use HF token

src/models/llm_manager.py

@@ -5,6 +5,8 @@ import torch
 from transformers import AutoTokenizer, AutoModelForCausalLM
 
 os.environ["TOKENIZERS_PARALLELISM"] = "false"
+HF_TOKEN = os.getenv("HF_TOKEN")
+
 
 class LLMManager:
     """Manages LLM model loading and text generation operations"""
@@ -15,8 +17,8 @@ class LLMManager:
         
     def load_models(self, model_name="meta-llama/Llama-3.2-1B-Instruct"):
         """Load the LLM model and tokenizer"""
-        self.tokenizer = AutoTokenizer.from_pretrained(model_name)
-        self.model = AutoModelForCausalLM.from_pretrained(model_name)
+        self.tokenizer = AutoTokenizer.from_pretrained(model_name, token=HF_TOKEN)
+        self.model = AutoModelForCausalLM.from_pretrained(model_name, token=HF_TOKEN)
         
         if self.tokenizer.pad_token is None:
             self.tokenizer.pad_token = self.tokenizer.eos_token