Carton

QuickstartDocsModels

facebook / bart-large-mnli

BART Large MNLI is a model that can do zero shot classificiation.

Examples

quickstart

Inputs

Name: candidate_labels

Name: input

Name: max_length

Outputs

Name: scores

Usage

Inputs

Name: input

Description: The strings to classifiy

Type: string

Shape: [N]

Name: candidate_labels

Description: The candidate labels

Type: string

Shape: [L]

Name: template

Description: An optional template string for the model to use. Defaults to 'This example is about {}.'

Type: string

Shape: Scalar

Name: max_length

Description: An optional max_length to pass to the model. Defaults to 128.

Type: uint32

Shape: Scalar

Outputs

Name: scores

Description: Scores between 0 and 1 for each element of `input` for each label in `candidate_labels`

Type: string

Shape: [N, L]

Readme

See here for more details.

Note: This model performs multi-label classification (i.e. zero or more labels may be true for each input).

Get it

Copy the model URL:

https://carton.pub/facebook/bart-large-mnli/98424a1e2ab50e5b228cdc5c10e07d325e063a1e06771644dde71049eb9ce3de
This model has quickstart code available for every supported language.

Homepage

https://huggingface.co/facebook/bart-large-mnli

License

MIT

Tasks

nlp/zero-shot-classification