Instructions to use deepseek-ai/DeepSeek-V3.2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use deepseek-ai/DeepSeek-V3.2 with Transformers:

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

pipe = pipeline("text-generation", model="deepseek-ai/DeepSeek-V3.2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("deepseek-ai/DeepSeek-V3.2", dtype="auto")

Inference
HuggingChat
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use deepseek-ai/DeepSeek-V3.2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "deepseek-ai/DeepSeek-V3.2"
# 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-V3.2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/deepseek-ai/DeepSeek-V3.2

SGLang

How to use deepseek-ai/DeepSeek-V3.2 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-V3.2" \
    --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-V3.2",
		"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-V3.2" \
        --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-V3.2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use deepseek-ai/DeepSeek-V3.2 with Docker Model Runner:
```
docker model run hf.co/deepseek-ai/DeepSeek-V3.2
```

miss chat template file?

by reking - opened Dec 1, 2025

Discussion

reking

Dec 1, 2025

no chat template in tokenizer_config.json file, could we use the file provided in V3.2-exp

jinmingyi

Dec 1, 2025

but tool call changed a lot

wangtianshu

Dec 2, 2025

•

edited Dec 2, 2025

~~I tried the v3.2-exp template, and it looks normal in scenarios not involving tool calls.~~

AIR-hl

Dec 2, 2025

Is there anyone have a solution?

bryanangkawidjaya

Dec 2, 2025

•

edited Dec 2, 2025

Quoting from the README:

import transformers
# encoding/encoding_dsv32.py
from encoding_dsv32 import encode_messages, parse_message_from_completion_text

tokenizer = transformers.AutoTokenizer.from_pretrained("deepseek-ai/DeepSeek-V3.2")

messages = [
    {"role": "user", "content": "hello"},
    {"role": "assistant", "content": "Hello! I am DeepSeek.", "reasoning_content": "thinking..."},
    {"role": "user", "content": "1+1=?"}
]
encode_config = dict(thinking_mode="thinking", drop_thinking=True, add_default_bos_token=True)

# messages -> string
prompt = encode_messages(messages, **encode_config)
# Output: "<｜begin▁of▁sentence｜><｜User｜>hello<｜Assistant｜></think>Hello! I am DeepSeek.<｜end▁of▁sentence｜><｜User｜>1+1=?<｜Assistant｜><think>"

# string -> tokens
tokens = tokenizer.encode(prompt)
# Output: [0, 128803, 33310, 128804, 128799, 19923, 3, 342, 1030, 22651, 4374, 1465, 16, 1, 128803, 19, 13, 19, 127252, 128804, 128798]

This release does not include a Jinja-format chat template. Please refer to the Python code mentioned above.

The encode_messagesfunction acts roughly the same way as a typical Jinja2 chat template, where given messages and other args, in return, you'll get the "rendered" prompt string that you can send for Completions. A slight thing to look out for are for tool definitions, response format, etc, where this new approach defines them as messages attributes.

I encourage you to read through the render_messages() function. It is very intuitive and easy to read. For me personally, this is a better approach and is better than reading through Jinja2 template. For the most part, the encoding_dsv32.py file still contains quite a lot of template strings. But the logic and branching is easier to read through and debug, because all is done in standard Python.

Hope this helps.

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