Define Models

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

required

Internal name of your AI model. Used for indicating the model to use in an API call.

task

string

required

Training intent of model, such as classification or embedding.

sourceModel

string

required

Relative path of model within provider.

provider

string

required

Source location of model, such as hugging-face or openai.

host

string

required

Runtime provider of model.

Show host types

hypermode

string

Dynamically deployed models on Hypermode.

custom

string

Fine-tuned models on Hypermode.

...

string

Name of a project-defined host.

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.