Instructions to use yuanzu/DeepSeek-R1-INT8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use yuanzu/DeepSeek-R1-INT8 with Transformers:

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

pipe = pipeline("text-generation", model="yuanzu/DeepSeek-R1-INT8", 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("yuanzu/DeepSeek-R1-INT8", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("yuanzu/DeepSeek-R1-INT8", 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 Settings

vLLM

How to use yuanzu/DeepSeek-R1-INT8 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "yuanzu/DeepSeek-R1-INT8"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "yuanzu/DeepSeek-R1-INT8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/yuanzu/DeepSeek-R1-INT8

SGLang

How to use yuanzu/DeepSeek-R1-INT8 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 "yuanzu/DeepSeek-R1-INT8" \
    --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": "yuanzu/DeepSeek-R1-INT8",
		"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 "yuanzu/DeepSeek-R1-INT8" \
        --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": "yuanzu/DeepSeek-R1-INT8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use yuanzu/DeepSeek-R1-INT8 with Docker Model Runner:
```
docker model run hf.co/yuanzu/DeepSeek-R1-INT8
```

yuanzu commited on Feb 21, 2025

Commit

e9488d7

verified ·

1 Parent(s): 8b69bfe

Add files using upload-large-folder tool

Browse files

Files changed (9) hide show

model-00024-of-000163.safetensors +3 -0
model-00025-of-000163.safetensors +3 -0
model-00028-of-000163.safetensors +3 -0
model-00069-of-000163.safetensors +3 -0
model-00080-of-000163.safetensors +3 -0
model-00122-of-000163.safetensors +3 -0
model-00143-of-000163.safetensors +3 -0
model-00158-of-000163.safetensors +3 -0
model-00160-of-000163.safetensors +3 -0

model-00024-of-000163.safetensors ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:0e8883adbea2854784a796d3ade28dc97380cf9b4dbbe286dc32c6aa59475c25
+size 4302380800

model-00025-of-000163.safetensors ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:e0cda63dd4ec452f137d7a509e6ca7596fce20b3ce5d5342b27c9c031608bb44
+size 4302381256

model-00028-of-000163.safetensors ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:b4d80040bd05b3d617e4323c9d51f91a7f3641d2168c1bbd2b53de871d666e5f
+size 4302381256

model-00069-of-000163.safetensors ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:65e69e5b07949084483353bd07e5ec91f9175fe7f206068ca1f176005bc76ab9
+size 4302381256

model-00080-of-000163.safetensors ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:23655f1fea92a32b695ac2e06e1387b070fe1f3940a494c2e6c1322ba8e639de
+size 4302381208

model-00122-of-000163.safetensors ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:5c09fc4afb3f226675271b82d193b89c6fa5f7455117eaa26ef3788777729d10
+size 1747412272

model-00143-of-000163.safetensors ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:e6bc7fb2811b4dc37c1d8277ebf379610adcafc77c248a713abb972ac4e8a538
+size 4302381208

model-00158-of-000163.safetensors ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:f442a9410f6ea548ac51431e1eb1547abe6a3f05418a77e3869b1b3eb7f10e78
+size 4302346776

model-00160-of-000163.safetensors ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:742babf1f416ff05ea53ac7ac1feb42117e4c5f30d314a801e5a6b33323c94e5
+size 5230634696