Update app.py

app.py

@@ -3,8 +3,8 @@ import spaces
 from transformers import AutoTokenizer, AutoModelForCausalLM
 import torch
 
-tokenizer = AutoTokenizer.from_pretrained("deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct", trust_remote_code=True)
-model = AutoModelForCausalLM.from_pretrained("deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct", trust_remote_code=True, torch_dtype=torch.bfloat16).cuda()    
+tokenizer = AutoTokenizer.from_pretrained("BirdL/DeepSeek-Coder-V2-Lite-Instruct-FlashAttnPatch", trust_remote_code=True)
+model = AutoModelForCausalLM.from_pretrained("BirdL/DeepSeek-Coder-V2-Lite-Instruct-FlashAttnPatch", trust_remote_code=True, torch_dtype=torch.bfloat16).cuda()    
 
 @spaces.GPU
 def respond(message):