Update app.py

app.py

@@ -52,7 +52,7 @@ from modeling_llama import LlamaForCausalLM
 # config = CLEXLlamaConfig.from_pretrained(
 #         model_id
 #     )
-model = LlamaForCausalLM.from_pretrained(model_id, torch_dtype=torch.float16, trust_remote_code=True, low_cpu_mem_usage=True, device_map="auto")
+model = LlamaForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, trust_remote_code=True, low_cpu_mem_usage=True, device_map="auto")
 tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True, use_fast=False)
 tokenizer.use_default_system_prompt = False