initial commit

.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

@@ -1,3 +1,161 @@
 ---
 license: gemma
+library_name: transformers
+base_model:
+- Dexmal/DM05
+tags:
+- robotics
+- robot-control
+- vision-language-action
+- vla
+- dm05
+- dm0.5
+- robodojo
+- simulation
+- memory
+- opendm
 ---
+
+# DM05-MEM-Robodojo-Sim
+
+![DM0.5](https://raw.githubusercontent.com/dexmal/opendm/main/docs/image/header.png)
+
+<p align="center">
+  <a href="https://www.dexmal.com/blog/dm0.5/index_en.html"><img src="https://img.shields.io/badge/%F0%9F%93%96-Tech_Blog-blue" alt="Tech Blog"></a>
+  <a href="https://github.com/dexmal/opendm"><img src="https://img.shields.io/badge/GitHub-OpenDM-181717?logo=github" alt="GitHub"></a>
+  <a href="https://robodojo-benchmark.com/leaderboard"><img src="https://img.shields.io/badge/Benchmark-RoboDojo-orange" alt="RoboDojo Leaderboard"></a>
+  <a href="https://maas.dexmal.com/"><img src="https://img.shields.io/badge/MaaS-Online-brightgreen.svg" alt="MaaS"></a>
+</p>
+
+## Introduction
+
+DM05-MEM-Robodojo-Sim is the RoboDojo simulation fine-tuned generalist checkpoint of DM0.5, Dexmal's open-world Vision-Language-Action foundation model for embodied intelligence. DM0.5 uses a Gemma 3 4B vision-language backbone with a 680M Action Expert to generate continuous robot actions, and is designed for natural-language manipulation, zero-shot generalization, efficient downstream fine-tuning, long-horizon historical context, robust policy behavior, and transfer across robot embodiments.
+
+This memory-enabled checkpoint targets the ARX X5 bimanual embodiment used by RoboDojo-Sim. It consumes current head, left-wrist, and right-wrist RGB views together with up to 20 head-camera history frames sampled at 1 FPS. At the beginning of an episode, unavailable history slots are left-padded until enough observations have been collected. The model generates 14-dimensional absolute joint-position action chunks of length 50, and the RoboDojo evaluation adapter executes the first 25 actions from each predicted chunk.
+
+### RoboDojo-Sim Results
+
+The following results are a snapshot of the official RoboDojo leaderboard on August 24, 2026.
+
+| Metric | Gen-Std | Gen-Rand | Precision | Long-Horizon | Memory | Open | Average |
+| --- | ---: | ---: | ---: | ---: | ---: | ---: | ---: |
+| Score | 23.49 | 8.06 | 24.82 | 33.70 | 47.74 | 2.43 | 24.90 |
+| Success Rate (%) | 18.00 | 4.00 | 16.75 | 19.50 | 47.44 | 2.08 | 19.34 |
+
+Generalization is reported separately for the standard (`Gen-Std`) and randomized (`Gen-Rand`) settings. See the [official RoboDojo leaderboard](https://robodojo-benchmark.com/leaderboard) for detailed per-task results, rollout videos, metric definitions, and the latest rankings.
+
+## Quick Start
+
+We recommend using Docker to set up the runtime environment first, which helps avoid version mismatches across CUDA, PyTorch, flash-attn, and other dependencies on the host machine.
+
+### Requirements
+
+```text
+System requirements:
+Ubuntu 20.04 / 22.04
+NVIDIA GPU
+NVIDIA Driver
+Docker
+NVIDIA Container Toolkit
+Conda (optional, only required for local pip installation)
+
+Recommended GPUs:
+A100, H100, H20
+1 GPU is sufficient for deployment inference.
+```
+
+### Download the Checkpoint
+
+```bash
+pip install -U "huggingface_hub[cli]"
+
+hf download Dexmal/DM05-MEM-Robodojo-Sim \
+  --local-dir ./checkpoints/DM05-MEM-Robodojo-Sim
+```
+
+The checkpoint directory must include its matching `norm_stats.json`.
+
+### Docker Installation
+
+```bash
+git clone https://github.com/dexmal/opendm.git
+cd opendm
+
+docker run -it --rm --gpus all --network host \
+  --name opendm \
+  --shm-size=16g \
+  -v "$PWD":/app/opendm \
+  -w /app/opendm \
+  dexmal/opendm:latest /bin/bash
+
+# Run from the OpenDM repository root inside the container.
+conda activate opendm
+pip install -e .
+```
+
+### Local Installation
+
+```bash
+conda create -n opendm python=3.10 -y
+conda activate opendm
+
+pip install torch torchvision \
+  --index-url https://download.pytorch.org/whl/cu128
+
+pip install ninja packaging
+MAX_JOBS=2 pip install flash-attn --no-build-isolation
+
+# Enter the OpenDM repository root.
+cd opendm
+pip install -e .
+```
+
+## RoboDojo-Sim Testing
+
+Use RoboDojo's official evaluation workflow to test this checkpoint. RoboDojo runs the simulation benchmark client, while policy integration and serving are managed through XPolicyLab.
+
+Follow these official guides in order:
+
+1. [Install RoboDojo and download its assets and data](https://robodojo-benchmark.com/doc/usage/install-and-download/).
+2. [Set up or select the model integration in XPolicyLab](https://robodojo-benchmark.com/doc/usage/xpolicylab/).
+3. [Run the RoboDojo Quick Evaluation workflow](https://robodojo-benchmark.com/doc/usage/quick-evaluation/).
+
+Use the released checkpoint together with its bundled `norm_stats.json`. Keep the official camera order and absolute joint-position action mode unchanged, provide up to 20 head-camera history frames sampled at 1 FPS with left-padding during episode warm-up, predict 50-step action chunks, and execute the first 25 actions from each chunk.
+
+For the model-specific XPolicyLab integration, see [XPolicyLab PR #101](https://github.com/XPolicyLab/XPolicyLab/pull/101). If the PR has already been merged, use the official XPolicyLab code from the `main` branch directly; otherwise, use the integration code provided by the PR.
+
+For benchmark rules, multi-seed reporting, and verified leaderboard publication requirements, see the [official evaluation protocol](https://robodojo-benchmark.com/leaderboard/protocol). Detailed results should be referenced directly from the [official leaderboard](https://robodojo-benchmark.com/leaderboard).
+
+## Intended Use and Limitations
+
+This checkpoint is intended for research evaluation on RoboDojo-Sim with the matching ARX X5 observation/action convention, normalization statistics, camera order, action horizon, and history-input policy. Using a different embodiment, state/action ordering, camera layout, action mode, or history sampling strategy requires an adapted configuration and may substantially reduce performance.
+
+RoboDojo is an intentionally challenging benchmark. The aggregate results above do not imply reliable success on every task, and performance in simulation does not guarantee safe or successful real-world deployment.
+
+## Community and Support
+
+- Learn more about Dexmal products and model updates on the [Dexmal website](https://www.dexmal.com/).
+- If you encounter OpenDM issues, please report them through [GitHub Issues](https://github.com/dexmal/opendm/issues).
+- For RoboDojo setup and evaluation questions, see the [official documentation](https://robodojo-benchmark.com/doc/) and [community page](https://robodojo-benchmark.com/community).
+- For further discussion with Dexmal, scan the [WeChat QR code](https://raw.githubusercontent.com/dexmal/opendm/main/docs/image/wechat.jpeg) to contact us.
+
+We will continue to release more model weights, technical documentation, and examples. If this project is helpful to you, please consider giving us a star on GitHub [![GitHub](https://img.shields.io/github/stars/dexmal/opendm?color=5B5BD6)](https://github.com/dexmal/opendm). Your support helps us move forward.
+
+## Citation
+
+```bibtex
+@misc{dm05,
+    title  = {{DM0.5}: An Open-World Foundation Model for General-Purpose Embodied Intelligence},
+    author = {{Dexmal Team}},
+    month  = {July},
+    year   = {2026},
+    url    = {https://www.dexmal.com/blog/dm0.5/index_en.html}
+}
+
+@article{chen2026robodojo,
+    title   = {{RoboDojo}: A Unified Sim-and-Real Benchmark for Comprehensive Evaluation of Generalist Robot Manipulation Policies},
+    author  = {Chen, Tianxing and Chen, Yue and Li, Zixuan and Tang, Junyuan and Su, Kailun and Wan, Weijie and Chen, Baijun and Lu, Haoran and Yan, Haowen and Su, Honghao and others},
+    journal = {arXiv preprint arXiv:2607.04434},
+    year    = {2026}
+}
+```

chat_template.jinja

@@ -0,0 +1,47 @@
+{{ bos_token }}
+{%- if messages[0]['role'] == 'system' -%}
+    {%- if messages[0]['content'] is string -%}
+        {%- set first_user_prefix = messages[0]['content'] + '
+
+' -%}
+    {%- else -%}
+        {%- set first_user_prefix = messages[0]['content'][0]['text'] + '
+
+' -%}
+    {%- endif -%}
+    {%- set loop_messages = messages[1:] -%}
+{%- else -%}
+    {%- set first_user_prefix = "" -%}
+    {%- set loop_messages = messages -%}
+{%- endif -%}
+{%- for message in loop_messages -%}
+    {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}
+        {{ raise_exception("Conversation roles must alternate user/assistant/user/assistant/...") }}
+    {%- endif -%}
+    {%- if (message['role'] == 'assistant') -%}
+        {%- set role = "model" -%}
+    {%- else -%}
+        {%- set role = message['role'] -%}
+    {%- endif -%}
+    {{ '<start_of_turn>' + role + '
+' + (first_user_prefix if loop.first else "") }}
+    {%- if message['content'] is string -%}
+        {{ message['content'] | trim }}
+    {%- elif message['content'] is iterable -%}
+        {%- for item in message['content'] -%}
+            {%- if item['type'] == 'image' -%}
+                {{ '<start_of_image>' }}
+            {%- elif item['type'] == 'text' -%}
+                {{ item['text'] | trim }}
+            {%- endif -%}
+        {%- endfor -%}
+    {%- else -%}
+        {{ raise_exception("Invalid content type") }}
+    {%- endif -%}
+    {{ '<end_of_turn>
+' }}
+{%- endfor -%}
+{%- if add_generation_prompt -%}
+    {{'<start_of_turn>model
+'}}
+{%- endif -%}

config.json

@@ -0,0 +1,261 @@
+{
+  "action_config": {
+    "_name_or_path": "",
+    "_sliding_window_pattern": 6,
+    "architectures": null,
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "attn_logit_softcapping": null,
+    "bos_token_id": 2,
+    "chunk_size_feed_forward": 0,
+    "dtype": null,
+    "eos_token_id": 1,
+    "final_logit_softcapping": null,
+    "head_dim": 256,
+    "hidden_activation": "gelu_pytorch_tanh",
+    "hidden_size": 1024,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
+    "intermediate_size": 4096,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_types": [
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention"
+    ],
+    "max_position_embeddings": 131072,
+    "model_type": "gemma3_text",
+    "num_attention_heads": 8,
+    "num_hidden_layers": 34,
+    "num_key_value_heads": 4,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "pad_token_id": 0,
+    "problem_type": null,
+    "query_pre_attn_scalar": 256,
+    "return_dict": true,
+    "rms_norm_eps": 1e-06,
+    "rope_parameters": {
+      "full_attention": {
+        "factor": 8.0,
+        "rope_theta": 1000000.0,
+        "rope_type": "linear"
+      },
+      "sliding_attention": {
+        "rope_theta": 10000.0,
+        "rope_type": "default"
+      }
+    },
+    "sliding_window": 4096,
+    "tie_word_embeddings": true,
+    "use_bidirectional_attention": false,
+    "use_cache": true,
+    "vocab_size": 262208
+  },
+  "action_dim": 32,
+  "architectures": [
+    "DM05ForConditionalGeneration"
+  ],
+  "bos_token_id": 2,
+  "chunk_size": 50,
+  "dtype": "float32",
+  "eos_token_id": 1,
+  "model_type": "dm05",
+  "pad_token_id": 0,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.3.0",
+  "use_cache": false,
+  "vlm_config": {
+    "_name_or_path": "",
+    "architectures": [
+      "Gemma3ForConditionalGeneration"
+    ],
+    "boi_token_index": 255999,
+    "chunk_size_feed_forward": 0,
+    "dtype": "bfloat16",
+    "eoi_token_index": 256000,
+    "eos_token_id": [
+      1,
+      106
+    ],
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "image_token_index": 262144,
+    "initializer_range": 0.02,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "mm_tokens_per_image": 256,
+    "model_type": "gemma3",
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "problem_type": null,
+    "return_dict": true,
+    "text_config": {
+      "_name_or_path": "",
+      "_sliding_window_pattern": 6,
+      "architectures": null,
+      "attention_bias": false,
+      "attention_dropout": 0.0,
+      "attn_logit_softcapping": null,
+      "bos_token_id": 2,
+      "chunk_size_feed_forward": 0,
+      "dtype": "bfloat16",
+      "eos_token_id": 1,
+      "final_logit_softcapping": null,
+      "head_dim": 256,
+      "hidden_activation": "gelu_pytorch_tanh",
+      "hidden_size": 2560,
+      "id2label": {
+        "0": "LABEL_0",
+        "1": "LABEL_1"
+      },
+      "initializer_range": 0.02,
+      "intermediate_size": 10240,
+      "is_encoder_decoder": false,
+      "label2id": {
+        "LABEL_0": 0,
+        "LABEL_1": 1
+      },
+      "layer_types": [
+        "sliding_attention",
+        "sliding_attention",
+        "sliding_attention",
+        "sliding_attention",
+        "sliding_attention",
+        "full_attention",
+        "sliding_attention",
+        "sliding_attention",
+        "sliding_attention",
+        "sliding_attention",
+        "sliding_attention",
+        "full_attention",
+        "sliding_attention",
+        "sliding_attention",
+        "sliding_attention",
+        "sliding_attention",
+        "sliding_attention",
+        "full_attention",
+        "sliding_attention",
+        "sliding_attention",
+        "sliding_attention",
+        "sliding_attention",
+        "sliding_attention",
+        "full_attention",
+        "sliding_attention",
+        "sliding_attention",
+        "sliding_attention",
+        "sliding_attention",
+        "sliding_attention",
+        "full_attention",
+        "sliding_attention",
+        "sliding_attention",
+        "sliding_attention",
+        "sliding_attention"
+      ],
+      "max_position_embeddings": 131072,
+      "model_type": "gemma3_text",
+      "num_attention_heads": 8,
+      "num_hidden_layers": 34,
+      "num_key_value_heads": 4,
+      "output_attentions": false,
+      "output_hidden_states": false,
+      "pad_token_id": 0,
+      "problem_type": null,
+      "query_pre_attn_scalar": 256,
+      "return_dict": true,
+      "rms_norm_eps": 1e-06,
+      "rope_parameters": {
+        "full_attention": {
+          "factor": 8.0,
+          "rope_theta": 1000000.0,
+          "rope_type": "linear"
+        },
+        "sliding_attention": {
+          "rope_theta": 10000.0,
+          "rope_type": "default"
+        }
+      },
+      "sliding_window": 4096,
+      "tie_word_embeddings": true,
+      "use_bidirectional_attention": false,
+      "use_cache": true,
+      "vocab_size": 262208
+    },
+    "tie_word_embeddings": true,
+    "use_cache": false,
+    "vision_config": {
+      "_name_or_path": "",
+      "architectures": null,
+      "attention_dropout": 0.0,
+      "chunk_size_feed_forward": 0,
+      "dtype": "bfloat16",
+      "hidden_act": "gelu_pytorch_tanh",
+      "hidden_size": 1152,
+      "id2label": {
+        "0": "LABEL_0",
+        "1": "LABEL_1"
+      },
+      "image_size": 448,
+      "intermediate_size": 4304,
+      "is_encoder_decoder": false,
+      "label2id": {
+        "LABEL_0": 0,
+        "LABEL_1": 1
+      },
+      "layer_norm_eps": 1e-06,
+      "model_type": "siglip_vision_model",
+      "num_attention_heads": 16,
+      "num_channels": 3,
+      "num_hidden_layers": 27,
+      "output_attentions": false,
+      "output_hidden_states": false,
+      "patch_size": 14,
+      "problem_type": null,
+      "return_dict": true,
+      "vision_use_head": false
+    }
+  }
+}

generation_config.json

@@ -0,0 +1,11 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 2,
+  "eos_token_id": [
+    1
+  ],
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "pad_token_id": 0,
+  "transformers_version": "5.3.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db5f19ac29bd049ceee542db37263a470c15a6c33a589a446e274c5ac5cbf3ba
+size 23316655136

norm_stats.json

@@ -0,0 +1,136 @@
+{
+  "norm_stats": {
+    "action": {
+      "q01": [
+        -1.0515477853775024,
+        -0.00019582325220107721,
+        -0.000275185357034205,
+        -1.5994959164619447,
+        -0.5985351327896119,
+        -1.6704550132751466,
+        -3.212450869184004e-17,
+        -0.46170408163070675,
+        -9.994709491728537e-05,
+        -0.0003595338851213603,
+        -1.6613843360900877,
+        -1.2665581749439239,
+        -1.853231241607666,
+        -3.212450869184004e-17
+      ],
+      "q99": [
+        0.5367332942962646,
+        2.495384642624855,
+        2.4934933600619438,
+        1.3306754426479337,
+        1.2496659922599793,
+        1.7398107671737675,
+        0.9998,
+        1.0818604693889617,
+        2.4177335428893567,
+        2.353996460956335,
+        1.135059226226807,
+        0.5195488495349885,
+        1.4993711612701413,
+        0.9998
+      ],
+      "mean": [
+        -0.1985221654176712,
+        0.9079715013504028,
+        0.6757031083106995,
+        -0.32898271083831787,
+        0.06580515950918198,
+        0.0013387879589572549,
+        0.7721145749092102,
+        0.17236194014549255,
+        0.8203134536743164,
+        0.6191819310188293,
+        -0.3604429066181183,
+        -0.0635266900062561,
+        0.0015465744072571397,
+        0.7840675115585327
+      ],
+      "std": [
+        0.34116998314857483,
+        0.894352376461029,
+        0.7339895367622375,
+        0.6470863223075867,
+        0.29868993163108826,
+        0.5827605724334717,
+        0.3431955575942993,
+        0.3195728361606598,
+        0.8766812086105347,
+        0.7170135378837585,
+        0.6054048538208008,
+        0.28483811020851135,
+        0.5430217385292053,
+        0.3419511616230011
+      ]
+    },
+    "state": {
+      "q01": [
+        -1.0534918258666992,
+        -0.0015211447954177615,
+        -0.004196205082535737,
+        -1.6003682508945465,
+        -0.6024927369117737,
+        -1.6716857118606567,
+        -3.212450869184004e-17,
+        -0.45030778880119327,
+        -0.00448935736417766,
+        -0.0030238371610641634,
+        -1.640114754486084,
+        -1.2678002521514893,
+        -1.7492679929733277,
+        -3.212450869184004e-17
+      ],
+      "q99": [
+        0.5425654157638551,
+        2.4947219818532465,
+        2.4950617679521443,
+        1.32456910161972,
+        1.2496659922599793,
+        1.7447335615158082,
+        0.9998,
+        1.0805942146301266,
+        2.4162704061329365,
+        2.3468916522204877,
+        1.1401234123229984,
+        0.5195488495349885,
+        1.4901870164871216,
+        0.9998
+      ],
+      "mean": [
+        -0.2014683485031128,
+        0.9308192729949951,
+        0.6917645931243896,
+        -0.3417535722255707,
+        0.06616466492414474,
+        0.004166342318058014,
+        0.7702585458755493,
+        0.17401453852653503,
+        0.8261928558349609,
+        0.6223200559616089,
+        -0.36173784732818604,
+        -0.06290490925312042,
+        0.004132931120693684,
+        0.784990131855011
+      ],
+      "std": [
+        0.3436912000179291,
+        0.8878186345100403,
+        0.7304802536964417,
+        0.6499956250190735,
+        0.29976922273635864,
+        0.585997462272644,
+        0.3436921536922455,
+        0.32037559151649475,
+        0.8737387657165527,
+        0.7136965990066528,
+        0.6033461689949036,
+        0.28427162766456604,
+        0.5374496579170227,
+        0.34115591645240784
+      ]
+    }
+  }
+}

processor_config.json

@@ -0,0 +1,29 @@
+{
+  "image_processor": {
+    "data_format": "channels_first",
+    "do_convert_rgb": null,
+    "do_normalize": true,
+    "do_rescale": true,
+    "do_resize": true,
+    "image_mean": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "image_processor_type": "Gemma3ImageProcessorFast",
+    "image_seq_length": 256,
+    "image_std": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "resample": 2,
+    "rescale_factor": 0.00392156862745098,
+    "size": {
+      "height": 448,
+      "width": 448
+    }
+  },
+  "image_seq_length": 256,
+  "processor_class": "Gemma3Processor"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:daab2354f8a74e70d70b4d1f804939b68a8c9624dd06cb7858e52dd8970e9726
+size 33384567

tokenizer_config.json

@@ -0,0 +1,24 @@
+{
+  "backend": "tokenizers",
+  "boi_token": "<start_of_image>",
+  "bos_token": "<bos>",
+  "clean_up_tokenization_spaces": false,
+  "eoi_token": "<end_of_image>",
+  "eos_token": "<eos>",
+  "image_token": "<image_soft_token>",
+  "is_local": true,
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "model_specific_special_tokens": {
+    "boi_token": "<start_of_image>",
+    "eoi_token": "<end_of_image>",
+    "image_token": "<image_soft_token>"
+  },
+  "pad_token": "<pad>",
+  "processor_class": "Gemma3Processor",
+  "sp_model_kwargs": null,
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}