.linear2.bias": "model-00003-of-00003.safetensors",
+    "action_head.model.single_blocks.0.linear2.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.single_blocks.0.mlp_proj.bias": "model-00003-of-00003.safetensors",
+    "action_head.model.single_blocks.0.mlp_proj.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.single_blocks.0.q_norm.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.single_blocks.1.k_norm.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.single_blocks.1.linear1.bias": "model-00003-of-00003.safetensors",
+    "action_head.model.single_blocks.1.linear1.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.single_blocks.1.linear2.bias": "model-00003-of-00003.safetensors",
+    "action_head.model.single_blocks.1.linear2.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.single_blocks.1.mlp_proj.bias": "model-00003-of-00003.safetensors",
+    "action_head.model.single_blocks.1.mlp_proj.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.single_blocks.1.q_norm.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.single_blocks.2.k_norm.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.single_blocks.2.linear1.bias": "model-00003-of-00003.safetensors",
+    "action_head.model.single_blocks.2.linear1.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.single_blocks.2.linear2.bias": "model-00003-of-00003.safetensors",
+    "action_head.model.single_blocks.2.linear2.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.single_blocks.2.mlp_proj.bias": "model-00003-of-00003.safetensors",
+    "action_head.model.single_blocks.2.mlp_proj.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.single_blocks.2.q_norm.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.single_blocks.3.k_norm.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.single_blocks.3.linear1.bias": "model-00003-of-00003.safetensors",
+    "action_head.model.single_blocks.3.linear1.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.single_blocks.3.linear2.bias": "model-00003-of-00003.safetensors",
+    "action_head.model.single_blocks.3.linear2.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.single_blocks.3.mlp_proj.bias": "model-00003-of-00003.safetensors",
+    "action_head.model.single_blocks.3.mlp_proj.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.single_blocks.3.q_norm.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.single_blocks.4.k_norm.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.single_blocks.4.linear1.bias": "model-00003-of-00003.safetensors",
+    "action_head.model.single_blocks.4.linear1.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.single_blocks.4.linear2.bias": "model-00003-of-00003.safetensors",
+    "action_head.model.single_blocks.4.linear2.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.single_blocks.4.mlp_proj.bias": "model-00003-of-00003.safetensors",
+    "action_head.model.single_blocks.4.mlp_proj.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.single_blocks.4.q_norm.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.single_blocks.5.k_norm.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.single_blocks.5.linear1.bias": "model-00003-of-00003.safetensors",
+    "action_head.model.single_blocks.5.linear1.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.single_blocks.5.linear2.bias": "model-00003-of-00003.safetensors",
+    "action_head.model.single_blocks.5.linear2.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.single_blocks.5.mlp_proj.bias": "model-00003-of-00003.safetensors",
+    "action_head.model.single_blocks.5.mlp_proj.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.single_blocks.5.q_norm.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.single_blocks.6.k_norm.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.single_blocks.6.linear1.bias": "model-00003-of-00003.safetensors",
+    "action_head.model.single_blocks.6.linear1.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.single_blocks.6.linear2.bias": "model-00003-of-00003.safetensors",
+    "action_head.model.single_blocks.6.linear2.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.single_blocks.6.mlp_proj.bias": "model-00003-of-00003.safetensors",
+    "action_head.model.single_blocks.6.mlp_proj.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.single_blocks.6.q_norm.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.single_blocks.7.k_norm.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.single_blocks.7.linear1.bias": "model-00003-of-00003.safetensors",
+    "action_head.model.single_blocks.7.linear1.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.single_blocks.7.linear2.bias": "model-00003-of-00003.safetensors",
+    "action_head.model.single_blocks.7.linear2.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.single_blocks.7.mlp_proj.bias": "model-00003-of-00003.safetensors",
+    "action_head.model.single_blocks.7.mlp_proj.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.single_blocks.7.q_norm.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.timestep_encoder.timestep_embedder.linear_1.bias": "model-00003-of-00003.safetensors",
+    "action_head.model.timestep_encoder.timestep_embedder.linear_1.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.timestep_encoder.timestep_embedder.linear_2.bias": "model-00003-of-00003.safetensors",
+    "action_head.model.timestep_encoder.timestep_embedder.linear_2.weight": "model-00003-of-00003.safetensors",
+    "action_head.model.vl_proj_to_sa.bias": "model-00003-of-00003.safetensors",
+    "action_head.model.vl_proj_to_sa.weight": "model-00003-of-00003.safetensors",
+    "action_head.position_embedding.weight": "model-00003-of-00003.safetensors",
+    "action_head.state_encoder.layer1.W": "model-00003-of-00003.safetensors",
+    "action_head.state_encoder.layer1.b": "model-00003-of-00003.safetensors",
+    "action_head.state_encoder.layer2.W": "model-00003-of-00003.safetensors",
+    "action_head.state_encoder.layer2.b": "model-00003-of-00003.safetensors",
+    "backbone.meta_emb": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.lm_head.weight": "model-00003-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.embed_tokens.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.0.layer.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.0.layer.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.0.layer.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.0.layer.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.0.layer.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.0.layer.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.0.layer.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.0.layer.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.0.layer.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.0.layer.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.0.layer.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.1.layer.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.1.layer.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.1.layer.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.1.layer.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.1.layer.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.1.layer.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.1.layer.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.1.layer.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.1.layer.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.1.layer.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.1.layer.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.10.layer.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.10.layer.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.10.layer.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.10.layer.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.10.layer.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.10.layer.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.10.layer.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.10.layer.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.10.layer.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.10.layer.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.10.layer.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.11.layer.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.11.layer.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.11.layer.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.11.layer.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.11.layer.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.11.layer.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.11.layer.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.11.layer.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.11.layer.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.11.layer.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.11.layer.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.12.layer.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.12.layer.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.12.layer.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.12.layer.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.12.layer.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.12.layer.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.12.layer.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.12.layer.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.12.layer.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.12.layer.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.12.layer.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.13.layer.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.13.layer.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.13.layer.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.13.layer.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.13.layer.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.13.layer.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.13.layer.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.13.layer.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.13.layer.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.13.layer.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.13.layer.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.14.layer.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.14.layer.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.14.layer.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.14.layer.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.14.layer.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.14.layer.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.14.layer.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.14.layer.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.14.layer.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.14.layer.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.14.layer.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.15.layer.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.15.layer.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.15.layer.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.15.layer.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.15.layer.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.15.layer.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.15.layer.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.15.layer.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.15.layer.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.15.layer.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.15.layer.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.16.layer.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.16.layer.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.16.layer.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.16.layer.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.16.layer.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.16.layer.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.16.layer.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.16.layer.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.16.layer.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.16.layer.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.16.layer.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.17.layer.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.17.layer.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.17.layer.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.17.layer.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.17.layer.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.17.layer.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.17.layer.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.17.layer.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.17.layer.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.17.layer.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.17.layer.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.2.layer.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.2.layer.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.2.layer.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.2.layer.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.2.layer.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.2.layer.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.2.layer.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.2.layer.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.2.layer.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.2.layer.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.2.layer.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.3.layer.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.3.layer.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.3.layer.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.3.layer.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.3.layer.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.3.layer.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.3.layer.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.3.layer.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.3.layer.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.3.layer.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.3.layer.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.4.layer.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.4.layer.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.4.layer.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.4.layer.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.4.layer.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.4.layer.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.4.layer.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.4.layer.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.4.layer.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.4.layer.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.4.layer.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.5.layer.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.5.layer.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.5.layer.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.5.layer.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.5.layer.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.5.layer.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.5.layer.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.5.layer.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.5.layer.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.5.layer.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.5.layer.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.6.layer.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.6.layer.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.6.layer.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.6.layer.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.6.layer.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.6.layer.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.6.layer.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.6.layer.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.6.layer.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.6.layer.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.6.layer.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.7.layer.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.7.layer.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.7.layer.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.7.layer.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.7.layer.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.7.layer.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.7.layer.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.7.layer.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.7.layer.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.7.layer.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.7.layer.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.8.layer.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.8.layer.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.8.layer.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.8.layer.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.8.layer.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.8.layer.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.8.layer.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.8.layer.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.8.layer.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.8.layer.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.8.layer.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.9.layer.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.9.layer.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.9.layer.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.9.layer.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.9.layer.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.9.layer.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.9.layer.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.9.layer.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.9.layer.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.9.layer.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.layers.9.layer.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.language_model.norm.weight": "model-00002-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.0.attn.proj.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.0.attn.proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.0.attn.qkv.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.0.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.0.mlp.linear_fc1.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.0.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.0.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.0.mlp.linear_fc2.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.0.norm1.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.0.norm1.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.0.norm2.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.0.norm2.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.1.attn.proj.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.1.attn.proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.1.attn.qkv.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.1.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.1.mlp.linear_fc1.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.1.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.1.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.1.mlp.linear_fc2.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.1.norm1.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.1.norm1.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.1.norm2.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.1.norm2.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.10.attn.proj.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.10.attn.proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.10.attn.qkv.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.10.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.10.mlp.linear_fc1.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.10.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.10.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.10.mlp.linear_fc2.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.10.norm1.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.10.norm1.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.10.norm2.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.10.norm2.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.11.attn.proj.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.11.attn.proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.11.attn.qkv.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.11.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.11.mlp.linear_fc1.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.11.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.11.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.11.mlp.linear_fc2.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.11.norm1.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.11.norm1.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.11.norm2.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.11.norm2.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.12.attn.proj.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.12.attn.proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.12.attn.qkv.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.12.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.12.mlp.linear_fc1.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.12.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.12.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.12.mlp.linear_fc2.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.12.norm1.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.12.norm1.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.12.norm2.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.12.norm2.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.13.attn.proj.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.13.attn.proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.13.attn.qkv.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.13.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.13.mlp.linear_fc1.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.13.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.13.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.13.mlp.linear_fc2.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.13.norm1.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.13.norm1.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.13.norm2.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.13.norm2.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.14.attn.proj.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.14.attn.proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.14.attn.qkv.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.14.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.14.mlp.linear_fc1.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.14.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.14.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.14.mlp.linear_fc2.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.14.norm1.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.14.norm1.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.14.norm2.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.14.norm2.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.15.attn.proj.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.15.attn.proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.15.attn.qkv.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.15.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.15.mlp.linear_fc1.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.15.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.15.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.15.mlp.linear_fc2.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.15.norm1.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.15.norm1.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.15.norm2.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.15.norm2.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.16.attn.proj.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.16.attn.proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.16.attn.qkv.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.16.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.16.mlp.linear_fc1.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.16.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.16.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.16.mlp.linear_fc2.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.16.norm1.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.16.norm1.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.16.norm2.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.16.norm2.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.17.attn.proj.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.17.attn.proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.17.attn.qkv.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.17.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.17.mlp.linear_fc1.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.17.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.17.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.17.mlp.linear_fc2.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.17.norm1.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.17.norm1.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.17.norm2.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.17.norm2.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.18.attn.proj.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.18.attn.proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.18.attn.qkv.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.18.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.18.mlp.linear_fc1.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.18.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.18.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.18.mlp.linear_fc2.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.18.norm1.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.18.norm1.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.18.norm2.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.18.norm2.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.19.attn.proj.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.19.attn.proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.19.attn.qkv.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.19.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.19.mlp.linear_fc1.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.19.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.19.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.19.mlp.linear_fc2.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.19.norm1.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.19.norm1.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.19.norm2.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.19.norm2.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.2.attn.proj.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.2.attn.proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.2.attn.qkv.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.2.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.2.mlp.linear_fc1.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.2.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.2.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.2.mlp.linear_fc2.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.2.norm1.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.2.norm1.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.2.norm2.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.2.norm2.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.20.attn.proj.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.20.attn.proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.20.attn.qkv.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.20.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.20.mlp.linear_fc1.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.20.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.20.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.20.mlp.linear_fc2.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.20.norm1.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.20.norm1.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.20.norm2.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.20.norm2.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.21.attn.proj.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.21.attn.proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.21.attn.qkv.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.21.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.21.mlp.linear_fc1.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.21.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.21.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.21.mlp.linear_fc2.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.21.norm1.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.21.norm1.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.21.norm2.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.21.norm2.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.22.attn.proj.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.22.attn.proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.22.attn.qkv.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.22.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.22.mlp.linear_fc1.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.22.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.22.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.22.mlp.linear_fc2.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.22.norm1.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.22.norm1.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.22.norm2.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.22.norm2.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.23.attn.proj.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.23.attn.proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.23.attn.qkv.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.23.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.23.mlp.linear_fc1.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.23.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.23.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.23.mlp.linear_fc2.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.23.norm1.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.23.norm1.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.23.norm2.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.23.norm2.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.24.attn.proj.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.24.attn.proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.24.attn.qkv.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.24.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.24.mlp.linear_fc1.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.24.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.24.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.24.mlp.linear_fc2.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.24.norm1.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.24.norm1.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.24.norm2.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.24.norm2.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.25.attn.proj.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.25.attn.proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.25.attn.qkv.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.25.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.25.mlp.linear_fc1.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.25.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.25.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.25.mlp.linear_fc2.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.25.norm1.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.25.norm1.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.25.norm2.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.25.norm2.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.26.attn.proj.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.26.attn.proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.26.attn.qkv.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.26.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.26.mlp.linear_fc1.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.26.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.26.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.26.mlp.linear_fc2.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.26.norm1.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.26.norm1.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.26.norm2.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.26.norm2.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.3.attn.proj.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.3.attn.proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.3.attn.qkv.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.3.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.3.mlp.linear_fc1.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.3.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.3.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.3.mlp.linear_fc2.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.3.norm1.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.3.norm1.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.3.norm2.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.3.norm2.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.4.attn.proj.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.4.attn.proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.4.attn.qkv.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.4.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.4.mlp.linear_fc1.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.4.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.4.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.4.mlp.linear_fc2.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.4.norm1.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.4.norm1.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.4.norm2.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.4.norm2.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.5.attn.proj.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.5.attn.proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.5.attn.qkv.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.5.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.5.mlp.linear_fc1.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.5.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.5.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.5.mlp.linear_fc2.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.5.norm1.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.5.norm1.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.5.norm2.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.5.norm2.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.6.attn.proj.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.6.attn.proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.6.attn.qkv.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.6.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.6.mlp.linear_fc1.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.6.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.6.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.6.mlp.linear_fc2.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.6.norm1.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.6.norm1.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.6.norm2.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.6.norm2.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.7.attn.proj.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.7.attn.proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.7.attn.qkv.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.7.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.7.mlp.linear_fc1.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.7.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.7.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.7.mlp.linear_fc2.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.7.norm1.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.7.norm1.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.7.norm2.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.7.norm2.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.8.attn.proj.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.8.attn.proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.8.attn.qkv.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.8.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.8.mlp.linear_fc1.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.8.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.8.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.8.mlp.linear_fc2.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.8.norm1.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.8.norm1.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.8.norm2.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.8.norm2.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.9.attn.proj.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.9.attn.proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.9.attn.qkv.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.9.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.9.mlp.linear_fc1.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.9.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.9.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.9.mlp.linear_fc2.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.9.norm1.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.9.norm1.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.9.norm2.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.blocks.9.norm2.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.deepstack_merger_list.0.linear_fc1.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.deepstack_merger_list.0.linear_fc1.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.deepstack_merger_list.0.linear_fc2.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.deepstack_merger_list.0.linear_fc2.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.deepstack_merger_list.0.norm.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.deepstack_merger_list.0.norm.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.deepstack_merger_list.1.linear_fc1.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.deepstack_merger_list.1.linear_fc1.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.deepstack_merger_list.1.linear_fc2.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.deepstack_merger_list.1.linear_fc2.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.deepstack_merger_list.1.norm.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.deepstack_merger_list.1.norm.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.deepstack_merger_list.2.linear_fc1.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.deepstack_merger_list.2.linear_fc1.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.deepstack_merger_list.2.linear_fc2.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.deepstack_merger_list.2.linear_fc2.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.deepstack_merger_list.2.norm.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.deepstack_merger_list.2.norm.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.merger.linear_fc1.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.merger.linear_fc1.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.merger.linear_fc2.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.merger.linear_fc2.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.merger.norm.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.merger.norm.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.patch_embed.proj.bias": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.patch_embed.proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.qwen_model.model.visual.pos_embed.weight": "model-00001-of-00003.safetensors"
+  }
+}

checkpoint-25000/processor_config.json

@@ -0,0 +1,3250 @@
+{
+  "processor_class": "AlinVLAv0Processor",
+  "processor_kwargs": {
+    "modality_configs": {
+      "humanoid_everyday_g1": {
+        "video": {
+          "delta_indices": [
+            -6,
+            -4,
+            -2,
+            0
+          ],
+          "modality_keys": [
+            "egocentric_resized"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "state": {
+          "delta_indices": [
+            0
+          ],
+          "modality_keys": [
+            "left_arm",
+            "left_hand",
+            "right_arm",
+            "right_hand"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "action": {
+          "delta_indices": [
+            0,
+            1,
+            2,
+            3,
+            4,
+            5,
+            6,
+            7,
+            8,
+            9,
+            10,
+            11,
+            12,
+            13,
+            14,
+            15
+          ],
+          "modality_keys": [
+            "left_arm",
+            "left_hand",
+            "right_arm",
+            "right_hand"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": [
+            {
+              "rep": "ABSOLUTE",
+              "type": "NON_EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "ABSOLUTE",
+              "type": "NON_EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "ABSOLUTE",
+              "type": "NON_EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "ABSOLUTE",
+              "type": "NON_EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            }
+          ]
+        },
+        "language": {
+          "delta_indices": [
+            0
+          ],
+          "modality_keys": [
+            "annotation.human.action.task_description"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        }
+      },
+      "kuka": {
+        "video": {
+          "delta_indices": [
+            -6,
+            -4,
+            -2,
+            0
+          ],
+          "modality_keys": [
+            "primary"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "state": {
+          "delta_indices": [
+            0
+          ],
+          "modality_keys": [
+            "end_effector_position",
+            "end_effector_rotation",
+            "gripper_position"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "action": {
+          "delta_indices": [
+            0,
+            1,
+            2,
+            3,
+            4,
+            5,
+            6,
+            7,
+            8,
+            9,
+            10,
+            11,
+            12,
+            13,
+            14,
+            15
+          ],
+          "modality_keys": [
+            "end_effector_position",
+            "end_effector_rotation",
+            "gripper_close"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": [
+            {
+              "rep": "DELTA",
+              "type": "EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "DELTA",
+              "type": "EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "ABSOLUTE",
+              "type": "NON_EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            }
+          ]
+        },
+        "language": {
+          "delta_indices": [
+            0
+          ],
+          "modality_keys": [
+            "annotation.human.action.task_description"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        }
+      },
+      "cmu_stretch": {
+        "video": {
+          "delta_indices": [
+            -6,
+            -4,
+            -2,
+            0
+          ],
+          "modality_keys": [
+            "primary"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "state": {
+          "delta_indices": [
+            0
+          ],
+          "modality_keys": [
+            "end_effector_position",
+            "end_effector_rotation",
+            "gripper_position"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "action": {
+          "delta_indices": [
+            0,
+            1,
+            2,
+            3,
+            4,
+            5,
+            6,
+            7,
+            8,
+            9,
+            10,
+            11,
+            12,
+            13,
+            14,
+            15
+          ],
+          "modality_keys": [
+            "end_effector_position",
+            "end_effector_rotation",
+            "gripper_close"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": [
+            {
+              "rep": "DELTA",
+              "type": "EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "DELTA",
+              "type": "EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "ABSOLUTE",
+              "type": "NON_EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            }
+          ]
+        },
+        "language": {
+          "delta_indices": [
+            0
+          ],
+          "modality_keys": [
+            "annotation.human.action.task_description"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        }
+      },
+      "stanford_hydra_dataset_converted_externally_to_rlds": {
+        "video": {
+          "delta_indices": [
+            -6,
+            -4,
+            -2,
+            0
+          ],
+          "modality_keys": [
+            "primary",
+            "wrist"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "state": {
+          "delta_indices": [
+            0
+          ],
+          "modality_keys": [
+            "end_effector_position",
+            "end_effector_rotation",
+            "gripper_position"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "action": {
+          "delta_indices": [
+            0,
+            1,
+            2,
+            3,
+            4,
+            5,
+            6,
+            7,
+            8,
+            9,
+            10,
+            11,
+            12,
+            13,
+            14,
+            15
+          ],
+          "modality_keys": [
+            "end_effector_position",
+            "end_effector_rotation",
+            "gripper_close"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": [
+            {
+              "rep": "DELTA",
+              "type": "EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "DELTA",
+              "type": "EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "ABSOLUTE",
+              "type": "NON_EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            }
+          ]
+        },
+        "language": {
+          "delta_indices": [
+            0
+          ],
+          "modality_keys": [
+            "annotation.human.action.task_description"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        }
+      },
+      "iamlab_cmu_pickup_insert_converted_externally_to_rlds": {
+        "video": {
+          "delta_indices": [
+            -6,
+            -4,
+            -2,
+            0
+          ],
+          "modality_keys": [
+            "primary",
+            "wrist"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "state": {
+          "delta_indices": [
+            0
+          ],
+          "modality_keys": [
+            "end_effector_position",
+            "end_effector_rotation",
+            "gripper_position"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "action": {
+          "delta_indices": [
+            0,
+            1,
+            2,
+            3,
+            4,
+            5,
+            6,
+            7,
+            8,
+            9,
+            10,
+            11,
+            12,
+            13,
+            14,
+            15
+          ],
+          "modality_keys": [
+            "end_effector_position",
+            "end_effector_rotation",
+            "gripper_close"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": [
+            {
+              "rep": "DELTA",
+              "type": "EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "DELTA",
+              "type": "EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "ABSOLUTE",
+              "type": "NON_EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            }
+          ]
+        },
+        "language": {
+          "delta_indices": [
+            0
+          ],
+          "modality_keys": [
+            "annotation.human.action.task_description"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        }
+      },
+      "berkeley_fanuc_manipulation": {
+        "video": {
+          "delta_indices": [
+            -6,
+            -4,
+            -2,
+            0
+          ],
+          "modality_keys": [
+            "primary",
+            "wrist"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "state": {
+          "delta_indices": [
+            0
+          ],
+          "modality_keys": [
+            "joint_position",
+            "gripper_position"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "action": {
+          "delta_indices": [
+            0,
+            1,
+            2,
+            3,
+            4,
+            5,
+            6,
+            7,
+            8,
+            9,
+            10,
+            11,
+            12,
+            13,
+            14,
+            15
+          ],
+          "modality_keys": [
+            "end_effector_position",
+            "end_effector_rotation",
+            "gripper_close"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": [
+            {
+              "rep": "DELTA",
+              "type": "EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "DELTA",
+              "type": "EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "ABSOLUTE",
+              "type": "NON_EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            }
+          ]
+        },
+        "language": {
+          "delta_indices": [
+            0
+          ],
+          "modality_keys": [
+            "annotation.human.action.task_description"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        }
+      },
+      "viola": {
+        "video": {
+          "delta_indices": [
+            -6,
+            -4,
+            -2,
+            0
+          ],
+          "modality_keys": [
+            "primary",
+            "wrist"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "state": {
+          "delta_indices": [
+            0
+          ],
+          "modality_keys": [
+            "joint_position",
+            "gripper_position"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "action": {
+          "delta_indices": [
+            0,
+            1,
+            2,
+            3,
+            4,
+            5,
+            6,
+            7,
+            8,
+            9,
+            10,
+            11,
+            12,
+            13,
+            14,
+            15
+          ],
+          "modality_keys": [
+            "end_effector_position",
+            "end_effector_rotation",
+            "gripper_close"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": [
+            {
+              "rep": "DELTA",
+              "type": "EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "DELTA",
+              "type": "EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "ABSOLUTE",
+              "type": "NON_EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            }
+          ]
+        },
+        "language": {
+          "delta_indices": [
+            0
+          ],
+          "modality_keys": [
+            "annotation.human.action.task_description"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        }
+      },
+      "galaxea": {
+        "video": {
+          "delta_indices": [
+            -6,
+            -4,
+            -2,
+            0
+          ],
+          "modality_keys": [
+            "primary",
+            "wrist_left",
+            "wrist_right"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "state": {
+          "delta_indices": [
+            0
+          ],
+          "modality_keys": [
+            "state"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "action": {
+          "delta_indices": [
+            0,
+            1,
+            2,
+            3,
+            4,
+            5,
+            6,
+            7,
+            8,
+            9,
+            10,
+            11,
+            12,
+            13,
+            14,
+            15
+          ],
+          "modality_keys": [
+            "action"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": [
+            {
+              "rep": "ABSOLUTE",
+              "type": "NON_EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            }
+          ]
+        },
+        "language": {
+          "delta_indices": [
+            0
+          ],
+          "modality_keys": [
+            "annotation.human.action.task_description"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        }
+      },
+      "utaustin_mutex": {
+        "video": {
+          "delta_indices": [
+            -6,
+            -4,
+            -2,
+            0
+          ],
+          "modality_keys": [
+            "primary",
+            "wrist"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "state": {
+          "delta_indices": [
+            0
+          ],
+          "modality_keys": [
+            "joint_position",
+            "gripper_position"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "action": {
+          "delta_indices": [
+            0,
+            1,
+            2,
+            3,
+            4,
+            5,
+            6,
+            7,
+            8,
+            9,
+            10,
+            11,
+            12,
+            13,
+            14,
+            15
+          ],
+          "modality_keys": [
+            "end_effector_position",
+            "end_effector_rotation",
+            "gripper_close"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": [
+            {
+              "rep": "DELTA",
+              "type": "EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "DELTA",
+              "type": "EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "ABSOLUTE",
+              "type": "NON_EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            }
+          ]
+        },
+        "language": {
+          "delta_indices": [
+            0
+          ],
+          "modality_keys": [
+            "annotation.human.action.task_description"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        }
+      },
+      "dobbe": {
+        "video": {
+          "delta_indices": [
+            -6,
+            -4,
+            -2,
+            0
+          ],
+          "modality_keys": [
+            "wrist"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "state": {
+          "delta_indices": [
+            0
+          ],
+          "modality_keys": [
+            "end_effector_position",
+            "end_effector_rotation",
+            "gripper_position"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "action": {
+          "delta_indices": [
+            0,
+            1,
+            2,
+            3,
+            4,
+            5,
+            6,
+            7,
+            8,
+            9,
+            10,
+            11,
+            12,
+            13,
+            14,
+            15
+          ],
+          "modality_keys": [
+            "end_effector_position",
+            "end_effector_rotation",
+            "gripper_close"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": [
+            {
+              "rep": "DELTA",
+              "type": "EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "DELTA",
+              "type": "EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "ABSOLUTE",
+              "type": "NON_EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            }
+          ]
+        },
+        "language": {
+          "delta_indices": [
+            0
+          ],
+          "modality_keys": [
+            "annotation.human.action.task_description"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        }
+      },
+      "taco_play": {
+        "video": {
+          "delta_indices": [
+            -6,
+            -4,
+            -2,
+            0
+          ],
+          "modality_keys": [
+            "primary",
+            "wrist"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "state": {
+          "delta_indices": [
+            0
+          ],
+          "modality_keys": [
+            "end_effector_position",
+            "end_effector_rotation",
+            "gripper_position"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "action": {
+          "delta_indices": [
+            0,
+            1,
+            2,
+            3,
+            4,
+            5,
+            6,
+            7,
+            8,
+            9,
+            10,
+            11,
+            12,
+            13,
+            14,
+            15
+          ],
+          "modality_keys": [
+            "end_effector_position",
+            "end_effector_rotation",
+            "gripper_close"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": [
+            {
+              "rep": "DELTA",
+              "type": "EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "DELTA",
+              "type": "EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "ABSOLUTE",
+              "type": "NON_EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            }
+          ]
+        },
+        "language": {
+          "delta_indices": [
+            0
+          ],
+          "modality_keys": [
+            "annotation.human.action.task_description"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        }
+      },
+      "humanoid_everyday_h1": {
+        "video": {
+          "delta_indices": [
+            -6,
+            -4,
+            -2,
+            0
+          ],
+          "modality_keys": [
+            "egocentric_resized"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "state": {
+          "delta_indices": [
+            0
+          ],
+          "modality_keys": [
+            "left_arm",
+            "left_hand",
+            "right_arm",
+            "right_hand"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "action": {
+          "delta_indices": [
+            0,
+            1,
+            2,
+            3,
+            4,
+            5,
+            6,
+            7,
+            8,
+            9,
+            10,
+            11,
+            12,
+            13,
+            14,
+            15
+          ],
+          "modality_keys": [
+            "left_arm",
+            "left_hand",
+            "right_arm",
+            "right_hand"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": [
+            {
+              "rep": "ABSOLUTE",
+              "type": "NON_EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "ABSOLUTE",
+              "type": "NON_EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "ABSOLUTE",
+              "type": "NON_EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "ABSOLUTE",
+              "type": "NON_EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            }
+          ]
+        },
+        "language": {
+          "delta_indices": [
+            0
+          ],
+          "modality_keys": [
+            "annotation.human.action.task_description"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        }
+      },
+      "berkeley_autolab_ur5": {
+        "video": {
+          "delta_indices": [
+            -6,
+            -4,
+            -2,
+            0
+          ],
+          "modality_keys": [
+            "primary",
+            "wrist"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "state": {
+          "delta_indices": [
+            0
+          ],
+          "modality_keys": [
+            "end_effector_position",
+            "end_effector_rotation",
+            "gripper_position"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "action": {
+          "delta_indices": [
+            0,
+            1,
+            2,
+            3,
+            4,
+            5,
+            6,
+            7,
+            8,
+            9,
+            10,
+            11,
+            12,
+            13,
+            14,
+            15
+          ],
+          "modality_keys": [
+            "end_effector_position",
+            "end_effector_rotation",
+            "gripper_close"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": [
+            {
+              "rep": "DELTA",
+              "type": "EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "DELTA",
+              "type": "EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "ABSOLUTE",
+              "type": "NON_EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            }
+          ]
+        },
+        "language": {
+          "delta_indices": [
+            0
+          ],
+          "modality_keys": [
+            "annotation.human.action.task_description"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        }
+      },
+      "jaco_play": {
+        "video": {
+          "delta_indices": [
+            -6,
+            -4,
+            -2,
+            0
+          ],
+          "modality_keys": [
+            "primary",
+            "wrist"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "state": {
+          "delta_indices": [
+            0
+          ],
+          "modality_keys": [
+            "end_effector_position",
+            "end_effector_rotation",
+            "gripper_position"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "action": {
+          "delta_indices": [
+            0,
+            1,
+            2,
+            3,
+            4,
+            5,
+            6,
+            7,
+            8,
+            9,
+            10,
+            11,
+            12,
+            13,
+            14,
+            15
+          ],
+          "modality_keys": [
+            "end_effector_position",
+            "end_effector_rotation",
+            "gripper_close"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": [
+            {
+              "rep": "DELTA",
+              "type": "EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "DELTA",
+              "type": "EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "ABSOLUTE",
+              "type": "NON_EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            }
+          ]
+        },
+        "language": {
+          "delta_indices": [
+            0
+          ],
+          "modality_keys": [
+            "annotation.human.action.task_description"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        }
+      },
+      "furniture_bench_dataset_converted_externally_to_rlds": {
+        "video": {
+          "delta_indices": [
+            -6,
+            -4,
+            -2,
+            0
+          ],
+          "modality_keys": [
+            "primary",
+            "wrist"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "state": {
+          "delta_indices": [
+            0
+          ],
+          "modality_keys": [
+            "end_effector_position",
+            "end_effector_rotation",
+            "gripper_position"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "action": {
+          "delta_indices": [
+            0,
+            1,
+            2,
+            3,
+            4,
+            5,
+            6,
+            7,
+            8,
+            9,
+            10,
+            11,
+            12,
+            13,
+            14,
+            15
+          ],
+          "modality_keys": [
+            "end_effector_position",
+            "end_effector_rotation",
+            "gripper_close"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": [
+            {
+              "rep": "DELTA",
+              "type": "EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "DELTA",
+              "type": "EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "ABSOLUTE",
+              "type": "NON_EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            }
+          ]
+        },
+        "language": {
+          "delta_indices": [
+            0
+          ],
+          "modality_keys": [
+            "annotation.human.action.task_description"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        }
+      },
+      "berkeley_cable_routing": {
+        "video": {
+          "delta_indices": [
+            -6,
+            -4,
+            -2,
+            0
+          ],
+          "modality_keys": [
+            "primary",
+            "secondary",
+            "wrist"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "state": {
+          "delta_indices": [
+            0
+          ],
+          "modality_keys": [
+            "joint_position"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "action": {
+          "delta_indices": [
+            0,
+            1,
+            2,
+            3,
+            4,
+            5,
+            6,
+            7,
+            8,
+            9,
+            10,
+            11,
+            12,
+            13,
+            14,
+            15
+          ],
+          "modality_keys": [
+            "end_effector_position",
+            "end_effector_rotation",
+            "gripper_close"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": [
+            {
+              "rep": "DELTA",
+              "type": "EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "DELTA",
+              "type": "EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "ABSOLUTE",
+              "type": "NON_EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            }
+          ]
+        },
+        "language": {
+          "delta_indices": [
+            0
+          ],
+          "modality_keys": [
+            "annotation.human.action.task_description"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        }
+      },
+      "nyu_franka_play_dataset_converted_externally_to_rlds": {
+        "video": {
+          "delta_indices": [
+            -6,
+            -4,
+            -2,
+            0
+          ],
+          "modality_keys": [
+            "primary",
+            "secondary"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "state": {
+          "delta_indices": [
+            0
+          ],
+          "modality_keys": [
+            "end_effector_position",
+            "end_effector_rotation",
+            "gripper_position"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "action": {
+          "delta_indices": [
+            0,
+            1,
+            2,
+            3,
+            4,
+            5,
+            6,
+            7,
+            8,
+            9,
+            10,
+            11,
+            12,
+            13,
+            14,
+            15
+          ],
+          "modality_keys": [
+            "end_effector_position",
+            "end_effector_rotation",
+            "gripper_close"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": [
+            {
+              "rep": "DELTA",
+              "type": "EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "DELTA",
+              "type": "EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "ABSOLUTE",
+              "type": "NON_EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            }
+          ]
+        },
+        "language": {
+          "delta_indices": [
+            0
+          ],
+          "modality_keys": [
+            "annotation.human.action.task_description"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        }
+      },
+      "bridge_orig": {
+        "video": {
+          "delta_indices": [
+            -6,
+            -4,
+            -2,
+            0
+          ],
+          "modality_keys": [
+            "primary",
+            "secondary"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "state": {
+          "delta_indices": [
+            0
+          ],
+          "modality_keys": [
+            "end_effector_position",
+            "end_effector_rotation",
+            "gripper_position"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "action": {
+          "delta_indices": [
+            0,
+            1,
+            2,
+            3,
+            4,
+            5,
+            6,
+            7,
+            8,
+            9,
+            10,
+            11,
+            12,
+            13,
+            14,
+            15
+          ],
+          "modality_keys": [
+            "end_effector_position",
+            "end_effector_rotation",
+            "gripper_close"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": [
+            {
+              "rep": "DELTA",
+              "type": "EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "DELTA",
+              "type": "EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "ABSOLUTE",
+              "type": "NON_EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            }
+          ]
+        },
+        "language": {
+          "delta_indices": [
+            0
+          ],
+          "modality_keys": [
+            "annotation.human.action.task_description"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        }
+      },
+      "droid": {
+        "video": {
+          "delta_indices": [
+            -6,
+            -4,
+            -2,
+            0
+          ],
+          "modality_keys": [
+            "primary",
+            "secondary",
+            "wrist"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "state": {
+          "delta_indices": [
+            0
+          ],
+          "modality_keys": [
+            "end_effector_position",
+            "end_effector_rotation",
+            "gripper_position"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "action": {
+          "delta_indices": [
+            0,
+            1,
+            2,
+            3,
+            4,
+            5,
+            6,
+            7,
+            8,
+            9,
+            10,
+            11,
+            12,
+            13,
+            14,
+            15
+          ],
+          "modality_keys": [
+            "end_effector_position",
+            "end_effector_rotation",
+            "gripper_close"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": [
+            {
+              "rep": "DELTA",
+              "type": "EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "DELTA",
+              "type": "EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "ABSOLUTE",
+              "type": "NON_EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            }
+          ]
+        },
+        "language": {
+          "delta_indices": [
+            0
+          ],
+          "modality_keys": [
+            "annotation.human.action.task_description"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        }
+      },
+      "agibot_gripper": {
+        "video": {
+          "delta_indices": [
+            -6,
+            -4,
+            -2,
+            0
+          ],
+          "modality_keys": [
+            "primary",
+            "wrist_left",
+            "wrist_right"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "state": {
+          "delta_indices": [
+            0
+          ],
+          "modality_keys": [
+            "state"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "action": {
+          "delta_indices": [
+            0,
+            1,
+            2,
+            3,
+            4,
+            5,
+            6,
+            7,
+            8,
+            9,
+            10,
+            11,
+            12,
+            13,
+            14,
+            15
+          ],
+          "modality_keys": [
+            "action"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": [
+            {
+              "rep": "ABSOLUTE",
+              "type": "NON_EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            }
+          ]
+        },
+        "language": {
+          "delta_indices": [
+            0
+          ],
+          "modality_keys": [
+            "annotation.human.action.task_description"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        }
+      },
+      "simulation_gr1": {
+        "video": {
+          "delta_indices": [
+            -6,
+            -4,
+            -2,
+            0
+          ],
+          "modality_keys": [
+            "ego_view"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "state": {
+          "delta_indices": [
+            0
+          ],
+          "modality_keys": [
+            "left_arm",
+            "left_hand",
+            "left_leg",
+            "neck",
+            "right_arm",
+            "right_hand",
+            "right_leg",
+            "waist"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "action": {
+          "delta_indices": [
+            0,
+            1,
+            2,
+            3,
+            4,
+            5,
+            6,
+            7,
+            8,
+            9,
+            10,
+            11,
+            12,
+            13,
+            14,
+            15
+          ],
+          "modality_keys": [
+            "left_arm",
+            "left_hand",
+            "left_leg",
+            "neck",
+            "right_arm",
+            "right_hand",
+            "right_leg",
+            "waist"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": [
+            {
+              "rep": "ABSOLUTE",
+              "type": "NON_EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "ABSOLUTE",
+              "type": "NON_EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "ABSOLUTE",
+              "type": "NON_EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "ABSOLUTE",
+              "type": "NON_EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "ABSOLUTE",
+              "type": "NON_EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "ABSOLUTE",
+              "type": "NON_EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "ABSOLUTE",
+              "type": "NON_EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "ABSOLUTE",
+              "type": "NON_EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            }
+          ]
+        },
+        "language": {
+          "delta_indices": [
+            0
+          ],
+          "modality_keys": [
+            "annotation.human.action.task_description"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        }
+      },
+      "austin_sirius_dataset_converted_externally_to_rlds": {
+        "video": {
+          "delta_indices": [
+            -6,
+            -4,
+            -2,
+            0
+          ],
+          "modality_keys": [
+            "primary",
+            "wrist"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "state": {
+          "delta_indices": [
+            0
+          ],
+          "modality_keys": [
+            "end_effector_position",
+            "end_effector_rotation",
+            "gripper_position"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "action": {
+          "delta_indices": [
+            0,
+            1,
+            2,
+            3,
+            4,
+            5,
+            6,
+            7,
+            8,
+            9,
+            10,
+            11,
+            12,
+            13,
+            14,
+            15
+          ],
+          "modality_keys": [
+            "end_effector_position",
+            "end_effector_rotation",
+            "gripper_close"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": [
+            {
+              "rep": "DELTA",
+              "type": "EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "DELTA",
+              "type": "EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "ABSOLUTE",
+              "type": "NON_EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            }
+          ]
+        },
+        "language": {
+          "delta_indices": [
+            0
+          ],
+          "modality_keys": [
+            "annotation.human.action.task_description"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        }
+      },
+      "austin_sailor_dataset_converted_externally_to_rlds": {
+        "video": {
+          "delta_indices": [
+            -6,
+            -4,
+            -2,
+            0
+          ],
+          "modality_keys": [
+            "primary",
+            "wrist"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "state": {
+          "delta_indices": [
+            0
+          ],
+          "modality_keys": [
+            "end_effector_position",
+            "end_effector_rotation",
+            "gripper_position"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "action": {
+          "delta_indices": [
+            0,
+            1,
+            2,
+            3,
+            4,
+            5,
+            6,
+            7,
+            8,
+            9,
+            10,
+            11,
+            12,
+            13,
+            14,
+            15
+          ],
+          "modality_keys": [
+            "end_effector_position",
+            "end_effector_rotation",
+            "gripper_close"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": [
+            {
+              "rep": "DELTA",
+              "type": "EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "DELTA",
+              "type": "EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "ABSOLUTE",
+              "type": "NON_EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            }
+          ]
+        },
+        "language": {
+          "delta_indices": [
+            0
+          ],
+          "modality_keys": [
+            "annotation.human.action.task_description"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        }
+      },
+      "language_table": {
+        "video": {
+          "delta_indices": [
+            -6,
+            -4,
+            -2,
+            0
+          ],
+          "modality_keys": [
+            "primary"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "state": {
+          "delta_indices": [
+            0
+          ],
+          "modality_keys": [
+            "end_effector_position"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "action": {
+          "delta_indices": [
+            0,
+            1,
+            2,
+            3,
+            4,
+            5,
+            6,
+            7,
+            8,
+            9,
+            10,
+            11,
+            12,
+            13,
+            14,
+            15
+          ],
+          "modality_keys": [
+            "end_effector_position"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": [
+            {
+              "rep": "DELTA",
+              "type": "EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            }
+          ]
+        },
+        "language": {
+          "delta_indices": [
+            0
+          ],
+          "modality_keys": [
+            "annotation.human.action.task_description"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        }
+      },
+      "ucsd_kitchen_dataset_converted_externally_to_rlds": {
+        "video": {
+          "delta_indices": [
+            -6,
+            -4,
+            -2,
+            0
+          ],
+          "modality_keys": [
+            "primary"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "state": {
+          "delta_indices": [
+            0
+          ],
+          "modality_keys": [
+            "joint_position"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "action": {
+          "delta_indices": [
+            0,
+            1,
+            2,
+            3,
+            4,
+            5,
+            6,
+            7,
+            8,
+            9,
+            10,
+            11,
+            12,
+            13,
+            14,
+            15
+          ],
+          "modality_keys": [
+            "end_effector_position",
+            "end_effector_rotation",
+            "gripper_close"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": [
+            {
+              "rep": "DELTA",
+              "type": "EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "DELTA",
+              "type": "EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "ABSOLUTE",
+              "type": "NON_EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            }
+          ]
+        },
+        "language": {
+          "delta_indices": [
+            0
+          ],
+          "modality_keys": [
+            "annotation.human.action.task_description"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        }
+      },
+      "dlr_edan_shared_control_converted_externally_to_rlds": {
+        "video": {
+          "delta_indices": [
+            -6,
+            -4,
+            -2,
+            0
+          ],
+          "modality_keys": [
+            "primary"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "state": {
+          "delta_indices": [
+            0
+          ],
+          "modality_keys": [
+            "end_effector_position",
+            "end_effector_rotation",
+            "gripper_position"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "action": {
+          "delta_indices": [
+            0,
+            1,
+            2,
+            3,
+            4,
+            5,
+            6,
+            7,
+            8,
+            9,
+            10,
+            11,
+            12,
+            13,
+            14,
+            15
+          ],
+          "modality_keys": [
+            "end_effector_position",
+            "end_effector_rotation",
+            "gripper_close"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": [
+            {
+              "rep": "DELTA",
+              "type": "EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "DELTA",
+              "type": "EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "ABSOLUTE",
+              "type": "NON_EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            }
+          ]
+        },
+        "language": {
+          "delta_indices": [
+            0
+          ],
+          "modality_keys": [
+            "annotation.human.action.task_description"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        }
+      },
+      "bc_z": {
+        "video": {
+          "delta_indices": [
+            -6,
+            -4,
+            -2,
+            0
+          ],
+          "modality_keys": [
+            "primary"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "state": {
+          "delta_indices": [
+            0
+          ],
+          "modality_keys": [
+            "end_effector_position",
+            "end_effector_rotation",
+            "gripper_position"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "action": {
+          "delta_indices": [
+            0,
+            1,
+            2,
+            3,
+            4,
+            5,
+            6,
+            7,
+            8,
+            9,
+            10,
+            11,
+            12,
+            13,
+            14,
+            15
+          ],
+          "modality_keys": [
+            "end_effector_position",
+            "end_effector_rotation",
+            "gripper_close"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": [
+            {
+              "rep": "DELTA",
+              "type": "EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "DELTA",
+              "type": "EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "ABSOLUTE",
+              "type": "NON_EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            }
+          ]
+        },
+        "language": {
+          "delta_indices": [
+            0
+          ],
+          "modality_keys": [
+            "annotation.human.action.task_description"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        }
+      },
+      "austin_buds_dataset_converted_externally_to_rlds": {
+        "video": {
+          "delta_indices": [
+            -6,
+            -4,
+            -2,
+            0
+          ],
+          "modality_keys": [
+            "primary",
+            "wrist"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "state": {
+          "delta_indices": [
+            0
+          ],
+          "modality_keys": [
+            "joint_position",
+            "gripper_position"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "action": {
+          "delta_indices": [
+            0,
+            1,
+            2,
+            3,
+            4,
+            5,
+            6,
+            7,
+            8,
+            9,
+            10,
+            11,
+            12,
+            13,
+            14,
+            15
+          ],
+          "modality_keys": [
+            "end_effector_position",
+            "end_effector_rotation",
+            "gripper_close"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": [
+            {
+              "rep": "DELTA",
+              "type": "EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "DELTA",
+              "type": "EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "ABSOLUTE",
+              "type": "NON_EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            }
+          ]
+        },
+        "language": {
+          "delta_indices": [
+            0
+          ],
+          "modality_keys": [
+            "annotation.human.action.task_description"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        }
+      },
+      "agibot_dexhand": {
+        "video": {
+          "delta_indices": [
+            -6,
+            -4,
+            -2,
+            0
+          ],
+          "modality_keys": [
+            "primary"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "state": {
+          "delta_indices": [
+            0
+          ],
+          "modality_keys": [
+            "state"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "action": {
+          "delta_indices": [
+            0,
+            1,
+            2,
+            3,
+            4,
+            5,
+            6,
+            7,
+            8,
+            9,
+            10,
+            11,
+            12,
+            13,
+            14,
+            15
+          ],
+          "modality_keys": [
+            "action"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": [
+            {
+              "rep": "ABSOLUTE",
+              "type": "NON_EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            }
+          ]
+        },
+        "language": {
+          "delta_indices": [
+            0
+          ],
+          "modality_keys": [
+            "annotation.human.action.task_description"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        }
+      },
+      "fractal20220817_data": {
+        "video": {
+          "delta_indices": [
+            -6,
+            -4,
+            -2,
+            0
+          ],
+          "modality_keys": [
+            "primary"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "state": {
+          "delta_indices": [
+            0
+          ],
+          "modality_keys": [
+            "end_effector_position",
+            "end_effector_rotation",
+            "gripper_position"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "action": {
+          "delta_indices": [
+            0,
+            1,
+            2,
+            3,
+            4,
+            5,
+            6,
+            7,
+            8,
+            9,
+            10,
+            11,
+            12,
+            13,
+            14,
+            15
+          ],
+          "modality_keys": [
+            "end_effector_position",
+            "end_effector_rotation",
+            "gripper_close"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": [
+            {
+              "rep": "DELTA",
+              "type": "EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "DELTA",
+              "type": "EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "ABSOLUTE",
+              "type": "NON_EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            }
+          ]
+        },
+        "language": {
+          "delta_indices": [
+            0
+          ],
+          "modality_keys": [
+            "annotation.human.action.task_description"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        }
+      },
+      "neural_gr1": {
+        "video": {
+          "delta_indices": [
+            -6,
+            -4,
+            -2,
+            0
+          ],
+          "modality_keys": [
+            "ego_view"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "state": {
+          "delta_indices": [
+            0
+          ],
+          "modality_keys": [
+            "left_arm",
+            "left_hand",
+            "left_leg",
+            "neck",
+            "right_arm",
+            "right_hand",
+            "right_leg",
+            "waist"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "action": {
+          "delta_indices": [
+            0,
+            1,
+            2,
+            3,
+            4,
+            5,
+            6,
+            7,
+            8,
+            9,
+            10,
+            11,
+            12,
+            13,
+            14,
+            15
+          ],
+          "modality_keys": [
+            "left_arm",
+            "left_hand",
+            "left_leg",
+            "neck",
+            "right_arm",
+            "right_hand",
+            "right_leg",
+            "waist"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": [
+            {
+              "rep": "ABSOLUTE",
+              "type": "NON_EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "ABSOLUTE",
+              "type": "NON_EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "ABSOLUTE",
+              "type": "NON_EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "ABSOLUTE",
+              "type": "NON_EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "ABSOLUTE",
+              "type": "NON_EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "ABSOLUTE",
+              "type": "NON_EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "ABSOLUTE",
+              "type": "NON_EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "ABSOLUTE",
+              "type": "NON_EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            }
+          ]
+        },
+        "language": {
+          "delta_indices": [
+            0
+          ],
+          "modality_keys": [
+            "annotation.human.action.task_description"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        }
+      },
+      "roboturk": {
+        "video": {
+          "delta_indices": [
+            -6,
+            -4,
+            -2,
+            0
+          ],
+          "modality_keys": [
+            "primary"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "state": {
+          "delta_indices": [
+            0
+          ],
+          "modality_keys": [
+            "none"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "action": {
+          "delta_indices": [
+            0,
+            1,
+            2,
+            3,
+            4,
+            5,
+            6,
+            7,
+            8,
+            9,
+            10,
+            11,
+            12,
+            13,
+            14,
+            15
+          ],
+          "modality_keys": [
+            "end_effector_position",
+            "end_effector_rotation",
+            "gripper_close"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": [
+            {
+              "rep": "DELTA",
+              "type": "EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "DELTA",
+              "type": "EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "ABSOLUTE",
+              "type": "NON_EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            }
+          ]
+        },
+        "language": {
+          "delta_indices": [
+            0
+          ],
+          "modality_keys": [
+            "annotation.human.action.task_description"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        }
+      },
+      "fmb_dataset": {
+        "video": {
+          "delta_indices": [
+            -6,
+            -4,
+            -2,
+            0
+          ],
+          "modality_keys": [
+            "primary",
+            "secondary",
+            "wrist"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "state": {
+          "delta_indices": [
+            0
+          ],
+          "modality_keys": [
+            "end_effector_position",
+            "end_effector_rotation",
+            "gripper_position"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "action": {
+          "delta_indices": [
+            0,
+            1,
+            2,
+            3,
+            4,
+            5,
+            6,
+            7,
+            8,
+            9,
+            10,
+            11,
+            12,
+            13,
+            14,
+            15
+          ],
+          "modality_keys": [
+            "end_effector_position",
+            "end_effector_rotation",
+            "gripper_close"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": [
+            {
+              "rep": "DELTA",
+              "type": "EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "DELTA",
+              "type": "EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "ABSOLUTE",
+              "type": "NON_EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            }
+          ]
+        },
+        "language": {
+          "delta_indices": [
+            0
+          ],
+          "modality_keys": [
+            "annotation.human.action.task_description"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        }
+      },
+      "toto": {
+        "video": {
+          "delta_indices": [
+            -6,
+            -4,
+            -2,
+            0
+          ],
+          "modality_keys": [
+            "primary"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "state": {
+          "delta_indices": [
+            0
+          ],
+          "modality_keys": [
+            "joint_position",
+            "gripper_position"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "action": {
+          "delta_indices": [
+            0,
+            1,
+            2,
+            3,
+            4,
+            5,
+            6,
+            7,
+            8,
+            9,
+            10,
+            11,
+            12,
+            13,
+            14,
+            15
+          ],
+          "modality_keys": [
+            "end_effector_position",
+            "end_effector_rotation",
+            "gripper_close"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": [
+            {
+              "rep": "DELTA",
+              "type": "EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "DELTA",
+              "type": "EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "ABSOLUTE",
+              "type": "NON_EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            }
+          ]
+        },
+        "language": {
+          "delta_indices": [
+            0
+          ],
+          "modality_keys": [
+            "annotation.human.action.task_description"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        }
+      },
+      "action_net": {
+        "video": {
+          "delta_indices": [
+            -6,
+            -4,
+            -2,
+            0
+          ],
+          "modality_keys": [
+            "primary"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "state": {
+          "delta_indices": [
+            0
+          ],
+          "modality_keys": [
+            "state"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "action": {
+          "delta_indices": [
+            0,
+            1,
+            2,
+            3,
+            4,
+            5,
+            6,
+            7,
+            8,
+            9,
+            10,
+            11,
+            12,
+            13,
+            14,
+            15
+          ],
+          "modality_keys": [
+            "action"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": [
+            {
+              "rep": "ABSOLUTE",
+              "type": "NON_EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            }
+          ]
+        },
+        "language": {
+          "delta_indices": [
+            0
+          ],
+          "modality_keys": [
+            "annotation.human.action.task_description"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        }
+      },
+      "new_embodiment": {
+        "video": {
+          "delta_indices": [
+            -9,
+            -7,
+            -5,
+            -3,
+            -8,
+            -6,
+            -4,
+            -2,
+            -7,
+            -5,
+            -3,
+            -1,
+            -6,
+            -4,
+            -2,
+            0
+          ],
+          "modality_keys": [
+            "camera_ego_left",
+            "camera_ego_right"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "state": {
+          "delta_indices": [
+            -3,
+            -2,
+            -1,
+            0
+          ],
+          "modality_keys": [
+            "right_arm_joints",
+            "left_arm_joints",
+            "right_hand_joints",
+            "left_hand_joints",
+            "neck_joints"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        },
+        "action": {
+          "delta_indices": [
+            0,
+            1,
+            2,
+            3,
+            4,
+            5,
+            6,
+            7,
+            8,
+            9,
+            10,
+            11,
+            12,
+            13,
+            14,
+            15,
+            16,
+            17,
+            18,
+            19,
+            20,
+            21,
+            22,
+            23,
+            24,
+            25,
+            26,
+            27,
+            28,
+            29,
+            30,
+            31,
+            32,
+            33,
+            34,
+            35,
+            36,
+            37,
+            38,
+            39
+          ],
+          "modality_keys": [
+            "right_arm_joints",
+            "left_arm_joints",
+            "right_hand_joints",
+            "left_hand_joints",
+            "neck_joints"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": [
+            {
+              "rep": "ABSOLUTE",
+              "type": "NON_EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "ABSOLUTE",
+              "type": "NON_EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "ABSOLUTE",
+              "type": "NON_EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "ABSOLUTE",
+              "type": "NON_EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            },
+            {
+              "rep": "ABSOLUTE",
+              "type": "NON_EEF",
+              "format": "DEFAULT",
+              "state_key": null
+            }
+          ]
+        },
+        "language": {
+          "delta_indices": [
+            0
+          ],
+          "modality_keys": [
+            "annotation.human.task_description"
+          ],
+          "sin_cos_embedding_keys": null,
+          "mean_std_embedding_keys": null,
+          "action_configs": null
+        }
+      }
+    },
+    "image_crop_size": null,
+    "image_target_size": null,
+    "use_albumentations": true,
+    "random_rotation_angle": null,
+    "color_jitter_params": {
+      "brightness": 0.3,
+      "contrast": 0.4,
+      "hue": 0.08,
+      "saturation": 0.5
+    },
+    "shortest_image_edge": null,
+    "crop_fraction": 0.95,
+    "max_area": 65536,
+    "resize_m": 32,
+    "model_name": "huiwon/alinvlm_v1_3",
+    "model_type": "contextvla_qwen3_vl_legacy",
+    "formalize_language": true,
+    "max_state_dim": 64,
+    "max_action_dim": 64,
+    "max_action_horizon": 40,
+    "use_percentiles": true,
+    "clip_outliers": true,
+    "apply_sincos_state_encoding": false,
+    "use_relative_action": true,
+    "memory_length": 1,
+    "new_embodiment_train_ratio": 0
+  }
+}

checkpoint-25000/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d004e6279a62acb05b996376edf85f97b3dd2a489b9c3dfc08bea9744fcfa1c
+size 15429

checkpoint-25000/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe232cd3e0f7a7e6e3cd86f4c2ef35c6ba4474ca36b1ede1645462da1a14cb87
+size 15429

checkpoint-25000/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a1d5b5d9708266e5843f70a2b10e198cd759c3e18155d87b18c02bb45e17d81
+size 15429

checkpoint-25000/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad65d115e38ad07a2a386a620a8c4bd993eb36b081d71aa9e703023a9afb0014
+size 15429