Instructions to use Illaitar/aidnd-router with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Illaitar/aidnd-router with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Illaitar/aidnd-router",
	filename="aidnd-router-q4_k_m.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 Illaitar/aidnd-router 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 Illaitar/aidnd-router:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Illaitar/aidnd-router:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Illaitar/aidnd-router:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Illaitar/aidnd-router:Q4_K_M

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 Illaitar/aidnd-router:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Illaitar/aidnd-router:Q4_K_M

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 Illaitar/aidnd-router:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Illaitar/aidnd-router:Q4_K_M

Use Docker

docker model run hf.co/Illaitar/aidnd-router:Q4_K_M

LM Studio
Jan
Ollama
How to use Illaitar/aidnd-router with Ollama:
```
ollama run hf.co/Illaitar/aidnd-router:Q4_K_M
```

Unsloth Studio

How to use Illaitar/aidnd-router 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 Illaitar/aidnd-router 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 Illaitar/aidnd-router to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Illaitar/aidnd-router to start chatting

How to use Illaitar/aidnd-router with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Illaitar/aidnd-router:Q4_K_M

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": "Illaitar/aidnd-router:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use Illaitar/aidnd-router with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Illaitar/aidnd-router:Q4_K_M

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 Illaitar/aidnd-router:Q4_K_M

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use Illaitar/aidnd-router with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Illaitar/aidnd-router:Q4_K_M

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 "Illaitar/aidnd-router:Q4_K_M" \
  --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 Illaitar/aidnd-router with Docker Model Runner:
```
docker model run hf.co/Illaitar/aidnd-router:Q4_K_M
```

Lemonade

How to use Illaitar/aidnd-router with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Illaitar/aidnd-router:Q4_K_M

Run and chat with the model

lemonade run user.aidnd-router-Q4_K_M

List all available models

lemonade list

aidnd-router — классификатор намерений игрока (Qwen3.5-9B + LoRA)

Роутер ввода для движка AI-DnD. На вход — сцена (место/выходы/affordances), присутствующие NPC, недавняя история и реплика игрока. На выход — один JSON:

{"kind": "query|dialogue|command|freeform", "query_type": …, "verb": …, "target": …, "tone": …}

query — вопрос о мире/себе (look/items/who/exits/inventory/status/map);
dialogue — речь присутствующему NPC (tone: neutral/friendly/hostile/deceptive/fearful);
command — явная команда движку (verb: move/attack/buy/sell/loot/search/inspect/…);
freeform — всё остальное (уходит арбитру на разрешение броском).

Как получился

База: unsloth/Qwen3.5-9B (Apache-2.0).
Метод: QLoRA SFT (4-bit), 178 примеров, 3 эпохи; учили только ответ ассистента. Затем мердж в базу и квантизация в Q4_K_M GGUF.
Оценка (24 отложенных примера, стратиф. по 6 на класс; метрика — совпадение с эталоном):

kind +field full

база Qwen3.5-9B 75% 67% 50%

aidnd-router 92% 83% 71%

Роутинг база умеет и сама (это классификация), но адаптер убирает ~⅓–½ ошибок, особенно на «грязных» вводах (сленг, опечатки, многословие) и в строгом full (тон/target).

	kind	+field	full
база Qwen3.5-9B	75%	67%	50%
aidnd-router	92%	83%	71%

Запуск локально через Ollama

hf download Illaitar/aidnd-router aidnd-router-q4_k_m.gguf Modelfile --local-dir aidnd-router
cd aidnd-router && ollama create aidnd-router -f Modelfile
ollama run aidnd-router

Требуется Ollama 0.17.1+ (Modelfile использует RENDERER/PARSER qwen3.5).

В движке AI-DnD роль router уже указывает на aidnd-router (AIDND_ROUTER_MODEL, с откатом на базовую модель, если адаптера нет на сервере).

Downloads last month: 11

GGUF

Model size

9B params

Architecture

qwen35

Hardware compatibility

4-bit

Inference Providers NEW

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

Model tree for Illaitar/aidnd-router

Base model

Qwen/Qwen3.5-9B-Base

Finetuned

Qwen/Qwen3.5-9B

Finetuned

unsloth/Qwen3.5-9B

Adapter

(83)

this model