Text Generation
English
deepseek_v4
deepseek
Mixture of Experts
sovereign
agentic
speculative-decoding
4-bit precision
gptq
Instructions to use Codexcoder/deepseek-v4-sovereign with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Local Apps Settings
- vLLM
How to use Codexcoder/deepseek-v4-sovereign with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Codexcoder/deepseek-v4-sovereign" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Codexcoder/deepseek-v4-sovereign", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Codexcoder/deepseek-v4-sovereign
- SGLang
How to use Codexcoder/deepseek-v4-sovereign 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 "Codexcoder/deepseek-v4-sovereign" \ --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": "Codexcoder/deepseek-v4-sovereign", "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 "Codexcoder/deepseek-v4-sovereign" \ --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": "Codexcoder/deepseek-v4-sovereign", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use Codexcoder/deepseek-v4-sovereign with Docker Model Runner:
docker model run hf.co/Codexcoder/deepseek-v4-sovereign
SOVEREIGN — sovereign AI model card (derived from DeepSeek-V4-Flash-0731): specs, config, tokenizer, generation config
f6fec0c verified | { | |
| "tokenizer_class": "LlamaTokenizer", | |
| "model_max_length": 1048576, | |
| "padding_side": "right", | |
| "truncation_side": "right", | |
| "bos_token": "<|begin▁of▁sentence|>", | |
| "eos_token": "<|end▁of▁sentence|>", | |
| "pad_token": "<|end▁of▁sentence|>", | |
| "unk_token": "<|unk|>", | |
| "chat_template_note": "Use encoding_dsv4 (see models/deepseek-v4-flash-0731/docs) — no Jinja template ships with this release." | |
| } | |