Instructions to use nursimakgul/emotionlab-gemma4-4b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use nursimakgul/emotionlab-gemma4-4b 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 nursimakgul/emotionlab-gemma4-4b:BF16
# Run inference directly in the terminal:
llama cli -hf nursimakgul/emotionlab-gemma4-4b:BF16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf nursimakgul/emotionlab-gemma4-4b:BF16
# Run inference directly in the terminal:
llama cli -hf nursimakgul/emotionlab-gemma4-4b:BF16

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 nursimakgul/emotionlab-gemma4-4b:BF16
# Run inference directly in the terminal:
./llama-cli -hf nursimakgul/emotionlab-gemma4-4b:BF16

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 nursimakgul/emotionlab-gemma4-4b:BF16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf nursimakgul/emotionlab-gemma4-4b:BF16

Use Docker

docker model run hf.co/nursimakgul/emotionlab-gemma4-4b:BF16

LM Studio
Jan
Ollama
How to use nursimakgul/emotionlab-gemma4-4b with Ollama:
```
ollama run hf.co/nursimakgul/emotionlab-gemma4-4b:BF16
```

Unsloth Studio

How to use nursimakgul/emotionlab-gemma4-4b 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 nursimakgul/emotionlab-gemma4-4b 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 nursimakgul/emotionlab-gemma4-4b to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for nursimakgul/emotionlab-gemma4-4b to start chatting

How to use nursimakgul/emotionlab-gemma4-4b with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf nursimakgul/emotionlab-gemma4-4b:BF16

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": "nursimakgul/emotionlab-gemma4-4b:BF16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use nursimakgul/emotionlab-gemma4-4b with Docker Model Runner:
```
docker model run hf.co/nursimakgul/emotionlab-gemma4-4b:BF16
```

Lemonade

How to use nursimakgul/emotionlab-gemma4-4b with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull nursimakgul/emotionlab-gemma4-4b:BF16

Run and chat with the model

lemonade run user.emotionlab-gemma4-4b-BF16

List all available models

lemonade list

Hermes Agent

How to use nursimakgul/emotionlab-gemma4-4b with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf nursimakgul/emotionlab-gemma4-4b:BF16

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 nursimakgul/emotionlab-gemma4-4b:BF16

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use nursimakgul/emotionlab-gemma4-4b with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf nursimakgul/emotionlab-gemma4-4b:BF16

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 "nursimakgul/emotionlab-gemma4-4b:BF16" \
  --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"

EmotionLab — Gemma 4 4B (Özel Eğitim)

Bu model, özel eğitim alanında Türkçe pedagojik öneriler üretmek için google/gemma-4-4b-it modeline LoRA fine-tuning uygulanarak elde edilmiştir.

Kullanım Alanı

Otizm, Down sendromu, yaygın gelişimsel bozukluk vb. tanılı çocuklar için bireysel eğitim planı oluşturma
Eğitim sürecini değerlendirme ve bir sonraki hedefleri belirleme
Aile rehberliği önerileri üretme

Eğitim Detayları

Parametre	Değer
Base model	google/gemma-4-4b-it
Dataset	emotionlab_dataset_v5 (513 kayıt)
Format	Alpaca (Türkçe)
LoRA rank	16
Epoch	3
Max seq length	2048
Framework	Unsloth + TRL

Hızlı Kullanım

from unsloth import FastLanguageModel

model, tokenizer = FastLanguageModel.from_pretrained(
    model_name="nursimakgul/emotionlab-gemma4-4b",
    max_seq_length=2048,
    load_in_4bit=True,
)
FastLanguageModel.for_inference(model)

⚠️ Sınırlılıklar

Bu model gerçek klinik karar verme süreçlerinde kullanılmamalıdır. Yalnızca eğitim destek aracı olarak tasarlanmıştır. Tüm öneriler uzman özel eğitim öğretmeni denetiminde değerlendirilmelidir.

Downloads last month: 7

GGUF

Model size

8B params

Architecture

gemma4

Hardware compatibility

4-bit

Inference Providers NEW

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