Instructions to use opensourcerelease/DeepSeek-R1-bf16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use opensourcerelease/DeepSeek-R1-bf16 with Transformers:

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

pipe = pipeline("text-generation", model="opensourcerelease/DeepSeek-R1-bf16", 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("opensourcerelease/DeepSeek-R1-bf16", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("opensourcerelease/DeepSeek-R1-bf16", trust_remote_code=True)
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]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use opensourcerelease/DeepSeek-R1-bf16 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "opensourcerelease/DeepSeek-R1-bf16"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "opensourcerelease/DeepSeek-R1-bf16",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/opensourcerelease/DeepSeek-R1-bf16

SGLang

How to use opensourcerelease/DeepSeek-R1-bf16 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 "opensourcerelease/DeepSeek-R1-bf16" \
    --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": "opensourcerelease/DeepSeek-R1-bf16",
		"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 "opensourcerelease/DeepSeek-R1-bf16" \
        --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": "opensourcerelease/DeepSeek-R1-bf16",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use opensourcerelease/DeepSeek-R1-bf16 with Docker Model Runner:
```
docker model run hf.co/opensourcerelease/DeepSeek-R1-bf16
```

OpenSourceRonin commited on Jan 21, 2025

Commit

3c458a2

verified ·

1 Parent(s): 9a29778

Add files using upload-large-folder tool

Browse files

Files changed (12) hide show

model-00022-of-000163.safetensors +3 -0
model-00040-of-000163.safetensors +3 -0
model-00062-of-000163.safetensors +3 -0
model-00063-of-000163.safetensors +3 -0
model-00079-of-000163.safetensors +3 -0
model-00097-of-000163.safetensors +3 -0
model-00109-of-000163.safetensors +3 -0
model-00113-of-000163.safetensors +3 -0
model-00116-of-000163.safetensors +3 -0
model-00138-of-000163.safetensors +3 -0
model-00151-of-000163.safetensors +3 -0
model-00155-of-000163.safetensors +3 -0

+version https://git-lfs.github.com/spec/v1
+oid sha256:3f73806d4cb4f80e744b6dd6a79bd97d4c9466e48a7191066cb154f19a650fee
+size 8602554416

+version https://git-lfs.github.com/spec/v1
+oid sha256:51f26d9fb09724bd77af78f97e0f8180e323e163a1186424dc74f8877aa12ed8
+size 8598786608

+version https://git-lfs.github.com/spec/v1
+oid sha256:c5dd301776f19c530c46d38b28746fd6b46ebdedb44094f9ba467db5add10387
+size 8602554320

+version https://git-lfs.github.com/spec/v1
+oid sha256:d51a3594ec79036244fca6d106de95d6303380b8acd1e3d79d34149145264d5d
+size 8598757608

+version https://git-lfs.github.com/spec/v1
+oid sha256:b1ee6840bb4ae390869954c4abe97030a163b6479985344dc723ff957a6ac2af
+size 8598786720

+version https://git-lfs.github.com/spec/v1
+oid sha256:d4c6ba178de822b0844ef5c8b2b6d524d44c96f549bab95a05049adb0add54db
+size 8598786504

+version https://git-lfs.github.com/spec/v1
+oid sha256:effffc667d242969d444fdc6e813b1ca704f7c228605a88a967bbc82953697f5
+size 8602554448

+version https://git-lfs.github.com/spec/v1
+oid sha256:962ca7aaf44448e5365a8e918a9eae9b69be92968db82114643fba11f7b5d023
+size 8598786616

	@@ -0,0 +1,3 @@

	@@ -0,0 +1,3 @@

	@@ -0,0 +1,3 @@

	@@ -0,0 +1,3 @@