deepseek-ai
/

DeepSeek-V4-Pro

Text Generation

8-bit precision

Model card Files Files and versions

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

Libraries

How to use deepseek-ai/DeepSeek-V4-Pro with Transformers:

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

pipe = pipeline("text-generation", model="deepseek-ai/DeepSeek-V4-Pro")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

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

Inference
HuggingChat
Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use deepseek-ai/DeepSeek-V4-Pro 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-Pro"
# 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-Pro",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/deepseek-ai/DeepSeek-V4-Pro

How to use deepseek-ai/DeepSeek-V4-Pro 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-Pro" \
    --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-Pro",
		"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-Pro" \
        --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-Pro",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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

Resources

View closed (13)

即使引导早已破碎，也请您当上大语言模型之王。

#105 opened 6 months ago by

前排合影！

#104 opened 6 months ago by

deepseek王者归来

#103 opened 6 months ago by

让算了算北京新能源积分是多少，v4、gemini、豆包都沦陷了

#102 opened 6 months ago by

I just came

#101 opened 6 months ago by

开源伟大！

#100 opened 6 months ago by

deepseek，为你骄傲

#99 opened 6 months ago by

Is Engram included in V4?

#98 opened 6 months ago by

等了好久终于来了

#97 opened 6 months ago by

所以我猜是混合精度加模型太大导致暂时还没有量化的模型出来

#96 opened 6 months ago by

Not able to run deepseek v4 pro using transformers in Google Collab

#95 opened 6 months ago by

good job!!!

#94 opened 6 months ago by

Waiting for Distill 10B \ 35B \70B

#93 opened 6 months ago by

坐等27B量化，坐等Jackrong大佬蒸馏Opus^_^

#92 opened 6 months ago by

合影来了

#91 opened 6 months ago by

ds现在真的是拉完了，全面落后

#90 opened 6 months ago by

好用吗

#89 opened 6 months ago by

合影！！！

#88 opened 6 months ago by

牛逼，开源精神伟大

#87 opened 6 months ago by

终于等到你，v4合影

#86 opened 6 months ago by

为开源之光点赞

#85 opened 6 months ago by

对不起了GLM token plan，我将拥抱开源之源神

#84 opened 6 months ago by

合影合影

#83 opened 6 months ago by

恭喜DeepSeek国王陛下于今日抵达他忠实的抱抱脸

#82 opened 6 months ago by

敬你是条汉子没有4.30当天发

#81 opened 6 months ago by

Its cost is too low

#80 opened 6 months ago by

我超，源！

#79 opened 6 months ago by

WOW 1.6T Params

#78 opened 6 months ago by

向 DS 致敬 (^^ゞ

#77 opened 6 months ago by

前排合影

#76 opened 6 months ago by

862B?

#75 opened 6 months ago by

体验了会儿V4，我仿佛看到核弹炸在眼前然后从椅子上摔下来，瘫坐在地！

#74 opened 6 months ago by

Base都开源了太大方了致敬

#73 opened 6 months ago by

在此迎接开源的王

#72 opened 6 months ago by

王振兴在此祝贺DeepSeek

#71 opened 6 months ago by

AI Agent 何时出现？

#70 opened 6 months ago by

KakumuraArimura

make ds greate again

#69 opened 6 months ago by

DeepSeek威武，中国威武，终于等到你

#68 opened 6 months ago by

How to convert fp8 on Hopper?

#67 opened 6 months ago by

他妈的甘，我的苦日子终于到头了

#66 opened 6 months ago by

ds上号

#65 opened 6 months ago by

源神牛逼

#64 opened 6 months ago by

有人知道用的哪家的芯片吗？

#63 opened 6 months ago by

终于来了~

#62 opened 6 months ago by

就看哪家厂商的code plan能让我用上了

#61 opened 6 months ago by

真国货之光

#60 opened 6 months ago by

牛皮！合影留念

#59 opened 6 months ago by

未来已来

#58 opened 6 months ago by

合影留念

#57 opened 6 months ago by

牛逼！

#56 opened 6 months ago by