Highlights
- Pro
Block or Report
Block or report hugoabonizio
Contact GitHub support about this userโs behavior. Learn more about reporting abuse.
Report abuseLists (11)
Sort Name ascending (A-Z)
Stars
Language
Sort by: Recently starred
Repository for "MultiHop-RAG: A Dataset for Evaluating Retrieval-Augmented Generation Across Documents"
A pair of tiny foundational models trained in Brazilian Portuguese.๐ฆ๐ฆ
Freeing data processing from scripting madness by providing a set of platform-agnostic customizable pipeline processing blocks.
Minimalistic large language model 3D-parallelism training
Everything you want to know about Google Cloud TPU
A Natural Portuguese Language Benchmark (Napolab) for the evaluation of language models.
Fine-tuning OpenLlama-Instruct with portuguese data, for commercial use.
Automated benchmarking for language-optimized LLMs. Evaluates both grammatical accuracy and semantic closeness of translations.
Code and documentation for the MariTalk API
List of resources and tools developed with focus on Portuguese.
Code and data to evaluate LLMs on the ENEM, the main standardized Brazilian university admission exams.
Python-based research interface for blackbox and hyperparameter optimization, based on the internal Google Vizier Service.
TorchGeo: datasets, samplers, transforms, and pre-trained models for geospatial data
A new markup-based typesetting system that is powerful and easy to learn.
Experiments in weaponizing Crystal for offensive operations.
Running large language models on a single GPU for throughput-oriented scenarios.
Optical illusions using stable diffusion
The lean application framework for Python. Build sophisticated user interfaces with a simple Python API. Run your apps in the terminal and a web browser.
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.
๐ฆ๐ Build context-aware reasoning applications
Bindings to use Crystal compiled to WebAssembly in a JavaScript environment, such as Node.js, Deno or the Web.