nateraw/wizard-mega-13b-awq – Run with an API on Replicate

nateraw / wizard-mega-13b-awq

wizard-mega-13b quantized with AWQ and served with vLLM

Cold

Public
5.4K runs
L40S
GitHub

Run with an API

Playground API Examples README Versions

Input

message

*string

Shift + Return to add a new line

write me a short itinerary for my dog's birthday party.write me a short itinerary for my dog's birthday party.

max_new_tokens

integer

The maximum number of tokens the model should generate as output.

Default: 512

temperature

number

The value used to modulate the next token probabilities.

Default: 1

top_p

number

A probability threshold for generating the output. If < 1.0, only keep the top tokens with cumulative probability >= top_p (nucleus filtering). Nucleus filtering is described in Holtzman et al. (http://arxiv.org/abs/1904.09751).

Default: 1

top_k

integer

The number of highest probability tokens to consider for generating the output. If > 0, only keep the top k tokens with highest probability (top-k filtering).

Default: 50

presence_penalty

number

Presence penalty

Default: 1.15

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

npx create-replicate --model=nateraw/wizard-mega-13b-awq

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 nateraw/wizard-mega-13b-awq using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "nateraw/wizard-mega-13b-awq:a4be2a7c75e51c53b22167d44de3333436f1aa9253a201d2619cf74286478599",
  {
    input: {
      top_k: 50,
      top_p: 0.95,
      message: "write me a short itinerary for my dog's birthday party.",
      temperature: 0.8,
      max_new_tokens: 512,
      presence_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 nateraw/wizard-mega-13b-awq using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "nateraw/wizard-mega-13b-awq:a4be2a7c75e51c53b22167d44de3333436f1aa9253a201d2619cf74286478599",
    input={
        "top_k": 50,
        "top_p": 0.95,
        "message": "write me a short itinerary for my dog's birthday party.",
        "temperature": 0.8,
        "max_new_tokens": 512,
        "presence_penalty": 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 nateraw/wizard-mega-13b-awq 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": "a4be2a7c75e51c53b22167d44de3333436f1aa9253a201d2619cf74286478599",
    "input": {
      "top_k": 50,
      "top_p": 0.95,
      "message": "write me a short itinerary for my dog\'s birthday party.",
      "temperature": 0.8,
      "max_new_tokens": 512,
      "presence_penalty": 1
    }
  }' \
  https://api.replicate.com/v1/predictions

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

You can run this model locally using Cog. First, install Cog:

brew install cog

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

Run this to download the model and run it in your local environment:

cog predict r8.im/nateraw/wizard-mega-13b-awq@sha256:a4be2a7c75e51c53b22167d44de3333436f1aa9253a201d2619cf74286478599 \
  -i 'top_k=50' \
  -i 'top_p=0.95' \
  -i $'message="write me a short itinerary for my dog\'s birthday party."' \
  -i 'temperature=0.8' \
  -i 'max_new_tokens=512' \
  -i 'presence_penalty=1'

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

Run this to download the model and run it in your local environment:

docker run -d -p 5000:5000 --gpus=all r8.im/nateraw/wizard-mega-13b-awq@sha256:a4be2a7c75e51c53b22167d44de3333436f1aa9253a201d2619cf74286478599
curl -s -X POST \
  -H "Content-Type: application/json" \
  -d $'{
    "input": {
      "top_k": 50,
      "top_p": 0.95,
      "message": "write me a short itinerary for my dog\'s birthday party.",
      "temperature": 0.8,
      "max_new_tokens": 512,
      "presence_penalty": 1
    }
  }' \
  http://localhost:5000/predictions

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

Output

Great idea! Here's a short itinerary for your dog's birthday party: 1. Introduction: Introduce your dog to the guests and explain the plan for the day. 2. Games and Activities: Set up some fun games and activities for the dogs to play, such as a scavenger hunt, obstacle course, or agility training. 3. Cake and Presents: Cut the dog-friendly cake and let each dog have a piece. Also, set out presents for the dogs to open and play with. 4. Photo Opportunity: Take a group photo with all the dogs and guests. 5. Treats and Refreshments: Provide water and treats for the dogs and guests to enjoy. 6. Relaxation: End the party with a relaxing activity, such as a massage or belly rub for the dogs. 7. Goodbye: Thank everyone for coming and send them home with some dog-themed party favors. I hope this itinerary helps you plan a memorable birthday party for your dog!

{
  "completed_at": "2023-09-26T20:29:49.566852Z",
  "created_at": "2023-09-26T20:28:30.060819Z",
  "data_removed": false,
  "error": null,
  "id": "tvtpeolb5fv5rzljmjqnuskzem",
  "input": {
    "top_k": 50,
    "top_p": 0.95,
    "message": "write me a short itinerary for my dog's birthday party.",
    "temperature": 0.8,
    "max_new_tokens": 512,
    "presence_penalty": 1
  },
  "logs": "Processed prompts:   0%|          | 0/2 [00:00<?, ?it/s]\nProcessed prompts:  50%|█████     | 1/2 [00:04<00:04,  4.17s/it]\nProcessed prompts: 100%|██████████| 2/2 [00:05<00:00,  2.69s/it]\nProcessed prompts: 100%|██████████| 2/2 [00:05<00:00,  2.91s/it]\nGenerated 241 tokens in 5.8255774974823 seconds.",
  "metrics": {
    "predict_time": 5.952111,
    "total_time": 79.506033
  },
  "output": "Great idea! Here's a short itinerary for your dog's birthday party:\n\n1. Introduction: Introduce your dog to the guests and explain the plan for the day.\n2. Games and Activities: Set up some fun games and activities for the dogs to play, such as a scavenger hunt, obstacle course, or agility training.\n3. Cake and Presents: Cut the dog-friendly cake and let each dog have a piece. Also, set out presents for the dogs to open and play with.\n4. Photo Opportunity: Take a group photo with all the dogs and guests.\n5. Treats and Refreshments: Provide water and treats for the dogs and guests to enjoy.\n6. Relaxation: End the party with a relaxing activity, such as a massage or belly rub for the dogs.\n7. Goodbye: Thank everyone for coming and send them home with some dog-themed party favors.\n\nI hope this itinerary helps you plan a memorable birthday party for your dog!",
  "started_at": "2023-09-26T20:29:43.614741Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/tvtpeolb5fv5rzljmjqnuskzem",
    "cancel": "https://api.replicate.com/v1/predictions/tvtpeolb5fv5rzljmjqnuskzem/cancel"
  },
  "version": "a4be2a7c75e51c53b22167d44de3333436f1aa9253a201d2619cf74286478599"
}

Generated in

6.0 seconds

Tweak it Report

Run time and cost

This model costs approximately $0.0029 to run on Replicate, or 344 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 3 seconds.

Readme

Read the official model card here: https://huggingface.co/TheBloke/wizard-mega-13B-AWQ

Thank you to TheBloke for sharing this model!