jaaari/gemma-2-ataraxy-antislop:3f5a1f3a – Run with an API on Replicate

Version

You're looking at a specific version of this model. Jump to the model overview.

jaaari /gemma-2-ataraxy-antislop:3f5a1f3a

Playground API Setup logs

Input

prompt

*string

Shift + Return to add a new line

Text prompt to generate completion for

max_new_tokens

integer

(minimum: 1, maximum: 2048)

Maximum number of tokens to generate

Default: 512

temperature

number

(minimum: 0.1, maximum: 2)

Sampling temperature; higher values make output more random, lower values more deterministic

Default: 0.7

top_p

number

(minimum: 0, maximum: 1)

Nucleus sampling probability threshold

Default: 0.9

top_k

integer

(minimum: 0)

Top-k sampling threshold

Default: 50

min_p

number

(minimum: 0, maximum: 1)

Minimum probability threshold for sampling

Default: 0.05

slop_phrases

List of [phrase, adjustment] pairs for slop control. Example: [["a testament to", "0.3"], ["tapestry of", "0.1"]]

adjustment_strength

number

(minimum: 0)

Strength of slop adjustments

Default: 20

antislop_enabled

boolean

Enable AntiSlop functionality

Default: true

enforce_json

boolean

Enforce JSON formatting in output

Default: false

regex_bans

string[]

List of regex patterns to ban in generation

Run this model in Node.js with one line of code:

npx create-replicate --model=jaaari/gemma-2-ataraxy-antislop

or set up a project from scratch

Install Replicate’s Node.js client library:

npm install replicate

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Import and set up the client:

import Replicate from "replicate";

const replicate = new Replicate({
  auth: process.env.REPLICATE_API_TOKEN,
});

Run jaaari/gemma-2-ataraxy-antislop using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "jaaari/gemma-2-ataraxy-antislop:3f5a1f3af40f942ac8bc5978c6cc60afb0ac929f41cf63d0599c4804a74eadd4",
  {
    input: {
      min_p: 0.05,
      top_k: 50,
      top_p: 0.9,
      temperature: 0.7,
      enforce_json: false,
      max_new_tokens: 512,
      antislop_enabled: true,
      adjustment_strength: 20
    }
  }
);

console.log(output);

To learn more, take a look at the guide on getting started with Node.js.

Install Replicate’s Python client library:

pip install replicate

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Import the client:

import replicate

Run jaaari/gemma-2-ataraxy-antislop using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "jaaari/gemma-2-ataraxy-antislop:3f5a1f3af40f942ac8bc5978c6cc60afb0ac929f41cf63d0599c4804a74eadd4",
    input={
        "min_p": 0.05,
        "top_k": 50,
        "top_p": 0.9,
        "temperature": 0.7,
        "enforce_json": False,
        "max_new_tokens": 512,
        "antislop_enabled": True,
        "adjustment_strength": 20
    }
)
print(output)

To learn more, take a look at the guide on getting started with Python.

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Run jaaari/gemma-2-ataraxy-antislop using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

curl -s -X POST \
  -H "Authorization: Bearer $REPLICATE_API_TOKEN" \
  -H "Content-Type: application/json" \
  -H "Prefer: wait" \
  -d $'{
    "version": "3f5a1f3af40f942ac8bc5978c6cc60afb0ac929f41cf63d0599c4804a74eadd4",
    "input": {
      "min_p": 0.05,
      "top_k": 50,
      "top_p": 0.9,
      "temperature": 0.7,
      "enforce_json": false,
      "max_new_tokens": 512,
      "antislop_enabled": true,
      "adjustment_strength": 20
    }
  }' \
  https://api.replicate.com/v1/predictions

To learn more, take a look at Replicate’s HTTP API reference docs.

Output

No output yet! Press "Submit" to start a prediction.