Aitana-2B-S-tourism-base-1.0

Aitana-2B-S-tourism-base-1.0 is a generative language model from the Aitana family, developed by the GPLSI (Language and Information System Group) at the University of Alicante. This model is based on gplsi/Aitana-2B-S-base-1.0 and has been further trained on tourism domain data to enhance performance in tourism-related text generation.

Table of Contents

• Model Description
• Training Data
• Intended Uses
• How to Use
• GGUF for LM Studio
• Additional Information

Model Description

Property	Value
Base Model	gplsi/Aitana-2B-S-base-1.0
Architecture	Transformer decoder-only
Parameters	~2.25B
Languages	Valencian, Spanish, English
License	Apache 2.0

Aitana-2B-S-tourism-base-1.0 extends the Aitana-2B-S-base-1.0 foundation with additional training on tourism domain data. This specialized training makes it particularly well-suited for tourism-related applications in Valencian, Spanish, and English.

Training Data

This model was trained on the following tourism domain dataset:

Dataset ID	Name	Language	Source
dc7	tourism_va_2025	Valencian	gplsi/alia_tourism
dc7	tourism_es_2025	Spanish	gplsi/alia_tourism
dc7	tourism_en_2025	English	gplsi/alia_tourism

Data Source

• Tourism: Multilingual tourism domain content covering tourist information, destinations, accommodations, cultural sites, and travel-related text in Valencian, Spanish, and English.

Intended Uses

This model can be used for:

• Tourism text generation in Valencian, Spanish, and English
• Travel content creation and assistance
• Fine-tuning for specific tourism downstream tasks
• Domain adaptation for hospitality and travel applications

Note: This model is specifically optimized for tourism domain content. For general-purpose or administrative/legal text, consider using other models in the Aitana family.

How to Use

Transformers

import torch
from transformers import pipeline, AutoTokenizer

model_id = "gplsi/Aitana-2B-S-tourism-base-1.0"
tokenizer = AutoTokenizer.from_pretrained(model_id)

generator = pipeline(
    "text-generation",
    model=model_id,
    tokenizer=tokenizer,
    torch_dtype=torch.bfloat16,
    device_map="auto",
)

# Tourism example in Spanish
text = "El turismo en la Comunidad Valenciana ofrece"
result = generator(text, do_sample=True, top_k=10, max_new_tokens=100)
print(result[0]['generated_text'])

# Tourism example in Valencian
text = "Les platges de la Costa Blanca són"
result = generator(text, do_sample=True, top_k=10, max_new_tokens=100)
print(result[0]['generated_text'])

# Tourism example in English
text = "The best beaches in Valencia include"
result = generator(text, do_sample=True, top_k=10, max_new_tokens=100)
print(result[0]['generated_text'])

GGUF for LM Studio

This repository includes a GGUF version for use with LM Studio, Ollama, and other llama.cpp-based tools.

File	Precision	Size
Aitana-s2b-c0dc7-f16.gguf	F16	~4.5 GB

Using with llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
    repo_id="gplsi/Aitana-2B-S-tourism-base-1.0",
    filename="Aitana-s2b-c0dc7-f16.gguf",
)

output = llm("El turismo en Valencia ofrece", max_tokens=100)
print(output["choices"][0]["text"])

Additional Information

Author

GPLSI - Language and Information System Group
University of Alicante
https://gplsi.dlsi.ua.es/

Part of the Aitana Family

This model is part of the Aitana model family, which includes:

• gplsi/Aitana-2B-S-base-1.0 - Valencian-focused base model
• gplsi/Aitana-2B-S - Valencian-focused base model
• gplsi/Aitana-TA-2B-S - Translation model (Spanish ↔ Valencian)
• gplsi/Aitana-s2b-c0dc17 - Multi-domain model (administrative, legal, tourism)

Funding

This work was funded by:

• ILENIA project
• VIVES project (2022/TL22/00215334)

License

Apache License 2.0

Disclaimer

This model is intended for general purposes and is available under a permissive Apache License 2.0. Be aware that the model may have biases and/or undesirable outputs. Users deploying systems based on this model are responsible for mitigating risks and complying with applicable AI regulations.

---

Copyright © 2025 GPLSI - University of Alicante