Instructions to use QuantFactory/leniachat-qwen2-1.5B-v0-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use QuantFactory/leniachat-qwen2-1.5B-v0-GGUF with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("QuantFactory/leniachat-qwen2-1.5B-v0-GGUF", dtype="auto") - llama-cpp-python
How to use QuantFactory/leniachat-qwen2-1.5B-v0-GGUF with llama-cpp-python:
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="QuantFactory/leniachat-qwen2-1.5B-v0-GGUF", filename="leniachat-qwen2-1.5B-v0.Q2_K.gguf", )
llm.create_chat_completion( messages = "No input example has been defined for this model task." )
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- llama.cpp
How to use QuantFactory/leniachat-qwen2-1.5B-v0-GGUF with llama.cpp:
Install from brew
brew install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf QuantFactory/leniachat-qwen2-1.5B-v0-GGUF:Q4_K_M # Run inference directly in the terminal: llama-cli -hf QuantFactory/leniachat-qwen2-1.5B-v0-GGUF:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf QuantFactory/leniachat-qwen2-1.5B-v0-GGUF:Q4_K_M # Run inference directly in the terminal: llama-cli -hf QuantFactory/leniachat-qwen2-1.5B-v0-GGUF: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 QuantFactory/leniachat-qwen2-1.5B-v0-GGUF:Q4_K_M # Run inference directly in the terminal: ./llama-cli -hf QuantFactory/leniachat-qwen2-1.5B-v0-GGUF: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 QuantFactory/leniachat-qwen2-1.5B-v0-GGUF:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf QuantFactory/leniachat-qwen2-1.5B-v0-GGUF:Q4_K_M
Use Docker
docker model run hf.co/QuantFactory/leniachat-qwen2-1.5B-v0-GGUF:Q4_K_M
- LM Studio
- Jan
- Ollama
How to use QuantFactory/leniachat-qwen2-1.5B-v0-GGUF with Ollama:
ollama run hf.co/QuantFactory/leniachat-qwen2-1.5B-v0-GGUF:Q4_K_M
- Unsloth Studio new
How to use QuantFactory/leniachat-qwen2-1.5B-v0-GGUF 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 QuantFactory/leniachat-qwen2-1.5B-v0-GGUF 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 QuantFactory/leniachat-qwen2-1.5B-v0-GGUF to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for QuantFactory/leniachat-qwen2-1.5B-v0-GGUF to start chatting
- Docker Model Runner
How to use QuantFactory/leniachat-qwen2-1.5B-v0-GGUF with Docker Model Runner:
docker model run hf.co/QuantFactory/leniachat-qwen2-1.5B-v0-GGUF:Q4_K_M
- Lemonade
How to use QuantFactory/leniachat-qwen2-1.5B-v0-GGUF with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull QuantFactory/leniachat-qwen2-1.5B-v0-GGUF:Q4_K_M
Run and chat with the model
lemonade run user.leniachat-qwen2-1.5B-v0-GGUF-Q4_K_M
List all available models
lemonade list
- QuantFactory/leniachat-qwen2-1.5B-v0-GGUF
- Original Model Card
- Chat & Instructions 1.5B LLM by LenguajeNatural.AI | Modelo LenguajeNatural.AI Chat e Instrucciones 1.5B
- Developed by LenguajeNatural.AI
- Desarrollado por LenguajeNatural.AI
- License
- Licencia
- Base Model
- Modelo Base
- Language
- Idioma
- Training
- Entrenamiento
- Maximum Sequence Length
- Tama帽o m谩ximo de secuencia
- Usage and Limitations
- Usos y Limitaciones
- How to start?
- 驴C贸mo empezar?
- Evaluation
- Evaluaci贸n
- Contributions and Future Versions
- Contribuciones
- Futuras Versiones
QuantFactory/leniachat-qwen2-1.5B-v0-GGUF
This is quantized version of LenguajeNaturalAI/leniachat-qwen2-1.5B-v0 created using llama.cpp
Original Model Card
Chat & Instructions 1.5B LLM by LenguajeNatural.AI | Modelo LenguajeNatural.AI Chat e Instrucciones 1.5B
Developed by LenguajeNatural.AI
This model has been developed by LenguajeNatural.AI, with the aim of providing the Spanish-speaking community with advanced tools for text generation, chat, and instructions. It is the second released model of the LeNIA series, significantly outperforming the first one, being also smaller (1.5B vs 2B) and with a larger sequence size (32K vs 8K).
Technical Details
- Maximum Sequence Length: 32K
- Model Size: 1.5B parameters
- Architecture: Qwen2
- Trained in 3 steps:
- Domain Flan-style adaptation to Spanish: Massive Spanish instruction tuning
- High Quality Spanish Instruction Tuning
- Chat-Abstractive QA Fine-Tuning
Desarrollado por LenguajeNatural.AI
Este modelo ha sido desarrollado por LenguajeNatural.AI, con el objetivo de proporcionar a la comunidad de habla hispana herramientas avanzadas para la generaci贸n de texto, chat e instrucciones. Es el segundo modelo liberado de la saga LeNIA, superando con bastante margen el rendimiento del primero de ellos, siendo adem谩s m谩s peque帽o (1.5B vs 2B) y con mayor tama帽o de secuencia (32K vs 8K).
License
This model is distributed under Apache 2.0. License.
Licencia
Este modelo se distribuye bajo la licencia Apache 2.0.
Base Model
This model has been fine-tuned from Qwen/Qwen2-1.5B, incorporating advanced features for better text generation and understanding in Spanish chat and instruction tasks.
Modelo Base
Este modelo se ha afinado a partir de Qwen/Qwen2-1.5B, incorporando caracter铆sticas avanzadas para una mejor generaci贸n de texto y comprensi贸n en tareas de chat e instrucciones en espa帽ol.
Language
The model has been trained exclusively in Spanish, with the aim of maximizing its effectiveness in applications intended for Spanish-speaking users.
Idioma
El modelo ha sido entrenado exclusivamente en espa帽ol, con el objetivo de maximizar su efectividad en aplicaciones destinadas a usuarios de habla hispana.
Training
The model has been trained in three distinct phases to ensure good performance across a wide range of tasks:
- Multi-task learning in Spanish: Using multiple supervised datasets for FLAN-style training.
- High-quality instruction training: Fine-tuning the model to understand and generate responses to complex instructions.
- Chat and abstractive QA training: Optimizing the model for smooth conversations and generating answers to abstract questions.
In all three phases, training was carried out thanks to our library autotransformers.
Entrenamiento
El modelo se ha entrenado en tres fases distintas para asegurar un buen rendimiento en una amplia gama de tareas:
- Aprendizaje multi-tarea en espa帽ol: Utilizando m煤ltiples conjuntos de datos supervisados para un entrenamiento al estilo FLAN.
- Entrenamiento de instrucciones de alta calidad: Afinando el modelo para entender y generar respuestas a instrucciones complejas.
- Entrenamiento de chat y QA abstractivo: Optimizando el modelo para conversaciones fluidas y la generaci贸n de respuestas a preguntas abstractas.
En las 3 fases se ha llevado a cabo el entrenamiento gracias a nuestra librer铆a autotransformers.
Maximum Sequence Length
The maximum sequence length for this model is 32768 tokens, 4x more than the previous LeNIA-Chat version.
Tama帽o m谩ximo de secuencia
El tama帽o m谩ximo de secuencia para este modelo es de 8192 tokens, 4 veces m谩s que la versi贸n anterior de LeNIA-Chat.
Usage and Limitations
This model is designed to be used in text generation applications, chatbots, and virtual assistants in Spanish. Although it has been trained to minimize biases and errors, we recommend evaluating its performance in its specific context of use. Users should be aware of the inherent limitations of language models and use this model responsibly. Additionally, it should be noted that the base model is only 1.5B parameters, so this model shares the inherent limitations of models of that size.
Usos y Limitaciones
Este modelo est谩 dise帽ado para ser utilizado en aplicaciones de generaci贸n de texto, chatbots, y asistentes virtuales en espa帽ol. Aunque ha sido entrenado para minimizar sesgos y errores, recomendamos evaluar su desempe帽o en su contexto espec铆fico de uso. Los usuarios deben ser conscientes de las limitaciones inherentes a los modelos de lenguaje y utilizar este modelo de manera responsable. Adem谩s, debe tenerse en cuenta que el modelo base es de 煤nicamente 1.5b par谩metros, por lo que este modelo comparte las limitaciones inherentes a los modelos de ese tama帽o.
How to start?
You can start using this model through the Hugging Face API or integrate it into your applications using the transformers library. Here is an example of how to load the model:
驴C贸mo empezar?
Puedes empezar a utilizar este modelo a trav茅s de la API de Hugging Face o integrarlo en tus aplicaciones utilizando la biblioteca transformers. Aqu铆 tienes un ejemplo de c贸mo cargar el modelo:
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch
model_name = "LenguajeNaturalAI/leniachat-gemma-2b-v0"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name)
# Generar texto
messages = [
{"role": "system", "content": "Eres un asistente que ayuda al usuario a lo largo de la conversaci贸n resolviendo sus dudas."},
{"role": "user", "content": "驴Qu茅 fue la revoluci贸n industrial?"}
]
input_ids = tokenizer.apply_chat_template(messages, tokenize=True, return_tensors="pt")
with torch.no_grad():
output = model.generate(input_ids, max_new_tokens=50)
print(tokenizer.decode(output[0], skip_special_tokens=True))
Evaluation
To ensure the quality of the model, an extensive evaluation has been carried out on several datasets, showing significant performance in text generation and understanding instructions in Spanish. The specific details of the evaluation of the LeNIA-Chat models are available in the following table.
Evaluaci贸n
Para asegurar la calidad del modelo, se ha realizado una evaluaci贸n exhaustiva en varios conjuntos de datos, mostrando un rendimiento significativo en la generaci贸n de texto y la comprensi贸n de instrucciones en espa帽ol. Los detalles espec铆ficos de la evaluaci贸n de los modelos LeNIA-Chat est谩n disponibles en la siguiente tabla.
Contributions and Future Versions
We encourage the community to help to build better LLMs in Spanish by providing suggestions or feedback to improve the model. Collaboration is fundamental for AI advancements, specially to make it accessible and ethical.
We plan to keep on improving this model and launch future versions with advanced capabilities. Stay tuned to our updates through our webpage or our LinkedIn page
Contribuciones
Animamos a la comunidad a contribuir con retroalimentaci贸n, sugerencias, y mejoras para este modelo. La colaboraci贸n es fundamental para el avance de la inteligencia artificial accesible y 茅tica.
Futuras Versiones
Planeamos continuar mejorando este modelo y lanzar versiones futuras con capacidades ampliadas. Mantente atento a nuestras actualizaciones. Puedes estar al tanto en nuestra p谩gina web o nuestra p谩gina de LinkedIn.
- Downloads last month
- 356
2-bit
3-bit
4-bit
5-bit
6-bit
8-bit
Model tree for QuantFactory/leniachat-qwen2-1.5B-v0-GGUF
Base model
Qwen/Qwen2-1.5B

