You're looking at a specific version of this model. Jump to the model overview.
paragekbote /gemma3-torchao-quant-sparse:ee0d1f2a
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 |
|---|---|---|---|
| prompt |
string
|
Input text prompt
|
|
| image_url |
string
|
Optional image URL
|
|
| max_new_tokens |
integer
|
128
Min: 1 Max: 2500 |
Maximum number of new tokens
|
| temperature |
number
|
0.7
Max: 2 |
Sampling temperature
|
| top_p |
number
|
0.9
Max: 1 |
Top-p nucleus sampling
|
| seed |
integer
|
42
|
Seed for reproducibility
|
| use_quantization |
string
|
true
|
Enable INT8 quantization using torchao
|
| use_sparsity |
string
|
false
|
Enable sparsity optimization using torchao
|
| sparsity_type |
string
|
magnitude
|
Type of sparsity
|
| sparsity_ratio |
number
|
0.3
Max: 0.8 |
None
|
Output schema
The shape of the response you’ll get when you run this model with an API.
Schema
{'title': 'Output', 'type': 'string'}