Update app.py

app.py

@@ -10,11 +10,11 @@ sys.path.append(
 from transformers import AutoModelForCausalLM,AutoTokenizer,LlamaTokenizer
 
 print("Creat tokenizer...")
-tokenizer = LlamaTokenizer.from_pretrained('IEITYuan/Yuan2-2B-hf', add_eos_token=False, add_bos_token=False, eos_token='<eod>')
+tokenizer = LlamaTokenizer.from_pretrained('IEITYuan/Yuan2-2B-Janus-hf', add_eos_token=False, add_bos_token=False, eos_token='<eod>')
 tokenizer.add_tokens(['<sep>', '<pad>', '<mask>', '<predict>', '<FIM_SUFFIX>', '<FIM_PREFIX>', '<FIM_MIDDLE>','<commit_before>','<commit_msg>','<commit_after>','<jupyter_start>','<jupyter_text>','<jupyter_code>','<jupyter_output>','<empty_output>'], special_tokens=True)
 
 print("Creat model...")
-model = AutoModelForCausalLM.from_pretrained('IEITYuan/Yuan2-2B-hf', device_map='auto', torch_dtype=torch.bfloat16, trust_remote_code=True)
+model = AutoModelForCausalLM.from_pretrained('IEITYuan/Yuan2-2B-Janus-hf', device_map='auto', torch_dtype=torch.bfloat16, trust_remote_code=True)
 # using CUDA for an optimal experience
 device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
 model = model.to(device)