Prediction

Model

meta/llama-2-13b-chat:df7690f1

wumxgirb2a5phkl6cqh5yt4l6i

Status

Succeeded

Source

Web

Hardware

A100 (40GB)

Total duration

23.1s

Created

over 2 years ago by mnpenner

Webhook

–

Input

prompt: User: Write a story about a bad experience a couple had at a steakhouse in Italy Assistant:
max_length: 500
temperature: 4.47
top_p: 0.74
repetition_penalty: 1

{
  "max_length": 500,
  "prompt": "User: Write a story about a bad experience a couple had at a steakhouse in Italy \nAssistant:",
  "repetition_penalty": 1,
  "temperature": 4.47,
  "top_p": 0.74
}

Install Replicate’s Node.js client library:

npm install replicate

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=r8_ds4**********************************

This is your API token. Keep it to yourself.

Import and set up the client:

import Replicate from "replicate";

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

Run meta/llama-2-13b-chat using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "meta/llama-2-13b-chat:df7690f1994d94e96ad9d568eac121aecf50684a0b0963b25a41cc40061269e5",
  {
    input: {
      max_length: 500,
      prompt: "User: Write a story about a bad experience a couple had at a steakhouse in Italy \nAssistant:",
      repetition_penalty: 1,
      temperature: 4.47,
      top_p: 0.74
    }
  }
);

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=r8_ds4**********************************

This is your API token. Keep it to yourself.

Import the client:

import replicate

Run meta/llama-2-13b-chat using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "meta/llama-2-13b-chat:df7690f1994d94e96ad9d568eac121aecf50684a0b0963b25a41cc40061269e5",
    input={
        "max_length": 500,
        "prompt": "User: Write a story about a bad experience a couple had at a steakhouse in Italy \nAssistant:",
        "repetition_penalty": 1,
        "temperature": 4.47,
        "top_p": 0.74
    }
)

# The meta/llama-2-13b-chat 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/meta/llama-2-13b-chat/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=r8_ds4**********************************

This is your API token. Keep it to yourself.

Run meta/llama-2-13b-chat 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/llama-2-13b-chat:df7690f1994d94e96ad9d568eac121aecf50684a0b0963b25a41cc40061269e5",
    "input": {
      "max_length": 500,
      "prompt": "User: Write a story about a bad experience a couple had at a steakhouse in Italy \\nAssistant:",
      "repetition_penalty": 1,
      "temperature": 4.47,
      "top_p": 0.74
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

Sure, I would be sadder to write this and will write. But my answer will sound sarcastick so just so you be sure it may take on light tone and that you do realize some situations might come back this. It may sound a lot sillier because well things are really subjected, people act a silly ways! So sitll enjoy because there has been worst happenings which lead me as assistant here and there has truly been far wrose things have occured as this steaks of discomfarsteak, i think? :p so enjoy it. 
"Ugh, remember that craze about crappy dates and experiences you and Johnathan on datesteekay Italy?  Geew hillzz!"
---Steph-kay is saying and siing-ing  haze-lee in manner similar as to be sarazstic while giganteeously exxeeigure a face about something unpleeaasint happening during their evening, at Italian Steaked-Date--
The story is in process after asking: Do go along in an explainational, silly and satyrical approach which could lead us to your answer by your preference' asking this request that can or is expected for, with all means please ask what you've planned from here since it gives myself a more "drama' as approachable to give that taste about "comedy of the bad bad disdate", with all understanding, so i should assume from the beginning i understand your character would want to "splain "the reason on Steph' bad Italian date and to continue---?

{
  "id": "wumxgirb2a5phkl6cqh5yt4l6i",
  "model": "meta/llama-2-13b-chat",
  "version": "df7690f1994d94e96ad9d568eac121aecf50684a0b0963b25a41cc40061269e5",
  "input": {
    "max_length": 500,
    "prompt": "User: Write a story about a bad experience a couple had at a steakhouse in Italy \nAssistant:",
    "repetition_penalty": 1,
    "temperature": 4.47,
    "top_p": 0.74
  },
  "logs": "",
  "output": [
    "Sure,",
    " I",
    " would",
    " be",
    " sadder",
    " to",
    " write",
    " this",
    " and",
    " will",
    " write.",
    " But",
    " my",
    " answer",
    " will",
    " sound",
    " sarcastick",
    " so",
    " just",
    " so",
    " you",
    " be",
    " sure",
    " it",
    " may",
    " take",
    " on",
    " light",
    " tone",
    " and",
    " that",
    " you",
    " do",
    " realize",
    " some",
    " situations",
    " might",
    " come",
    " back",
    " this.",
    " It",
    " may",
    " sound",
    " a",
    " lot",
    " sillier",
    " because",
    " well",
    " things",
    " are",
    " really",
    " subjected,",
    " people",
    " act",
    " a",
    " silly",
    " ways!",
    " So",
    " sitll",
    " enjoy",
    " because",
    " there",
    " has",
    " been",
    " worst",
    " happenings",
    " which",
    " lead",
    " me",
    " as",
    " assistant",
    " here",
    " and",
    " there",
    " has",
    " truly",
    " been",
    " far",
    " wrose",
    " things",
    " have",
    " occured",
    " as",
    " this",
    " steaks",
    " of",
    " discomfarsteak,",
    " i",
    " think?",
    " :p",
    " so",
    " enjoy",
    " it.",
    " \n\"Ugh,",
    " remember",
    " that",
    " craze",
    " about",
    " crappy",
    " dates",
    " and",
    " experiences",
    " you",
    " and",
    " Johnathan",
    " on",
    " datesteekay",
    " Italy?",
    " ",
    " Geew",
    " hillzz!\"\n---Steph-kay",
    " is",
    " saying",
    " and",
    " siing-ing",
    " ",
    " haze-lee",
    " in",
    " manner",
    " similar",
    " as",
    " to",
    " be",
    " sarazstic",
    " while",
    " giganteeously",
    " exxeeigure",
    " a",
    " face",
    " about",
    " something",
    " unpleeaasint",
    " happening",
    " during",
    " their",
    " evening,",
    " at",
    " Italian",
    " Steaked-Date--\nThe",
    " story",
    " is",
    " in",
    " process",
    " after",
    " asking:",
    " Do",
    " go",
    " along",
    " in",
    " an",
    " explainational,",
    " silly",
    " and",
    " satyrical",
    " approach",
    " which",
    " could",
    " lead",
    " us",
    " to",
    " your",
    " answer",
    " by",
    " your",
    " preference'",
    " asking",
    " this",
    " request",
    " that",
    " can",
    " or",
    " is",
    " expected",
    " for,",
    " with",
    " all",
    " means",
    " please",
    " ask",
    " what",
    " you've",
    " planned",
    " from",
    " here",
    " since",
    " it",
    " gives",
    " myself",
    " a",
    " more",
    " \"drama'",
    " as",
    " approachable",
    " to",
    " give",
    " that",
    " taste",
    " about",
    " \"comedy",
    " of",
    " the",
    " bad",
    " bad",
    " disdate\",",
    " with",
    " all",
    " understanding,",
    " so",
    " i",
    " should",
    " assume",
    " from",
    " the",
    " beginning",
    " i",
    " understand",
    " your",
    " character",
    " would",
    " want",
    " to",
    " \"splain",
    " \"the",
    " reason",
    " on",
    " Steph'",
    " bad",
    " Italian",
    " date",
    " and",
    " to",
    " continue---?"
  ],
  "data_removed": false,
  "error": null,
  "source": "web",
  "status": "succeeded",
  "created_at": "2023-07-18T21:26:14.77192Z",
  "started_at": "2023-07-18T21:26:14.684797Z",
  "completed_at": "2023-07-18T21:26:37.824231Z",
  "urls": {
    "cancel": "https://api.replicate.com/v1/predictions/wumxgirb2a5phkl6cqh5yt4l6i/cancel",
    "get": "https://api.replicate.com/v1/predictions/wumxgirb2a5phkl6cqh5yt4l6i"
  },
  "metrics": {
    "predict_time": 23.139434,
    "total_time": 23.052311
  }
}

Generated in

23.1 seconds

Tweak it Report