Open Issues Need Help
View All on GitHub Human-labeled evaluation of real PT-BR use cases 28 days ago
help wanted evaluation
Local-first decision models for fast typed decisions at scale, with PT-BR-first evaluation.
Python
#calibration#decision-engine#local-ai#machine-learning#multilingual#open-source#pt-br#python
Benchmark v2: more sources and a score task about 1 month ago
help wanted evaluation
Local-first decision models for fast typed decisions at scale, with PT-BR-first evaluation.
Python
#calibration#decision-engine#local-ai#machine-learning#multilingual#open-source#pt-br#python
Train and select the first Saracura universal checkpoint about 1 month ago
help wanted roadmap model
Local-first decision models for fast typed decisions at scale, with PT-BR-first evaluation.
Python
#calibration#decision-engine#local-ai#machine-learning#multilingual#open-source#pt-br#python
Publish same-hardware PT-BR quality and throughput evidence about 1 month ago
help wanted roadmap evaluation release
Local-first decision models for fast typed decisions at scale, with PT-BR-first evaluation.
Python
#calibration#decision-engine#local-ai#machine-learning#multilingual#open-source#pt-br#python
Package public weights, model card, and one-command local inference about 1 month ago
help wanted roadmap model release
Local-first decision models for fast typed decisions at scale, with PT-BR-first evaluation.
Python
#calibration#decision-engine#local-ai#machine-learning#multilingual#open-source#pt-br#python
Freeze the v0.2 PT-BR model evaluation protocol about 1 month ago
help wanted roadmap evaluation
Local-first decision models for fast typed decisions at scale, with PT-BR-first evaluation.
Python
#calibration#decision-engine#local-ai#machine-learning#multilingual#open-source#pt-br#python