Fix padding and truncation issues

llama_models.py

@@ -14,17 +14,14 @@ def load_model(model_name):
     if not tokenizer or not model:
         print("Loading model and tokenizer...")
         tokenizer = AutoTokenizer.from_pretrained(model_name)
+        tokenizer.pad_token = tokenizer.eos_token  # Set pad_token to eos_token
         model = AutoModelForCausalLM.from_pretrained(model_name)  # Ensure correct model class
         print("Model and tokenizer loaded successfully.")
     return tokenizer, model
 
 async def process_text_local(model_name, text):
-    print("Loading model and tokenizer...")
     tokenizer, model = load_model(model_name)
-    print("Encoding text...")
-    inputs = tokenizer(text, return_tensors="pt", padding=True, truncation=True)
-    print("Generating output...")
+    inputs = tokenizer(text, return_tensors="pt", padding=True, truncation=True, max_length=512)  # Set max_length to 512
     outputs = model.generate(**inputs, max_length=512)
-    print("Decoding output...")
     result = tokenizer.decode(outputs[0], skip_special_tokens=True)
     return result