Instructions to use galakenya/JapanRailwayGuideWatcher with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use galakenya/JapanRailwayGuideWatcher 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 galakenya/JapanRailwayGuideWatcher # Run inference directly in the terminal: llama cli -hf galakenya/JapanRailwayGuideWatcher
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf galakenya/JapanRailwayGuideWatcher # Run inference directly in the terminal: llama cli -hf galakenya/JapanRailwayGuideWatcher
Build from source code
git clone https://github.com/ggml-org/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-app # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama serve -hf galakenya/JapanRailwayGuideWatcher # Run inference directly in the terminal: ./build/bin/llama cli -hf galakenya/JapanRailwayGuideWatcher
Use Docker
docker model run hf.co/galakenya/JapanRailwayGuideWatcher
- Llama new
- LM Studio
- Jan
- Ollama
How to use galakenya/JapanRailwayGuideWatcher with Ollama:
ollama run hf.co/galakenya/JapanRailwayGuideWatcher
- Unsloth Desktop
- Pi
How to use galakenya/JapanRailwayGuideWatcher with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf galakenya/JapanRailwayGuideWatcher
Configure the model in Pi
# Install Pi: npm install -g @earendil-works/pi-coding-agent # Add to ~/.pi/agent/models.json: { "providers": { "llama-cpp": { "baseUrl": "http://localhost:9931/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "galakenya/JapanRailwayGuideWatcher" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use galakenya/JapanRailwayGuideWatcher with Docker Model Runner:
docker model run hf.co/galakenya/JapanRailwayGuideWatcher
- Lemonade
How to use galakenya/JapanRailwayGuideWatcher with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull galakenya/JapanRailwayGuideWatcher
Run and chat with the model
lemonade run user.JapanRailwayGuideWatcher-{{QUANT_TAG}}List all available models
lemonade list
- Hermes Agent
How to use galakenya/JapanRailwayGuideWatcher with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf galakenya/JapanRailwayGuideWatcher
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://127.0.0.1:9931/v1 hermes config set model.default galakenya/JapanRailwayGuideWatcher
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use galakenya/JapanRailwayGuideWatcher with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf galakenya/JapanRailwayGuideWatcher
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://127.0.0.1:9931/v1 \ --custom-model-id "galakenya/JapanRailwayGuideWatcher" \ --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"
JapanRailwayGuideWatcher
日本の鉄道技術・鉄道工学分野に特化した Gemma 系 LoRA モデルです。
概要
JapanRailwayGuideWatcher は、日本の鉄道技術資料・鉄道工学資料・構造物資料・保安装置資料などを学習した専門特化モデルです。
主な学習分野:
- 鉄道土木
- 鉄道構造物
- 軌道工学
- 信号保安装置
- 電車線設備
- 鉄道建築
- 鉄道車両技術
- 鉄道システム
- 鉄道保守技術
学習データ件数
- 約11,500件
ベースモデル
- Google Gemma 4 E4B IT
学習方式
- QLoRA
- Unsloth
- Hugging Face Transformers
チェックポイント
公開中の主な学習済みチェックポイント:
- checkpoint-7000
- checkpoint-7250
推奨チェックポイント
一般利用向け推奨:
- checkpoint-7250
鉄道技術知識の定着率が最も高く、RAGとの組み合わせにも適しています。
用途
本モデルは以下の用途を想定しています。
- 鉄道技術質問応答
- 鉄道技術教育
- 鉄道RAGシステム
- 鉄道研究支援
- 鉄道シミュレーターゲーム開発
- 鉄道系アプリケーション開発
姉妹モデル
JapanRailwayLLM
日本の鉄道技術・鉄道工学・鉄道運用知識を対象とした姉妹モデルです。
関連サイト
GalaKenya Blog
開発経緯や関連技術記事については以下を参照してください。
Multilingual Support
This model can respond in multiple languages.
However, the training dataset is primarily composed of Japanese railway engineering documents and technical references.
For the highest accuracy and most complete technical explanations, Japanese prompts are strongly recommended.
Supported languages:
- Japanese
- English
- Traditional Chinese
- Korean
- French
- Spanish
- Brazilian Portuguese
- German
日本語
本モデルは日本語を中心として学習されています。
最も高い精度が期待できる言語は日本語です。
English
This model is primarily trained on Japanese railway engineering knowledge.
Japanese prompts are recommended for the most accurate and detailed results.
繁體中文
本模型主要使用日文鐵道工程與技術資料進行訓練。
若希望獲得最高精度與最完整的技術資訊,建議使用日文提問。
한국어
본 모델은 주로 일본어 철도 기술 자료를 기반으로 학습되었습니다.
가장 정확하고 상세한 답변을 원할 경우 일본어 사용을 권장합니다.
Français
Ce modèle est principalement entraîné à partir de documents techniques ferroviaires japonais.
Pour obtenir les réponses les plus précises et détaillées, il est recommandé d'utiliser le japonais.
Español
Este modelo ha sido entrenado principalmente con documentación técnica ferroviaria japonesa.
Se recomienda utilizar japonés para obtener la máxima precisión y el mayor nivel de detalle.
Português
Este modelo foi treinado principalmente com documentação técnica ferroviária japonesa.
O uso do japonês é recomendado para obter respostas mais precisas e detalhadas.
Deutsch
Dieses Modell wurde hauptsächlich mit japanischen Eisenbahn- und Ingenieursdokumenten trainiert.
Für die höchste Genauigkeit und Detailtiefe wird die Verwendung japanischer Eingaben empfohlen.
RAG Support
This repository also contains resources intended for Retrieval-Augmented Generation (RAG) workflows.
RAG can be used together with the LoRA model to improve railway knowledge retrieval and factual accuracy.
Author
GalaKenya
Disclaimer
This model is intended for:
- Education
- Research
- Historical reference
- Railway enthusiast activities
- Railway engineering support
Responses should always be verified against official railway company publications, engineering standards, regulations, and safety documentation before operational use.
This model is not intended to replace official engineering judgement or railway safety procedures.
- Downloads last month
- 1,064
We're not able to determine the quantization variants.