joehoover/cog-llongma-2-13b-16k – Run with an API on Replicate

joehoover / cog-llongma-2-13b-16k

Cold

Public
18 runs
A100 (80GB)

Run with an API

Playground API Examples Train README Versions

Input

prompt

*string

Shift + Return to add a new line

Prompt to send to Llama v2.

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 Llama v2. 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_new_tokens

integer

(minimum: 1)

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

Default: 500

min_new_tokens

integer

(minimum: -1)

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

Default: -1

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: 0.95

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: 0)

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

Default: 250

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: 1.15

repetition_penalty_sustain

integer

(minimum: -1)

Number of most recent tokens to apply repetition penalty to, -1 to apply to whole context

Default: 256

token_repetition_penalty_decay

integer

(minimum: 1)

Gradually decrease penalty over this many tokens

Default: 128

debug

boolean

provide debugging output in logs

Default: false

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

npx create-replicate --model=joehoover/cog-llongma-2-13b-16k

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 joehoover/cog-llongma-2-13b-16k using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "joehoover/cog-llongma-2-13b-16k:ba67b9d08d1cf840584a0339091797429c7b4520ef43f2e07f974d7f60413da4",
  {
    input: {
      debug: false,
      top_k: 250,
      top_p: 0.95,
      temperature: 0.95,
      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,
      min_new_tokens: -1,
      repetition_penalty: 1.15,
      repetition_penalty_sustain: 256,
      token_repetition_penalty_decay: 128
    }
  }
);
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 joehoover/cog-llongma-2-13b-16k using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "joehoover/cog-llongma-2-13b-16k:ba67b9d08d1cf840584a0339091797429c7b4520ef43f2e07f974d7f60413da4",
    input={
        "debug": False,
        "top_k": 250,
        "top_p": 0.95,
        "temperature": 0.95,
        "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,
        "min_new_tokens": -1,
        "repetition_penalty": 1.15,
        "repetition_penalty_sustain": 256,
        "token_repetition_penalty_decay": 128
    }
)

# The joehoover/cog-llongma-2-13b-16k 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/joehoover/cog-llongma-2-13b-16k/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 joehoover/cog-llongma-2-13b-16k 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": "ba67b9d08d1cf840584a0339091797429c7b4520ef43f2e07f974d7f60413da4",
    "input": {
      "debug": false,
      "top_k": 250,
      "top_p": 0.95,
      "temperature": 0.95,
      "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,
      "min_new_tokens": -1,
      "repetition_penalty": 1.15,
      "repetition_penalty_sustain": 256,
      "token_repetition_penalty_decay": 128
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Install Cog

brew install cog

If you don’t have Homebrew, there are other installation options available.

Pull and run joehoover/cog-llongma-2-13b-16k using Cog (this will download the full model and run it in your local environment):

cog predict r8.im/joehoover/cog-llongma-2-13b-16k@sha256:ba67b9d08d1cf840584a0339091797429c7b4520ef43f2e07f974d7f60413da4 \
  -i 'debug=false' \
  -i 'top_k=250' \
  -i 'top_p=0.95' \
  -i 'temperature=0.95' \
  -i $'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."' \
  -i 'max_new_tokens=500' \
  -i 'min_new_tokens=-1' \
  -i 'repetition_penalty=1.15' \
  -i 'repetition_penalty_sustain=256' \
  -i 'token_repetition_penalty_decay=128'

To learn more, take a look at the Cog documentation.

Pull and run joehoover/cog-llongma-2-13b-16k using Docker (this will download the full model and run it in your local environment):

docker run -d -p 5000:5000 --gpus=all r8.im/joehoover/cog-llongma-2-13b-16k@sha256:ba67b9d08d1cf840584a0339091797429c7b4520ef43f2e07f974d7f60413da4
curl -s -X POST \
  -H "Content-Type: application/json" \
  -d $'{
    "input": {
      "debug": false,
      "top_k": 250,
      "top_p": 0.95,
      "temperature": 0.95,
      "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,
      "min_new_tokens": -1,
      "repetition_penalty": 1.15,
      "repetition_penalty_sustain": 256,
      "token_repetition_penalty_decay": 128
    }
  }' \
  http://localhost:5000/predictions

Output

No output yet! Press "Submit" to start a prediction.

Run time and cost

This model runs on Nvidia A100 (80GB) GPU hardware. We don't yet have enough runs of this model to provide performance information.

Readme

This model doesn't have a readme.