meta/llama-2-13b-chat:56acad22 – Run with an API on Replicate

meta /llama-2-13b-chat:56acad22

Input

prompt

*string

Shift + Return to add a new line

User: Respond to this question only based on the information provided here. Cats like dogs, and dogs like rabbits. Cats like anything that dogs like. I really really dislike rabbits. How do cats feel about rabbits?
Assistant:User: Respond to this question only based on the information provided here. Cats like dogs, and dogs like rabbits. Cats like anything that dogs like. I really really dislike rabbits. How do cats feel about rabbits?
Assistant:

Prompt to send to Llama v2.

max_length

integer

(minimum: 1)

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

Default: 500

temperature

number

(minimum: 0.01, maximum: 5)

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

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: 1

repetition_penalty

number

(minimum: 0.01, 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

debug

boolean

provide debugging output in logs

Default: false

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 output = await replicate.run(
  "meta/llama-2-13b-chat:56acad22679f6b95d6e45c78309a2b50a670d5ed29a37dd73d182e89772c02f1",
  {
    input: {
      debug: false,
      top_p: 0.2,
      prompt: "User: Respond to this question only based on the information provided here. Cats like dogs, and dogs like rabbits. Cats like anything that dogs like. I really really dislike rabbits. How do cats feel about rabbits?\nAssistant:",
      max_length: 500,
      temperature: 0.75,
      repetition_penalty: 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 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:56acad22679f6b95d6e45c78309a2b50a670d5ed29a37dd73d182e89772c02f1",
    input={
        "debug": False,
        "top_p": 0.2,
        "prompt": "User: Respond to this question only based on the information provided here. Cats like dogs, and dogs like rabbits. Cats like anything that dogs like. I really really dislike rabbits. How do cats feel about rabbits?\nAssistant:",
        "max_length": 500,
        "temperature": 0.75,
        "repetition_penalty": 1
    }
)

# 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=<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 $'{
    "version": "56acad22679f6b95d6e45c78309a2b50a670d5ed29a37dd73d182e89772c02f1",
    "input": {
      "debug": false,
      "top_p": 0.2,
      "prompt": "User: Respond to this question only based on the information provided here. Cats like dogs, and dogs like rabbits. Cats like anything that dogs like. I really really dislike rabbits. How do cats feel about rabbits?\\nAssistant:",
      "max_length": 500,
      "temperature": 0.75,
      "repetition_penalty": 1
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

Based on the information provided, cats like dogs, and dogs like rabbits. Since cats like anything that dogs like, it can be inferred that cats also like rabbits. However, you mentioned that you really dislike rabbits, so it's possible that cats may not share the same sentiment.

Generated in

4.1 seconds

Tweak it Report