The Natural Portuguese Language Benchmark (Napolab). Stay up to date with the latest advancements in Portuguese language models and their performance across carefully curated Portuguese language tasks.
☆71Jul 28, 2025Updated last year
Alternatives and similar repositories for napolab
Users that are interested in napolab are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆12Oct 12, 2023Updated 3 years ago
- Code and data to evaluate LLMs on the ENEM, the main standardized Brazilian university admission exams.☆54Dec 6, 2024Updated last year
- List of resources and tools developed with focus on Portuguese.☆375Jun 25, 2026Updated 4 months ago
- Portuguese translation of the GLUE benchmark and Scitail dataset☆33Jun 27, 2022Updated 4 years ago
- ☆12Apr 29, 2022Updated 4 years ago
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- SemClinBr - a multi-institutional and multi-specialty semantically annotated corpus for Portuguese clinical NLP tasks☆38Mar 12, 2024Updated 2 years ago
- ☆30Apr 6, 2026Updated 7 months ago
- Brazilian Tertiary Care Dataset☆21Dec 14, 2022Updated 3 years ago
- This repository contains the necessary code to run POETA V2.☆13Jun 18, 2026Updated 4 months ago
- ☆27Jan 23, 2024Updated 2 years ago
- Supporting code for the paper "Portuguese Language Models and Word Embeddings: Evaluating on Semantic Similarity Tasks".☆11Dec 8, 2022Updated 3 years ago
- ☆19Dec 22, 2023Updated 2 years ago
- ☆17May 27, 2020Updated 6 years ago
- Transformer-powered hashtag segmentation with beam search, RRF ensembles, and agent-ready MCP workflows. A scalable alternative to heuris…☆78Aug 4, 2026Updated 3 months ago
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- ☆47Feb 7, 2024Updated 2 years ago
- Adapting Qwen2.5-14B to Brazilian SUS clinical guidelines. Includes 2 open benchmarks (HealthBench-BR, PCDT-QA) and 8 model checkpoints f…☆15May 7, 2026Updated 5 months ago
- ☆13Nov 10, 2024Updated last year
- Evaluation and baseline scripts for the ASSIN shared task.☆11Oct 12, 2019Updated 7 years ago
- Transformer model for Portuguese language (Brazil pt_BR)☆16Sep 1, 2026Updated 2 months ago
- A pair of tiny foundational models trained in Brazilian Portuguese.🦙🦙☆46Feb 24, 2026Updated 8 months ago
- NoHarm Discharge Summary - Improving Care Transition with LLM☆26Sep 23, 2026Updated last month
- A multilingual version of MS MARCO passage ranking dataset☆148Oct 19, 2023Updated 3 years ago
- Portuguese Named Entity Recognition☆63Sep 27, 2023Updated 3 years ago
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- Portuguese pre-trained BERT models☆888Jun 17, 2024Updated 2 years ago
- INCOME: An Easy Repository for Training and Evaluation of Index Compression Methods in Dense Retrieval. Includes BPR and JPQ.☆24Sep 24, 2023Updated 3 years ago
- Self-contained, comprehensive overview of PT-BR-LLMs advancements, architectures, and resources.☆37Aug 18, 2026Updated 2 months ago
- ☆29Feb 2, 2024Updated 2 years ago
- Code and documentation for the MariTalk API☆332Updated this week
- Fine-tuning OpenLlama-Instruct with portuguese data, for commercial use.☆20Aug 8, 2023Updated 3 years ago
- Inquisitive Parrots for Search☆203Updated this week
- ☆40May 13, 2023Updated 3 years ago
- ☆55Feb 25, 2026Updated 8 months ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- ☆13Jan 8, 2024Updated 2 years ago
- 🐦 Opytimizer is a Python library consisting of meta-heuristic optimization algorithms.☆26Updated this week
- Related resources to the paper RoBERTaLexPT: A Legal RoBERTa Model pretrained with deduplication for Portuguese.☆23Mar 14, 2024Updated 2 years ago
- Finetuning Stanford Alpaca (LLaMA) with Brazilian Portuguese data☆39Apr 10, 2023Updated 3 years ago
- Materials of the Tropical Probabilistic AI School 2024.☆23Feb 1, 2024Updated 2 years ago
- Minimal implementation of multiple PEFT methods for LLaMA fine-tuning☆13May 7, 2023Updated 3 years ago
- Instruct-tuning LLaMA on consumer hardware with machine-translated data☆19Apr 17, 2023Updated 3 years ago