Instructions to use barismenderes/aktapokus-gmail-v3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use barismenderes/aktapokus-gmail-v3 with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="barismenderes/aktapokus-gmail-v3",
	filename="Qwen2.5-3B-Instruct.Q4_K_M_V3.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use barismenderes/aktapokus-gmail-v3 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 barismenderes/aktapokus-gmail-v3:Q4_K_M_V
# Run inference directly in the terminal:
llama cli -hf barismenderes/aktapokus-gmail-v3:Q4_K_M_V

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf barismenderes/aktapokus-gmail-v3:Q4_K_M_V
# Run inference directly in the terminal:
llama cli -hf barismenderes/aktapokus-gmail-v3:Q4_K_M_V

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 barismenderes/aktapokus-gmail-v3:Q4_K_M_V
# Run inference directly in the terminal:
./llama-cli -hf barismenderes/aktapokus-gmail-v3:Q4_K_M_V

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 barismenderes/aktapokus-gmail-v3:Q4_K_M_V
# Run inference directly in the terminal:
./build/bin/llama-cli -hf barismenderes/aktapokus-gmail-v3:Q4_K_M_V

Use Docker

docker model run hf.co/barismenderes/aktapokus-gmail-v3:Q4_K_M_V

LM Studio
Jan
Ollama
How to use barismenderes/aktapokus-gmail-v3 with Ollama:
```
ollama run hf.co/barismenderes/aktapokus-gmail-v3:Q4_K_M_V
```

Unsloth Studio

How to use barismenderes/aktapokus-gmail-v3 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 barismenderes/aktapokus-gmail-v3 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 barismenderes/aktapokus-gmail-v3 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for barismenderes/aktapokus-gmail-v3 to start chatting

How to use barismenderes/aktapokus-gmail-v3 with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf barismenderes/aktapokus-gmail-v3:Q4_K_M_V

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": "barismenderes/aktapokus-gmail-v3:Q4_K_M_V"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use barismenderes/aktapokus-gmail-v3 with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf barismenderes/aktapokus-gmail-v3:Q4_K_M_V

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 barismenderes/aktapokus-gmail-v3:Q4_K_M_V

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use barismenderes/aktapokus-gmail-v3 with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf barismenderes/aktapokus-gmail-v3:Q4_K_M_V

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 "barismenderes/aktapokus-gmail-v3:Q4_K_M_V" \
  --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"

Docker Model Runner
How to use barismenderes/aktapokus-gmail-v3 with Docker Model Runner:
```
docker model run hf.co/barismenderes/aktapokus-gmail-v3:Q4_K_M_V
```

Lemonade

How to use barismenderes/aktapokus-gmail-v3 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull barismenderes/aktapokus-gmail-v3:Q4_K_M_V

Run and chat with the model

lemonade run user.aktapokus-gmail-v3-Q4_K_M_V

List all available models

lemonade list

Aktapokus Gmail v3 — Turkish email classification (Qwen2.5-3B, GGUF)

Qwen2.5-3B-Instruct fine-tuned with QLoRA (via Unsloth on a free Google Colab T4 GPU) to classify Turkish emails into a fixed set of categories. Quantized to GGUF (Q4_K_M) for local inference via Ollama.

Built for the Aktapokus Gmail Düzenleyici tool — a local-first digital operations assistant.

Training

Base model: unsloth/Qwen2.5-3B-Instruct-bnb-4bit
Method: QLoRA (r=16, targeting q/k/v/o/gate/up/down proj), ~1-2% of parameters trained
Data: synthetic Turkish email examples with varied instruction phrasing, so the model learns the task (classify an email) rather than one fixed prompt template
3 epochs, batch size 2, lr 2e-4

Usage with Ollama

Download Qwen2.5-3B-Instruct.Q4_K_M_V3.gguf from this repo, then in the same folder create a file named Modelfile:

FROM ./Qwen2.5-3B-Instruct.Q4_K_M_V3.gguf

ollama create aktapokus-gmail-v3 -f Modelfile

Prompt pattern the model was trained on:

Aşağıdaki e-postayı incele ve şu kategorilerden birine ata: reklam_pazarlama, bulten, fatura, is, kisisel, spam_supheli, diger.

Kimden: <gönderen>
Konu: <konu>

Sadece kategori adını yaz, başka hiçbir şey ekleme.

License

Same provisional terms as the Aktapokus core project — personal/educational use permitted, commercial use requires a separate agreement with the author.

Downloads last month: 8

GGUF

Model size

3B params

Architecture

qwen2

Hardware compatibility

4-bit

Inference Providers NEW

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

Model tree for barismenderes/aktapokus-gmail-v3

Base model

Qwen/Qwen2.5-3B

Finetuned

Qwen/Qwen2.5-3B-Instruct

Quantized

(259)

this model

barismenderes
/

aktapokus-gmail-v3

Aktapokus Gmail v3 — Turkish email classification (Qwen2.5-3B, GGUF)

Categories

Training

Usage with Ollama

License

Model tree for barismenderes/aktapokus-gmail-v3