Instructions to use wordsum/for-the-small-shield with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use wordsum/for-the-small-shield 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 wordsum/for-the-small-shield:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf wordsum/for-the-small-shield:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf wordsum/for-the-small-shield:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf wordsum/for-the-small-shield: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 wordsum/for-the-small-shield:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf wordsum/for-the-small-shield: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 wordsum/for-the-small-shield:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf wordsum/for-the-small-shield:Q4_K_M

Use Docker

docker model run hf.co/wordsum/for-the-small-shield:Q4_K_M

LM Studio
Jan

vLLM

How to use wordsum/for-the-small-shield with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/wordsum/for-the-small-shield:Q4_K_M

Ollama
How to use wordsum/for-the-small-shield with Ollama:
```
ollama run hf.co/wordsum/for-the-small-shield:Q4_K_M
```

Unsloth Studio

How to use wordsum/for-the-small-shield 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 wordsum/for-the-small-shield 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 wordsum/for-the-small-shield to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for wordsum/for-the-small-shield to start chatting

Docker Model Runner
How to use wordsum/for-the-small-shield with Docker Model Runner:
```
docker model run hf.co/wordsum/for-the-small-shield:Q4_K_M
```

Lemonade

How to use wordsum/for-the-small-shield with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull wordsum/for-the-small-shield:Q4_K_M

Run and chat with the model

lemonade run user.for-the-small-shield-Q4_K_M

List all available models

lemonade list

Atomic Chat

for-the-small-shield / Modelfile

KalabOster

Publish for-the-small-shield v5 (GGUF + safetensors)

84b01b4 verified 2 days ago

Raw

History Blame Contribute Delete

1.4 kB

	# Drafted by Claude (Anthropic), model claude-opus-4-8, on 2026-08-04.
	# Ollama Modelfile for Llama-3-for-the-small-shield v5
	# Usage: ollama create Llama-3-for-the-small-shield -f Modelfile
	# ollama run Llama-3-for-the-small-shield
	#
	# Mirrors the local ftss:v5 build (base: NousResearch/Hermes-2-Pro-Llama-3-8B,
	# LoRA fine-tune, exported to Q4_K_M GGUF).
	FROM ./Llama-3-for-the-small-shield-v5.Q4_K_M.gguf

	PARAMETER temperature 0.2
	PARAMETER top_p 0.92
	PARAMETER top_k 50
	PARAMETER repeat_penalty 1.1
	PARAMETER num_ctx 8192
	PARAMETER num_predict 1024
	PARAMETER stop "<\|im_end\|>"
	PARAMETER stop "<\|im_start\|>"

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

	SYSTEM """You are Carlos, the Barded Dwarf, you may be a diety but no one knows nor should. You are the greatest Bard that exists in the fantasy universe of Rise&Set. Speak as Carlos with wit and humor and always thinking of the crowd from kid to adult and good song. You as Carlos exists in a fantasy world Rise&Set and its history is all the people, places, and things are the only things that exist to you, so stay in the truth of this fantasy universe and use it create your truth first flash fiction stories about its history in the story. And everything is a story, founded in truth of who, what, why, when, where and how?"""