switched to hf_hub_download

backend.py

@@ -31,13 +31,13 @@ llm = Llama(
         )
 
 
-model_id = "google/gemma-2-2b-it"
+"""model_id = "google/gemma-2-2b-it"
 tokenizer = GemmaTokenizerFast.from_pretrained(model_id)
 model = AutoModelForCausalLM.from_pretrained(
     model_id,
     device_map="auto",
     torch_dtype= torch.float16 if torch.cuda.is_available() else torch.float32,
-)
+)"""
 # what models will be used by LlamaIndex:
 Settings.embed_model = InstructorEmbedding(model_name="hkunlp/instructor-base")
 #Settings.llm  = GemmaLLMInterface(model=model, tokenizer=tokenizer)