Update app.py

app.py

@@ -4,9 +4,11 @@ from transformers import AutoTokenizer, AutoModelForCausalLM
 
 # Load your model from Hugging Face Transformers
 model_name = "deepseek-ai/DeepSeek-V2-Lite"
-tokenizer = AutoTokenizer.from_pretrained(model_name)
-model = AutoModelForCausalLM.from_pretrained(model_name)
 
+tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
+model = AutoModelForCausalLM.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.bfloat16).cpu()
+model.generation_config = GenerationConfig.from_pretrained(model_name)
+model.generation_config.pad_token_id = model.generation_config.eos_token_id
 # Define a function to use the model
 def math_inference(input_text):
     inputs = tokenizer(input_text, return_tensors="pt")