Update app.py

app.py

@@ -22,7 +22,7 @@ class CFG():
     num_return_sequences = 5
     seed = 42
 
-
+print('ok')
 
 device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
 
@@ -35,13 +35,15 @@ def seed_everything(seed=42):
     torch.backends.cudnn.deterministic = True
 seed_everything(seed=CFG.seed) 
 
+print('ok')
+print(CFG.input_data)
 tokenizer = AutoTokenizer.from_pretrained(CFG.model_name_or_path, return_tensors='pt')
     
 if CFG.model == 't5':
     model = AutoModelForSeq2SeqLM.from_pretrained(CFG.model_name_or_path).to(device)
 elif CFG.model == 'deberta':
     model = EncoderDecoderModel.from_pretrained(CFG.model_name_or_path).to(device)
-    
+print('ok')
 input_compound = CFG.input_data
 min_length = min(input_compound.find('CATALYST') - input_compound.find(':') - 10, 0)
 inp = tokenizer(input_compound, return_tensors='pt').to(device)
@@ -60,4 +62,5 @@ if type(mol) == None:
 output += scores
 output = [input_compound] + output
 output_df = pd.DataFrame(np.array(output).reshape(1, -1), columns=['input'] + [f'{i}th' for i in range(CFG.num_beams)] + ['valid compound'] + [f'{i}th score' for i in range(CFG.num_beams)] + ['valid compound score'])
-print(output)
+print(output)
+print('ok')