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

Libraries

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

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

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

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

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

Install from pip and serve model

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

Use Docker

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

SGLang

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

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

DeepSeek-V4-Pro / inference /config.json

SinterForge

Duplicate from deepseek-ai/DeepSeek-V4-Pro

321811e 13 days ago

raw

history blame contribute delete

1.07 kB

	{
	"vocab_size": 129280,
	"dim": 7168,
	"moe_inter_dim": 3072,
	"n_layers": 61,
	"n_hash_layers": 3,
	"n_heads": 128,
	"n_routed_experts": 384,
	"n_shared_experts": 1,
	"n_activated_experts": 6,
	"score_func": "sqrtsoftplus",
	"route_scale": 2.5,
	"swiglu_limit": 10.0,
	"q_lora_rank": 1536,
	"head_dim": 512,
	"rope_head_dim": 64,
	"o_groups": 16,
	"o_lora_rank": 1024,
	"window_size": 128,
	"original_seq_len": 65536,
	"rope_theta": 10000,
	"rope_factor": 16,
	"beta_fast": 32,
	"beta_slow": 1,
	"index_n_heads": 64,
	"index_head_dim": 128,
	"index_topk": 512,
	"hc_mult": 4,
	"hc_sinkhorn_iters": 20,
	"dtype": "fp8",
	"scale_fmt": "ue8m0",
	"expert_dtype": "fp4",
	"compress_rope_theta": 160000,
	"compress_ratios": [128, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 0]
	}