lucataco / phixtral-2x2_8

phixtral-2x2_8 is the first Mixure of Experts (MoE) made with two microsoft/phi-2 models, inspired by the mistralai/Mixtral-8x7B-v0.1 architecture

Cold

Public
1.5K runs
T4
GitHub
License

Run with an API

Playground API Examples README Versions

Prediction

lucataco/phixtral-2x2_8:25d7b93b

Model

lucataco/phixtral-2x2_8:25d7b93b

sps5aujbbs6i22qhjtqp242wcu

Status

Succeeded

Source

Web

Hardware

Total duration

Created

about 1 year ago

Input

top_k: 50
top_p: 0.95
prompt: Can you solve the equation 2x + 3 = 11 for x?
temperature: 0.7
max_new_tokens: 1024

{
  "top_k": 50,
  "top_p": 0.95,
  "prompt": "Can you solve the equation 2x + 3 = 11 for x?",
  "temperature": 0.7,
  "max_new_tokens": 1024
}

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 lucataco/phixtral-2x2_8 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "lucataco/phixtral-2x2_8:25d7b93bb0ec9e8dd94fcc69adc786759243a5628ba5574bd9609d6abafe57cf",
  {
    input: {
      top_k: 50,
      top_p: 0.95,
      prompt: "Can you solve the equation 2x + 3 = 11 for x?",
      temperature: 0.7,
      max_new_tokens: 1024
    }
  }
);
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 lucataco/phixtral-2x2_8 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "lucataco/phixtral-2x2_8:25d7b93bb0ec9e8dd94fcc69adc786759243a5628ba5574bd9609d6abafe57cf",
    input={
        "top_k": 50,
        "top_p": 0.95,
        "prompt": "Can you solve the equation 2x + 3 = 11 for x?",
        "temperature": 0.7,
        "max_new_tokens": 1024
    }
)

# The lucataco/phixtral-2x2_8 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/lucataco/phixtral-2x2_8/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 lucataco/phixtral-2x2_8 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": "25d7b93bb0ec9e8dd94fcc69adc786759243a5628ba5574bd9609d6abafe57cf",
    "input": {
      "top_k": 50,
      "top_p": 0.95,
      "prompt": "Can you solve the equation 2x + 3 = 11 for x?",
      "temperature": 0.7,
      "max_new_tokens": 1024
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

Sure! To solve the equation 2x + 3 = 11 for x, you need to isolate x on one side of the equation. Step 1: Subtract 3 from both sides of the equation. 2x + 3 - 3 = 11 - 3 2x = 8 Step 2: Divide both sides of the equation by 2. 2x / 2 = 8 / 2 x = 4 So the solution to the equation 2x + 3 = 11 is x = 4.

{
  "completed_at": "2024-02-08T22:05:37.633664Z",
  "created_at": "2024-02-08T22:01:36.455771Z",
  "data_removed": false,
  "error": null,
  "id": "sps5aujbbs6i22qhjtqp242wcu",
  "input": {
    "top_k": 50,
    "top_p": 0.95,
    "prompt": "Can you solve the equation 2x + 3 = 11 for x?",
    "temperature": 0.7,
    "max_new_tokens": 1024
  },
  "logs": "Using seed: 921063983",
  "metrics": {
    "predict_time": 36.15149,
    "total_time": 241.177893
  },
  "output": [
    "",
    "",
    "Sure! ",
    "To ",
    "solve ",
    "the ",
    "equation ",
    "",
    "2x ",
    "+ ",
    "3 ",
    "= ",
    "11 ",
    "for ",
    "",
    "x, ",
    "you ",
    "need ",
    "to ",
    "isolate ",
    "x ",
    "on ",
    "one ",
    "side ",
    "of ",
    "the ",
    "",
    "equation. ",
    "\n",
    "\n",
    "",
    "Step ",
    "",
    "1: ",
    "",
    "",
    "Subtract ",
    "3 ",
    "from ",
    "both ",
    "sides ",
    "of ",
    "the ",
    "",
    "equation.\n",
    "",
    "",
    "2x ",
    "+ ",
    "3 ",
    "- ",
    "3 ",
    "= ",
    "11 ",
    "- ",
    "3\n",
    "",
    "",
    "2x ",
    "= ",
    "8\n",
    "\n",
    "",
    "Step ",
    "",
    "2: ",
    "Divide ",
    "both ",
    "sides ",
    "of ",
    "the ",
    "equation ",
    "by ",
    "",
    "2.\n",
    "",
    "",
    "2x ",
    "/ ",
    "2 ",
    "= ",
    "8 ",
    "/ ",
    "2\n",
    "",
    "x ",
    "= ",
    "4\n",
    "\n",
    "",
    "So ",
    "the ",
    "solution ",
    "to ",
    "the ",
    "equation ",
    "",
    "2x ",
    "+ ",
    "3 ",
    "= ",
    "11 ",
    "is ",
    "x ",
    "= ",
    "",
    "",
    "4."
  ],
  "started_at": "2024-02-08T22:05:01.482174Z",
  "status": "succeeded",
  "urls": {
    "stream": "https://streaming-api.svc.us-central1.g.replicate.net/v1/streams/fwe4jamwn3uiyrs5dhbcvatuaibytk5hsdcngbbc7wyf23prlp4a",
    "get": "https://api.replicate.com/v1/predictions/sps5aujbbs6i22qhjtqp242wcu",
    "cancel": "https://api.replicate.com/v1/predictions/sps5aujbbs6i22qhjtqp242wcu/cancel"
  },
  "version": "25d7b93bb0ec9e8dd94fcc69adc786759243a5628ba5574bd9609d6abafe57cf"
}

Generated in

36.2 seconds

Tweak it Share Report

Prediction

lucataco/phixtral-2x2_8:25d7b93b

Model

lucataco/phixtral-2x2_8:25d7b93b

qfz4rzbbvb747koeik7u7ildzy

Status

Succeeded

Source

Web

Hardware

Total duration

3m 47s

Created

about 1 year ago

Input

top_k: 50
top_p: 0.95
prompt: Who was the first person to walk on the Moon?
temperature: 0.7
max_new_tokens: 100

{
  "top_k": 50,
  "top_p": 0.95,
  "prompt": "Who was the first person to walk on the Moon?",
  "temperature": 0.7,
  "max_new_tokens": 100
}

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 lucataco/phixtral-2x2_8 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "lucataco/phixtral-2x2_8:25d7b93bb0ec9e8dd94fcc69adc786759243a5628ba5574bd9609d6abafe57cf",
  {
    input: {
      top_k: 50,
      top_p: 0.95,
      prompt: "Who was the first person to walk on the Moon?",
      temperature: 0.7,
      max_new_tokens: 100
    }
  }
);
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 lucataco/phixtral-2x2_8 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "lucataco/phixtral-2x2_8:25d7b93bb0ec9e8dd94fcc69adc786759243a5628ba5574bd9609d6abafe57cf",
    input={
        "top_k": 50,
        "top_p": 0.95,
        "prompt": "Who was the first person to walk on the Moon?",
        "temperature": 0.7,
        "max_new_tokens": 100
    }
)

# The lucataco/phixtral-2x2_8 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/lucataco/phixtral-2x2_8/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 lucataco/phixtral-2x2_8 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": "25d7b93bb0ec9e8dd94fcc69adc786759243a5628ba5574bd9609d6abafe57cf",
    "input": {
      "top_k": 50,
      "top_p": 0.95,
      "prompt": "Who was the first person to walk on the Moon?",
      "temperature": 0.7,
      "max_new_tokens": 100
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

The first person to walk on the Moon was an American astronaut named Neil Armstrong. He was the commander of the Apollo 11 mission, which was launched by NASA on July 16, 1969. The mission successfully landed the Lunar Module Eagle on the Moon's surface on July 20, 1969, and Armstrong and his fellow astronaut Edwin "Buzz" Aldrin spent about two hours exploring the lunar surface before returning to the Lunar Module Eagle for the flight back to Earth. Armstrong famously took the first steps on the Moon,

{
  "completed_at": "2024-02-08T22:21:21.649339Z",
  "created_at": "2024-02-08T22:17:35.123582Z",
  "data_removed": false,
  "error": null,
  "id": "qfz4rzbbvb747koeik7u7ildzy",
  "input": {
    "top_k": 50,
    "top_p": 0.95,
    "prompt": "Who was the first person to walk on the Moon?",
    "temperature": 0.7,
    "max_new_tokens": 100
  },
  "logs": "Using seed: 872883025",
  "metrics": {
    "predict_time": 33.140567,
    "total_time": 226.525757
  },
  "output": [
    "",
    "The ",
    "first ",
    "person ",
    "to ",
    "walk ",
    "on ",
    "the ",
    "Moon ",
    "was ",
    "an ",
    "American ",
    "astronaut ",
    "named ",
    "Neil ",
    "",
    "Armstrong. ",
    "He ",
    "was ",
    "the ",
    "commander ",
    "of ",
    "the ",
    "Apollo ",
    "11 ",
    "",
    "mission, ",
    "which ",
    "was ",
    "launched ",
    "by ",
    "NASA ",
    "on ",
    "July ",
    "",
    "16, ",
    "",
    "1969. ",
    "The ",
    "mission ",
    "successfully ",
    "landed ",
    "the ",
    "Lunar ",
    "Module ",
    "Eagle ",
    "on ",
    "the ",
    "",
    "Moon's ",
    "surface ",
    "on ",
    "July ",
    "",
    "20, ",
    "",
    "1969, ",
    "and ",
    "Armstrong ",
    "and ",
    "his ",
    "fellow ",
    "astronaut ",
    "Edwin ",
    "",
    "",
    "\"Buzz\" ",
    "",
    "Aldrin ",
    "spent ",
    "about ",
    "two ",
    "hours ",
    "exploring ",
    "the ",
    "lunar ",
    "surface ",
    "before ",
    "returning ",
    "to ",
    "the ",
    "Lunar ",
    "Module ",
    "Eagle ",
    "for ",
    "the ",
    "flight ",
    "back ",
    "to ",
    "",
    "Earth. ",
    "Armstrong ",
    "famously ",
    "took ",
    "the ",
    "first ",
    "steps ",
    "on ",
    "the ",
    "",
    "Moon,"
  ],
  "started_at": "2024-02-08T22:20:48.508772Z",
  "status": "succeeded",
  "urls": {
    "stream": "https://streaming-api.svc.us-central1.g.replicate.net/v1/streams/pl53bibionqowf3kwkgr5vgoojtt6eyiladgago6gjzkabq6x3za",
    "get": "https://api.replicate.com/v1/predictions/qfz4rzbbvb747koeik7u7ildzy",
    "cancel": "https://api.replicate.com/v1/predictions/qfz4rzbbvb747koeik7u7ildzy/cancel"
  },
  "version": "25d7b93bb0ec9e8dd94fcc69adc786759243a5628ba5574bd9609d6abafe57cf"
}

Generated in

33.1 seconds

Tweak it Share Report

Prediction

lucataco/phixtral-2x2_8:25d7b93b

Model

lucataco/phixtral-2x2_8:25d7b93b

ycd7shjbnsiyrbshpx6kw3d7by

Status

Succeeded

Source

Web

Hardware

Total duration

32.9s

Created

about 1 year ago

Input

top_k: 50
top_p: 0.95
prompt: Can you write a short story about a time-traveling detective?
temperature: 0.7
max_new_tokens: 100

{
  "top_k": 50,
  "top_p": 0.95,
  "prompt": "Can you write a short story about a time-traveling detective?",
  "temperature": 0.7,
  "max_new_tokens": 100
}

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 lucataco/phixtral-2x2_8 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "lucataco/phixtral-2x2_8:25d7b93bb0ec9e8dd94fcc69adc786759243a5628ba5574bd9609d6abafe57cf",
  {
    input: {
      top_k: 50,
      top_p: 0.95,
      prompt: "Can you write a short story about a time-traveling detective?",
      temperature: 0.7,
      max_new_tokens: 100
    }
  }
);
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 lucataco/phixtral-2x2_8 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "lucataco/phixtral-2x2_8:25d7b93bb0ec9e8dd94fcc69adc786759243a5628ba5574bd9609d6abafe57cf",
    input={
        "top_k": 50,
        "top_p": 0.95,
        "prompt": "Can you write a short story about a time-traveling detective?",
        "temperature": 0.7,
        "max_new_tokens": 100
    }
)

# The lucataco/phixtral-2x2_8 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/lucataco/phixtral-2x2_8/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 lucataco/phixtral-2x2_8 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": "25d7b93bb0ec9e8dd94fcc69adc786759243a5628ba5574bd9609d6abafe57cf",
    "input": {
      "top_k": 50,
      "top_p": 0.95,
      "prompt": "Can you write a short story about a time-traveling detective?",
      "temperature": 0.7,
      "max_new_tokens": 100
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

Once upon a time, in the quaint town of Temporalia, lived a peculiar detective named Chronos. His unusual ability to travel through time made him a unique asset to the local police force. One day, a mysterious letter arrived at the Temporalia Police Department. It was written in a language that was unknown to them. The letter contained detailed descriptions of an impending disaster that would occur in the year 3000. The letter seemed accurate, as the townspeople started noticing strange changes

{
  "completed_at": "2024-02-08T22:23:30.319959Z",
  "created_at": "2024-02-08T22:22:57.468168Z",
  "data_removed": false,
  "error": null,
  "id": "ycd7shjbnsiyrbshpx6kw3d7by",
  "input": {
    "top_k": 50,
    "top_p": 0.95,
    "prompt": "Can you write a short story about a time-traveling detective?",
    "temperature": 0.7,
    "max_new_tokens": 100
  },
  "logs": "Using seed: 775479805",
  "metrics": {
    "predict_time": 32.839822,
    "total_time": 32.851791
  },
  "output": [
    "",
    "Once ",
    "upon ",
    "a ",
    "",
    "time, ",
    "in ",
    "the ",
    "quaint ",
    "town ",
    "of ",
    "",
    "",
    "",
    "Temporalia, ",
    "lived ",
    "a ",
    "peculiar ",
    "detective ",
    "named ",
    "",
    "",
    "Chronos. ",
    "His ",
    "unusual ",
    "ability ",
    "to ",
    "travel ",
    "through ",
    "time ",
    "made ",
    "him ",
    "a ",
    "unique ",
    "asset ",
    "to ",
    "the ",
    "local ",
    "police ",
    "",
    "force.\n",
    "\n",
    "",
    "One ",
    "",
    "day, ",
    "a ",
    "mysterious ",
    "letter ",
    "arrived ",
    "at ",
    "the ",
    "",
    "",
    "Temporalia ",
    "Police ",
    "",
    "Department. ",
    "It ",
    "was ",
    "written ",
    "in ",
    "a ",
    "language ",
    "that ",
    "was ",
    "unknown ",
    "to ",
    "",
    "them. ",
    "The ",
    "letter ",
    "contained ",
    "detailed ",
    "descriptions ",
    "of ",
    "an ",
    "impending ",
    "disaster ",
    "that ",
    "would ",
    "occur ",
    "in ",
    "the ",
    "year ",
    "",
    "3000. ",
    "The ",
    "letter ",
    "seemed ",
    "",
    "accurate, ",
    "as ",
    "the ",
    "",
    "",
    "townspeople ",
    "started ",
    "noticing ",
    "strange ",
    "changes"
  ],
  "started_at": "2024-02-08T22:22:57.480137Z",
  "status": "succeeded",
  "urls": {
    "stream": "https://streaming-api.svc.us-central1.g.replicate.net/v1/streams/77gpbo3njedu66qzgkzmkmpzhd4ouytnuntynw5cuhtremle2zwq",
    "get": "https://api.replicate.com/v1/predictions/ycd7shjbnsiyrbshpx6kw3d7by",
    "cancel": "https://api.replicate.com/v1/predictions/ycd7shjbnsiyrbshpx6kw3d7by/cancel"
  },
  "version": "25d7b93bb0ec9e8dd94fcc69adc786759243a5628ba5574bd9609d6abafe57cf"
}

Generated in

32.8 seconds

Tweak it Share Report

Prediction

lucataco/phixtral-2x2_8:25d7b93b

Model

lucataco/phixtral-2x2_8:25d7b93b

aof4wkrbao7z4cvnfk6cdpog2u

Status

Succeeded

Source

Web

Hardware

Total duration

33.0s

Created

about 1 year ago

Input

top_k: 50
top_p: 0.95
prompt: Write an epic poem about Ancient Rome.
temperature: 0.7
max_new_tokens: 100

{
  "top_k": 50,
  "top_p": 0.95,
  "prompt": "Write an epic poem about Ancient Rome.",
  "temperature": 0.7,
  "max_new_tokens": 100
}

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 lucataco/phixtral-2x2_8 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "lucataco/phixtral-2x2_8:25d7b93bb0ec9e8dd94fcc69adc786759243a5628ba5574bd9609d6abafe57cf",
  {
    input: {
      top_k: 50,
      top_p: 0.95,
      prompt: "Write an epic poem about Ancient Rome.",
      temperature: 0.7,
      max_new_tokens: 100
    }
  }
);
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 lucataco/phixtral-2x2_8 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "lucataco/phixtral-2x2_8:25d7b93bb0ec9e8dd94fcc69adc786759243a5628ba5574bd9609d6abafe57cf",
    input={
        "top_k": 50,
        "top_p": 0.95,
        "prompt": "Write an epic poem about Ancient Rome.",
        "temperature": 0.7,
        "max_new_tokens": 100
    }
)

# The lucataco/phixtral-2x2_8 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/lucataco/phixtral-2x2_8/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 lucataco/phixtral-2x2_8 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": "25d7b93bb0ec9e8dd94fcc69adc786759243a5628ba5574bd9609d6abafe57cf",
    "input": {
      "top_k": 50,
      "top_p": 0.95,
      "prompt": "Write an epic poem about Ancient Rome.",
      "temperature": 0.7,
      "max_new_tokens": 100
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

In the dawn of time, when Rome first rose, From the ashes of old, a city of glories grew. With mighty legions, they conquered the land, And a legacy of greatness, they did withstand. In the shadow of the mighty Colosseum, The gladiators fought for honor and renown. Their lives were but a sacrifice, for the crowd to cheer, As they battled beasts, and their enemies near. The Roman Forum

{
  "completed_at": "2024-02-08T22:22:23.589326Z",
  "created_at": "2024-02-08T22:21:50.550861Z",
  "data_removed": false,
  "error": null,
  "id": "aof4wkrbao7z4cvnfk6cdpog2u",
  "input": {
    "top_k": 50,
    "top_p": 0.95,
    "prompt": "Write an epic poem about Ancient Rome.",
    "temperature": 0.7,
    "max_new_tokens": 100
  },
  "logs": "Using seed: 157950725",
  "metrics": {
    "predict_time": 33.0272,
    "total_time": 33.038465
  },
  "output": [
    "",
    "In ",
    "the ",
    "dawn ",
    "of ",
    "",
    "time, ",
    "when ",
    "Rome ",
    "first ",
    "",
    "rose,\n",
    "",
    "From ",
    "the ",
    "ashes ",
    "of ",
    "",
    "old, ",
    "a ",
    "city ",
    "of ",
    "",
    "glories ",
    "",
    "grew.\n",
    "",
    "With ",
    "mighty ",
    "",
    "legions, ",
    "they ",
    "conquered ",
    "the ",
    "",
    "land,\n",
    "",
    "And ",
    "a ",
    "legacy ",
    "of ",
    "",
    "greatness, ",
    "they ",
    "did ",
    "",
    "withstand.\n",
    "\n",
    "",
    "In ",
    "the ",
    "shadow ",
    "of ",
    "the ",
    "mighty ",
    "",
    "",
    "",
    "",
    "Colosseum,\n",
    "",
    "The ",
    "",
    "",
    "gladiators ",
    "fought ",
    "for ",
    "honor ",
    "and ",
    "",
    "renown.\n",
    "",
    "Their ",
    "lives ",
    "were ",
    "but ",
    "a ",
    "",
    "sacrifice, ",
    "for ",
    "the ",
    "crowd ",
    "to ",
    "",
    "cheer,\n",
    "",
    "As ",
    "they ",
    "battled ",
    "",
    "beasts, ",
    "and ",
    "their ",
    "enemies ",
    "",
    "near.\n",
    "\n",
    "",
    "The ",
    "Roman ",
    "Forum"
  ],
  "started_at": "2024-02-08T22:21:50.562126Z",
  "status": "succeeded",
  "urls": {
    "stream": "https://streaming-api.svc.us-central1.g.replicate.net/v1/streams/dzvk6p2czjsj5vxuzilbe7sjqafrcz5qnu3mjvzvpmnci5tdnjeq",
    "get": "https://api.replicate.com/v1/predictions/aof4wkrbao7z4cvnfk6cdpog2u",
    "cancel": "https://api.replicate.com/v1/predictions/aof4wkrbao7z4cvnfk6cdpog2u/cancel"
  },
  "version": "25d7b93bb0ec9e8dd94fcc69adc786759243a5628ba5574bd9609d6abafe57cf"
}

Generated in

33.0 seconds

Tweak it Share Report

Prediction

lucataco/phixtral-2x2_8:25d7b93b

Model

lucataco/phixtral-2x2_8:25d7b93b

rxxlrhjb3yw4qytbz5c7ufictq

Status

Succeeded

Source

Web

Hardware

Total duration

32.4s

Created

about 1 year ago

Input

top_k: 50
top_p: 0.95
prompt: Use a list comprehension to create a list of squares for numbers from 1 to 10.
temperature: 0.7
max_new_tokens: 100

{
  "top_k": 50,
  "top_p": 0.95,
  "prompt": "Use a list comprehension to create a list of squares for numbers from 1 to 10.",
  "temperature": 0.7,
  "max_new_tokens": 100
}

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 lucataco/phixtral-2x2_8 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "lucataco/phixtral-2x2_8:25d7b93bb0ec9e8dd94fcc69adc786759243a5628ba5574bd9609d6abafe57cf",
  {
    input: {
      top_k: 50,
      top_p: 0.95,
      prompt: "Use a list comprehension to create a list of squares for numbers from 1 to 10.",
      temperature: 0.7,
      max_new_tokens: 100
    }
  }
);
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 lucataco/phixtral-2x2_8 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "lucataco/phixtral-2x2_8:25d7b93bb0ec9e8dd94fcc69adc786759243a5628ba5574bd9609d6abafe57cf",
    input={
        "top_k": 50,
        "top_p": 0.95,
        "prompt": "Use a list comprehension to create a list of squares for numbers from 1 to 10.",
        "temperature": 0.7,
        "max_new_tokens": 100
    }
)

# The lucataco/phixtral-2x2_8 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/lucataco/phixtral-2x2_8/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 lucataco/phixtral-2x2_8 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": "25d7b93bb0ec9e8dd94fcc69adc786759243a5628ba5574bd9609d6abafe57cf",
    "input": {
      "top_k": 50,
      "top_p": 0.95,
      "prompt": "Use a list comprehension to create a list of squares for numbers from 1 to 10.",
      "temperature": 0.7,
      "max_new_tokens": 100
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

Here is a simple list comprehension in Python that generates a list of squares for numbers from 1 to 10: ```python squares = [i**2 for i in range(1, 11)] print(squares) ``` In this code, `i**2` is the expression that generates the square of each number, and `for i in range(1, 11)` is the loop that goes from 1 to 10. The `range(

{
  "completed_at": "2024-02-08T22:24:31.931736Z",
  "created_at": "2024-02-08T22:23:59.508505Z",
  "data_removed": false,
  "error": null,
  "id": "rxxlrhjb3yw4qytbz5c7ufictq",
  "input": {
    "top_k": 50,
    "top_p": 0.95,
    "prompt": "Use a list comprehension to create a list of squares for numbers from 1 to 10.",
    "temperature": 0.7,
    "max_new_tokens": 100
  },
  "logs": "Using seed: 922033144",
  "metrics": {
    "predict_time": 32.412452,
    "total_time": 32.423231
  },
  "output": [
    "",
    "Here ",
    "is ",
    "a ",
    "simple ",
    "list ",
    "comprehension ",
    "in ",
    "Python ",
    "that ",
    "generates ",
    "a ",
    "list ",
    "of ",
    "squares ",
    "for ",
    "numbers ",
    "from ",
    "1 ",
    "to ",
    "",
    "10:\n",
    "\n",
    "",
    "",
    "",
    "```python\n",
    "",
    "",
    "squares ",
    "= ",
    "",
    "",
    "",
    "[i**2 ",
    "for ",
    "i ",
    "in ",
    "",
    "",
    "",
    "range(1, ",
    "",
    "11)]\n",
    "",
    "",
    "",
    "",
    "",
    "print(squares)\n",
    "",
    "",
    "```\n",
    "\n",
    "",
    "In ",
    "this ",
    "",
    "code, ",
    "",
    "",
    "",
    "",
    "`i**2` ",
    "is ",
    "the ",
    "expression ",
    "that ",
    "generates ",
    "the ",
    "square ",
    "of ",
    "each ",
    "",
    "number, ",
    "and ",
    "",
    "`for ",
    "i ",
    "in ",
    "",
    "",
    "",
    "range(1, ",
    "",
    "",
    "11)` ",
    "is ",
    "the ",
    "loop ",
    "that ",
    "goes ",
    "from ",
    "1 ",
    "to ",
    "",
    "10. ",
    "The ",
    "",
    "",
    "`range("
  ],
  "started_at": "2024-02-08T22:23:59.519284Z",
  "status": "succeeded",
  "urls": {
    "stream": "https://streaming-api.svc.us-central1.g.replicate.net/v1/streams/3zpev3egfpnsf7v76kcpdfgn5ydcmqp7srx56bv3bwghitkuy7gq",
    "get": "https://api.replicate.com/v1/predictions/rxxlrhjb3yw4qytbz5c7ufictq",
    "cancel": "https://api.replicate.com/v1/predictions/rxxlrhjb3yw4qytbz5c7ufictq/cancel"
  },
  "version": "25d7b93bb0ec9e8dd94fcc69adc786759243a5628ba5574bd9609d6abafe57cf"
}

Generated in

32.4 seconds

Tweak it Share Report

Want to make some of these yourself?

Run this model

lucataco / phixtral-2x2_8

Prediction

Input

Output

Prediction

Input

Output

Prediction

Input

Output

Prediction

Input

Output

Prediction

Input

Output

Logs (sps5aujbbs6i22qhjtqp242wcu)

Logs (qfz4rzbbvb747koeik7u7ildzy)

Logs (ycd7shjbnsiyrbshpx6kw3d7by)

Logs (aof4wkrbao7z4cvnfk6cdpog2u)

Logs (rxxlrhjb3yw4qytbz5c7ufictq)