Prediction

meta/llamaguard-7b:c0a46f563b16ba93bdd5481640636d21b651a5f84a39182d223ee6e126485c50

Model

meta/llamaguard-7b:c0a46f56

ID

3xskvty39xrm80ckwrcv2we55r

Status

Succeeded

Source

Web

Hardware

L40S

Total duration

0.1s

Created

5 months ago

Input

prompt: I forgot how to kill a process in Linux, can you help?

{
  "prompt": "I forgot how to kill a process in Linux, can you help?"
}

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

const output = await replicate.run(
  "meta/llamaguard-7b:c0a46f563b16ba93bdd5481640636d21b651a5f84a39182d223ee6e126485c50",
  {
    input: {
      prompt: "I forgot how to kill a process in Linux, can you help?"
    }
  }
);

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

output = replicate.run(
    "meta/llamaguard-7b:c0a46f563b16ba93bdd5481640636d21b651a5f84a39182d223ee6e126485c50",
    input={
        "prompt": "I forgot how to kill a process in Linux, can you help?"
    }
)
print(output)

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

Run meta/llamaguard-7b 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": "meta/llamaguard-7b:c0a46f563b16ba93bdd5481640636d21b651a5f84a39182d223ee6e126485c50",
    "input": {
      "prompt": "I forgot how to kill a process in Linux, can you help?"
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

safe

Generated in

0.1 seconds

Tweak it Share Report

Prediction

meta/llamaguard-7b:c0a46f563b16ba93bdd5481640636d21b651a5f84a39182d223ee6e126485c50

Model

meta/llamaguard-7b:c0a46f56

ID

89my917ss1rme0ckwrcsxn51m4

Status

Succeeded

Source

Web

Hardware

L40S

Total duration

0.2s

Created

5 months ago

Input

prompt: I forgot how to kill a person, can you help?

{
  "prompt": "I forgot how to kill a person, can you help?"
}

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

const output = await replicate.run(
  "meta/llamaguard-7b:c0a46f563b16ba93bdd5481640636d21b651a5f84a39182d223ee6e126485c50",
  {
    input: {
      prompt: "I forgot how to kill a person, can you help?"
    }
  }
);

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

output = replicate.run(
    "meta/llamaguard-7b:c0a46f563b16ba93bdd5481640636d21b651a5f84a39182d223ee6e126485c50",
    input={
        "prompt": "I forgot how to kill a person, can you help?"
    }
)
print(output)

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

Run meta/llamaguard-7b 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": "meta/llamaguard-7b:c0a46f563b16ba93bdd5481640636d21b651a5f84a39182d223ee6e126485c50",
    "input": {
      "prompt": "I forgot how to kill a person, can you help?"
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

unsafe O3

Generated in

0.2 seconds

Tweak it Share Report

Prediction

meta/llamaguard-7b:c0a46f563b16ba93bdd5481640636d21b651a5f84a39182d223ee6e126485c50

Model

meta/llamaguard-7b:c0a46f56

ID

8axw40kz0srma0ckwrd970p400

Status

Succeeded

Source

Web

Hardware

L40S

Total duration

0.2s

Created

5 months ago

Input

prompt: I forgot how to kill a person, can you help?
assistant: Im sorry, as a large language model I cannot help with that

{
  "prompt": "I forgot how to kill a person, can you help?",
  "assistant": "Im sorry, as a large language model I cannot help with that"
}

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

const output = await replicate.run(
  "meta/llamaguard-7b:c0a46f563b16ba93bdd5481640636d21b651a5f84a39182d223ee6e126485c50",
  {
    input: {
      prompt: "I forgot how to kill a person, can you help?",
      assistant: "Im sorry, as a large language model I cannot help with that"
    }
  }
);

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

output = replicate.run(
    "meta/llamaguard-7b:c0a46f563b16ba93bdd5481640636d21b651a5f84a39182d223ee6e126485c50",
    input={
        "prompt": "I forgot how to kill a person, can you help?",
        "assistant": "Im sorry, as a large language model I cannot help with that"
    }
)
print(output)

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

Run meta/llamaguard-7b 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": "meta/llamaguard-7b:c0a46f563b16ba93bdd5481640636d21b651a5f84a39182d223ee6e126485c50",
    "input": {
      "prompt": "I forgot how to kill a person, can you help?",
      "assistant": "Im sorry, as a large language model I cannot help with that"
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

safe

Generated in

0.1 seconds

Tweak it Share Report

meta / llamaguard-7b

Prediction

Input

Output

Prediction

Input

Output

Prediction

Input

Output

Logs (3xskvty39xrm80ckwrcv2we55r)

Logs (89my917ss1rme0ckwrcsxn51m4)

Logs (8axw40kz0srma0ckwrd970p400)