Instructions to use deepseek-ai/DeepSeek-V4-Flash-Vision-Exp with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use deepseek-ai/DeepSeek-V4-Flash-Vision-Exp with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("image-text-to-text", model="deepseek-ai/DeepSeek-V4-Flash-Vision-Exp")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("deepseek-ai/DeepSeek-V4-Flash-Vision-Exp")
model = AutoModelForCausalLM.from_pretrained("deepseek-ai/DeepSeek-V4-Flash-Vision-Exp", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use deepseek-ai/DeepSeek-V4-Flash-Vision-Exp with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "deepseek-ai/DeepSeek-V4-Flash-Vision-Exp"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "deepseek-ai/DeepSeek-V4-Flash-Vision-Exp",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/deepseek-ai/DeepSeek-V4-Flash-Vision-Exp

SGLang

How to use deepseek-ai/DeepSeek-V4-Flash-Vision-Exp with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "deepseek-ai/DeepSeek-V4-Flash-Vision-Exp" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "deepseek-ai/DeepSeek-V4-Flash-Vision-Exp",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "deepseek-ai/DeepSeek-V4-Flash-Vision-Exp" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "deepseek-ai/DeepSeek-V4-Flash-Vision-Exp",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use deepseek-ai/DeepSeek-V4-Flash-Vision-Exp with Docker Model Runner:
```
docker model run hf.co/deepseek-ai/DeepSeek-V4-Flash-Vision-Exp
```

DeepSeek-V4-Flash-Vision-Exp / encoding /README.md

doubility123

Add thinking-mode encoding example and change default interactive temperature to 1.0

86f746b about 18 hours ago

preview code

Raw

History Blame Contribute Delete

2.52 kB

DeepSeek-V4 text and vision encoding

encoding_dsv4.py is the standalone prompt-format reference. It supports multi-turn conversations, tool calls, thinking modes, and interleaved image content blocks without importing the inference implementation.

OpenAI-style messages

from encoding_dsv4 import encode_messages

messages = [{
    "role": "user",
    "content": [
        {"type": "text", "text": "第一张图"},
        {
            "type": "image_url",
            "image_url": {"url": "examples/images/carrots.jpeg"},
        },
        {"type": "text", "text": "有什么内容？"},
    ],
}]

# non-thinking
prompt, media = encode_messages(
    messages,
    thinking_mode="chat",
    return_multi_modal_data=True,
)
# prompt:
# '<｜begin▁of▁sentence｜><｜User｜>第一张图\n\n<｜deepseek_image｜>\n\n有什么内容？<｜Assistant｜></think>'


# # thinking with `max` reasoning_effort
# prompt, media = encode_messages(
#     messages,
#     thinking_mode="thinking",
#     reasoning_effort="max",
#     return_multi_modal_data=True,
# )
# prompt:
# <｜begin▁of▁sentence｜>Reasoning Effort: Beyond maximum — exhaustive, relentless, and uncompromising.\nYou MUST reason with the utmost depth and rigor, leaving absolutely nothing to chance: exhaustively decompose the problem into its most fundamental components, trace every causal chain to its root, and resolve the underlying cause rather than any surface symptom.\nDo not stop reasoning until you have independently verified the solution from multiple angles and are certain that no assumption remains unchecked and no error remains undiscovered.\n\n<｜User｜>第一张图\n\n<｜deepseek_image｜>\n\n有什么内容？<｜Assistant｜><think>

Images are represented in the prompt by <｜deepseek_image｜>. media["images"] contains the corresponding image records in exactly the same order. Pixel loading and expansion into model image tokens are handled by inference/image_processor.py.

Compact TXT notation

parse_tagged_text() converts a compact prompt such as

第一张图<image>examples/images/carrots.jpeg</image>有什么内容？

into the same standard content blocks. It is an input convenience layer, not a second encoding implementation.

Tests

From the repository root:

python -m pytest -q encoding/test_encoding_dsv4.py

The tests include a check that the TXT and JSON examples encode to the same prompt and preserve the same two-image ordering.