Instructions to use AiLab-IMCS-UL/EuroLLM-9B-Instruct-LVportals-15K with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AiLab-IMCS-UL/EuroLLM-9B-Instruct-LVportals-15K with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="AiLab-IMCS-UL/EuroLLM-9B-Instruct-LVportals-15K",
	filename="unsloth.F16.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use AiLab-IMCS-UL/EuroLLM-9B-Instruct-LVportals-15K with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf AiLab-IMCS-UL/EuroLLM-9B-Instruct-LVportals-15K:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf AiLab-IMCS-UL/EuroLLM-9B-Instruct-LVportals-15K:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf AiLab-IMCS-UL/EuroLLM-9B-Instruct-LVportals-15K:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf AiLab-IMCS-UL/EuroLLM-9B-Instruct-LVportals-15K: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 AiLab-IMCS-UL/EuroLLM-9B-Instruct-LVportals-15K:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf AiLab-IMCS-UL/EuroLLM-9B-Instruct-LVportals-15K: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 AiLab-IMCS-UL/EuroLLM-9B-Instruct-LVportals-15K:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf AiLab-IMCS-UL/EuroLLM-9B-Instruct-LVportals-15K:Q4_K_M

Use Docker

docker model run hf.co/AiLab-IMCS-UL/EuroLLM-9B-Instruct-LVportals-15K:Q4_K_M

LM Studio
Jan

vLLM

How to use AiLab-IMCS-UL/EuroLLM-9B-Instruct-LVportals-15K with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "AiLab-IMCS-UL/EuroLLM-9B-Instruct-LVportals-15K"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "AiLab-IMCS-UL/EuroLLM-9B-Instruct-LVportals-15K",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/AiLab-IMCS-UL/EuroLLM-9B-Instruct-LVportals-15K:Q4_K_M

Ollama
How to use AiLab-IMCS-UL/EuroLLM-9B-Instruct-LVportals-15K with Ollama:
```
ollama run hf.co/AiLab-IMCS-UL/EuroLLM-9B-Instruct-LVportals-15K:Q4_K_M
```

Unsloth Studio

How to use AiLab-IMCS-UL/EuroLLM-9B-Instruct-LVportals-15K 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 AiLab-IMCS-UL/EuroLLM-9B-Instruct-LVportals-15K 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 AiLab-IMCS-UL/EuroLLM-9B-Instruct-LVportals-15K to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for AiLab-IMCS-UL/EuroLLM-9B-Instruct-LVportals-15K to start chatting

Docker Model Runner
How to use AiLab-IMCS-UL/EuroLLM-9B-Instruct-LVportals-15K with Docker Model Runner:
```
docker model run hf.co/AiLab-IMCS-UL/EuroLLM-9B-Instruct-LVportals-15K:Q4_K_M
```

Lemonade

How to use AiLab-IMCS-UL/EuroLLM-9B-Instruct-LVportals-15K with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull AiLab-IMCS-UL/EuroLLM-9B-Instruct-LVportals-15K:Q4_K_M

Run and chat with the model

lemonade run user.EuroLLM-9B-Instruct-LVportals-15K-Q4_K_M

List all available models

lemonade list

This is a fine-tuned version of the EuroLLM-9B-Instruct model, adapted for answering questions about legislation in Latvia. The model was fine-tuned on a dataset of ~15 thousand question–answer pairs sourced from the LVportals.lv archive.

Quantized versions of the model are available for use with Ollama or other local LLM runtime environments that support the GGUF format.

The data preparation, fine-tuning process, and comprehensive evaluation are described in more detail in:

Artis Pauniņš. Evaluation and Adaptation of Large Language Models for Question-Answering on Legislation. Master’s Thesis. University of Latvia, 2025.

Note:

The model may occasionally generate overly long responses. To prevent this, it is recommended to set the num_predict parameter to limit the number of tokens generated - either in your Python code or in the Modelfile, depending on how the model is run.