AIFunOver commited on
Commit
9492b65
1 Parent(s): e3e96d4

Upload openvino_detokenizer.xml with huggingface_hub

Browse files
Files changed (1) hide show
  1. openvino_detokenizer.xml +120 -0
openvino_detokenizer.xml ADDED
@@ -0,0 +1,120 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ <?xml version="1.0"?>
2
+ <net name="detokenizer" version="11">
3
+ <layers>
4
+ <layer id="0" name="Parameter_1357472" type="Parameter" version="opset1">
5
+ <data shape="?,?" element_type="i64" />
6
+ <output>
7
+ <port id="0" precision="I64" names="Parameter_1357472">
8
+ <dim>-1</dim>
9
+ <dim>-1</dim>
10
+ </port>
11
+ </output>
12
+ </layer>
13
+ <layer id="1" name="Constant_1357399" type="Const" version="opset1">
14
+ <data element_type="u8" shape="1018544" offset="0" size="1018544" />
15
+ <output>
16
+ <port id="0" precision="U8">
17
+ <dim>1018544</dim>
18
+ </port>
19
+ </output>
20
+ </layer>
21
+ <layer id="2" name="Convert_1357482" type="Convert" version="opset1">
22
+ <data destination_type="i32" />
23
+ <input>
24
+ <port id="0" precision="I64">
25
+ <dim>-1</dim>
26
+ <dim>-1</dim>
27
+ </port>
28
+ </input>
29
+ <output>
30
+ <port id="1" precision="I32">
31
+ <dim>-1</dim>
32
+ <dim>-1</dim>
33
+ </port>
34
+ </output>
35
+ </layer>
36
+ <layer id="3" name="SentencepieceDetokenizer_1357473" type="SentencepieceDetokenizer" version="extension">
37
+ <input>
38
+ <port id="0" precision="U8">
39
+ <dim>1018544</dim>
40
+ </port>
41
+ <port id="1" precision="I32">
42
+ <dim>-1</dim>
43
+ <dim>-1</dim>
44
+ </port>
45
+ </input>
46
+ <output>
47
+ <port id="2" precision="I32">
48
+ <dim>-1</dim>
49
+ </port>
50
+ <port id="3" precision="I32">
51
+ <dim>-1</dim>
52
+ </port>
53
+ <port id="4" precision="U8">
54
+ <dim>-1</dim>
55
+ </port>
56
+ </output>
57
+ </layer>
58
+ <layer id="4" name="StringTensorPack_1357474" type="StringTensorPack" version="extension">
59
+ <data mode="begins_ends" />
60
+ <input>
61
+ <port id="0" precision="I32">
62
+ <dim>-1</dim>
63
+ </port>
64
+ <port id="1" precision="I32">
65
+ <dim>-1</dim>
66
+ </port>
67
+ <port id="2" precision="U8">
68
+ <dim>-1</dim>
69
+ </port>
70
+ </input>
71
+ <output>
72
+ <port id="3" precision="STRING" names="string_output">
73
+ <dim>-1</dim>
74
+ </port>
75
+ </output>
76
+ </layer>
77
+ <layer id="5" name="Result_1357475" type="Result" version="opset1">
78
+ <input>
79
+ <port id="0" precision="STRING">
80
+ <dim>-1</dim>
81
+ </port>
82
+ </input>
83
+ </layer>
84
+ </layers>
85
+ <edges>
86
+ <edge from-layer="0" from-port="0" to-layer="2" to-port="0" />
87
+ <edge from-layer="1" from-port="0" to-layer="3" to-port="0" />
88
+ <edge from-layer="2" from-port="1" to-layer="3" to-port="1" />
89
+ <edge from-layer="3" from-port="2" to-layer="4" to-port="0" />
90
+ <edge from-layer="3" from-port="3" to-layer="4" to-port="1" />
91
+ <edge from-layer="3" from-port="4" to-layer="4" to-port="2" />
92
+ <edge from-layer="4" from-port="3" to-layer="5" to-port="0" />
93
+ </edges>
94
+ <rt_info>
95
+ <add_attention_mask value="True" />
96
+ <add_prefix_space />
97
+ <add_special_tokens value="True" />
98
+ <chat_template value="{% for message in messages %}{% if loop.first %}[gMASK]sop&lt;|{{ message['role'] }}|>&#10; {{ message['content'] }}{% else %}&lt;|{{ message['role'] }}|>&#10; {{ message['content'] }}{% endif %}{% endfor %}{% if add_generation_prompt %}&lt;|assistant|>{% endif %}" />
99
+ <clean_up_tokenization_spaces value="False" />
100
+ <detokenizer_input_type value="i64" />
101
+ <eos_token_id value="2" />
102
+ <handle_special_tokens_with_re value="True" />
103
+ <number_of_inputs value="1" />
104
+ <openvino_tokenizers_version value="2024.5.0.0.dev20241030" />
105
+ <openvino_version value="2024.5.0.dev20241030" />
106
+ <original_tokenizer_class value="&lt;class 'transformers_modules.THUDM.chatglm3-6b.67d005d386a01d4825649743f41e90f83edd6094.tokenization_chatglm.ChatGLMTokenizer'>" />
107
+ <pad_token_id value="0" />
108
+ <sentencepiece_version value="0.2.0" />
109
+ <skip_special_tokens value="True" />
110
+ <streaming_detokenizer value="False" />
111
+ <tiktoken_version value="0.8.0" />
112
+ <tokenizer_output_type value="i64" />
113
+ <tokenizers_version value="0.20.1" />
114
+ <transformers_version value="4.45.2" />
115
+ <use_max_padding value="False" />
116
+ <use_sentencepiece_backend value="False" />
117
+ <utf8_replace_mode />
118
+ <with_detokenizer value="True" />
119
+ </rt_info>
120
+ </net>