Model Cards
What is Model Card?
Model card is a file that accompany the models, which is a Markdown file, with a YAML section at the top that contains metadata about the model. A model repository will render its README.md as a model card. The model card includes key information of the model. It can help users better understand and use your model correctly. We recommend that you create your model card according to the model card specification.
What Information Should be Included in the Model Card?
The model card should describe:
- Model Name
- Model Overview: Include model features and structure.
- Usage: Provide detailed examples and code to illustrate the use of the model as much as possible. Introduce and explain the model operation environment, how to perform model inference and tuning.
- Scenarios: Describe the target scenarios, intended uses, and potential limitations of the model.
- Training Data: Describe what datasets and training parameters were used.
- Training Process: The specific training process.
- Model Evaluation Results: Demonstrate the performance evaluation results of the model.
Model Card Metadata
Model card is composed of YAML metadata and Markdown text content. You can add metadata by editing the YAML section of the README.md file, separated by three "---". Markdown text shows the model information and related descriptions.
You can refer to the following template to create your model card.
---
# License
license: apache-2.0
# User-defined tags
tags:
- image-classification
- customize tags
---
<!--- The above is in YAML format, providing license and task descriptions--->
<!--- The following is the model description in markdown format--->
# Model name
Introduce general information of the model
## Model details
### Model description
Describe the model, including the developer, model type, framework, related language, and the license.
## Usage
### How to use
Describe how the model is used.
## Risks and limitations
Describe the risks and limitations of the model
### Recommendations
Recommendations for users
## How to get started with models
Introduce how to get started with the model
## Training details
### Training data
Introduce the training data for the model
### Training process
Introduce the training process of the model
## Evaluation
### Test data, factors, and metrics
#### Test Data
Introduce the test data used
#### Factors
Describe the environment and conditions associated with the test
#### Metrics
Introduce the metrics used to test the model
### Results
#### Summary of results
Introduce test results of the model
Supported Model Tags
| Task |
|---|
| image-classification |
| image-segmentation |
| ocr |
| skin-retouching |
| image-to-image |
| video-detection |
| video-segmentation |
| video-generation |
| video-captioning |
| face-detection |
| face-recognition |
| face-image-generation |
| image-object-detection |
| image-super-resolution |
| action-detection |
| semantic-segmentation |
| word-segmentation |
| named-entity-recognition |
| part-of-speech |
| document-segmentation |
| text-classification |
| sentiment-classification |
| nli |
| conversational |
| translation |
| text-generation |
| text-summarization |
| feature-extraction |
| relation-extraction |
| auto-speech-recognition |
| text-to-speech |
| audio-classification |
| text-to-image |
| visual-question-answering |
| image-text-retrieval |
Supported Industry Tags
| Task |
|---|
| Automotive |
| Manufacturing |
| Energy |
| Telecommunications and Electronic Information |
| Transportation and Logistics |
| Construction and Real Estate |
| Financial Services |
| Agriculture |
| Chemical Industry |
| Environmental Protection |
| Healthcare and Medical Services |
| Education and Training |
| Food and Beverage |
| Retail and Consumer Goods |
| Tourism and Hospitality |
| Information Technology (IT) |
| Culture and Entertainment |