Instructions to use Sweaterdog/Smol-Reason with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Sweaterdog/Smol-Reason with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Sweaterdog/Smol-Reason",
	filename="Smol-reason.F16.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use Sweaterdog/Smol-Reason with llama.cpp:

Install from brew

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

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Sweaterdog/Smol-Reason:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf Sweaterdog/Smol-Reason: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-Reason:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Sweaterdog/Smol-Reason: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-Reason:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Sweaterdog/Smol-Reason:Q4_K_M

Use Docker

docker model run hf.co/Sweaterdog/Smol-Reason:Q4_K_M

LM Studio
Jan
Ollama
How to use Sweaterdog/Smol-Reason with Ollama:
```
ollama run hf.co/Sweaterdog/Smol-Reason:Q4_K_M
```

Unsloth Studio

How to use Sweaterdog/Smol-Reason 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 Sweaterdog/Smol-Reason 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 Sweaterdog/Smol-Reason to start chatting

Using HuggingFace Spaces for Unsloth

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

Docker Model Runner
How to use Sweaterdog/Smol-Reason with Docker Model Runner:
```
docker model run hf.co/Sweaterdog/Smol-Reason:Q4_K_M
```

Lemonade

How to use Sweaterdog/Smol-Reason with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Sweaterdog/Smol-Reason:Q4_K_M

Run and chat with the model

lemonade run user.Smol-Reason-Q4_K_M

List all available models

lemonade list

Sweaterdog commited on Mar 21, 2025

Commit

6de0c46

verified ·

1 Parent(s): f6762c5

Update Modelfile

Browse files

Files changed (1) hide show

Modelfile +16 -4

Modelfile CHANGED Viewed

@@ -1,5 +1,3 @@
-FROM /content/Sweaterdog/Smol-Reason/unsloth.F16.gguf
 TEMPLATE """{{ if .System }}<|im_start|>system
 {{ .System }}<|im_end|>
 {{ end }}{{ if .Prompt }}<|im_start|>user
@@ -7,7 +5,21 @@ TEMPLATE """{{ if .System }}<|im_start|>system
 {{ end }}<|im_start|>assistant
 {{ .Response }}<|im_end|>
 """
 PARAMETER stop "<|im_start|>"
 PARAMETER stop "<|im_end|>"
-PARAMETER temperature 1.5
-PARAMETER min_p 0.1

 TEMPLATE """{{ if .System }}<|im_start|>system
 {{ .System }}<|im_end|>
 {{ end }}{{ if .Prompt }}<|im_start|>user
 {{ end }}<|im_start|>assistant
 {{ .Response }}<|im_end|>
 """
+SYSTEM_PROMPT """
+Respond in the following format:
+<think>
+...
+</think>
+<answer
+...
+</answer>
+"""
 PARAMETER stop "<|im_start|>"
 PARAMETER stop "<|im_end|>"
+PARAMETER temperature 0.6
+PARAMETER min_p 0.1
+PARAMETER repeat_last_n 128
+PARAMETER repeat_penalty 1.3
+PARAMETER top_k 20
+PARAMETER top_p 0.7
+PARAMETER min_p 0.05