Update app.py

app.py

@@ -1,5 +1,6 @@
 import gradio as gr
 import torch
+from unsloth import FastLanguageModel
 from transformers import TextStreamer
 from transformers import AutoModelForCausalLM, AutoTokenizer
 
@@ -13,6 +14,9 @@ max_seq_length = 512
 dtype = torch.bfloat16
 load_in_4bit = True
 
+#model = FastLanguageModel.from_pretrained(MODEL_NAME, max_seq_length=max_seq_length, dtype=dtype, load_in_4bit=load_in_4bit)
+#tokenizer = model.tokenizer
+
 model = AutoModelForCausalLM.from_pretrained(MODEL_NAME, torch_dtype=torch.bfloat16, device_map="auto")
 tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)