by renatospessotto
Fine-tunes and evaluates Laya for Portuguese review aspect classification
Teste do encoder Laya em PT-BR: Laya, BERTimbau e Qwen3.5-2B (QLoRA) destilados do Claude para extrair aspectos de reviews. F1 0,74 a 1/30 do custo; cascata calibrada supera o Claude com 20% das chamadas. Modelos no Hugging Face, Docker.
Platforms
Related projects
laya
NandhaKishorM
Runs multilingual typed-decision models and provides routing, serving, and integration options
laya-mlx
mizorewww
Runs Laya typed-decision models locally on Apple Silicon using MLX
laya
convaiinnovations
A multilingual-ready System 1 model that returns calibrated typed decisions over text in one pass
laya-coreml
mizorewww
Runs Laya typed-decision models locally on Apple Silicon using Core ML and the Neural Engine
laya-multilingual
convaiinnovations
A multilingual System 1 model that returns calibrated typed decisions over text in one pass
openJev-verdict-2.0
Heman10x-NGU
Develops and benchmarks a non-autoregressive typed-decision model against Jev and Laya