Instructions to use ai-literacy-innovation-institute/islamic_nusantara_nlp_v02 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ai-literacy-innovation-institute/islamic_nusantara_nlp_v02 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("image-text-to-text", model="ai-literacy-innovation-institute/islamic_nusantara_nlp_v02")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("ai-literacy-innovation-institute/islamic_nusantara_nlp_v02")
model = AutoModelForMultimodalLM.from_pretrained("ai-literacy-innovation-institute/islamic_nusantara_nlp_v02", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use ai-literacy-innovation-institute/islamic_nusantara_nlp_v02 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 ai-literacy-innovation-institute/islamic_nusantara_nlp_v02:BF16
# Run inference directly in the terminal:
llama cli -hf ai-literacy-innovation-institute/islamic_nusantara_nlp_v02:BF16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf ai-literacy-innovation-institute/islamic_nusantara_nlp_v02:BF16
# Run inference directly in the terminal:
llama cli -hf ai-literacy-innovation-institute/islamic_nusantara_nlp_v02: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 ai-literacy-innovation-institute/islamic_nusantara_nlp_v02:BF16
# Run inference directly in the terminal:
./llama-cli -hf ai-literacy-innovation-institute/islamic_nusantara_nlp_v02: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 ai-literacy-innovation-institute/islamic_nusantara_nlp_v02:BF16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf ai-literacy-innovation-institute/islamic_nusantara_nlp_v02:BF16

Use Docker

docker model run hf.co/ai-literacy-innovation-institute/islamic_nusantara_nlp_v02:BF16

LM Studio
Jan

vLLM

How to use ai-literacy-innovation-institute/islamic_nusantara_nlp_v02 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ai-literacy-innovation-institute/islamic_nusantara_nlp_v02"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ai-literacy-innovation-institute/islamic_nusantara_nlp_v02",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/ai-literacy-innovation-institute/islamic_nusantara_nlp_v02:BF16

SGLang

How to use ai-literacy-innovation-institute/islamic_nusantara_nlp_v02 with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "ai-literacy-innovation-institute/islamic_nusantara_nlp_v02" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ai-literacy-innovation-institute/islamic_nusantara_nlp_v02",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "ai-literacy-innovation-institute/islamic_nusantara_nlp_v02" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ai-literacy-innovation-institute/islamic_nusantara_nlp_v02",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Ollama
How to use ai-literacy-innovation-institute/islamic_nusantara_nlp_v02 with Ollama:
```
ollama run hf.co/ai-literacy-innovation-institute/islamic_nusantara_nlp_v02:BF16
```

Unsloth Studio

How to use ai-literacy-innovation-institute/islamic_nusantara_nlp_v02 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 ai-literacy-innovation-institute/islamic_nusantara_nlp_v02 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 ai-literacy-innovation-institute/islamic_nusantara_nlp_v02 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for ai-literacy-innovation-institute/islamic_nusantara_nlp_v02 to start chatting

How to use ai-literacy-innovation-institute/islamic_nusantara_nlp_v02 with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ai-literacy-innovation-institute/islamic_nusantara_nlp_v02: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": "ai-literacy-innovation-institute/islamic_nusantara_nlp_v02:BF16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use ai-literacy-innovation-institute/islamic_nusantara_nlp_v02 with Docker Model Runner:
```
docker model run hf.co/ai-literacy-innovation-institute/islamic_nusantara_nlp_v02:BF16
```

Lemonade

How to use ai-literacy-innovation-institute/islamic_nusantara_nlp_v02 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull ai-literacy-innovation-institute/islamic_nusantara_nlp_v02:BF16

Run and chat with the model

lemonade run user.islamic_nusantara_nlp_v02-BF16

List all available models

lemonade list

Hermes Agent

How to use ai-literacy-innovation-institute/islamic_nusantara_nlp_v02 with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ai-literacy-innovation-institute/islamic_nusantara_nlp_v02: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 ai-literacy-innovation-institute/islamic_nusantara_nlp_v02:BF16

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use ai-literacy-innovation-institute/islamic_nusantara_nlp_v02 with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ai-literacy-innovation-institute/islamic_nusantara_nlp_v02: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 "ai-literacy-innovation-institute/islamic_nusantara_nlp_v02: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"

🕌 Islamic Nusantara NLP v2.0 (Master Edition)

Islamic Nusantara NLP v2.0 adalah model bahasa khusus (LLM/VLM) yang dikembangkan oleh Artificial Intelligence Literacy and Innovation Institute (ALII). Model ini dirancang untuk menjadi jembatan antara teknologi AI modern dengan warisan literatur klasik Islam (Turats).

Model ini merupakan hasil penggabungan tiga disiplin ilmu utama dalam satu arsitektur terpadu, memungkinkan pemahaman lintas kitab yang lebih koheren.

🏛 Riset & Pengembangan

Model ini adalah bagian dari proyek preservasi digital warisan ulama Nusantara yang berfokus pada:

Digitalisasi literatur klasik (OCR & Understanding).
Analisis semantik teks Arab-Melayu/Indonesia.
Ekstraksi entitas ulama dan sanad secara otomatis.

🔗 Pelajari lebih lanjut: alii.uinjkt.ac.id

📌 Deskripsi Model & Cakupan Data

Versi Master (v2.0) ini dilatih menggunakan 44.339 entri terstruktur yang mencakup:

Jarh wa Ta'dil: Biografi dan penilaian perawi dari Mizan al-I'tidal (Imam Adz-Dzahabi).
Sejarah (Tarikh): Kronologi peristiwa dan biografi dari Tarikh al-Islam (Imam Adz-Dzahabi).
Tafsir: Interpretasi mendalam ayat Al-Qur'an dari Tafsir al-Tabari (Imam At-Thabari).

🚀 Fitur Multimodal (Vision-Ready)

Berbeda dengan LLM standar, model ini menyertakan proyektor visi (mmproj), memberikan fondasi untuk pengembangan fitur OCR Cerdas yang mampu membaca scan manuskrip atau Kitab Kuning secara langsung di masa depan.

🛠 Detail Teknis Training

Base Model: Qwen2.5 (Family).
Framework: Unsloth (2x faster training).
Format: GGUF (Quantized Q4_K_M).
Labeling Standard: Menggunakan sistem tagar XML-style khusus (e.g., <ULAMA>, <SANAD>, <KOTA>).
Hardware: NVIDIA GPU (Infrastruktur RunPod).

📖 Cara Penggunaan lokal (vía LM Studio / GGUF)

Unduh file Qwen3.5-2B.Q4_K_M.gguf. (Gunakan nama Qwen2.5 untuk pencarian parameter yang tepat).
Gunakan aplikasi LM Studio, Ollama, atau Jan.ai.
System Prompt yang disarankan:

"Anda adalah asisten ahli dari ALII yang mahir dalam ilmu hadis, tafsir, dan sejarah Islam Nusantara. Berikan jawaban berdasarkan rujukan kitab klasik yang akurat."

🏷️ Daftar Label Entitas (Special Tokens)

Model ini dilatih untuk mengenali tag berikut:

Tokoh: <ULAMA_HADIS>, <RAWI>, <SAHABAT>
Penilaian: <MUTQIN>, <DHAIF>, <SHADUQ>
Struktur: <SANAD>, <MATAN>, <KITAB>
Geografi: <KOTA>, <WILAYAH>

📜 Kontribusi & Sitasi

Model ini bersifat Open Access untuk kepentingan riset dan pendidikan. Mohon kutip lembaga ALII dalam publikasi ilmiah Anda yang menggunakan model ini.

Tim Pengembang:

AI Literacy and Innovation Institute (ALII)
UIN Syarif Hidayatullah Jakarta

Downloads last month: 19

GGUF

Model size

2B params

Architecture

qwen35

Hardware compatibility

4-bit