Instructions to use NisalDeZoysa/qwen3-4b-sl-marriage-law-full with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use NisalDeZoysa/qwen3-4b-sl-marriage-law-full with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("NisalDeZoysa/qwen3-4b-sl-marriage-law-full", dtype="auto")

llama-cpp-python

How to use NisalDeZoysa/qwen3-4b-sl-marriage-law-full with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="NisalDeZoysa/qwen3-4b-sl-marriage-law-full",
	filename="unsloth.Q4_K_M.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 NisalDeZoysa/qwen3-4b-sl-marriage-law-full 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 NisalDeZoysa/qwen3-4b-sl-marriage-law-full:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf NisalDeZoysa/qwen3-4b-sl-marriage-law-full:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf NisalDeZoysa/qwen3-4b-sl-marriage-law-full:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf NisalDeZoysa/qwen3-4b-sl-marriage-law-full: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 NisalDeZoysa/qwen3-4b-sl-marriage-law-full:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf NisalDeZoysa/qwen3-4b-sl-marriage-law-full: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 NisalDeZoysa/qwen3-4b-sl-marriage-law-full:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf NisalDeZoysa/qwen3-4b-sl-marriage-law-full:Q4_K_M

Use Docker

docker model run hf.co/NisalDeZoysa/qwen3-4b-sl-marriage-law-full:Q4_K_M

LM Studio
Jan
Ollama
How to use NisalDeZoysa/qwen3-4b-sl-marriage-law-full with Ollama:
```
ollama run hf.co/NisalDeZoysa/qwen3-4b-sl-marriage-law-full:Q4_K_M
```

Unsloth Studio

How to use NisalDeZoysa/qwen3-4b-sl-marriage-law-full 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 NisalDeZoysa/qwen3-4b-sl-marriage-law-full 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 NisalDeZoysa/qwen3-4b-sl-marriage-law-full to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for NisalDeZoysa/qwen3-4b-sl-marriage-law-full to start chatting

How to use NisalDeZoysa/qwen3-4b-sl-marriage-law-full with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf NisalDeZoysa/qwen3-4b-sl-marriage-law-full: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": "NisalDeZoysa/qwen3-4b-sl-marriage-law-full:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use NisalDeZoysa/qwen3-4b-sl-marriage-law-full with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf NisalDeZoysa/qwen3-4b-sl-marriage-law-full: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 NisalDeZoysa/qwen3-4b-sl-marriage-law-full:Q4_K_M

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use NisalDeZoysa/qwen3-4b-sl-marriage-law-full with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf NisalDeZoysa/qwen3-4b-sl-marriage-law-full: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 "NisalDeZoysa/qwen3-4b-sl-marriage-law-full: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 NisalDeZoysa/qwen3-4b-sl-marriage-law-full with Docker Model Runner:
```
docker model run hf.co/NisalDeZoysa/qwen3-4b-sl-marriage-law-full:Q4_K_M
```

Lemonade

How to use NisalDeZoysa/qwen3-4b-sl-marriage-law-full with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull NisalDeZoysa/qwen3-4b-sl-marriage-law-full:Q4_K_M

Run and chat with the model

lemonade run user.qwen3-4b-sl-marriage-law-full-Q4_K_M

List all available models

lemonade list

Uploaded model

Qwen3-4B Sinhala Marriage Law Fine-Tuned Model

Developed by: Final Year Project Group, Faculty of Engineering, University of Ruhuna /n License: Apache-2.0 Based on: unsloth/Qwen3-4B-unsloth-bnb-4bit

This is a fine-tuned Qwen3 model trained specifically on Sri Lankan law text, including marriage and related legislation. The model supports text generation tasks and has been optimized for efficiency with Unsloth’s fast training utilities.

Highlights:

Fine-tuned on legal domain text for improved accuracy in Sinhala law queries.

Trained with Unsloth for 2× faster training and memory-efficient 4-bit quantization.

Compatible with GGUF format for local inference or deployment in frameworks like Ollama.

Intended Use:

Generating legal guidance and summaries in Sinhala based on the trained domain corpus.

Educational and research purposes in law-focused NLP applications.

Downloads last month: 8

GGUF

Model size

4B params

Architecture

qwen3

Hardware compatibility

4-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for NisalDeZoysa/qwen3-4b-sl-marriage-law-full

Base model

Qwen/Qwen3-4B-Base

Finetuned

Qwen/Qwen3-4B

Quantized

unsloth/Qwen3-4B-unsloth-bnb-4bit

Quantized

(36)

this model

NisalDeZoysa
/

qwen3-4b-sl-marriage-law-full

Uploaded model

Model tree for NisalDeZoysa/qwen3-4b-sl-marriage-law-full

Dataset used to train NisalDeZoysa/qwen3-4b-sl-marriage-law-full