luc1-7B-FinChile Training

Entrenamiento del modelo especializado en razonamiento financiero chileno.

  • Modelo base: Qwen/Qwen2.5-7B-Instruct
  • Dataset: 710 ejemplos (luc1K-1K)
  • Método: SFT + QLoRA en 4-bit
  • Técnica: Budget Forcing (en inferencia)
Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support