increased max_length to 6000

app.py

@@ -15,7 +15,7 @@ model = AutoModelForCausalLM.from_pretrained(MODEL_NAME, torch_dtype=torch.float
 def generate_sql_query(user_input):
     """ Convert natural language input into an SQL query """
     inputs = tokenizer(user_input, return_tensors="pt", padding=True, truncation=True).to(device)
-    outputs = model.generate(**inputs, max_length=100, do_sample=False, num_beams=2)
+    outputs = model.generate(**inputs, max_length=600, do_sample=False, num_beams=2)
     return tokenizer.decode(outputs[0], skip_special_tokens=True, clean_up_tokenization_spaces=True)
 
 @app.post("/chat")