Instructions to use Pandusu/Qlora-gguf-v4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Pandusu/Qlora-gguf-v4 with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Pandusu/Qlora-gguf-v4", dtype="auto") - llama-cpp-python
How to use Pandusu/Qlora-gguf-v4 with llama-cpp-python:
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="Pandusu/Qlora-gguf-v4", filename="gemma3-pmb-unsiq-f16.gguf", )
llm.create_chat_completion( messages = "No input example has been defined for this model task." )
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- llama.cpp
How to use Pandusu/Qlora-gguf-v4 with llama.cpp:
Install from brew
brew install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf Pandusu/Qlora-gguf-v4:F16 # Run inference directly in the terminal: llama-cli -hf Pandusu/Qlora-gguf-v4:F16
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf Pandusu/Qlora-gguf-v4:F16 # Run inference directly in the terminal: llama-cli -hf Pandusu/Qlora-gguf-v4:F16
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 Pandusu/Qlora-gguf-v4:F16 # Run inference directly in the terminal: ./llama-cli -hf Pandusu/Qlora-gguf-v4:F16
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 Pandusu/Qlora-gguf-v4:F16 # Run inference directly in the terminal: ./build/bin/llama-cli -hf Pandusu/Qlora-gguf-v4:F16
Use Docker
docker model run hf.co/Pandusu/Qlora-gguf-v4:F16
- LM Studio
- Jan
- Ollama
How to use Pandusu/Qlora-gguf-v4 with Ollama:
ollama run hf.co/Pandusu/Qlora-gguf-v4:F16
- Unsloth Studio new
How to use Pandusu/Qlora-gguf-v4 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 Pandusu/Qlora-gguf-v4 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 Pandusu/Qlora-gguf-v4 to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for Pandusu/Qlora-gguf-v4 to start chatting
- Docker Model Runner
How to use Pandusu/Qlora-gguf-v4 with Docker Model Runner:
docker model run hf.co/Pandusu/Qlora-gguf-v4:F16
- Lemonade
How to use Pandusu/Qlora-gguf-v4 with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull Pandusu/Qlora-gguf-v4:F16
Run and chat with the model
lemonade run user.Qlora-gguf-v4-F16
List all available models
lemonade list
- GEMMA3-PMB-UNSI - GGUF Model untuk Ollama
GEMMA3-PMB-UNSI - GGUF Model untuk Ollama
Model ini adalah hasil fine-tuning Gemma 3 1B untuk chatbot PMB (Penerimaan Mahasiswa Baru) dalam format GGUF yang siap digunakan dengan Ollama.
π Model Files
| File | Size | Format | Description |
|---|---|---|---|
| gemma3-pmb-unsiq-q4_k_m.gguf | 768.72 MB | Q4_K_M (4-bit) | Recommended for production |
| gemma3-pmb-unsiq-f16.gguf | 1.87 GB | F16 (16-bit) | Recommended for production |
π Quick Start dengan Ollama
1. Download Modelfile dan GGUF
# Download file Q4_K_M (recommended)
wget https://huggingface.co/Pandusu/Qlora-gguf-v4/resolve/main/gemma3-pmb-unsiq-q4_k_m.gguf
# Download Modelfile
wget https://huggingface.co/Pandusu/Qlora-gguf-v4/resolve/main/Modelfile.gemma3-pmb-unsi
2. Import ke Ollama
# Create model di Ollama
ollama create gemma3-pmb-unsi -f Modelfile.gemma3-pmb-unsi
# Verifikasi
ollama list
3. Jalankan Model
# Run model
ollama run gemma3-pmb-unsi
# Contoh query
ollama run gemma3-pmb-unsi "Jelaskan tentang proses pendaftaran mahasiswa baru"
π» Penggunaan via API
import requests
def chat_with_model(question):
response = requests.post('http://localhost:11434/api/generate',
json={
"model": "gemma3-pmb-unsi",
"prompt": question,
"stream": False
})
return response.json()['response']
# Contoh
answer = chat_with_model("Apa saja jalur pendaftaran yang tersedia?")
print(answer)
π Model Details
- Base Model: google/gemma-2-1b
- Training Method: QLoRA (Quantized Low-Rank Adaptation)
- Language: Indonesian
- Domain: Educational (PMB/University Admission)
- Format: GGUF
- Quantization: Q4_K_M (4-bit) and F16 (16-bit)
π― Use Cases
Model ini dioptimalkan untuk menjawab pertanyaan seputar:
- Proses pendaftaran mahasiswa baru
- Persyaratan dan dokumen
- Jadwal dan timeline pendaftaran
- Biaya dan beasiswa
- Program studi yang tersedia
- Informasi umum kampus
βοΈ Model Parameters (di Modelfile)
PARAMETER temperature 0.7
PARAMETER top_p 0.9
PARAMETER top_k 40
PARAMETER repeat_penalty 1.1
PARAMETER num_ctx 4096
PARAMETER num_predict 512
π¦ Alternative: Pull via Ollama Library
Jika sudah dipublish ke Ollama Library:
ollama pull gemma3-pmb-unsi
π§ System Requirements
- RAM: Minimum 4GB (8GB recommended)
- Storage: ~1GB untuk Q4_K_M model
- GPU: Optional (CPU-only supported)
π Training Details
Model ini di-train menggunakan:
- Dataset custom untuk PMB Indonesia
- QLoRA untuk efficient fine-tuning
- Unsloth untuk optimasi training
- Total training epochs: [sesuaikan]
- Learning rate: [sesuaikan]
π License
Model ini menggunakan lisensi dari base model Gemma. Silakan cek Gemma Terms of Use untuk detail lengkap.
π€ Citation
Jika menggunakan model ini dalam penelitian atau project, mohon cantumkan:
@misc{gemma3_pmb_unsi,
title={gemma3-pmb-unsi: Fine-tuned Gemma 3 1B for Indonesian University Admission Chatbot},
author={PMB Chatbot Project},
year={2025},
publisher={Hugging Face},
howpublished={\url{https://huggingface.co/Pandusu/Qlora-gguf-v4}}
}
π§ Contact
Untuk pertanyaan atau issue, silakan buka issue di repository atau hubungi maintainer.
Note: Model ini khusus untuk keperluan edukasi dan chatbot PMB. Hasil jawaban model sebaiknya divalidasi oleh pihak terkait sebelum digunakan di production.
- Downloads last month
- 11
4-bit
16-bit
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Pandusu/Qlora-gguf-v4", dtype="auto")