You're looking at a specific version of this model. Jump to the model overview.

yoadtew /arithmetic:737d4915

Playground API

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
image1
string
Final result will be: image1 + (image2 - image3)
image2
string
Final result will be: image1 + (image2 - image3)
image3
string
Final result will be: image1 + (image2 - image3)
cond_text
string
Image of a
conditional text
beam_size
integer
3

Min: 1

Max: 10

Number of beams to use
end_factors
number
1.06

Min: 1.0

Max: 1.1

Higher value for shorter captions
max_seq_lengths
integer
3

Min: 1

Max: 20

Maximum number of tokens to generate
ce_loss_scale
number
0.2

Max: 0.6

Scale of cross-entropy loss with un-shifted language model

Output schema

The shape of the response you’ll get when you run this model with an API.

Schema 
{'items': {'properties': {'file': {'format': 'uri',
                                   'type': 'string',
                                   'x-order': 0},
                          'text': {'type': 'string', 'x-order': 1}},
           'type': 'object'},
 'type': 'array',
 'x-cog-array-type': 'iterator'}