Update README.md

README.md

@@ -9,7 +9,7 @@ pipeline_tag: question-answering
 
 First of all, we would like to express our gratitude to [PartAI](https://huggingface.co/PartAI) for their efforts in expanding large language models in the Persian language by releasing the ["Darna"](https://huggingface.co/PartAI/Dorna-Llama3-8B-Instruct) model.
 
-The quantized version of the "Darna" language model requires only 6GB of GPU memory for loading, while the original model requires 40GB of GPU memory.
+The quantized version of the "Darna" language model requires only ~6GB of GPU memory for loading, while the original model requires ~40GB of GPU memory.
 
 This model based on AWQ quantize method that decrease the volume of model in minimum decrease of Accuracy by changing type of weights