projecte-aina / FlorRAG

FLOR-6.3B Model optimized for Retrieval Augmented Generation

Table of Contents

Model description

FlorRAG is a 6.3B-parameter transformer-based causal language model for Catalan, Spanish, and English, trained 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: projecte-aina/RAG_Multilingual

Intended uses and limitations

The FlorRAG model is ready-to-use for RAG applications optimized for Catalan, English and Spanish languages. It can perform text-generation in the context of RAG applications.

How to use

import torch
from transformers import pipeline

pipe = pipeline("text-generation", model="projecte-aina/FlorRAG")

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)
'Mataró té una població de 130.000 habitants. Aquesta ciutat catalana, situada al litoral mediterrani, a uns 30 km al nord-est de Barcelona, ha estat històricament un important centre administratiu i un important pol de dinamisme econòmic.'

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 56.406 RAG instruction following examples, created from extractive QA instances that were used as 'kernels of truth' to prompt a Mixture of expert model to generate more human-like and complete answers, based on a context. See Data Card at projecte-aina/RAG_Multilingual .

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) 2024 by Language Technologies Unit, Barcelona Supercomputing Center.

License

Apache License, Version 2.0

Funding

This work/research has been promoted and financed by the Government of Catalonia through the Aina project .

Disclaimer