lucataco/llama-2-7b-chat | Run with an API on Replicate

lucataco / llama-2-7b-chat

Meta's Llama 2 7b Chat - GPTQ

Cold

Public
20.3K runs
L40S
GitHub
Paper
License

Iterate in playground

Run with an API

Playground API Examples README Versions

Input

prompt

string

Shift + Return to add a new line

Prompt to send to Llama v2

Default: "Tell me about AI"

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 that 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. 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."

max_new_tokens

integer

(minimum: 1, maximum: 4096)

Number of new tokens

Default: 512

temperature

number

(minimum: 0, maximum: 5)

Randomness of outputs, 0 is deterministic, greater than 1 is random

Default: 0.75

top_p

number

(minimum: 0.01, maximum: 1)

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

Default: 0.95

repetition_penalty

number

(minimum: 0, maximum: 5)

Penalty for repeated words in generated text; 1 is no penalty, values greater than 1 discourage repetition, less than 1 encourage it

Default: 1.1

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

npx create-replicate --model=lucataco/llama-2-7b-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 lucataco/llama-2-7b-chat using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "lucataco/llama-2-7b-chat:6ab580ab4eef2c2b440f2441ec0fc0ace5470edaf2cbea50b8550aec0b3fbd38",
  {
    input: {
      top_p: 0.95,
      prompt: "Tell me about AI",
      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. 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.",
      max_new_tokens: 256,
      repetition_penalty: 1.1
    }
  }
);

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 lucataco/llama-2-7b-chat using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "lucataco/llama-2-7b-chat:6ab580ab4eef2c2b440f2441ec0fc0ace5470edaf2cbea50b8550aec0b3fbd38",
    input={
        "top_p": 0.95,
        "prompt": "Tell me about AI",
        "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. 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.",
        "max_new_tokens": 256,
        "repetition_penalty": 1.1
    }
)

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 lucataco/llama-2-7b-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": "lucataco/llama-2-7b-chat:6ab580ab4eef2c2b440f2441ec0fc0ace5470edaf2cbea50b8550aec0b3fbd38",
    "input": {
      "top_p": 0.95,
      "prompt": "Tell me about AI",
      "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. 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.",
      "max_new_tokens": 256,
      "repetition_penalty": 1.1
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

Of course! I'd be happy to help you learn more about AI! 🤖 Artificial intelligence (AI) refers to the development of computer systems that can perform tasks that typically require human intelligence, such as visual perception, speech recognition, decision-making, and language translation. AI technologies are able to process vast amounts of data quickly and accurately, making them incredibly useful for a wide range of applications. 💻 There are several types of AI, including: 1. Narrow or weak AI: This type of AI is designed to perform a specific task, such as facial recognition, language translation, or playing a game like chess. Narrow AI is the most common form of AI and is used in many applications, including virtual assistants, self-driving cars, and medical diagnosis. 2. General or strong AI: This type of AI is designed to perform any intellectual task that a human can, such as reasoning, problem-solving, and learning. General AI has not yet been developed, but researchers are working towards creating it. 🔥 3. Superintelligence: This type

{
  "completed_at": "2023-07-24T15:36:09.758557Z",
  "created_at": "2023-07-24T15:35:59.937096Z",
  "data_removed": false,
  "error": null,
  "id": "go6aggtby57c7inaffs6w4gety",
  "input": {
    "top_p": 0.95,
    "prompt": "Tell me about AI",
    "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. 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.",
    "max_new_tokens": 256,
    "repetition_penalty": 1.1
  },
  "logs": null,
  "metrics": {
    "predict_time": 9.818046,
    "total_time": 9.821461
  },
  "output": "  Of course! I'd be happy to help you learn more about AI! 🤖\nArtificial intelligence (AI) refers to the development of computer systems that can perform tasks that typically require human intelligence, such as visual perception, speech recognition, decision-making, and language translation. AI technologies are able to process vast amounts of data quickly and accurately, making them incredibly useful for a wide range of applications. 💻\nThere are several types of AI, including:\n1. Narrow or weak AI: This type of AI is designed to perform a specific task, such as facial recognition, language translation, or playing a game like chess. Narrow AI is the most common form of AI and is used in many applications, including virtual assistants, self-driving cars, and medical diagnosis.\n2. General or strong AI: This type of AI is designed to perform any intellectual task that a human can, such as reasoning, problem-solving, and learning. General AI has not yet been developed, but researchers are working towards creating it. 🔥\n3. Superintelligence: This type",
  "started_at": "2023-07-24T15:35:59.940511Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/go6aggtby57c7inaffs6w4gety",
    "cancel": "https://api.replicate.com/v1/predictions/go6aggtby57c7inaffs6w4gety/cancel"
  },
  "version": "6ab580ab4eef2c2b440f2441ec0fc0ace5470edaf2cbea50b8550aec0b3fbd38"
}

Generated in

9.8 seconds

Tweak it Report View full prediction

Run time and cost

This model costs approximately $0.0054 to run on Replicate, or 185 runs per $1, but this varies depending on your inputs. It is also open source and you can run it on your own computer with Docker.

This model runs on Nvidia L40S GPU hardware. Predictions typically complete within 6 seconds.