Upload SO-101 init checkpoint (converted from nvidia/Cosmos3-Edge-Policy-DROID)

.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

README.md

@@ -0,0 +1,63 @@
+---
+license: other
+license_name: nvidia-open-model-license
+base_model: nvidia/Cosmos3-Edge-Policy-DROID
+tags:
+  - lerobot
+  - cosmos3
+  - robotics
+  - so101
+---
+
+# Cosmos3-Edge-Policy-SO101-init
+
+`nvidia/Cosmos3-Edge-Policy-DROID` (4B Mixture-of-Transformers world action model,
+DROID 8-D joint policy) converted to the **LeRobot `cosmos3` policy format** and
+retargeted to the **SO-101** embodiment (5 joints + gripper, absolute joint position).
+This is the **un-finetuned initialization checkpoint**: weights are bit-identical to
+the NVIDIA release; only the config/normalization contract changed. No weight surgery
+is needed because the Cosmos3 action head is a `DomainAwareLinear` over a zero-padded
+64-dim action vector with a per-sample raw-dim mask.
+
+Converted with `scripts/convert_cosmos3_edge_policy_to_lerobot.py` from
+[nota-github/xpu-lerobot#6](https://github.com/nota-github/xpu-lerobot/pull/6).
+
+## SO-101 retargeting (vs the DROID contract)
+
+| field | DROID | this repo |
+|---|---|---|
+| `raw_action_dim` | 8 (7 joints + gripper) | **6 (5 joints + gripper)** |
+| cameras | wrist + left/right over-shoulder | **wrist + top** (3rd view zero-padded) |
+| normalization | — | **QUANTILES (q01/q99 → [-1,1])**, stats injected from the training dataset at train time |
+| `conditioning_fps` | 15 | **30** |
+| `invert_gripper` | true | **false** |
+| `chunk_size` / `n_action_steps` | 32 / 32 | 32 / 32 |
+| `domain_id` | 8 (`droid_lerobot`) | 8 (reused, adapted by fine-tuning) |
+
+## Usage
+
+Requires the `cosmos3` policy from the PR above and `diffusers` git main (>= 0.40.0.dev0
+schema — 0.39 silently drops `use_und_k_norm_for_gen`/`qk_norm_for_text`/`hidden_act`
+and builds a different architecture), `huggingface_hub>=1.23`, `safetensors>=0.8`.
+
+```bash
+lerobot-train \
+  --policy.path=geonmin-kim/Cosmos3-Edge-Policy-SO101-init \
+  --dataset.repo_id=<your SO-101 LeRobot dataset> ...
+```
+
+Note: `config.json`'s `text_processor_name_or_path` points at the checkpoint
+directory; when loading from the Hub on a fresh machine, download the full snapshot
+(`snapshot_download`) and pass the local path, or override
+`--policy.text_processor_name_or_path=<local snapshot dir>` (the Qwen tokenizer files
+`tokenizer.json` / `tokenizer_config.json` / `special_tokens_map.json` /
+`chat_template.jinja` ship in this repo).
+
+## Fine-tuned descendants
+
+- Flow matching (4-step): `geonmin-kim/Cosmos3-Edge-SO101-Morig-D6231-step{3000..30000}` —
+  use `guidance_scale=1.0` at inference (no prompt dropout during fine-tuning, CFG hurts).
+- Drift 1-step (`num_inference_steps=1`): `geonmin-kim/Cosmos3-Edge-SO101-Drift-D6231-step{5000..100000}` —
+  recommended for deployment (open-loop MAE 5.45 vs 26.96, latency 0.25s vs 0.62s per chunk on B200).
+
+Training data of the descendants: `geonmin-kim/SO101-large-small-cube-11dataset-ratio6231-0729`.

chat_template.jinja

@@ -0,0 +1,324 @@
+
+{% macro render_extra_keys(json_dict, handled_keys) %}
+    {%- if json_dict is mapping %}
+        {%- for json_key in json_dict if json_key not in handled_keys %}
+            {%- if json_dict[json_key] is mapping or (json_dict[json_key] is sequence and json_dict[json_key] is not string) %}
+                {{- '
+<' ~ json_key ~ '>' ~ (json_dict[json_key] | tojson | safe) ~ '</' ~ json_key ~ '>' }}
+            {%- else %}
+                {{-'
+<' ~ json_key ~ '>' ~ (json_dict[json_key] | string) ~ '</' ~ json_key ~ '>' }}
+            {%- endif %}
+        {%- endfor %}
+    {%- endif %}
+{% endmacro %}
+{%- set enable_thinking = enable_thinking if enable_thinking is defined else True %}
+{%- set truncate_history_thinking = truncate_history_thinking if truncate_history_thinking is defined else True %}
+
+{%- set ns = namespace(last_user_idx = -1) %}
+{%- set loop_messages = messages %}
+{%- for m in loop_messages %}
+  {%- if m["role"] == "user" %}
+    {%- set ns.last_user_idx = loop.index0 %}
+  {%- endif %}
+{%- endfor %}
+
+{%- if messages[0]["role"] == "system" %}
+    {%- if messages[0]["content"] is string %}
+        {%- set system_message = messages[0]["content"] %}
+    {%- else %}
+        {%- set ns = namespace(system_text="") %}
+        {%- for part in messages[0]["content"] %}
+            {%- if 'text' in part %}
+                {%- set ns.system_text = ns.system_text + part.text %}
+            {%- endif %}
+        {%- endfor %}
+        {%- set system_message = ns.system_text %}
+    {%- endif %}
+
+    {%- set loop_messages = messages[1:] %}
+{%- else %}
+    {%- set system_message = "" %}
+    {%- set loop_messages = messages %}
+{%- endif %}
+{%- if not tools is defined %}
+    {%- set tools = [] %}
+{%- endif %}
+{# Recompute last_user_idx relative to loop_messages after handling system #}
+{%- set ns = namespace(last_user_idx = -1) %}
+{%- for m in loop_messages %}
+  {%- if m["role"] == "user" %}
+    {%- set ns.last_user_idx = loop.index0 %}
+  {%- endif %}
+{%- endfor %}
+{%- if system_message is defined %}
+    {{- "<|im_start|>system
+" + system_message }}
+{%- else %}
+    {%- if tools is iterable and tools | length > 0 %}
+        {{- "<|im_start|>system
+" }}
+    {%- endif %}
+{%- endif %}
+{%- if tools is iterable and tools | length > 0 %}
+    {%- if system_message is defined and system_message | length > 0 %}
+        {{- "
+
+" }}
+    {%- endif %}
+    {{- "# Tools
+
+You have access to the following functions:
+
+" }}
+    {{- "<tools>" }}
+    {%- for tool in tools %}
+        {%- if tool.function is defined %}
+            {%- set tool = tool.function %}
+        {%- endif %}
+        {{- "
+<function>
+<name>" ~ tool.name ~ "</name>" }}
+        {%- if tool.description is defined %}
+            {{- '
+<description>' ~ (tool.description | trim) ~ '</description>' }}
+        {%- endif %}
+        {{- '
+<parameters>' }}
+        {%- if tool.parameters is defined and tool.parameters is mapping and tool.parameters.properties is defined and tool.parameters.properties is mapping %}
+            {%- for param_name, param_fields in tool.parameters.properties|items %}
+                {{- '
+<parameter>' }}
+                {{- '
+<name>' ~ param_name ~ '</name>' }}
+                {%- if param_fields.type is defined %}
+                    {{- '
+<type>' ~ (param_fields.type | string) ~ '</type>' }}
+                {%- endif %}
+                {%- if param_fields.description is defined %}
+                    {{- '
+<description>' ~ (param_fields.description | trim) ~ '</description>' }}
+                {%- endif %}
+                {%- if param_fields.enum is defined %}
+                    {{- '
+<enum>' ~ (param_fields.enum | tojson | safe) ~ '</enum>' }}
+                {%- endif %}
+                {%- set handled_keys = ['name', 'type', 'description', 'enum'] %}
+                {{- render_extra_keys(param_fields, handled_keys) }}
+                {{- '
+</parameter>' }}
+            {%- endfor %}
+        {%- endif %}
+        {% set handled_keys = ['type', 'properties', 'required'] %}
+        {{- render_extra_keys(tool.parameters, handled_keys) }}
+        {%- if tool.parameters is defined and tool.parameters.required is defined %}
+            {{- '
+<required>' ~ (tool.parameters.required | tojson | safe) ~ '</required>' }}
+        {%- endif %}
+        {{- '
+</parameters>' }}
+        {%- set handled_keys = ['type', 'name', 'description', 'parameters'] %}
+        {{- render_extra_keys(tool, handled_keys) }}
+        {{- '
+</function>' }}
+    {%- endfor %}
+    {{- "
+</tools>" }}
+
+    {{- '
+
+If you choose to call a function ONLY reply in the following format with NO suffix:
+
+<tool_call>
+<function=example_function_name>
+<parameter=example_parameter_1>
+value_1
+</parameter>
+<parameter=example_parameter_2>
+This is the value for the second parameter
+that can span
+multiple lines
+</parameter>
+</function>
+</tool_call>
+
+<IMPORTANT>
+Reminder:
+- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags
+- Required parameters MUST be specified
+- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after
+- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls
+</IMPORTANT>' }}
+{%- endif %}
+
+
+{%- if system_message is defined %}
+    {{- '<|im_end|>
+' }}
+{%- else %}
+    {%- if tools is iterable and tools | length > 0 %}
+        {{- '<|im_end|>
+' }}
+    {%- endif %}
+{%- endif %}
+
+{%- set image_count = namespace(value=0) %}
+{%- set video_count = namespace(value=0) %}
+{%- for message in loop_messages %}
+    {%- if message.role == "assistant" %}
+        {# Add reasoning content in to content field for unified processing below. #}
+        {%- set text_content = namespace(text_content="") -%}
+        {%- if message.content is string %}
+            {%- set text_content.text_content = message.content %}
+        {%- else %}
+            {%- for content in message.content %}
+                {%- if 'text' in content %}
+                    {%- set text_content.text_content = content.text %}
+                    {%- break %}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {%- if message.reasoning_content is defined and message.reasoning_content is string and message.reasoning_content | trim | length > 0 %}
+            {%- set content = "<think>
+" ~ message.reasoning_content ~ "
+</think>
+" ~ (text_content.text_content | default('', true)) %}
+        {%- else %}
+            {%- set content = text_content.text_content | default('', true) %}
+            {# Allow downstream logic to to take care of broken thought, only handle coherent reasoning here. #}
+            {%- if '<think>' not in content and '</think>' not in content %}
+                {%- set content = "<think></think>" ~ content %}
+            {%- else %}
+                {%- set content = content %}
+            {%- endif -%}
+        {%- endif %}
+        {%- if message.tool_calls is defined and message.tool_calls is iterable and message.tool_calls | length > 0 %}
+            {# Assistant message has tool calls. #}
+            {{- '<|im_start|>assistant
+' }}
+                {%- set include_content = not (truncate_history_thinking and loop.index0 < ns.last_user_idx) %}
+                {%- if content is string and content | trim | length > 0 %}
+                    {%- if include_content %}
+                        {{- (content | trim) ~ '
+' -}}
+                    {%- else %}
+                        {%- set c = (content | string) %}
+                        {%- if '</think>' in c %}
+                            {# Keep only content after the last closing think. Also generation prompt causes this. #}
+                            {%- set c = c.split('</think>')[-1] %}
+                        {%- elif '<think>' in c %}
+                            {# If <think> was opened but never closed, drop the trailing think segment #}
+                            {%- set c = c.split('<think>')[0] %}
+                        {%- endif %}
+                        {%- set c = "<think></think>" ~ c | trim %}
+                        {%- if c | length > 0 %}
+                            {{- c ~ '
+' -}}
+                        {%- endif %}
+                    {%- endif %}
+                {%- else %}
+                    {{- "<think></think>" -}}
+                {%- endif %}
+                {%- for tool_call in message.tool_calls %}
+                    {%- if tool_call.function is defined %}
+                        {%- set tool_call = tool_call.function %}
+                    {%- endif %}
+                    {{- '<tool_call>
+<function=' ~ tool_call.name ~ '>
+' -}}
+                        {%- if tool_call.arguments is defined %}
+                            {%- for args_name, args_value in tool_call.arguments|items %}
+                                {{- '<parameter=' ~ args_name ~ '>
+' -}}
+                                    {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
+                                {{- args_value ~ '
+</parameter>
+' -}}
+                            {%- endfor %}
+                        {%- endif %}
+                    {{- '</function>
+</tool_call>
+' -}}
+                {%- endfor %}
+                {{- '<|im_end|>
+' }}
+        {%- else %}
+            {# Assistant message doesn't have tool calls. #}
+            {%- if not (truncate_history_thinking and loop.index0 < ns.last_user_idx) %}
+                {{- '<|im_start|>assistant
+' ~ (content | default('', true) | string | trim) ~ '<|im_end|>
+' }}
+            {%- else %}
+                {%- set c = (content | default('', true) | string) %}
+                {%- if '<think>' in c and '</think>' in c %}
+                    {%- set c = "<think></think>" ~ c.split('</think>')[-1] %}
+                {%- endif %}
+                {%- set c = c | trim %}
+                {%- if c | length > 0 %}
+                    {{- '<|im_start|>assistant
+' ~ c ~ '<|im_end|>
+' }}
+                {%- else %}
+                    {{- '<|im_start|>assistant
+<|im_end|>
+' }}
+                {%- endif %}
+            {%- endif %}
+        {%- endif %}
+    {%- elif message.role == "user" or message.role == "system" %}
+        {{- '<|im_start|>' + message.role + '
+' }}
+        {%- if message.content is string %}
+            {{- message.content }}
+        {%- 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 %}
+        {%- endif %}
+        {{- '<|im_end|>
+' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.previtem and loop.previtem.role != "tool" %}
+            {{- '<|im_start|>user
+' }}
+        {%- endif %}
+        {{- '<tool_response>
+' }}
+        {{- message.content }}
+        {{- '
+</tool_response>
+' }}
+        {%- if not loop.last and loop.nextitem.role != "tool" %}
+            {{- '<|im_end|>
+' }}
+        {%- elif loop.last %}
+            {{- '<|im_end|>
+' }}
+        {%- endif %}
+    {%- else %}
+        {{- '<|im_start|>' + message.role + '
+' + message.content + '<|im_end|>
+' }}
+    {%- endif %}
+{%- endfor %}
+
+{%- if add_generation_prompt %}
+    {%- if enable_thinking %}
+        {{- '<|im_start|>assistant
+<think>
+' }}
+    {%- else %}
+        {{- '<|im_start|>assistant
+<think></think>' }}
+    {%- endif %}
+{%- endif %}

config.json

@@ -0,0 +1,307 @@
+{
+  "type": "cosmos3",
+  "n_obs_steps": 1,
+  "input_features": {
+    "observation.images.wrist": {
+      "type": "VISUAL",
+      "shape": [
+        3,
+        360,
+        640
+      ]
+    },
+    "observation.images.top": {
+      "type": "VISUAL",
+      "shape": [
+        3,
+        360,
+        640
+      ]
+    },
+    "observation.state": {
+      "type": "STATE",
+      "shape": [
+        6
+      ]
+    }
+  },
+  "output_features": {
+    "action": {
+      "type": "ACTION",
+      "shape": [
+        6
+      ]
+    }
+  },
+  "device": "cpu",
+  "use_amp": false,
+  "use_peft": false,
+  "push_to_hub": true,
+  "repo_id": null,
+  "private": null,
+  "tags": null,
+  "license": null,
+  "pretrained_path": null,
+  "pretrained_revision": null,
+  "text_processor_name_or_path": "/NHNHOME/WORKSPACE/26-AD010033_A/gmkim/xpu-lerobot/checkpoints/Cosmos3-Edge-Policy-SO101-init",
+  "transformer_config": {
+    "action_dim": 64,
+    "action_gen": true,
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "base_fps": 24,
+    "enable_fps_modulation": true,
+    "head_dim": 128,
+    "hidden_act": "relu2",
+    "hidden_size": 2048,
+    "intermediate_size": 9216,
+    "latent_channel": 48,
+    "latent_patch_size": 2,
+    "num_attention_heads": 16,
+    "num_embodiment_domains": 32,
+    "num_hidden_layers": 28,
+    "num_key_value_heads": 8,
+    "patch_latent_dim": 192,
+    "qk_norm_for_text": false,
+    "rms_norm_eps": 1e-05,
+    "rope_axes_dim": [
+      24,
+      20,
+      20
+    ],
+    "rope_scaling": {
+      "mrope_section": [
+        24,
+        20,
+        20
+      ]
+    },
+    "rope_theta": 100000000.0,
+    "sound_dim": null,
+    "sound_gen": false,
+    "sound_latent_fps": 25.0,
+    "timestep_scale": 0.001,
+    "unified_3d_mrope_reset_spatial_ids": true,
+    "unified_3d_mrope_temporal_modality_margin": 15000,
+    "use_und_k_norm_for_gen": true,
+    "vocab_size": 131072
+  },
+  "vae_config": {
+    "attn_scales": [],
+    "base_dim": 160,
+    "decoder_base_dim": 256,
+    "dim_mult": [
+      1,
+      2,
+      4,
+      4
+    ],
+    "dropout": 0.0,
+    "in_channels": 12,
+    "is_residual": true,
+    "latents_mean": [
+      -0.2289,
+      -0.0052,
+      -0.1323,
+      -0.2339,
+      -0.2799,
+      0.0174,
+      0.1838,
+      0.1557,
+      -0.1382,
+      0.0542,
+      0.2813,
+      0.0891,
+      0.157,
+      -0.0098,
+      0.0375,
+      -0.1825,
+      -0.2246,
+      -0.1207,
+      -0.0698,
+      0.5109,
+      0.2665,
+      -0.2108,
+      -0.2158,
+      0.2502,
+      -0.2055,
+      -0.0322,
+      0.1109,
+      0.1567,
+      -0.0729,
+      0.0899,
+      -0.2799,
+      -0.123,
+      -0.0313,
+      -0.1649,
+      0.0117,
+      0.0723,
+      -0.2839,
+      -0.2083,
+      -0.052,
+      0.3748,
+      0.0152,
+      0.1957,
+      0.1433,
+      -0.2944,
+      0.3573,
+      -0.0548,
+      -0.1681,
+      -0.0667
+    ],
+    "latents_std": [
+      0.4765,
+      1.0364,
+      0.4514,
+      1.1677,
+      0.5313,
+      0.499,
+      0.4818,
+      0.5013,
+      0.8158,
+      1.0344,
+      0.5894,
+      1.0901,
+      0.6885,
+      0.6165,
+      0.8454,
+      0.4978,
+      0.5759,
+      0.3523,
+      0.7135,
+      0.6804,
+      0.5833,
+      1.4146,
+      0.8986,
+      0.5659,
+      0.7069,
+      0.5338,
+      0.4889,
+      0.4917,
+      0.4069,
+      0.4999,
+      0.6866,
+      0.4093,
+      0.5709,
+      0.6065,
+      0.6415,
+      0.4944,
+      0.5726,
+      1.2042,
+      0.5458,
+      1.6887,
+      0.3971,
+      1.06,
+      0.3943,
+      0.5537,
+      0.5444,
+      0.4089,
+      0.7468,
+      0.7744
+    ],
+    "num_res_blocks": 2,
+    "out_channels": 12,
+    "patch_size": 2,
+    "scale_factor_spatial": 16,
+    "scale_factor_temporal": 4,
+    "temperal_downsample": [
+      false,
+      true,
+      true
+    ],
+    "z_dim": 48
+  },
+  "scheduler_config": {
+    "_class_name": "UniPCMultistepScheduler",
+    "_diffusers_version": "0.40.0.dev0",
+    "beta_end": 0.02,
+    "beta_schedule": "linear",
+    "beta_start": 0.0001,
+    "disable_corrector": [],
+    "dynamic_thresholding_ratio": 0.995,
+    "final_sigmas_type": "zero",
+    "flow_shift": 5.0,
+    "lower_order_final": true,
+    "num_train_timesteps": 1000,
+    "predict_x0": true,
+    "prediction_type": "flow_prediction",
+    "rescale_betas_zero_snr": false,
+    "sample_max_value": 1.0,
+    "shift_terminal": null,
+    "sigma_max": null,
+    "sigma_min": null,
+    "solver_order": 2,
+    "solver_p": null,
+    "solver_type": "bh2",
+    "steps_offset": 0,
+    "thresholding": false,
+    "time_shift_type": "exponential",
+    "timestep_spacing": "linspace",
+    "trained_betas": null,
+    "use_beta_sigmas": false,
+    "use_dynamic_shifting": false,
+    "use_exponential_sigmas": false,
+    "use_flow_sigmas": true,
+    "use_karras_sigmas": false
+  },
+  "freeze_vae": true,
+  "dtype": "bfloat16",
+  "local_files_only": true,
+  "chunk_size": 32,
+  "n_action_steps": 32,
+  "raw_action_dim": 6,
+  "max_action_dim": 64,
+  "max_state_dim": 6,
+  "joint_position_dim": 5,
+  "gripper_position_dim": 1,
+  "use_state": true,
+  "history_length": 1,
+  "action_space": "joint_pos",
+  "invert_gripper": false,
+  "domain_name": "droid_lerobot",
+  "domain_id": 8,
+  "eos_token_id": 11,
+  "start_of_generation_token_id": 20,
+  "mode": "policy",
+  "viewpoint": "concat_view",
+  "additional_view_description": "The top row is from the wrist-mounted camera. The bottom row contains a third-person top-down view of the scene with the robot visible, and a blank padded view.",
+  "conditioning_fps": 30.0,
+  "resolution_tier": 480,
+  "guidance_scale": 3.0,
+  "num_inference_steps": 4,
+  "shift": 5.0,
+  "seed": 0,
+  "deterministic_seed": false,
+  "generate_video": false,
+  "output_type": "latent",
+  "train_time_video_distribution": "waver",
+  "video_loss_weight": 10.0,
+  "action_loss_weight": 10.0,
+  "normalize_loss_by_active": false,
+  "image_keys": [
+    "observation.images.wrist",
+    "observation.images.top"
+  ],
+  "num_views": 3,
+  "image_height": 360,
+  "image_width": 640,
+  "composed_image_height": 540,
+  "composed_image_width": 640,
+  "prompt_key": "task",
+  "normalization_mapping": {
+    "VISUAL": "IDENTITY",
+    "STATE": "QUANTILES",
+    "ACTION": "QUANTILES"
+  },
+  "optimizer_lr": 1e-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": 0.0
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:232d45077024cc6a256252d8a0d5f7609c8c9897ffb8a87f914bda3b81f335dc
+size 8158233656

policy_postprocessor.json

@@ -0,0 +1,31 @@
+{
+  "name": "policy_postprocessor",
+  "steps": [
+    {
+      "registry_name": "unnormalizer_processor",
+      "config": {
+        "eps": 1e-08,
+        "features": {
+          "action": {
+            "type": "ACTION",
+            "shape": [
+              6
+            ]
+          }
+        },
+        "norm_map": {
+          "VISUAL": "IDENTITY",
+          "STATE": "QUANTILES",
+          "ACTION": "QUANTILES"
+        }
+      }
+    },
+    {
+      "registry_name": "device_processor",
+      "config": {
+        "device": "cpu",
+        "float_dtype": null
+      }
+    }
+  ]
+}

policy_preprocessor.json

@@ -0,0 +1,96 @@
+{
+  "name": "policy_preprocessor",
+  "steps": [
+    {
+      "registry_name": "rename_observations_processor",
+      "config": {
+        "rename_map": {}
+      }
+    },
+    {
+      "registry_name": "to_batch_processor",
+      "config": {}
+    },
+    {
+      "registry_name": "normalizer_processor",
+      "config": {
+        "eps": 1e-08,
+        "features": {
+          "observation.images.wrist": {
+            "type": "VISUAL",
+            "shape": [
+              3,
+              360,
+              640
+            ]
+          },
+          "observation.images.top": {
+            "type": "VISUAL",
+            "shape": [
+              3,
+              360,
+              640
+            ]
+          },
+          "observation.state": {
+            "type": "STATE",
+            "shape": [
+              6
+            ]
+          },
+          "action": {
+            "type": "ACTION",
+            "shape": [
+              6
+            ]
+          }
+        },
+        "norm_map": {
+          "VISUAL": "IDENTITY",
+          "STATE": "QUANTILES",
+          "ACTION": "QUANTILES"
+        }
+      }
+    },
+    {
+      "registry_name": "cosmos3_pack_inputs",
+      "config": {
+        "image_keys": [
+          "observation.images.wrist",
+          "observation.images.top"
+        ],
+        "num_views": 3,
+        "image_height": 360,
+        "chunk_size": 32,
+        "raw_action_dim": 6,
+        "max_action_dim": 64,
+        "max_state_dim": 6,
+        "use_state": true,
+        "history_length": 1,
+        "invert_gripper": false,
+        "domain_id": 8,
+        "conditioning_fps": 30.0,
+        "resolution_tier": 480,
+        "viewpoint": "concat_view",
+        "additional_view_description": "The top row is from the wrist-mounted camera. The bottom row contains a third-person top-down view of the scene with the robot visible, and a blank padded view.",
+        "prompt_key": "task",
+        "composed_image_height": 540,
+        "composed_image_width": 640
+      }
+    },
+    {
+      "registry_name": "cosmos3_qwen_prompt_tokenizer",
+      "config": {
+        "processor_name": "/NHNHOME/WORKSPACE/26-AD010033_A/gmkim/xpu-lerobot/checkpoints/Cosmos3-Edge-Policy-SO101-init",
+        "local_files_only": true
+      }
+    },
+    {
+      "registry_name": "device_processor",
+      "config": {
+        "device": "cpu",
+        "float_dtype": null
+      }
+    }
+  ]
+}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4dc692a99dca6d92a44e9529ffb53541eb79bb260eec7281bc51268c05d7311c
+size 17077500