Instructions to use deepseek-ai/DeepSeek-R1-Distill-Qwen-14B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use deepseek-ai/DeepSeek-R1-Distill-Qwen-14B with Transformers:

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

pipe = pipeline("text-generation", model="deepseek-ai/DeepSeek-R1-Distill-Qwen-14B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("deepseek-ai/DeepSeek-R1-Distill-Qwen-14B")
model = AutoModelForCausalLM.from_pretrained("deepseek-ai/DeepSeek-R1-Distill-Qwen-14B", 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-R1-Distill-Qwen-14B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B"
# 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-R1-Distill-Qwen-14B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B

SGLang

How to use deepseek-ai/DeepSeek-R1-Distill-Qwen-14B 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-R1-Distill-Qwen-14B" \
    --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-R1-Distill-Qwen-14B",
		"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-R1-Distill-Qwen-14B" \
        --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-R1-Distill-Qwen-14B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use deepseek-ai/DeepSeek-R1-Distill-Qwen-14B with Docker Model Runner:
```
docker model run hf.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B
```

Why change the configuration of the tokenizer?

by Lingrui - opened Jan 22, 2025

Discussion

Lingrui

Jan 22, 2025

•

edited Jan 22, 2025

Why change the configuration of the tokenizer instead of continuing to use Qwen2.5's chat template?

From what I have observed, the Distill model tokenizer has replaced the token IDs that were already trained in the Qwen2.5-Instruct model. I believe these token IDs might have been assigned certain meanings by the model. However, the structure of the Distill chat template could potentially alter the meanings of these token IDs. Could this lead to a decline in performance or make it more difficult to inject new capabilities?

GeeeekExplorer

DeepSeek org Jan 22, 2025

These tokens from Qwen are reserved for multimodal models. We replace them for the reasoning model.

CHNtentes

Jan 23, 2025

These tokens from Qwen are reserved for multimodal models. We replace them for the reasoning model.

May I ask why you use '<｜' and '｜>' instead of '<|' and '|>'? Not a very common pick.

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