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

Libraries

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

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

pipe = pipeline("text-generation", model="deepseek-ai/DeepSeek-V3", 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", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("deepseek-ai/DeepSeek-V3", 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=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 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"
# 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",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

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

SGLang

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

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

DeepSeekDDM commited on Jan 24, 2025

Commit

0cf1748

verified ·

1 Parent(s): 108e1e0

Update README_WEIGHTS.md

Browse files

Files changed (1) hide show

README_WEIGHTS.md +3 -3

README_WEIGHTS.md CHANGED Viewed

@@ -18,7 +18,7 @@ The DeepSeek-V3 weight file consists of two main components: **Main Model Weight
   - Input/output embedding layers and a complete set of 61 Transformer hidden layers.
 - **Parameter Count**:
   - Total parameters: **671B**
-  - Activation parameters: **36.6B**.
 #### Structural Details
@@ -35,8 +35,8 @@ The DeepSeek-V3 weight file consists of two main components: **Main Model Weight
 - **Composition**:
   - Additional MTP Modules defined by the `num_nextn_predict_layers` field. In this model, the value is set to 1.
 - **Parameter Count**:
-  - Parameters: **11.5B unique parameters**, excluding the shared 0.9B Embedding and 0.9B output Head).
-  - Activation parameters: **2.4B** (including the shared 0.9B Embedding and 0.9B output Head).
 #### Structural Details

   - Input/output embedding layers and a complete set of 61 Transformer hidden layers.
 - **Parameter Count**:
   - Total parameters: **671B**
+  - Activation parameters: **36.6B** (including 0.9B for the output Head).
 #### Structural Details
 - **Composition**:
   - Additional MTP Modules defined by the `num_nextn_predict_layers` field. In this model, the value is set to 1.
 - **Parameter Count**:
+  - Parameters: **11.5B unique parameters** (excluding the shared 0.9B Embedding and 0.9B output Head).
+  - Activation parameters: **1.5B** (including 0.9B for the output Head).
 #### Structural Details