projecte-aina / Flor1.3RAG

FLOR-1.3B Model optimized for QA

Table of Contents

Model description

Flor1.3RAG is a 6.3B-parameter transformer-based causal language model for Catalan, Spanish, and English, trained on 3 epochs on a customized QA dataset from various sources especifically to be used in RAG (Retrieval-Aumented Generation) Applications. The dataset used to fine tune the model is: PureInstructQA

Intended uses and limitations

The Flor1.3RAG model is ready-to-use for RAG applications optimized for Catalan language. It can perform text-generation Question Answering in the context of RAG applications. This model does not require a GPU to run.

How to use

import torch
from transformers import pipeline

pipe = pipeline("text-generation", model="projecte-aina/Flor1.3RAG")

instruction = "Quants habitants té Mataró?"

context = "Mataró és una ciutat de Catalunya, capital de la comarca del Maresme. Situada al litoral mediterrani, a uns 30 km al nord-est de Barcelona, ha estat tradicionalment un centre administratiu de rellevància territorial i un pol de dinamisme econòmic. Compta amb prop de 130.000 habitants, essent actualment la vuitena població del Principat i la tretzena dels Països Catalans. "

# We need to format the prompt and context using ### and \n

def givePrediction(instruction, context, max_new_tokens=50, repetition_penalty=1.2, top_k=50, top_p=0.95, do_sample=True, temperature=0.5):
    text = f"### Instruction\n{{instruction}}\n### Context\n{{context}}\n### Answer\n"
    response = pipe(text.format(instruction=instruction, context=context),temperature=temperature,repetition_penalty=repetition_penalty, max_new_tokens=max_new_tokens,top_k=top_k, top_p=top_p, do_sample=do_sample)[0]["generated_text"]
    answer = response.split("###")[-1][8:-1]
    return answer

answer = givePrediction(instruction, context)

print(answer)
'130 000'

Limitations and bias

At the time of submission, no measures have been taken to estimate the bias and toxicity embedded in the model. However, we are well aware that our models may be biased since the corpora have been collected using crawling techniques on multiple web sources. We intend to conduct research in these areas in the future, and if completed, this model card will be updated.

Training

Instruction Data

The training corpus is composed of 82,539 QA instruction following examples. See Data Card at PureInstructQA .

Additional information

Author

The Language Technologies Unit from Barcelona Supercomputing Center.

Contact

For further information, please send an email to [email protected] .

Copyright

Copyright(c) 2023 by Language Technologies Unit, Barcelona Supercomputing Center.

License

Apache License, Version 2.0

Funding

This work was funded by Departament de la Vicepresidència i de Polítiques Digitals i Territori de la Generalitat de Catalunya within the framework of Projecte AINA .

Disclaimer