jaaari
/
gemma-2-ataraxy-antislop
- Public
- 9 runs
Run jaaari/gemma-2-ataraxy-antislop with an API
Use one of our client libraries to get started quickly. Clicking on a library will take you to the Playground tab where you can tweak different inputs, see the results, and copy the corresponding code to use in your own project.
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
|
Text prompt to generate completion for
|
|
| max_new_tokens |
integer
|
512
Min: 1 Max: 2048 |
Maximum number of tokens to generate
|
| temperature |
number
|
0.7
Min: 0.1 Max: 2 |
Sampling temperature; higher values make output more random, lower values more deterministic
|
| top_p |
number
|
0.9
Max: 1 |
Nucleus sampling probability threshold
|
| top_k |
integer
|
50
|
Top-k sampling threshold
|
| min_p |
number
|
0.05
Max: 1 |
Minimum probability threshold for sampling
|
| slop_phrases |
array
|
List of [phrase, adjustment] pairs for slop control. Example: [["a testament to", "0.3"], ["tapestry of", "0.1"]]
|
|
| adjustment_strength |
number
|
100
|
Strength of the slop adjustments (0 to disable, 100+ for strong effect)
|
| antislop_enabled |
boolean
|
True
|
Enable AntiSlop functionality
|
| enforce_json |
boolean
|
False
|
Enforce JSON formatting in output
|
| regex_bans |
array
|
List of regex patterns to ban in generation
|
{
"type": "object",
"title": "Input",
"required": [
"prompt"
],
"properties": {
"min_p": {
"type": "number",
"title": "Min P",
"default": 0.05,
"maximum": 1,
"minimum": 0,
"x-order": 5,
"description": "Minimum probability threshold for sampling"
},
"top_k": {
"type": "integer",
"title": "Top K",
"default": 50,
"minimum": 0,
"x-order": 4,
"description": "Top-k sampling threshold"
},
"top_p": {
"type": "number",
"title": "Top P",
"default": 0.9,
"maximum": 1,
"minimum": 0,
"x-order": 3,
"description": "Nucleus sampling probability threshold"
},
"prompt": {
"type": "string",
"title": "Prompt",
"x-order": 0,
"description": "Text prompt to generate completion for"
},
"regex_bans": {
"type": "array",
"items": {
"type": "string"
},
"title": "Regex Bans",
"x-order": 10,
"description": "List of regex patterns to ban in generation"
},
"temperature": {
"type": "number",
"title": "Temperature",
"default": 0.7,
"maximum": 2,
"minimum": 0.1,
"x-order": 2,
"description": "Sampling temperature; higher values make output more random, lower values more deterministic"
},
"enforce_json": {
"type": "boolean",
"title": "Enforce Json",
"default": false,
"x-order": 9,
"description": "Enforce JSON formatting in output"
},
"slop_phrases": {
"type": "array",
"items": {
"type": "array",
"items": {
"type": "string"
}
},
"title": "Slop Phrases",
"x-order": 6,
"description": "List of [phrase, adjustment] pairs for slop control. Example: [[\"a testament to\", \"0.3\"], [\"tapestry of\", \"0.1\"]]"
},
"max_new_tokens": {
"type": "integer",
"title": "Max New Tokens",
"default": 512,
"maximum": 2048,
"minimum": 1,
"x-order": 1,
"description": "Maximum number of tokens to generate"
},
"antislop_enabled": {
"type": "boolean",
"title": "Antislop Enabled",
"default": true,
"x-order": 8,
"description": "Enable AntiSlop functionality"
},
"adjustment_strength": {
"type": "number",
"title": "Adjustment Strength",
"default": 100,
"minimum": 0,
"x-order": 7,
"description": "Strength of the slop adjustments (0 to disable, 100+ for strong effect)"
}
}
}
Output schema
The shape of the response you’ll get when you run this model with an API.
Schema
{
"type": "string",
"title": "Output"
}