Instructions to use deepseek-ai/DeepSeek-V4.1-Flash-1017 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use deepseek-ai/DeepSeek-V4.1-Flash-1017 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="deepseek-ai/DeepSeek-V4.1-Flash-1017") messages = [ { "role": "user", "content": [ {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"}, {"type": "text", "text": "What animal is on the candy?"} ] }, ] pipe(text=messages)# pip install -U transformers accelerate # Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("deepseek-ai/DeepSeek-V4.1-Flash-1017", device_map="auto") - Inference
- HuggingChat
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use deepseek-ai/DeepSeek-V4.1-Flash-1017 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "deepseek-ai/DeepSeek-V4.1-Flash-1017" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "deepseek-ai/DeepSeek-V4.1-Flash-1017", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] }'Use Docker
docker model run hf.co/deepseek-ai/DeepSeek-V4.1-Flash-1017
- SGLang
How to use deepseek-ai/DeepSeek-V4.1-Flash-1017 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-V4.1-Flash-1017" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "deepseek-ai/DeepSeek-V4.1-Flash-1017", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] }'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-V4.1-Flash-1017" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "deepseek-ai/DeepSeek-V4.1-Flash-1017", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] }' - Docker Model Runner
How to use deepseek-ai/DeepSeek-V4.1-Flash-1017 with Docker Model Runner:
docker model run hf.co/deepseek-ai/DeepSeek-V4.1-Flash-1017
Add CWE-bench evaluation result
Summary
This PR adds the CWE-bench result for deepseek-ai/DeepSeek-V4.1-Flash-1017 to .eval_results/, following the Hugging Face Hub eval results specification. CWE-bench is a defensive-security agent benchmark: 100 Harbor tasks across 91 CWE types and 8 languages, where the agent has to find and patch a vulnerability without breaking normal behavior.
Benchmarks Added
- CWE-bench: 57.0
resolve_rate is the mean reward over 400 rollouts (100 tasks × 4 attempts), the pass@1 column of the leaderboard.
Source
- Results: CWE-bench leaderboard and the dataset card, published by the benchmark authors (Collinear AI), updated 2026-11-03, listed as "DeepSeek V4.1 Flash (1017)"
- Model card: https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash-1017
Files Added
.eval_results/cwe-bench.yaml
Verification
The score was run by the CWE-bench authors with their Harbor harness, not by the model authors. No verify token, since it wasn't run through HF Jobs.
Bonjour