feat: publish portable Isaac-0.5 artifact

.gitattributes

@@ -39,3 +39,6 @@ isaac_model_card_assets/perception-benchmarks.png filter=lfs diff=lfs merge=lfs
 isaac_model_card_assets/scaling-law-contours.png filter=lfs diff=lfs merge=lfs -text
 isaac_model_card_assets/training-data-plane.png filter=lfs diff=lfs merge=lfs -text
 isaac_model_card_assets/yam-simulation-tasks.png filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text
+policy_normalization.json filter=lfs diff=lfs merge=lfs -text
+policy_inference_recipe.json filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -0,0 +1,3 @@
+# Local runtime caches.
+__pycache__/
+.ruff_cache/

LICENSE

@@ -0,0 +1,202 @@
+
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

README.md

@@ -1,6 +1,7 @@
 ---
 language:
 - en
+license: apache-2.0
 tags:
 - robotics
 - vision-language-model
@@ -8,8 +9,6 @@ tags:
 - embodied-ai
 ---
 
-<!-- Add the final license and pipeline_tag before publication. -->
-
 # Isaac 0.5 by Perceptron
 
 Introducing Isaac 0.5, our open foundation model for robot learning.
@@ -18,13 +17,30 @@ Isaac 0.5 brings multimodal video understanding, embodied reasoning, spatial gro
 
 To our knowledge, Isaac 0.5 is the first open model operating at the frontier of multimodal video understanding, embodied reasoning, and robot control.
 
-**[Read the paper](https://pub-d90b81cad7254a1aa6b148ac18153c0c.r2.dev/isaac-0.5.pdf) · [Download the weights (COMING SOON)](https://huggingface.co/PerceptronAI/Isaac-0.5) · [View the code](https://github.com/perceptron-ai-inc/isaac)**
+**[Read the paper](https://pub-d90b81cad7254a1aa6b148ac18153c0c.r2.dev/isaac-0.5.pdf) · [Download the weights](https://huggingface.co/PerceptronAI/Isaac-0.5) · [View the code](https://github.com/perceptron-ai-inc/isaac)**
+
+## Using this checkpoint
+
+This checkpoint is consumed through the [Perceptron Isaac repository](https://github.com/perceptron-ai-inc/isaac). Direct Transformers and stock LeRobot usage are not currently supported. It is compatible with [Perceptron Isaac commit `be6507b`](https://github.com/perceptron-ai-inc/isaac/commit/be6507b4aed7472f2029606c22684d4ebc9d73e6).
+
+```bash
+git clone https://github.com/perceptron-ai-inc/isaac.git
+cd isaac
+git checkout be6507b4aed7472f2029606c22684d4ebc9d73e6
+git submodule update --init --recursive
+git -C lerobot fetch origin main
+git -C lerobot checkout e12389c1f8f591ad05dced4e284d4e92e48c5df4
+cd lerobot
+uv sync --locked --extra perceptron_isaac
+```
+
+The pinned repository lockfile defines the supported runtime versions.
 
 ## Extending the frontier of open robot learning
 
 Isaac 0.5 is trained on more than 35 robot systems, 100,000 hours of robot experience, one million hours of general video, and three trillion multimodal tokens. Video understanding, spatial grounding, task progress, future-percept prediction, and robot action are co-trained from the beginning on one shared backbone.
 
-Teams can fine-tune Isaac as a robot policy or use its visual outputs inside a planner, controller, or data engine. The release includes base and action checkpoints, action-training and inference code, LeRobot integration, a reference policy server, evaluation tools, and the manifests needed to reproduce the model's data and checkpoint interfaces.
+Teams can fine-tune Isaac as a robot policy or use its visual outputs inside a planner, controller, or data engine. This model repository provides checkpoint weights and portable runtime manifests. The companion [Perceptron Isaac repository](https://github.com/perceptron-ai-inc/isaac) provides action-training and inference code, LeRobot integration, a reference policy server, evaluation tools, and reproduction guides.
 
 ## What's new in Isaac 0.5
 
@@ -33,7 +49,7 @@ Teams can fine-tune Isaac as a robot policy or use its visual outputs inside a p
 - **Unified perception, reasoning, and control:** One shared sparse backbone supports video understanding, pointing, tracking, task-state estimation, and robot action generation.
 - **Continuous and discrete action interfaces:** Isaac supports continuous control through a dedicated Flow expert and diffusion transformer, plus discrete control through a 2,048-token FAST action vocabulary.
 - **Real-time closed-loop control:** Isaac predicts the next action chunk while the current chunk is still executing, using the latest observation and previously issued commands.
-- **Open training and deployment stack:** The release includes model weights, training code, inference code, LeRobot integration, a reference policy server, evaluation code, and reproduction manifests.
+- **Open training and deployment stack:** This model repository publishes checkpoint weights and portable manifests; the companion [Perceptron Isaac repository](https://github.com/perceptron-ai-inc/isaac) provides training, inference, LeRobot integration, the reference policy server, and evaluation code.
 
 ## A scaling law for video and robot experience
 
@@ -101,23 +117,27 @@ We evaluate the same Isaac checkpoints across multimodal video understanding, sp
 
 Isaac 0.5 can be fine-tuned on new demonstrations, used as a visual backbone inside a larger embodied system, or deployed as an action policy through LeRobot or our reference server.
 
-The release includes:
+This model repository provides:
 
-- base and action-capable weights;
+- checkpoint weights;
 - continuous Flow and discrete FAST action configurations;
-- action training and fine-tuning code;
 - text, pointing, tracking, and task-state output schemas;
+- checkpoint, data, and model-I/O manifests;
+- the technical report and model card.
+
+The companion [Perceptron Isaac repository](https://github.com/perceptron-ai-inc/isaac) provides:
+
+- action training, fine-tuning, and inference code;
 - LeRobot integration and a reference policy server;
 - evaluation code, task definitions, and rollout manifests;
-- checkpoint, data, and model-I/O manifests;
-- the technical report, model card, and reproduction guide.
+- reproduction and deployment guides.
 
 ## Resources
 
-- **Weights (COMING SOON):** [Hugging Face](https://huggingface.co/PerceptronAI/Isaac-0.5)
+- **Weights:** [Hugging Face](https://huggingface.co/PerceptronAI/Isaac-0.5)
 - **Code:** [GitHub](https://github.com/perceptron-ai-inc/isaac)
 - **Technical report:** [Read the paper](https://pub-d90b81cad7254a1aa6b148ac18153c0c.r2.dev/isaac-0.5.pdf)
 
-Open models are essential to robotics progress. We are releasing Isaac 0.5 with its weights, code, interfaces, benchmarks, and manifests so others can inspect, reproduce, and extend the work.
+Open models are essential to robotics progress. The weights and portable manifests are published here; code, interfaces, evaluation tools, and deployment guides are maintained in the companion [Perceptron Isaac repository](https://github.com/perceptron-ai-inc/isaac).
 
 For help deploying Isaac on your infrastructure, contact [sales@perceptron.inc](mailto:sales@perceptron.inc).

chat_template.jinja

@@ -0,0 +1,154 @@
+{%- set image_count = namespace(value=0) %}
+{%- set video_count = namespace(value=0) %}
+{%- macro render_content(content, do_vision_count, is_system_content=false) %}
+    {%- if content is string %}
+        {{- content }}
+    {%- elif content is iterable and content is not mapping %}
+        {%- for item in content %}
+            {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
+                {%- if is_system_content %}
+                    {{- raise_exception('System message cannot contain images.') }}
+                {%- endif %}
+                {%- if do_vision_count %}
+                    {%- set image_count.value = image_count.value + 1 %}
+                {%- endif %}
+                {%- if add_vision_id %}
+                    {{- 'Picture ' ~ image_count.value ~ ': ' }}
+                {%- endif %}
+                {{- '<|vision_start|><|image_pad|><|vision_end|>' }}
+            {%- elif 'video' in item or item.type == 'video' %}
+                {%- if is_system_content %}
+                    {{- raise_exception('System message cannot contain videos.') }}
+                {%- endif %}
+                {%- if do_vision_count %}
+                    {%- set video_count.value = video_count.value + 1 %}
+                {%- endif %}
+                {%- if add_vision_id %}
+                    {{- 'Video ' ~ video_count.value ~ ': ' }}
+                {%- endif %}
+                {{- '<|vision_start|><|video_pad|><|vision_end|>' }}
+            {%- elif 'text' in item %}
+                {{- item.text }}
+            {%- else %}
+                {{- raise_exception('Unexpected item type in content.') }}
+            {%- endif %}
+        {%- endfor %}
+    {%- elif content is none or content is undefined %}
+        {{- '' }}
+    {%- else %}
+        {{- raise_exception('Unexpected content type.') }}
+    {%- endif %}
+{%- endmacro %}
+{%- if not messages %}
+    {{- raise_exception('No messages provided.') }}
+{%- endif %}
+{%- if tools and tools is iterable and tools is not mapping %}
+    {{- '<|im_start|>system\n' }}
+    {{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>" }}
+    {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- 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\n</IMPORTANT>' }}
+    {%- if messages[0].role == 'system' %}
+        {%- set content = render_content(messages[0].content, false, true)|trim %}
+        {%- if content %}
+            {{- '\n\n' + content }}
+        {%- endif %}
+    {%- endif %}
+    {{- '<|im_end|>\n' }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {%- set content = render_content(messages[0].content, false, true)|trim %}
+        {{- '<|im_start|>system\n' + content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" %}
+        {%- set content = render_content(message.content, false)|trim %}
+        {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
+            {%- set ns.multi_step_tool = false %}
+            {%- set ns.last_query_index = index %}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if ns.multi_step_tool %}
+    {{- raise_exception('No user query found in messages.') }}
+{%- endif %}
+{%- for message in messages %}
+    {%- set content = render_content(message.content, true)|trim %}
+    {%- if message.role == "system" %}
+        {%- if not loop.first %}
+            {{- raise_exception('System message must be at the beginning.') }}
+        {%- endif %}
+    {%- elif message.role == "user" %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- set reasoning_content = reasoning_content|trim %}
+        {%- if (preserve_thinking is defined and preserve_thinking is true) or (loop.index0 > ns.last_query_index) %}
+            {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if tool_call.function is defined %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {%- if loop.first %}
+                    {%- if content|trim %}
+                        {{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                    {%- else %}
+                        {{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                    {%- endif %}
+                {%- else %}
+                    {{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                {%- endif %}
+                {%- if tool_call.arguments is defined %}
+                    {%- for args_name, args_value in tool_call.arguments|items %}
+                        {{- '<parameter=' + args_name + '>\n' }}
+                        {%- set args_value = args_value | string if args_value is string else args_value | tojson | safe %}
+                        {{- args_value }}
+                        {{- '\n</parameter>\n' }}
+                    {%- endfor %}
+                {%- endif %}
+                {{- '</function>\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.previtem and loop.previtem.role != "tool" %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if not loop.last and loop.nextitem.role != "tool" %}
+            {{- '<|im_end|>\n' }}
+        {%- elif loop.last %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- else %}
+        {{- raise_exception('Unexpected message role.') }}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- else %}
+        {{- '<think>\n' }}
+    {%- endif %}
+{%- endif %}

config.json

@@ -0,0 +1,313 @@
+{
+  "_name_or_path": "",
+  "action_expert": {
+    "action_dim": 64,
+    "action_horizon": 64,
+    "causal_attn": false,
+    "context_layer_norm": true,
+    "drop_action_dim_overflow": false,
+    "ffn_multiple_of": 256,
+    "hidden_dim": 768,
+    "k_batched_cross_attn": true,
+    "k_batched_cross_attn_backend": "flash_gqa",
+    "mask_padded_action_rows": true,
+    "mlp_ratio": 4.0,
+    "num_heads": 8,
+    "num_inference_steps": 10,
+    "num_layers": 36,
+    "qk_norm": true,
+    "qk_norm_eps": 1e-06,
+    "rope": true,
+    "rtc_delay_sampling": "poisson",
+    "rtc_max_delay_steps": 12,
+    "rtc_poisson_mean": 5.0,
+    "rtc_probability": 0.5,
+    "schema_version": 1,
+    "timestep_embed_dim": 256,
+    "timestep_sampling_alpha": 1.5,
+    "timestep_sampling_beta": 1.0,
+    "timestep_sampling_offset": 0.001,
+    "timestep_sampling_scale": 0.999,
+    "train_samples_per_chunk": 8,
+    "type": "dit"
+  },
+  "architectures": [
+    "Isaac05ForConditionalGeneration"
+  ],
+  "auto_map": {
+    "AutoConfig": "configuration_isaac05.Isaac05Config",
+    "AutoModelForCausalLM": "modeling_isaac05.Isaac05ForConditionalGeneration",
+    "AutoProcessor": "processing_isaac05.Isaac05Processor"
+  },
+  "chunk_size_feed_forward": 0,
+  "dtype": "bfloat16",
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1"
+  },
+  "image_token_id": 248056,
+  "is_encoder_decoder": false,
+  "isaac05_artifact": {
+    "artifact_kind": "trained_policy",
+    "schema_version": 1,
+    "tensor_bytes": 142894027456,
+    "tensor_count": 1616
+  },
+  "isaac05_coord_tokens": {
+    "enabled": true,
+    "offset": 248320,
+    "size": 1001
+  },
+  "isaac05_fast_tokens": {
+    "enabled": true,
+    "offset": 249321,
+    "size": 2048,
+    "tokenizer": "physical-intelligence/fast"
+  },
+  "isaac05_moe": {
+    "logical_router_outputs": 512,
+    "num_null_experts": 256,
+    "num_real_experts": 256,
+    "physical_router_outputs": 257,
+    "route_norm": true,
+    "route_scale": 1.0,
+    "router_contract": [
+      256,
+      256
+    ],
+    "router_contract_version": 1,
+    "score_before_experts": false,
+    "score_func": "softmax",
+    "shared_null_router_row": true,
+    "top_k": 8,
+    "uses_expert_bias": false
+  },
+  "isaac05_test_only_reduced_geometry": false,
+  "isaac05_vla": {
+    "action_expert": {
+      "action_dim": 64,
+      "action_horizon": 64,
+      "causal_attn": false,
+      "context_layer_norm": true,
+      "drop_action_dim_overflow": false,
+      "ffn_multiple_of": 256,
+      "hidden_dim": 768,
+      "k_batched_cross_attn": true,
+      "k_batched_cross_attn_backend": "flash_gqa",
+      "mask_padded_action_rows": true,
+      "mlp_ratio": 4.0,
+      "num_heads": 8,
+      "num_inference_steps": 10,
+      "num_layers": 36,
+      "qk_norm": true,
+      "qk_norm_eps": 1e-06,
+      "rope": true,
+      "rtc_delay_sampling": "poisson",
+      "rtc_max_delay_steps": 12,
+      "rtc_poisson_mean": 5.0,
+      "rtc_probability": 0.5,
+      "schema_version": 1,
+      "timestep_embed_dim": 256,
+      "timestep_sampling_alpha": 1.5,
+      "timestep_sampling_beta": 1.0,
+      "timestep_sampling_offset": 0.001,
+      "timestep_sampling_scale": 0.999,
+      "train_samples_per_chunk": 8,
+      "type": "dit"
+    },
+    "mtp": {
+      "action_runtime": "exclude",
+      "physical_layers": 0,
+      "present": false,
+      "rollout_steps": 0
+    },
+    "rmsnorm_weight_convention": "zero_centered_1_plus_weight",
+    "schema_version": 1,
+    "state_dict_schema": "pr3154_v1",
+    "vector_encoder": {
+      "bias": false,
+      "hidden_dim": 2048,
+      "max_states": 128,
+      "output_dim": 2048,
+      "type": "linear_silu_linear"
+    }
+  },
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1
+  },
+  "max_sequence_length": 262144,
+  "model_type": "isaac_0_5",
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "problem_type": null,
+  "return_dict": true,
+  "runtime_dtype": "bfloat16",
+  "storage_dtype": "float32",
+  "text_config": {
+    "_name_or_path": "",
+    "architectures": null,
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "attn_output_gate": true,
+    "bos_token_id": 248044,
+    "chunk_size_feed_forward": 0,
+    "dtype": "bfloat16",
+    "eos_token_id": 248044,
+    "full_attention_interval": 4,
+    "head_dim": 256,
+    "hidden_act": "silu",
+    "hidden_size": 2048,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
+    "is_encoder_decoder": false,
+    "isaac05_moe": {
+      "logical_router_outputs": 512,
+      "num_null_experts": 256,
+      "num_real_experts": 256,
+      "physical_router_outputs": 257,
+      "route_norm": true,
+      "route_scale": 1.0,
+      "router_contract": [
+        256,
+        256
+      ],
+      "router_contract_version": 1,
+      "score_before_experts": false,
+      "score_func": "softmax",
+      "shared_null_router_row": true,
+      "top_k": 8,
+      "uses_expert_bias": false
+    },
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_types": [
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention"
+    ],
+    "linear_conv_kernel_dim": 4,
+    "linear_key_head_dim": 128,
+    "linear_num_key_heads": 16,
+    "linear_num_value_heads": 32,
+    "linear_value_head_dim": 128,
+    "mamba_ssm_dtype": "float32",
+    "max_position_embeddings": 262144,
+    "model_type": "qwen3_5_moe_text",
+    "moe_intermediate_size": 512,
+    "mtp_num_hidden_layers": 0,
+    "mtp_use_dedicated_embeddings": false,
+    "num_attention_heads": 16,
+    "num_experts": 256,
+    "num_experts_per_tok": 8,
+    "num_hidden_layers": 40,
+    "num_key_value_heads": 2,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_router_logits": false,
+    "pad_token_id": null,
+    "partial_rotary_factor": 0.25,
+    "problem_type": null,
+    "return_dict": true,
+    "rms_norm_eps": 1e-06,
+    "rope_parameters": {
+      "mrope_interleaved": true,
+      "mrope_section": [
+        11,
+        11,
+        10
+      ],
+      "partial_rotary_factor": 0.25,
+      "rope_theta": 10000000,
+      "rope_type": "default"
+    },
+    "router_aux_loss_coef": 0.001,
+    "shared_expert_intermediate_size": 512,
+    "tie_word_embeddings": false,
+    "use_cache": true,
+    "vocab_size": 256279
+  },
+  "tie_word_embeddings": false,
+  "transformers_version": "5.5.4",
+  "vector_max_states": 128,
+  "video_token_id": 248057,
+  "vision_config": {
+    "_name_or_path": "",
+    "architectures": null,
+    "chunk_size_feed_forward": 0,
+    "deepstack_visual_indexes": [],
+    "depth": 27,
+    "dtype": null,
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 1152,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "in_channels": 3,
+    "initializer_range": 0.02,
+    "intermediate_size": 4304,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "model_type": "qwen3_5_moe",
+    "num_heads": 16,
+    "num_position_embeddings": 2304,
+    "out_hidden_size": 2048,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "patch_size": 16,
+    "problem_type": null,
+    "return_dict": true,
+    "spatial_merge_size": 2,
+    "temporal_patch_size": 2
+  },
+  "vision_end_token_id": 248054,
+  "vision_rescale_factor": 0.00392156862745098,
+  "vision_start_token_id": 248053,
+  "vision_token": "<|image_pad|>"
+}

configuration_isaac05.py

@@ -0,0 +1,188 @@
+"""Transformers configuration for the portable Isaac-0.5 VLA repository."""
+
+from __future__ import annotations
+
+import copy
+from collections.abc import Mapping
+from typing import Any
+
+from transformers import Qwen3_5MoeConfig
+
+_ISAAC05_ARCHITECTURES = ["Isaac05ForConditionalGeneration"]
+_ISAAC05_AUTO_MAP = {
+    "AutoConfig": "configuration_isaac05.Isaac05Config",
+    "AutoModelForCausalLM": "modeling_isaac05.Isaac05ForConditionalGeneration",
+    "AutoProcessor": "processing_isaac05.Isaac05Processor",
+}
+_PRODUCTION_COORD_TOKENS = {"enabled": True, "offset": 248_320, "size": 1_001}
+_PRODUCTION_FAST_TOKENS = {
+    "enabled": True,
+    "tokenizer": "physical-intelligence/fast",
+    "offset": 249_321,
+    "size": 2_048,
+}
+_PRODUCTION_ARTIFACT = {
+    "schema_version": 1,
+    "artifact_kind": "trained_policy",
+    "tensor_count": 1_616,
+    "tensor_bytes": 142_894_027_456,
+}
+_PRODUCTION_VECTOR_ENCODER = {
+    "type": "linear_silu_linear",
+    "max_states": 128,
+    "hidden_dim": 2_048,
+    "output_dim": 2_048,
+    "bias": False,
+}
+_PRODUCTION_ACTION_EXPERT = {
+    "action_dim": 64,
+    "action_horizon": 64,
+    "num_layers": 36,
+    "hidden_dim": 768,
+    "num_heads": 8,
+    "mlp_ratio": 4.0,
+    "num_inference_steps": 10,
+    "timestep_sampling_alpha": 1.5,
+    "timestep_sampling_beta": 1.0,
+    "timestep_sampling_scale": 0.999,
+    "timestep_sampling_offset": 0.001,
+    "train_samples_per_chunk": 8,
+    "timestep_embed_dim": 256,
+    "rtc_max_delay_steps": 12,
+    "rtc_probability": 0.5,
+    "rtc_delay_sampling": "poisson",
+    "rtc_poisson_mean": 5.0,
+    "mask_padded_action_rows": True,
+    "drop_action_dim_overflow": False,
+    "ffn_multiple_of": 256,
+    "qk_norm": True,
+    "qk_norm_eps": 1e-6,
+    "rope": True,
+    "context_layer_norm": True,
+    "causal_attn": False,
+    "k_batched_cross_attn": True,
+    "k_batched_cross_attn_backend": "flash_gqa",
+    "schema_version": 1,
+    "type": "dit",
+}
+_PRODUCTION_MTP = {
+    "present": False,
+    "physical_layers": 0,
+    "rollout_steps": 0,
+    "action_runtime": "exclude",
+}
+
+
+def _copy_mapping(value: Mapping[str, Any] | None, *, name: str) -> dict[str, Any]:
+    if not isinstance(value, Mapping):
+        raise ValueError(f"Isaac05Config {name} must be a JSON object.")
+    return copy.deepcopy(dict(value))
+
+
+def _require_exact(value: Mapping[str, Any], expected: Mapping[str, Any], *, name: str) -> None:
+    if dict(value) != dict(expected):
+        raise ValueError(f"Isaac05Config {name} does not match the portable artifact contract.")
+
+
+def _reserved_token_range(value: Mapping[str, Any], *, name: str) -> range:
+    if value.get("enabled") is not True:
+        raise ValueError(f"Isaac05Config {name}.enabled must be true.")
+    offset = value.get("offset")
+    size = value.get("size")
+    if not isinstance(offset, int) or isinstance(offset, bool) or offset < 0:
+        raise ValueError(f"Isaac05Config {name}.offset must be a non-negative integer.")
+    if not isinstance(size, int) or isinstance(size, bool) or size <= 0:
+        raise ValueError(f"Isaac05Config {name}.size must be a positive integer.")
+    return range(offset, offset + size)
+
+
+class Isaac05Config(Qwen3_5MoeConfig):
+    """Portable Isaac-0.5 configuration for the published checkpoint."""
+
+    model_type = "isaac_0_5"
+    has_no_defaults_at_init = True
+
+    def __init__(
+        self,
+        *,
+        isaac05_artifact: Mapping[str, Any] | None = None,
+        isaac05_coord_tokens: Mapping[str, Any] | None = None,
+        isaac05_fast_tokens: Mapping[str, Any] | None = None,
+        isaac05_vla: Mapping[str, Any] | None = None,
+        storage_dtype: str = "float32",
+        runtime_dtype: str = "bfloat16",
+        max_sequence_length: int = 262_144,
+        vision_token: str = "<|image_pad|>",
+        vision_rescale_factor: float = 1 / 255,
+        isaac05_test_only_reduced_geometry: bool = False,
+        **kwargs: Any,
+    ) -> None:
+        architectures = kwargs.pop("architectures", _ISAAC05_ARCHITECTURES)
+        auto_map = kwargs.pop("auto_map", _ISAAC05_AUTO_MAP)
+        if architectures != _ISAAC05_ARCHITECTURES:
+            raise ValueError(f"Isaac05Config architectures must be {_ISAAC05_ARCHITECTURES!r}.")
+        if auto_map != _ISAAC05_AUTO_MAP:
+            raise ValueError("Isaac05Config auto_map does not match the portable repository API.")
+
+        artifact = _copy_mapping(isaac05_artifact, name="isaac05_artifact")
+        coord_tokens = _copy_mapping(isaac05_coord_tokens, name="isaac05_coord_tokens")
+        fast_tokens = _copy_mapping(isaac05_fast_tokens, name="isaac05_fast_tokens")
+        vla = _copy_mapping(isaac05_vla, name="isaac05_vla")
+
+        if storage_dtype != "float32":
+            raise ValueError("Isaac05Config storage_dtype must be 'float32'.")
+        if runtime_dtype != "bfloat16":
+            raise ValueError("Isaac05Config runtime_dtype must be 'bfloat16'.")
+        if max_sequence_length <= 0:
+            raise ValueError("Isaac05Config max_sequence_length must be positive.")
+        if not vision_token:
+            raise ValueError("Isaac05Config vision_token must not be empty.")
+        if vision_rescale_factor <= 0:
+            raise ValueError("Isaac05Config vision_rescale_factor must be positive.")
+        coord_range = _reserved_token_range(coord_tokens, name="isaac05_coord_tokens")
+        fast_range = _reserved_token_range(fast_tokens, name="isaac05_fast_tokens")
+        if coord_range.start < fast_range.stop and fast_range.start < coord_range.stop:
+            raise ValueError("Isaac05Config reserved token ranges overlap.")
+        if not isaac05_test_only_reduced_geometry:
+            _require_exact(artifact, _PRODUCTION_ARTIFACT, name="isaac05_artifact")
+            _require_exact(coord_tokens, _PRODUCTION_COORD_TOKENS, name="isaac05_coord_tokens")
+            _require_exact(fast_tokens, _PRODUCTION_FAST_TOKENS, name="isaac05_fast_tokens")
+            _require_exact(
+                _copy_mapping(vla.get("vector_encoder"), name="isaac05_vla.vector_encoder"),
+                _PRODUCTION_VECTOR_ENCODER,
+                name="isaac05_vla.vector_encoder",
+            )
+            _require_exact(
+                _copy_mapping(vla.get("action_expert"), name="isaac05_vla.action_expert"),
+                _PRODUCTION_ACTION_EXPERT,
+                name="isaac05_vla.action_expert",
+            )
+        _require_exact(
+            _copy_mapping(vla.get("mtp"), name="isaac05_vla.mtp"),
+            _PRODUCTION_MTP,
+            name="isaac05_vla.mtp",
+        )
+        if vla.get("schema_version") != 1:
+            raise ValueError("Isaac05Config isaac05_vla.schema_version must be 1.")
+        if vla.get("state_dict_schema") != "pr3154_v1":
+            raise ValueError("Isaac05Config isaac05_vla.state_dict_schema must be 'pr3154_v1'.")
+        if vla.get("rmsnorm_weight_convention") != "zero_centered_1_plus_weight":
+            raise ValueError(
+                "Isaac05Config isaac05_vla.rmsnorm_weight_convention must be 'zero_centered_1_plus_weight'."
+            )
+
+        super().__init__(architectures=architectures, auto_map=auto_map, **kwargs)
+        self.isaac05_artifact = artifact
+        self.isaac05_coord_tokens = coord_tokens
+        self.isaac05_fast_tokens = fast_tokens
+        self.isaac05_vla = vla
+        vector_encoder = _copy_mapping(vla.get("vector_encoder"), name="isaac05_vla.vector_encoder")
+        action_expert = _copy_mapping(vla.get("action_expert"), name="isaac05_vla.action_expert")
+        self.vector_max_states = int(vector_encoder["max_states"])
+        self.action_expert = action_expert
+        self.storage_dtype = storage_dtype
+        self.runtime_dtype = runtime_dtype
+        self.max_sequence_length = int(max_sequence_length)
+        self.vision_token = vision_token
+        self.vision_rescale_factor = float(vision_rescale_factor)
+        self.isaac05_test_only_reduced_geometry = bool(isaac05_test_only_reduced_geometry)

fast_processor_pinned/processing_action_tokenizer.py

@@ -0,0 +1,158 @@
+import logging
+from typing import ClassVar
+
+import numpy as np
+from scipy.fft import dct
+from scipy.fft import idct
+from tokenizers import ByteLevelBPETokenizer
+from tokenizers.trainers import BpeTrainer
+from transformers import PreTrainedTokenizerFast
+from transformers.processing_utils import ProcessorMixin
+
+
+class UniversalActionProcessor(ProcessorMixin):
+    attributes: ClassVar[list[str]] = ["bpe_tokenizer"]
+    bpe_tokenizer_class: str = "AutoTokenizer"
+
+    def __init__(
+        self,
+        bpe_tokenizer: PreTrainedTokenizerFast,
+        scale: float = 10,
+        vocab_size: int = 1024,
+        min_token: int = 0,
+        *,
+        action_dim: int | None = None,
+        time_horizon: int | None = None,
+    ):
+        self.scale = scale
+        self.vocab_size = vocab_size
+        self.min_token = min_token
+
+        # Action horizon and dimension needed during decoding. These can be specified
+        # in three ways (in order of priority):
+        # 1. passed in as kwargs to decode()
+        # 2. in the constructor
+        # 3. cached from the last time decode() was called
+        self.time_horizon = time_horizon
+        self.action_dim = action_dim
+        self.called_time_horizon = time_horizon
+        self.called_action_dim = action_dim
+
+        super().__init__(bpe_tokenizer)
+
+    def __call__(self, action_chunk: np.array) -> np.array:
+        assert action_chunk.ndim <= 3, "Only 3 dimensions supported: [batch, timesteps, action_dim]"
+        if action_chunk.ndim == 2:
+            action_chunk = action_chunk[None, ...]
+
+        # Cache the time horizon and action dimension for decoding
+        self.called_time_horizon = action_chunk.shape[-2]
+        self.called_action_dim = action_chunk.shape[-1]
+
+        dct_coeff = dct(action_chunk, axis=1, norm="ortho")
+        dct_coeff = np.around(dct_coeff * self.scale)
+        tokens = []
+        for elem in dct_coeff:
+            token_str = "".join(map(chr, np.maximum(elem.flatten() - self.min_token, 0).astype(int)))
+            tokens.append(self.bpe_tokenizer(token_str)["input_ids"])
+        return tokens
+
+    def decode(
+        self,
+        tokens: list[list[int]],
+        *,
+        time_horizon: int | None = None,
+        action_dim: int | None = None,
+    ) -> np.array:
+        self.time_horizon = time_horizon or self.time_horizon or self.called_time_horizon
+        self.action_dim = action_dim or self.action_dim or self.called_action_dim
+
+        # Cache the time horizon and action dimension for the next call
+        self.called_time_horizon = self.time_horizon
+        self.called_action_dim = self.action_dim
+
+        assert (
+            self.time_horizon is not None and self.action_dim is not None
+        ), "Tokenizer not initialized, call encode() once or pass in time_horizon and action_dim."
+
+        decoded_actions = []
+        for token in tokens:
+            try:
+                decoded_tokens = self.bpe_tokenizer.decode(token)
+                decoded_dct_coeff = np.array(list(map(ord, decoded_tokens))) + self.min_token
+                decoded_dct_coeff = decoded_dct_coeff.reshape(-1, self.action_dim)
+                assert (
+                    decoded_dct_coeff.shape
+                    == (
+                        self.time_horizon,
+                        self.action_dim,
+                    )
+                ), f"Decoded DCT coefficients have shape {decoded_dct_coeff.shape}, expected ({self.time_horizon}, {self.action_dim})"
+            except Exception as e:
+                print(f"Error decoding tokens: {e}")
+                print(f"Tokens: {token}")
+                decoded_dct_coeff = np.zeros((self.time_horizon, self.action_dim))
+            decoded_actions.append(idct(decoded_dct_coeff / self.scale, axis=0, norm="ortho"))
+        return np.stack(decoded_actions)
+
+    @classmethod
+    def fit(
+        cls,
+        action_data: list[np.array],
+        scale: float = 10,
+        vocab_size: int = 1024,
+        *,
+        time_horizon: int | None = None,
+        action_dim: int | None = None,
+    ) -> "UniversalActionProcessor":
+        # Run DCT over all inputs
+        dct_tokens = [dct(a, axis=0, norm="ortho").flatten() for a in action_data]
+
+        # Quantize and find min token
+        max_token = int(np.around(np.concatenate(dct_tokens) * scale).max())
+        min_token = int(np.around(np.concatenate(dct_tokens) * scale).min())
+        min_vocab_size = max_token - min_token
+
+        assert (
+            min_vocab_size <= vocab_size
+        ), f"Vocab size {vocab_size} is too small for the range of tokens {min_vocab_size}"
+        if min_vocab_size + 100 > vocab_size:
+            logging.warning(
+                f"Initial alphabet size {min_vocab_size} is almost as large as the vocab"
+                f"size {vocab_size}, consider increasing vocab size"
+            )
+
+        # Make token iterator for BPE training
+        def _token_iter():
+            for tokens in dct_tokens:
+                rounded_tokens = np.around(tokens * scale) - min_token
+                rounded_tokens = rounded_tokens.astype(int)
+                string = "".join(map(chr, rounded_tokens))
+                yield string
+
+        # Train BPE tokenizer
+        bpe = ByteLevelBPETokenizer()
+
+        # Set up the entire range of possible tokens as the initial alphabet
+        alphabet = [chr(i) for i in range(max_token - min_token + 1)]
+        trainer = BpeTrainer(
+            vocab_size=vocab_size,
+            min_frequency=2,
+            show_progress=True,
+            special_tokens=[],
+            initial_alphabet=alphabet,
+            max_token_length=10000,
+        )
+
+        # Train the inner tokenizer (don't use ByteLevelBPETokenizer.train_from_iterator()
+        # because it doesn't support custom alphabets)
+        bpe._tokenizer.train_from_iterator(_token_iter(), trainer=trainer)
+
+        return cls(
+            PreTrainedTokenizerFast(tokenizer_object=bpe, clean_up_tokenization_spaces=False),
+            scale=scale,
+            vocab_size=vocab_size,
+            min_token=min_token,
+            time_horizon=time_horizon,
+            action_dim=action_dim,
+        )

fast_processor_pinned/processor_config.json

@@ -0,0 +1,11 @@
+{
+  "action_dim": null,
+  "auto_map": {
+    "AutoProcessor": "processing_action_tokenizer.UniversalActionProcessor"
+  },
+  "min_token": -354,
+  "processor_class": "UniversalActionProcessor",
+  "scale": 10,
+  "time_horizon": null,
+  "vocab_size": 2048
+}

fast_processor_pinned/special_tokens_map.json

@@ -0,0 +1 @@
+{}

fast_processor_pinned/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6507dd709287fd018882120c0071787f1f62bad9f180f1e8c5235bda1b71fa78
+size 686974

fast_processor_pinned/tokenizer_config.json

@@ -0,0 +1,10 @@
+{
+  "added_tokens_decoder": {},
+  "auto_map": {
+    "AutoProcessor": "processing_action_tokenizer.UniversalActionProcessor"
+  },
+  "clean_up_tokenization_spaces": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "processor_class": "UniversalActionProcessor",
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}

isaac_deployment_adapter.json

@@ -0,0 +1,47 @@
+{
+  "schema": "perceptron_isaac_deployment_adapter_v1",
+  "contract_sha256": {
+    "policy_state_contracts.json": "8f83eb9eff2defdef07a2e297b401de475668063e27c3eb5d80963ddb67f1a5e",
+    "policy_normalization.json": "f829a6f6f72be41196820a1591fb8e7047d9ab674f77a0bec1ba53713ac0c1dc",
+    "policy_inference_recipe.json": "85e5f52d50a3c89b6ff3adc594189bde3e1d345fbecc7bda082561308b3ee905"
+  },
+  "policy_state_dataset": "libero",
+  "normalization_scope": "libero_spatial",
+  "objective": "Flow",
+  "render_dataset_name": "libero",
+  "robot_type": "libero",
+  "control_mode": "ee",
+  "image_size": [
+    256,
+    256
+  ],
+  "camera_order": [
+    "image",
+    "wrist_image"
+  ],
+  "camera_views": [
+    "primary",
+    "wrist"
+  ],
+  "n_action_steps": 8,
+  "num_inference_steps": 10,
+  "num_flow_samples": 1,
+  "flow_seed_base": 20260826,
+  "clip_action_pose": true,
+  "gripper_binary_to_signed": false,
+  "num_settle_steps": 40,
+  "settle_gripper": -1.0,
+  "normalize_task_text": true,
+  "joint_signs": null,
+  "joint_offsets": null,
+  "normalization_profile_id": null,
+  "normalization_profile_scope": null,
+  "normalization_validation_status": null,
+  "adapter_validation_status": "reviewed_offline",
+  "provenance": {
+    "checkpoint": "PerceptronAI/Isaac-0.5",
+    "purpose": "LIBERO Spatial Flow reference deployment profile",
+    "profile_source": "LeRobot tested LIBERO deployment profile",
+    "selected_by": "user"
+  }
+}

isaac_stats.json

@@ -0,0 +1,60 @@
+{
+  "action": {
+    "q01": [
+      -0.7454732060432434,
+      -0.6616071462631226,
+      -0.9375,
+      -0.1071428582072258,
+      -0.20678570866584778,
+      -0.1842857152223587,
+      -1.0
+    ],
+    "q99": [
+      0.9375,
+      0.8758928775787354,
+      0.9321428537368774,
+      0.1039285734295845,
+      0.17678570747375488,
+      0.14571428298950195,
+      1.0
+    ]
+  },
+  "action_dim": 7,
+  "action_horizon": 50,
+  "action_normalization_eps": 1e-06,
+  "action_representation": "absolute",
+  "clip_normalized_actions": true,
+  "clip_normalized_max": 10.0,
+  "profile_id": null,
+  "profile_scope": null,
+  "proprio": {
+    "q01": [
+      -0.27276572585105896,
+      -0.237214133143425,
+      0.916006326675415,
+      2.779496669769287,
+      -1.3187512159347534,
+      -0.4198998212814331,
+      0.001503719249740243,
+      -0.03989770635962486
+    ],
+    "q99": [
+      0.1352936029434204,
+      0.362916499376297,
+      1.286232590675354,
+      3.2829697132110596,
+      0.9332759976387024,
+      0.6325722336769104,
+      0.03993396461009979,
+      -0.0016719202976673841
+    ]
+  },
+  "proprio_dim": 8,
+  "proprio_normalization_eps": 1e-06,
+  "relative_exclude_joints": [],
+  "schema": "flow_matching_stats_v1",
+  "state_action_schema": "gripper_7",
+  "stats_sha256": "b2676fdb56b148f49f21fb7633769a2d2e152a7c4cd63e05884232274748ead0",
+  "target_fps": 20.0,
+  "validation_status": null
+}

lerobot_policy/config.json

@@ -0,0 +1,123 @@
+{
+    "type": "perceptron_isaac",
+    "n_obs_steps": 3,
+    "input_features": {},
+    "output_features": {},
+    "device": "cuda",
+    "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,
+    "chunk_size": 50,
+    "n_action_steps": 8,
+    "action_dim": 7,
+    "max_action_dim": 64,
+    "max_action_horizon": 64,
+    "proprio_dim": 8,
+    "max_state_dim": 128,
+    "inference_backend": "native_mharmony",
+    "action_expert_type": "molmoact",
+    "num_inference_steps": 10,
+    "num_flow_samples": 1,
+    "flow_seed_base": 20260826,
+    "clip_normalized_max": 10.0,
+    "fast_clip_normalized_max": 1.0,
+    "clip_action_pose": true,
+    "num_settle_steps": 40,
+    "settle_gripper": -1.0,
+    "rtc_prefix_length": 0,
+    "image_size": [
+        256,
+        256
+    ],
+    "image_preprocessing": "stretch",
+    "camera_order": [
+        "image",
+        "wrist_image"
+    ],
+    "serving_camera_roles": null,
+    "allow_image_key_fallback": false,
+    "normalize_gripper": true,
+    "gripper_binary_to_signed": false,
+    "joint_signs": null,
+    "joint_offsets": null,
+    "training_action_frame_contract_version": 2,
+    "hf_model_path": "..",
+    "artifact_kind": "trained_policy",
+    "apply_offset_norm": false,
+    "config_toml_path": null,
+    "stats_path": null,
+    "per_suite_stats_dir": null,
+    "include_scene_description": false,
+    "vector_max_states": 128,
+    "normalize_task_text": true,
+    "action_conditioning": false,
+    "action_conditioning_role": "user",
+    "mistake_conditioning": false,
+    "render_processor_enabled": false,
+    "render_patch_size": 16,
+    "render_pixel_shuffle_scale": 2,
+    "render_temporal_patch_size": 2,
+    "render_max_num_patches": 576,
+    "render_min_num_patches": null,
+    "dataset_name": "libero",
+    "policy_state_dataset": "libero",
+    "robot_type": "libero",
+    "control_mode": "ee",
+    "target_fps": 20.0,
+    "action_feature_names": null,
+    "state_feature_names": null,
+    "strict_hardware_feature_contract": false,
+    "strict_environment_feature_contract": true,
+    "normalization_profile_id": null,
+    "normalization_profile_scope": null,
+    "normalization_validation_status": null,
+    "deployment_adapter_sha256": "da15a0d08fd70c5a10de150d341e2890e87325aa542e36929179c9f7527f16df",
+    "native_render_metadata_path": null,
+    "native_stats_path": "isaac_stats.json",
+    "suite_stats_path": null,
+    "suite_by_task_index_path": null,
+    "fast_processor_path": "../fast_processor_pinned",
+    "fast_processor_tree_sha256": "127eb029e5acb8242c7bc2c8efcea6c5dd6ffb565353b5c689b8c8ac55f33a8a",
+    "mharmony_version": "0.1.0",
+    "native_require_processor_stream": true,
+    "objective": "mixed",
+    "loss_plan": "text_ntp_fast_flow_action",
+    "train_expert_only": false,
+    "flow_matching_detach_vlm_activations": false,
+    "exclude_non_agent_roles": true,
+    "train_samples_per_chunk": 8,
+    "train_clip_normalized_actions": true,
+    "train_skip_outlier_threshold": 20.0,
+    "train_max_sequence_length": 4096,
+    "flow_rtc_max_delay_steps": 0,
+    "flow_rtc_delay_sampling": "uniform",
+    "flow_dual_timestep_ratio": 0.0,
+    "flow_mask_padded_action_rows": true,
+    "softmax_auxiliary_loss_scale": 0.0001,
+    "freeze_input_embeddings": true,
+    "dtype": "bfloat16",
+    "train_storage_fp32": true,
+    "normalization_mapping": {
+        "VISUAL": "IDENTITY",
+        "STATE": "IDENTITY",
+        "ACTION": "IDENTITY"
+    },
+    "optimizer_lr": 1e-05,
+    "optimizer_vit_lr": 5e-06,
+    "optimizer_action_expert_lr": 5e-05,
+    "optimizer_betas": [
+        0.9,
+        0.95
+    ],
+    "optimizer_eps": 1e-06,
+    "optimizer_weight_decay": 0.0,
+    "optimizer_grad_clip_norm": 1.0,
+    "optimizer_warmup_steps": 200,
+    "max_train_steps": 30000
+}

lerobot_policy/isaac_deployment_adapter.json

@@ -0,0 +1,47 @@
+{
+  "schema": "perceptron_isaac_deployment_adapter_v1",
+  "contract_sha256": {
+    "policy_state_contracts.json": "8f83eb9eff2defdef07a2e297b401de475668063e27c3eb5d80963ddb67f1a5e",
+    "policy_normalization.json": "f829a6f6f72be41196820a1591fb8e7047d9ab674f77a0bec1ba53713ac0c1dc",
+    "policy_inference_recipe.json": "85e5f52d50a3c89b6ff3adc594189bde3e1d345fbecc7bda082561308b3ee905"
+  },
+  "policy_state_dataset": "libero",
+  "normalization_scope": "libero_spatial",
+  "objective": "Flow",
+  "render_dataset_name": "libero",
+  "robot_type": "libero",
+  "control_mode": "ee",
+  "image_size": [
+    256,
+    256
+  ],
+  "camera_order": [
+    "image",
+    "wrist_image"
+  ],
+  "camera_views": [
+    "primary",
+    "wrist"
+  ],
+  "n_action_steps": 8,
+  "num_inference_steps": 10,
+  "num_flow_samples": 1,
+  "flow_seed_base": 20260826,
+  "clip_action_pose": true,
+  "gripper_binary_to_signed": false,
+  "num_settle_steps": 40,
+  "settle_gripper": -1.0,
+  "normalize_task_text": true,
+  "joint_signs": null,
+  "joint_offsets": null,
+  "normalization_profile_id": null,
+  "normalization_profile_scope": null,
+  "normalization_validation_status": null,
+  "adapter_validation_status": "reviewed_offline",
+  "provenance": {
+    "checkpoint": "PerceptronAI/Isaac-0.5",
+    "purpose": "LIBERO Spatial Flow reference deployment profile",
+    "profile_source": "LeRobot tested LIBERO deployment profile",
+    "selected_by": "user"
+  }
+}

lerobot_policy/isaac_stats.json

@@ -0,0 +1,60 @@
+{
+  "action": {
+    "q01": [
+      -0.7454732060432434,
+      -0.6616071462631226,
+      -0.9375,
+      -0.1071428582072258,
+      -0.20678570866584778,
+      -0.1842857152223587,
+      -1.0
+    ],
+    "q99": [
+      0.9375,
+      0.8758928775787354,
+      0.9321428537368774,
+      0.1039285734295845,
+      0.17678570747375488,
+      0.14571428298950195,
+      1.0
+    ]
+  },
+  "action_dim": 7,
+  "action_horizon": 50,
+  "action_normalization_eps": 1e-06,
+  "action_representation": "absolute",
+  "clip_normalized_actions": true,
+  "clip_normalized_max": 10.0,
+  "profile_id": null,
+  "profile_scope": null,
+  "proprio": {
+    "q01": [
+      -0.27276572585105896,
+      -0.237214133143425,
+      0.916006326675415,
+      2.779496669769287,
+      -1.3187512159347534,
+      -0.4198998212814331,
+      0.001503719249740243,
+      -0.03989770635962486
+    ],
+    "q99": [
+      0.1352936029434204,
+      0.362916499376297,
+      1.286232590675354,
+      3.2829697132110596,
+      0.9332759976387024,
+      0.6325722336769104,
+      0.03993396461009979,
+      -0.0016719202976673841
+    ]
+  },
+  "proprio_dim": 8,
+  "proprio_normalization_eps": 1e-06,
+  "relative_exclude_joints": [],
+  "schema": "flow_matching_stats_v1",
+  "state_action_schema": "gripper_7",
+  "stats_sha256": "b2676fdb56b148f49f21fb7633769a2d2e152a7c4cd63e05884232274748ead0",
+  "target_fps": 20.0,
+  "validation_status": null
+}

lerobot_policy/policy_postprocessor.json

@@ -0,0 +1,36 @@
+{
+  "name": "policy_postprocessor",
+  "steps": [
+    {
+      "registry_name": "perceptron_isaac_action_unnormalize",
+      "config": {
+        "enabled": true,
+        "stats_path": null,
+        "clip_normalized_max": 10.0,
+        "clip_action_pose": true,
+        "gripper_binary_to_signed": false,
+        "normalization_profile_id": null,
+        "normalization_profile_scope": null,
+        "normalization_validation_status": null,
+        "normalize_gripper": true,
+        "action_feature_names": null,
+        "state_feature_names": null
+      },
+      "state_file": "policy_postprocessor_step_0_perceptron_isaac_action_unnormalize.safetensors"
+    },
+    {
+      "registry_name": "perceptron_isaac_action_frame_transform",
+      "config": {
+        "joint_signs": null,
+        "joint_offsets": null
+      }
+    },
+    {
+      "registry_name": "device_processor",
+      "config": {
+        "device": "cpu",
+        "float_dtype": null
+      }
+    }
+  ]
+}

lerobot_policy/policy_postprocessor_step_0_perceptron_isaac_action_unnormalize.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be4a256dbc65a14c295bbf9aa39ed28028b39b8a220e737a176912621b60c86c
+size 726

lerobot_policy/policy_preprocessor.json

@@ -0,0 +1,103 @@
+{
+  "name": "policy_preprocessor",
+  "steps": [
+    {
+      "registry_name": "rename_observations_processor",
+      "config": {
+        "rename_map": {
+          "observation.images.image2": "observation.images.wrist_image"
+        }
+      }
+    },
+    {
+      "registry_name": "to_batch_processor",
+      "config": {}
+    },
+    {
+      "registry_name": "perceptron_isaac_state_frame_transform",
+      "config": {
+        "joint_signs": null,
+        "joint_offsets": null
+      }
+    },
+    {
+      "registry_name": "perceptron_isaac_training_action_frame_transform",
+      "config": {
+        "joint_signs": null,
+        "joint_offsets": null
+      }
+    },
+    {
+      "registry_name": "perceptron_isaac_mharmony_pack",
+      "config": {
+        "enabled": true,
+        "inference_backend": "native_mharmony",
+        "config_toml_path": null,
+        "stats_path": null,
+        "camera_order": [
+          "image",
+          "wrist_image"
+        ],
+        "image_size": [
+          256,
+          256
+        ],
+        "image_preprocessing": "stretch",
+        "image_keys": [
+          "observation.images.image",
+          "observation.images.wrist_image"
+        ],
+        "allow_image_key_fallback": false,
+        "normalize_language": true,
+        "n_obs_steps": 3,
+        "chunk_size": 50,
+        "objective": "mixed",
+        "patch_size": 16,
+        "max_num_patches": 576,
+        "min_num_patches": null,
+        "pixel_shuffle_scale": 2,
+        "temporal_patch_size": 2,
+        "device": "cuda",
+        "dtype": "bfloat16",
+        "stream_key": "perceptron_isaac_stream",
+        "metadata_key": "perceptron_isaac_render_meta",
+        "target_fps": 20.0,
+        "normalization_profile_id": null,
+        "normalization_profile_scope": null,
+        "normalization_validation_status": null,
+        "suite_stats_path": null,
+        "suite_by_task_index_path": null,
+        "native_render_metadata_path": null,
+        "native_stats_path": null,
+        "fast_processor_path": "../fast_processor_pinned",
+        "fast_processor_tree_sha256": "127eb029e5acb8242c7bc2c8efcea6c5dd6ffb565353b5c689b8c8ac55f33a8a",
+        "mharmony_version": "0.1.0",
+        "action_dim": 7,
+        "proprio_dim": 8,
+        "vector_max_states": 128,
+        "dataset_name": "libero",
+        "robot_type": "libero",
+        "action_conditioning": false,
+        "action_conditioning_role": "user",
+        "mistake_conditioning": false,
+        "render_metadata": null,
+        "train_clip_normalized_actions": true,
+        "clip_normalized_max": 10.0,
+        "fast_clip_normalized_max": 1.0,
+        "train_skip_outlier_threshold": 20.0,
+        "train_max_sequence_length": 4096,
+        "normalize_gripper": true,
+        "action_feature_names": null,
+        "state_feature_names": null
+      },
+      "state_file": "policy_preprocessor_step_4_perceptron_isaac_mharmony_pack.safetensors"
+    },
+    {
+      "registry_name": "device_processor",
+      "config": {
+        "device": "cuda",
+        "float_dtype": null
+      }
+    }
+  ]
+}

lerobot_policy/policy_preprocessor_step_4_perceptron_isaac_mharmony_pack.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be4a256dbc65a14c295bbf9aa39ed28028b39b8a220e737a176912621b60c86c
+size 726

model-00001-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71548e066c99a1c63a5307e7d506824429a6b297788f8e1faf80391a6c696c6c
+size 4416265552

model-00002-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70b95d3b872486e3cc85b03e20d6efb30cc6d0f4510a9cf14b4d908f813bc731
+size 3308063024

model-00003-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6db7db8779542ebf8392f2a26cb8aeada24b5691d09e6bafa058aaf5c9f2c514
+size 3370814568

model-00004-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72a6cf2afdc5bb8bff40436da2c2882a9df3a6d86d6b694dc4df2c75ca6dc5b9
+size 3370814584

model-00005-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9bdda50a48758cb84e949abaa0d5100d5e304408d0ca9c9ac8bac420eca0105
+size 3235939552

model-00006-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3ec16af11ecbd1b76b4afef37fa97129b6172892fb615eebc62ad90845bd5ac
+size 3479869320

model-00007-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6fdb07421e4b8ed3f02b9d0c80f23eb05db8f477f32a63ad59f943df8609a3d
+size 3370814592

model-00008-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc401c60fb6652be8305fb4f76cb8557bb1baf69f3e5e813afae0473d3651be1
+size 3370814592

model-00009-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4078a95d5c1167fb8235eae76d898b3876af2e3760460601a814c603685f1f73
+size 3235939552

model-00010-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e2e329b533cd98e6453ac5dc7b8359590a2a30ae5bab9ea314ad7eb9506fa1c
+size 3479869320

model-00011-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0125ce1d57b0312de64a3921e901c6a46b6f712bbac365fcfd0a91a133da2240
+size 3370814592

model-00012-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:674225ed2bfa7af034b36442659e5e29dc0ed3f7c7c892125857cc74c84d184a
+size 3370814592

model-00013-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75702cda92f90725e206ef45a4b0ab5b2e97155e5b207d3c463de3a46838da15
+size 3235939552

model-00014-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be75df9f9b4386ee8bfe477a569612fa9dfb5fff52f68140045b526d5caffa97
+size 3479869304

model-00015-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2407f893f730efea4bac097894f87b2f685db86b2db0dba2a74bf47dee0a4f3a
+size 3370814584

model-00016-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d98445ad557f0a3c360cab0c6d6ac9bbba8e39f4f6c7db7064ff41d967f83bd
+size 3370814592

model-00017-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb18753df67ec7c857cbe38561c2a720d195011a7e0bc112da465b129a12daee
+size 3370814592

model-00018-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50329180cf5d0807eb144bf0a98f9cd9c4d88f3d8355cc46db662fbede0307ba
+size 3235939552

model-00019-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:848a86b200296b0f3730c065461486596c0b93209a87967c5cefdac4bc375a5a
+size 3479869320

model-00020-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:669c3d350570c8581b30f0753184f65522966ea8bc3abb37e258e3b222af2bf7
+size 3370814592

model-00021-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06aced85fd27a61af9e83331a778b747ee2e33738ee31484f5f65dd531d9978f
+size 3370814592

model-00022-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8b3f39b64e04e624ed58d72cad1f59c754c5b3bb858a24b5252b5302657c561
+size 3235939552

model-00023-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1469fa1c66accef373c64371c6b1c35f487bf1d08f75d48781af02a434f8a489
+size 3479869320

model-00024-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c09825c3dd19364ff70a91d30dd181b533d500a75067d59949dabb23f86c7781
+size 3370814592

model-00025-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba12b1f13f318163c13a1fe632a370626961e27ab01102dae6e4288426313409
+size 3235939552

model-00026-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3dd5247014f129ebe23a849c381101794a119576723aa4eef098f9460cc07c63
+size 3479869304

model-00027-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78e42c7ffa62b84d4cee9d55da8f8c8c2350cd36c6dcc5bd65482053a8e38e02
+size 3235939552

model-00028-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:827fff97afce3730dfb86b463cc0055c9b7b1147fe3e66151bc3d97b14c7cc96
+size 3479869320

model-00029-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14308b38442f97722d8b842c10066a84b7578a2040477c147aedd60b664dd30c
+size 3370814592