Hugging Face's logo

AIFunOver
/
Qwen2.5-Coder-7B-Instruct-openvino-4bit

Text Generation
Transformers
Safetensors
OpenVINO
English
qwen2
code
codeqwen
chat
qwen
qwen-coder
nncf
4-bit precision
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
AIFunOver commited on
Commit
30e3e21
·
verified ·
1 Parent(s): 6fe5188

Upload openvino_detokenizer.xml with huggingface_hub

Browse files
Files changed (1) hide show
  1. openvino_detokenizer.xml +11 -11
openvino_detokenizer.xml CHANGED
@@ -1,16 +1,16 @@
1
  <?xml version="1.0"?>
2
  <net name="detokenizer" version="11">
3
  <layers>
4
- <layer id="0" name="Parameter_1949814" type="Parameter" version="opset1">
5
  <data shape="?,?" element_type="i64" />
6
  <output>
7
- <port id="0" precision="I64" names="Parameter_1949814">
8
  <dim>-1</dim>
9
  <dim>-1</dim>
10
  </port>
11
  </output>
12
  </layer>
13
- <layer id="1" name="Convert_1949825" type="Convert" version="opset1">
14
  <data destination_type="i32" />
15
  <input>
16
  <port id="0" precision="I64">
@@ -25,7 +25,7 @@
25
  </port>
26
  </output>
27
  </layer>
28
- <layer id="2" name="Constant_1949789" type="Const" version="opset1">
29
  <data element_type="u8" shape="1582931" offset="0" size="1582931" />
30
  <output>
31
  <port id="0" precision="U8">
@@ -33,7 +33,7 @@
33
  </port>
34
  </output>
35
  </layer>
36
- <layer id="3" name="StringTensorUnpack_1949790" type="StringTensorUnpack" version="extension">
37
  <data mode="begins_ends" />
38
  <input>
39
  <port id="0" precision="U8">
@@ -52,7 +52,7 @@
52
  </port>
53
  </output>
54
  </layer>
55
- <layer id="4" name="VocabDecoder_1949815" type="VocabDecoder" version="extension">
56
  <data skip_tokens="151643, 151644, 151645, 151646, 151647, 151648, 151649, 151650, 151651, 151652, 151653, 151654, 151655, 151656" />
57
  <input>
58
  <port id="0" precision="I32">
@@ -87,7 +87,7 @@
87
  </port>
88
  </output>
89
  </layer>
90
- <layer id="5" name="FuzeRagged_1949816" type="FuzeRagged" version="extension">
91
  <input>
92
  <port id="0" precision="I32">
93
  <dim>-1</dim>
@@ -111,7 +111,7 @@
111
  </port>
112
  </output>
113
  </layer>
114
- <layer id="6" name="StringTensorPack_1949817" type="StringTensorPack" version="extension">
115
  <data mode="begins_ends" />
116
  <input>
117
  <port id="0" precision="I32">
@@ -130,7 +130,7 @@
130
  </port>
131
  </output>
132
  </layer>
133
- <layer id="7" name="Result_1949818" type="Result" version="opset1">
134
  <input>
135
  <port id="0" precision="STRING">
136
  <dim>-1</dim>
@@ -164,8 +164,8 @@
164
  <eos_token_id value="151645" />
165
  <handle_special_tokens_with_re />
166
  <number_of_inputs value="1" />
167
- <openvino_tokenizers_version value="2024.5.0.0.dev20241030" />
168
- <openvino_version value="2024.5.0.dev20241030" />
169
  <original_tokenizer_class value="&lt;class 'transformers.models.qwen2.tokenization_qwen2_fast.Qwen2TokenizerFast'>" />
170
  <pad_token_id value="151643" />
171
  <sentencepiece_version value="0.2.0" />
 
1
  <?xml version="1.0"?>
2
  <net name="detokenizer" version="11">
3
  <layers>
4
+ <layer id="0" name="Parameter_690378" type="Parameter" version="opset1">
5
  <data shape="?,?" element_type="i64" />
6
  <output>
7
+ <port id="0" precision="I64" names="Parameter_690378">
8
  <dim>-1</dim>
9
  <dim>-1</dim>
10
  </port>
11
  </output>
12
  </layer>
13
+ <layer id="1" name="Convert_690389" type="Convert" version="opset1">
14
  <data destination_type="i32" />
15
  <input>
16
  <port id="0" precision="I64">
 
25
  </port>
26
  </output>
27
  </layer>
28
+ <layer id="2" name="Constant_690353" type="Const" version="opset1">
29
  <data element_type="u8" shape="1582931" offset="0" size="1582931" />
30
  <output>
31
  <port id="0" precision="U8">
 
33
  </port>
34
  </output>
35
  </layer>
36
+ <layer id="3" name="StringTensorUnpack_690354" type="StringTensorUnpack" version="extension">
37
  <data mode="begins_ends" />
38
  <input>
39
  <port id="0" precision="U8">
 
52
  </port>
53
  </output>
54
  </layer>
55
+ <layer id="4" name="VocabDecoder_690379" type="VocabDecoder" version="extension">
56
  <data skip_tokens="151643, 151644, 151645, 151646, 151647, 151648, 151649, 151650, 151651, 151652, 151653, 151654, 151655, 151656" />
57
  <input>
58
  <port id="0" precision="I32">
 
87
  </port>
88
  </output>
89
  </layer>
90
+ <layer id="5" name="FuzeRagged_690380" type="FuzeRagged" version="extension">
91
  <input>
92
  <port id="0" precision="I32">
93
  <dim>-1</dim>
 
111
  </port>
112
  </output>
113
  </layer>
114
+ <layer id="6" name="StringTensorPack_690381" type="StringTensorPack" version="extension">
115
  <data mode="begins_ends" />
116
  <input>
117
  <port id="0" precision="I32">
 
130
  </port>
131
  </output>
132
  </layer>
133
+ <layer id="7" name="Result_690382" type="Result" version="opset1">
134
  <input>
135
  <port id="0" precision="STRING">
136
  <dim>-1</dim>
 
164
  <eos_token_id value="151645" />
165
  <handle_special_tokens_with_re />
166
  <number_of_inputs value="1" />
167
+ <openvino_tokenizers_version value="2025.0.0.0.dev20241112" />
168
+ <openvino_version value="2025.0.0.dev20241112" />
169
  <original_tokenizer_class value="&lt;class 'transformers.models.qwen2.tokenization_qwen2_fast.Qwen2TokenizerFast'>" />
170
  <pad_token_id value="151643" />
171
  <sentencepiece_version value="0.2.0" />