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

Libraries

How to use unsloth/DeepSeek-R1 with Transformers:

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

pipe = pipeline("text-generation", model="unsloth/DeepSeek-R1", 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("unsloth/DeepSeek-R1", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("unsloth/DeepSeek-R1", 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 unsloth/DeepSeek-R1 with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/unsloth/DeepSeek-R1

SGLang

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

Unsloth Studio new

How to use unsloth/DeepSeek-R1 with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for unsloth/DeepSeek-R1 to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for unsloth/DeepSeek-R1 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for unsloth/DeepSeek-R1 to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="unsloth/DeepSeek-R1",
    max_seq_length=2048,
)

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

danielhanchen commited on Apr 20, 2025

Commit

32adcc5

verified ·

1 Parent(s): cc41504

Add files using upload-large-folder tool

Browse files

Files changed (5) hide show

.gitattributes +1 -0
config.json +2 -10
model-00001-of-000163.safetensors +2 -2
model-00002-of-000163.safetensors +2 -2
model-00003-of-000163.safetensors +2 -2

.gitattributes CHANGED Viewed

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text

 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+figures/benchmark.jpg filter=lfs diff=lfs merge=lfs -text

config.json CHANGED Viewed

@@ -37,15 +37,6 @@
   "q_lora_rank": 1536,
   "qk_nope_head_dim": 128,
   "qk_rope_head_dim": 64,
-  "quantization_config": {
-    "activation_scheme": "dynamic",
-    "fmt": "e4m3",
-    "quant_method": "fp8",
-    "weight_block_size": [
-      128,
-      128
-    ]
-  },
   "rms_norm_eps": 1e-06,
   "rope_scaling": {
     "beta_fast": 32,
@@ -64,7 +55,8 @@
   "topk_group": 4,
   "topk_method": "noaux_tc",
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.46.3",
   "use_cache": true,
   "v_head_dim": 128,
   "vocab_size": 129280

   "q_lora_rank": 1536,
   "qk_nope_head_dim": 128,
   "qk_rope_head_dim": 64,
   "rms_norm_eps": 1e-06,
   "rope_scaling": {
     "beta_fast": 32,
   "topk_group": 4,
   "topk_method": "noaux_tc",
   "torch_dtype": "bfloat16",
+  "transformers_version": "4.48.1",
+  "unsloth_fixed": true,
   "use_cache": true,
   "v_head_dim": 128,
   "vocab_size": 129280

model-00001-of-000163.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2388e6b127ce6664e35c5e2529c3ce4bfc99f4f7fb6fa48e92b29ed5e4922af
-size 5234139343

 version https://git-lfs.github.com/spec/v1
+oid sha256:e5e87b89ead036e72853e1d7cf48136d40d85b90cc242944e58aa7f88900092f
+size 8609454256

model-00002-of-000163.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f450c75da7eb897b74a092eee65df8bb115fce81cccd2bbaeb220bd97197875
-size 4302383966

 version https://git-lfs.github.com/spec/v1
+oid sha256:b620aa86006f54aac8d8453e9370cb8411119e3038e13df0bce82ebd954729f1
+size 8602553952

model-00003-of-000163.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c79b3418357348d089e88f9de17ac52d7b7a1cfe5dfc7c1b2f1ac1451298b080
-size 4302384375

 version https://git-lfs.github.com/spec/v1
+oid sha256:0be9a653c37d1b3d0817a4721349491cee42c9e5ff0c8658a31dc2291cf1db14
+size 8602554152