Image-Text-to-Text
Transformers
Safetensors
Cosmos
English
qwen2_5_vl
image-to-text
nvidia
conversational
text-generation-inference
harrim-nv commited on
Commit
4b2bdaa
·
verified ·
1 Parent(s): 25940bb

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +5 -3
README.md CHANGED
@@ -48,7 +48,9 @@ The Cosmos-Reason1 includes the following model:
48
 
49
  ### License:
50
 
51
- 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 [cosmos-license@nvidia.com](mailto:cosmos-license@nvidia.com).
 
 
52
 
53
  Under the NVIDIA Open Model License, NVIDIA confirms:
54
 
@@ -356,7 +358,7 @@ We value you, the datasets, the diversity they represent, and what we have been
356
  | Verified to have met prescribed NVIDIA quality standards: | Yes |
357
  | 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. |
358
  | Potential Known Risks: | The model's output can generate all forms of texts, including what may be considered toxic, offensive, or indecent. |
359
- | Licensing: | [NVIDIA Open Model License](https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license) |
360
 
361
  ### Privacy
362
 
@@ -377,6 +379,6 @@ We value you, the datasets, the diversity they represent, and what we have been
377
  | :---------------------------------------------- | :----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
378
  | Model Application(s): | Physical AI common sense understanding and embodied reasoning |
379
  | Describe the life critical impact (if present). | None Known |
380
- | Use Case Restrictions: | [NVIDIA Open Model License](https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license) |
381
  | 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. |
382
 
 
48
 
49
  ### License:
50
 
51
+ This model is released under the [NVIDIA Open Model License](https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license). Additional Information: [Apache License 2.0](https://huggingface.co/datasets/choosealicense/licenses/blob/main/markdown/apache-2.0.md).
52
+
53
+ For a custom license, please contact [[email protected]](mailto:[email protected]).
54
 
55
  Under the NVIDIA Open Model License, NVIDIA confirms:
56
 
 
358
  | Verified to have met prescribed NVIDIA quality standards: | Yes |
359
  | 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. |
360
  | Potential Known Risks: | The model's output can generate all forms of texts, including what may be considered toxic, offensive, or indecent. |
361
+ | Licensing: | [NVIDIA Open Model License](https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license). Additional Information: [Apache License 2.0](https://huggingface.co/datasets/choosealicense/licenses/blob/main/markdown/apache-2.0.md). |
362
 
363
  ### Privacy
364
 
 
379
  | :---------------------------------------------- | :----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
380
  | Model Application(s): | Physical AI common sense understanding and embodied reasoning |
381
  | Describe the life critical impact (if present). | None Known |
382
+ | Use Case Restrictions: | [NVIDIA Open Model License](https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license). Additional Information: [Apache License 2.0](https://huggingface.co/datasets/choosealicense/licenses/blob/main/markdown/apache-2.0.md). |
383
  | 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. |
384