Instructions to use NrengifoBTS/redactoria_V3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- llama-cpp-python
How to use NrengifoBTS/redactoria_V3 with llama-cpp-python:
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="NrengifoBTS/redactoria_V3", filename="Meta-Llama-3.1-8B.Q4_K_M.gguf", )
output = llm( "Once upon a time,", max_tokens=512, echo=True ) print(output)
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use NrengifoBTS/redactoria_V3 with llama.cpp:
Install from brew
brew install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf NrengifoBTS/redactoria_V3:Q4_K_M # Run inference directly in the terminal: llama-cli -hf NrengifoBTS/redactoria_V3:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf NrengifoBTS/redactoria_V3:Q4_K_M # Run inference directly in the terminal: llama-cli -hf NrengifoBTS/redactoria_V3: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 NrengifoBTS/redactoria_V3:Q4_K_M # Run inference directly in the terminal: ./llama-cli -hf NrengifoBTS/redactoria_V3: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 NrengifoBTS/redactoria_V3:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf NrengifoBTS/redactoria_V3:Q4_K_M
Use Docker
docker model run hf.co/NrengifoBTS/redactoria_V3:Q4_K_M
- LM Studio
- Jan
- Ollama
How to use NrengifoBTS/redactoria_V3 with Ollama:
ollama run hf.co/NrengifoBTS/redactoria_V3:Q4_K_M
- Unsloth Studio
How to use NrengifoBTS/redactoria_V3 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 NrengifoBTS/redactoria_V3 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 NrengifoBTS/redactoria_V3 to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for NrengifoBTS/redactoria_V3 to start chatting
- Atomic Chat new
- Docker Model Runner
How to use NrengifoBTS/redactoria_V3 with Docker Model Runner:
docker model run hf.co/NrengifoBTS/redactoria_V3:Q4_K_M
- Lemonade
How to use NrengifoBTS/redactoria_V3 with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull NrengifoBTS/redactoria_V3:Q4_K_M
Run and chat with the model
lemonade run user.redactoria_V3-Q4_K_M
List all available models
lemonade list
redactoria_V3 : GGUF
This model was finetuned and converted to GGUF format using Unsloth.
Example usage:
- For text only LLMs:
llama-cli -hf NrengifoBTS/redactoria_V3 --jinja - For multimodal models:
llama-mtmd-cli -hf NrengifoBTS/redactoria_V3 --jinja
Available Model files:
Meta-Llama-3.1-8B.Q4_K_M.ggufThis was trained 2x faster with Unsloth
license: apache-2.0 base_model: unsloth/meta-llama-3.1-8b-bnb-4bit tags: - marketing - seo - car-rental - automated-content - unsloth - trl - llama-3 language: - es metrics: - loss library_name: adapter
Redactoria V1 - Matrix Structure Generator 馃殫馃彚
Este modelo es una versi贸n finetuneada de Llama 3.1 8B dise帽ada espec铆ficamente para la generaci贸n de estructuras de contenido (matrices) para Landing Pages de renta de autos y hoteles, optimizadas para SEO.
馃摑 Descripci贸n del Modelo
El modelo ha sido entrenado para transformar par谩metros t茅cnicos (Marca, Tema, Template) en una matriz de contenido completa que sigue la jerarqu铆a visual y t茅cnica de la agencia:
- Formato de salida: Estructura de bloques delimitada por pipes (
| PG: | BLQ: | TIPO: | ES: |). - Tono de voz: Experto en Marketing Digital y SEO, profesional y persuasivo.
- Restricciones: No usa emojis, no usa negritas con
**y respeta estrictamente la jerarqu铆a de etiquetas (H1, H2, FAQ, etc.).
馃殌 Uso (Inferencia)
Para obtener los mejores resultados, utiliza el formato Alpaca y aseg煤rate de proporcionar el contexto completo.
from unsloth import FastLanguageModel
import torch
model, tokenizer = FastLanguageModel.from_pretrained("tu-usuario/nombre-del-modelo")
FastLanguageModel.for_inference(model)
alpaca_prompt = """### Instruction:
Generar el contenido para una landing page siguiendo el tono de voz de la marca y la estructura de bloques indicada.
### Input:
TEMA: {tema}
MARCA: {marca}
TEMPLATE: {template}
### Response:
"""
inputs = tokenizer([alpaca_prompt.format(
"Alquiler de autos en Miami",
"Viajemos",
"Template Agencias"
)], return_tensors = "pt").to("cuda")
outputs = model.generate(**inputs, max_new_tokens = 2048)
print(tokenizer.decode(outputs[0]))
- Downloads last month
- 2
4-bit
Model tree for NrengifoBTS/redactoria_V3
Base model
meta-llama/Llama-3.1-8B