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

Libraries

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

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

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

Use Docker

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

SGLang

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

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

IDEA: Bitnet 1.58 (a4.8) version in future variants would be so incredible!

by apiarium - opened 6 days ago

Discussion

apiarium

6 days ago

Deepseek-V4-Pro-Dspark is incredible — thanks for releasing the weights. Would the team consider releasing a BitNet 1.58 (a4.8) variant in a future update? For anyone unfamiliar: ternary weights {-1, 0, +1} at 1.58 bits/param plus 4-bit activations means matmul becomes pure integer addition, no floating-point multipliers needed. Microsoft's bitnet.cpp already runs a 100B BitNet model on a single CPU at reading speed (5–7 tok/s) with 2–6× speedups on consumer hardware. The BitNet 1.58 paper (arXiv:2402.17764) showed perplexity parity with FP16 at 7B scale, and the a4.8 paper (arXiv:2411.04965) pushed activations down further with minimal quality loss. Training recipe is public at microsoft/unilm. A BitNet-native V4 or future versions would run offline on ordinary laptops and phones — no GPU needed — which is exactly the kind of accessibility a model this good deserves. Just putting it out there!

apiarium changed discussion title from Idea: Bitnet 1.58 (a4.8) version in future versions would be so incredible! to Idea: Bitnet 1.58 (a4.8) version in future variants would be so incredible! 6 days ago

apiarium changed discussion title from Idea: Bitnet 1.58 (a4.8) version in future variants would be so incredible! to IDEA: Bitnet 1.58 (a4.8) version in future variants would be so incredible! 6 days ago

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment