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

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/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

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/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
```

joelniklaus HF Staff commited on 29 days ago

Commit

4efaecd

verified ·

1 Parent(s): b5968e9

Add LEXam-hard evaluation result

Browse files

Adds this model's score on the [LEXam-hard](https://huggingface.co/datasets/joelniklaus/LEXam-hard) benchmark, the 518 LEXam open questions the strongest open models score lowest on.

The score is the pooled mean DeepSeek-R1-0528 judge grade (0-100) over those questions, recomputed from the per-sample outputs of the [SwissLegalEvals](https://huggingface.co/blog/joelniklaus/swiss-legal-evals) run (lighteval, LEXam paper prompts, one response per question, no tools). The raw outputs are in the public `joelniklaus/SwissLegalEvals` bucket; the recomputation is `reproduction/lexam_hard_results.py` in the dataset repository.

Files changed (1) hide show

.eval_results/lexam-hard.yaml +12 -0

.eval_results/lexam-hard.yaml ADDED Viewed

	@@ -0,0 +1,12 @@

+- dataset:
+    id: joelniklaus/LEXam-hard
+    task_id: lexam_hard
+    revision: ed6d99edf964592f1a1d34f52ca9158ceda0f7af
+  value: 39.17
+  date: '2026-06-13'
+  source:
+    url: https://huggingface.co/buckets/joelniklaus/SwissLegalEvals
+    name: SwissLegalEvals per-sample details (lighteval)
+    user: joelniklaus
+  notes: lighteval, LEXam paper prompts, one response per question, no tools; DeepSeek-R1-0528 judge;
+    pooled mean over the 518 questions, 0-100