joehoover
/
bart-large-mnli
Zero-shot classification document classification with a light-weight model.
Run joehoover/bart-large-mnli with an API
Use one of our client libraries to get started quickly. Clicking on a library will take you to the Playground tab where you can tweak different inputs, see the results, and copy the corresponding code to use in your own project.
Input schema
The fields you can use to run this model with an API. If you don't give a value for a field its default value will be used.
Field | Type | Default value | Description |
---|---|---|---|
input |
string
|
Replicate, I think I might...like you a lot!
|
Text sequence to classify.
|
class_labels |
string
|
positive, negative, neutral
|
Class names. Must be a comma-delimited string of labels.
|
multi_label |
boolean
|
False
|
If True, then class scores are independent.
|
hypothesis_template |
string
|
This example is {}.
|
Hypothesis into which class labels are piped. Must contain '{}'.
|
{
"type": "object",
"title": "Input",
"properties": {
"input": {
"type": "string",
"title": "Input",
"default": "Replicate, I think I might...like you a lot!",
"x-order": 0,
"description": "Text sequence to classify."
},
"multi_label": {
"type": "boolean",
"title": "Multi Label",
"default": false,
"x-order": 2,
"description": "If True, then class scores are independent."
},
"class_labels": {
"type": "string",
"title": "Class Labels",
"default": "positive, negative, neutral",
"x-order": 1,
"description": "Class names. Must be a comma-delimited string of labels."
},
"hypothesis_template": {
"type": "string",
"title": "Hypothesis Template",
"default": "This example is {}.",
"x-order": 3,
"description": "Hypothesis into which class labels are piped. Must contain '{}'."
}
}
}
Output schema
The shape of the response you’ll get when you run this model with an API.
Schema
{
"type": "object",
"title": "Output"
}