hf-transformers-bot commited on
Commit
de5ece8
·
verified ·
1 Parent(s): 95d04bd

Add tiny processor fixture for testing

Browse files
chat_template.jinja ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ {%- for message in messages %}
3
+ {#-- Validate role is a stringified integer --#}
4
+ {%- if not message['role'] is string or not message['role'].isdigit() %}
5
+ {{- raise_exception("The role must be an integer or a stringified integer (e.g. '0') designating the speaker id") }}
6
+ {%- endif %}
7
+
8
+ {#-- Validate content is a list --#}
9
+ {%- set content = message['content'] %}
10
+ {%- if content is not iterable or content is string %}
11
+ {{- raise_exception("The content must be a list") }}
12
+ {%- endif %}
13
+
14
+ {#-- Collect content types --#}
15
+ {%- set content_types = content | map(attribute='type') | list %}
16
+ {%- set is_last = loop.last %}
17
+
18
+ {#-- Last message validation --#}
19
+ {%- if is_last %}
20
+ {%- if 'text' not in content_types %}
21
+ {{- raise_exception("The last message must include one item of type 'text'") }}
22
+ {%- elif (content_types | select('equalto', 'text') | list | length > 1) or (content_types | select('equalto', 'audio') | list | length > 1) %}
23
+ {{- raise_exception("At most two items are allowed in the last message: one 'text' and one 'audio'") }}
24
+ {%- endif %}
25
+
26
+ {#-- All other messages validation --#}
27
+ {%- else %}
28
+ {%- if content_types | select('equalto', 'text') | list | length != 1
29
+ or content_types | select('equalto', 'audio') | list | length != 1 %}
30
+ {{- raise_exception("Each message (except the last) must contain exactly one 'text' and one 'audio' item") }}
31
+ {%- elif content_types | reject('in', ['text', 'audio']) | list | length > 0 %}
32
+ {{- raise_exception("Only 'text' and 'audio' types are allowed in content") }}
33
+ {%- endif %}
34
+ {%- endif %}
35
+ {%- endfor %}
36
+
37
+ {%- for message in messages %}
38
+ {{- bos_token }}
39
+ {{- '[' + message['role'] + ']' }}
40
+ {{- message['content'][0]['text'] }}
41
+ {{- eos_token }}
42
+ {%- if message['content']|length > 1 %}
43
+ {{- '<|AUDIO|><|audio_eos|>' }}
44
+ {%- endif %}
45
+ {%- endfor %}
preprocessor_config.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "chunk_length_s": null,
3
+ "feature_extractor_type": "EncodecFeatureExtractor",
4
+ "feature_size": 1,
5
+ "overlap": null,
6
+ "padding_side": "right",
7
+ "padding_value": 0.0,
8
+ "processor_class": "CsmProcessor",
9
+ "return_attention_mask": true,
10
+ "sampling_rate": 24000
11
+ }
tokenizer.json ADDED
@@ -0,0 +1,4124 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "1.0",
3
+ "truncation": null,
4
+ "padding": null,
5
+ "added_tokens": [
6
+ {
7
+ "id": 500,
8
+ "content": "<|begin_of_text|>",
9
+ "single_word": false,
10
+ "lstrip": false,
11
+ "rstrip": false,
12
+ "normalized": false,
13
+ "special": true
14
+ },
15
+ {
16
+ "id": 501,
17
+ "content": "<|end_of_text|>",
18
+ "single_word": false,
19
+ "lstrip": false,
20
+ "rstrip": false,
21
+ "normalized": false,
22
+ "special": true
23
+ },
24
+ {
25
+ "id": 502,
26
+ "content": "<|AUDIO|>",
27
+ "single_word": false,
28
+ "lstrip": false,
29
+ "rstrip": false,
30
+ "normalized": false,
31
+ "special": true
32
+ },
33
+ {
34
+ "id": 503,
35
+ "content": "<|audio_eos|>",
36
+ "single_word": false,
37
+ "lstrip": false,
38
+ "rstrip": false,
39
+ "normalized": false,
40
+ "special": true
41
+ },
42
+ {
43
+ "id": 504,
44
+ "content": "<|finetune_right_pad_id|>",
45
+ "single_word": false,
46
+ "lstrip": false,
47
+ "rstrip": false,
48
+ "normalized": false,
49
+ "special": true
50
+ },
51
+ {
52
+ "id": 505,
53
+ "content": "<|reserved_special_token_2|>",
54
+ "single_word": false,
55
+ "lstrip": false,
56
+ "rstrip": false,
57
+ "normalized": false,
58
+ "special": true
59
+ },
60
+ {
61
+ "id": 506,
62
+ "content": "<|start_header_id|>",
63
+ "single_word": false,
64
+ "lstrip": false,
65
+ "rstrip": false,
66
+ "normalized": false,
67
+ "special": true
68
+ },
69
+ {
70
+ "id": 507,
71
+ "content": "<|end_header_id|>",
72
+ "single_word": false,
73
+ "lstrip": false,
74
+ "rstrip": false,
75
+ "normalized": false,
76
+ "special": true
77
+ },
78
+ {
79
+ "id": 508,
80
+ "content": "<|eom_id|>",
81
+ "single_word": false,
82
+ "lstrip": false,
83
+ "rstrip": false,
84
+ "normalized": false,
85
+ "special": true
86
+ },
87
+ {
88
+ "id": 509,
89
+ "content": "<|eot_id|>",
90
+ "single_word": false,
91
+ "lstrip": false,
92
+ "rstrip": false,
93
+ "normalized": false,
94
+ "special": true
95
+ },
96
+ {
97
+ "id": 510,
98
+ "content": "<|python_tag|>",
99
+ "single_word": false,
100
+ "lstrip": false,
101
+ "rstrip": false,
102
+ "normalized": false,
103
+ "special": true
104
+ },
105
+ {
106
+ "id": 511,
107
+ "content": "<|reserved_special_token_3|>",
108
+ "single_word": false,
109
+ "lstrip": false,
110
+ "rstrip": false,
111
+ "normalized": false,
112
+ "special": true
113
+ },
114
+ {
115
+ "id": 512,
116
+ "content": "<|reserved_special_token_4|>",
117
+ "single_word": false,
118
+ "lstrip": false,
119
+ "rstrip": false,
120
+ "normalized": false,
121
+ "special": true
122
+ },
123
+ {
124
+ "id": 513,
125
+ "content": "<|reserved_special_token_5|>",
126
+ "single_word": false,
127
+ "lstrip": false,
128
+ "rstrip": false,
129
+ "normalized": false,
130
+ "special": true
131
+ },
132
+ {
133
+ "id": 514,
134
+ "content": "<|reserved_special_token_6|>",
135
+ "single_word": false,
136
+ "lstrip": false,
137
+ "rstrip": false,
138
+ "normalized": false,
139
+ "special": true
140
+ },
141
+ {
142
+ "id": 515,
143
+ "content": "<|reserved_special_token_7|>",
144
+ "single_word": false,
145
+ "lstrip": false,
146
+ "rstrip": false,
147
+ "normalized": false,
148
+ "special": true
149
+ },
150
+ {
151
+ "id": 516,
152
+ "content": "<|reserved_special_token_8|>",
153
+ "single_word": false,
154
+ "lstrip": false,
155
+ "rstrip": false,
156
+ "normalized": false,
157
+ "special": true
158
+ },
159
+ {
160
+ "id": 517,
161
+ "content": "<|reserved_special_token_9|>",
162
+ "single_word": false,
163
+ "lstrip": false,
164
+ "rstrip": false,
165
+ "normalized": false,
166
+ "special": true
167
+ },
168
+ {
169
+ "id": 518,
170
+ "content": "<|reserved_special_token_10|>",
171
+ "single_word": false,
172
+ "lstrip": false,
173
+ "rstrip": false,
174
+ "normalized": false,
175
+ "special": true
176
+ },
177
+ {
178
+ "id": 519,
179
+ "content": "<|reserved_special_token_11|>",
180
+ "single_word": false,
181
+ "lstrip": false,
182
+ "rstrip": false,
183
+ "normalized": false,
184
+ "special": true
185
+ },
186
+ {
187
+ "id": 520,
188
+ "content": "<|reserved_special_token_12|>",
189
+ "single_word": false,
190
+ "lstrip": false,
191
+ "rstrip": false,
192
+ "normalized": false,
193
+ "special": true
194
+ },
195
+ {
196
+ "id": 521,
197
+ "content": "<|reserved_special_token_13|>",
198
+ "single_word": false,
199
+ "lstrip": false,
200
+ "rstrip": false,
201
+ "normalized": false,
202
+ "special": true
203
+ },
204
+ {
205
+ "id": 522,
206
+ "content": "<|reserved_special_token_14|>",
207
+ "single_word": false,
208
+ "lstrip": false,
209
+ "rstrip": false,
210
+ "normalized": false,
211
+ "special": true
212
+ },
213
+ {
214
+ "id": 523,
215
+ "content": "<|reserved_special_token_15|>",
216
+ "single_word": false,
217
+ "lstrip": false,
218
+ "rstrip": false,
219
+ "normalized": false,
220
+ "special": true
221
+ },
222
+ {
223
+ "id": 524,
224
+ "content": "<|reserved_special_token_16|>",
225
+ "single_word": false,
226
+ "lstrip": false,
227
+ "rstrip": false,
228
+ "normalized": false,
229
+ "special": true
230
+ },
231
+ {
232
+ "id": 525,
233
+ "content": "<|reserved_special_token_17|>",
234
+ "single_word": false,
235
+ "lstrip": false,
236
+ "rstrip": false,
237
+ "normalized": false,
238
+ "special": true
239
+ },
240
+ {
241
+ "id": 526,
242
+ "content": "<|reserved_special_token_18|>",
243
+ "single_word": false,
244
+ "lstrip": false,
245
+ "rstrip": false,
246
+ "normalized": false,
247
+ "special": true
248
+ },
249
+ {
250
+ "id": 527,
251
+ "content": "<|reserved_special_token_19|>",
252
+ "single_word": false,
253
+ "lstrip": false,
254
+ "rstrip": false,
255
+ "normalized": false,
256
+ "special": true
257
+ },
258
+ {
259
+ "id": 528,
260
+ "content": "<|reserved_special_token_20|>",
261
+ "single_word": false,
262
+ "lstrip": false,
263
+ "rstrip": false,
264
+ "normalized": false,
265
+ "special": true
266
+ },
267
+ {
268
+ "id": 529,
269
+ "content": "<|reserved_special_token_21|>",
270
+ "single_word": false,
271
+ "lstrip": false,
272
+ "rstrip": false,
273
+ "normalized": false,
274
+ "special": true
275
+ },
276
+ {
277
+ "id": 530,
278
+ "content": "<|reserved_special_token_22|>",
279
+ "single_word": false,
280
+ "lstrip": false,
281
+ "rstrip": false,
282
+ "normalized": false,
283
+ "special": true
284
+ },
285
+ {
286
+ "id": 531,
287
+ "content": "<|reserved_special_token_23|>",
288
+ "single_word": false,
289
+ "lstrip": false,
290
+ "rstrip": false,
291
+ "normalized": false,
292
+ "special": true
293
+ },
294
+ {
295
+ "id": 532,
296
+ "content": "<|reserved_special_token_24|>",
297
+ "single_word": false,
298
+ "lstrip": false,
299
+ "rstrip": false,
300
+ "normalized": false,
301
+ "special": true
302
+ },
303
+ {
304
+ "id": 533,
305
+ "content": "<|reserved_special_token_25|>",
306
+ "single_word": false,
307
+ "lstrip": false,
308
+ "rstrip": false,
309
+ "normalized": false,
310
+ "special": true
311
+ },
312
+ {
313
+ "id": 534,
314
+ "content": "<|reserved_special_token_26|>",
315
+ "single_word": false,
316
+ "lstrip": false,
317
+ "rstrip": false,
318
+ "normalized": false,
319
+ "special": true
320
+ },
321
+ {
322
+ "id": 535,
323
+ "content": "<|reserved_special_token_27|>",
324
+ "single_word": false,
325
+ "lstrip": false,
326
+ "rstrip": false,
327
+ "normalized": false,
328
+ "special": true
329
+ },
330
+ {
331
+ "id": 536,
332
+ "content": "<|reserved_special_token_28|>",
333
+ "single_word": false,
334
+ "lstrip": false,
335
+ "rstrip": false,
336
+ "normalized": false,
337
+ "special": true
338
+ },
339
+ {
340
+ "id": 537,
341
+ "content": "<|reserved_special_token_29|>",
342
+ "single_word": false,
343
+ "lstrip": false,
344
+ "rstrip": false,
345
+ "normalized": false,
346
+ "special": true
347
+ },
348
+ {
349
+ "id": 538,
350
+ "content": "<|reserved_special_token_30|>",
351
+ "single_word": false,
352
+ "lstrip": false,
353
+ "rstrip": false,
354
+ "normalized": false,
355
+ "special": true
356
+ },
357
+ {
358
+ "id": 539,
359
+ "content": "<|reserved_special_token_31|>",
360
+ "single_word": false,
361
+ "lstrip": false,
362
+ "rstrip": false,
363
+ "normalized": false,
364
+ "special": true
365
+ },
366
+ {
367
+ "id": 540,
368
+ "content": "<|reserved_special_token_32|>",
369
+ "single_word": false,
370
+ "lstrip": false,
371
+ "rstrip": false,
372
+ "normalized": false,
373
+ "special": true
374
+ },
375
+ {
376
+ "id": 541,
377
+ "content": "<|reserved_special_token_33|>",
378
+ "single_word": false,
379
+ "lstrip": false,
380
+ "rstrip": false,
381
+ "normalized": false,
382
+ "special": true
383
+ },
384
+ {
385
+ "id": 542,
386
+ "content": "<|reserved_special_token_34|>",
387
+ "single_word": false,
388
+ "lstrip": false,
389
+ "rstrip": false,
390
+ "normalized": false,
391
+ "special": true
392
+ },
393
+ {
394
+ "id": 543,
395
+ "content": "<|reserved_special_token_35|>",
396
+ "single_word": false,
397
+ "lstrip": false,
398
+ "rstrip": false,
399
+ "normalized": false,
400
+ "special": true
401
+ },
402
+ {
403
+ "id": 544,
404
+ "content": "<|reserved_special_token_36|>",
405
+ "single_word": false,
406
+ "lstrip": false,
407
+ "rstrip": false,
408
+ "normalized": false,
409
+ "special": true
410
+ },
411
+ {
412
+ "id": 545,
413
+ "content": "<|reserved_special_token_37|>",
414
+ "single_word": false,
415
+ "lstrip": false,
416
+ "rstrip": false,
417
+ "normalized": false,
418
+ "special": true
419
+ },
420
+ {
421
+ "id": 546,
422
+ "content": "<|reserved_special_token_38|>",
423
+ "single_word": false,
424
+ "lstrip": false,
425
+ "rstrip": false,
426
+ "normalized": false,
427
+ "special": true
428
+ },
429
+ {
430
+ "id": 547,
431
+ "content": "<|reserved_special_token_39|>",
432
+ "single_word": false,
433
+ "lstrip": false,
434
+ "rstrip": false,
435
+ "normalized": false,
436
+ "special": true
437
+ },
438
+ {
439
+ "id": 548,
440
+ "content": "<|reserved_special_token_40|>",
441
+ "single_word": false,
442
+ "lstrip": false,
443
+ "rstrip": false,
444
+ "normalized": false,
445
+ "special": true
446
+ },
447
+ {
448
+ "id": 549,
449
+ "content": "<|reserved_special_token_41|>",
450
+ "single_word": false,
451
+ "lstrip": false,
452
+ "rstrip": false,
453
+ "normalized": false,
454
+ "special": true
455
+ },
456
+ {
457
+ "id": 550,
458
+ "content": "<|reserved_special_token_42|>",
459
+ "single_word": false,
460
+ "lstrip": false,
461
+ "rstrip": false,
462
+ "normalized": false,
463
+ "special": true
464
+ },
465
+ {
466
+ "id": 551,
467
+ "content": "<|reserved_special_token_43|>",
468
+ "single_word": false,
469
+ "lstrip": false,
470
+ "rstrip": false,
471
+ "normalized": false,
472
+ "special": true
473
+ },
474
+ {
475
+ "id": 552,
476
+ "content": "<|reserved_special_token_44|>",
477
+ "single_word": false,
478
+ "lstrip": false,
479
+ "rstrip": false,
480
+ "normalized": false,
481
+ "special": true
482
+ },
483
+ {
484
+ "id": 553,
485
+ "content": "<|reserved_special_token_45|>",
486
+ "single_word": false,
487
+ "lstrip": false,
488
+ "rstrip": false,
489
+ "normalized": false,
490
+ "special": true
491
+ },
492
+ {
493
+ "id": 554,
494
+ "content": "<|reserved_special_token_46|>",
495
+ "single_word": false,
496
+ "lstrip": false,
497
+ "rstrip": false,
498
+ "normalized": false,
499
+ "special": true
500
+ },
501
+ {
502
+ "id": 555,
503
+ "content": "<|reserved_special_token_47|>",
504
+ "single_word": false,
505
+ "lstrip": false,
506
+ "rstrip": false,
507
+ "normalized": false,
508
+ "special": true
509
+ },
510
+ {
511
+ "id": 556,
512
+ "content": "<|reserved_special_token_48|>",
513
+ "single_word": false,
514
+ "lstrip": false,
515
+ "rstrip": false,
516
+ "normalized": false,
517
+ "special": true
518
+ },
519
+ {
520
+ "id": 557,
521
+ "content": "<|reserved_special_token_49|>",
522
+ "single_word": false,
523
+ "lstrip": false,
524
+ "rstrip": false,
525
+ "normalized": false,
526
+ "special": true
527
+ },
528
+ {
529
+ "id": 558,
530
+ "content": "<|reserved_special_token_50|>",
531
+ "single_word": false,
532
+ "lstrip": false,
533
+ "rstrip": false,
534
+ "normalized": false,
535
+ "special": true
536
+ },
537
+ {
538
+ "id": 559,
539
+ "content": "<|reserved_special_token_51|>",
540
+ "single_word": false,
541
+ "lstrip": false,
542
+ "rstrip": false,
543
+ "normalized": false,
544
+ "special": true
545
+ },
546
+ {
547
+ "id": 560,
548
+ "content": "<|reserved_special_token_52|>",
549
+ "single_word": false,
550
+ "lstrip": false,
551
+ "rstrip": false,
552
+ "normalized": false,
553
+ "special": true
554
+ },
555
+ {
556
+ "id": 561,
557
+ "content": "<|reserved_special_token_53|>",
558
+ "single_word": false,
559
+ "lstrip": false,
560
+ "rstrip": false,
561
+ "normalized": false,
562
+ "special": true
563
+ },
564
+ {
565
+ "id": 562,
566
+ "content": "<|reserved_special_token_54|>",
567
+ "single_word": false,
568
+ "lstrip": false,
569
+ "rstrip": false,
570
+ "normalized": false,
571
+ "special": true
572
+ },
573
+ {
574
+ "id": 563,
575
+ "content": "<|reserved_special_token_55|>",
576
+ "single_word": false,
577
+ "lstrip": false,
578
+ "rstrip": false,
579
+ "normalized": false,
580
+ "special": true
581
+ },
582
+ {
583
+ "id": 564,
584
+ "content": "<|reserved_special_token_56|>",
585
+ "single_word": false,
586
+ "lstrip": false,
587
+ "rstrip": false,
588
+ "normalized": false,
589
+ "special": true
590
+ },
591
+ {
592
+ "id": 565,
593
+ "content": "<|reserved_special_token_57|>",
594
+ "single_word": false,
595
+ "lstrip": false,
596
+ "rstrip": false,
597
+ "normalized": false,
598
+ "special": true
599
+ },
600
+ {
601
+ "id": 566,
602
+ "content": "<|reserved_special_token_58|>",
603
+ "single_word": false,
604
+ "lstrip": false,
605
+ "rstrip": false,
606
+ "normalized": false,
607
+ "special": true
608
+ },
609
+ {
610
+ "id": 567,
611
+ "content": "<|reserved_special_token_59|>",
612
+ "single_word": false,
613
+ "lstrip": false,
614
+ "rstrip": false,
615
+ "normalized": false,
616
+ "special": true
617
+ },
618
+ {
619
+ "id": 568,
620
+ "content": "<|reserved_special_token_60|>",
621
+ "single_word": false,
622
+ "lstrip": false,
623
+ "rstrip": false,
624
+ "normalized": false,
625
+ "special": true
626
+ },
627
+ {
628
+ "id": 569,
629
+ "content": "<|reserved_special_token_61|>",
630
+ "single_word": false,
631
+ "lstrip": false,
632
+ "rstrip": false,
633
+ "normalized": false,
634
+ "special": true
635
+ },
636
+ {
637
+ "id": 570,
638
+ "content": "<|reserved_special_token_62|>",
639
+ "single_word": false,
640
+ "lstrip": false,
641
+ "rstrip": false,
642
+ "normalized": false,
643
+ "special": true
644
+ },
645
+ {
646
+ "id": 571,
647
+ "content": "<|reserved_special_token_63|>",
648
+ "single_word": false,
649
+ "lstrip": false,
650
+ "rstrip": false,
651
+ "normalized": false,
652
+ "special": true
653
+ },
654
+ {
655
+ "id": 572,
656
+ "content": "<|reserved_special_token_64|>",
657
+ "single_word": false,
658
+ "lstrip": false,
659
+ "rstrip": false,
660
+ "normalized": false,
661
+ "special": true
662
+ },
663
+ {
664
+ "id": 573,
665
+ "content": "<|reserved_special_token_65|>",
666
+ "single_word": false,
667
+ "lstrip": false,
668
+ "rstrip": false,
669
+ "normalized": false,
670
+ "special": true
671
+ },
672
+ {
673
+ "id": 574,
674
+ "content": "<|reserved_special_token_66|>",
675
+ "single_word": false,
676
+ "lstrip": false,
677
+ "rstrip": false,
678
+ "normalized": false,
679
+ "special": true
680
+ },
681
+ {
682
+ "id": 575,
683
+ "content": "<|reserved_special_token_67|>",
684
+ "single_word": false,
685
+ "lstrip": false,
686
+ "rstrip": false,
687
+ "normalized": false,
688
+ "special": true
689
+ },
690
+ {
691
+ "id": 576,
692
+ "content": "<|reserved_special_token_68|>",
693
+ "single_word": false,
694
+ "lstrip": false,
695
+ "rstrip": false,
696
+ "normalized": false,
697
+ "special": true
698
+ },
699
+ {
700
+ "id": 577,
701
+ "content": "<|reserved_special_token_69|>",
702
+ "single_word": false,
703
+ "lstrip": false,
704
+ "rstrip": false,
705
+ "normalized": false,
706
+ "special": true
707
+ },
708
+ {
709
+ "id": 578,
710
+ "content": "<|reserved_special_token_70|>",
711
+ "single_word": false,
712
+ "lstrip": false,
713
+ "rstrip": false,
714
+ "normalized": false,
715
+ "special": true
716
+ },
717
+ {
718
+ "id": 579,
719
+ "content": "<|reserved_special_token_71|>",
720
+ "single_word": false,
721
+ "lstrip": false,
722
+ "rstrip": false,
723
+ "normalized": false,
724
+ "special": true
725
+ },
726
+ {
727
+ "id": 580,
728
+ "content": "<|reserved_special_token_72|>",
729
+ "single_word": false,
730
+ "lstrip": false,
731
+ "rstrip": false,
732
+ "normalized": false,
733
+ "special": true
734
+ },
735
+ {
736
+ "id": 581,
737
+ "content": "<|reserved_special_token_73|>",
738
+ "single_word": false,
739
+ "lstrip": false,
740
+ "rstrip": false,
741
+ "normalized": false,
742
+ "special": true
743
+ },
744
+ {
745
+ "id": 582,
746
+ "content": "<|reserved_special_token_74|>",
747
+ "single_word": false,
748
+ "lstrip": false,
749
+ "rstrip": false,
750
+ "normalized": false,
751
+ "special": true
752
+ },
753
+ {
754
+ "id": 583,
755
+ "content": "<|reserved_special_token_75|>",
756
+ "single_word": false,
757
+ "lstrip": false,
758
+ "rstrip": false,
759
+ "normalized": false,
760
+ "special": true
761
+ },
762
+ {
763
+ "id": 584,
764
+ "content": "<|reserved_special_token_76|>",
765
+ "single_word": false,
766
+ "lstrip": false,
767
+ "rstrip": false,
768
+ "normalized": false,
769
+ "special": true
770
+ },
771
+ {
772
+ "id": 585,
773
+ "content": "<|reserved_special_token_77|>",
774
+ "single_word": false,
775
+ "lstrip": false,
776
+ "rstrip": false,
777
+ "normalized": false,
778
+ "special": true
779
+ },
780
+ {
781
+ "id": 586,
782
+ "content": "<|reserved_special_token_78|>",
783
+ "single_word": false,
784
+ "lstrip": false,
785
+ "rstrip": false,
786
+ "normalized": false,
787
+ "special": true
788
+ },
789
+ {
790
+ "id": 587,
791
+ "content": "<|reserved_special_token_79|>",
792
+ "single_word": false,
793
+ "lstrip": false,
794
+ "rstrip": false,
795
+ "normalized": false,
796
+ "special": true
797
+ },
798
+ {
799
+ "id": 588,
800
+ "content": "<|reserved_special_token_80|>",
801
+ "single_word": false,
802
+ "lstrip": false,
803
+ "rstrip": false,
804
+ "normalized": false,
805
+ "special": true
806
+ },
807
+ {
808
+ "id": 589,
809
+ "content": "<|reserved_special_token_81|>",
810
+ "single_word": false,
811
+ "lstrip": false,
812
+ "rstrip": false,
813
+ "normalized": false,
814
+ "special": true
815
+ },
816
+ {
817
+ "id": 590,
818
+ "content": "<|reserved_special_token_82|>",
819
+ "single_word": false,
820
+ "lstrip": false,
821
+ "rstrip": false,
822
+ "normalized": false,
823
+ "special": true
824
+ },
825
+ {
826
+ "id": 591,
827
+ "content": "<|reserved_special_token_83|>",
828
+ "single_word": false,
829
+ "lstrip": false,
830
+ "rstrip": false,
831
+ "normalized": false,
832
+ "special": true
833
+ },
834
+ {
835
+ "id": 592,
836
+ "content": "<|reserved_special_token_84|>",
837
+ "single_word": false,
838
+ "lstrip": false,
839
+ "rstrip": false,
840
+ "normalized": false,
841
+ "special": true
842
+ },
843
+ {
844
+ "id": 593,
845
+ "content": "<|reserved_special_token_85|>",
846
+ "single_word": false,
847
+ "lstrip": false,
848
+ "rstrip": false,
849
+ "normalized": false,
850
+ "special": true
851
+ },
852
+ {
853
+ "id": 594,
854
+ "content": "<|reserved_special_token_86|>",
855
+ "single_word": false,
856
+ "lstrip": false,
857
+ "rstrip": false,
858
+ "normalized": false,
859
+ "special": true
860
+ },
861
+ {
862
+ "id": 595,
863
+ "content": "<|reserved_special_token_87|>",
864
+ "single_word": false,
865
+ "lstrip": false,
866
+ "rstrip": false,
867
+ "normalized": false,
868
+ "special": true
869
+ },
870
+ {
871
+ "id": 596,
872
+ "content": "<|reserved_special_token_88|>",
873
+ "single_word": false,
874
+ "lstrip": false,
875
+ "rstrip": false,
876
+ "normalized": false,
877
+ "special": true
878
+ },
879
+ {
880
+ "id": 597,
881
+ "content": "<|reserved_special_token_89|>",
882
+ "single_word": false,
883
+ "lstrip": false,
884
+ "rstrip": false,
885
+ "normalized": false,
886
+ "special": true
887
+ },
888
+ {
889
+ "id": 598,
890
+ "content": "<|reserved_special_token_90|>",
891
+ "single_word": false,
892
+ "lstrip": false,
893
+ "rstrip": false,
894
+ "normalized": false,
895
+ "special": true
896
+ },
897
+ {
898
+ "id": 599,
899
+ "content": "<|reserved_special_token_91|>",
900
+ "single_word": false,
901
+ "lstrip": false,
902
+ "rstrip": false,
903
+ "normalized": false,
904
+ "special": true
905
+ },
906
+ {
907
+ "id": 600,
908
+ "content": "<|reserved_special_token_92|>",
909
+ "single_word": false,
910
+ "lstrip": false,
911
+ "rstrip": false,
912
+ "normalized": false,
913
+ "special": true
914
+ },
915
+ {
916
+ "id": 601,
917
+ "content": "<|reserved_special_token_93|>",
918
+ "single_word": false,
919
+ "lstrip": false,
920
+ "rstrip": false,
921
+ "normalized": false,
922
+ "special": true
923
+ },
924
+ {
925
+ "id": 602,
926
+ "content": "<|reserved_special_token_94|>",
927
+ "single_word": false,
928
+ "lstrip": false,
929
+ "rstrip": false,
930
+ "normalized": false,
931
+ "special": true
932
+ },
933
+ {
934
+ "id": 603,
935
+ "content": "<|reserved_special_token_95|>",
936
+ "single_word": false,
937
+ "lstrip": false,
938
+ "rstrip": false,
939
+ "normalized": false,
940
+ "special": true
941
+ },
942
+ {
943
+ "id": 604,
944
+ "content": "<|reserved_special_token_96|>",
945
+ "single_word": false,
946
+ "lstrip": false,
947
+ "rstrip": false,
948
+ "normalized": false,
949
+ "special": true
950
+ },
951
+ {
952
+ "id": 605,
953
+ "content": "<|reserved_special_token_97|>",
954
+ "single_word": false,
955
+ "lstrip": false,
956
+ "rstrip": false,
957
+ "normalized": false,
958
+ "special": true
959
+ },
960
+ {
961
+ "id": 606,
962
+ "content": "<|reserved_special_token_98|>",
963
+ "single_word": false,
964
+ "lstrip": false,
965
+ "rstrip": false,
966
+ "normalized": false,
967
+ "special": true
968
+ },
969
+ {
970
+ "id": 607,
971
+ "content": "<|reserved_special_token_99|>",
972
+ "single_word": false,
973
+ "lstrip": false,
974
+ "rstrip": false,
975
+ "normalized": false,
976
+ "special": true
977
+ },
978
+ {
979
+ "id": 608,
980
+ "content": "<|reserved_special_token_100|>",
981
+ "single_word": false,
982
+ "lstrip": false,
983
+ "rstrip": false,
984
+ "normalized": false,
985
+ "special": true
986
+ },
987
+ {
988
+ "id": 609,
989
+ "content": "<|reserved_special_token_101|>",
990
+ "single_word": false,
991
+ "lstrip": false,
992
+ "rstrip": false,
993
+ "normalized": false,
994
+ "special": true
995
+ },
996
+ {
997
+ "id": 610,
998
+ "content": "<|reserved_special_token_102|>",
999
+ "single_word": false,
1000
+ "lstrip": false,
1001
+ "rstrip": false,
1002
+ "normalized": false,
1003
+ "special": true
1004
+ },
1005
+ {
1006
+ "id": 611,
1007
+ "content": "<|reserved_special_token_103|>",
1008
+ "single_word": false,
1009
+ "lstrip": false,
1010
+ "rstrip": false,
1011
+ "normalized": false,
1012
+ "special": true
1013
+ },
1014
+ {
1015
+ "id": 612,
1016
+ "content": "<|reserved_special_token_104|>",
1017
+ "single_word": false,
1018
+ "lstrip": false,
1019
+ "rstrip": false,
1020
+ "normalized": false,
1021
+ "special": true
1022
+ },
1023
+ {
1024
+ "id": 613,
1025
+ "content": "<|reserved_special_token_105|>",
1026
+ "single_word": false,
1027
+ "lstrip": false,
1028
+ "rstrip": false,
1029
+ "normalized": false,
1030
+ "special": true
1031
+ },
1032
+ {
1033
+ "id": 614,
1034
+ "content": "<|reserved_special_token_106|>",
1035
+ "single_word": false,
1036
+ "lstrip": false,
1037
+ "rstrip": false,
1038
+ "normalized": false,
1039
+ "special": true
1040
+ },
1041
+ {
1042
+ "id": 615,
1043
+ "content": "<|reserved_special_token_107|>",
1044
+ "single_word": false,
1045
+ "lstrip": false,
1046
+ "rstrip": false,
1047
+ "normalized": false,
1048
+ "special": true
1049
+ },
1050
+ {
1051
+ "id": 616,
1052
+ "content": "<|reserved_special_token_108|>",
1053
+ "single_word": false,
1054
+ "lstrip": false,
1055
+ "rstrip": false,
1056
+ "normalized": false,
1057
+ "special": true
1058
+ },
1059
+ {
1060
+ "id": 617,
1061
+ "content": "<|reserved_special_token_109|>",
1062
+ "single_word": false,
1063
+ "lstrip": false,
1064
+ "rstrip": false,
1065
+ "normalized": false,
1066
+ "special": true
1067
+ },
1068
+ {
1069
+ "id": 618,
1070
+ "content": "<|reserved_special_token_110|>",
1071
+ "single_word": false,
1072
+ "lstrip": false,
1073
+ "rstrip": false,
1074
+ "normalized": false,
1075
+ "special": true
1076
+ },
1077
+ {
1078
+ "id": 619,
1079
+ "content": "<|reserved_special_token_111|>",
1080
+ "single_word": false,
1081
+ "lstrip": false,
1082
+ "rstrip": false,
1083
+ "normalized": false,
1084
+ "special": true
1085
+ },
1086
+ {
1087
+ "id": 620,
1088
+ "content": "<|reserved_special_token_112|>",
1089
+ "single_word": false,
1090
+ "lstrip": false,
1091
+ "rstrip": false,
1092
+ "normalized": false,
1093
+ "special": true
1094
+ },
1095
+ {
1096
+ "id": 621,
1097
+ "content": "<|reserved_special_token_113|>",
1098
+ "single_word": false,
1099
+ "lstrip": false,
1100
+ "rstrip": false,
1101
+ "normalized": false,
1102
+ "special": true
1103
+ },
1104
+ {
1105
+ "id": 622,
1106
+ "content": "<|reserved_special_token_114|>",
1107
+ "single_word": false,
1108
+ "lstrip": false,
1109
+ "rstrip": false,
1110
+ "normalized": false,
1111
+ "special": true
1112
+ },
1113
+ {
1114
+ "id": 623,
1115
+ "content": "<|reserved_special_token_115|>",
1116
+ "single_word": false,
1117
+ "lstrip": false,
1118
+ "rstrip": false,
1119
+ "normalized": false,
1120
+ "special": true
1121
+ },
1122
+ {
1123
+ "id": 624,
1124
+ "content": "<|reserved_special_token_116|>",
1125
+ "single_word": false,
1126
+ "lstrip": false,
1127
+ "rstrip": false,
1128
+ "normalized": false,
1129
+ "special": true
1130
+ },
1131
+ {
1132
+ "id": 625,
1133
+ "content": "<|reserved_special_token_117|>",
1134
+ "single_word": false,
1135
+ "lstrip": false,
1136
+ "rstrip": false,
1137
+ "normalized": false,
1138
+ "special": true
1139
+ },
1140
+ {
1141
+ "id": 626,
1142
+ "content": "<|reserved_special_token_118|>",
1143
+ "single_word": false,
1144
+ "lstrip": false,
1145
+ "rstrip": false,
1146
+ "normalized": false,
1147
+ "special": true
1148
+ },
1149
+ {
1150
+ "id": 627,
1151
+ "content": "<|reserved_special_token_119|>",
1152
+ "single_word": false,
1153
+ "lstrip": false,
1154
+ "rstrip": false,
1155
+ "normalized": false,
1156
+ "special": true
1157
+ },
1158
+ {
1159
+ "id": 628,
1160
+ "content": "<|reserved_special_token_120|>",
1161
+ "single_word": false,
1162
+ "lstrip": false,
1163
+ "rstrip": false,
1164
+ "normalized": false,
1165
+ "special": true
1166
+ },
1167
+ {
1168
+ "id": 629,
1169
+ "content": "<|reserved_special_token_121|>",
1170
+ "single_word": false,
1171
+ "lstrip": false,
1172
+ "rstrip": false,
1173
+ "normalized": false,
1174
+ "special": true
1175
+ },
1176
+ {
1177
+ "id": 630,
1178
+ "content": "<|reserved_special_token_122|>",
1179
+ "single_word": false,
1180
+ "lstrip": false,
1181
+ "rstrip": false,
1182
+ "normalized": false,
1183
+ "special": true
1184
+ },
1185
+ {
1186
+ "id": 631,
1187
+ "content": "<|reserved_special_token_123|>",
1188
+ "single_word": false,
1189
+ "lstrip": false,
1190
+ "rstrip": false,
1191
+ "normalized": false,
1192
+ "special": true
1193
+ },
1194
+ {
1195
+ "id": 632,
1196
+ "content": "<|reserved_special_token_124|>",
1197
+ "single_word": false,
1198
+ "lstrip": false,
1199
+ "rstrip": false,
1200
+ "normalized": false,
1201
+ "special": true
1202
+ },
1203
+ {
1204
+ "id": 633,
1205
+ "content": "<|reserved_special_token_125|>",
1206
+ "single_word": false,
1207
+ "lstrip": false,
1208
+ "rstrip": false,
1209
+ "normalized": false,
1210
+ "special": true
1211
+ },
1212
+ {
1213
+ "id": 634,
1214
+ "content": "<|reserved_special_token_126|>",
1215
+ "single_word": false,
1216
+ "lstrip": false,
1217
+ "rstrip": false,
1218
+ "normalized": false,
1219
+ "special": true
1220
+ },
1221
+ {
1222
+ "id": 635,
1223
+ "content": "<|reserved_special_token_127|>",
1224
+ "single_word": false,
1225
+ "lstrip": false,
1226
+ "rstrip": false,
1227
+ "normalized": false,
1228
+ "special": true
1229
+ },
1230
+ {
1231
+ "id": 636,
1232
+ "content": "<|reserved_special_token_128|>",
1233
+ "single_word": false,
1234
+ "lstrip": false,
1235
+ "rstrip": false,
1236
+ "normalized": false,
1237
+ "special": true
1238
+ },
1239
+ {
1240
+ "id": 637,
1241
+ "content": "<|reserved_special_token_129|>",
1242
+ "single_word": false,
1243
+ "lstrip": false,
1244
+ "rstrip": false,
1245
+ "normalized": false,
1246
+ "special": true
1247
+ },
1248
+ {
1249
+ "id": 638,
1250
+ "content": "<|reserved_special_token_130|>",
1251
+ "single_word": false,
1252
+ "lstrip": false,
1253
+ "rstrip": false,
1254
+ "normalized": false,
1255
+ "special": true
1256
+ },
1257
+ {
1258
+ "id": 639,
1259
+ "content": "<|reserved_special_token_131|>",
1260
+ "single_word": false,
1261
+ "lstrip": false,
1262
+ "rstrip": false,
1263
+ "normalized": false,
1264
+ "special": true
1265
+ },
1266
+ {
1267
+ "id": 640,
1268
+ "content": "<|reserved_special_token_132|>",
1269
+ "single_word": false,
1270
+ "lstrip": false,
1271
+ "rstrip": false,
1272
+ "normalized": false,
1273
+ "special": true
1274
+ },
1275
+ {
1276
+ "id": 641,
1277
+ "content": "<|reserved_special_token_133|>",
1278
+ "single_word": false,
1279
+ "lstrip": false,
1280
+ "rstrip": false,
1281
+ "normalized": false,
1282
+ "special": true
1283
+ },
1284
+ {
1285
+ "id": 642,
1286
+ "content": "<|reserved_special_token_134|>",
1287
+ "single_word": false,
1288
+ "lstrip": false,
1289
+ "rstrip": false,
1290
+ "normalized": false,
1291
+ "special": true
1292
+ },
1293
+ {
1294
+ "id": 643,
1295
+ "content": "<|reserved_special_token_135|>",
1296
+ "single_word": false,
1297
+ "lstrip": false,
1298
+ "rstrip": false,
1299
+ "normalized": false,
1300
+ "special": true
1301
+ },
1302
+ {
1303
+ "id": 644,
1304
+ "content": "<|reserved_special_token_136|>",
1305
+ "single_word": false,
1306
+ "lstrip": false,
1307
+ "rstrip": false,
1308
+ "normalized": false,
1309
+ "special": true
1310
+ },
1311
+ {
1312
+ "id": 645,
1313
+ "content": "<|reserved_special_token_137|>",
1314
+ "single_word": false,
1315
+ "lstrip": false,
1316
+ "rstrip": false,
1317
+ "normalized": false,
1318
+ "special": true
1319
+ },
1320
+ {
1321
+ "id": 646,
1322
+ "content": "<|reserved_special_token_138|>",
1323
+ "single_word": false,
1324
+ "lstrip": false,
1325
+ "rstrip": false,
1326
+ "normalized": false,
1327
+ "special": true
1328
+ },
1329
+ {
1330
+ "id": 647,
1331
+ "content": "<|reserved_special_token_139|>",
1332
+ "single_word": false,
1333
+ "lstrip": false,
1334
+ "rstrip": false,
1335
+ "normalized": false,
1336
+ "special": true
1337
+ },
1338
+ {
1339
+ "id": 648,
1340
+ "content": "<|reserved_special_token_140|>",
1341
+ "single_word": false,
1342
+ "lstrip": false,
1343
+ "rstrip": false,
1344
+ "normalized": false,
1345
+ "special": true
1346
+ },
1347
+ {
1348
+ "id": 649,
1349
+ "content": "<|reserved_special_token_141|>",
1350
+ "single_word": false,
1351
+ "lstrip": false,
1352
+ "rstrip": false,
1353
+ "normalized": false,
1354
+ "special": true
1355
+ },
1356
+ {
1357
+ "id": 650,
1358
+ "content": "<|reserved_special_token_142|>",
1359
+ "single_word": false,
1360
+ "lstrip": false,
1361
+ "rstrip": false,
1362
+ "normalized": false,
1363
+ "special": true
1364
+ },
1365
+ {
1366
+ "id": 651,
1367
+ "content": "<|reserved_special_token_143|>",
1368
+ "single_word": false,
1369
+ "lstrip": false,
1370
+ "rstrip": false,
1371
+ "normalized": false,
1372
+ "special": true
1373
+ },
1374
+ {
1375
+ "id": 652,
1376
+ "content": "<|reserved_special_token_144|>",
1377
+ "single_word": false,
1378
+ "lstrip": false,
1379
+ "rstrip": false,
1380
+ "normalized": false,
1381
+ "special": true
1382
+ },
1383
+ {
1384
+ "id": 653,
1385
+ "content": "<|reserved_special_token_145|>",
1386
+ "single_word": false,
1387
+ "lstrip": false,
1388
+ "rstrip": false,
1389
+ "normalized": false,
1390
+ "special": true
1391
+ },
1392
+ {
1393
+ "id": 654,
1394
+ "content": "<|reserved_special_token_146|>",
1395
+ "single_word": false,
1396
+ "lstrip": false,
1397
+ "rstrip": false,
1398
+ "normalized": false,
1399
+ "special": true
1400
+ },
1401
+ {
1402
+ "id": 655,
1403
+ "content": "<|reserved_special_token_147|>",
1404
+ "single_word": false,
1405
+ "lstrip": false,
1406
+ "rstrip": false,
1407
+ "normalized": false,
1408
+ "special": true
1409
+ },
1410
+ {
1411
+ "id": 656,
1412
+ "content": "<|reserved_special_token_148|>",
1413
+ "single_word": false,
1414
+ "lstrip": false,
1415
+ "rstrip": false,
1416
+ "normalized": false,
1417
+ "special": true
1418
+ },
1419
+ {
1420
+ "id": 657,
1421
+ "content": "<|reserved_special_token_149|>",
1422
+ "single_word": false,
1423
+ "lstrip": false,
1424
+ "rstrip": false,
1425
+ "normalized": false,
1426
+ "special": true
1427
+ },
1428
+ {
1429
+ "id": 658,
1430
+ "content": "<|reserved_special_token_150|>",
1431
+ "single_word": false,
1432
+ "lstrip": false,
1433
+ "rstrip": false,
1434
+ "normalized": false,
1435
+ "special": true
1436
+ },
1437
+ {
1438
+ "id": 659,
1439
+ "content": "<|reserved_special_token_151|>",
1440
+ "single_word": false,
1441
+ "lstrip": false,
1442
+ "rstrip": false,
1443
+ "normalized": false,
1444
+ "special": true
1445
+ },
1446
+ {
1447
+ "id": 660,
1448
+ "content": "<|reserved_special_token_152|>",
1449
+ "single_word": false,
1450
+ "lstrip": false,
1451
+ "rstrip": false,
1452
+ "normalized": false,
1453
+ "special": true
1454
+ },
1455
+ {
1456
+ "id": 661,
1457
+ "content": "<|reserved_special_token_153|>",
1458
+ "single_word": false,
1459
+ "lstrip": false,
1460
+ "rstrip": false,
1461
+ "normalized": false,
1462
+ "special": true
1463
+ },
1464
+ {
1465
+ "id": 662,
1466
+ "content": "<|reserved_special_token_154|>",
1467
+ "single_word": false,
1468
+ "lstrip": false,
1469
+ "rstrip": false,
1470
+ "normalized": false,
1471
+ "special": true
1472
+ },
1473
+ {
1474
+ "id": 663,
1475
+ "content": "<|reserved_special_token_155|>",
1476
+ "single_word": false,
1477
+ "lstrip": false,
1478
+ "rstrip": false,
1479
+ "normalized": false,
1480
+ "special": true
1481
+ },
1482
+ {
1483
+ "id": 664,
1484
+ "content": "<|reserved_special_token_156|>",
1485
+ "single_word": false,
1486
+ "lstrip": false,
1487
+ "rstrip": false,
1488
+ "normalized": false,
1489
+ "special": true
1490
+ },
1491
+ {
1492
+ "id": 665,
1493
+ "content": "<|reserved_special_token_157|>",
1494
+ "single_word": false,
1495
+ "lstrip": false,
1496
+ "rstrip": false,
1497
+ "normalized": false,
1498
+ "special": true
1499
+ },
1500
+ {
1501
+ "id": 666,
1502
+ "content": "<|reserved_special_token_158|>",
1503
+ "single_word": false,
1504
+ "lstrip": false,
1505
+ "rstrip": false,
1506
+ "normalized": false,
1507
+ "special": true
1508
+ },
1509
+ {
1510
+ "id": 667,
1511
+ "content": "<|reserved_special_token_159|>",
1512
+ "single_word": false,
1513
+ "lstrip": false,
1514
+ "rstrip": false,
1515
+ "normalized": false,
1516
+ "special": true
1517
+ },
1518
+ {
1519
+ "id": 668,
1520
+ "content": "<|reserved_special_token_160|>",
1521
+ "single_word": false,
1522
+ "lstrip": false,
1523
+ "rstrip": false,
1524
+ "normalized": false,
1525
+ "special": true
1526
+ },
1527
+ {
1528
+ "id": 669,
1529
+ "content": "<|reserved_special_token_161|>",
1530
+ "single_word": false,
1531
+ "lstrip": false,
1532
+ "rstrip": false,
1533
+ "normalized": false,
1534
+ "special": true
1535
+ },
1536
+ {
1537
+ "id": 670,
1538
+ "content": "<|reserved_special_token_162|>",
1539
+ "single_word": false,
1540
+ "lstrip": false,
1541
+ "rstrip": false,
1542
+ "normalized": false,
1543
+ "special": true
1544
+ },
1545
+ {
1546
+ "id": 671,
1547
+ "content": "<|reserved_special_token_163|>",
1548
+ "single_word": false,
1549
+ "lstrip": false,
1550
+ "rstrip": false,
1551
+ "normalized": false,
1552
+ "special": true
1553
+ },
1554
+ {
1555
+ "id": 672,
1556
+ "content": "<|reserved_special_token_164|>",
1557
+ "single_word": false,
1558
+ "lstrip": false,
1559
+ "rstrip": false,
1560
+ "normalized": false,
1561
+ "special": true
1562
+ },
1563
+ {
1564
+ "id": 673,
1565
+ "content": "<|reserved_special_token_165|>",
1566
+ "single_word": false,
1567
+ "lstrip": false,
1568
+ "rstrip": false,
1569
+ "normalized": false,
1570
+ "special": true
1571
+ },
1572
+ {
1573
+ "id": 674,
1574
+ "content": "<|reserved_special_token_166|>",
1575
+ "single_word": false,
1576
+ "lstrip": false,
1577
+ "rstrip": false,
1578
+ "normalized": false,
1579
+ "special": true
1580
+ },
1581
+ {
1582
+ "id": 675,
1583
+ "content": "<|reserved_special_token_167|>",
1584
+ "single_word": false,
1585
+ "lstrip": false,
1586
+ "rstrip": false,
1587
+ "normalized": false,
1588
+ "special": true
1589
+ },
1590
+ {
1591
+ "id": 676,
1592
+ "content": "<|reserved_special_token_168|>",
1593
+ "single_word": false,
1594
+ "lstrip": false,
1595
+ "rstrip": false,
1596
+ "normalized": false,
1597
+ "special": true
1598
+ },
1599
+ {
1600
+ "id": 677,
1601
+ "content": "<|reserved_special_token_169|>",
1602
+ "single_word": false,
1603
+ "lstrip": false,
1604
+ "rstrip": false,
1605
+ "normalized": false,
1606
+ "special": true
1607
+ },
1608
+ {
1609
+ "id": 678,
1610
+ "content": "<|reserved_special_token_170|>",
1611
+ "single_word": false,
1612
+ "lstrip": false,
1613
+ "rstrip": false,
1614
+ "normalized": false,
1615
+ "special": true
1616
+ },
1617
+ {
1618
+ "id": 679,
1619
+ "content": "<|reserved_special_token_171|>",
1620
+ "single_word": false,
1621
+ "lstrip": false,
1622
+ "rstrip": false,
1623
+ "normalized": false,
1624
+ "special": true
1625
+ },
1626
+ {
1627
+ "id": 680,
1628
+ "content": "<|reserved_special_token_172|>",
1629
+ "single_word": false,
1630
+ "lstrip": false,
1631
+ "rstrip": false,
1632
+ "normalized": false,
1633
+ "special": true
1634
+ },
1635
+ {
1636
+ "id": 681,
1637
+ "content": "<|reserved_special_token_173|>",
1638
+ "single_word": false,
1639
+ "lstrip": false,
1640
+ "rstrip": false,
1641
+ "normalized": false,
1642
+ "special": true
1643
+ },
1644
+ {
1645
+ "id": 682,
1646
+ "content": "<|reserved_special_token_174|>",
1647
+ "single_word": false,
1648
+ "lstrip": false,
1649
+ "rstrip": false,
1650
+ "normalized": false,
1651
+ "special": true
1652
+ },
1653
+ {
1654
+ "id": 683,
1655
+ "content": "<|reserved_special_token_175|>",
1656
+ "single_word": false,
1657
+ "lstrip": false,
1658
+ "rstrip": false,
1659
+ "normalized": false,
1660
+ "special": true
1661
+ },
1662
+ {
1663
+ "id": 684,
1664
+ "content": "<|reserved_special_token_176|>",
1665
+ "single_word": false,
1666
+ "lstrip": false,
1667
+ "rstrip": false,
1668
+ "normalized": false,
1669
+ "special": true
1670
+ },
1671
+ {
1672
+ "id": 685,
1673
+ "content": "<|reserved_special_token_177|>",
1674
+ "single_word": false,
1675
+ "lstrip": false,
1676
+ "rstrip": false,
1677
+ "normalized": false,
1678
+ "special": true
1679
+ },
1680
+ {
1681
+ "id": 686,
1682
+ "content": "<|reserved_special_token_178|>",
1683
+ "single_word": false,
1684
+ "lstrip": false,
1685
+ "rstrip": false,
1686
+ "normalized": false,
1687
+ "special": true
1688
+ },
1689
+ {
1690
+ "id": 687,
1691
+ "content": "<|reserved_special_token_179|>",
1692
+ "single_word": false,
1693
+ "lstrip": false,
1694
+ "rstrip": false,
1695
+ "normalized": false,
1696
+ "special": true
1697
+ },
1698
+ {
1699
+ "id": 688,
1700
+ "content": "<|reserved_special_token_180|>",
1701
+ "single_word": false,
1702
+ "lstrip": false,
1703
+ "rstrip": false,
1704
+ "normalized": false,
1705
+ "special": true
1706
+ },
1707
+ {
1708
+ "id": 689,
1709
+ "content": "<|reserved_special_token_181|>",
1710
+ "single_word": false,
1711
+ "lstrip": false,
1712
+ "rstrip": false,
1713
+ "normalized": false,
1714
+ "special": true
1715
+ },
1716
+ {
1717
+ "id": 690,
1718
+ "content": "<|reserved_special_token_182|>",
1719
+ "single_word": false,
1720
+ "lstrip": false,
1721
+ "rstrip": false,
1722
+ "normalized": false,
1723
+ "special": true
1724
+ },
1725
+ {
1726
+ "id": 691,
1727
+ "content": "<|reserved_special_token_183|>",
1728
+ "single_word": false,
1729
+ "lstrip": false,
1730
+ "rstrip": false,
1731
+ "normalized": false,
1732
+ "special": true
1733
+ },
1734
+ {
1735
+ "id": 692,
1736
+ "content": "<|reserved_special_token_184|>",
1737
+ "single_word": false,
1738
+ "lstrip": false,
1739
+ "rstrip": false,
1740
+ "normalized": false,
1741
+ "special": true
1742
+ },
1743
+ {
1744
+ "id": 693,
1745
+ "content": "<|reserved_special_token_185|>",
1746
+ "single_word": false,
1747
+ "lstrip": false,
1748
+ "rstrip": false,
1749
+ "normalized": false,
1750
+ "special": true
1751
+ },
1752
+ {
1753
+ "id": 694,
1754
+ "content": "<|reserved_special_token_186|>",
1755
+ "single_word": false,
1756
+ "lstrip": false,
1757
+ "rstrip": false,
1758
+ "normalized": false,
1759
+ "special": true
1760
+ },
1761
+ {
1762
+ "id": 695,
1763
+ "content": "<|reserved_special_token_187|>",
1764
+ "single_word": false,
1765
+ "lstrip": false,
1766
+ "rstrip": false,
1767
+ "normalized": false,
1768
+ "special": true
1769
+ },
1770
+ {
1771
+ "id": 696,
1772
+ "content": "<|reserved_special_token_188|>",
1773
+ "single_word": false,
1774
+ "lstrip": false,
1775
+ "rstrip": false,
1776
+ "normalized": false,
1777
+ "special": true
1778
+ },
1779
+ {
1780
+ "id": 697,
1781
+ "content": "<|reserved_special_token_189|>",
1782
+ "single_word": false,
1783
+ "lstrip": false,
1784
+ "rstrip": false,
1785
+ "normalized": false,
1786
+ "special": true
1787
+ },
1788
+ {
1789
+ "id": 698,
1790
+ "content": "<|reserved_special_token_190|>",
1791
+ "single_word": false,
1792
+ "lstrip": false,
1793
+ "rstrip": false,
1794
+ "normalized": false,
1795
+ "special": true
1796
+ },
1797
+ {
1798
+ "id": 699,
1799
+ "content": "<|reserved_special_token_191|>",
1800
+ "single_word": false,
1801
+ "lstrip": false,
1802
+ "rstrip": false,
1803
+ "normalized": false,
1804
+ "special": true
1805
+ },
1806
+ {
1807
+ "id": 700,
1808
+ "content": "<|reserved_special_token_192|>",
1809
+ "single_word": false,
1810
+ "lstrip": false,
1811
+ "rstrip": false,
1812
+ "normalized": false,
1813
+ "special": true
1814
+ },
1815
+ {
1816
+ "id": 701,
1817
+ "content": "<|reserved_special_token_193|>",
1818
+ "single_word": false,
1819
+ "lstrip": false,
1820
+ "rstrip": false,
1821
+ "normalized": false,
1822
+ "special": true
1823
+ },
1824
+ {
1825
+ "id": 702,
1826
+ "content": "<|reserved_special_token_194|>",
1827
+ "single_word": false,
1828
+ "lstrip": false,
1829
+ "rstrip": false,
1830
+ "normalized": false,
1831
+ "special": true
1832
+ },
1833
+ {
1834
+ "id": 703,
1835
+ "content": "<|reserved_special_token_195|>",
1836
+ "single_word": false,
1837
+ "lstrip": false,
1838
+ "rstrip": false,
1839
+ "normalized": false,
1840
+ "special": true
1841
+ },
1842
+ {
1843
+ "id": 704,
1844
+ "content": "<|reserved_special_token_196|>",
1845
+ "single_word": false,
1846
+ "lstrip": false,
1847
+ "rstrip": false,
1848
+ "normalized": false,
1849
+ "special": true
1850
+ },
1851
+ {
1852
+ "id": 705,
1853
+ "content": "<|reserved_special_token_197|>",
1854
+ "single_word": false,
1855
+ "lstrip": false,
1856
+ "rstrip": false,
1857
+ "normalized": false,
1858
+ "special": true
1859
+ },
1860
+ {
1861
+ "id": 706,
1862
+ "content": "<|reserved_special_token_198|>",
1863
+ "single_word": false,
1864
+ "lstrip": false,
1865
+ "rstrip": false,
1866
+ "normalized": false,
1867
+ "special": true
1868
+ },
1869
+ {
1870
+ "id": 707,
1871
+ "content": "<|reserved_special_token_199|>",
1872
+ "single_word": false,
1873
+ "lstrip": false,
1874
+ "rstrip": false,
1875
+ "normalized": false,
1876
+ "special": true
1877
+ },
1878
+ {
1879
+ "id": 708,
1880
+ "content": "<|reserved_special_token_200|>",
1881
+ "single_word": false,
1882
+ "lstrip": false,
1883
+ "rstrip": false,
1884
+ "normalized": false,
1885
+ "special": true
1886
+ },
1887
+ {
1888
+ "id": 709,
1889
+ "content": "<|reserved_special_token_201|>",
1890
+ "single_word": false,
1891
+ "lstrip": false,
1892
+ "rstrip": false,
1893
+ "normalized": false,
1894
+ "special": true
1895
+ },
1896
+ {
1897
+ "id": 710,
1898
+ "content": "<|reserved_special_token_202|>",
1899
+ "single_word": false,
1900
+ "lstrip": false,
1901
+ "rstrip": false,
1902
+ "normalized": false,
1903
+ "special": true
1904
+ },
1905
+ {
1906
+ "id": 711,
1907
+ "content": "<|reserved_special_token_203|>",
1908
+ "single_word": false,
1909
+ "lstrip": false,
1910
+ "rstrip": false,
1911
+ "normalized": false,
1912
+ "special": true
1913
+ },
1914
+ {
1915
+ "id": 712,
1916
+ "content": "<|reserved_special_token_204|>",
1917
+ "single_word": false,
1918
+ "lstrip": false,
1919
+ "rstrip": false,
1920
+ "normalized": false,
1921
+ "special": true
1922
+ },
1923
+ {
1924
+ "id": 713,
1925
+ "content": "<|reserved_special_token_205|>",
1926
+ "single_word": false,
1927
+ "lstrip": false,
1928
+ "rstrip": false,
1929
+ "normalized": false,
1930
+ "special": true
1931
+ },
1932
+ {
1933
+ "id": 714,
1934
+ "content": "<|reserved_special_token_206|>",
1935
+ "single_word": false,
1936
+ "lstrip": false,
1937
+ "rstrip": false,
1938
+ "normalized": false,
1939
+ "special": true
1940
+ },
1941
+ {
1942
+ "id": 715,
1943
+ "content": "<|reserved_special_token_207|>",
1944
+ "single_word": false,
1945
+ "lstrip": false,
1946
+ "rstrip": false,
1947
+ "normalized": false,
1948
+ "special": true
1949
+ },
1950
+ {
1951
+ "id": 716,
1952
+ "content": "<|reserved_special_token_208|>",
1953
+ "single_word": false,
1954
+ "lstrip": false,
1955
+ "rstrip": false,
1956
+ "normalized": false,
1957
+ "special": true
1958
+ },
1959
+ {
1960
+ "id": 717,
1961
+ "content": "<|reserved_special_token_209|>",
1962
+ "single_word": false,
1963
+ "lstrip": false,
1964
+ "rstrip": false,
1965
+ "normalized": false,
1966
+ "special": true
1967
+ },
1968
+ {
1969
+ "id": 718,
1970
+ "content": "<|reserved_special_token_210|>",
1971
+ "single_word": false,
1972
+ "lstrip": false,
1973
+ "rstrip": false,
1974
+ "normalized": false,
1975
+ "special": true
1976
+ },
1977
+ {
1978
+ "id": 719,
1979
+ "content": "<|reserved_special_token_211|>",
1980
+ "single_word": false,
1981
+ "lstrip": false,
1982
+ "rstrip": false,
1983
+ "normalized": false,
1984
+ "special": true
1985
+ },
1986
+ {
1987
+ "id": 720,
1988
+ "content": "<|reserved_special_token_212|>",
1989
+ "single_word": false,
1990
+ "lstrip": false,
1991
+ "rstrip": false,
1992
+ "normalized": false,
1993
+ "special": true
1994
+ },
1995
+ {
1996
+ "id": 721,
1997
+ "content": "<|reserved_special_token_213|>",
1998
+ "single_word": false,
1999
+ "lstrip": false,
2000
+ "rstrip": false,
2001
+ "normalized": false,
2002
+ "special": true
2003
+ },
2004
+ {
2005
+ "id": 722,
2006
+ "content": "<|reserved_special_token_214|>",
2007
+ "single_word": false,
2008
+ "lstrip": false,
2009
+ "rstrip": false,
2010
+ "normalized": false,
2011
+ "special": true
2012
+ },
2013
+ {
2014
+ "id": 723,
2015
+ "content": "<|reserved_special_token_215|>",
2016
+ "single_word": false,
2017
+ "lstrip": false,
2018
+ "rstrip": false,
2019
+ "normalized": false,
2020
+ "special": true
2021
+ },
2022
+ {
2023
+ "id": 724,
2024
+ "content": "<|reserved_special_token_216|>",
2025
+ "single_word": false,
2026
+ "lstrip": false,
2027
+ "rstrip": false,
2028
+ "normalized": false,
2029
+ "special": true
2030
+ },
2031
+ {
2032
+ "id": 725,
2033
+ "content": "<|reserved_special_token_217|>",
2034
+ "single_word": false,
2035
+ "lstrip": false,
2036
+ "rstrip": false,
2037
+ "normalized": false,
2038
+ "special": true
2039
+ },
2040
+ {
2041
+ "id": 726,
2042
+ "content": "<|reserved_special_token_218|>",
2043
+ "single_word": false,
2044
+ "lstrip": false,
2045
+ "rstrip": false,
2046
+ "normalized": false,
2047
+ "special": true
2048
+ },
2049
+ {
2050
+ "id": 727,
2051
+ "content": "<|reserved_special_token_219|>",
2052
+ "single_word": false,
2053
+ "lstrip": false,
2054
+ "rstrip": false,
2055
+ "normalized": false,
2056
+ "special": true
2057
+ },
2058
+ {
2059
+ "id": 728,
2060
+ "content": "<|reserved_special_token_220|>",
2061
+ "single_word": false,
2062
+ "lstrip": false,
2063
+ "rstrip": false,
2064
+ "normalized": false,
2065
+ "special": true
2066
+ },
2067
+ {
2068
+ "id": 729,
2069
+ "content": "<|reserved_special_token_221|>",
2070
+ "single_word": false,
2071
+ "lstrip": false,
2072
+ "rstrip": false,
2073
+ "normalized": false,
2074
+ "special": true
2075
+ },
2076
+ {
2077
+ "id": 730,
2078
+ "content": "<|reserved_special_token_222|>",
2079
+ "single_word": false,
2080
+ "lstrip": false,
2081
+ "rstrip": false,
2082
+ "normalized": false,
2083
+ "special": true
2084
+ },
2085
+ {
2086
+ "id": 731,
2087
+ "content": "<|reserved_special_token_223|>",
2088
+ "single_word": false,
2089
+ "lstrip": false,
2090
+ "rstrip": false,
2091
+ "normalized": false,
2092
+ "special": true
2093
+ },
2094
+ {
2095
+ "id": 732,
2096
+ "content": "<|reserved_special_token_224|>",
2097
+ "single_word": false,
2098
+ "lstrip": false,
2099
+ "rstrip": false,
2100
+ "normalized": false,
2101
+ "special": true
2102
+ },
2103
+ {
2104
+ "id": 733,
2105
+ "content": "<|reserved_special_token_225|>",
2106
+ "single_word": false,
2107
+ "lstrip": false,
2108
+ "rstrip": false,
2109
+ "normalized": false,
2110
+ "special": true
2111
+ },
2112
+ {
2113
+ "id": 734,
2114
+ "content": "<|reserved_special_token_226|>",
2115
+ "single_word": false,
2116
+ "lstrip": false,
2117
+ "rstrip": false,
2118
+ "normalized": false,
2119
+ "special": true
2120
+ },
2121
+ {
2122
+ "id": 735,
2123
+ "content": "<|reserved_special_token_227|>",
2124
+ "single_word": false,
2125
+ "lstrip": false,
2126
+ "rstrip": false,
2127
+ "normalized": false,
2128
+ "special": true
2129
+ },
2130
+ {
2131
+ "id": 736,
2132
+ "content": "<|reserved_special_token_228|>",
2133
+ "single_word": false,
2134
+ "lstrip": false,
2135
+ "rstrip": false,
2136
+ "normalized": false,
2137
+ "special": true
2138
+ },
2139
+ {
2140
+ "id": 737,
2141
+ "content": "<|reserved_special_token_229|>",
2142
+ "single_word": false,
2143
+ "lstrip": false,
2144
+ "rstrip": false,
2145
+ "normalized": false,
2146
+ "special": true
2147
+ },
2148
+ {
2149
+ "id": 738,
2150
+ "content": "<|reserved_special_token_230|>",
2151
+ "single_word": false,
2152
+ "lstrip": false,
2153
+ "rstrip": false,
2154
+ "normalized": false,
2155
+ "special": true
2156
+ },
2157
+ {
2158
+ "id": 739,
2159
+ "content": "<|reserved_special_token_231|>",
2160
+ "single_word": false,
2161
+ "lstrip": false,
2162
+ "rstrip": false,
2163
+ "normalized": false,
2164
+ "special": true
2165
+ },
2166
+ {
2167
+ "id": 740,
2168
+ "content": "<|reserved_special_token_232|>",
2169
+ "single_word": false,
2170
+ "lstrip": false,
2171
+ "rstrip": false,
2172
+ "normalized": false,
2173
+ "special": true
2174
+ },
2175
+ {
2176
+ "id": 741,
2177
+ "content": "<|reserved_special_token_233|>",
2178
+ "single_word": false,
2179
+ "lstrip": false,
2180
+ "rstrip": false,
2181
+ "normalized": false,
2182
+ "special": true
2183
+ },
2184
+ {
2185
+ "id": 742,
2186
+ "content": "<|reserved_special_token_234|>",
2187
+ "single_word": false,
2188
+ "lstrip": false,
2189
+ "rstrip": false,
2190
+ "normalized": false,
2191
+ "special": true
2192
+ },
2193
+ {
2194
+ "id": 743,
2195
+ "content": "<|reserved_special_token_235|>",
2196
+ "single_word": false,
2197
+ "lstrip": false,
2198
+ "rstrip": false,
2199
+ "normalized": false,
2200
+ "special": true
2201
+ },
2202
+ {
2203
+ "id": 744,
2204
+ "content": "<|reserved_special_token_236|>",
2205
+ "single_word": false,
2206
+ "lstrip": false,
2207
+ "rstrip": false,
2208
+ "normalized": false,
2209
+ "special": true
2210
+ },
2211
+ {
2212
+ "id": 745,
2213
+ "content": "<|reserved_special_token_237|>",
2214
+ "single_word": false,
2215
+ "lstrip": false,
2216
+ "rstrip": false,
2217
+ "normalized": false,
2218
+ "special": true
2219
+ },
2220
+ {
2221
+ "id": 746,
2222
+ "content": "<|reserved_special_token_238|>",
2223
+ "single_word": false,
2224
+ "lstrip": false,
2225
+ "rstrip": false,
2226
+ "normalized": false,
2227
+ "special": true
2228
+ },
2229
+ {
2230
+ "id": 747,
2231
+ "content": "<|reserved_special_token_239|>",
2232
+ "single_word": false,
2233
+ "lstrip": false,
2234
+ "rstrip": false,
2235
+ "normalized": false,
2236
+ "special": true
2237
+ },
2238
+ {
2239
+ "id": 748,
2240
+ "content": "<|reserved_special_token_240|>",
2241
+ "single_word": false,
2242
+ "lstrip": false,
2243
+ "rstrip": false,
2244
+ "normalized": false,
2245
+ "special": true
2246
+ },
2247
+ {
2248
+ "id": 749,
2249
+ "content": "<|reserved_special_token_241|>",
2250
+ "single_word": false,
2251
+ "lstrip": false,
2252
+ "rstrip": false,
2253
+ "normalized": false,
2254
+ "special": true
2255
+ },
2256
+ {
2257
+ "id": 750,
2258
+ "content": "<|reserved_special_token_242|>",
2259
+ "single_word": false,
2260
+ "lstrip": false,
2261
+ "rstrip": false,
2262
+ "normalized": false,
2263
+ "special": true
2264
+ },
2265
+ {
2266
+ "id": 751,
2267
+ "content": "<|reserved_special_token_243|>",
2268
+ "single_word": false,
2269
+ "lstrip": false,
2270
+ "rstrip": false,
2271
+ "normalized": false,
2272
+ "special": true
2273
+ },
2274
+ {
2275
+ "id": 752,
2276
+ "content": "<|reserved_special_token_244|>",
2277
+ "single_word": false,
2278
+ "lstrip": false,
2279
+ "rstrip": false,
2280
+ "normalized": false,
2281
+ "special": true
2282
+ },
2283
+ {
2284
+ "id": 753,
2285
+ "content": "<|reserved_special_token_245|>",
2286
+ "single_word": false,
2287
+ "lstrip": false,
2288
+ "rstrip": false,
2289
+ "normalized": false,
2290
+ "special": true
2291
+ },
2292
+ {
2293
+ "id": 754,
2294
+ "content": "<|reserved_special_token_246|>",
2295
+ "single_word": false,
2296
+ "lstrip": false,
2297
+ "rstrip": false,
2298
+ "normalized": false,
2299
+ "special": true
2300
+ },
2301
+ {
2302
+ "id": 755,
2303
+ "content": "<|reserved_special_token_247|>",
2304
+ "single_word": false,
2305
+ "lstrip": false,
2306
+ "rstrip": false,
2307
+ "normalized": false,
2308
+ "special": true
2309
+ }
2310
+ ],
2311
+ "normalizer": null,
2312
+ "pre_tokenizer": {
2313
+ "type": "Sequence",
2314
+ "pretokenizers": [
2315
+ {
2316
+ "type": "Split",
2317
+ "pattern": {
2318
+ "Regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?\\p{L}+|\\p{N}{1,3}| ?[^\\s\\p{L}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+"
2319
+ },
2320
+ "behavior": "Isolated",
2321
+ "invert": false
2322
+ },
2323
+ {
2324
+ "type": "ByteLevel",
2325
+ "add_prefix_space": false,
2326
+ "trim_offsets": true,
2327
+ "use_regex": false
2328
+ }
2329
+ ]
2330
+ },
2331
+ "post_processor": {
2332
+ "type": "TemplateProcessing",
2333
+ "single": [
2334
+ {
2335
+ "SpecialToken": {
2336
+ "id": "<|begin_of_text|>",
2337
+ "type_id": 0
2338
+ }
2339
+ },
2340
+ {
2341
+ "Sequence": {
2342
+ "id": "A",
2343
+ "type_id": 0
2344
+ }
2345
+ },
2346
+ {
2347
+ "SpecialToken": {
2348
+ "id": "<|end_of_text|>",
2349
+ "type_id": 0
2350
+ }
2351
+ }
2352
+ ],
2353
+ "pair": [
2354
+ {
2355
+ "SpecialToken": {
2356
+ "id": "<|begin_of_text|>",
2357
+ "type_id": 0
2358
+ }
2359
+ },
2360
+ {
2361
+ "Sequence": {
2362
+ "id": "A",
2363
+ "type_id": 0
2364
+ }
2365
+ },
2366
+ {
2367
+ "SpecialToken": {
2368
+ "id": "<|end_of_text|>",
2369
+ "type_id": 0
2370
+ }
2371
+ },
2372
+ {
2373
+ "SpecialToken": {
2374
+ "id": "<|begin_of_text|>",
2375
+ "type_id": 1
2376
+ }
2377
+ },
2378
+ {
2379
+ "Sequence": {
2380
+ "id": "B",
2381
+ "type_id": 1
2382
+ }
2383
+ },
2384
+ {
2385
+ "SpecialToken": {
2386
+ "id": "<|end_of_text|>",
2387
+ "type_id": 1
2388
+ }
2389
+ }
2390
+ ],
2391
+ "special_tokens": {
2392
+ "<|begin_of_text|>": {
2393
+ "id": "<|begin_of_text|>",
2394
+ "ids": [
2395
+ 500
2396
+ ],
2397
+ "tokens": [
2398
+ "<|begin_of_text|>"
2399
+ ]
2400
+ },
2401
+ "<|end_of_text|>": {
2402
+ "id": "<|end_of_text|>",
2403
+ "ids": [
2404
+ 501
2405
+ ],
2406
+ "tokens": [
2407
+ "<|end_of_text|>"
2408
+ ]
2409
+ }
2410
+ }
2411
+ },
2412
+ "decoder": {
2413
+ "type": "ByteLevel",
2414
+ "add_prefix_space": true,
2415
+ "trim_offsets": true,
2416
+ "use_regex": true
2417
+ },
2418
+ "model": {
2419
+ "type": "BPE",
2420
+ "dropout": null,
2421
+ "unk_token": null,
2422
+ "continuing_subword_prefix": null,
2423
+ "end_of_word_suffix": null,
2424
+ "fuse_unk": false,
2425
+ "byte_fallback": false,
2426
+ "ignore_merges": true,
2427
+ "vocab": {
2428
+ "!": 0,
2429
+ "\"": 1,
2430
+ "#": 2,
2431
+ "$": 3,
2432
+ "%": 4,
2433
+ "&": 5,
2434
+ "'": 6,
2435
+ "(": 7,
2436
+ ")": 8,
2437
+ "*": 9,
2438
+ "+": 10,
2439
+ ",": 11,
2440
+ "-": 12,
2441
+ ".": 13,
2442
+ "/": 14,
2443
+ "0": 15,
2444
+ "1": 16,
2445
+ "2": 17,
2446
+ "3": 18,
2447
+ "4": 19,
2448
+ "5": 20,
2449
+ "6": 21,
2450
+ "7": 22,
2451
+ "8": 23,
2452
+ "9": 24,
2453
+ ":": 25,
2454
+ ";": 26,
2455
+ "<": 27,
2456
+ "=": 28,
2457
+ ">": 29,
2458
+ "?": 30,
2459
+ "@": 31,
2460
+ "A": 32,
2461
+ "B": 33,
2462
+ "C": 34,
2463
+ "D": 35,
2464
+ "E": 36,
2465
+ "F": 37,
2466
+ "G": 38,
2467
+ "H": 39,
2468
+ "I": 40,
2469
+ "J": 41,
2470
+ "K": 42,
2471
+ "L": 43,
2472
+ "M": 44,
2473
+ "N": 45,
2474
+ "O": 46,
2475
+ "P": 47,
2476
+ "Q": 48,
2477
+ "R": 49,
2478
+ "S": 50,
2479
+ "T": 51,
2480
+ "U": 52,
2481
+ "V": 53,
2482
+ "W": 54,
2483
+ "X": 55,
2484
+ "Y": 56,
2485
+ "Z": 57,
2486
+ "[": 58,
2487
+ "\\": 59,
2488
+ "]": 60,
2489
+ "^": 61,
2490
+ "_": 62,
2491
+ "`": 63,
2492
+ "a": 64,
2493
+ "b": 65,
2494
+ "c": 66,
2495
+ "d": 67,
2496
+ "e": 68,
2497
+ "f": 69,
2498
+ "g": 70,
2499
+ "h": 71,
2500
+ "i": 72,
2501
+ "j": 73,
2502
+ "k": 74,
2503
+ "l": 75,
2504
+ "m": 76,
2505
+ "n": 77,
2506
+ "o": 78,
2507
+ "p": 79,
2508
+ "q": 80,
2509
+ "r": 81,
2510
+ "s": 82,
2511
+ "t": 83,
2512
+ "u": 84,
2513
+ "v": 85,
2514
+ "w": 86,
2515
+ "x": 87,
2516
+ "y": 88,
2517
+ "z": 89,
2518
+ "{": 90,
2519
+ "|": 91,
2520
+ "}": 92,
2521
+ "~": 93,
2522
+ "¡": 94,
2523
+ "¢": 95,
2524
+ "£": 96,
2525
+ "¤": 97,
2526
+ "¥": 98,
2527
+ "¦": 99,
2528
+ "§": 100,
2529
+ "¨": 101,
2530
+ "©": 102,
2531
+ "ª": 103,
2532
+ "«": 104,
2533
+ "¬": 105,
2534
+ "®": 106,
2535
+ "¯": 107,
2536
+ "°": 108,
2537
+ "±": 109,
2538
+ "²": 110,
2539
+ "³": 111,
2540
+ "´": 112,
2541
+ "µ": 113,
2542
+ "¶": 114,
2543
+ "·": 115,
2544
+ "¸": 116,
2545
+ "¹": 117,
2546
+ "º": 118,
2547
+ "»": 119,
2548
+ "¼": 120,
2549
+ "½": 121,
2550
+ "¾": 122,
2551
+ "¿": 123,
2552
+ "À": 124,
2553
+ "Á": 125,
2554
+ "��": 126,
2555
+ "Ã": 127,
2556
+ "Ä": 128,
2557
+ "Å": 129,
2558
+ "Æ": 130,
2559
+ "Ç": 131,
2560
+ "È": 132,
2561
+ "É": 133,
2562
+ "Ê": 134,
2563
+ "Ë": 135,
2564
+ "Ì": 136,
2565
+ "Í": 137,
2566
+ "Î": 138,
2567
+ "Ï": 139,
2568
+ "Ð": 140,
2569
+ "Ñ": 141,
2570
+ "Ò": 142,
2571
+ "Ó": 143,
2572
+ "Ô": 144,
2573
+ "Õ": 145,
2574
+ "Ö": 146,
2575
+ "×": 147,
2576
+ "Ø": 148,
2577
+ "Ù": 149,
2578
+ "Ú": 150,
2579
+ "Û": 151,
2580
+ "Ü": 152,
2581
+ "Ý": 153,
2582
+ "Þ": 154,
2583
+ "ß": 155,
2584
+ "à": 156,
2585
+ "á": 157,
2586
+ "â": 158,
2587
+ "ã": 159,
2588
+ "ä": 160,
2589
+ "å": 161,
2590
+ "æ": 162,
2591
+ "ç": 163,
2592
+ "è": 164,
2593
+ "é": 165,
2594
+ "ê": 166,
2595
+ "ë": 167,
2596
+ "ì": 168,
2597
+ "í": 169,
2598
+ "î": 170,
2599
+ "ï": 171,
2600
+ "ð": 172,
2601
+ "ñ": 173,
2602
+ "ò": 174,
2603
+ "ó": 175,
2604
+ "ô": 176,
2605
+ "õ": 177,
2606
+ "ö": 178,
2607
+ "÷": 179,
2608
+ "ø": 180,
2609
+ "ù": 181,
2610
+ "ú": 182,
2611
+ "û": 183,
2612
+ "ü": 184,
2613
+ "ý": 185,
2614
+ "þ": 186,
2615
+ "ÿ": 187,
2616
+ "Ā": 188,
2617
+ "ā": 189,
2618
+ "Ă": 190,
2619
+ "ă": 191,
2620
+ "Ą": 192,
2621
+ "ą": 193,
2622
+ "Ć": 194,
2623
+ "ć": 195,
2624
+ "Ĉ": 196,
2625
+ "ĉ": 197,
2626
+ "Ċ": 198,
2627
+ "ċ": 199,
2628
+ "Č": 200,
2629
+ "č": 201,
2630
+ "Ď": 202,
2631
+ "ď": 203,
2632
+ "Đ": 204,
2633
+ "đ": 205,
2634
+ "Ē": 206,
2635
+ "ē": 207,
2636
+ "Ĕ": 208,
2637
+ "ĕ": 209,
2638
+ "Ė": 210,
2639
+ "ė": 211,
2640
+ "Ę": 212,
2641
+ "ę": 213,
2642
+ "Ě": 214,
2643
+ "ě": 215,
2644
+ "Ĝ": 216,
2645
+ "ĝ": 217,
2646
+ "Ğ": 218,
2647
+ "ğ": 219,
2648
+ "Ġ": 220,
2649
+ "ġ": 221,
2650
+ "Ģ": 222,
2651
+ "ģ": 223,
2652
+ "Ĥ": 224,
2653
+ "ĥ": 225,
2654
+ "Ħ": 226,
2655
+ "ħ": 227,
2656
+ "Ĩ": 228,
2657
+ "ĩ": 229,
2658
+ "Ī": 230,
2659
+ "ī": 231,
2660
+ "Ĭ": 232,
2661
+ "ĭ": 233,
2662
+ "Į": 234,
2663
+ "į": 235,
2664
+ "İ": 236,
2665
+ "ı": 237,
2666
+ "IJ": 238,
2667
+ "ij": 239,
2668
+ "Ĵ": 240,
2669
+ "ĵ": 241,
2670
+ "Ķ": 242,
2671
+ "ķ": 243,
2672
+ "ĸ": 244,
2673
+ "Ĺ": 245,
2674
+ "ĺ": 246,
2675
+ "Ļ": 247,
2676
+ "ļ": 248,
2677
+ "Ľ": 249,
2678
+ "ľ": 250,
2679
+ "Ŀ": 251,
2680
+ "ŀ": 252,
2681
+ "Ł": 253,
2682
+ "ł": 254,
2683
+ "Ń": 255,
2684
+ "ĠĠ": 256,
2685
+ "ĠĠĠĠ": 257,
2686
+ "in": 258,
2687
+ "Ġt": 259,
2688
+ "ĠĠĠĠĠĠĠĠ": 260,
2689
+ "er": 261,
2690
+ "ĠĠĠ": 262,
2691
+ "on": 263,
2692
+ "Ġa": 264,
2693
+ "re": 265,
2694
+ "at": 266,
2695
+ "st": 267,
2696
+ "en": 268,
2697
+ "or": 269,
2698
+ "Ġth": 270,
2699
+ "ĊĊ": 271,
2700
+ "Ġc": 272,
2701
+ "le": 273,
2702
+ "Ġs": 274,
2703
+ "it": 275,
2704
+ "an": 276,
2705
+ "ar": 277,
2706
+ "al": 278,
2707
+ "Ġthe": 279,
2708
+ ";Ċ": 280,
2709
+ "Ġp": 281,
2710
+ "Ġf": 282,
2711
+ "ou": 283,
2712
+ "Ġ=": 284,
2713
+ "is": 285,
2714
+ "ĠĠĠĠĠĠĠ": 286,
2715
+ "ing": 287,
2716
+ "es": 288,
2717
+ "Ġw": 289,
2718
+ "ion": 290,
2719
+ "ed": 291,
2720
+ "ic": 292,
2721
+ "Ġb": 293,
2722
+ "Ġd": 294,
2723
+ "et": 295,
2724
+ "Ġm": 296,
2725
+ "Ġo": 297,
2726
+ "ĉĉ": 298,
2727
+ "ro": 299,
2728
+ "as": 300,
2729
+ "el": 301,
2730
+ "ct": 302,
2731
+ "nd": 303,
2732
+ "Ġin": 304,
2733
+ "Ġh": 305,
2734
+ "ent": 306,
2735
+ "id": 307,
2736
+ "Ġn": 308,
2737
+ "am": 309,
2738
+ "ĠĠĠĠĠĠĠĠĠĠĠ": 310,
2739
+ "Ġto": 311,
2740
+ "Ġre": 312,
2741
+ "--": 313,
2742
+ "Ġ{": 314,
2743
+ "Ġof": 315,
2744
+ "om": 316,
2745
+ ");Ċ": 317,
2746
+ "im": 318,
2747
+ "čĊ": 319,
2748
+ "Ġ(": 320,
2749
+ "il": 321,
2750
+ "//": 322,
2751
+ "Ġand": 323,
2752
+ "ur": 324,
2753
+ "se": 325,
2754
+ "Ġl": 326,
2755
+ "ex": 327,
2756
+ "ĠS": 328,
2757
+ "ad": 329,
2758
+ "Ġ\"": 330,
2759
+ "ch": 331,
2760
+ "ut": 332,
2761
+ "if": 333,
2762
+ "**": 334,
2763
+ "Ġ}": 335,
2764
+ "em": 336,
2765
+ "ol": 337,
2766
+ "ĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠ": 338,
2767
+ "th": 339,
2768
+ ")Ċ": 340,
2769
+ "Ġ{Ċ": 341,
2770
+ "Ġg": 342,
2771
+ "ig": 343,
2772
+ "iv": 344,
2773
+ ",Ċ": 345,
2774
+ "ce": 346,
2775
+ "od": 347,
2776
+ "Ġv": 348,
2777
+ "ate": 349,
2778
+ "ĠT": 350,
2779
+ "ag": 351,
2780
+ "ay": 352,
2781
+ "Ġ*": 353,
2782
+ "ot": 354,
2783
+ "us": 355,
2784
+ "ĠC": 356,
2785
+ "Ġst": 357,
2786
+ "ĠI": 358,
2787
+ "un": 359,
2788
+ "ul": 360,
2789
+ "ue": 361,
2790
+ "ĠA": 362,
2791
+ "ow": 363,
2792
+ "Ġ'": 364,
2793
+ "ew": 365,
2794
+ "Ġ<": 366,
2795
+ "ation": 367,
2796
+ "()": 368,
2797
+ "Ġfor": 369,
2798
+ "ab": 370,
2799
+ "ort": 371,
2800
+ "um": 372,
2801
+ "ame": 373,
2802
+ "Ġis": 374,
2803
+ "pe": 375,
2804
+ "tr": 376,
2805
+ "ck": 377,
2806
+ "âĢ": 378,
2807
+ "Ġy": 379,
2808
+ "ist": 380,
2809
+ "----": 381,
2810
+ ".ĊĊ": 382,
2811
+ "he": 383,
2812
+ "Ġe": 384,
2813
+ "lo": 385,
2814
+ "ĠM": 386,
2815
+ "Ġbe": 387,
2816
+ "ers": 388,
2817
+ "Ġon": 389,
2818
+ "Ġcon": 390,
2819
+ "ap": 391,
2820
+ "ub": 392,
2821
+ "ĠP": 393,
2822
+ "ĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠ": 394,
2823
+ "ass": 395,
2824
+ "int": 396,
2825
+ ">Ċ": 397,
2826
+ "ly": 398,
2827
+ "urn": 399,
2828
+ "Ġ$": 400,
2829
+ ";ĊĊ": 401,
2830
+ "av": 402,
2831
+ "port": 403,
2832
+ "ir": 404,
2833
+ "->": 405,
2834
+ "nt": 406,
2835
+ "ction": 407,
2836
+ "end": 408,
2837
+ "Ġde": 409,
2838
+ "00": 410,
2839
+ "ith": 411,
2840
+ "out": 412,
2841
+ "turn": 413,
2842
+ "our": 414,
2843
+ "ĠĠĠĠĠ": 415,
2844
+ "lic": 416,
2845
+ "res": 417,
2846
+ "pt": 418,
2847
+ "==": 419,
2848
+ "Ġthis": 420,
2849
+ "Ġwh": 421,
2850
+ "Ġif": 422,
2851
+ "ĠD": 423,
2852
+ "ver": 424,
2853
+ "age": 425,
2854
+ "ĠB": 426,
2855
+ "ht": 427,
2856
+ "ext": 428,
2857
+ "=\"": 429,
2858
+ "Ġthat": 430,
2859
+ "****": 431,
2860
+ "ĠR": 432,
2861
+ "Ġit": 433,
2862
+ "ess": 434,
2863
+ "ĠF": 435,
2864
+ "Ġr": 436,
2865
+ "os": 437,
2866
+ "and": 438,
2867
+ "Ġas": 439,
2868
+ "ect": 440,
2869
+ "ke": 441,
2870
+ "rom": 442,
2871
+ "Ġ//": 443,
2872
+ "con": 444,
2873
+ "ĠL": 445,
2874
+ "(\"": 446,
2875
+ "qu": 447,
2876
+ "lass": 448,
2877
+ "Ġwith": 449,
2878
+ "iz": 450,
2879
+ "de": 451,
2880
+ "ĠN": 452,
2881
+ "Ġal": 453,
2882
+ "op": 454,
2883
+ "up": 455,
2884
+ "get": 456,
2885
+ "Ġ}Ċ": 457,
2886
+ "ile": 458,
2887
+ "Ġan": 459,
2888
+ "ata": 460,
2889
+ "ore": 461,
2890
+ "ri": 462,
2891
+ "Ġpro": 463,
2892
+ ";čĊ": 464,
2893
+ "ĉĉĉĉ": 465,
2894
+ "ter": 466,
2895
+ "ain": 467,
2896
+ "ĠW": 468,
2897
+ "ĠE": 469,
2898
+ "Ġcom": 470,
2899
+ "Ġreturn": 471,
2900
+ "art": 472,
2901
+ "ĠH": 473,
2902
+ "ack": 474,
2903
+ "import": 475,
2904
+ "ublic": 476,
2905
+ "Ġor": 477,
2906
+ "est": 478,
2907
+ "ment": 479,
2908
+ "ĠG": 480,
2909
+ "able": 481,
2910
+ "Ġ-": 482,
2911
+ "ine": 483,
2912
+ "ill": 484,
2913
+ "ind": 485,
2914
+ "ere": 486,
2915
+ "::": 487,
2916
+ "ity": 488,
2917
+ "Ġ+": 489,
2918
+ "Ġtr": 490,
2919
+ "elf": 491,
2920
+ "ight": 492,
2921
+ "('": 493,
2922
+ "orm": 494,
2923
+ "ult": 495,
2924
+ "str": 496,
2925
+ "..": 497,
2926
+ "\",": 498,
2927
+ "Ġyou": 499
2928
+ },
2929
+ "merges": [
2930
+ [
2931
+ "Ġ",
2932
+ "Ġ"
2933
+ ],
2934
+ [
2935
+ "Ġ",
2936
+ "ĠĠĠ"
2937
+ ],
2938
+ [
2939
+ "ĠĠ",
2940
+ "ĠĠ"
2941
+ ],
2942
+ [
2943
+ "ĠĠĠ",
2944
+ "Ġ"
2945
+ ],
2946
+ [
2947
+ "i",
2948
+ "n"
2949
+ ],
2950
+ [
2951
+ "Ġ",
2952
+ "t"
2953
+ ],
2954
+ [
2955
+ "Ġ",
2956
+ "ĠĠĠĠĠĠĠ"
2957
+ ],
2958
+ [
2959
+ "ĠĠĠĠ",
2960
+ "ĠĠĠĠ"
2961
+ ],
2962
+ [
2963
+ "ĠĠĠ",
2964
+ "ĠĠĠĠĠ"
2965
+ ],
2966
+ [
2967
+ "ĠĠĠĠĠĠĠ",
2968
+ "Ġ"
2969
+ ],
2970
+ [
2971
+ "ĠĠĠĠĠ",
2972
+ "ĠĠĠ"
2973
+ ],
2974
+ [
2975
+ "e",
2976
+ "r"
2977
+ ],
2978
+ [
2979
+ "Ġ",
2980
+ "ĠĠ"
2981
+ ],
2982
+ [
2983
+ "ĠĠ",
2984
+ "Ġ"
2985
+ ],
2986
+ [
2987
+ "o",
2988
+ "n"
2989
+ ],
2990
+ [
2991
+ "Ġ",
2992
+ "a"
2993
+ ],
2994
+ [
2995
+ "r",
2996
+ "e"
2997
+ ],
2998
+ [
2999
+ "a",
3000
+ "t"
3001
+ ],
3002
+ [
3003
+ "s",
3004
+ "t"
3005
+ ],
3006
+ [
3007
+ "e",
3008
+ "n"
3009
+ ],
3010
+ [
3011
+ "o",
3012
+ "r"
3013
+ ],
3014
+ [
3015
+ "Ġ",
3016
+ "th"
3017
+ ],
3018
+ [
3019
+ "Ġt",
3020
+ "h"
3021
+ ],
3022
+ [
3023
+ "Ċ",
3024
+ "Ċ"
3025
+ ],
3026
+ [
3027
+ "Ġ",
3028
+ "c"
3029
+ ],
3030
+ [
3031
+ "l",
3032
+ "e"
3033
+ ],
3034
+ [
3035
+ "Ġ",
3036
+ "s"
3037
+ ],
3038
+ [
3039
+ "i",
3040
+ "t"
3041
+ ],
3042
+ [
3043
+ "a",
3044
+ "n"
3045
+ ],
3046
+ [
3047
+ "a",
3048
+ "r"
3049
+ ],
3050
+ [
3051
+ "a",
3052
+ "l"
3053
+ ],
3054
+ [
3055
+ "Ġt",
3056
+ "he"
3057
+ ],
3058
+ [
3059
+ "Ġth",
3060
+ "e"
3061
+ ],
3062
+ [
3063
+ ";",
3064
+ "Ċ"
3065
+ ],
3066
+ [
3067
+ "Ġ",
3068
+ "p"
3069
+ ],
3070
+ [
3071
+ "Ġ",
3072
+ "f"
3073
+ ],
3074
+ [
3075
+ "o",
3076
+ "u"
3077
+ ],
3078
+ [
3079
+ "Ġ",
3080
+ "="
3081
+ ],
3082
+ [
3083
+ "i",
3084
+ "s"
3085
+ ],
3086
+ [
3087
+ "ĠĠ",
3088
+ "ĠĠĠĠĠ"
3089
+ ],
3090
+ [
3091
+ "ĠĠĠĠ",
3092
+ "ĠĠĠ"
3093
+ ],
3094
+ [
3095
+ "ĠĠĠ",
3096
+ "ĠĠĠĠ"
3097
+ ],
3098
+ [
3099
+ "ĠĠĠĠĠ",
3100
+ "ĠĠ"
3101
+ ],
3102
+ [
3103
+ "in",
3104
+ "g"
3105
+ ],
3106
+ [
3107
+ "e",
3108
+ "s"
3109
+ ],
3110
+ [
3111
+ "Ġ",
3112
+ "w"
3113
+ ],
3114
+ [
3115
+ "i",
3116
+ "on"
3117
+ ],
3118
+ [
3119
+ "e",
3120
+ "d"
3121
+ ],
3122
+ [
3123
+ "i",
3124
+ "c"
3125
+ ],
3126
+ [
3127
+ "Ġ",
3128
+ "b"
3129
+ ],
3130
+ [
3131
+ "Ġ",
3132
+ "d"
3133
+ ],
3134
+ [
3135
+ "e",
3136
+ "t"
3137
+ ],
3138
+ [
3139
+ "Ġ",
3140
+ "m"
3141
+ ],
3142
+ [
3143
+ "Ġ",
3144
+ "o"
3145
+ ],
3146
+ [
3147
+ "ĉ",
3148
+ "ĉ"
3149
+ ],
3150
+ [
3151
+ "r",
3152
+ "o"
3153
+ ],
3154
+ [
3155
+ "a",
3156
+ "s"
3157
+ ],
3158
+ [
3159
+ "e",
3160
+ "l"
3161
+ ],
3162
+ [
3163
+ "c",
3164
+ "t"
3165
+ ],
3166
+ [
3167
+ "n",
3168
+ "d"
3169
+ ],
3170
+ [
3171
+ "Ġ",
3172
+ "in"
3173
+ ],
3174
+ [
3175
+ "Ġ",
3176
+ "h"
3177
+ ],
3178
+ [
3179
+ "e",
3180
+ "nt"
3181
+ ],
3182
+ [
3183
+ "en",
3184
+ "t"
3185
+ ],
3186
+ [
3187
+ "i",
3188
+ "d"
3189
+ ],
3190
+ [
3191
+ "Ġ",
3192
+ "n"
3193
+ ],
3194
+ [
3195
+ "a",
3196
+ "m"
3197
+ ],
3198
+ [
3199
+ "ĠĠĠĠ",
3200
+ "ĠĠĠĠĠĠĠ"
3201
+ ],
3202
+ [
3203
+ "ĠĠĠĠĠĠĠĠ",
3204
+ "ĠĠĠ"
3205
+ ],
3206
+ [
3207
+ "ĠĠĠ",
3208
+ "ĠĠĠĠĠĠĠĠ"
3209
+ ],
3210
+ [
3211
+ "ĠĠĠĠĠĠĠ",
3212
+ "ĠĠĠĠ"
3213
+ ],
3214
+ [
3215
+ "Ġt",
3216
+ "o"
3217
+ ],
3218
+ [
3219
+ "Ġ",
3220
+ "re"
3221
+ ],
3222
+ [
3223
+ "Ġr",
3224
+ "e"
3225
+ ],
3226
+ [
3227
+ "-",
3228
+ "-"
3229
+ ],
3230
+ [
3231
+ "Ġ",
3232
+ "{"
3233
+ ],
3234
+ [
3235
+ "Ġo",
3236
+ "f"
3237
+ ],
3238
+ [
3239
+ "o",
3240
+ "m"
3241
+ ],
3242
+ [
3243
+ ")",
3244
+ ";Ċ"
3245
+ ],
3246
+ [
3247
+ "i",
3248
+ "m"
3249
+ ],
3250
+ [
3251
+ "č",
3252
+ "Ċ"
3253
+ ],
3254
+ [
3255
+ "Ġ",
3256
+ "("
3257
+ ],
3258
+ [
3259
+ "i",
3260
+ "l"
3261
+ ],
3262
+ [
3263
+ "/",
3264
+ "/"
3265
+ ],
3266
+ [
3267
+ "Ġ",
3268
+ "and"
3269
+ ],
3270
+ [
3271
+ "Ġa",
3272
+ "nd"
3273
+ ],
3274
+ [
3275
+ "Ġan",
3276
+ "d"
3277
+ ],
3278
+ [
3279
+ "u",
3280
+ "r"
3281
+ ],
3282
+ [
3283
+ "s",
3284
+ "e"
3285
+ ],
3286
+ [
3287
+ "Ġ",
3288
+ "l"
3289
+ ],
3290
+ [
3291
+ "e",
3292
+ "x"
3293
+ ],
3294
+ [
3295
+ "Ġ",
3296
+ "S"
3297
+ ],
3298
+ [
3299
+ "a",
3300
+ "d"
3301
+ ],
3302
+ [
3303
+ "Ġ",
3304
+ "\""
3305
+ ],
3306
+ [
3307
+ "c",
3308
+ "h"
3309
+ ],
3310
+ [
3311
+ "u",
3312
+ "t"
3313
+ ],
3314
+ [
3315
+ "i",
3316
+ "f"
3317
+ ],
3318
+ [
3319
+ "*",
3320
+ "*"
3321
+ ],
3322
+ [
3323
+ "Ġ",
3324
+ "}"
3325
+ ],
3326
+ [
3327
+ "e",
3328
+ "m"
3329
+ ],
3330
+ [
3331
+ "o",
3332
+ "l"
3333
+ ],
3334
+ [
3335
+ "Ġ",
3336
+ "ĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠ"
3337
+ ],
3338
+ [
3339
+ "ĠĠĠĠĠĠĠĠ",
3340
+ "ĠĠĠĠĠĠĠĠ"
3341
+ ],
3342
+ [
3343
+ "ĠĠĠĠĠĠĠĠĠĠĠ",
3344
+ "ĠĠĠĠĠ"
3345
+ ],
3346
+ [
3347
+ "ĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠ",
3348
+ "Ġ"
3349
+ ],
3350
+ [
3351
+ "ĠĠĠĠĠ",
3352
+ "ĠĠĠĠĠĠĠĠĠĠĠ"
3353
+ ],
3354
+ [
3355
+ "t",
3356
+ "h"
3357
+ ],
3358
+ [
3359
+ ")",
3360
+ "Ċ"
3361
+ ],
3362
+ [
3363
+ "Ġ{",
3364
+ "Ċ"
3365
+ ],
3366
+ [
3367
+ "Ġ",
3368
+ "g"
3369
+ ],
3370
+ [
3371
+ "i",
3372
+ "g"
3373
+ ],
3374
+ [
3375
+ "i",
3376
+ "v"
3377
+ ],
3378
+ [
3379
+ ",",
3380
+ "Ċ"
3381
+ ],
3382
+ [
3383
+ "c",
3384
+ "e"
3385
+ ],
3386
+ [
3387
+ "o",
3388
+ "d"
3389
+ ],
3390
+ [
3391
+ "Ġ",
3392
+ "v"
3393
+ ],
3394
+ [
3395
+ "at",
3396
+ "e"
3397
+ ],
3398
+ [
3399
+ "Ġ",
3400
+ "T"
3401
+ ],
3402
+ [
3403
+ "a",
3404
+ "g"
3405
+ ],
3406
+ [
3407
+ "a",
3408
+ "y"
3409
+ ],
3410
+ [
3411
+ "Ġ",
3412
+ "*"
3413
+ ],
3414
+ [
3415
+ "o",
3416
+ "t"
3417
+ ],
3418
+ [
3419
+ "u",
3420
+ "s"
3421
+ ],
3422
+ [
3423
+ "Ġ",
3424
+ "C"
3425
+ ],
3426
+ [
3427
+ "Ġ",
3428
+ "st"
3429
+ ],
3430
+ [
3431
+ "Ġs",
3432
+ "t"
3433
+ ],
3434
+ [
3435
+ "Ġ",
3436
+ "I"
3437
+ ],
3438
+ [
3439
+ "u",
3440
+ "n"
3441
+ ],
3442
+ [
3443
+ "u",
3444
+ "l"
3445
+ ],
3446
+ [
3447
+ "u",
3448
+ "e"
3449
+ ],
3450
+ [
3451
+ "Ġ",
3452
+ "A"
3453
+ ],
3454
+ [
3455
+ "o",
3456
+ "w"
3457
+ ],
3458
+ [
3459
+ "Ġ",
3460
+ "'"
3461
+ ],
3462
+ [
3463
+ "e",
3464
+ "w"
3465
+ ],
3466
+ [
3467
+ "Ġ",
3468
+ "<"
3469
+ ],
3470
+ [
3471
+ "at",
3472
+ "ion"
3473
+ ],
3474
+ [
3475
+ "(",
3476
+ ")"
3477
+ ],
3478
+ [
3479
+ "Ġf",
3480
+ "or"
3481
+ ],
3482
+ [
3483
+ "a",
3484
+ "b"
3485
+ ],
3486
+ [
3487
+ "or",
3488
+ "t"
3489
+ ],
3490
+ [
3491
+ "u",
3492
+ "m"
3493
+ ],
3494
+ [
3495
+ "am",
3496
+ "e"
3497
+ ],
3498
+ [
3499
+ "Ġ",
3500
+ "is"
3501
+ ],
3502
+ [
3503
+ "p",
3504
+ "e"
3505
+ ],
3506
+ [
3507
+ "t",
3508
+ "r"
3509
+ ],
3510
+ [
3511
+ "c",
3512
+ "k"
3513
+ ],
3514
+ [
3515
+ "â",
3516
+ "Ģ"
3517
+ ],
3518
+ [
3519
+ "Ġ",
3520
+ "y"
3521
+ ],
3522
+ [
3523
+ "i",
3524
+ "st"
3525
+ ],
3526
+ [
3527
+ "is",
3528
+ "t"
3529
+ ],
3530
+ [
3531
+ "--",
3532
+ "--"
3533
+ ],
3534
+ [
3535
+ ".",
3536
+ "ĊĊ"
3537
+ ],
3538
+ [
3539
+ "h",
3540
+ "e"
3541
+ ],
3542
+ [
3543
+ "Ġ",
3544
+ "e"
3545
+ ],
3546
+ [
3547
+ "l",
3548
+ "o"
3549
+ ],
3550
+ [
3551
+ "Ġ",
3552
+ "M"
3553
+ ],
3554
+ [
3555
+ "Ġb",
3556
+ "e"
3557
+ ],
3558
+ [
3559
+ "er",
3560
+ "s"
3561
+ ],
3562
+ [
3563
+ "Ġ",
3564
+ "on"
3565
+ ],
3566
+ [
3567
+ "Ġo",
3568
+ "n"
3569
+ ],
3570
+ [
3571
+ "Ġ",
3572
+ "con"
3573
+ ],
3574
+ [
3575
+ "Ġc",
3576
+ "on"
3577
+ ],
3578
+ [
3579
+ "a",
3580
+ "p"
3581
+ ],
3582
+ [
3583
+ "u",
3584
+ "b"
3585
+ ],
3586
+ [
3587
+ "Ġ",
3588
+ "P"
3589
+ ],
3590
+ [
3591
+ "ĠĠĠĠ",
3592
+ "ĠĠĠĠĠĠĠĠĠĠĠ"
3593
+ ],
3594
+ [
3595
+ "ĠĠĠĠĠĠĠĠ",
3596
+ "ĠĠĠĠĠĠĠ"
3597
+ ],
3598
+ [
3599
+ "ĠĠĠĠĠĠĠ",
3600
+ "ĠĠĠĠĠĠĠĠ"
3601
+ ],
3602
+ [
3603
+ "ĠĠĠĠĠĠĠĠĠĠĠ",
3604
+ "ĠĠĠĠ"
3605
+ ],
3606
+ [
3607
+ "as",
3608
+ "s"
3609
+ ],
3610
+ [
3611
+ "i",
3612
+ "nt"
3613
+ ],
3614
+ [
3615
+ "in",
3616
+ "t"
3617
+ ],
3618
+ [
3619
+ ">",
3620
+ "Ċ"
3621
+ ],
3622
+ [
3623
+ "l",
3624
+ "y"
3625
+ ],
3626
+ [
3627
+ "ur",
3628
+ "n"
3629
+ ],
3630
+ [
3631
+ "Ġ",
3632
+ "$"
3633
+ ],
3634
+ [
3635
+ ";",
3636
+ "ĊĊ"
3637
+ ],
3638
+ [
3639
+ ";Ċ",
3640
+ "Ċ"
3641
+ ],
3642
+ [
3643
+ "a",
3644
+ "v"
3645
+ ],
3646
+ [
3647
+ "p",
3648
+ "ort"
3649
+ ],
3650
+ [
3651
+ "i",
3652
+ "r"
3653
+ ],
3654
+ [
3655
+ "-",
3656
+ ">"
3657
+ ],
3658
+ [
3659
+ "n",
3660
+ "t"
3661
+ ],
3662
+ [
3663
+ "ct",
3664
+ "ion"
3665
+ ],
3666
+ [
3667
+ "e",
3668
+ "nd"
3669
+ ],
3670
+ [
3671
+ "en",
3672
+ "d"
3673
+ ],
3674
+ [
3675
+ "Ġ",
3676
+ "de"
3677
+ ],
3678
+ [
3679
+ "Ġd",
3680
+ "e"
3681
+ ],
3682
+ [
3683
+ "0",
3684
+ "0"
3685
+ ],
3686
+ [
3687
+ "i",
3688
+ "th"
3689
+ ],
3690
+ [
3691
+ "it",
3692
+ "h"
3693
+ ],
3694
+ [
3695
+ "o",
3696
+ "ut"
3697
+ ],
3698
+ [
3699
+ "ou",
3700
+ "t"
3701
+ ],
3702
+ [
3703
+ "t",
3704
+ "urn"
3705
+ ],
3706
+ [
3707
+ "o",
3708
+ "ur"
3709
+ ],
3710
+ [
3711
+ "ou",
3712
+ "r"
3713
+ ],
3714
+ [
3715
+ "Ġ",
3716
+ "ĠĠĠĠ"
3717
+ ],
3718
+ [
3719
+ "ĠĠ",
3720
+ "ĠĠĠ"
3721
+ ],
3722
+ [
3723
+ "ĠĠĠĠ",
3724
+ "Ġ"
3725
+ ],
3726
+ [
3727
+ "ĠĠĠ",
3728
+ "ĠĠ"
3729
+ ],
3730
+ [
3731
+ "l",
3732
+ "ic"
3733
+ ],
3734
+ [
3735
+ "r",
3736
+ "es"
3737
+ ],
3738
+ [
3739
+ "re",
3740
+ "s"
3741
+ ],
3742
+ [
3743
+ "p",
3744
+ "t"
3745
+ ],
3746
+ [
3747
+ "=",
3748
+ "="
3749
+ ],
3750
+ [
3751
+ "Ġth",
3752
+ "is"
3753
+ ],
3754
+ [
3755
+ "Ġw",
3756
+ "h"
3757
+ ],
3758
+ [
3759
+ "Ġ",
3760
+ "if"
3761
+ ],
3762
+ [
3763
+ "Ġ",
3764
+ "D"
3765
+ ],
3766
+ [
3767
+ "v",
3768
+ "er"
3769
+ ],
3770
+ [
3771
+ "ag",
3772
+ "e"
3773
+ ],
3774
+ [
3775
+ "Ġ",
3776
+ "B"
3777
+ ],
3778
+ [
3779
+ "h",
3780
+ "t"
3781
+ ],
3782
+ [
3783
+ "ex",
3784
+ "t"
3785
+ ],
3786
+ [
3787
+ "=",
3788
+ "\""
3789
+ ],
3790
+ [
3791
+ "Ġth",
3792
+ "at"
3793
+ ],
3794
+ [
3795
+ "**",
3796
+ "**"
3797
+ ],
3798
+ [
3799
+ "Ġ",
3800
+ "R"
3801
+ ],
3802
+ [
3803
+ "Ġ",
3804
+ "it"
3805
+ ],
3806
+ [
3807
+ "es",
3808
+ "s"
3809
+ ],
3810
+ [
3811
+ "Ġ",
3812
+ "F"
3813
+ ],
3814
+ [
3815
+ "Ġ",
3816
+ "r"
3817
+ ],
3818
+ [
3819
+ "o",
3820
+ "s"
3821
+ ],
3822
+ [
3823
+ "a",
3824
+ "nd"
3825
+ ],
3826
+ [
3827
+ "an",
3828
+ "d"
3829
+ ],
3830
+ [
3831
+ "Ġ",
3832
+ "as"
3833
+ ],
3834
+ [
3835
+ "Ġa",
3836
+ "s"
3837
+ ],
3838
+ [
3839
+ "e",
3840
+ "ct"
3841
+ ],
3842
+ [
3843
+ "k",
3844
+ "e"
3845
+ ],
3846
+ [
3847
+ "r",
3848
+ "om"
3849
+ ],
3850
+ [
3851
+ "ro",
3852
+ "m"
3853
+ ],
3854
+ [
3855
+ "Ġ",
3856
+ "//"
3857
+ ],
3858
+ [
3859
+ "c",
3860
+ "on"
3861
+ ],
3862
+ [
3863
+ "Ġ",
3864
+ "L"
3865
+ ],
3866
+ [
3867
+ "(",
3868
+ "\""
3869
+ ],
3870
+ [
3871
+ "q",
3872
+ "u"
3873
+ ],
3874
+ [
3875
+ "l",
3876
+ "ass"
3877
+ ],
3878
+ [
3879
+ "Ġw",
3880
+ "ith"
3881
+ ],
3882
+ [
3883
+ "i",
3884
+ "z"
3885
+ ],
3886
+ [
3887
+ "d",
3888
+ "e"
3889
+ ],
3890
+ [
3891
+ "Ġ",
3892
+ "N"
3893
+ ],
3894
+ [
3895
+ "Ġ",
3896
+ "al"
3897
+ ],
3898
+ [
3899
+ "Ġa",
3900
+ "l"
3901
+ ],
3902
+ [
3903
+ "o",
3904
+ "p"
3905
+ ],
3906
+ [
3907
+ "u",
3908
+ "p"
3909
+ ],
3910
+ [
3911
+ "g",
3912
+ "et"
3913
+ ],
3914
+ [
3915
+ "Ġ}",
3916
+ "Ċ"
3917
+ ],
3918
+ [
3919
+ "i",
3920
+ "le"
3921
+ ],
3922
+ [
3923
+ "il",
3924
+ "e"
3925
+ ],
3926
+ [
3927
+ "Ġ",
3928
+ "an"
3929
+ ],
3930
+ [
3931
+ "Ġa",
3932
+ "n"
3933
+ ],
3934
+ [
3935
+ "at",
3936
+ "a"
3937
+ ],
3938
+ [
3939
+ "o",
3940
+ "re"
3941
+ ],
3942
+ [
3943
+ "or",
3944
+ "e"
3945
+ ],
3946
+ [
3947
+ "r",
3948
+ "i"
3949
+ ],
3950
+ [
3951
+ "Ġp",
3952
+ "ro"
3953
+ ],
3954
+ [
3955
+ ";",
3956
+ "čĊ"
3957
+ ],
3958
+ [
3959
+ "ĉĉ",
3960
+ "ĉĉ"
3961
+ ],
3962
+ [
3963
+ "t",
3964
+ "er"
3965
+ ],
3966
+ [
3967
+ "a",
3968
+ "in"
3969
+ ],
3970
+ [
3971
+ "Ġ",
3972
+ "W"
3973
+ ],
3974
+ [
3975
+ "Ġ",
3976
+ "E"
3977
+ ],
3978
+ [
3979
+ "Ġc",
3980
+ "om"
3981
+ ],
3982
+ [
3983
+ "Ġre",
3984
+ "turn"
3985
+ ],
3986
+ [
3987
+ "ar",
3988
+ "t"
3989
+ ],
3990
+ [
3991
+ "Ġ",
3992
+ "H"
3993
+ ],
3994
+ [
3995
+ "a",
3996
+ "ck"
3997
+ ],
3998
+ [
3999
+ "im",
4000
+ "port"
4001
+ ],
4002
+ [
4003
+ "ub",
4004
+ "lic"
4005
+ ],
4006
+ [
4007
+ "Ġ",
4008
+ "or"
4009
+ ],
4010
+ [
4011
+ "Ġo",
4012
+ "r"
4013
+ ],
4014
+ [
4015
+ "e",
4016
+ "st"
4017
+ ],
4018
+ [
4019
+ "es",
4020
+ "t"
4021
+ ],
4022
+ [
4023
+ "m",
4024
+ "ent"
4025
+ ],
4026
+ [
4027
+ "Ġ",
4028
+ "G"
4029
+ ],
4030
+ [
4031
+ "ab",
4032
+ "le"
4033
+ ],
4034
+ [
4035
+ "Ġ",
4036
+ "-"
4037
+ ],
4038
+ [
4039
+ "in",
4040
+ "e"
4041
+ ],
4042
+ [
4043
+ "il",
4044
+ "l"
4045
+ ],
4046
+ [
4047
+ "i",
4048
+ "nd"
4049
+ ],
4050
+ [
4051
+ "in",
4052
+ "d"
4053
+ ],
4054
+ [
4055
+ "e",
4056
+ "re"
4057
+ ],
4058
+ [
4059
+ "er",
4060
+ "e"
4061
+ ],
4062
+ [
4063
+ ":",
4064
+ ":"
4065
+ ],
4066
+ [
4067
+ "it",
4068
+ "y"
4069
+ ],
4070
+ [
4071
+ "Ġ",
4072
+ "+"
4073
+ ],
4074
+ [
4075
+ "Ġ",
4076
+ "tr"
4077
+ ],
4078
+ [
4079
+ "Ġt",
4080
+ "r"
4081
+ ],
4082
+ [
4083
+ "el",
4084
+ "f"
4085
+ ],
4086
+ [
4087
+ "ig",
4088
+ "ht"
4089
+ ],
4090
+ [
4091
+ "(",
4092
+ "'"
4093
+ ],
4094
+ [
4095
+ "or",
4096
+ "m"
4097
+ ],
4098
+ [
4099
+ "ul",
4100
+ "t"
4101
+ ],
4102
+ [
4103
+ "s",
4104
+ "tr"
4105
+ ],
4106
+ [
4107
+ "st",
4108
+ "r"
4109
+ ],
4110
+ [
4111
+ ".",
4112
+ "."
4113
+ ],
4114
+ [
4115
+ "\"",
4116
+ ","
4117
+ ],
4118
+ [
4119
+ "Ġy",
4120
+ "ou"
4121
+ ]
4122
+ ]
4123
+ }
4124
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,2064 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "128000": {
4
+ "content": "<|begin_of_text|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "128001": {
12
+ "content": "<|end_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "128002": {
20
+ "content": "<|AUDIO|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "128003": {
28
+ "content": "<|audio_eos|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128004": {
36
+ "content": "<|finetune_right_pad_id|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128005": {
44
+ "content": "<|reserved_special_token_2|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "128006": {
52
+ "content": "<|start_header_id|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "128007": {
60
+ "content": "<|end_header_id|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "128008": {
68
+ "content": "<|eom_id|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "128009": {
76
+ "content": "<|eot_id|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "128010": {
84
+ "content": "<|python_tag|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128011": {
92
+ "content": "<|reserved_special_token_3|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128012": {
100
+ "content": "<|reserved_special_token_4|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128013": {
108
+ "content": "<|reserved_special_token_5|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "128014": {
116
+ "content": "<|reserved_special_token_6|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "128015": {
124
+ "content": "<|reserved_special_token_7|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "128016": {
132
+ "content": "<|reserved_special_token_8|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "128017": {
140
+ "content": "<|reserved_special_token_9|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "128018": {
148
+ "content": "<|reserved_special_token_10|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "128019": {
156
+ "content": "<|reserved_special_token_11|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "128020": {
164
+ "content": "<|reserved_special_token_12|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "128021": {
172
+ "content": "<|reserved_special_token_13|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "128022": {
180
+ "content": "<|reserved_special_token_14|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "128023": {
188
+ "content": "<|reserved_special_token_15|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "128024": {
196
+ "content": "<|reserved_special_token_16|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "128025": {
204
+ "content": "<|reserved_special_token_17|>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "128026": {
212
+ "content": "<|reserved_special_token_18|>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "128027": {
220
+ "content": "<|reserved_special_token_19|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "128028": {
228
+ "content": "<|reserved_special_token_20|>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "128029": {
236
+ "content": "<|reserved_special_token_21|>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "128030": {
244
+ "content": "<|reserved_special_token_22|>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "128031": {
252
+ "content": "<|reserved_special_token_23|>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "128032": {
260
+ "content": "<|reserved_special_token_24|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "128033": {
268
+ "content": "<|reserved_special_token_25|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "128034": {
276
+ "content": "<|reserved_special_token_26|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "128035": {
284
+ "content": "<|reserved_special_token_27|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "128036": {
292
+ "content": "<|reserved_special_token_28|>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "128037": {
300
+ "content": "<|reserved_special_token_29|>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "128038": {
308
+ "content": "<|reserved_special_token_30|>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "128039": {
316
+ "content": "<|reserved_special_token_31|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "128040": {
324
+ "content": "<|reserved_special_token_32|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128041": {
332
+ "content": "<|reserved_special_token_33|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "128042": {
340
+ "content": "<|reserved_special_token_34|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "128043": {
348
+ "content": "<|reserved_special_token_35|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "128044": {
356
+ "content": "<|reserved_special_token_36|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "128045": {
364
+ "content": "<|reserved_special_token_37|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "128046": {
372
+ "content": "<|reserved_special_token_38|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "128047": {
380
+ "content": "<|reserved_special_token_39|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "128048": {
388
+ "content": "<|reserved_special_token_40|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "128049": {
396
+ "content": "<|reserved_special_token_41|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "128050": {
404
+ "content": "<|reserved_special_token_42|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "128051": {
412
+ "content": "<|reserved_special_token_43|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "128052": {
420
+ "content": "<|reserved_special_token_44|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "128053": {
428
+ "content": "<|reserved_special_token_45|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "128054": {
436
+ "content": "<|reserved_special_token_46|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "128055": {
444
+ "content": "<|reserved_special_token_47|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "128056": {
452
+ "content": "<|reserved_special_token_48|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "128057": {
460
+ "content": "<|reserved_special_token_49|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "128058": {
468
+ "content": "<|reserved_special_token_50|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "128059": {
476
+ "content": "<|reserved_special_token_51|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "128060": {
484
+ "content": "<|reserved_special_token_52|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "128061": {
492
+ "content": "<|reserved_special_token_53|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "128062": {
500
+ "content": "<|reserved_special_token_54|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "128063": {
508
+ "content": "<|reserved_special_token_55|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "128064": {
516
+ "content": "<|reserved_special_token_56|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "128065": {
524
+ "content": "<|reserved_special_token_57|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "128066": {
532
+ "content": "<|reserved_special_token_58|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "128067": {
540
+ "content": "<|reserved_special_token_59|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "128068": {
548
+ "content": "<|reserved_special_token_60|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "128069": {
556
+ "content": "<|reserved_special_token_61|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "128070": {
564
+ "content": "<|reserved_special_token_62|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "128071": {
572
+ "content": "<|reserved_special_token_63|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "128072": {
580
+ "content": "<|reserved_special_token_64|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "128073": {
588
+ "content": "<|reserved_special_token_65|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "128074": {
596
+ "content": "<|reserved_special_token_66|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "128075": {
604
+ "content": "<|reserved_special_token_67|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "128076": {
612
+ "content": "<|reserved_special_token_68|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "128077": {
620
+ "content": "<|reserved_special_token_69|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "128078": {
628
+ "content": "<|reserved_special_token_70|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "128079": {
636
+ "content": "<|reserved_special_token_71|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "128080": {
644
+ "content": "<|reserved_special_token_72|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "128081": {
652
+ "content": "<|reserved_special_token_73|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "128082": {
660
+ "content": "<|reserved_special_token_74|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "128083": {
668
+ "content": "<|reserved_special_token_75|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "128084": {
676
+ "content": "<|reserved_special_token_76|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "128085": {
684
+ "content": "<|reserved_special_token_77|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "128086": {
692
+ "content": "<|reserved_special_token_78|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "128087": {
700
+ "content": "<|reserved_special_token_79|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "128088": {
708
+ "content": "<|reserved_special_token_80|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "128089": {
716
+ "content": "<|reserved_special_token_81|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "128090": {
724
+ "content": "<|reserved_special_token_82|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "128091": {
732
+ "content": "<|reserved_special_token_83|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "128092": {
740
+ "content": "<|reserved_special_token_84|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "128093": {
748
+ "content": "<|reserved_special_token_85|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "128094": {
756
+ "content": "<|reserved_special_token_86|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "128095": {
764
+ "content": "<|reserved_special_token_87|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "128096": {
772
+ "content": "<|reserved_special_token_88|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "128097": {
780
+ "content": "<|reserved_special_token_89|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "128098": {
788
+ "content": "<|reserved_special_token_90|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "128099": {
796
+ "content": "<|reserved_special_token_91|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "128100": {
804
+ "content": "<|reserved_special_token_92|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "128101": {
812
+ "content": "<|reserved_special_token_93|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "128102": {
820
+ "content": "<|reserved_special_token_94|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128103": {
828
+ "content": "<|reserved_special_token_95|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "128104": {
836
+ "content": "<|reserved_special_token_96|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "128105": {
844
+ "content": "<|reserved_special_token_97|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "128106": {
852
+ "content": "<|reserved_special_token_98|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "128107": {
860
+ "content": "<|reserved_special_token_99|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "128108": {
868
+ "content": "<|reserved_special_token_100|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "128109": {
876
+ "content": "<|reserved_special_token_101|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "128110": {
884
+ "content": "<|reserved_special_token_102|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "128111": {
892
+ "content": "<|reserved_special_token_103|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "128112": {
900
+ "content": "<|reserved_special_token_104|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "128113": {
908
+ "content": "<|reserved_special_token_105|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "128114": {
916
+ "content": "<|reserved_special_token_106|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "128115": {
924
+ "content": "<|reserved_special_token_107|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "128116": {
932
+ "content": "<|reserved_special_token_108|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "128117": {
940
+ "content": "<|reserved_special_token_109|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "128118": {
948
+ "content": "<|reserved_special_token_110|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "128119": {
956
+ "content": "<|reserved_special_token_111|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "128120": {
964
+ "content": "<|reserved_special_token_112|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "128121": {
972
+ "content": "<|reserved_special_token_113|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "128122": {
980
+ "content": "<|reserved_special_token_114|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "128123": {
988
+ "content": "<|reserved_special_token_115|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "128124": {
996
+ "content": "<|reserved_special_token_116|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "128125": {
1004
+ "content": "<|reserved_special_token_117|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "128126": {
1012
+ "content": "<|reserved_special_token_118|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "128127": {
1020
+ "content": "<|reserved_special_token_119|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128128": {
1028
+ "content": "<|reserved_special_token_120|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "128129": {
1036
+ "content": "<|reserved_special_token_121|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "128130": {
1044
+ "content": "<|reserved_special_token_122|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "128131": {
1052
+ "content": "<|reserved_special_token_123|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "128132": {
1060
+ "content": "<|reserved_special_token_124|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "128133": {
1068
+ "content": "<|reserved_special_token_125|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "128134": {
1076
+ "content": "<|reserved_special_token_126|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "128135": {
1084
+ "content": "<|reserved_special_token_127|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "128136": {
1092
+ "content": "<|reserved_special_token_128|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "128137": {
1100
+ "content": "<|reserved_special_token_129|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "128138": {
1108
+ "content": "<|reserved_special_token_130|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "128139": {
1116
+ "content": "<|reserved_special_token_131|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "128140": {
1124
+ "content": "<|reserved_special_token_132|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "128141": {
1132
+ "content": "<|reserved_special_token_133|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "128142": {
1140
+ "content": "<|reserved_special_token_134|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "128143": {
1148
+ "content": "<|reserved_special_token_135|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "128144": {
1156
+ "content": "<|reserved_special_token_136|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "128145": {
1164
+ "content": "<|reserved_special_token_137|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "128146": {
1172
+ "content": "<|reserved_special_token_138|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "128147": {
1180
+ "content": "<|reserved_special_token_139|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "128148": {
1188
+ "content": "<|reserved_special_token_140|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "128149": {
1196
+ "content": "<|reserved_special_token_141|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "128150": {
1204
+ "content": "<|reserved_special_token_142|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "128151": {
1212
+ "content": "<|reserved_special_token_143|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "128152": {
1220
+ "content": "<|reserved_special_token_144|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "128153": {
1228
+ "content": "<|reserved_special_token_145|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "128154": {
1236
+ "content": "<|reserved_special_token_146|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "128155": {
1244
+ "content": "<|reserved_special_token_147|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "128156": {
1252
+ "content": "<|reserved_special_token_148|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "128157": {
1260
+ "content": "<|reserved_special_token_149|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "128158": {
1268
+ "content": "<|reserved_special_token_150|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "128159": {
1276
+ "content": "<|reserved_special_token_151|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "128160": {
1284
+ "content": "<|reserved_special_token_152|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "128161": {
1292
+ "content": "<|reserved_special_token_153|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "128162": {
1300
+ "content": "<|reserved_special_token_154|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "128163": {
1308
+ "content": "<|reserved_special_token_155|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "128164": {
1316
+ "content": "<|reserved_special_token_156|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "128165": {
1324
+ "content": "<|reserved_special_token_157|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "128166": {
1332
+ "content": "<|reserved_special_token_158|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "128167": {
1340
+ "content": "<|reserved_special_token_159|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "128168": {
1348
+ "content": "<|reserved_special_token_160|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "128169": {
1356
+ "content": "<|reserved_special_token_161|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "128170": {
1364
+ "content": "<|reserved_special_token_162|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "128171": {
1372
+ "content": "<|reserved_special_token_163|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "128172": {
1380
+ "content": "<|reserved_special_token_164|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "128173": {
1388
+ "content": "<|reserved_special_token_165|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "128174": {
1396
+ "content": "<|reserved_special_token_166|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "128175": {
1404
+ "content": "<|reserved_special_token_167|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "128176": {
1412
+ "content": "<|reserved_special_token_168|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "128177": {
1420
+ "content": "<|reserved_special_token_169|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "128178": {
1428
+ "content": "<|reserved_special_token_170|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "128179": {
1436
+ "content": "<|reserved_special_token_171|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "128180": {
1444
+ "content": "<|reserved_special_token_172|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "128181": {
1452
+ "content": "<|reserved_special_token_173|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "128182": {
1460
+ "content": "<|reserved_special_token_174|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "128183": {
1468
+ "content": "<|reserved_special_token_175|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "128184": {
1476
+ "content": "<|reserved_special_token_176|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "128185": {
1484
+ "content": "<|reserved_special_token_177|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "128186": {
1492
+ "content": "<|reserved_special_token_178|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "128187": {
1500
+ "content": "<|reserved_special_token_179|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "128188": {
1508
+ "content": "<|reserved_special_token_180|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "128189": {
1516
+ "content": "<|reserved_special_token_181|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "128190": {
1524
+ "content": "<|reserved_special_token_182|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "128191": {
1532
+ "content": "<|reserved_special_token_183|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "128192": {
1540
+ "content": "<|reserved_special_token_184|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "128193": {
1548
+ "content": "<|reserved_special_token_185|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "128194": {
1556
+ "content": "<|reserved_special_token_186|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "128195": {
1564
+ "content": "<|reserved_special_token_187|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "128196": {
1572
+ "content": "<|reserved_special_token_188|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "128197": {
1580
+ "content": "<|reserved_special_token_189|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "128198": {
1588
+ "content": "<|reserved_special_token_190|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "128199": {
1596
+ "content": "<|reserved_special_token_191|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "128200": {
1604
+ "content": "<|reserved_special_token_192|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "128201": {
1612
+ "content": "<|reserved_special_token_193|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "128202": {
1620
+ "content": "<|reserved_special_token_194|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "128203": {
1628
+ "content": "<|reserved_special_token_195|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "128204": {
1636
+ "content": "<|reserved_special_token_196|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "128205": {
1644
+ "content": "<|reserved_special_token_197|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "128206": {
1652
+ "content": "<|reserved_special_token_198|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "128207": {
1660
+ "content": "<|reserved_special_token_199|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "128208": {
1668
+ "content": "<|reserved_special_token_200|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "128209": {
1676
+ "content": "<|reserved_special_token_201|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "128210": {
1684
+ "content": "<|reserved_special_token_202|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "128211": {
1692
+ "content": "<|reserved_special_token_203|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "128212": {
1700
+ "content": "<|reserved_special_token_204|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "128213": {
1708
+ "content": "<|reserved_special_token_205|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "128214": {
1716
+ "content": "<|reserved_special_token_206|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "128215": {
1724
+ "content": "<|reserved_special_token_207|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "128216": {
1732
+ "content": "<|reserved_special_token_208|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "128217": {
1740
+ "content": "<|reserved_special_token_209|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "128218": {
1748
+ "content": "<|reserved_special_token_210|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "128219": {
1756
+ "content": "<|reserved_special_token_211|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "128220": {
1764
+ "content": "<|reserved_special_token_212|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "128221": {
1772
+ "content": "<|reserved_special_token_213|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "128222": {
1780
+ "content": "<|reserved_special_token_214|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "128223": {
1788
+ "content": "<|reserved_special_token_215|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "128224": {
1796
+ "content": "<|reserved_special_token_216|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "128225": {
1804
+ "content": "<|reserved_special_token_217|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "128226": {
1812
+ "content": "<|reserved_special_token_218|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "128227": {
1820
+ "content": "<|reserved_special_token_219|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "128228": {
1828
+ "content": "<|reserved_special_token_220|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "128229": {
1836
+ "content": "<|reserved_special_token_221|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "128230": {
1844
+ "content": "<|reserved_special_token_222|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "128231": {
1852
+ "content": "<|reserved_special_token_223|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "128232": {
1860
+ "content": "<|reserved_special_token_224|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "128233": {
1868
+ "content": "<|reserved_special_token_225|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "128234": {
1876
+ "content": "<|reserved_special_token_226|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "128235": {
1884
+ "content": "<|reserved_special_token_227|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "128236": {
1892
+ "content": "<|reserved_special_token_228|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "128237": {
1900
+ "content": "<|reserved_special_token_229|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "128238": {
1908
+ "content": "<|reserved_special_token_230|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "128239": {
1916
+ "content": "<|reserved_special_token_231|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "128240": {
1924
+ "content": "<|reserved_special_token_232|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "128241": {
1932
+ "content": "<|reserved_special_token_233|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "128242": {
1940
+ "content": "<|reserved_special_token_234|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "128243": {
1948
+ "content": "<|reserved_special_token_235|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "128244": {
1956
+ "content": "<|reserved_special_token_236|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "128245": {
1964
+ "content": "<|reserved_special_token_237|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "128246": {
1972
+ "content": "<|reserved_special_token_238|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "128247": {
1980
+ "content": "<|reserved_special_token_239|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "128248": {
1988
+ "content": "<|reserved_special_token_240|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "128249": {
1996
+ "content": "<|reserved_special_token_241|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "128250": {
2004
+ "content": "<|reserved_special_token_242|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "128251": {
2012
+ "content": "<|reserved_special_token_243|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "128252": {
2020
+ "content": "<|reserved_special_token_244|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "128253": {
2028
+ "content": "<|reserved_special_token_245|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "128254": {
2036
+ "content": "<|reserved_special_token_246|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "128255": {
2044
+ "content": "<|reserved_special_token_247|>",
2045
+ "lstrip": false,
2046
+ "normalized": false,
2047
+ "rstrip": false,
2048
+ "single_word": false,
2049
+ "special": true
2050
+ }
2051
+ },
2052
+ "bos_token": "<|begin_of_text|>",
2053
+ "clean_up_tokenization_spaces": true,
2054
+ "eos_token": "<|end_of_text|>",
2055
+ "extra_special_tokens": {},
2056
+ "model_input_names": [
2057
+ "input_ids",
2058
+ "attention_mask"
2059
+ ],
2060
+ "model_max_length": 131072,
2061
+ "pad_token": "<|end_of_text|>",
2062
+ "processor_class": "CsmProcessor",
2063
+ "tokenizer_class": "PreTrainedTokenizer"
2064
+ }