Instructions to use cortexso/simplescaling-s1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use cortexso/simplescaling-s1 with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="cortexso/simplescaling-s1",
	filename="s1-32b-q2_k.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/simplescaling-s1 with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf cortexso/simplescaling-s1:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf cortexso/simplescaling-s1: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/simplescaling-s1:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf cortexso/simplescaling-s1: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/simplescaling-s1:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf cortexso/simplescaling-s1: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/simplescaling-s1:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf cortexso/simplescaling-s1:Q4_K_M

Use Docker

docker model run hf.co/cortexso/simplescaling-s1:Q4_K_M

LM Studio
Jan

vLLM

How to use cortexso/simplescaling-s1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "cortexso/simplescaling-s1"
# 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/simplescaling-s1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/cortexso/simplescaling-s1:Q4_K_M

Ollama
How to use cortexso/simplescaling-s1 with Ollama:
```
ollama run hf.co/cortexso/simplescaling-s1:Q4_K_M
```

Unsloth Studio new

How to use cortexso/simplescaling-s1 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/simplescaling-s1 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/simplescaling-s1 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for cortexso/simplescaling-s1 to start chatting

Pi new

How to use cortexso/simplescaling-s1 with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf cortexso/simplescaling-s1:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "cortexso/simplescaling-s1:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use cortexso/simplescaling-s1 with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf cortexso/simplescaling-s1:Q4_K_M

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default cortexso/simplescaling-s1:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use cortexso/simplescaling-s1 with Docker Model Runner:
```
docker model run hf.co/cortexso/simplescaling-s1:Q4_K_M
```

Lemonade

How to use cortexso/simplescaling-s1 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull cortexso/simplescaling-s1:Q4_K_M

Run and chat with the model

lemonade run user.simplescaling-s1-Q4_K_M

List all available models

lemonade list

@@ -33,3 +33,13 @@ 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
+s1-32b-q2_k.gguf filter=lfs diff=lfs merge=lfs -text
+s1-32b-q3_k_l.gguf filter=lfs diff=lfs merge=lfs -text
+s1-32b-q3_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+s1-32b-q3_k_s.gguf filter=lfs diff=lfs merge=lfs -text
+s1-32b-q4_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+s1-32b-q4_k_s.gguf filter=lfs diff=lfs merge=lfs -text
+s1-32b-q5_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+s1-32b-q5_k_s.gguf filter=lfs diff=lfs merge=lfs -text
+s1-32b-q6_k.gguf filter=lfs diff=lfs merge=lfs -text
+s1-32b-q8_0.gguf filter=lfs diff=lfs merge=lfs -text

cortexso
/

simplescaling-s1

Upload folder using huggingface_hub

+version https://git-lfs.github.com/spec/v1
+oid sha256:0408b6fffb71cc0c5be14a3eae1ea5193e126522a8ddbbf25bff329e7041ebb4
+size 12313098944

+version https://git-lfs.github.com/spec/v1
+oid sha256:e66eeefecf5fa6cb9f8697230ef3595205f5f16dc4dc86e4be03b19677fe6cd6
+size 17247079104

+version https://git-lfs.github.com/spec/v1
+oid sha256:11b63a8cc94b39a87c3900df5a927ef5b4cb39f8360df0b7b6bfcb87fb9245a8
+size 15935048384

+version https://git-lfs.github.com/spec/v1
+oid sha256:cee2643041c51c76e1f31621205a3a79f8380c1eafada77b4ea28473e2c1b518
+size 14392330944

+version https://git-lfs.github.com/spec/v1
+oid sha256:4b9d686fd805368fd221ad79273d86f8a762f169fce30510b6103766727bdc38
+size 19851336384

+version https://git-lfs.github.com/spec/v1
+oid sha256:8d64dc4901f6846693e4738bb27a5d14f461f64cee1005409ae18e8be06c7124
+size 18784410304

+version https://git-lfs.github.com/spec/v1
+oid sha256:e36e999e96ad1bd6774c8e53b1acf0762694ffe06c5328352a8b13f5186d4674
+size 23262157504

+version https://git-lfs.github.com/spec/v1
+oid sha256:66ee7f79bbf3ae70e90b861fac86053bd7a5ae3da037211f778a0cc6ff7f0c52
+size 22638254784

+version https://git-lfs.github.com/spec/v1
+oid sha256:271d5a9ed04b1ff60a88d15277d2d92bd05eb3234c7c7ae1f4a607637040f302
+size 26886154944

+version https://git-lfs.github.com/spec/v1
+oid sha256:e97ad1ef6037f116c0ea8556b5a20dbd897c9db866ff23a03ab6886b0ccd088a
+size 34820885184

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

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

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

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