@huggingface/tasks/src/tasks/token-classification/spec/input.json

List of ML tasks for huggingface.co/tasks

{
	"$id": "/inference/schemas/token-classification/input.json",
	"$schema": "http://json-schema.org/draft-06/schema#",
	"description": "Inputs for Token Classification inference",
	"title": "TokenClassificationInput",
	"type": "object",
	"properties": {
		"inputs": {
			"description": "The input text data",
			"type": "string"
		},
		"parameters": {
			"description": "Additional inference parameters for Token Classification",
			"$ref": "#/$defs/TokenClassificationParameters"
		}
	},
	"$defs": {
		"TokenClassificationParameters": {
			"title": "TokenClassificationParameters",
			"type": "object",
			"properties": {
				"ignore_labels": {
					"type": "array",
					"items": {
						"type": "string"
					},
					"description": "A list of labels to ignore"
				},
				"stride": {
					"type": "integer",
					"description": "The number of overlapping tokens between chunks when splitting the input text."
				},
				"aggregation_strategy": {
					"title": "TokenClassificationAggregationStrategy",
					"type": "string",
					"description": "The strategy used to fuse tokens based on model predictions",
					"oneOf": [
						{
							"const": "none",
							"description": "Do not aggregate tokens"
						},
						{
							"const": "simple",
							"description": "Group consecutive tokens with the same label in a single entity."
						},
						{
							"const": "first",
							"description": "Similar to \"simple\", also preserves word integrity (use the label predicted for the first token in a word)."
						},
						{
							"const": "average",
							"description": "Similar to \"simple\", also preserves word integrity (uses the label with the highest score, averaged across the word's tokens)."
						},
						{
							"const": "max",
							"description": "Similar to \"simple\", also preserves word integrity (uses the label with the highest score across the word's tokens)."
						}
					]
				}
			}
		}
	},
	"required": ["inputs"]
}