Instructions to use deepseek-ai/DeepSeek-V4-Flash with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use deepseek-ai/DeepSeek-V4-Flash with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="deepseek-ai/DeepSeek-V4-Flash")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("deepseek-ai/DeepSeek-V4-Flash") model = AutoModelForCausalLM.from_pretrained("deepseek-ai/DeepSeek-V4-Flash", device_map="auto") - Inference
- HuggingChat
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use deepseek-ai/DeepSeek-V4-Flash 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-Flash" # 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-Flash", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/deepseek-ai/DeepSeek-V4-Flash
- SGLang
How to use deepseek-ai/DeepSeek-V4-Flash 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-Flash" \ --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-Flash", "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-Flash" \ --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-Flash", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use deepseek-ai/DeepSeek-V4-Flash with Docker Model Runner:
docker model run hf.co/deepseek-ai/DeepSeek-V4-Flash
Commit History
-
Add user field to Claw-Eval results
Verified signaturec8fbf85 -
Add Claw-Eval evaluation results
Verified signature1202e06
-
Update technical report
6976c7f
-
Update config.json
Verified signaturefd53f94 -
Update inference/model.py
Verified signature2b2bebc
-
Update technical report
6c858e7 -
Update README
6e76323 -
Update README
fea5c29 -
Update benchmark figure
0cad8ee -
Update technical report
efc8551 -
Update technical report
a8bd4f4 -
Update technical report link
26456c7 -
Update inference/generate.py
Verified signaturead664d5 -
Upload config.json
Verified signature216d766 -
Release DeepSeek-V4
a7aaed8
-
use sys.path for encoding
Verified signatured07dda5 -
Upload folder using huggingface_hub
Verified signature24d73e8 -
add inference code
Verified signature2b88d47 -
Add files using upload-large-folder tool
Verified signature7d0cce9
-
initial commit
Verified signature1afa6f9