chenxwh/deepseek-vl2:8ea88789 | Run with an API on Replicate

Version

You're looking at a specific version of this model. Jump to the model overview.

chenxwh /deepseek-vl2:8ea88789

Playground API

Input

text

string

Shift + Return to add a new line

Input text.

Default: "Describe this image."

image1

*file

Preview

First image

image2

file

Optional, second image for multiple images image2text

image3

file

Optional, third image for multiple images image2text

max_new_tokens

integer

(minimum: 0, maximum: 4096)

The maximum numbers of tokens to generate

Default: 2048

temperature

number

The value used to modulate the probabilities of the next token. Set the temperature to 0 for deterministic generation

Default: 0.1

top_p

number

If set to float < 1, only the smallest set of most probable tokens with probabilities that add up to top_p or higher are kept for generation.

Default: 0.9

repetition_penalty

number

(minimum: 0, maximum: 2)

Repetition penalty

Default: 1.1

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

npx create-replicate --model=chenxwh/deepseek-vl2

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 chenxwh/deepseek-vl2 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "chenxwh/deepseek-vl2:8ea887897e772107ce53f3a7fa4850e78ae88b2b73ff854b4700db9f0d59c7cb",
  {
    input: {
      text: "<|ref|>The giraffe at the back.<|/ref|>",
      top_p: 0.9,
      image1: "https://raw.githubusercontent.com/deepseek-ai/DeepSeek-VL2/refs/heads/main/images/visual_grounding_1.jpeg",
      temperature: 0.1,
      max_new_tokens: 2048,
      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 chenxwh/deepseek-vl2 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "chenxwh/deepseek-vl2:8ea887897e772107ce53f3a7fa4850e78ae88b2b73ff854b4700db9f0d59c7cb",
    input={
        "text": "<|ref|>The giraffe at the back.<|/ref|>",
        "top_p": 0.9,
        "image1": "https://raw.githubusercontent.com/deepseek-ai/DeepSeek-VL2/refs/heads/main/images/visual_grounding_1.jpeg",
        "temperature": 0.1,
        "max_new_tokens": 2048,
        "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 chenxwh/deepseek-vl2 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": "chenxwh/deepseek-vl2:8ea887897e772107ce53f3a7fa4850e78ae88b2b73ff854b4700db9f0d59c7cb",
    "input": {
      "text": "<|ref|>The giraffe at the back.<|/ref|>",
      "top_p": 0.9,
      "image1": "https://raw.githubusercontent.com/deepseek-ai/DeepSeek-VL2/refs/heads/main/images/visual_grounding_1.jpeg",
      "temperature": 0.1,
      "max_new_tokens": 2048,
      "repetition_penalty": 1.1
    }
  }' \
  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/chenxwh/deepseek-vl2@sha256:8ea887897e772107ce53f3a7fa4850e78ae88b2b73ff854b4700db9f0d59c7cb \
  -i 'text="<|ref|>The giraffe at the back.<|/ref|>"' \
  -i 'top_p=0.9' \
  -i 'image1="https://raw.githubusercontent.com/deepseek-ai/DeepSeek-VL2/refs/heads/main/images/visual_grounding_1.jpeg"' \
  -i 'temperature=0.1' \
  -i 'max_new_tokens=2048' \
  -i 'repetition_penalty=1.1'

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/chenxwh/deepseek-vl2@sha256:8ea887897e772107ce53f3a7fa4850e78ae88b2b73ff854b4700db9f0d59c7cb
curl -s -X POST \
  -H "Content-Type: application/json" \
  -d $'{
    "input": {
      "text": "<|ref|>The giraffe at the back.<|/ref|>",
      "top_p": 0.9,
      "image1": "https://raw.githubusercontent.com/deepseek-ai/DeepSeek-VL2/refs/heads/main/images/visual_grounding_1.jpeg",
      "temperature": 0.1,
      "max_new_tokens": 2048,
      "repetition_penalty": 1.1
    }
  }' \
  http://localhost:5000/predictions

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

Output

img_out

text_out

<|ref|>The giraffe at the back.<|/ref|><|det|>[[583, 271, 942, 888]]<|/det|><｜end▁of▁sentence｜>

Generated in

8.5 seconds

Tweak it ShareReport