Prediction

replicate/flan-t5-xl:1457f256622cd45415aa70c02105a917b39dc96e58601d7c2df5a30d2e3092e7

Model

replicate/flan-t5-xl:1457f256

oi3gyjmgzbd37le4d3otrjdjyq

Status

Succeeded

Source

Web

Hardware

–

Total duration

0.3s

Created

about 2 years ago by @daanelson

Input

top_p: "0.95"
prompt: Here are some phrases and sentiments. \nI love this spaghetti: Positive \nThe air outside is great: Positive \nYou hated the cat in the hat: Negative \nHe is in a foul mood: Negative \nThe dinner was horrible:
max_length: 50
temperature: "0.7"
repetition_penalty: 1

{
  "top_p": "0.95",
  "prompt": "Here are some phrases and sentiments. \\nI love this spaghetti: Positive \\nThe air outside is great: Positive \\nYou hated the cat in the hat: Negative \\nHe is in a foul mood: Negative \\nThe dinner was horrible: ",
  "max_length": 50,
  "temperature": "0.7",
  "repetition_penalty": 1
}

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 replicate/flan-t5-xl using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "replicate/flan-t5-xl:1457f256622cd45415aa70c02105a917b39dc96e58601d7c2df5a30d2e3092e7",
  {
    input: {
      top_p: "0.95",
      prompt: "Here are some phrases and sentiments. \\nI love this spaghetti: Positive \\nThe air outside is great: Positive \\nYou hated the cat in the hat: Negative \\nHe is in a foul mood: Negative \\nThe dinner was horrible: ",
      max_length: 50,
      temperature: "0.7",
      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 replicate/flan-t5-xl using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "replicate/flan-t5-xl:1457f256622cd45415aa70c02105a917b39dc96e58601d7c2df5a30d2e3092e7",
    input={
        "top_p": "0.95",
        "prompt": "Here are some phrases and sentiments. \\nI love this spaghetti: Positive \\nThe air outside is great: Positive \\nYou hated the cat in the hat: Negative \\nHe is in a foul mood: Negative \\nThe dinner was horrible: ",
        "max_length": 50,
        "temperature": "0.7",
        "repetition_penalty": 1
    }
)
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 replicate/flan-t5-xl 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": "1457f256622cd45415aa70c02105a917b39dc96e58601d7c2df5a30d2e3092e7",
    "input": {
      "top_p": "0.95",
      "prompt": "Here are some phrases and sentiments. \\\\nI love this spaghetti: Positive \\\\nThe air outside is great: Positive \\\\nYou hated the cat in the hat: Negative \\\\nHe is in a foul mood: Negative \\\\nThe dinner was horrible: ",
      "max_length": 50,
      "temperature": "0.7",
      "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/replicate/flan-t5-xl@sha256:1457f256622cd45415aa70c02105a917b39dc96e58601d7c2df5a30d2e3092e7 \
  -i 'top_p="0.95"' \
  -i $'prompt="Here are some phrases and sentiments. \\\\nI love this spaghetti: Positive \\\\nThe air outside is great: Positive \\\\nYou hated the cat in the hat: Negative \\\\nHe is in a foul mood: Negative \\\\nThe dinner was horrible: "' \
  -i 'max_length=50' \
  -i 'temperature="0.7"' \
  -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/replicate/flan-t5-xl@sha256:1457f256622cd45415aa70c02105a917b39dc96e58601d7c2df5a30d2e3092e7
curl -s -X POST \
  -H "Content-Type: application/json" \
  -d $'{
    "input": {
      "top_p": "0.95",
      "prompt": "Here are some phrases and sentiments. \\\\nI love this spaghetti: Positive \\\\nThe air outside is great: Positive \\\\nYou hated the cat in the hat: Negative \\\\nHe is in a foul mood: Negative \\\\nThe dinner was horrible: ",
      "max_length": 50,
      "temperature": "0.7",
      "repetition_penalty": 1
    }
  }' \
  http://localhost:5000/predictions

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

Output

[ "Negative" ]

Generated in

0.2 seconds

Tweak it Report