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)

# 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)
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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

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
```

deepseek v3.1在理解用户问题能力/指令遵循上变得有些奇怪

#44

by ChrisJuanes - opened Aug 21, 2025

Discussion

ChrisJuanes

Aug 21, 2025

在 deepseek 更新到v3.1 以后，对于指令遵循似乎出现了一些奇怪的偏移

例如提问【JS如何获取当前时间，格式为〝2025-08-21 10:17:32"】时
在 V3-0324 上会正确的给出js 的代码，如下：

要在JavaScript中获取当前时间并格式化为“2025-08-21 10:17:32”的标准字符串，可通过以下几种方法实现，涵盖原生API和第三方库方案：
1. 原生Date对象 + 手动格式化
....

但是V3.1以后，DS会尝试去编写创建页面的代码:

获取当前时间并格式化显示
我将创建一个页面，展示如何使用JavaScript获取当前时间并格式化为"2025-08-21 10:17:32"的格式。
设计思路
创建一个简洁现代的界面
显示实时更新的格式化时间
提供手动刷新按钮
展示JavaScript实现代码
实现代码
...

在 V3.1上这个理解为需要创建一个网页的的回复有比较高的概率出现(deepseek web 版 2025/08/21)

ChrisJuanes changed discussion title from deepseek 在理解用户问题能力/指令遵循上变得有些奇怪 to deepseek v3.1在理解用户问题能力/指令遵循上变得有些奇怪 Aug 21, 2025

Arker

Aug 21, 2025

base模型,不擅长指令遵循

ChrisJuanes

Aug 21, 2025

似乎在在https://huggingface.co/deepseek-ai/DeepSeek-V3.1 也出现了这个问题

base模型,不擅长指令遵循

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