x54-729 commited on
Commit
edf2879
1 Parent(s): 1857a15

fix no white space when using stream_chat with fast tokenizer

Browse files
Files changed (1) hide show
  1. tokenization_internlm2_fast.py +8 -8
tokenization_internlm2_fast.py CHANGED
@@ -56,14 +56,14 @@ class InternLM2Converter(SpmConverter):
56
  return unk_id
57
 
58
  def decoder(self, replacement, add_prefix_space):
59
- return decoders.Sequence(
60
- [
61
- decoders.Replace("▁", " "),
62
- decoders.ByteFallback(),
63
- decoders.Fuse(),
64
- decoders.Strip(content=" ", left=1),
65
- ]
66
- )
67
 
68
  def tokenizer(self, proto):
69
  model_type = proto.trainer_spec.model_type
 
56
  return unk_id
57
 
58
  def decoder(self, replacement, add_prefix_space):
59
+ decoders_sequence = [
60
+ decoders.Replace("▁", " "),
61
+ decoders.ByteFallback(),
62
+ decoders.Fuse(),
63
+ ]
64
+ if self.proto.normalizer_spec.add_dummy_prefix:
65
+ decoders_sequence.append(decoders.Strip(content=" ", left=1))
66
+ return decoders.Sequence(decoders_sequence)
67
 
68
  def tokenizer(self, proto):
69
  model_type = proto.trainer_spec.model_type