meta/llama-2-13b-chat – Run with an API on Replicate

Official

meta / llama-2-13b-chat

A 13 billion parameter language model from Meta, fine tuned for chat completions

Warm

Public
4.8M runs
Priced per token
GitHub
Paper
License

Run with an API

Playground API Examples README

Input

prompt

*string

Shift + Return to add a new line

Write a story in the style of James Joyce. The story should be about a trip to the Irish countryside in 2083, to see the beautiful scenery and robots.Write a story in the style of James Joyce. The story should be about a trip to the Irish countryside in 2083, to see the beautiful scenery and robots.

Prompt to send to the model.

system_prompt

string

Shift + Return to add a new line

You are a helpful, respectful and honest assistant. Always answer as helpfully as possible, while being safe. Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature.

If a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you don't know the answer to a question, please don't share false information.You are a helpful, respectful and honest assistant. Always answer as helpfully as possible, while being safe. Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature.

If a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you don't know the answer to a question, please don't share false information.

System prompt to send to the model. This is prepended to the prompt and helps guide system behavior.

Default: "You are a helpful, respectful and honest assistant. Always answer as helpfully as possible, while being safe. Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature.\n\nIf a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you don't know the answer to a question, please don't share false information."

max_tokens

integer

(minimum: 1)

Maximum number of tokens to generate. A word is generally 2-3 tokens.

Default: 512

min_tokens

integer

(minimum: -1)

Minimum number of tokens to generate. To disable, set to -1. A word is generally 2-3 tokens.

temperature

number

(minimum: 0, maximum: 5)

Adjusts randomness of outputs, greater than 1 is random and 0 is deterministic, 0.75 is a good starting value.

Default: 0.7

top_p

number

(minimum: 0, maximum: 1)

When decoding text, samples from the top p percentage of most likely tokens; lower to ignore less likely tokens.

Default: 0.95

top_k

integer

(minimum: -1)

When decoding text, samples from the top k most likely tokens; lower to ignore less likely tokens.

Default: 0

stop_sequences

string

Shift + Return to add a new line

A comma-separated list of sequences to stop generation at. For example, '<end>,<stop>' will stop generation at the first instance of 'end' or '<stop>'.

length_penalty

number

(minimum: 0, maximum: 5)

A parameter that controls how long the outputs are. If < 1, the model will tend to generate shorter outputs, and > 1 will tend to generate longer outputs.

Default: 1

presence_penalty

number

A parameter that penalizes repeated tokens regardless of the number of appearances. As the value increases, the model will be less likely to repeat tokens in the output.

Default: 0

seed

integer

Random seed. Leave blank to randomize the seed.

prompt_template

string

Shift + Return to add a new line

<s>[INST] <<SYS>>
{system_prompt}
<</SYS>>

{prompt} [/INST]<s>[INST] <<SYS>>
{system_prompt}
<</SYS>>

{prompt} [/INST]

Template for formatting the prompt. Can be an arbitrary string, but must contain the substring `{prompt}`.

Default: "<s>[INST] <<SYS>>\n{system_prompt}\n<</SYS>>\n\n{prompt} [/INST]"

log_performance_metrics

boolean

Default: false

max_new_tokens

integer

(minimum: 1)

This parameter has been renamed to max_tokens. max_new_tokens only exists for backwards compatibility purposes. We recommend you use max_tokens instead. Both may not be specified.

min_new_tokens

integer

(minimum: -1)

This parameter has been renamed to min_tokens. min_new_tokens only exists for backwards compatibility purposes. We recommend you use min_tokens instead. Both may not be specified.

Run this model in Node.js with one line of code:

npx create-replicate --model=meta/llama-2-13b-chat

or set up a project from scratch

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-chat using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const input = {
  top_k: 0,
  top_p: 1,
  prompt: "Write a story in the style of James Joyce. The story should be about a trip to the Irish countryside in 2083, to see the beautiful scenery and robots.",
  max_tokens: 512,
  temperature: 0.75,
  system_prompt: "You are a helpful, respectful and honest assistant. Always answer as helpfully as possible, while being safe. Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature.\n\nIf a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you don't know the answer to a question, please don't share false information.",
  length_penalty: 1,
  max_new_tokens: 500,
  prompt_template: "<s>[INST] <<SYS>>\n{system_prompt}\n<</SYS>>\n\n{prompt} [/INST]",
  presence_penalty: 0,
  log_performance_metrics: false
};

for await (const event of replicate.stream("meta/llama-2-13b-chat", { 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-chat using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

# The meta/llama-2-13b-chat model can stream output as it's running.
for event in replicate.stream(
    "meta/llama-2-13b-chat",
    input={
        "top_k": 0,
        "top_p": 1,
        "prompt": "Write a story in the style of James Joyce. The story should be about a trip to the Irish countryside in 2083, to see the beautiful scenery and robots.",
        "max_tokens": 512,
        "temperature": 0.75,
        "system_prompt": "You are a helpful, respectful and honest assistant. Always answer as helpfully as possible, while being safe. Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature.\n\nIf a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you don't know the answer to a question, please don't share false information.",
        "length_penalty": 1,
        "max_new_tokens": 500,
        "prompt_template": "<s>[INST] <<SYS>>\n{system_prompt}\n<</SYS>>\n\n{prompt} [/INST]",
        "presence_penalty": 0,
        "log_performance_metrics": False
    },
):
    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-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 $'{
    "input": {
      "top_k": 0,
      "top_p": 1,
      "prompt": "Write a story in the style of James Joyce. The story should be about a trip to the Irish countryside in 2083, to see the beautiful scenery and robots.",
      "max_tokens": 512,
      "temperature": 0.75,
      "system_prompt": "You are a helpful, respectful and honest assistant. Always answer as helpfully as possible, while being safe. Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature.\\n\\nIf a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you don\'t know the answer to a question, please don\'t share false information.",
      "length_penalty": 1,
      "max_new_tokens": 500,
      "prompt_template": "<s>[INST] <<SYS>>\\n{system_prompt}\\n<</SYS>>\\n\\n{prompt} [/INST]",
      "presence_penalty": 0,
      "log_performance_metrics": false
    }
  }' \
  https://api.replicate.com/v1/models/meta/llama-2-13b-chat/predictions

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

Output

Sure, I'd be happy to help! Here's a story in the style of James Joyce, set in the Irish countryside in 2083: As I stepped off the pod-train and onto the lush green grass of the countryside, the crisp air filled my lungs and invigorated my senses. The year was 2083, and yet the rolling hills and sparkling lakes of Ireland seemed unchanged by the passage of time. The only difference was the presence of robots, their sleek metallic bodies and glowing blue eyes a testament to the advancements of technology. I had come to this place seeking solace and inspiration, to lose myself in the beauty of nature and the wonder of machines. As I wandered through the hills, I came across a group of robots tending to a field of crops, their delicate movements and precise calculations ensuring a bountiful harvest. One of the robots, a sleek and agile model with wings like a dragonfly, fluttered over to me and offered a friendly greeting. "Good day, traveler," it said in a melodic voice. "What brings you to our humble abode?" I explained my desire to experience the beauty of the Irish countryside, and the robot nodded sympathetically. "Ah, yes," it said. "There is much to see and explore here. Would you like a guided tour?" I eagerly accepted the offer, and the robot led me on a journey through the rolling hills and sparkling lakes. We saw towering waterfalls and ancient ruins, and the robot shared stories of the history and culture of the land. As we walked, the sun began to set, casting a golden glow over the landscape. As the stars began to twinkle in the night sky, the robot and I sat down on a hill overlooking the countryside. "This is a special place," the robot said, its voice filled with a sense of wonder. "A place where nature and technology coexist in harmony." I nodded in agreement, feeling a sense of awe and gratitude for this wondrous place. And as I looked out at the stars, I knew that this trip to the

{
  "completed_at": "2023-07-22T00:45:01.280236Z",
  "created_at": "2023-07-22T00:44:36.461840Z",
  "data_removed": false,
  "error": null,
  "id": "y2ym6szb57znjkirlbyxc4dlcm",
  "input": {
    "top_p": 1,
    "prompt": "Write a story in the style of James Joyce. The story should be about a trip to the Irish countryside in 2083, to see the beautiful scenery and robots.",
    "temperature": 0.75,
    "system_prompt": "You are a helpful, respectful and honest assistant. Always answer as helpfully as possible, while being safe. Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature.\n\nIf a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you don't know the answer to a question, please don't share false information.",
    "max_new_tokens": 500,
    "repetition_penalty": 1
  },
  "logs": "Formatted input prompt:\n[INST] <<SYS>>\nYou are a helpful, respectful and honest assistant. Always answer as helpfully as possible, while being safe. Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature.\nIf a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you don't know the answer to a question, please don't share false information.\n<</SYS>>\nWrite a story in the style of James Joyce. The story should be about a trip to the Irish countryside in 2083, to see the beautiful scenery and robots. [/INST]",
  "metrics": {
    "predict_time": 24.882469,
    "total_time": 24.818396
  },
  "output": [
    " Sure,",
    " I'd",
    " be",
    " happy",
    " to",
    " help!",
    " Here's",
    " a",
    " story",
    " in",
    " the",
    " style",
    " of",
    " James",
    " Joyce,",
    " set",
    " in",
    " the",
    " Irish",
    " countryside",
    " in",
    " 2083:\nAs",
    " I",
    " stepped",
    " off",
    " the",
    " pod-train",
    " and",
    " onto",
    " the",
    " lush",
    " green",
    " grass",
    " of",
    " the",
    " countryside,",
    " the",
    " crisp",
    " air",
    " filled",
    " my",
    " lungs",
    " and",
    " invigorated",
    " my",
    " senses.",
    " The",
    " year",
    " was",
    " 2083,",
    " and",
    " yet",
    " the",
    " rolling",
    " hills",
    " and",
    " sparkling",
    " lakes",
    " of",
    " Ireland",
    " seemed",
    " unchanged",
    " by",
    " the",
    " passage",
    " of",
    " time.",
    " The",
    " only",
    " difference",
    " was",
    " the",
    " presence",
    " of",
    " robots,",
    " their",
    " sleek",
    " metallic",
    " bodies",
    " and",
    " glowing",
    " blue",
    " eyes",
    " a",
    " testament",
    " to",
    " the",
    " advancements",
    " of",
    " technology.\nI",
    " had",
    " come",
    " to",
    " this",
    " place",
    " seeking",
    " solace",
    " and",
    " inspiration,",
    " to",
    " lose",
    " myself",
    " in",
    " the",
    " beauty",
    " of",
    " nature",
    " and",
    " the",
    " wonder",
    " of",
    " machines.",
    " As",
    " I",
    " wandered",
    " through",
    " the",
    " hills,",
    " I",
    " came",
    " across",
    " a",
    " group",
    " of",
    " robots",
    " tending",
    " to",
    " a",
    " field",
    " of",
    " crops,",
    " their",
    " delicate",
    " movements",
    " and",
    " precise",
    " calculations",
    " ensuring",
    " a",
    " bountiful",
    " harvest.\nOne",
    " of",
    " the",
    " robots,",
    " a",
    " sleek",
    " and",
    " agile",
    " model",
    " with",
    " wings",
    " like",
    " a",
    " dragonfly,",
    " fluttered",
    " over",
    " to",
    " me",
    " and",
    " offered",
    " a",
    " friendly",
    " greeting.",
    " \"Good",
    " day,",
    " traveler,\"",
    " it",
    " said",
    " in",
    " a",
    " melodic",
    " voice.",
    " \"What",
    " brings",
    " you",
    " to",
    " our",
    " humble",
    " abode?\"\nI",
    " explained",
    " my",
    " desire",
    " to",
    " experience",
    " the",
    " beauty",
    " of",
    " the",
    " Irish",
    " countryside,",
    " and",
    " the",
    " robot",
    " nodded",
    " sympathetically.",
    " \"Ah,",
    " yes,\"",
    " it",
    " said.",
    " \"There",
    " is",
    " much",
    " to",
    " see",
    " and",
    " explore",
    " here.",
    " Would",
    " you",
    " like",
    " a",
    " guided",
    " tour?\"\nI",
    " eagerly",
    " accepted",
    " the",
    " offer,",
    " and",
    " the",
    " robot",
    " led",
    " me",
    " on",
    " a",
    " journey",
    " through",
    " the",
    " rolling",
    " hills",
    " and",
    " sparkling",
    " lakes.",
    " We",
    " saw",
    " towering",
    " waterfalls",
    " and",
    " ancient",
    " ruins,",
    " and",
    " the",
    " robot",
    " shared",
    " stories",
    " of",
    " the",
    " history",
    " and",
    " culture",
    " of",
    " the",
    " land.",
    " As",
    " we",
    " walked,",
    " the",
    " sun",
    " began",
    " to",
    " set,",
    " casting",
    " a",
    " golden",
    " glow",
    " over",
    " the",
    " landscape.\nAs",
    " the",
    " stars",
    " began",
    " to",
    " twinkle",
    " in",
    " the",
    " night",
    " sky,",
    " the",
    " robot",
    " and",
    " I",
    " sat",
    " down",
    " on",
    " a",
    " hill",
    " overlooking",
    " the",
    " countryside.",
    " \"This",
    " is",
    " a",
    " special",
    " place,\"",
    " the",
    " robot",
    " said,",
    " its",
    " voice",
    " filled",
    " with",
    " a",
    " sense",
    " of",
    " wonder.",
    " \"A",
    " place",
    " where",
    " nature",
    " and",
    " technology",
    " coexist",
    " in",
    " harmony.\"\nI",
    " nodded",
    " in",
    " agreement,",
    " feeling",
    " a",
    " sense",
    " of",
    " awe",
    " and",
    " gratitude",
    " for",
    " this",
    " wondrous",
    " place.",
    " And",
    " as",
    " I",
    " looked",
    " out",
    " at",
    " the",
    " stars,",
    " I",
    " knew",
    " that",
    " this",
    " trip",
    " to",
    " the"
  ],
  "started_at": "2023-07-22T00:44:36.397767Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/y2ym6szb57znjkirlbyxc4dlcm",
    "cancel": "https://api.replicate.com/v1/predictions/y2ym6szb57znjkirlbyxc4dlcm/cancel"
  },
  "version": "6b4da803a2382c08868c5af10a523892f38e2de1aafb2ee55b020d9efef2fdb8"
}

Generated in

24.9 seconds

Tweak it Report

Pricing

This language model is priced by how many input tokens are sent as inputs and how many output tokens are generated.

Type	Per unit	Per $1
Input	$0.10 / 1M tokens or 10M tokens / $1
Output	$0.50 / 1M tokens or 2M tokens / $1

For example, for $10 you can run around 28,571 predictions where the input is a sentence or two (15 tokens) and the output is a few paragraphs (700 tokens).

Check out our docs for more information about how per-token pricing works on Replicate.

Readme

Llama 2 is a collection of pretrained and fine-tuned generative text models ranging in scale from 7 billion to 70 billion parameters. This is the repository for the 13 billion parameter chat model, which has been fine-tuned on instructions to make it better at being a chat bot.

Learn more about running Llama 2 with an API and the different models.

Please see ai.meta.com/llama for more information about the model, licensing, and acceptable use.

How to prompt Llama 2 chat

To use this model, you can simply pass a prompt or instruction to the prompt argument. We handle prompt formatting on the backend so that you don’t need to worry about it.

Formatting prompts for chat interfaces

However, if you’re managing dialogue state with multiple exchanges between a user and the model, you need to mark the dialogue turns with instruction tags that indicate the beginning ("[INST]") and end (`”/INST]”) of user input. For example, a properly formatted dialogue looks like:

prompt = """\
[INST] Hi! [/INST]
Hello! How are you?
[INST] I'm great, thanks for asking. Could you help me with a task? [/INST]"""

In this example, the hypothetical user has first prompted "Hi!" and received the response "Hello! How are you?". Then, the user responded "I'm great, thanks for asking. Could you help me with a task?".

Modifying the system prompt

In addition to supporting dialogue exchanges, this deployment also allows you to modify the system prompt that is used to guide model responses. By altering the input to the system_prompt argument, you can inject custom context or information that will be used to guide model output.

To learn more, see this guide to prompting Llama 2.