Instructions to use alfonsodlg/iucia-v47-gemma3-4b 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 alfonsodlg/iucia-v47-gemma3-4b 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 alfonsodlg/iucia-v47-gemma3-4b:Q4_K_M # Run inference directly in the terminal: llama cli -hf alfonsodlg/iucia-v47-gemma3-4b:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf alfonsodlg/iucia-v47-gemma3-4b:Q4_K_M # Run inference directly in the terminal: llama cli -hf alfonsodlg/iucia-v47-gemma3-4b: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 alfonsodlg/iucia-v47-gemma3-4b:Q4_K_M # Run inference directly in the terminal: ./llama-cli -hf alfonsodlg/iucia-v47-gemma3-4b: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 alfonsodlg/iucia-v47-gemma3-4b:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf alfonsodlg/iucia-v47-gemma3-4b:Q4_K_M
Use Docker
docker model run hf.co/alfonsodlg/iucia-v47-gemma3-4b:Q4_K_M
- LM Studio
- Jan
- Ollama
How to use alfonsodlg/iucia-v47-gemma3-4b with Ollama:
ollama run hf.co/alfonsodlg/iucia-v47-gemma3-4b:Q4_K_M
- Unsloth Desktop
- Docker Model Runner
How to use alfonsodlg/iucia-v47-gemma3-4b with Docker Model Runner:
docker model run hf.co/alfonsodlg/iucia-v47-gemma3-4b:Q4_K_M
- Lemonade
How to use alfonsodlg/iucia-v47-gemma3-4b with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull alfonsodlg/iucia-v47-gemma3-4b:Q4_K_M
Run and chat with the model
lemonade run user.iucia-v47-gemma3-4b-Q4_K_M
List all available models
lemonade list
- Atomic Chat
IUCIA v47 - Asistente de Ventas
Modelo conversacional para asistencia de ventas en español, basado en Gemma 3 4B.
Métricas
- Precisión: 90% (12 errores en 120 tests)
- Dataset: 2,975 conversaciones reales
- Cuantización: Q4_K_M (2.4GB)
- Temperatura: 0.3
Uso
from llama_cpp import Llama
llm = Llama(
model_path="iucia-v47-q4_k_m.gguf",
n_ctx=2048,
n_threads=8
)
response = llm.create_chat_completion(
messages=[
{"role": "user", "content": "busco samsung"}
],
temperature=0.3
)
Capacidades
- Búsqueda de productos por marca, precio, especificaciones
- Comparación de productos
- Confirmación de compras
- Manejo de referencias contextuales
Limitaciones
- Optimizado para dominio de celulares
- Requiere integración con base de datos de productos
- 12 patrones edge conocidos (ver documentación)
Entrenamiento
- Base: google/gemma-3-4b-it
- Steps: 500
- Learning rate: 2e-4
- Loss final: 0.086
Licencia
Apache 2.0
- Downloads last month
- 9
Hardware compatibility
Log In to add your hardware
4-bit
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support