Cosmos
nvidia
harrim-nv commited on
Commit
a3ea692
·
verified ·
1 Parent(s): 2f0b7fe

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +13 -2
README.md CHANGED
@@ -100,10 +100,13 @@ extra_gated_button_content: Submit
100
  Cosmos-UpsamplePrompt1-12B-Transfer is a multimodal model designed to transform original input prompts into more detailed and enriched versions based on the control video. It improves the prompts by adding more details and maintaining a consistent description structure before they are used in a conditional world generation model, which generally leads to higher quality outputs. This model is ready for commercial use.
101
 
102
  ### License:
103
- 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).
104
 
 
105
  Additional Information: [Apache License Version 2.0](https://huggingface.co/datasets/choosealicense/licenses/blob/main/markdown/apache-2.0.md).
106
 
 
 
107
  Under the NVIDIA Open Model License, NVIDIA confirms:
108
 
109
  * Models are commercially usable.
@@ -114,6 +117,13 @@ Under the NVIDIA Open Model License, NVIDIA confirms:
114
  associated safety guardrail hyperparameter, encryption, security, digital rights management, or authentication mechanism contained
115
  in the Model, your rights under [NVIDIA Open Model License Agreement](https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license) will automatically terminate.
116
 
 
 
 
 
 
 
 
117
  ## Model Architecture:
118
  **Architecture Type:** Transformer <br>
119
  **Network Architecture:** [Pixtral 12B](https://huggingface.co/mistralai/Pixtral-12B-2409) <br>
@@ -138,6 +148,7 @@ in the Model, your rights under [NVIDIA Open Model License Agreement](https://ww
138
  **Supported Hardware Microarchitecture Compatibility:** <br>
139
  * NVIDIA Ampere <br>
140
  * NVIDIA Hopper <br>
 
141
  **Supported Operating System(s):** Linux <br>
142
 
143
  ## Model Version:
@@ -192,7 +203,7 @@ Technical Limitations:
192
  Verified to have met prescribed NVIDIA quality standards: | Yes
193
  Performance Metrics: | Human Evaluation
194
  Potential Known Risks: | The model's output can generate all forms of text, including what may be considered toxic, offensive, or indecent.
195
- Licensing: | [NVIDIA Open Model License](https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license). Additional Information: [Apache License Version 2.0](https://huggingface.co/datasets/choosealicense/licenses/blob/main/markdown/apache-2.0.md).
196
 
197
 
198
  ### Privacy
 
100
  Cosmos-UpsamplePrompt1-12B-Transfer is a multimodal model designed to transform original input prompts into more detailed and enriched versions based on the control video. It improves the prompts by adding more details and maintaining a consistent description structure before they are used in a conditional world generation model, which generally leads to higher quality outputs. This model is ready for commercial use.
101
 
102
  ### License:
103
+ GOVERNING TERMS: Use of this model is governed by the NVIDIA Open Model License Agreement. Additional Information: Apache License Version 2.0.
104
 
105
+ GOVERNING TERMS: Use of this model is governed by the [NVIDIA Open Model License](https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license).
106
  Additional Information: [Apache License Version 2.0](https://huggingface.co/datasets/choosealicense/licenses/blob/main/markdown/apache-2.0.md).
107
 
108
+ For a custom license, please contact [[email protected]](mailto:[email protected]).
109
+
110
  Under the NVIDIA Open Model License, NVIDIA confirms:
111
 
112
  * Models are commercially usable.
 
117
  associated safety guardrail hyperparameter, encryption, security, digital rights management, or authentication mechanism contained
118
  in the Model, your rights under [NVIDIA Open Model License Agreement](https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license) will automatically terminate.
119
 
120
+ ### Deployment Geography:
121
+ Global
122
+ ### Use Case:
123
+ It improves the prompts by adding more details and maintaining a consistent description structure before they are used in a conditional world generation model, which generally leads to higher quality outputs. Intended for research and development purposes.
124
+ ### Release Date:
125
+ Hugging Face 03/18/2025 via [https://huggingface.co/nvidia/Cosmos-UpsamplePrompt1-12B-Transfer](https://huggingface.co/nvidia/Cosmos-UpsamplePrompt1-12B-Transfer)
126
+
127
  ## Model Architecture:
128
  **Architecture Type:** Transformer <br>
129
  **Network Architecture:** [Pixtral 12B](https://huggingface.co/mistralai/Pixtral-12B-2409) <br>
 
148
  **Supported Hardware Microarchitecture Compatibility:** <br>
149
  * NVIDIA Ampere <br>
150
  * NVIDIA Hopper <br>
151
+
152
  **Supported Operating System(s):** Linux <br>
153
 
154
  ## Model Version:
 
203
  Verified to have met prescribed NVIDIA quality standards: | Yes
204
  Performance Metrics: | Human Evaluation
205
  Potential Known Risks: | The model's output can generate all forms of text, including what may be considered toxic, offensive, or indecent.
206
+ Licensing: | Abide by [NVIDIA Open Model License](https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license). Additional Information: [Apache License Version 2.0](https://huggingface.co/datasets/choosealicense/licenses/blob/main/markdown/apache-2.0.md).
207
 
208
 
209
  ### Privacy