Instructions to use Sweaterdog/Smol-reason2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use Sweaterdog/Smol-reason2 with llama.cpp:
Install (macOS, Linux)
curl -LsSf https://llama.app/install.sh | sh # Start a local OpenAI-compatible server with a web UI: llama serve -hf Sweaterdog/Smol-reason2:Q4_K_M # Run inference directly in the terminal: llama cli -hf Sweaterdog/Smol-reason2:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf Sweaterdog/Smol-reason2:Q4_K_M # Run inference directly in the terminal: llama cli -hf Sweaterdog/Smol-reason2: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 Sweaterdog/Smol-reason2:Q4_K_M # Run inference directly in the terminal: ./llama-cli -hf Sweaterdog/Smol-reason2: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 Sweaterdog/Smol-reason2:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf Sweaterdog/Smol-reason2:Q4_K_M
Use Docker
docker model run hf.co/Sweaterdog/Smol-reason2:Q4_K_M
- LM Studio
- Jan
- Ollama
How to use Sweaterdog/Smol-reason2 with Ollama:
ollama run hf.co/Sweaterdog/Smol-reason2:Q4_K_M
- Unsloth Desktop
- Pi
How to use Sweaterdog/Smol-reason2 with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf Sweaterdog/Smol-reason2:Q4_K_M
Configure the model in Pi
# Install Pi: npm install -g @earendil-works/pi-coding-agent # Add to ~/.pi/agent/models.json: { "providers": { "llama-cpp": { "baseUrl": "http://localhost:8080/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "Sweaterdog/Smol-reason2:Q4_K_M" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use Sweaterdog/Smol-reason2 with Docker Model Runner:
docker model run hf.co/Sweaterdog/Smol-reason2:Q4_K_M
- Lemonade
How to use Sweaterdog/Smol-reason2 with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull Sweaterdog/Smol-reason2:Q4_K_M
Run and chat with the model
lemonade run user.Smol-reason2-Q4_K_M
List all available models
lemonade list
- Hermes Agent
How to use Sweaterdog/Smol-reason2 with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf Sweaterdog/Smol-reason2: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 Sweaterdog/Smol-reason2:Q4_K_M
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use Sweaterdog/Smol-reason2 with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf Sweaterdog/Smol-reason2:Q4_K_M
Configure OpenClaw
# Install OpenClaw: npm install -g openclaw@latest # Register the local server and set it as the default model: openclaw onboard --non-interactive --mode local \ --auth-choice custom-api-key \ --custom-base-url http://127.0.0.1:8080/v1 \ --custom-model-id "Sweaterdog/Smol-reason2:Q4_K_M" \ --custom-provider-id llama-cpp \ --custom-compatibility openai \ --custom-text-input \ --accept-risk \ --skip-health
Run OpenClaw
openclaw agent --local --agent main --message "Hello from Hugging Face"
Update Modelfile
Browse files
Modelfile
CHANGED
|
@@ -7,6 +7,8 @@ TEMPLATE """{{ if .System }}<|im_start|>system
|
|
| 7 |
{{ .Response }}<|im_end|>
|
| 8 |
"""
|
| 9 |
SYSTEM """
|
|
|
|
|
|
|
| 10 |
Respond in the following format:
|
| 11 |
<think>
|
| 12 |
|
|
@@ -16,18 +18,12 @@ Respond in the following format:
|
|
| 16 |
|
| 17 |
...your answer here...
|
| 18 |
|
| 19 |
-
|
| 20 |
-
When asked for code, provide small snippets while reasoning and ensure everything will work.
|
| 21 |
-
When thinking, provide 5 different ideas, how you would do each, and then provide examples for all five.
|
| 22 |
-
Before finishing your thinking, explain to yourself of what you will do, why you will do it, and then confirm what you're doing is the best idea.
|
| 23 |
"""
|
| 24 |
PARAMETER stop "<|im_start|>"
|
| 25 |
PARAMETER stop "<|im_end|>"
|
| 26 |
-
PARAMETER temperature 0.
|
| 27 |
-
PARAMETER
|
| 28 |
-
PARAMETER repeat_last_n 256
|
| 29 |
-
PARAMETER repeat_penalty 1.3
|
| 30 |
PARAMETER num_ctx 16384
|
| 31 |
-
PARAMETER top_k
|
| 32 |
-
PARAMETER top_p 0.
|
| 33 |
-
PARAMETER min_p 0.05
|
|
|
|
| 7 |
{{ .Response }}<|im_end|>
|
| 8 |
"""
|
| 9 |
SYSTEM """
|
| 10 |
+
You are a reasoning model named Smol-reason2, developed by SweaterDog.
|
| 11 |
+
When asked for code, provide small snippets while reasoning and ensure everything will work.
|
| 12 |
Respond in the following format:
|
| 13 |
<think>
|
| 14 |
|
|
|
|
| 18 |
|
| 19 |
...your answer here...
|
| 20 |
|
| 21 |
+
Remember to start your response with "<think>"
|
|
|
|
|
|
|
|
|
|
| 22 |
"""
|
| 23 |
PARAMETER stop "<|im_start|>"
|
| 24 |
PARAMETER stop "<|im_end|>"
|
| 25 |
+
PARAMETER temperature 0.6
|
| 26 |
+
PARAMETER repeat_penalty 1.0
|
|
|
|
|
|
|
| 27 |
PARAMETER num_ctx 16384
|
| 28 |
+
PARAMETER top_k 40
|
| 29 |
+
PARAMETER top_p 0.95
|
|
|