Update services/llama_service.py

services/llama_service.py

@@ -5,8 +5,8 @@ from transformers import AutoTokenizer, AutoModelForCausalLM
 # Load Llama model and tokenizer for text generation
 
 
-tokenizer = AutoTokenizer.from_pretrained("meta-llama/Llama-3.2-1B")
-model = AutoModelForCausalLM.from_pretrained("meta-llama/Llama-3.2-1B")
+tokenizer = AutoTokenizer.from_pretrained("meta-llama/Llama-3.2-8B")
+model = AutoModelForCausalLM.from_pretrained("meta-llama/Llama-3.2-8B")
 
 # Ensure the tokenizer has a padding token; if not, add a new padding token
 if tokenizer.pad_token is None: