# Persian optimization

Dorna2-Llama3.1-8B-Instruct is an 8B parameter large language model developed by Part AI based on Meta Llama 3.1 Instruct, specifically optimized for Persian language.

This is a sentence transformer model fine-tuned on xlm-roberta-large, which can map text to a 1024-dimensional vector space and support multilingual semantic understanding tasks.

4-bit quantized version of Dorna-Llama3-8B-Instruct, optimized for Persian language with Flash Attention 2 technology for enhanced inference efficiency

Dorna-Llama3-8B-Instruct is an 8B parameter instruction fine-tuned model based on Meta Llama 3, specifically optimized for Persian language, developed by Part AI.