google-deepmind/gemma-7b-it:2790a695 | Run with an API on Replicate

Version

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

google-deepmind /gemma-7b-it:2790a695

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

Default: 200

min_new_tokens

integer

(minimum: -1)

Minimum number of tokens to generate. To disable, set to -1. A word is generally 2-3 tokens.

Default: -1

temperature

number

(minimum: 0.01, maximum: 5)

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

Default: 0.7

top_p

number

(minimum: 0, maximum: 1)

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

Default: 0.95

top_k

integer

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: 1.15

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

npx create-replicate --model=google-deepmind/gemma-7b-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/gemma-7b-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/gemma-7b-it:2790a695e5dcae15506138cc4718d1106d0d475e6dca4b1d43f42414647993d5",
  {
    input: {
      top_k: 50,
      top_p: 0.95,
      prompt: "Write me a poem about Machine Learning.",
      temperature: 0.7,
      max_new_tokens: 512,
      min_new_tokens: -1,
      repetition_penalty: 1
    }
  }
);

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/gemma-7b-it using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "google-deepmind/gemma-7b-it:2790a695e5dcae15506138cc4718d1106d0d475e6dca4b1d43f42414647993d5",
    input={
        "top_k": 50,
        "top_p": 0.95,
        "prompt": "Write me a poem about Machine Learning.",
        "temperature": 0.7,
        "max_new_tokens": 512,
        "min_new_tokens": -1,
        "repetition_penalty": 1
    }
)

# The google-deepmind/gemma-7b-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/gemma-7b-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/gemma-7b-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/gemma-7b-it:2790a695e5dcae15506138cc4718d1106d0d475e6dca4b1d43f42414647993d5",
    "input": {
      "top_k": 50,
      "top_p": 0.95,
      "prompt": "Write me a poem about Machine Learning.",
      "temperature": 0.7,
      "max_new_tokens": 512,
      "min_new_tokens": -1,
      "repetition_penalty": 1
    }
  }' \
  https://api.replicate.com/v1/predictions

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

You can run this model locally using Cog. First, install Cog:

brew install cog

If you don’t have Homebrew, there are other installation options available.

Run this to download the model and run it in your local environment:

cog predict r8.im/google-deepmind/gemma-7b-it@sha256:2790a695e5dcae15506138cc4718d1106d0d475e6dca4b1d43f42414647993d5 \
  -i 'top_k=50' \
  -i 'top_p=0.95' \
  -i 'prompt="Write me a poem about Machine Learning."' \
  -i 'temperature=0.7' \
  -i 'max_new_tokens=512' \
  -i 'min_new_tokens=-1' \
  -i 'repetition_penalty=1'

To learn more, take a look at the Cog documentation.

Run this to download the model and run it in your local environment:

docker run -d -p 5000:5000 --gpus=all r8.im/google-deepmind/gemma-7b-it@sha256:2790a695e5dcae15506138cc4718d1106d0d475e6dca4b1d43f42414647993d5
curl -s -X POST \
  -H "Content-Type: application/json" \
  -d $'{
    "input": {
      "top_k": 50,
      "top_p": 0.95,
      "prompt": "Write me a poem about Machine Learning.",
      "temperature": 0.7,
      "max_new_tokens": 512,
      "min_new_tokens": -1,
      "repetition_penalty": 1
    }
  }' \
  http://localhost:5000/predictions

To learn more, take a look at the Cog documentation.

Output

In the realm of data, a tale unfolds, Where algorithms dance, tales are told. A machine learning model, a master of craft, Unveils patterns, hidden in the draft. With neural networks, it learns to see, The secrets embedded in data, free. From images to text, it can perceive, And make decisions, beyond belief. The model's mind, a labyrinth of code, Uncovers insights, secrets to be told. It finds relationships, hidden in the past, And predicts future trends, built to last. But beware, dear friend, of biases blind, For algorithms can amplify what's wrong. In fairness and justice, we must stand, To ensure that AI serves our hand. So let us harness this powerful force, For the betterment of humanity's course. With machine learning, we can soar, To heights we've never reached before. A journey into the future, a tale to be told, Where machine learning transforms the old. A tale of progress, a tale of might, A future where data shines so bright.

{
  "completed_at": "2024-02-21T21:11:23.562266Z",
  "created_at": "2024-02-21T21:11:14.580859Z",
  "data_removed": false,
  "error": null,
  "id": "btssyhlbwyroq35ce25lmtkruy",
  "input": {
    "top_k": 50,
    "top_p": 0.95,
    "prompt": "Write me a poem about Machine Learning.",
    "temperature": 0.7,
    "max_new_tokens": 512,
    "min_new_tokens": -1,
    "repetition_penalty": 1
  },
  "logs": null,
  "metrics": {
    "predict_time": 8.940067,
    "total_time": 8.981407
  },
  "output": [
    "\n\n",
    "",
    "In ",
    "the ",
    "realm ",
    "of ",
    "",
    "data, ",
    "a ",
    "tale ",
    "",
    "unfolds,\n",
    "",
    "Where ",
    "algorithms ",
    "",
    "dance, ",
    "tales ",
    "are ",
    "",
    "told.\n",
    "",
    "A ",
    "machine ",
    "learning ",
    "",
    "model, ",
    "a ",
    "master ",
    "of ",
    "",
    "craft,\n",
    "",
    "",
    "",
    "Unveils ",
    "",
    "patterns, ",
    "hidden ",
    "in ",
    "the ",
    "",
    "draft.\n\n",
    "",
    "With ",
    "neural ",
    "",
    "networks, ",
    "it ",
    "learns ",
    "to ",
    "",
    "see,\n",
    "",
    "The ",
    "secrets ",
    "embedded ",
    "in ",
    "",
    "data, ",
    "",
    "free.\n",
    "",
    "From ",
    "images ",
    "to ",
    "",
    "text, ",
    "it ",
    "can ",
    "",
    "perceive,\n",
    "",
    "And ",
    "make ",
    "",
    "decisions, ",
    "beyond ",
    "",
    "belief.\n\n",
    "",
    "The ",
    "",
    "",
    "model's ",
    "",
    "mind, ",
    "a ",
    "labyrinth ",
    "of ",
    "",
    "code,\n",
    "",
    "",
    "Uncovers ",
    "",
    "insights, ",
    "secrets ",
    "to ",
    "be ",
    "",
    "told.\n",
    "",
    "It ",
    "finds ",
    "",
    "relationships, ",
    "hidden ",
    "in ",
    "the ",
    "",
    "past,\n",
    "",
    "And ",
    "predicts ",
    "future ",
    "",
    "trends, ",
    "built ",
    "to ",
    "",
    "last.\n\n",
    "",
    "But ",
    "",
    "beware, ",
    "dear ",
    "",
    "friend, ",
    "of ",
    "biases ",
    "",
    "blind,\n",
    "",
    "For ",
    "algorithms ",
    "can ",
    "amplify ",
    "",
    "",
    "what's ",
    "",
    "wrong.\n",
    "",
    "In ",
    "fairness ",
    "and ",
    "",
    "justice, ",
    "we ",
    "must ",
    "",
    "stand,\n",
    "",
    "To ",
    "ensure ",
    "that ",
    "AI ",
    "serves ",
    "our ",
    "",
    "hand.\n\n",
    "",
    "So ",
    "let ",
    "us ",
    "harness ",
    "this ",
    "powerful ",
    "",
    "force,\n",
    "",
    "For ",
    "the ",
    "betterment ",
    "of ",
    "",
    "",
    "humanity's ",
    "",
    "course.\n",
    "",
    "With ",
    "machine ",
    "",
    "learning, ",
    "we ",
    "can ",
    "",
    "soar,\n",
    "",
    "To ",
    "heights ",
    "",
    "",
    "we've ",
    "never ",
    "reached ",
    "",
    "before.\n\n",
    "",
    "A ",
    "journey ",
    "into ",
    "the ",
    "",
    "future, ",
    "a ",
    "tale ",
    "to ",
    "be ",
    "",
    "told,\n",
    "",
    "Where ",
    "machine ",
    "learning ",
    "transforms ",
    "the ",
    "",
    "old.\n",
    "",
    "A ",
    "tale ",
    "of ",
    "",
    "progress, ",
    "a ",
    "tale ",
    "of ",
    "",
    "might,\n",
    "",
    "A ",
    "future ",
    "where ",
    "data ",
    "shines ",
    "so ",
    "",
    "",
    "bright."
  ],
  "started_at": "2024-02-21T21:11:14.622199Z",
  "status": "succeeded",
  "urls": {
    "stream": "https://streaming-api.svc.us.c.replicate.net/v1/streams/qelc5njozompuurkw5dxtgl3rie63v74sltpkwzb6inromxub6bq",
    "get": "https://api.replicate.com/v1/predictions/btssyhlbwyroq35ce25lmtkruy",
    "cancel": "https://api.replicate.com/v1/predictions/btssyhlbwyroq35ce25lmtkruy/cancel"
  },
  "version": "2790a695e5dcae15506138cc4718d1106d0d475e6dca4b1d43f42414647993d5"
}

Generated in

8.9 seconds

Tweak it Report View full prediction