Update app.py

app.py

@@ -6,7 +6,7 @@ from threading import Thread
 from transformers import TextIteratorStreamer
 
 model_name = "numfa/numfa_v2-3b"
-model = AutoModelForCausalLM.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(model_name,torch_dtype=torch.float16, device_map="auto")
 tokenizer = AutoTokenizer.from_pretrained(model_name)
 if tokenizer.pad_token_id is None:
     tokenizer.pad_token_id = tokenizer.eos_token_id