Update app.py

app.py

@@ -3,17 +3,15 @@ from transformers import AutoModelForCausalLM, AutoTokenizer
 import numpy as np
 import gradio as gr
 import spaces
-import accelerate
+model_name = "Writer/camel-5b-hf"
 
+tokenizer = AutoTokenizer.from_pretrained(model_name)
 model = AutoModelForCausalLM.from_pretrained(
-    "microsoft/Phi-3-mini-4k-instruct", 
-    device_map="cuda", 
-    torch_dtype="auto", 
-    trust_remote_code=True, 
+    model_name,
+    device_map="auto",
+    torch_dtype=torch.float16
 )
 
-tokenizer = AutoTokenizer.from_pretrained("microsoft/Phi-3-mini-4k-instruct")
-
 print("Loading finished.")
 
 print(f"Is CUDA available: {torch.cuda.is_available()}")