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")

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

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

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
```

danielhanchen commited on Apr 24

Commit

249c19e

verified ·

1 Parent(s): 0317e1c

Mirror worker 5

Browse files

Files changed (9) hide show

model-00005-of-00064.safetensors +3 -0
model-00013-of-00064.safetensors +3 -0
model-00021-of-00064.safetensors +3 -0
model-00029-of-00064.safetensors +3 -0
model-00037-of-00064.safetensors +3 -0
model-00045-of-00064.safetensors +3 -0
model-00053-of-00064.safetensors +3 -0
model-00061-of-00064.safetensors +3 -0
model.safetensors.index.json +3 -0

model-00005-of-00064.safetensors ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:0833ba3fc3c9976388a72cc6f25fb2e9e3c7971bd7f9b21e651891f118852d8b
+size 13868522072

model-00013-of-00064.safetensors ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:20329c33fa44137d57a1cd6908cae0d667f2dc242a969899b2aa139c8df5addd
+size 13868524408

model-00021-of-00064.safetensors ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:0a60b02dc21dcf513fdd1c30ad6cdd91f9ff3943d77f1c085b1aa0525663186d
+size 13868524408

model-00029-of-00064.safetensors ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:cd38adfa81f429167f29db3a6381ade884cb9d718aa6f44aa013c35e621ec829
+size 13868524408

model-00037-of-00064.safetensors ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:e437b266df8e8f9381ddc3fb096a2cd7425aa61884e9be5e280034404f78ad57
+size 13868524408

model-00045-of-00064.safetensors ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:644bf603deaa4cef01778269b434dc5b15e38835a8d6b19b61cfba1f719d7025
+size 13868524408

model-00053-of-00064.safetensors ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:d9a746bf9bb208e5f07641a432e6f9d1194a4f8986ac6214a6335a05ec0b8be3
+size 13868524408

model-00061-of-00064.safetensors ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:b76467b20ebe9ca4952cbea00e5ea94c353ae472fae82d4fff824d107fea2b18
+size 13868524408

model.safetensors.index.json ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:a3a39b9ccb4e729851922fc9c770f5c5755e7b9d7e96cd02c23f0e12b5e25cb9
+size 11305684