Instructions to use pozapas/gemma-3-evacuation with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use pozapas/gemma-3-evacuation with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="pozapas/gemma-3-evacuation",
	filename="gemma-3-evacuation.Q8_0.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 pozapas/gemma-3-evacuation 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 pozapas/gemma-3-evacuation:Q8_0
# Run inference directly in the terminal:
llama cli -hf pozapas/gemma-3-evacuation:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf pozapas/gemma-3-evacuation:Q8_0
# Run inference directly in the terminal:
llama cli -hf pozapas/gemma-3-evacuation:Q8_0

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 pozapas/gemma-3-evacuation:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf pozapas/gemma-3-evacuation:Q8_0

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 pozapas/gemma-3-evacuation:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf pozapas/gemma-3-evacuation:Q8_0

Use Docker

docker model run hf.co/pozapas/gemma-3-evacuation:Q8_0

LM Studio
Jan
Ollama
How to use pozapas/gemma-3-evacuation with Ollama:
```
ollama run hf.co/pozapas/gemma-3-evacuation:Q8_0
```

Unsloth Studio

How to use pozapas/gemma-3-evacuation 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 pozapas/gemma-3-evacuation 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 pozapas/gemma-3-evacuation to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for pozapas/gemma-3-evacuation to start chatting

Atomic Chat new
Docker Model Runner
How to use pozapas/gemma-3-evacuation with Docker Model Runner:
```
docker model run hf.co/pozapas/gemma-3-evacuation:Q8_0
```

Lemonade

How to use pozapas/gemma-3-evacuation with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull pozapas/gemma-3-evacuation:Q8_0

Run and chat with the model

lemonade run user.gemma-3-evacuation-Q8_0

List all available models

lemonade list

pozapas commited on Jun 16, 2025

Commit

c5fec7a

verified ·

1 Parent(s): 2238c22

Update README.md

Browse files

Files changed (1) hide show

README.md +0 -24

README.md CHANGED Viewed

@@ -92,30 +92,6 @@ This model is available in GGUF format for efficient local inference with [llama
 ./main -m gemma-3-evacuation.Q8_0.gguf -n 512 --repeat_penalty 1.1 --color -i -r "USER: " -f prompts/chat-with-gemma-3.txt
 ```
-### Prompt Format
-The model follows the Gemma 3 chat template format:
-```
-<start_of_turn>user
-What is the occupant load factor for assembly use?
-<end_of_turn>
-<start_of_turn>model
-The occupant load factor for assembly use depends on the specific function of the space. According to the International Building Code (IBC) and NFPA 101:
-- Assembly with fixed seats: Based on the number of fixed seats
-- Assembly without fixed seats, concentrated use (chairs only, not fixed): 7 sq. ft. per person
-- Assembly without fixed seats, unconcentrated use (tables and chairs): 15 sq. ft. per person
-- Standing space: 5 sq. ft. per person
-- Stage areas: 15 sq. ft. per person
-- Assembly with tables and chairs (restaurant seating): 15 sq. ft. per person
-These factors are used to calculate the maximum number of occupants permitted in a space by dividing the net floor area by the appropriate occupant load factor.
-(Source: IBC Section 1004, NFPA 101 Chapter 7)
-<end_of_turn>
-```
 ## Acknowledgements
 - Google for the Gemma 3 base model

 ./main -m gemma-3-evacuation.Q8_0.gguf -n 512 --repeat_penalty 1.1 --color -i -r "USER: " -f prompts/chat-with-gemma-3.txt
 ```
 ## Acknowledgements
 - Google for the Gemma 3 base model