Update app.py

app.py

@@ -14,7 +14,7 @@ def infer(input_ids, max_length, temperature, top_k, top_p, num_return_sequences
 
     output_sequences = model.generate(
         input_ids=input_ids,
-        max_length=args.length + len(encoded_prompt[0]),
+        max_length=max_length,
         temperature=temperature,
         top_k=top_k,
         top_p=top_p,
@@ -55,7 +55,7 @@ for generated_sequence_idx, generated_sequence in enumerate(output_sequences):
     text = tokenizer.decode(generated_sequence, clean_up_tokenization_spaces=True)
 
     # Remove all text after the stop token
-    text = text[: text.find(args.stop_token) if args.stop_token else None]
+    #text = text[: text.find(args.stop_token) if args.stop_token else None]
 
     # Add the prompt at the beginning of the sequence. Remove the excess text that was used for pre-processing
     total_sequence = (