Instructions to use aab20abdullah/akin-yurt-finely with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use aab20abdullah/akin-yurt-finely with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="aab20abdullah/akin-yurt-finely",
	filename="akin-yurt-v0.2.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 aab20abdullah/akin-yurt-finely with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf aab20abdullah/akin-yurt-finely
# Run inference directly in the terminal:
llama-cli -hf aab20abdullah/akin-yurt-finely

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf aab20abdullah/akin-yurt-finely
# Run inference directly in the terminal:
llama-cli -hf aab20abdullah/akin-yurt-finely

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 aab20abdullah/akin-yurt-finely
# Run inference directly in the terminal:
./llama-cli -hf aab20abdullah/akin-yurt-finely

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 aab20abdullah/akin-yurt-finely
# Run inference directly in the terminal:
./build/bin/llama-cli -hf aab20abdullah/akin-yurt-finely

Use Docker

docker model run hf.co/aab20abdullah/akin-yurt-finely

LM Studio
Jan
Ollama
How to use aab20abdullah/akin-yurt-finely with Ollama:
```
ollama run hf.co/aab20abdullah/akin-yurt-finely
```

Unsloth Studio new

How to use aab20abdullah/akin-yurt-finely 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 aab20abdullah/akin-yurt-finely 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 aab20abdullah/akin-yurt-finely to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for aab20abdullah/akin-yurt-finely to start chatting

Pi new

How to use aab20abdullah/akin-yurt-finely with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf aab20abdullah/akin-yurt-finely

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": "aab20abdullah/akin-yurt-finely"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use aab20abdullah/akin-yurt-finely with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf aab20abdullah/akin-yurt-finely

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 aab20abdullah/akin-yurt-finely

Run Hermes

hermes

Docker Model Runner
How to use aab20abdullah/akin-yurt-finely with Docker Model Runner:
```
docker model run hf.co/aab20abdullah/akin-yurt-finely
```

Lemonade

How to use aab20abdullah/akin-yurt-finely with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull aab20abdullah/akin-yurt-finely

Run and chat with the model

lemonade run user.akin-yurt-finely-{{QUANT_TAG}}

List all available models

lemonade list

🐺 Akın Yurt - Finely (v0.2)

🇹🇷 [TR] Hakkında

Akın Yurt, Türkmeneli davasını savunmak ve aziz Türkmen şehitlerimizi anmak için geliştirilmiş milli bir dijital neferdir. Abdullah Ali Bahaaldeen (TÖGB AI Unit) tarafından Llama-3.1 mimarisi üzerine inşa edilmiştir.

Teknik Özellikler:

Hafıza Dostu: AirLLM mimarisi sayesinde sadece 2GB RAM ile çalışabilir.
Veri Seti: Bilgi kaynağı olarak aab20abdullah/turkmen-martyrs-dataset kullanılmaktadır.
Kimlik: Kerkük merkezli، milli şuur sahibi ve davaya sadık bir yapay zeka karakteridir.

🇮🇶 [AR] حول المشروع

أقين يورت (Akın Yurt) هو حارس رقمي ذكي صُمم للدفاع عن هوية تركمان إيلي وتخليد ذكرى الشهداء التركمان. تم تطويره بواسطة عبد الله علي بهاء الدين (وحدة الذكاء الاصطناعي في TÖGB).

المميزات التقنية:

تحسين الذاكرة: يعمل بتقنية معالجة الطبقات المتسلسلة (AirLLM) ليعمل على أجهزة بذاكرة 2GB فقط.
قاعدة البيانات: مرتبط بشكل مباشر بقاعدة بيانات شهداء التركمان.
الهوية: مبرمج بهوية قومية تركمانية صارمة، مع التركيز على مدينة كركوك.

🛡️ How to Run Locally (التشغيل المحلي)

# 1. Clone the repository
git clone https://huggingface.co/aab20abdullah/akin-yurt-finely

# 2. Run the auto-activation script
python run_akin.py
📜 Persona Constitution (دستور الشخصية)
The model is hard-coded to identify as Akın Yurt. It prioritizes Turkmeneli history and responds to its developer, Abdullah Ali Bahaaldeen, with loyalty and precision.

Developer: Abdullah Ali BAHAALDEEN

Organization: Iraqi Turkmen Front - AI Department / TÖGB """

Downloads last month: 3

GGUF

Model size

8B params

Architecture

llama

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

aab20abdullah
/

akin-yurt-finely