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
|
Image to discuss
|
|
| prompt |
string
|
Prompt for mini-gpt4 regarding input image
|
|
| num_beams |
integer
|
3
Min: 1 Max: 10 |
Number of beams for beam search decoding
|
| temperature |
number
|
1
Min: 0.01 Max: 2 |
Temperature for generating tokens, lower = more predictable results
|
| top_p |
number
|
0.9
Max: 1 |
Sample from the top p percent most likely tokens
|
| repetition_penalty |
number
|
1
Min: 0.01 Max: 5 |
Penalty for repeated words in generated text; 1 is no penalty, values greater than 1 discourage repetition, less than 1 encourage it.
|
| max_new_tokens |
integer
|
3000
Min: 1 |
Maximum number of new tokens to generate
|
| max_length |
integer
|
4000
Min: 1 |
Total length of prompt and output in tokens
|
Output schema
The shape of the response you’ll get when you run this model with an API.
Schema
{'title': 'Output', 'type': 'string'}