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

Libraries

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

# !pip install llama-cpp-python

from llama_cpp import Llama

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

Use Docker

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

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

Unsloth Studio

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

How to use Illaitar/aidnd-quest 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-quest: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-quest:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use Illaitar/aidnd-quest 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-quest: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-quest:Q4_K_M

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use Illaitar/aidnd-quest with Docker Model Runner:
```
docker model run hf.co/Illaitar/aidnd-quest:Q4_K_M
```

Lemonade

How to use Illaitar/aidnd-quest with Lemonade:

Pull the model

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

Run and chat with the model

lemonade run user.aidnd-quest-Q4_K_M

List all available models

lemonade list

aidnd-quest — генератор квестов D&D 5e (Qwen3.5-9B + LoRA)

Дообученный квест-дизайнер для движка AI-DnD (https://github.com/illaitar/ai-dnd). На вход — структурированный запрос квеста (cast: фракции/NPC/шаблоны предметов/локации; и фиксированные поля kind/theme/tier/giver/reward/allowed_preds). На выход один полный квест в JSON, на русском, заземлённый на переданный cast, предикаты завершения стадий только из allowed_preds.

Как получился

База: unsloth/Qwen3.5-9B (Apache-2.0).
Метод: QLoRA SFT (4-bit), 180 примеров, 3 эпохи, loss 1.13 → 0.28; обучали только ответ ассистента. Затем мердж в базу и квантизация в Q4_K_M GGUF.

Оценка (20 отложенных квестов, метрика — валидатор схемы квест-билда):

	JSON распарсен	прошёл схему
база Qwen3.5-9B	20/20 (100%)	0/20 (0%) — `missing key`
aidnd-quest (этот Q4_K_M GGUF, через Ollama)	20/20 (100%)	15/20 (75%)
(референс: слитый fp16, через transformers)	20/20 (100%)	17/20 (85%)

Запуск локально через Ollama

# 1) скачать GGUF + Modelfile из этого репозитория
hf download Illaitar/aidnd-quest aidnd-quest-q4_k_m.gguf Modelfile --local-dir aidnd-quest
# 2) зарегистрировать в Ollama
cd aidnd-quest && ollama create aidnd-quest -f Modelfile
# 3) пользоваться
ollama run aidnd-quest

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

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

Формат запроса

System-промпт и схема входа/выхода — см. datasets/quests/SCHEMA.md в репозитории движка. Промпт ожидает JSON-объект запроса в user и возвращает JSON-квест в assistant.