phamhai/Llama-3.2-3B-Instruct-Frog

The phamhai/Llama-3.2-3B-Instruct-Frog is a 3.2 billion parameter instruction-tuned causal language model developed by phamhai, based on Meta's Llama-3.2 architecture. This model is specifically optimized for Retrieval-Augmented Generation (RAG) tasks in Vietnamese, addressing the limited support for the language in the base Llama-3.2 models. It features a 131K context length and is designed for fast inference on edge devices, making it suitable for Vietnamese language applications requiring efficient RAG capabilities.