https://github.com/lucianosb/awesome-nlpbr

Curadoria dos melhores links compartilhados no grupo https://t.me/nlpbr no Telegram.
https://github.com/lucianosb/awesome-nlpbr

List: awesome-nlpbr

Last synced: 16 days ago
JSON representation

Curadoria dos melhores links compartilhados no grupo https://t.me/nlpbr no Telegram.

• Host: GitHub
• URL: https://github.com/lucianosb/awesome-nlpbr
• Owner: lucianosb
• License: mit
• Created: 2023-02-09T19:36:43.000Z (almost 2 years ago)
• Default Branch: main
• Last Pushed: 2024-04-10T19:49:16.000Z (8 months ago)
• Last Synced: 2024-05-22T19:06:53.517Z (7 months ago)
• Homepage:
• Size: 12.7 KB
• Stars: 10
• Watchers: 4
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

• ultimate-awesome - awesome-nlpbr - Curadoria dos melhores links compartilhados no grupo no Telegram. (Other Lists / Monkey C Lists)

README

        
# Awesome NLPBR

Curadoria dos melhores links compartilhados no grupo [nlpbr](https://t.me/nlpbr) no telegram.

## Datasets

- [Corpus do Português](https://www.corpusdoportugues.org)

- [Hate Speech BR](https://github.com/franciellevargas/HateBR)

- [Análise de Sentimentos](https://www.kaggle.com/datasets/fredericods/ptbr-sentiment-analysis-datasets)

- [dominguesm/Canarim-Instruct-PTBR-Dataset](https://huggingface.co/datasets/dominguesm/Canarim-Instruct-PTBR-Dataset)

- [dominguesm/alpaca-data-pt-br](https://huggingface.co/datasets/dominguesm/alpaca-data-pt-br)

## Modelos pré-treinados

- [Open Cabrita-3B](https://huggingface.co/22h/open-cabrita3b)

- [Open Cabrita-3B Quantizado](https://huggingface.co/lucianosb/open-cabrita3b-GGUF)

- [Canarim-7B](https://huggingface.co/dominguesm/canarim-7b)

- [Canarim-7B Quantizado](https://huggingface.co/lucianosb/canarim-7B-GGUF)

- [Canarim-7B Instruct](https://huggingface.co/dominguesm/Canarim-7B-Instruct)

- [Canarim-7B Instruct Quantizado](https://huggingface.co/lucianosb/canarim-7B-instruct-GGUF)

- [Sabiá-7B](https://huggingface.co/maritaca-ai/sabia-7b)

- [Sabiá-7B Quantizado](https://huggingface.co/lucianosb/sabia-7b-GGUF)

- [OPT - Alpa](https://opt.alpa.ai)

- [Bloom](https://huggingface.co/bigscience/bloom)

- [Legal BERTimbau](https://huggingface.co/stjiris/bert-large-portuguese-cased-legal-mlm)

- [T5 base QA](https://huggingface.co/pierreguillou/t5-base-qa-squad-v1.1-portuguese)

- [BERTimbau Base](https://huggingface.co/neuralmind/bert-base-portuguese-cased)

- [Repositório de Word Embeddings do NILC](http://nilc.icmc.usp.br/nilc/index.php/repositorio-de-word-embeddings-do-nilc)

- [dominguesm/canarim-7b-vestibulaide](https://huggingface.co/dominguesm/canarim-7b-vestibulaide)

- [dominguesm/alpaca-lora-ptbr-7b](https://huggingface.co/dominguesm/alpaca-lora-ptbr-7b)

## Ferramentas

- [🚀 Open Portuguese LLM Leaderboard](https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard)

- [Doccano Annotation Tool](https://github.com/doccano/doccano)

- [Label Studio](https://labelstud.io)

- [Google Colab - Naive Bayes para Análise de Sentimento](https://colab.research.google.com/drive/1q-kxE7Vi9lmvDc7nzfELiJn0qkKuqh2q?usp=sharing)

- [Parsr - Extração de PDFs](https://github.com/axa-group/Parsr)

- [Lemmatizer](https://portulanclarin.net/workbench/lx-lemmatizer/)

- [stopwords para uso em jurimetria](https://github.com/jjesusfilho/justop)

- [Prompts Royale](https://github.com/meistrari/prompts-royale)

## Tutoriais e Cursos

- [Livro Processamento de Linguagem Natural - Brasileiras PLN](https://brasileiraspln.com/livro-pln/)

- [NLPortuguês - Coursera](https://nlportugues.ime.usp.br/)

- [The Transformer Family Version 2.0](https://lilianweng.github.io/posts/2023-01-27-the-transformer-family-v2/)

## Outros

- [Portuguese-NLP](https://github.com/ajdavidl/Portuguese-NLP)