# Portuguese instruction fine-tuning

Portuguese model trained on a 300,000 Portuguese instruction dataset, fine-tuned from microsoft/Phi-3-mini-4k

A Portuguese large language model fine-tuned based on Mistral-7B-Instruct-v0.2, focusing on improving Portuguese text generation capabilities

This is a fine-tuned version based on the TinyLlama-1.1B model, specifically optimized for Portuguese instructions, supporting 8k context length, suitable for basic retrieval-augmented generation and QA tasks.

A bilingual (Portuguese/English) text generation model fine-tuned from Falcon-7B using QLoRA method