Instructions to use miesdevries/stay4s-unified-lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use miesdevries/stay4s-unified-lora with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-4B-Instruct-2507")
model = PeftModel.from_pretrained(base_model, "miesdevries/stay4s-unified-lora")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use miesdevries/stay4s-unified-lora 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 miesdevries/stay4s-unified-lora
# Run inference directly in the terminal:
llama cli -hf miesdevries/stay4s-unified-lora

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf miesdevries/stay4s-unified-lora
# Run inference directly in the terminal:
llama cli -hf miesdevries/stay4s-unified-lora

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 miesdevries/stay4s-unified-lora
# Run inference directly in the terminal:
./llama-cli -hf miesdevries/stay4s-unified-lora

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 miesdevries/stay4s-unified-lora
# Run inference directly in the terminal:
./build/bin/llama-cli -hf miesdevries/stay4s-unified-lora

Use Docker

docker model run hf.co/miesdevries/stay4s-unified-lora

LM Studio
Jan
Ollama
How to use miesdevries/stay4s-unified-lora with Ollama:
```
ollama run hf.co/miesdevries/stay4s-unified-lora
```
Unsloth Desktop

How to use miesdevries/stay4s-unified-lora with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf miesdevries/stay4s-unified-lora

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "miesdevries/stay4s-unified-lora"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use miesdevries/stay4s-unified-lora with Docker Model Runner:
```
docker model run hf.co/miesdevries/stay4s-unified-lora
```

Lemonade

How to use miesdevries/stay4s-unified-lora with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull miesdevries/stay4s-unified-lora

Run and chat with the model

lemonade run user.stay4s-unified-lora-{{QUANT_TAG}}

List all available models

lemonade list

Hermes Agent

How to use miesdevries/stay4s-unified-lora with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf miesdevries/stay4s-unified-lora

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 miesdevries/stay4s-unified-lora

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use miesdevries/stay4s-unified-lora with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf miesdevries/stay4s-unified-lora

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 "miesdevries/stay4s-unified-lora" \
  --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"

Stay4S Unified AI - LoRA Adapter

Model Description

Stay4S Unified AI is a Dutch-language AI assistant model fine-tuned on 33,994 records from 6 different agent datasets. Built for the Stay4S ecosystem (customer service, companion app, messaging).

Training Details

Base model: Qwen3-4B-Instruct-2507
Method: LoRA (Low-Rank Adaptation)
Rank (r): 64
Alpha: 64
Dropout: 0.05
Epochs: 3
Learning rate: 2e-4
Batch size: 2 (grad accum 8)
Max sequence length: 1024
Training time: 519.6 minutes (~8.7 hours)
Total steps: 6,057

Final Metrics

Eval loss: 0.576
Eval perplexity: 1.78

Training Data

Combined from 6 agent datasets:

Customer service conversations
Technical support
Sales assistant
General assistant
Domain-specific knowledge
Companion app interactions

Total: 33,994 records

Usage

from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-4B-Instruct-2507")
model = PeftModel.from_pretrained(model, "miesdevries/stay4s-unified-lora")
tokenizer = AutoTokenizer.from_pretrained("miesdevries/stay4s-unified-lora")

GGUF Version

A quantized GGUF Q8 version will be available in this repo once conversion completes.

License

Apache 2.0 - Stay4S / Het Nieuwe Begin BV

Downloads last month: 126

GGUF

Model size

4B params

Architecture

qwen3

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

Inference Providers NEW

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

Model tree for miesdevries/stay4s-unified-lora

Base model

Qwen/Qwen3-4B-Instruct-2507

Adapter

(5796)

this model