Instructions to use deepseek-ai/DeepSeek-V3.1-Base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use deepseek-ai/DeepSeek-V3.1-Base with Transformers:

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

pipe = pipeline("text-generation", model="deepseek-ai/DeepSeek-V3.1-Base", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("deepseek-ai/DeepSeek-V3.1-Base", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("deepseek-ai/DeepSeek-V3.1-Base", trust_remote_code=True, device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use deepseek-ai/DeepSeek-V3.1-Base with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "deepseek-ai/DeepSeek-V3.1-Base"
# 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-V3.1-Base",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/deepseek-ai/DeepSeek-V3.1-Base

SGLang

How to use deepseek-ai/DeepSeek-V3.1-Base 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-V3.1-Base" \
    --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-V3.1-Base",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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-V3.1-Base" \
        --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-V3.1-Base",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use deepseek-ai/DeepSeek-V3.1-Base with Docker Model Runner:
```
docker model run hf.co/deepseek-ai/DeepSeek-V3.1-Base
```

You made an error with SimpleQA scores

#50

by ID0M - opened Aug 21, 2025

Discussion

ID0M

Aug 21, 2025

•

edited Aug 21, 2025

EDIT: My mistake. Didn't realize this was with internet search.. Would love for them to quote the score with no tools/search.

Nocigar

Aug 21, 2025

Perhaps you meant to write something like 63.4 instead of 93.4%?

This is ridiculous and can't be right. Unless you tested it in some different unusual way, but they we can't compare this score against other models can we...

It's not an error. Because that SimpleQA is under Search Agent but not General.

koanho2

Aug 21, 2025

I think it is a base model, not an instruction-tuned model. They have not yet uploaded the 3.1 model.

mamaruo

Aug 21, 2025

I think it is a base model, not an instruction-tuned model. They have not yet uploaded the 3.1 model.

https://huggingface.co/deepseek-ai/DeepSeek-V3.1

ID0M

Aug 21, 2025

Perhaps you meant to write something like 63.4 instead of 93.4%?

This is ridiculous and can't be right. Unless you tested it in some different unusual way, but they we can't compare this score against other models can we...

It's not an error. Because that SimpleQA is under Search Agent but not General.

Yeah you are right, my bad. I realized this later and forgot about this discussion thread lol.

It would be nice for them to include the scores with no tools for this benchmark. I personally don't see much point testing world knowledge with internet access and making this benchmark saturated (which is otherwise a great metric)...

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