placed the model in float16

app.py

@@ -4,6 +4,7 @@ import spaces
 from transformers import GemmaTokenizer, AutoModelForCausalLM
 from transformers import AutoModelForCausalLM, AutoTokenizer, TextIteratorStreamer
 from threading import Thread
+import torch
 
 # Set an environment variable
 HF_TOKEN = os.environ.get("HF_TOKEN", None)
@@ -46,7 +47,7 @@ h1 {
 
 # Load the tokenizer and model
 tokenizer = AutoTokenizer.from_pretrained("meta-llama/Meta-Llama-3-8B-Instruct")
-model = AutoModelForCausalLM.from_pretrained("meta-llama/Meta-Llama-3-8B-Instruct", device_map="auto")  # to("cuda:0") 
+model = AutoModelForCausalLM.from_pretrained("meta-llama/Meta-Llama-3-8B-Instruct", device_map="auto", torch_dtpye=torch.float16)  # to("cuda:0") 
 terminators = [
     tokenizer.eos_token_id,
     tokenizer.convert_tokens_to_ids("<|eot_id|>")