You're looking at a specific version of this model. Jump to the model overview.
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 |
|---|---|---|---|
| image |
string
|
Input image
|
|
| question |
string
|
What is shown in the image?
|
Question to ask about this image
|
| context |
string
|
Optional - previous questions and answers to be used as context for answering current question
|
|
| caption |
boolean
|
False
|
Select if you want to generate image captions instead of asking questions
|
| system_prompt |
string
|
A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.
|
System prompt
|
| max_new_tokens |
integer
|
768
Min: 1 Max: 2048 |
Maximum number of new tokens to generate
|
| num_beams |
integer
|
1
Min: 1 Max: 10 |
Number of beams for beam search
|
| temperature |
number
|
1
Min: 0.5 Max: 1 |
Temperature for use with nucleus sampling
|
| top_k |
integer
|
50
Min: 1 |
The number of highest probability vocabulary tokens to keep for top-k sampling
|
| top_p |
number
|
1
Max: 1 |
The cumulative probability threshold for top-p sampling
|
| repetition_penalty |
number
|
1
|
The parameter for repetition penalty
|
| length_penalty |
number
|
1
|
The parameter for length penalty
|
| do_sample |
boolean
|
False
|
Whether to use sampling or not
|
Output schema
The shape of the response you’ll get when you run this model with an API.
Schema
{'title': 'Output', 'type': 'string'}