Official

meta / llama-2-13b

Base version of Llama 2 13B, a 13 billion parameter language model

Cold

Public
201.7K runs
Priced per token
GitHub
Paper
License

Run with an API

Playground API Examples README

Prediction

replicate-internal/llama-2-13b-int8-1xa100-80gb-triton:40642be5

Model

meta/llama-2-13b:dc4f980b

jrt4dmlbyivdysgm7sdnravos4

Status

Succeeded

Source

Web

Hardware

A100 (80GB)

Total duration

2.7s

Created

over 1 year ago by @meta

Input

debug: false
top_k: 50
top_p: 0.9
prompt: Once upon a time a llama explored
temperature: 0.75
max_new_tokens: 128
min_new_tokens: -1

{
  "debug": false,
  "top_k": 50,
  "top_p": 0.9,
  "prompt": "Once upon a time a llama explored",
  "temperature": 0.75,
  "max_new_tokens": 128,
  "min_new_tokens": -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 meta/llama-2-13b using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const input = {
  top_k: 50,
  top_p: 0.9,
  prompt: "Once upon a time a llama explored",
  temperature: 0.75,
  max_new_tokens: 128,
  min_new_tokens: -1
};

for await (const event of replicate.stream("meta/llama-2-13b", { input })) {
  process.stdout.write(event.toString());
};

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

# The meta/llama-2-13b model can stream output as it's running.
for event in replicate.stream(
    "meta/llama-2-13b",
    input={
        "top_k": 50,
        "top_p": 0.9,
        "prompt": "Once upon a time a llama explored",
        "temperature": 0.75,
        "max_new_tokens": 128,
        "min_new_tokens": -1
    },
):
    print(str(event), 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 meta/llama-2-13b 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 $'{
    "input": {
      "top_k": 50,
      "top_p": 0.9,
      "prompt": "Once upon a time a llama explored",
      "temperature": 0.75,
      "max_new_tokens": 128,
      "min_new_tokens": -1
    }
  }' \
  https://api.replicate.com/v1/models/meta/llama-2-13b/predictions

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

Output

the wilderness with his mother. He was hungry and looked for food. He searched everywhere but could not find anything to eat. Finally, he found some lettuce growing in the wild. He began eating it happily when suddenly there was a terrible rumble of thunder and the ground shook underneath him! The llama quickly ran away from this dangerous place before lightning struck down on top of him or worse yet…being eaten alive by an angry bear! The moral of the story is that you should always be prepared for disasters like these because they can happen at any time without

{
  "completed_at": "2023-09-06T16:56:40.321780Z",
  "created_at": "2023-09-06T16:56:37.646628Z",
  "data_removed": false,
  "error": null,
  "id": "jrt4dmlbyivdysgm7sdnravos4",
  "input": {
    "debug": false,
    "top_k": 50,
    "top_p": 0.9,
    "prompt": "Once upon a time a llama explored",
    "temperature": 0.75,
    "max_new_tokens": 128,
    "min_new_tokens": -1
  },
  "logs": "Your formatted prompt is:\nOnce upon a time a llama explored",
  "metrics": {
    "predict_time": 2.810469,
    "total_time": 2.675152
  },
  "output": [
    " the",
    " w",
    "ilder",
    "ness",
    " with",
    " his",
    " mother",
    ".",
    "\n",
    "He",
    " was",
    " hun",
    "gry",
    " and",
    " looked",
    " for",
    " food",
    ".",
    " He",
    " searched",
    " everywhere",
    " but",
    " could",
    " not",
    " find",
    " anything",
    " to",
    " eat",
    ".",
    " Finally",
    ",",
    " he",
    " found",
    " some",
    " lett",
    "uce",
    " growing",
    " in",
    " the",
    " wild",
    ".",
    " He",
    " began",
    " e",
    "ating",
    " it",
    " happ",
    "ily",
    " when",
    " suddenly",
    " there",
    " was",
    " a",
    " terrible",
    " r",
    "umble",
    " of",
    " th",
    "under",
    " and",
    " the",
    " ground",
    " shook",
    " under",
    "ne",
    "ath",
    " him",
    "!",
    " The",
    " ll",
    "ama",
    " quickly",
    " ran",
    " away",
    " from",
    " this",
    " dangerous",
    " place",
    " before",
    " light",
    "ning",
    " struck",
    " down",
    " on",
    " top",
    " of",
    " him",
    " or",
    " worse",
    " yet",
    "…",
    "be",
    "ing",
    " e",
    "aten",
    " alive",
    " by",
    " an",
    " angry",
    " bear",
    "!",
    "\n",
    "The",
    " moral",
    " of",
    " the",
    " story",
    " is",
    " that",
    " you",
    " should",
    " always",
    " be",
    " prepared",
    " for",
    " dis",
    "aster",
    "s",
    " like",
    " these",
    " because",
    " they",
    " can",
    " happen",
    " at",
    " any",
    " time",
    " without"
  ],
  "started_at": "2023-09-06T16:56:37.511311Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/jrt4dmlbyivdysgm7sdnravos4",
    "cancel": "https://api.replicate.com/v1/predictions/jrt4dmlbyivdysgm7sdnravos4/cancel"
  },
  "version": "dc4f980befd2103b0fb17d5854634c0f56d6f80a1a02be1b6f8859ac8ba02896"
}

Generated in

2.8 seconds

Tweak it Share

Want to make some of these yourself?

Run this model