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

Libraries

How to use unsloth/DeepSeek-V4-Pro with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("unsloth/DeepSeek-V4-Pro")
model = AutoModelForCausalLM.from_pretrained("unsloth/DeepSeek-V4-Pro")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use unsloth/DeepSeek-V4-Pro with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "unsloth/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": "unsloth/DeepSeek-V4-Pro",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/unsloth/DeepSeek-V4-Pro

SGLang

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

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

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text

 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+DeepSeek_V4.pdf filter=lfs diff=lfs merge=lfs -text

unsloth
/

DeepSeek-V4-Pro

Mirror worker 1

+version https://git-lfs.github.com/spec/v1
+oid sha256:fa4a3490e2dcc03c9da61b04a8be471795e9966ebbbf292a3899fa62683a330e
+size 4479901

+version https://git-lfs.github.com/spec/v1
+oid sha256:0ef64d991b80c86f24bd78d1bac9d452d95bc78e6b1d8feb6a182dae0240c7e5
+size 1853358176

+version https://git-lfs.github.com/spec/v1
+oid sha256:65d633781dad4735df26ad1ad428592513088ff9c5649ef4aae0ad80ead8abe1
+size 13868522072

+version https://git-lfs.github.com/spec/v1
+oid sha256:64159da36792f522305d580b725941c5b0abd29808c41eb944b8e9c8b1a85146
+size 13868524408

	@@ -0,0 +1,3 @@

	@@ -0,0 +1,3 @@

	@@ -0,0 +1,3 @@

	@@ -0,0 +1,3 @@