Instructions to use cortexso/deepseek-r1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use cortexso/deepseek-r1 with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="cortexso/deepseek-r1",
	filename="deepseek-r1-distill-llama-70b-q4_k_m.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use cortexso/deepseek-r1 with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf cortexso/deepseek-r1:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf cortexso/deepseek-r1:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf cortexso/deepseek-r1:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf cortexso/deepseek-r1:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf cortexso/deepseek-r1:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf cortexso/deepseek-r1:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf cortexso/deepseek-r1:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf cortexso/deepseek-r1:Q4_K_M

Use Docker

docker model run hf.co/cortexso/deepseek-r1:Q4_K_M

LM Studio
Jan

vLLM

How to use cortexso/deepseek-r1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "cortexso/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": "cortexso/deepseek-r1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/cortexso/deepseek-r1:Q4_K_M

Ollama
How to use cortexso/deepseek-r1 with Ollama:
```
ollama run hf.co/cortexso/deepseek-r1:Q4_K_M
```

Unsloth Studio new

How to use cortexso/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 cortexso/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 cortexso/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 cortexso/deepseek-r1 to start chatting

Docker Model Runner
How to use cortexso/deepseek-r1 with Docker Model Runner:
```
docker model run hf.co/cortexso/deepseek-r1:Q4_K_M
```

Lemonade

How to use cortexso/deepseek-r1 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull cortexso/deepseek-r1:Q4_K_M

Run and chat with the model

lemonade run user.deepseek-r1-Q4_K_M

List all available models

lemonade list

cortexso
/

deepseek-r1

Upload folder using huggingface_hub

+version https://git-lfs.github.com/spec/v1
+oid sha256:490a8a46c28805ddc9bab0c9bdabae3e0b9802e4fc27f40e4255d282e56450f1
+size 12313098080

+version https://git-lfs.github.com/spec/v1
+oid sha256:c2ae5c62c7dbe696bd6689308103563fb4145c7773c2e6c133268c4dc53be193
+size 17247078240

+version https://git-lfs.github.com/spec/v1
+oid sha256:1be21f71c2743b5969a427914386d10ccf7edc852c37885b57b6fd8f94246bd7
+size 15935047520

+version https://git-lfs.github.com/spec/v1
+oid sha256:04815eaeab500ccacf10117f8ab7d478f365cf519623bdf7ebbde014a4a8cab1
+size 14392330080

+version https://git-lfs.github.com/spec/v1
+oid sha256:1039daf05cf3d62fba6b56f7df65bdede8b8299042a876fd2ce44a6a4a393ddf
+size 19851335520

+version https://git-lfs.github.com/spec/v1
+oid sha256:c502efc7ce9478b105c9ebd23e083277f6957fadd03182be7236b19a5607e83a
+size 18784409440

+version https://git-lfs.github.com/spec/v1
+oid sha256:e296f99d1b2d5e3d0c475cf45614c48b8b56c5ca1088a624609ef6005d3ffbc6
+size 23262156640

+version https://git-lfs.github.com/spec/v1
+oid sha256:164f43ed691efd1f7ea42c67281c91db45f10487879330f41311d8302fbcabea
+size 22638253920

+version https://git-lfs.github.com/spec/v1
+oid sha256:01c8405f3df903c1c19d13f1ad394a18a23947e1150e0da214894e2ac97e1ebf
+size 26886154080

+version https://git-lfs.github.com/spec/v1
+oid sha256:186a1cbd69574ecbb9ebd9872a7bfb49d72bd3fd67d24777e443decaa8f8f5fa
+size 34820884320

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

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

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

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