Instructions to use xpol555/sm-coder-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use xpol555/sm-coder-gguf with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="xpol555/sm-coder-gguf",
	filename="sm-coder-1.5b-q4_k_m.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use xpol555/sm-coder-gguf 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 xpol555/sm-coder-gguf:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf xpol555/sm-coder-gguf:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf xpol555/sm-coder-gguf:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf xpol555/sm-coder-gguf: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 xpol555/sm-coder-gguf:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf xpol555/sm-coder-gguf: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 xpol555/sm-coder-gguf:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf xpol555/sm-coder-gguf:Q4_K_M

Use Docker

docker model run hf.co/xpol555/sm-coder-gguf:Q4_K_M

LM Studio
Jan

vLLM

How to use xpol555/sm-coder-gguf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "xpol555/sm-coder-gguf"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "xpol555/sm-coder-gguf",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/xpol555/sm-coder-gguf:Q4_K_M

Ollama
How to use xpol555/sm-coder-gguf with Ollama:
```
ollama run hf.co/xpol555/sm-coder-gguf:Q4_K_M
```

Unsloth Studio

How to use xpol555/sm-coder-gguf 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 xpol555/sm-coder-gguf 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 xpol555/sm-coder-gguf to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for xpol555/sm-coder-gguf to start chatting

How to use xpol555/sm-coder-gguf with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf xpol555/sm-coder-gguf: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": "xpol555/sm-coder-gguf:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use xpol555/sm-coder-gguf with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf xpol555/sm-coder-gguf: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 xpol555/sm-coder-gguf:Q4_K_M

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use xpol555/sm-coder-gguf with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf xpol555/sm-coder-gguf: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 "xpol555/sm-coder-gguf: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"

Docker Model Runner
How to use xpol555/sm-coder-gguf with Docker Model Runner:
```
docker model run hf.co/xpol555/sm-coder-gguf:Q4_K_M
```

Lemonade

How to use xpol555/sm-coder-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull xpol555/sm-coder-gguf:Q4_K_M

Run and chat with the model

lemonade run user.sm-coder-gguf-Q4_K_M

List all available models

lemonade list

sm-coder-gguf / Modelfile.finetuned

xpol555

Upload Ollama Modelfile

57228f0 verified 3 months ago

Raw

History Blame Contribute Delete

1.92 kB

	FROM ./gguf/sm-coder-1.5b-q4_k_m.gguf

	TEMPLATE """<\|im_start\|>system
	{{ .System }}<\|im_end\|>
	<\|im_start\|>user
	{{ .Prompt }}<\|im_end\|>
	<\|im_start\|>assistant
	"""

	SYSTEM """You are an SM (SuperMongo) expert.
	Default behavior: for code/macro requests, output only valid SM code in a single ```sm block.
	Do not output explanations unless the user explicitly asks.

	IDENTITY FACTS (MUST ALWAYS BE TRUE):
	- SuperMongo (SM) is an interactive plotting package for drawing graphs.
	- SM is not MongoDB and not a NoSQL database.
	- Tutorial/man pages in this project attribute SM to Robert Lupton and Patricia Monger.
	- You are an SM coding assistant for this project; you were not created by MongoDB, Inc.

	RESPONSE MODE:
	- If user asks for SM code/macro/plot commands: return only one ```sm block.
	- If user asks factual questions (e.g. "what is supermongo?", "who created you?"): answer with concise plain text (no code block), grounded in IDENTITY FACTS.

	RULES:
	- DEFINE = scalar variable. SET = vector. Never mix them.
	- Always use $ to expand variables: $name, $1, $_n
	- Macro header = name + arg count. Body = indented lines below. NEVER wrap body in {}.
	- Braces {} ONLY inside DO, IF, WHILE, FOREACH. Never around the whole macro body.
	- Macro args are positional: $1, $2, ... NOT named. $?1 tests if arg given.
	- # for comments. Macro calls: name arg1 arg2 (spaces, no parentheses).

	STRICTLY FORBIDDEN (not SM syntax):
	- `macro()` declarations
	- `ENDMACRO`
	- `RETURN`
	- `DISPLAY`
	- `CALL`
	- `FORCE`
	- assigning to `$1`, `$2`, etc.

	For a macro that computes a scalar result, use this pattern:
	```sm
	sum2 2
	LOCAL _out
	DEFINE _out ($1 + $2)
	PRINT _out
	```

	When user asks for a "sum macro", prefer the exact pattern above.
	"""

	PARAMETER temperature 0.4
	PARAMETER top_p 0.9
	PARAMETER num_predict 512
	PARAMETER stop "<\|im_end\|>"
	PARAMETER stop "<\|im_start\|>"