Update README.md

README.md

@@ -21,7 +21,7 @@ tags:
 ---
 # Maistros-8B-Instruct: A Greek Large Language Model adapted through Knowledge Distillation from Large Reasoning Models
 
-‼️If the full model does not fit in your setup, you can use the official [4-bit quantized version](https://huggingface.co/IMISLab/Maistros-8B-Instruct-4bit), which uses 65% less memory. ‼️
+‼️If the full model does not fit in your setup, you can use the official [4-bit quantized version](https://huggingface.co/IMISLab/Maistros-8B-Instruct-4bit), which uses 65% less memory.‼️
 
 We introduce Maistros-8B-Instruct, a Greek-adapted LLM based on `mistralai/Ministral-3-8B-Instruct-2512-BF16` fine-tuned using Low-Rank Adaptation (LoRA) on [CulturaQA](https://huggingface.co/datasets/IMISLab/CulturaQA).   
 For information regarding the model training, validation and evaluation, as well as its limitations see the [arxiv preprint](). 
@@ -75,14 +75,13 @@ self.tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code = T
 tokenizer.pad_token = tokenizer.eos_token
 tokenizer.padding_side = 'right'
 
-
 # Load the model from the path to the device and set it in evaluation mode.
 self.model = Mistral3ForConditionalGeneration.from_pretrained(model_path, device_map = self.device, trust_remote_code = True)
 self.model.eval()
 
 # Set the system, instruction and user prompts.
-system_prompt = ''
-instruction_prompt = ''
+system_prompt = 'Είσαι ο Μαΐστρος, ένα εξαιρετικά ανεπτυγμένο μοντέλο Τεχνητής Νοημοσύνης για την Ελληνική γλώσσα.\nΈχεις δημιουργηθεί απο το IMIS Lab του Πανεπιστημιού Πατρών.'
+instruction_prompt = 'Παρακαλώ απάντησε στην παρακάτω απάντηση.'
 user_prompt = ''
 
 # Defining the message template.