Multilingual fine tuned version of LLAMA-3-8B quantized in 4 bits.

Multilingual fine tuned version of LLAMA-3-8B quantized in 4 bits using common open source datasets and showing improvements over multilingual tasks. It has been used the standard bitquantized technique for post-fine-tuning quantization reducing the computational time complexity and space complexity required to run the model. The overall architecture it's all LLAMA-3 based.