Upload pot14 step1024 hf_ckpt + configs (weights)

.gitattributes

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

added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

chat_template.json

@@ -0,0 +1,3 @@
+{
+  "chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}"
+}

config.json

@@ -0,0 +1,54 @@
+{
+    "type": "pi0",
+    "n_obs_steps": 1,
+    "input_features": {},
+    "output_features": {},
+    "device": "cpu",
+    "use_amp": false,
+    "push_to_hub": true,
+    "repo_id": null,
+    "private": null,
+    "tags": null,
+    "license": null,
+    "pretrained_path": null,
+    "paligemma_variant": "gemma_2b",
+    "action_expert_variant": "gemma_300m",
+    "dtype": "float32",
+    "chunk_size": 50,
+    "n_action_steps": 50,
+    "max_state_dim": 75,
+    "max_action_dim": 75,
+    "num_inference_steps": 10,
+    "time_sampling_beta_alpha": 1.5,
+    "time_sampling_beta_beta": 1.0,
+    "time_sampling_scale": 0.999,
+    "time_sampling_offset": 0.001,
+    "min_period": 0.004,
+    "max_period": 4.0,
+    "rtc_config": null,
+    "image_resolution": [
+        224,
+        224
+    ],
+    "empty_cameras": 0,
+    "normalization_mapping": {
+        "VISUAL": "IDENTITY",
+        "STATE": "MEAN_STD",
+        "ACTION": "MEAN_STD"
+    },
+    "gradient_checkpointing": false,
+    "compile_model": false,
+    "compile_mode": "max-autotune",
+    "optimizer_lr": 2.5e-05,
+    "optimizer_betas": [
+        0.9,
+        0.95
+    ],
+    "optimizer_eps": 1e-08,
+    "optimizer_weight_decay": 0.01,
+    "optimizer_grad_clip_norm": 1.0,
+    "scheduler_warmup_steps": 1000,
+    "scheduler_decay_steps": 30000,
+    "scheduler_decay_lr": 2.5e-06,
+    "tokenizer_max_length": 72
+}

lingbotvla_cli.yaml

@@ -0,0 +1,137 @@
+data:
+  cameras:
+  - camera_top
+  - camera_wrist_left
+  - camera_wrist_right
+  chat_template: default
+  data_name: pot14
+  data_type: conversation
+  dataloader_type: native
+  datasets_type: vla
+  drop_last: true
+  img_size: 224
+  joints:
+  - '{''arm.position'': 6}'
+  - '{''effector.position'': 1}'
+  max_seq_len: 2048
+  norm_stats_file: assets/norm_stats/pot14_right_arm.json
+  norm_type: meanstd
+  num_workers: 4
+  pin_memory: true
+  prefetch_factor: 2
+  robot_config_root: configs/robot_configs
+  text_keys: messages
+  train_path: /root/autodl-tmp/data/processed/pot14_right_arm
+  train_size: 10000000
+  video_backend: torchcodec
+model:
+  adanorm_time: true
+  attn_implementation: flash_attention_2
+  basic_modules: []
+  config_path: /root/autodl-tmp/models/pretrained/lingbot-vla-4b
+  decoders: {}
+  encoders: {}
+  final_norm_adanorm: false
+  force_use_huggingface: false
+  model_path: /root/autodl-tmp/models/pretrained/lingbot-vla-4b
+  moge_path: null
+  morgbd_path: null
+  nosplit_gate_liner: false
+  post_training: true
+  separate_time_proj: false
+  split_gate_liner: false
+  tokenizer_path: /root/autodl-tmp/models/pretrained/Qwen2.5-VL-3B-Instruct
+  use_lm_head: false
+  vlm_repo_id: null
+  vocab_size: 0
+train:
+  action_dim: null
+  activation_gpu_limit: 0.0
+  adapt_to_pi_aloha: false
+  align_params: {}
+  bsz_warmup_init_mbtoken: 200
+  bsz_warmup_ratio: 0
+  chunk_size: 50
+  ckpt_manager: dcp
+  context_parallel_size: 1
+  data_parallel_mode: fsdp2
+  data_parallel_replicate_size: 1
+  data_parallel_shard_size: 1
+  decayed_max_grad_norm: 1.0
+  dyn_bsz: true
+  dyn_bsz_buffer_size: 200
+  dyn_bsz_margin: 0
+  empty_cache_steps: 500
+  enable_activation_offload: false
+  enable_expert_vision: false
+  enable_forward_prefetch: true
+  enable_fp32: true
+  enable_fsdp_offload: false
+  enable_full_determinism: false
+  enable_full_shard: false
+  enable_gradient_checkpointing: true
+  enable_mixed_precision: true
+  enable_profiling: false
+  enable_reentrant: false
+  enable_resume: false
+  expert_parallel_size: 1
+  expert_vision_path: null
+  expert_vision_type: null
+  freeze_vision_encoder: false
+  freeze_vit: false
+  global_batch_size: 32
+  gradient_accumulation_steps: 16
+  init_device: cuda
+  load_checkpoint_path: null
+  loss_type: fm
+  lr: 5.0e-05
+  lr_decay_ratio: 1.0
+  lr_decay_style: constant
+  lr_min: 1.0e-07
+  lr_start: 0.0
+  lr_warmup_ratio: 0
+  max_action_dim: 75
+  max_checkpoints_to_keep: 1
+  max_grad_norm: 1.0
+  max_state_dim: 75
+  max_steps: 1024
+  micro_batch_size: 2
+  module_fsdp_enable: true
+  norm_qkv: false
+  num_steps: 10
+  num_train_epochs: 999999999
+  optimizer: adamw
+  output_dir: output/pot14/
+  pipeline_parallel_size: 1
+  profile_end_step: 2
+  profile_profile_memory: true
+  profile_record_shapes: true
+  profile_start_step: 1
+  profile_trace_dir: ./trace
+  profile_with_stack: true
+  resize_imgs_with_padding:
+  - 224
+  - 224
+  resume_dataloader_state: true
+  rmpad: false
+  rmpad_with_pos_ids: false
+  save_epochs: 0
+  save_hf_weights: true
+  save_optimizer: false
+  save_steps: 0
+  seed: 42
+  stable_train_steps: 100000
+  tensor_parallel_size: 1
+  tokenizer_max_length: 72
+  train_expert_only: false
+  train_state_proj: true
+  ulysses_parallel_size: 1
+  use_cache: true
+  use_compile: true
+  use_delta_joint_actions_aloha: false
+  use_wandb: false
+  vit_lr: 1.0e-06
+  vlm_causal: false
+  wandb_name: null
+  wandb_project: LingBotVLA
+  weight_decay: 0

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83432b52caa7230dc0720c5290f3a04db8e7b1e4fd94a41eee4f72d5759a5f26
+size 4972318304

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ada73276d8e86f8c528efce746d11797449defa34f3a2e1ca7aea82452afd933
+size 4932955392

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77f05aa9d46d99b9b377f6b540b03a8277567e4f3af57fc733b4a2758b942004
+size 4932955480

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81459fd9ad3b2e922d0f8b241440d58e59fe84b89046a75249ce1f97784d3ee4
+size 1951701732

preprocessor_config.json

@@ -0,0 +1,29 @@
+{
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "Qwen2VLImageProcessor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "max_pixels": 12845056,
+  "merge_size": 2,
+  "min_pixels": 3136,
+  "patch_size": 14,
+  "processor_class": "Qwen2_5_VLProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "longest_edge": 12845056,
+    "shortest_edge": 3136
+  },
+  "temporal_patch_size": 2
+}

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

tokenizer_config.json

@@ -0,0 +1,210 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "processor_class": "Qwen2_5_VLProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}