jyoung105 / imp

a family of multimodal small language models

  • Public
  • 70 runs
  • GitHub
  • License
Iterate in playground

Input

image
*file

Input image

*string
Shift + Return to add a new line

Input prompt

integer

Maximum number of tokens to generate

Default: 100

number

Temperature for sampling

Default: 0.7

number

Top p for sampling

Default: 0.95

Output

The Little Book of Deep Learning
Generated in

Run time and cost

This model costs approximately $0.10 to run on Replicate, or 10 runs per $1, but this varies depending on your inputs. It is also open source and you can run it on your own computer with Docker.

This model runs on Nvidia L40S GPU hardware. Predictions typically complete within 105 seconds.

Readme

This model doesn't have a readme.