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

Libraries

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

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("deepseek-ai/DeepSeek-V3.2-Exp")
model = AutoModelForCausalLM.from_pretrained("deepseek-ai/DeepSeek-V3.2-Exp", 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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Inference
HuggingChat
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

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

Use Docker

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

SGLang

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

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

GeeeekExplorer commited on Sep 29, 2025

Commit

72cacec

1 Parent(s): 600c271

add figure

Browse files

Files changed (3) hide show

.gitattributes +1 -0
README.md +2 -2
assets/cost.png +3 -0

.gitattributes CHANGED Viewed

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text

 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+assets/cost.png filter=lfs diff=lfs merge=lfs -text

README.md CHANGED Viewed

@@ -2,7 +2,7 @@
 license: mit
 library_name: transformers
 base_model:
-  - deepseek-ai/DeepSeek-V3.1-Base
 ---
 # DeepSeek-V3.2-Exp
@@ -50,7 +50,7 @@ We are excited to announce the official release of DeepSeek-V3.2-Exp, an experim
 This experimental release represents our ongoing research into more efficient transformer architectures, particularly focusing on improving computational efficiency when processing extended text sequences.
 <div align="center">
- <img src="cost.jpg" >
 </div>
 - DeepSeek Sparse Attention (DSA) achieves fine-grained sparse attention for the first time, delivering substantial improvements in long-context training and inference efficiency while maintaining virtually identical model output quality.

 license: mit
 library_name: transformers
 base_model:
+  - deepseek-ai/DeepSeek-V3.2-Exp-Base
 ---
 # DeepSeek-V3.2-Exp
 This experimental release represents our ongoing research into more efficient transformer architectures, particularly focusing on improving computational efficiency when processing extended text sequences.
 <div align="center">
+ <img src="assets/cost.png" >
 </div>
 - DeepSeek Sparse Attention (DSA) achieves fine-grained sparse attention for the first time, delivering substantial improvements in long-context training and inference efficiency while maintaining virtually identical model output quality.

assets/cost.png ADDED Viewed

Git LFS Details

SHA256: d4b8e78d9a3220108e480bb44383b03a0d8ccbf7fc41ac113c5e67f5d7c8a44d
Pointer size: 131 Bytes
Size of remote file: 102 kB