Update app.py

app.py

@@ -42,8 +42,21 @@ def chat_with_distilgpt2(input_text):
     # Tokenize the input and convert to tensor
     input_ids = tokenizer.encode(full_input, return_tensors="pt").to(device)
     
-    # Generate the response using the model
-    outputs = model.generate(input_ids, max_length=150, num_return_sequences=1, pad_token_id=tokenizer.eos_token_id)
+    # Generate the response using the model with adjusted parameters
+    outputs = model.generate(
+        input_ids,
+        max_length=input_ids.shape[1] + 100,  # Limit total length
+        max_new_tokens=100,
+        num_return_sequences=1,
+        no_repeat_ngram_size=3,
+        repetition_penalty=1.2,
+        temperature=0.7,
+        top_k=50,
+        top_p=0.95,
+        early_stopping=True,
+        pad_token_id=tokenizer.eos_token_id,
+        eos_token_id=tokenizer.eos_token_id
+    )
     
     # Decode the model output
     response = tokenizer.decode(outputs[0], skip_special_tokens=True)