Configure Project
Define Models
Try a new model with a few lines of code
AI models are a core resource for inferencing. The project manifest allows you to easily define models whether hosted by Hypermode or another host.
hypermode.json
{
"models": [
{
"name": "sentiment-classifier",
"task": "classification",
"sourceModel": "distilbert/distilbert-base-uncased-finetuned-sst-2-english",
"provider": "hugging-face",
"host": "hypermode"
}
]
}
Properties
name
string
requiredInternal name of your AI model. Used for indicating the model to use in an API call.
task
string
requiredTraining intent of model, such as classification
or embedding
.
sourceModel
string
requiredRelative path of model within provider.
provider
string
requiredSource location of model, such as hugging-face
or openai
.
host
string
requiredRuntime provider of model.
Auto-deployed models
When using hugging-face
as the provider
and hypermode
as the host
, Hypermode automatically deploys a dedicated instance of the defined sourceModel
when deploying your project. Your project’s functions securely connect to the hosted model, with no further configuration required.