Update app.py

app.py

@@ -5,13 +5,12 @@ import gradio as gr
 from transformers import MarianMTModel, MarianTokenizer, AutoModelForCausalLM, AutoTokenizer
 import os
 
-# Load the translation model
+# Load models and tokenizers globally to avoid reloading them for every request
 model_name = "Helsinki-NLP/opus-mt-mul-en"
 translation_model = MarianMTModel.from_pretrained(model_name)
 translation_tokenizer = MarianTokenizer.from_pretrained(model_name)
 
-# Load GPT-Neo model and tokenizer
-gpt_model_name = "EleutherAI/gpt-neo-1.3B"  # You can also use gpt-neo-2.7B if needed
+gpt_model_name = "EleutherAI/gpt-neo-1.3B"
 gpt_tokenizer = AutoTokenizer.from_pretrained(gpt_model_name)
 gpt_model = AutoModelForCausalLM.from_pretrained(gpt_model_name)
 
@@ -24,7 +23,7 @@ def translate_text(tamil_text):
 def query_gpt_neo(translated_text):
     prompt = f"Continue the story based on the following text: {translated_text}"
     inputs = gpt_tokenizer(prompt, return_tensors="pt")
-    outputs = gpt_model.generate(inputs['input_ids'], max_length=100, num_return_sequences=1)
+    outputs = gpt_model.generate(inputs['input_ids'], max_length=50, num_return_sequences=1)  # Reduced max_length
     creative_text = gpt_tokenizer.decode(outputs[0], skip_special_tokens=True)
     return creative_text