Update app.py

app.py

@@ -17,7 +17,7 @@ DetectorFactory.seed = 0
 CHECKPOINT_FILE = "checkpoint.txt"
 TOKENIZER_DIR = "tokenizer_model"
 TOKENIZER_FILE = os.path.join(TOKENIZER_DIR, "tokenizer.json")
-MAX_SAMPLES = 3000000  # Όριο δειγμάτων
+MAX_SAMPLES = 50000000  # Όριο δειγμάτων
 
 # Παγκόσμια μεταβλητή ελέγχου συλλογής
 STOP_COLLECTION = False
@@ -172,7 +172,7 @@ with gr.Blocks() as demo:
             dataset_name = gr.Textbox(value="wikimedia/wikipedia", label="Dataset Name")
             configs = gr.Textbox(value="20231101.el,20231101.en", label="Configs")
             split = gr.Dropdown(choices=["train"], value="train", label="Split")
-            chunk_size = gr.Slider(500, 10000, value=5000, label="Chunk Size")
+            chunk_size = gr.Slider(500, 10000, value=50000, label="Chunk Size")
             vocab_size = gr.Slider(20000, 100000, value=50000, label="Vocabulary Size")
             min_freq = gr.Slider(1, 100, value=3, label="Minimum Frequency")
             test_text = gr.Textbox(value="Η Ακρόπολη είναι σύμβολο της αρχαίας Ελλάδας.", label="Test Text")