Update app.py

app.py

@@ -1,8 +1,7 @@
 import spaces
 import gradio as gr
 import torch
-from transformers import AutoModelForCausalLM, AutoTokenizer
-from transformers import StoppingCriteria, StoppingCriteriaList, TextIteratorStreamer
+from transformers import AutoModelForCausalLM, AutoTokenizer, StoppingCriteria, StoppingCriteriaList, TextIteratorStreamer
 from threading import Thread
 
 class StopOnTokens(StoppingCriteria):
@@ -18,11 +17,11 @@ def predict(message, history):
     torch.set_default_device("cuda")
 
     tokenizer = AutoTokenizer.from_pretrained(
-        "macadeliccc/laser-dolphin-mixtral-2x7b-dpo",
+        "cognitivecomputations/dolphin-2.8-mistral-7b-v02",
         trust_remote_code=True
     )
     model = AutoModelForCausalLM.from_pretrained(
-        "macadeliccc/laser-dolphin-mixtral-2x7b-dpo",
+        "cognitivecomputations/dolphin-2.8-mistral-7b-v02",
         torch_dtype="auto",
         load_in_4bit=True,
         trust_remote_code=True