Maicon Domingues's repositories
alpaca-lora-ptbr-7b
Finetuning Stanford Alpaca (LLaMA) with Brazilian Portuguese data
language-detection-lora
This model is an adjusted version of xlm-roberta-base to identify the language of a text.
pt_core_news_trf
Portuguese transformer pipeline (neuralmind/bert-base-portuguese-cased). Components: transformer, morphologizer, parser, ner, attribute_ruler, lemmatizer (trainable_lemmatizer).
alpaca-lora
Instruct-tune LLaMA on consumer hardware
canarim-7b-vestibulaide
Canarim-7B-VestibulAide é um modelo desenvolvido para auxiliar estudantes a resolver e compreender questões de vestibulares brasileiros, ajustado à língua portuguesa.
Canarim-Instruct-PTBR
Canarim, a set of instructions in Portuguese created for training new LLMs with over 300,000 examples.
stt_pt_quartznet15x5_ctc_small
Fine-tuned Quartznet-15x5 CTC small model for speech recognition in Portuguese
canarim-bert-nheengatu
BERT model pre-trained for the Nheengatu language
NeMo
NeMo: a toolkit for conversational AI
textstat
:memo: python package to calculate readability statistics of a text object - paragraphs, sentences, articles.
lama-cleaner
Image inpainting tool powered by SOTA AI Model. Remove any unwanted object, defect, people from your pictures or erase and replace(powered by stable diffusion) any thing on your pictures.