Instructions to use deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B 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-1.5B")
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-1.5B")
model = AutoModelForCausalLM.from_pretrained("deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B", 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
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B 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-1.5B"
# 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-1.5B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B

SGLang

How to use deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B 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-1.5B" \
    --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-1.5B",
		"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-1.5B" \
        --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-1.5B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B with Docker Model Runner:
```
docker model run hf.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
```

bos_token_id mismatch between model config and tokenizer

#25

by guangy10 - opened Feb 21, 2025

Discussion

guangy10

Feb 21, 2025

I'm able to export this model to ExecuTorch following this guide https://github.com/huggingface/optimum-executorch?tab=readme-ov-file#-quick-start by replacing the model_id with "deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B". When I'm running the model for inference, I got an error complaining the bos_token_id mismatch.

  File "~/optimum-executorch/optimum/executorch/modeling.py", line 351, in text_generation
    raise ValueError(
ValueError: The tokenizer's bos_token_id=151646 must be the same as the model's bos_token_id=151643.

Upon checking the config files, I notice:
In config.json, the bos_token_id is 151643: https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B/blob/main/config.json#L6-L7
And in tokenizer.json, the bos_token_id is 151646, same in generation_config.json: https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B/blob/main/generation_config.json#L3

It seems like a bug?

guangy10

Feb 21, 2025

BTW, if I switch to use "deepseek-ai/DeepSeek-R1-Distill-Llama-8B", it works e2e without any problem. So I think the issue is legitimate, and only shows in those using Qwen as the base model.

Valentin71

Mar 1, 2025

I noticed that tokenizer.all_special_tokens has only:

'<｜begin▁of▁sentence｜>', '<｜end▁of▁sentence｜>'

while tokenizer.chat_template has

'<｜User｜>', '<｜Assistant｜>', '<｜tool▁calls▁begin｜>', '<｜tool▁call▁begin｜>', '<｜tool▁sep｜>', '<think>'...

and many others. Is it bug too?
And what is the meaning of tool['type'] and difference from tool['function']['name']?

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