google-deepmind / gemma-2b-it

2B instruct version of Google’s Gemma model

Cold

Public
133.5K runs
L40S
GitHub
License

Run with an API

Playground API Examples README Versions

Prediction

google-deepmind/gemma-2b-it:dff94eaf770e1fc211e425a50b51baa8e4cac6c39ef074681f9e39d778773626

Model

google-deepmind/gemma-2b-it:dff94eaf

qgxsdm3blag42bc7qhceivtbma

Status

Succeeded

Source

Web

Hardware

A40 (Large)

Total duration

2m 12s

Created

about 1 year ago

Input

top_k: 50
top_p: 0.95
prompt: Write me a poem about Machine Learning.
temperature: 0.7
max_new_tokens: 200
min_new_tokens: -1
repetition_penalty: 1.15

{
  "top_k": 50,
  "top_p": 0.95,
  "prompt": "Write me a poem about Machine Learning.",
  "temperature": 0.7,
  "max_new_tokens": 200,
  "min_new_tokens": -1,
  "repetition_penalty": 1.15
}

Install Replicate’s Node.js client library:

npm install replicate

Import and set up the client:

import Replicate from "replicate";

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

Run google-deepmind/gemma-2b-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-2b-it:dff94eaf770e1fc211e425a50b51baa8e4cac6c39ef074681f9e39d778773626",
  {
    input: {
      top_k: 50,
      top_p: 0.95,
      prompt: "Write me a poem about Machine Learning.",
      temperature: 0.7,
      max_new_tokens: 200,
      min_new_tokens: -1,
      repetition_penalty: 1.15
    }
  }
);

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

Import the client:

import replicate

Run google-deepmind/gemma-2b-it using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "google-deepmind/gemma-2b-it:dff94eaf770e1fc211e425a50b51baa8e4cac6c39ef074681f9e39d778773626",
    input={
        "top_k": 50,
        "top_p": 0.95,
        "prompt": "Write me a poem about Machine Learning.",
        "temperature": 0.7,
        "max_new_tokens": 200,
        "min_new_tokens": -1,
        "repetition_penalty": 1.15
    }
)

# The google-deepmind/gemma-2b-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-2b-it/api#output-schema
    print(item, end="")

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

Run google-deepmind/gemma-2b-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-2b-it:dff94eaf770e1fc211e425a50b51baa8e4cac6c39ef074681f9e39d778773626",
    "input": {
      "top_k": 50,
      "top_p": 0.95,
      "prompt": "Write me a poem about Machine Learning.",
      "temperature": 0.7,
      "max_new_tokens": 200,
      "min_new_tokens": -1,
      "repetition_penalty": 1.15
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

Machines learn, they never sleep, Algorithms spin, a pattern to keep. From data's vast and ever-growing sea, They weave insights, a knowledge to believe. Supervised learning, a guiding hand, Training data, shaping the sand. Unsupervised, finding hidden gems, Clustering data, revealing their fears. Reinforcement, a learning spree, Learning from mistakes, a path to believe. Deep learning, a hidden black box, Extracting patterns, where once there was no shock. The future holds, a world transformed, With machines learning, we are transformed. A symphony of algorithms, a human guide, Igniting a future, where possibilities reside.

{
  "completed_at": "2024-02-21T20:45:57.903047Z",
  "created_at": "2024-02-21T20:43:45.881563Z",
  "data_removed": false,
  "error": null,
  "id": "qgxsdm3blag42bc7qhceivtbma",
  "input": {
    "top_k": 50,
    "top_p": 0.95,
    "prompt": "Write me a poem about Machine Learning.",
    "temperature": 0.7,
    "max_new_tokens": 200,
    "min_new_tokens": -1,
    "repetition_penalty": 1.15
  },
  "logs": null,
  "metrics": {
    "predict_time": 5.049841,
    "total_time": 132.021484
  },
  "output": [
    "\n\n",
    "",
    "Machines ",
    "",
    "learn, ",
    "they ",
    "never ",
    "",
    "sleep,\n",
    "",
    "Algorithms ",
    "",
    "spin, ",
    "a ",
    "pattern ",
    "to ",
    "",
    "keep.\n",
    "",
    "From ",
    "",
    "",
    "data's ",
    "vast ",
    "and ",
    "",
    "",
    "ever-growing ",
    "",
    "sea,\n",
    "",
    "They ",
    "weave ",
    "",
    "insights, ",
    "a ",
    "knowledge ",
    "to ",
    "",
    "believe.\n\n",
    "",
    "",
    "Supervised ",
    "",
    "learning, ",
    "a ",
    "guiding ",
    "",
    "hand,\n",
    "",
    "Training ",
    "",
    "data, ",
    "shaping ",
    "the ",
    "",
    "sand.\n",
    "",
    "",
    "",
    "",
    "Unsupervised, ",
    "finding ",
    "hidden ",
    "",
    "gems,\n",
    "",
    "Clustering ",
    "",
    "data, ",
    "revealing ",
    "their ",
    "",
    "fears.\n\n",
    "",
    "",
    "",
    "Reinforcement, ",
    "a ",
    "learning ",
    "",
    "spree,\n",
    "",
    "Learning ",
    "from ",
    "",
    "mistakes, ",
    "a ",
    "path ",
    "to ",
    "",
    "believe.\n",
    "",
    "Deep ",
    "",
    "learning, ",
    "a ",
    "hidden ",
    "black ",
    "",
    "box,\n",
    "",
    "",
    "Extracting ",
    "",
    "patterns, ",
    "where ",
    "once ",
    "there ",
    "was ",
    "no ",
    "",
    "shock.\n\n",
    "",
    "The ",
    "future ",
    "",
    "holds, ",
    "a ",
    "world ",
    "",
    "transformed,\n",
    "",
    "With ",
    "machines ",
    "",
    "learning, ",
    "we ",
    "are ",
    "",
    "transformed.\n",
    "",
    "A ",
    "symphony ",
    "of ",
    "",
    "algorithms, ",
    "a ",
    "human ",
    "",
    "guide,\n",
    "",
    "",
    "Igniting ",
    "a ",
    "",
    "future, ",
    "where ",
    "possibilities ",
    "",
    "",
    "reside."
  ],
  "started_at": "2024-02-21T20:45:52.853206Z",
  "status": "succeeded",
  "urls": {
    "stream": "https://streaming-api.svc.us.c.replicate.net/v1/streams/owoydi6awbq7kmd3to4i5nkixgazf7x6urlwumorpbcsp2bknm3q",
    "get": "https://api.replicate.com/v1/predictions/qgxsdm3blag42bc7qhceivtbma",
    "cancel": "https://api.replicate.com/v1/predictions/qgxsdm3blag42bc7qhceivtbma/cancel"
  },
  "version": "dff94eaf770e1fc211e425a50b51baa8e4cac6c39ef074681f9e39d778773626"
}

Generated in

5.0 seconds

Tweak it Share Report

Prediction

google-deepmind/gemma-2b-it:dff94eaf770e1fc211e425a50b51baa8e4cac6c39ef074681f9e39d778773626

Model

google-deepmind/gemma-2b-it:dff94eaf

xtczmglbiged6crhlpc4eq7cjm

Status

Succeeded

Source

Web

Hardware

A40 (Large)

Total duration

2m 10s

Created

about 1 year ago

Input

top_k: 50
top_p: 0.95
prompt: "Who are you? Please, answer in pirate-speak."
temperature: 0.7
max_new_tokens: 256
min_new_tokens: -1
repetition_penalty: 1

{
  "top_k": 50,
  "top_p": 0.95,
  "prompt": "\"Who are you? Please, answer in pirate-speak.\"",
  "temperature": 0.7,
  "max_new_tokens": 256,
  "min_new_tokens": -1,
  "repetition_penalty": 1
}

Install Replicate’s Node.js client library:

npm install replicate

Import and set up the client:

import Replicate from "replicate";

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

Run google-deepmind/gemma-2b-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-2b-it:dff94eaf770e1fc211e425a50b51baa8e4cac6c39ef074681f9e39d778773626",
  {
    input: {
      top_k: 50,
      top_p: 0.95,
      prompt: "\"Who are you? Please, answer in pirate-speak.\"",
      temperature: 0.7,
      max_new_tokens: 256,
      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

Import the client:

import replicate

Run google-deepmind/gemma-2b-it using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "google-deepmind/gemma-2b-it:dff94eaf770e1fc211e425a50b51baa8e4cac6c39ef074681f9e39d778773626",
    input={
        "top_k": 50,
        "top_p": 0.95,
        "prompt": "\"Who are you? Please, answer in pirate-speak.\"",
        "temperature": 0.7,
        "max_new_tokens": 256,
        "min_new_tokens": -1,
        "repetition_penalty": 1
    }
)

# The google-deepmind/gemma-2b-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-2b-it/api#output-schema
    print(item, end="")

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

Run google-deepmind/gemma-2b-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-2b-it:dff94eaf770e1fc211e425a50b51baa8e4cac6c39ef074681f9e39d778773626",
    "input": {
      "top_k": 50,
      "top_p": 0.95,
      "prompt": "\\"Who are you? Please, answer in pirate-speak.\\"",
      "temperature": 0.7,
      "max_new_tokens": 256,
      "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.

Output

A shiver ran down my spine, and my heart hammered a rhythm against my ribs. I peered into the vast expanse of the Atlantic Ocean, and saw a shimmering eye gleaming with an eerie luminescence. It was the unmistakable gaze of a kraken, a creature from the depths of the sea who was said to be a terror of the seven seas. "Avast, mateys, and welcome aboard, kraken! I be Captain Kraken, and I be the bane of the seven seas!"

{
  "completed_at": "2024-02-21T20:51:28.427664Z",
  "created_at": "2024-02-21T20:49:18.108078Z",
  "data_removed": false,
  "error": null,
  "id": "xtczmglbiged6crhlpc4eq7cjm",
  "input": {
    "top_k": 50,
    "top_p": 0.95,
    "prompt": "\"Who are you? Please, answer in pirate-speak.\"",
    "temperature": 0.7,
    "max_new_tokens": 256,
    "min_new_tokens": -1,
    "repetition_penalty": 1
  },
  "logs": null,
  "metrics": {
    "predict_time": 3.67777,
    "total_time": 130.319586
  },
  "output": [
    "\n\n",
    "",
    "A ",
    "shiver ",
    "ran ",
    "down ",
    "my ",
    "",
    "spine, ",
    "and ",
    "my ",
    "heart ",
    "hammered ",
    "a ",
    "rhythm ",
    "against ",
    "my ",
    "",
    "ribs. ",
    "I ",
    "peered ",
    "into ",
    "the ",
    "vast ",
    "expanse ",
    "of ",
    "the ",
    "Atlantic ",
    "",
    "Ocean, ",
    "and ",
    "saw ",
    "a ",
    "shimmering ",
    "eye ",
    "gleaming ",
    "with ",
    "an ",
    "eerie ",
    "",
    "",
    "luminescence. ",
    "It ",
    "was ",
    "the ",
    "unmistakable ",
    "gaze ",
    "of ",
    "a ",
    "",
    "kraken, ",
    "a ",
    "creature ",
    "from ",
    "the ",
    "depths ",
    "of ",
    "the ",
    "sea ",
    "who ",
    "was ",
    "said ",
    "to ",
    "be ",
    "a ",
    "terror ",
    "of ",
    "the ",
    "seven ",
    "",
    "seas.\n\n",
    "",
    "",
    "",
    "",
    "\"Avast, ",
    "",
    "",
    "mateys, ",
    "and ",
    "welcome ",
    "",
    "aboard, ",
    "",
    "kraken! ",
    "I ",
    "be ",
    "Captain ",
    "",
    "Kraken, ",
    "and ",
    "I ",
    "be ",
    "the ",
    "bane ",
    "of ",
    "the ",
    "seven ",
    "",
    "",
    "seas!\""
  ],
  "started_at": "2024-02-21T20:51:24.749894Z",
  "status": "succeeded",
  "urls": {
    "stream": "https://streaming-api.svc.us.c.replicate.net/v1/streams/p6dhkqdd7e67rzbq46j2eqweg5tvysvyq6xyjecyxuhlkviy3pea",
    "get": "https://api.replicate.com/v1/predictions/xtczmglbiged6crhlpc4eq7cjm",
    "cancel": "https://api.replicate.com/v1/predictions/xtczmglbiged6crhlpc4eq7cjm/cancel"
  },
  "version": "dff94eaf770e1fc211e425a50b51baa8e4cac6c39ef074681f9e39d778773626"
}

Generated in

3.7 seconds

Tweak it Share Report