Instructions to use vgcarlol/vialbot 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 vgcarlol/vialbot 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 vgcarlol/vialbot:Q8_0 # Run inference directly in the terminal: llama cli -hf vgcarlol/vialbot:Q8_0
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf vgcarlol/vialbot:Q8_0 # Run inference directly in the terminal: llama cli -hf vgcarlol/vialbot:Q8_0
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 vgcarlol/vialbot:Q8_0 # Run inference directly in the terminal: ./build/bin/llama cli -hf vgcarlol/vialbot:Q8_0
Use Docker
docker model run hf.co/vgcarlol/vialbot:Q8_0
- Llama new
- LM Studio
- Jan
- Ollama
How to use vgcarlol/vialbot with Ollama:
ollama run hf.co/vgcarlol/vialbot:Q8_0
- Unsloth Desktop
- Pi
How to use vgcarlol/vialbot with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf vgcarlol/vialbot:Q8_0
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": "vgcarlol/vialbot:Q8_0" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use vgcarlol/vialbot with Docker Model Runner:
docker model run hf.co/vgcarlol/vialbot:Q8_0
- Lemonade
How to use vgcarlol/vialbot with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull vgcarlol/vialbot:Q8_0
Run and chat with the model
lemonade run user.vialbot-Q8_0
List all available models
lemonade list
- Hermes Agent
How to use vgcarlol/vialbot with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf vgcarlol/vialbot:Q8_0
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 vgcarlol/vialbot:Q8_0
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use vgcarlol/vialbot with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf vgcarlol/vialbot:Q8_0
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 "vgcarlol/vialbot:Q8_0" \ --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"
VialBot — modelos entrenados
Modelos del trabajo de graduación Desarrollo de un Asistente Conversacional Inteligente para la Gestión de Consultas de Tránsito y Educación Vial en Guatemala mediante Procesamiento de Lenguaje Natural (Universidad del Valle de Guatemala, 2026). Autor: Carlos Alberto Valladares Guerra (221164).
Código fuente: https://github.com/GraduacionesUVG/2026-221164-valladares-guerra-carlos-alberto
| Archivo | Descripción |
|---|---|
models/vialbot-generator-v3-q8_0.gguf |
LLM generador: Qwen2.5-1.5B-Instruct + LoRA propio (v3), cuantizado Q8_0 |
models/Modelfile |
Registro en Ollama: ollama create vialbot -f Modelfile |
models/vialbot-generator-lora-v3/ |
Adaptador LoRA (MLX) usado para el modelo anterior |
models/vialbot-embedder/ |
Embeddings: paraphrase-multilingual-MiniLM-L12-v2 con fine-tuning contrastivo |
models/vialbot-classifier.joblib |
Clasificador de tema y de dominio (regresión logística sobre embeddings) |
chroma/ |
Base vectorial ChromaDB con la Ley de Tránsito (Decreto 132-96) y su Reglamento (AG 273-98) |
Uso: copiar models/ a src/AI/models/ y chroma/ a src/AI/data/chroma/ del repositorio, registrar el LLM en Ollama y levantar los servicios con docker compose up -d --build.
- Downloads last month
- 147
8-bit