Update README.md

README.md

@@ -69,30 +69,29 @@ device = 'cuda'
 set_seed(42)
 
 # Loading the model tokenizer.
-self.tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code = True)
+tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code = True)
 
 # Causal Language Models predict tokens from left to right and use EOS token for padding.
 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()
+model = Mistral3ForConditionalGeneration.from_pretrained(model_path, device_map = device, trust_remote_code = True)
+model.eval()
 
 # Set the system, instruction and user prompts.
 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 = ''
+user_prompt = 'Τι είναι η Ακρόπολη των Αθηνών;'
 
 # Defining the message template.
 messages = [
-    {'role': 'system', 'content': [{'type': 'text', 'text': system_prompt}]}
+    {'role': 'system', 'content': [{'type': 'text', 'text': system_prompt}]},
     {'role': 'user', 'content': [{'type': 'text', 'text': '\n\n'.join((instruction_prompt, user_prompt))}]}
 ]
 
 # Applying the tokenizer chat template.
-tokenized = self.tokenizer.apply_chat_template(
+tokenized = tokenizer.apply_chat_template(
     messages,
     add_generation_prompt = True,  
     return_tensors = 'pt', 
@@ -100,13 +99,13 @@ tokenized = self.tokenizer.apply_chat_template(
 )
 
 # Sending the tokenized instances to the device.  
-tokenized = {k: v.to(self.device) for k, v in tokenized.items()}
+tokenized = {k: v.to(device) for k, v in tokenized.items()}
 input_len = len(tokenized['input_ids'][0])
 
 # Generating the model output.
-output = self.model.generate(
+output = model.generate(
     **tokenized,
-    max_new_tokens = self.max_output_tokens,
+    max_new_tokens = 1024,
     do_sample = False, # Equivalent to temperature = 0.0
     temperature = None,
     top_p = None,
@@ -114,7 +113,7 @@ output = self.model.generate(
 )
 
 # Decoding the assistant part of the output and printing it.
-decoded_output = self.tokenizer.decode(output[0][input_len:], skip_special_tokens = True)
+decoded_output = tokenizer.decode(output[0][input_len:], skip_special_tokens = True)
 print(decoded_output)
 ```