zsxkib/molmo-7b

allenai/Molmo-7B-D-0924, Answers questions and caption about images

Capabilities

Reference ImagesMax TokensTop-P

Community model (estimated from hardware time)

Name	Type	Description	Default	Constraints
`image`*	string(uri)	Input image	`—`	—
`text`*	string	Text prompt or question about the image	`—`	—
`length_penalty`	number	Exponential penalty to the length (values < 1.0 encourage shorter outputs, > 1.0 encourage longer outputs)	`1`	min: 0.1, max: 2
`max_new_tokens`	integer	Maximum number of new tokens to generate	`200`	min: 1, max: 1000
`temperature`	number	Randomness in token selection (higher values increase randomness)	`1`	min: 0.1, max: 2
`top_k`	integer	Number of highest probability vocabulary tokens to keep for top-k-filtering	`50`	min: 1, max: 100
`top_p`	number	Cumulative probability for top-p-filtering	`1`	min: 0, max: 1

imagerequiredstring

Input image

textrequiredstring

Text prompt or question about the image

length_penaltynumber

Exponential penalty to the length (values < 1.0 encourage shorter outputs, > 1.0 encourage longer outputs)

Default: 1min: 0.1, max: 2

max_new_tokensinteger

Maximum number of new tokens to generate

Default: 200min: 1, max: 1000

temperaturenumber

Randomness in token selection (higher values increase randomness)

Default: 1min: 0.1, max: 2

top_kinteger

Number of highest probability vocabulary tokens to keep for top-k-filtering

Default: 50min: 1, max: 100

top_pnumber

Cumulative probability for top-p-filtering

Default: 1min: 0, max: 1

Version: 76ebd7008642Updated: 7/25/20261.3M runs