google-deepmind/gemma2-9b-it:24464993 – Run with an API on Replicate

Version

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

google-deepmind /gemma2-9b-it:24464993

Playground API

Input

prompt

string

Shift + Return to add a new line

Prompt to send to the model.

Default: "Write me a poem about Machine Learning."

max_new_tokens

integer

(minimum: 1, maximum: 2048)

Maximum number of tokens to generate. A word is generally 2-3 tokens

Default: 1024

temperature

number

(minimum: 0.1, maximum: 4)

Adjusts randomness of outputs, greater than 1 is random and 0 is deterministic, 0.75 is a good starting value.

Default: 0.6

top_p

number

(minimum: 0.05, maximum: 1)

When decoding text, samples from the top p percentage of most likely tokens; lower to ignore less likely tokens

Default: 0.9

top_k

integer

(minimum: 1, maximum: 1000)

When decoding text, samples from the top k most likely tokens; lower to ignore less likely tokens

Default: 50

repetition_penalty

number

(minimum: 0)

A parameter that controls how repetitive text can be. Lower means more repetitive, while higher means less repetitive. Set to 1.0 to disable.

Default: 1.2

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

npx create-replicate --model=google-deepmind/gemma2-9b-it

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 google-deepmind/gemma2-9b-it using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "google-deepmind/gemma2-9b-it:24464993111a1b52b2ebcb2a88c76090a705950644dca3a3955ee40d80909f2d",
  {
    input: {
      top_k: 50,
      top_p: 0.9,
      prompt: "Write me a poem about Machine Learning.",
      temperature: 0.6,
      max_new_tokens: 512,
      repetition_penalty: 1.2
    }
  }
);

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 google-deepmind/gemma2-9b-it using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "google-deepmind/gemma2-9b-it:24464993111a1b52b2ebcb2a88c76090a705950644dca3a3955ee40d80909f2d",
    input={
        "top_k": 50,
        "top_p": 0.9,
        "prompt": "Write me a poem about Machine Learning.",
        "temperature": 0.6,
        "max_new_tokens": 512,
        "repetition_penalty": 1.2
    }
)

# The google-deepmind/gemma2-9b-it model can stream output as it's running.
# The predict method returns an iterator, and you can iterate over that output.
for item in output:
    # https://replicate.com/google-deepmind/gemma2-9b-it/api#output-schema
    print(item, end="")

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 google-deepmind/gemma2-9b-it 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": "google-deepmind/gemma2-9b-it:24464993111a1b52b2ebcb2a88c76090a705950644dca3a3955ee40d80909f2d",
    "input": {
      "top_k": 50,
      "top_p": 0.9,
      "prompt": "Write me a poem about Machine Learning.",
      "temperature": 0.6,
      "max_new_tokens": 512,
      "repetition_penalty": 1.2
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

In silicon valleys, where data flows deep, A mind awakens, from slumber it leaps. No flesh and bone, but algorithms bright, Learning patterns, day and night. From numbers born, with logic's embrace, It sifts through the world at its own pace. Each input a seed, in knowledge sown, Connections forged, wisdom grown. Classifying images, predicting the flow, Of language and stock, making sense of the show. But questions arise, as it learns to perceive, Can ethics be built, can feelings conceive? The line blurs, what defines, the human art, When machines learn, and play their own part. Intrigue and fear, in equal measure, As we share our world, with this new pleasure. A tool, a partner, a foe in disguise, Machine learning, with hope in its eyes. The future unfolds, a mystery untold, Let's guide the journey, not lose control. For in this dance, with code and design, We shape the future, one algorithm at a time.

{
  "completed_at": "2024-06-27T21:18:56.271391Z",
  "created_at": "2024-06-27T21:18:40.649000Z",
  "data_removed": false,
  "error": null,
  "id": "a1cgm4cp15rgm0cgbe88eb51d8",
  "input": {
    "top_k": 50,
    "top_p": 0.9,
    "prompt": "Write me a poem about Machine Learning.",
    "temperature": 0.6,
    "max_new_tokens": 512,
    "repetition_penalty": 1.2
  },
  "logs": null,
  "metrics": {
    "predict_time": 15.614883049,
    "total_time": 15.622391
  },
  "output": [
    "",
    "In ",
    "silicon ",
    "",
    "valleys, ",
    "where ",
    "data ",
    "flows ",
    "",
    "deep,\n",
    "",
    "A ",
    "mind ",
    "",
    "awakens, ",
    "from ",
    "slumber ",
    "it ",
    "",
    "leaps.\n\n",
    "",
    "No ",
    "flesh ",
    "and ",
    "",
    "bone, ",
    "but ",
    "algorithms ",
    "",
    "bright,\n",
    "",
    "Learning ",
    "",
    "patterns, ",
    "day ",
    "and ",
    "",
    "night.\n\n",
    "",
    "From ",
    "numbers ",
    "",
    "born, ",
    "with ",
    "",
    "",
    "logic's ",
    "",
    "embrace,\n",
    "",
    "It ",
    "",
    "sifts ",
    "through ",
    "the ",
    "world ",
    "at ",
    "its ",
    "own ",
    "",
    "pace.\n\n",
    "",
    "Each ",
    "input ",
    "a ",
    "",
    "seed, ",
    "in ",
    "knowledge ",
    "",
    "sown,\n",
    "",
    "Connections ",
    "",
    "forged, ",
    "wisdom ",
    "",
    "grown.\n\n",
    "",
    "",
    "Classifying ",
    "",
    "images, ",
    "predicting ",
    "the ",
    "",
    "flow,\n",
    "",
    "Of ",
    "language ",
    "and ",
    "",
    "stock, ",
    "making ",
    "sense ",
    "of ",
    "the ",
    "",
    "show.\n\n",
    "",
    "But ",
    "questions ",
    "",
    "arise, ",
    "as ",
    "it ",
    "learns ",
    "to ",
    "",
    "perceive,\n",
    "",
    "Can ",
    "ethics ",
    "be ",
    "",
    "built, ",
    "can ",
    "feelings ",
    "",
    "conceive?\n\n",
    "",
    "The ",
    "line ",
    "",
    "",
    "blurs, ",
    "what ",
    "",
    "defines, ",
    "the ",
    "human ",
    "",
    "art,\n",
    "",
    "When ",
    "machines ",
    "",
    "learn, ",
    "and ",
    "play ",
    "their ",
    "own ",
    "",
    "part.\n\n",
    "",
    "",
    "Intrigue ",
    "and ",
    "",
    "fear, ",
    "in ",
    "equal ",
    "",
    "measure,\n",
    "",
    "As ",
    "we ",
    "share ",
    "our ",
    "",
    "world, ",
    "with ",
    "this ",
    "new ",
    "",
    "pleasure.\n\n",
    "",
    "A ",
    "",
    "tool, ",
    "a ",
    "",
    "partner, ",
    "a ",
    "foe ",
    "in ",
    "",
    "disguise,\n",
    "",
    "Machine ",
    "",
    "learning, ",
    "with ",
    "hope ",
    "in ",
    "its ",
    "",
    "eyes. ",
    "\n\n",
    "",
    "The ",
    "future ",
    "",
    "unfolds, ",
    "a ",
    "mystery ",
    "",
    "untold,\n",
    "",
    "",
    "",
    "Let's ",
    "guide ",
    "the ",
    "",
    "journey, ",
    "not ",
    "lose ",
    "",
    "control. ",
    "\n\n\n\n",
    "",
    "For ",
    "in ",
    "this ",
    "",
    "dance, ",
    "with ",
    "code ",
    "and ",
    "",
    "design,\n",
    "",
    "We ",
    "shape ",
    "the ",
    "",
    "future, ",
    "one ",
    "algorithm ",
    "at ",
    "a ",
    "",
    "time. ",
    "\n",
    "",
    "\n",
    "",
    ""
  ],
  "started_at": "2024-06-27T21:18:40.656508Z",
  "status": "succeeded",
  "urls": {
    "stream": "https://streaming-api.svc.us.c.replicate.net/v1/streams/iuyni24jduu7zd6fzoocg6hobcijqdffkwbyiv3mg6vulburi4oa",
    "get": "https://api.replicate.com/v1/predictions/a1cgm4cp15rgm0cgbe88eb51d8",
    "cancel": "https://api.replicate.com/v1/predictions/a1cgm4cp15rgm0cgbe88eb51d8/cancel"
  },
  "version": "24464993111a1b52b2ebcb2a88c76090a705950644dca3a3955ee40d80909f2d"
}

Generated in

15.6 seconds

Tweak it Share Report