more Storage

app.py

@@ -1,21 +1,49 @@
 from transformers import MBartForConditionalGeneration, MBart50Tokenizer
 import dat
+import os
+import platform
+
+
+
+def setvar():
+    if platform.system() == "Windows":
+        print("Windows detected. Assigning cache directory to Transformers in AppData \ Local.")
+        transformers_cache_directory = os.path.join(os.getenv('LOCALAPPDATA'), 'transformers_cache')
+        if not os.path.exists(transformers_cache_directory):
+            try:
+                os.mkdir(transformers_cache_directory)
+                print(f"First launch. Directory '{transformers_cache_directory}' created successfully.")
+            except OSError as e:
+                print(f"Error creating directory '{transformers_cache_directory}': {e}")
+        else:
+            print(f"Directory '{transformers_cache_directory}' already exists.")
+        os.environ['TRANSFORMERS_CACHE'] = transformers_cache_directory
+        print("Environment variable assigned.")
+        del transformers_cache_directory
+
+    else:
+        print("Windows not detected. Assignment of Transformers cache directory not necessary.")
+
 
 # Load the model and tokenizer
 model_name = "LocalDoc/mbart_large_qa_azerbaijan"
 tokenizer = MBart50Tokenizer.from_pretrained(model_name, src_lang="en_XX", tgt_lang="az_AZ")
 model = MBartForConditionalGeneration.from_pretrained(model_name)
 
+
+
+
+
 def answer_question(context, question):
     # Prepare input text
     input_text = f"context: {context} question: {question}"
-    inputs = tokenizer(input_text, return_tensors="pt", max_length=512, truncation=False, padding="max_length")
+    inputs = tokenizer(input_text, return_tensors="pt", max_length=5120000, truncation=False, padding="max_length")
     
     # Generate answer
     outputs = model.generate(
         input_ids=inputs["input_ids"],
         attention_mask=inputs["attention_mask"],
-        max_length=128,
+        max_length=5120000,
         num_beams=5,
         early_stopping=True
     )