Text Generation
Transformers
Safetensors
deepseek_v4
conversational
Eval Results
8-bit precision
fp8
Instructions to use deepseek-ai/DeepSeek-V4-Pro with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
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") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# 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") - Inference
- HuggingChat
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
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/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "deepseek-ai/DeepSeek-V4-Pro", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/deepseek-ai/DeepSeek-V4-Pro
- SGLang
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/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "deepseek-ai/DeepSeek-V4-Pro", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'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/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "deepseek-ai/DeepSeek-V4-Pro", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - 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
Upload wms-pro-dashboard-template (1).zip
#178 opened about 16 hours ago
by
hamid2015
Upload 11 files
#177 opened about 16 hours ago
by
hamid2015
Fixed a type annotation.
#175 opened 4 days ago
by
LIghtJUNction
Add Claw-Eval evaluation results
#173 opened 5 days ago
by
SaylorTwift
Question about causal safety in DeepSeek-V4 CSA prefill retrieval
#172 opened 6 days ago
by
Prachi01
Update README.md
#170 opened 7 days ago
by
nerualll63
Too much positivity bias
1
#169 opened 10 days ago
by
Monblant
Thank You, DeepSeek! Empower Local Open Source with Smaller Models for Consumer Hardware/感谢 DeepSeek!赋能本地开源,社区强烈呼吁推出适合家用硬件的小型模型 (
👍 3
5
#168 opened 12 days ago
by
VaLtEc-BoY
Deepseek web issue
#167 opened 13 days ago
by
NukeNotNull
Performance feedback
1
#166 opened 14 days ago
by
toton12
Add YC-Bench benchmark result (avg $1,066,426)
#165 opened 15 days ago
by
RiddleHe
Will there be small models like 12b?
👍👀 4
14
#164 opened 15 days ago
by
Crownelius
Assigned weights for different teachers. 教师权重的分配
#162 opened 16 days ago
by
lsh-algorithm
Where is HCA implemented?
2
#161 opened 16 days ago
by
lsh-algorithm
思考链下会出现英文混乱
6
#160 opened 16 days ago
by
smodeltest
Partial Rotary Positional Embedding 的笔误?
👀 4
#159 opened 17 days ago
by
WKQ9411
模型文件注释里的形状似乎写错了
#158 opened 18 days ago
by
yzll
什么时候支持api上传文档就好了
1
#156 opened 19 days ago
by
icbw
deepseek-ai/DeepSeek-V4-Pro
1
#153 opened 20 days ago
by
cmax123
16 - 24B models with FP8 quantization
👍 4
6
#152 opened 20 days ago
by
Duonglv
Support other low-bit quantization methods?
1
#151 opened 21 days ago
by
kiwei91
源神启动!恭喜deepseekV4顺利上线,合影!
3
#150 opened 21 days ago
by
JCrainy
Общение
11
#149 opened 21 days ago
by
Lev0478
Update README.md to add SGLang deployment option
#148 opened 22 days ago
by
zjxia
Add pipeline tag to allow for HF Inference Providers
#147 opened 22 days ago
by
nbroad
Add chat template
🔥 1
1
#146 opened 22 days ago
by
Rocketknight1
Instruction following still not good
4
#145 opened 22 days ago
by
xcx0902
核弹 椅子 摔 瘫坐
2
#144 opened 22 days ago
by
shishen
Is it possible to have API output with origin completion prompt including | DSML | token
1
#143 opened 22 days ago
by
httpwwwfszyc
恭喜deepseek v4可以撑地了
🚀 6
#142 opened 22 days ago
by
keflag
代码能力真的是世界第一吗!!!
2
#141 opened 22 days ago
by
LumiDriz
开源的模型可以自己去评测,闭源的模型怎么测试呢?最近扎堆发布,GPT5.5,HY3.0 Preview,大家是不是内部都知道各个产品的时间呢?
3
#140 opened 22 days ago
by
dennisbo
deepseek niu bee plus
#134 opened 22 days ago
by
shanxinle
I'm very disappointed in this release
🔥➕ 16
11
#131 opened 22 days ago
by
Dampfinchen
DeepSeek 666
#130 opened 22 days ago
by
dingwenzheng
Technical Report Summary
🧠 2
#129 opened 22 days ago
by
mishig
Legendary drop
🔥 2
1
#128 opened 22 days ago
by
kamell
关于 "Observations and Proposals" 中激活函数建议的疑问:去掉 gate projection 为何能放宽 EP 带宽要求?
2
#126 opened 22 days ago
by
MarjorTom
Help me recover my deepseek account
❤️ 2
1
#125 opened 22 days ago
by
lulavc
请问是否有计划出自己的coding plan?
#124 opened 22 days ago
by
jackz990