Remove

examples/benchmarks.py

@@ -309,7 +309,7 @@ def _compute_pytorch(model_names, dictionary, average_over, device, torchscript)
         model = AutoModel.from_pretrained(model_name, config=config)
         tokenizer = AutoTokenizer.from_pretrained(model_name)
 
-        tokenized_sequence = tokenizer.encode(input_text)
+        tokenized_sequence = tokenizer.encode(input_text, add_special_tokens=False)
 
         max_input_size = tokenizer.max_model_input_sizes[model_name]
         batch_sizes = [1, 2, 4, 8]
@@ -353,7 +353,7 @@ def _compute_tensorflow(model_names, dictionary, average_over):
         model = TFAutoModel.from_pretrained(model_name, config=config)
         tokenizer = AutoTokenizer.from_pretrained(model_name)
 
-        tokenized_sequence = tokenizer.encode(input_text)
+        tokenized_sequence = tokenizer.encode(input_text, add_special_tokens=False)
 
         max_input_size = tokenizer.max_model_input_sizes[model_name]
         batch_sizes = [1, 2, 4, 8]

examples/distillation/scripts/binarized_data.py

@@ -68,7 +68,7 @@ def main():
     start = time.time()
     for text in data:
         text = f'{bos} {text.strip()} {sep}'
-        token_ids = tokenizer.encode(text)
+        token_ids = tokenizer.encode(text, add_special_tokens=False)
         rslt.append(token_ids)
 
         iter += 1

examples/run_generation.py

@@ -223,7 +223,7 @@ def main():
         if args.model_type in ["transfo-xl", "xlnet"]:
             # Models with memory likes to have a long prompt for short inputs.
             raw_text = (args.padding_text if args.padding_text else PADDING_TEXT) + raw_text
-        context_tokens = tokenizer.encode(raw_text)
+        context_tokens = tokenizer.encode(raw_text, add_special_tokens=False)
         out = sample_sequence(
             model=model,
             context=context_tokens,