Add files using upload-large-folder tool

.gitattributes

@@ -33,3 +33,11 @@ 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
+mmproj-F16.gguf filter=lfs diff=lfs merge=lfs -text
+Cosmos-Reason1-7B-UD-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text
+mmproj-F32.gguf filter=lfs diff=lfs merge=lfs -text
+Cosmos-Reason1-7B-UD-Q2_K_XL.gguf filter=lfs diff=lfs merge=lfs -text
+Cosmos-Reason1-7B-UD-Q3_K_XL.gguf filter=lfs diff=lfs merge=lfs -text
+Cosmos-Reason1-7B-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Cosmos-Reason1-7B-UD-Q4_K_XL.gguf filter=lfs diff=lfs merge=lfs -text
+Cosmos-Reason1-7B-UD-Q5_K_XL.gguf filter=lfs diff=lfs merge=lfs -text

Cosmos-Reason1-7B-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a255a989ee7c179dbc5c16bc6a09998e2fb706f35f5020d2b18278654e540f94
+size 4683073664

Cosmos-Reason1-7B-UD-IQ1_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:375bab73919220d934fd5d60db37b9eae62af73500928c4ce26826c4f25e7d05
+size 2073763968

Cosmos-Reason1-7B-UD-Q2_K_XL.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ecac29d1234abe3f2f589e08b0722f926d4dc9d005a9a4eb163edb342396d3e
+size 3242950784

Cosmos-Reason1-7B-UD-Q3_K_XL.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b7ede9e7a61fee375b2b932ac0242fb2801fee53101eace7d69a77efd461b88
+size 4002672768

Cosmos-Reason1-7B-UD-Q4_K_XL.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a4ab8746afb88e3fc2c8ac6407623a0767c52d7e031f6fdcdfd8d48b62426f5
+size 4785160320

Cosmos-Reason1-7B-UD-Q5_K_XL.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91afd7f3c504ce48423b322f6c2ce8ef2d6be5c27b05f51003f1dc3c9da0854b
+size 5461547136

README.md

@@ -0,0 +1,262 @@
+---
+license: other
+license_name: nvidia-open-model-license
+license_link: >-
+  https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license
+datasets:
+- nvidia/Cosmos-Reason1-SFT-Dataset
+- nvidia/Cosmos-Reason1-RL-Dataset
+- nvidia/Cosmos-Reason1-Benchmark
+library_name: transformers
+language:
+- en
+base_model:
+- nvidia/Cosmos-Reason1-7B
+tags:
+- nvidia
+- unsloth
+- cosmos
+---
+<div>
+<p style="margin-top: 0;margin-bottom: 0;">
+    <em><a href="https://docs.unsloth.ai/basics/unsloth-dynamic-v2.0-gguf">Unsloth Dynamic 2.0</a> achieves superior accuracy & outperforms other leading quants.</em>
+  </p>
+  <div style="display: flex; gap: 5px; align-items: center; ">
+    <a href="https://github.com/unslothai/unsloth/">
+      <img src="https://github.com/unslothai/unsloth/raw/main/images/unsloth%20new%20logo.png" width="133">
+    </a>
+    <a href="https://discord.gg/unsloth">
+      <img src="https://github.com/unslothai/unsloth/raw/main/images/Discord%20button.png" width="173">
+    </a>
+    <a href="https://docs.unsloth.ai/basics/qwen3-how-to-run-and-fine-tune">
+      <img src="https://raw.githubusercontent.com/unslothai/unsloth/refs/heads/main/images/documentation%20green%20button.png" width="143">
+    </a>
+  </div>
+</div>
+
+
+
+# **Cosmos-Reason1: Physical AI Common Sense and Embodied Reasoning Models**
+
+[**Cosmos**](https://huggingface.co/collections/nvidia/cosmos-reason1-67c9e926206426008f1da1b7) | [**Code**](https://github.com/nvidia-cosmos/cosmos-reason1) | [**Paper**](https://arxiv.org/abs/2503.15558) | [**Paper Website**](https://research.nvidia.com/labs/dir/cosmos-reason1)
+
+# Model Overview
+
+## Description:
+
+**Cosmos-Reason1 Models**: Physical AI models understand physical common sense and generate appropriate embodied decisions in natural language through long chain-of-thought reasoning processes.
+
+The Cosmos-Reason1 models are post-trained with physical common sense and embodied reasoning data with supervised fine-tuning and reinforcement learning. These are Physical AI models that can understand space, time, and fundamental physics, and can serve as planning models to reason about the next steps of an embodied agent.
+
+The models are ready for commercial use.
+
+**Model Developer**: NVIDIA
+
+## Model Versions
+
+The Cosmos-Reason1 includes the following model:
+
+- [Cosmos-Reason1-7B](https://huggingface.co/nvidia/Cosmos-Reason1-7B): Given a text prompt and an input video, think and generate the answer with respect to the input text prompt and video.
+
+### License:
+
+This model is released under the  [NVIDIA Open Model License](https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license). For a custom license, please contact [[email protected]](mailto:[email protected]).
+
+Under the NVIDIA Open Model License, NVIDIA confirms:
+
+* Models are commercially usable.
+* You are free to create and distribute Derivative Models.
+* NVIDIA does not claim ownership to any outputs generated using the Models or Derivative Models.
+
+**Important Note**: If You bypass, disable, reduce the efficacy of, or circumvent any technical limitation, safety guardrail or associated safety guardrail hyperparameter, encryption, security, digital rights management, or authentication mechanism (collectively “Guardrail”) contained in the Model without a substantially similar Guardrail appropriate for your use case, your rights under this Agreement [NVIDIA Open Model License Agreement](https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license) will automatically terminate.
+
+### Deployment Geography:
+
+Global
+
+### Use Case:
+
+Physical AI: Space, time, fundamental physics understanding and embodied reasoning, encompassing robotics, and autonomous vehicles (AV).
+
+### Release Date:
+
+* Github: [05/17/2025](https://github.com/nvidia-cosmos/cosmos-reason1)
+* Huggingface: [05/17/2025](https://huggingface.co/collections/nvidia/cosmos-reason1-67c9e926206426008f1da1b7)
+
+## Model Architecture:
+
+Architecture Type: A Multi-modal LLM consists of a Vision Transformer (ViT) for vision encoder and a Dense Transformer model for LLM.
+Network Architecture: Qwen2.5-VL-7B-Instruct.
+
+Cosmos-Reason-7B is post-trained based on [Qwen2.5-VL-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-VL-7B-Instruct) and follows the same model architecture.
+
+
+## Input
+
+  **Input Type(s)**: Text+Video/Image
+
+   **Input Format(s)**:
+   * Text: String
+   * Video: mp4
+   * Image: jpg
+
+  **Input Parameters**:
+  * Text: One-dimensional (1D)
+  * Video: Three-dimensional (3D)
+  * Image: Two-dimensional (2D)
+  
+  **Other Properties Related to Input**:
+  * Use `FPS=4` for input video to match the training setup.
+  * Append `Answer the question in the following format: <think>\nyour reasoning\n</think>\n\n<answer>\nyour answer\n</answer>.` in the system prompt to encourage long chain-of-thought reasoning response.
+
+## Output
+
+ **Output Type(s)**: Text 
+
+ **Output Format**: String
+
+ **Output Parameters**: Text: One-dimensional (1D)
+
+ **Other Properties Related to Output**:
+ * Recommend using 4096 or more output max tokens to avoid truncation of long chain-of-thought response.
+ * Our AI models are designed and/or optimized to run on NVIDIA GPU-accelerated systems. By leveraging NVIDIA’s hardware (e.g. GPU cores) and software frameworks (e.g., CUDA libraries), the model achieves faster training and inference times compared to CPU-only solutions. <br>
+
+
+## Software Integration
+
+**Runtime Engine(s):**
+
+* [vLLM](https://github.com/vllm-project/vllm)
+
+**Supported Hardware Microarchitecture Compatibility:**
+
+* NVIDIA Blackwell
+* NVIDIA Hopper
+
+**Note**: We have only tested doing inference with BF16 precision.
+
+**Operating System(s):**
+
+* Linux (We have not tested on other operating systems.)
+
+
+# Usage
+
+See [Cosmos-Reason1](https://github.com/nvidia-cosmos/cosmos-reason1) for details.
+* Post Training: [Cosmos-Reason1](https://github.com/nvidia-cosmos/cosmos-reason1) provides examples of supervised fine-tuning and reinforcement learning on embodied reasoning datasets.
+
+# Evaluation
+
+Please see our [technical paper](https://arxiv.org/pdf/2503.15558) for detailed evaluations on physical common sense and embodied reasoning. Part of the evaluation datasets are released under [Cosmos-Reason1-Benchmark](https://huggingface.co/datasets/nvidia/Cosmos-Reason1-Benchmark). The embodied reasoning datasets and benchmarks focus on the following areas: robotics (RoboVQA, BridgeDataV2, Agibot, RobFail), ego-centric human demonstration (HoloAssist), and Autonomous Vehicle (AV) driving video data. The AV dataset is collected and annotated by NVIDIA.
+All datasets go through the data annotation process described in the technical paper to prepare training and evaluation data and annotations.
+
+**Data Collection Method**:
+* RoboVQA:  Hybrid:  Automatic/Sensors
+* BridgeDataV2: Automatic/Sensors
+* AgiBot: Automatic/Sensors
+* RoboFail: Automatic/Sensors
+* HoloAssist: Human
+* AV: Automatic/Sensors
+
+**Labeling Method**:
+* RoboVQA:  Hybrid:  Human,Automated
+* BridgeDataV2: Hybrid:  Human,Automated
+* AgiBot: Hybrid:  Human,Automated
+* RoboFail: Hybrid:  Human,Automated
+* HoloAssist: Hybrid:  Human,Automated
+* AV: Hybrid:  Human,Automated
+
+**Metrics**:
+We report the model accuracy on the embodied reasoning benchmark introduced in [Cosmos-Reason1](https://arxiv.org/abs/2503.15558). The results differ from those presented in Table 9 due to additional training aimed at supporting a broader range of Physical AI tasks beyond the benchmark.
+|                   | [RoboVQA](https://robovqa.github.io/)        | AV       | [BridgeDataV2](https://rail-berkeley.github.io/bridgedata/)| [Agibot](https://github.com/OpenDriveLab/AgiBot-World)| [HoloAssist](https://holoassist.github.io/)       | [RoboFail](https://robot-reflect.github.io/)                               | Average |
+|--------------------|---------------------------------------------|----------|------------------------------------------------------|------------------------------------------------|------------------------------------------------|------------------------------------------------|------------------------------------------------|
+| **Accuracy**        | 87.3                                        | 70.8    | 63.7                                                 | 48.9                                          | 62.7                                           | 57.2                                            |  65.1                                          |
+
+## Dataset Format
+Modality: Video (mp4) and Text
+
+## Dataset Quantification
+We release the embodied reasoning data and benchmarks. Each data sample is a pair of video and text. The text annotations include understanding and reasoning annotations described in the Cosmos-Reason1 paper. Each video may have multiple text annotations. The quantity of the video and text pairs is described in the table below.
+**The AV data is currently unavailable and will be uploaded soon!**
+
+|                   | [RoboVQA](https://robovqa.github.io/)        | AV       | [BridgeDataV2](https://rail-berkeley.github.io/bridgedata/)| [Agibot](https://github.com/OpenDriveLab/AgiBot-World)| [HoloAssist](https://holoassist.github.io/)       | [RoboFail](https://robot-reflect.github.io/)                               | Total Storage Size |
+|--------------------|---------------------------------------------|----------|------------------------------------------------------|------------------------------------------------|------------------------------------------------|------------------------------------------------|--------------------|
+| **SFT Data**        | 1.14m                                        | 24.7k    | 258k                                                 | 38.9k                                          | 273k                                           | N/A                                            | **300.6GB**         |
+| **RL Data**         | 252                                          | 200      | 240                                                  | 200                                            | 200                                            | N/A                                            | **2.6GB**           |
+| **Benchmark Data**  | 110                                          | 100      | 100                                                  | 100                                            | 100                                            | 100                                            | **1.5GB**           |
+
+
+
+We release text annotations for all embodied reasoning datasets and videos for RoboVQA and AV datasets. For other datasets, users may download the source videos from the original data source and find corresponding video sources via the video names. The held-out RoboFail benchmark is released for measuring the generalization capability.
+
+
+## Inference:
+**Acceleration Engine:** PyTorch, flash attention <br>
+**Test Hardware:** H100, A100, GB200 <br>
+* Minimum 2 GPU cards, multi nodes require Infiniband / ROCE connection <br>
+
+## Ethical Considerations
+
+NVIDIA believes Trustworthy AI is a shared responsibility and we have established policies and practices to enable development for a wide array of AI applications.  When downloaded or used in accordance with our terms of service, developers should work with their internal model team to ensure this model meets requirements for the relevant industry and use case and addresses unforeseen product misuse.
+
+Users are responsible for model inputs and outputs. Users are responsible for ensuring safe integration of this model, including implementing guardrails as well as other safety mechanisms, prior to deployment.
+
+For more detailed information on ethical considerations for this model, please see the subcards of Explainability, Bias, Safety & Security, and Privacy below. 
+
+Please report security vulnerabilities or NVIDIA AI Concerns [here](https://www.nvidia.com/en-us/support/submit-security-vulnerability/).
+
+### Plus Plus (++) Promise
+
+We value you, the datasets, the diversity they represent, and what we have been entrusted with. This model and its associated data have been:
+
+* Verified to comply with current applicable disclosure laws, regulations, and industry standards.
+* Verified to comply with applicable privacy labeling requirements.
+* Annotated to describe the collector/source (NVIDIA or a third-party).
+* Characterized for technical limitations.
+* Reviewed to ensure proper disclosure is accessible to, maintained for, and in compliance with NVIDIA data subjects and their requests.
+* Reviewed before release.
+* Tagged for known restrictions and potential safety implications.
+
+### Bias
+
+| Field                                                                                                                                                            | Response |
+| :--------------------------------------------------------------------------------------------------------------------------------------------------------------- | :------- |
+| Participation considerations from adversely impacted groups [protected classes](https://www.senate.ca.gov/content/protected-classes) in model design and testing: | None     |
+| Measures taken to mitigate against unwanted bias:                                                                                                                | The training video sources contain multiple physical embodiments and environments including human, car, single arm robot, bimanual robot in indoor and outdoor environments. By training on numerous and various physical interactions and curated datasets, we strive to provide a model that does not possess biases towards certain embodiments or environments.   |
+
+### Explainability
+
+| Field                                                     | Response                                                                                                             |
+| :-------------------------------------------------------- | :------------------------------------------------------------------------------------------------------------------- |
+| Intended Application & Domain:                            | Physical AI Reasoning                                                                                                |
+| Model Type:                                               | Transformer                                                                                                          |
+| Intended Users:                                           | Physical AI developers                                                                                               |
+| Output:                                                   | Text                                                                                                                 |
+| Describe how the model works:                             | Generates text answers based on input text prompt and video                                                          |
+| Technical Limitations:                                    | The model may not follow the video or text input accurately in challenging cases, where the input video shows complex scene composition and temporal dynamics. Examples of challenging scenes include: fast camera movements, overlapping human-object interactions, low lighting with high motion blur, and multiple people performing different actions simultaneously.  |
+| Verified to have met prescribed NVIDIA quality standards: | Yes                                                                                                                  |
+| Performance Metrics:                                      | Quantitative and Qualitative Evaluation. Cosmos-Reason1 proposes the embodied reasoning benchmark and physical common sense benchmark to evaluate accuracy with visual question answering.                                                                              |
+| Potential Known Risks:                                    | The model's output can generate all forms of texts, including what may be considered toxic, offensive, or indecent.  |
+| Licensing:                                                | [NVIDIA Open Model License](https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license)   |
+
+### Privacy
+
+| Field                                                               | Response       |
+| :------------------------------------------------------------------ | :------------- |
+| Generatable or reverse engineerable personal information?           | None Known     |
+| Protected class data used to create this model?                     | None Known     |
+| Was consent obtained for any personal data used?                    | None Known     |
+| How often is dataset reviewed?                                      | Before Release |
+| Is there provenance for all datasets used in training?              | Yes            |
+| Does data labeling (annotation, metadata) comply with privacy laws? | Yes            |
+| Applicable Privacy Policy | [NVIDIA Privacy Policy](https://www.nvidia.com/en-us/about-nvidia/privacy-policy)            |
+
+
+### Safety
+
+| Field                                           | Response                                                                                                                                                                                                                                                                                                                             |
+| :---------------------------------------------- | :----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| Model Application(s):                           | Physical AI common sense understanding and embodied reasoning                                                                                                                                                                                                                                                                                                                     |
+| Describe the life critical impact (if present). | None Known                                                                                                                                                                                                                                                                                                                           |
+| Use Case Restrictions:                          | [NVIDIA Open Model License](https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license)                                                                                                                                                                                                                   |
+| Model and dataset restrictions:                 | The Principle of least privilege (PoLP) is applied limiting access for dataset generation and model development.  Restrictions enforce dataset access during training, and dataset license constraints adhered to. Model checkpoints are made available on Hugging Face, and may become available on cloud providers' model catalog. |

config.json

@@ -0,0 +1,106 @@
+{
+  "architectures": [
+    "Qwen2_5_VLForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "image_token_id": 151655,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 128000,
+  "max_window_layers": 28,
+  "model_type": "qwen2_5_vl",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "pad_token_id": 151654,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": {
+    "mrope_section": [
+      16,
+      24,
+      24
+    ],
+    "rope_type": "default",
+    "type": "default"
+  },
+  "rope_theta": 1000000.0,
+  "sliding_window": 32768,
+  "text_config": {
+    "architectures": [
+      "Qwen2_5_VLForConditionalGeneration"
+    ],
+    "attention_dropout": 0.0,
+    "bos_token_id": 151643,
+    "eos_token_id": 151645,
+    "hidden_act": "silu",
+    "hidden_size": 3584,
+    "image_token_id": null,
+    "initializer_range": 0.02,
+    "intermediate_size": 18944,
+    "max_position_embeddings": 128000,
+    "max_window_layers": 28,
+    "model_type": "qwen2_5_vl_text",
+    "num_attention_heads": 28,
+    "num_hidden_layers": 28,
+    "num_key_value_heads": 4,
+    "rms_norm_eps": 1e-06,
+    "rope_scaling": {
+      "mrope_section": [
+        16,
+        24,
+        24
+      ],
+      "rope_type": "default",
+      "type": "default"
+    },
+    "rope_theta": 1000000.0,
+    "sliding_window": 32768,
+    "torch_dtype": "bfloat16",
+    "use_cache": true,
+    "use_sliding_window": false,
+    "video_token_id": null,
+    "vision_end_token_id": 151653,
+    "vision_start_token_id": 151652,
+    "vision_token_id": 151654,
+    "vocab_size": 152064
+  },
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.52.3",
+  "unsloth_fixed": true,
+  "use_cache": true,
+  "use_sliding_window": false,
+  "video_token_id": 151656,
+  "vision_config": {
+    "depth": 32,
+    "fullatt_block_indexes": [
+      7,
+      15,
+      23,
+      31
+    ],
+    "hidden_act": "silu",
+    "hidden_size": 1280,
+    "in_channels": 3,
+    "in_chans": 3,
+    "initializer_range": 0.02,
+    "intermediate_size": 3420,
+    "model_type": "qwen2_5_vl",
+    "num_heads": 16,
+    "out_hidden_size": 3584,
+    "patch_size": 14,
+    "spatial_merge_size": 2,
+    "spatial_patch_size": 14,
+    "temporal_patch_size": 2,
+    "tokens_per_second": 2,
+    "torch_dtype": "bfloat16",
+    "window_size": 112
+  },
+  "vision_end_token_id": 151653,
+  "vision_start_token_id": 151652,
+  "vision_token_id": 151654,
+  "vocab_size": 152064
+}

mmproj-F16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99c1280818185003a50306c1146d80ca04a67fea3974db38dcac6aa3767b9477
+size 1354164320

mmproj-F32.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:703d0ff0c7d0593952aeacd01b4deb8e11e1f1cc62f0db65f8f9f06485ee817e
+size 2703222880