hayooucom/vision-llama3 – Run with an API on Replicate

hayooucom / vision-llama3

for test

Cold

Public
256 runs
L40S

Iterate in playground

Run with an API

Playground API Examples README Versions

Input

prompt

string

Shift + Return to add a new line

Text prompt to send to the model.

Default: "hello ,who are you?"

max_new_tokens

integer

(minimum: 1, maximum: 128000)

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

Default: 200

max_tokens

integer

(minimum: 1, maximum: 128000)

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

Default: 45000

temperature

number

(minimum: 0, maximum: 5)

Adjusts randomness of outputs, greater than 1 is random and 0 is deterministic.

Default: 0.1

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

top_k

integer

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

Default: 1

repetition_penalty

number

(minimum: 0.01, maximum: 10)

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

system_prompt

string

Shift + Return to add a new line

System prompt.

Default: "You are a helpful AI assistant."

image_url

string[]

https://support.content.office.net/en-us/media/3dd2b79b-9160-403d-9967-af893d17b580.png

public image url.

Default: []

image_base64

string[]

image data base64 if no image url,use this.

Default: []

seed

integer

The seed for the random number generator

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

npx create-replicate --model=hayooucom/vision-llama3

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 hayooucom/vision-llama3 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "hayooucom/vision-llama3:26d113799e1efd638526bc541ba79241b786354388355beb79c249fd8a22d35c",
  {
    input: {
      top_k: 1,
      top_p: 1,
      prompt: "describe this image",
      image_url: ["https://support.content.office.net/en-us/media/3dd2b79b-9160-403d-9967-af893d17b580.png"],
      max_tokens: 45000,
      temperature: 0.1,
      image_base64: [],
      system_prompt: "You are a helpful AI assistant.",
      max_new_tokens: 200,
      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 hayooucom/vision-llama3 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "hayooucom/vision-llama3:26d113799e1efd638526bc541ba79241b786354388355beb79c249fd8a22d35c",
    input={
        "top_k": 1,
        "top_p": 1,
        "prompt": "describe this image",
        "image_url": ["https://support.content.office.net/en-us/media/3dd2b79b-9160-403d-9967-af893d17b580.png"],
        "max_tokens": 45000,
        "temperature": 0.1,
        "image_base64": [],
        "system_prompt": "You are a helpful AI assistant.",
        "max_new_tokens": 200,
        "repetition_penalty": 1.1
    }
)

# The hayooucom/vision-llama3 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/hayooucom/vision-llama3/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 hayooucom/vision-llama3 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": "hayooucom/vision-llama3:26d113799e1efd638526bc541ba79241b786354388355beb79c249fd8a22d35c",
    "input": {
      "top_k": 1,
      "top_p": 1,
      "prompt": "describe this image",
      "image_url": ["https://support.content.office.net/en-us/media/3dd2b79b-9160-403d-9967-af893d17b580.png"],
      "max_tokens": 45000,
      "temperature": 0.1,
      "image_base64": [],
      "system_prompt": "You are a helpful AI assistant.",
      "max_new_tokens": 200,
      "repetition_penalty": 1.1
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

The image is a screenshot of an Excel spreadsheet with the title "Sales Report". It contains data related to sales, including product names, quantities sold (Qtr 1 and Qtr 2), and total sales amounts. The products listed are Chocolade, Gummibären, Scottish Longbreads, Sir Rodney's Scones, Tarte au sucre, and Chocolate Biscuits. Each row represents a different product, and there is a column for each quarter's sales figures as well as a column for the grand total. The background color of the cells alternates between white and light blue, which helps in distinguishing between rows. The font used throughout the spreadsheet is sans-serif, and the numbers are aligned to the right within their cells.

{
  "completed_at": "2024-05-24T04:17:34.092885Z",
  "created_at": "2024-05-24T04:15:52.501000Z",
  "data_removed": false,
  "error": null,
  "id": "4dnx5rqppnrgg0cfn37rmqfmnr",
  "input": {
    "top_k": 1,
    "top_p": 1,
    "prompt": "describe this image",
    "image_url": [
      "https://support.content.office.net/en-us/media/3dd2b79b-9160-403d-9967-af893d17b580.png"
    ],
    "max_tokens": 45000,
    "temperature": 0.1,
    "image_base64": [],
    "system_prompt": "You are a helpful AI assistant.",
    "max_new_tokens": 200,
    "repetition_penalty": 1.1
  },
  "logs": "max_tokens 45000\ntoken_count0 3\nstop_ids [27, 27, 128009]\nres The image is a screenshot of an Excel spreadsheet with the title \"Sales Report\". It contains data related to sales, including product names, quantities sold (Qtr 1 and Qtr 2), and total sales amounts. The products listed are Chocolade, Gummibären, Scottish Longbreads, Sir Rodney's Scones, Tarte au sucre, and Chocolate Biscuits. Each row represents a different product, and there is a column for each quarter's sales figures as well as a column for the grand total. The background color of the cells alternates between white and light blue, which helps in distinguishing between rows. The font used throughout the spreadsheet is sans-serif, and the numbers are aligned to the right within their cells.",
  "metrics": {
    "predict_time": 11.39407,
    "total_time": 101.591885
  },
  "output": [
    "The image is a screenshot of an Excel spreadsheet with the title \"Sales Report\". It contains data related to sales, including product names, quantities sold (Qtr 1 and Qtr 2), and total sales amounts. The products listed are Chocolade, Gummibären, Scottish Longbreads, Sir Rodney's Scones, Tarte au sucre, and Chocolate Biscuits. Each row represents a different product, and there is a column for each quarter's sales figures as well as a column for the grand total. The background color of the cells alternates between white and light blue, which helps in distinguishing between rows. The font used throughout the spreadsheet is sans-serif, and the numbers are aligned to the right within their cells."
  ],
  "started_at": "2024-05-24T04:17:22.698815Z",
  "status": "succeeded",
  "urls": {
    "stream": "https://streaming-api.svc.us.c.replicate.net/v1/streams/jerxn2a7w23rlsjgd5jcaw5sroomgxh6lmx32xo6evkb2i6nhwpa",
    "get": "https://api.replicate.com/v1/predictions/4dnx5rqppnrgg0cfn37rmqfmnr",
    "cancel": "https://api.replicate.com/v1/predictions/4dnx5rqppnrgg0cfn37rmqfmnr/cancel"
  },
  "version": "26d113799e1efd638526bc541ba79241b786354388355beb79c249fd8a22d35c"
}

Generated in

11.4 seconds

Tweak it Share Report

Run time and cost

This model costs approximately $0.0051 to run on Replicate, or 196 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.

Readme

test