Hugging Face's logo

rippertnt
/
Phi-4-mini-it-ov-sym-int4

OpenVINO
phi3
custom_code
Model card Files Community
rippertnt commited on
Commit
f444965
·
verified ·
1 Parent(s): 8880432

Upload 15 files

Browse files
Files changed (16) hide show
  1. .gitattributes +1 -0
  2. added_tokens.json +12 -0
  3. config.json +144 -0
  4. generation_config.json +10 -0
  5. merges.txt +0 -0
  6. openvino_config.json +27 -0
  7. openvino_detokenizer.bin +3 -0
  8. openvino_detokenizer.xml +220 -0
  9. openvino_model.bin +3 -0
  10. openvino_model.xml +0 -0
  11. openvino_tokenizer.bin +3 -0
  12. openvino_tokenizer.xml +686 -0
  13. special_tokens_map.json +30 -0
  14. tokenizer.json +3 -0
  15. tokenizer_config.json +112 -0
  16. vocab.json +0 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
added_tokens.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<|/tool_call|>": 200026,
3
+ "<|/tool|>": 200024,
4
+ "<|assistant|>": 200019,
5
+ "<|end|>": 200020,
6
+ "<|system|>": 200022,
7
+ "<|tag|>": 200028,
8
+ "<|tool_call|>": 200025,
9
+ "<|tool_response|>": 200027,
10
+ "<|tool|>": 200023,
11
+ "<|user|>": 200021
12
+ }
config.json ADDED
@@ -0,0 +1,144 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_attn_implementation_autoset": true,
3
+ "architectures": [
4
+ "Phi3ForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "auto_map": {
9
+ "AutoConfig": "microsoft/Phi-4-mini-instruct--configuration_phi3.Phi3Config",
10
+ "AutoModelForCausalLM": "microsoft/Phi-4-mini-instruct--modeling_phi3.Phi3ForCausalLM",
11
+ "AutoTokenizer": "microsoft/Phi-4-mini-instruct--Xenova/gpt-4o"
12
+ },
13
+ "bos_token_id": 199999,
14
+ "embd_pdrop": 0.0,
15
+ "eos_token_id": 199999,
16
+ "full_attn_mod": 1,
17
+ "hidden_act": "silu",
18
+ "hidden_size": 3072,
19
+ "initializer_range": 0.02,
20
+ "intermediate_size": 8192,
21
+ "interpolate_factor": 1,
22
+ "lm_head_bias": false,
23
+ "max_position_embeddings": 131072,
24
+ "mlp_bias": false,
25
+ "model_type": "phi3",
26
+ "num_attention_heads": 24,
27
+ "num_hidden_layers": 32,
28
+ "num_key_value_heads": 8,
29
+ "original_max_position_embeddings": 4096,
30
+ "pad_token_id": 199999,
31
+ "partial_rotary_factor": 0.75,
32
+ "resid_pdrop": 0.0,
33
+ "rms_norm_eps": 1e-05,
34
+ "rope_scaling": {
35
+ "long_factor": [
36
+ 1,
37
+ 1.118320672,
38
+ 1.250641126,
39
+ 1.398617824,
40
+ 1.564103225,
41
+ 1.74916897,
42
+ 1.956131817,
43
+ 2.187582649,
44
+ 2.446418898,
45
+ 2.735880826,
46
+ 3.059592084,
47
+ 3.421605075,
48
+ 3.826451687,
49
+ 4.279200023,
50
+ 4.785517845,
51
+ 5.351743533,
52
+ 5.984965424,
53
+ 6.693110555,
54
+ 7.485043894,
55
+ 8.370679318,
56
+ 9.36110372,
57
+ 10.4687158,
58
+ 11.70738129,
59
+ 13.09260651,
60
+ 14.64173252,
61
+ 16.37415215,
62
+ 18.31155283,
63
+ 20.47818807,
64
+ 22.90118105,
65
+ 25.61086418,
66
+ 28.64115884,
67
+ 32.03,
68
+ 32.1,
69
+ 32.13,
70
+ 32.23,
71
+ 32.6,
72
+ 32.61,
73
+ 32.64,
74
+ 32.66,
75
+ 32.7,
76
+ 32.71,
77
+ 32.93,
78
+ 32.97,
79
+ 33.28,
80
+ 33.49,
81
+ 33.5,
82
+ 44.16,
83
+ 47.77
84
+ ],
85
+ "short_factor": [
86
+ 1.0,
87
+ 1.0,
88
+ 1.0,
89
+ 1.0,
90
+ 1.0,
91
+ 1.0,
92
+ 1.0,
93
+ 1.0,
94
+ 1.0,
95
+ 1.0,
96
+ 1.0,
97
+ 1.0,
98
+ 1.0,
99
+ 1.0,
100
+ 1.0,
101
+ 1.0,
102
+ 1.0,
103
+ 1.0,
104
+ 1.0,
105
+ 1.0,
106
+ 1.0,
107
+ 1.0,
108
+ 1.0,
109
+ 1.0,
110
+ 1.0,
111
+ 1.0,
112
+ 1.0,
113
+ 1.0,
114
+ 1.0,
115
+ 1.0,
116
+ 1.0,
117
+ 1.0,
118
+ 1.0,
119
+ 1.0,
120
+ 1.0,
121
+ 1.0,
122
+ 1.0,
123
+ 1.0,
124
+ 1.0,
125
+ 1.0,
126
+ 1.0,
127
+ 1.0,
128
+ 1.0,
129
+ 1.0,
130
+ 1.0,
131
+ 1.0,
132
+ 1.0,
133
+ 1.0
134
+ ],
135
+ "type": "longrope"
136
+ },
137
+ "rope_theta": 10000.0,
138
+ "sliding_window": 262144,
139
+ "tie_word_embeddings": true,
140
+ "torch_dtype": "bfloat16",
141
+ "transformers_version": "4.51.3",
142
+ "use_cache": true,
143
+ "vocab_size": 200064
144
+ }
generation_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 199999,
4
+ "eos_token_id": [
5
+ 200020,
6
+ 199999
7
+ ],
8
+ "pad_token_id": 199999,
9
+ "transformers_version": "4.51.3"
10
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
openvino_config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dtype": "int4",
3
+ "input_info": null,
4
+ "optimum_version": "1.25.3",
5
+ "quantization_config": {
6
+ "all_layers": null,
7
+ "backup_precision": null,
8
+ "bits": 4,
9
+ "dataset": "auto",
10
+ "dtype": "int4",
11
+ "gptq": null,
12
+ "group_size": 128,
13
+ "ignored_scope": null,
14
+ "lora_correction": null,
15
+ "num_samples": null,
16
+ "processor": null,
17
+ "quant_method": "awq",
18
+ "ratio": 1.0,
19
+ "scale_estimation": null,
20
+ "sensitivity_metric": null,
21
+ "sym": true,
22
+ "tokenizer": null,
23
+ "trust_remote_code": false
24
+ },
25
+ "save_onnx_model": false,
26
+ "transformers_version": "4.51.3"
27
+ }
openvino_detokenizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58ec20da66d1d780b298f3cdcf252ccc0e228636fc7bee219163af81f1837e0a
3
+ size 2998349
openvino_detokenizer.xml ADDED
@@ -0,0 +1,220 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ <?xml version="1.0"?>
2
+ <net name="detokenizer" version="11">
3
+ <layers>
4
+ <layer id="0" name="Parameter_170637" type="Parameter" version="opset1">
5
+ <data shape="?,?" element_type="i64" />
6
+ <output>
7
+ <port id="0" precision="I64" names="Parameter_170637">
8
+ <dim>-1</dim>
9
+ <dim>-1</dim>
10
+ </port>
11
+ </output>
12
+ </layer>
13
+ <layer id="1" name="Convert_170807" type="Convert" version="opset1">
14
+ <data destination_type="i32" />
15
+ <input>
16
+ <port id="0" precision="I64">
17
+ <dim>-1</dim>
18
+ <dim>-1</dim>
19
+ </port>
20
+ </input>
21
+ <output>
22
+ <port id="1" precision="I32">
23
+ <dim>-1</dim>
24
+ <dim>-1</dim>
25
+ </port>
26
+ </output>
27
+ </layer>
28
+ <layer id="2" name="Constant_170639" type="Const" version="opset1">
29
+ <data element_type="i32" shape="200029" offset="0" size="800116" />
30
+ <output>
31
+ <port id="0" precision="I32">
32
+ <dim>200029</dim>
33
+ </port>
34
+ </output>
35
+ </layer>
36
+ <layer id="3" name="Constant_170641" type="Const" version="opset1">
37
+ <data element_type="i32" shape="200029" offset="800116" size="800116" />
38
+ <output>
39
+ <port id="0" precision="I32">
40
+ <dim>200029</dim>
41
+ </port>
42
+ </output>
43
+ </layer>
44
+ <layer id="4" name="Constant_170643" type="Const" version="opset1">
45
+ <data element_type="u8" shape="1398089" offset="1600232" size="1398089" />
46
+ <output>
47
+ <port id="0" precision="U8">
48
+ <dim>1398089</dim>
49
+ </port>
50
+ </output>
51
+ </layer>
52
+ <layer id="5" name="Slice_170648" type="Const" version="opset1">
53
+ <data element_type="i32" shape="7" offset="2998321" size="28" />
54
+ <output>
55
+ <port id="0" precision="I32">
56
+ <dim>7</dim>
57
+ </port>
58
+ </output>
59
+ </layer>
60
+ <layer id="6" name="VocabDecoder_170650" type="VocabDecoder" version="extension">
61
+ <data skip_tokens="" />
62
+ <input>
63
+ <port id="0" precision="I32">
64
+ <dim>-1</dim>
65
+ <dim>-1</dim>
66
+ </port>
67
+ <port id="1" precision="I32">
68
+ <dim>200029</dim>
69
+ </port>
70
+ <port id="2" precision="I32">
71
+ <dim>200029</dim>
72
+ </port>
73
+ <port id="3" precision="U8">
74
+ <dim>1398089</dim>
75
+ </port>
76
+ <port id="4" precision="I32">
77
+ <dim>7</dim>
78
+ </port>
79
+ </input>
80
+ <output>
81
+ <port id="5" precision="I32">
82
+ <dim>-1</dim>
83
+ </port>
84
+ <port id="6" precision="I32">
85
+ <dim>-1</dim>
86
+ </port>
87
+ <port id="7" precision="I32">
88
+ <dim>-1</dim>
89
+ </port>
90
+ <port id="8" precision="I32">
91
+ <dim>-1</dim>
92
+ </port>
93
+ <port id="9" precision="U8">
94
+ <dim>-1</dim>
95
+ </port>
96
+ </output>
97
+ </layer>
98
+ <layer id="7" name="FuzeRagged_170651" type="FuzeRagged" version="extension">
99
+ <input>
100
+ <port id="0" precision="I32">
101
+ <dim>-1</dim>
102
+ </port>
103
+ <port id="1" precision="I32">
104
+ <dim>-1</dim>
105
+ </port>
106
+ <port id="2" precision="I32">
107
+ <dim>-1</dim>
108
+ </port>
109
+ <port id="3" precision="I32">
110
+ <dim>-1</dim>
111
+ </port>
112
+ </input>
113
+ <output>
114
+ <port id="4" precision="I32">
115
+ <dim>-1</dim>
116
+ </port>
117
+ <port id="5" precision="I32">
118
+ <dim>-1</dim>
119
+ </port>
120
+ </output>
121
+ </layer>
122
+ <layer id="8" name="UTF8Validate_170652" type="UTF8Validate" version="extension">
123
+ <data replace_mode="true" />
124
+ <input>
125
+ <port id="0" precision="I32">
126
+ <dim>-1</dim>
127
+ </port>
128
+ <port id="1" precision="I32">
129
+ <dim>-1</dim>
130
+ </port>
131
+ <port id="2" precision="U8">
132
+ <dim>-1</dim>
133
+ </port>
134
+ </input>
135
+ <output>
136
+ <port id="3" precision="I32">
137
+ <dim>-1</dim>
138
+ </port>
139
+ <port id="4" precision="I32">
140
+ <dim>-1</dim>
141
+ </port>
142
+ <port id="5" precision="U8">
143
+ <dim>-1</dim>
144
+ </port>
145
+ </output>
146
+ </layer>
147
+ <layer id="9" name="StringTensorPack_170653" type="StringTensorPack" version="opset15">
148
+ <input>
149
+ <port id="0" precision="I32">
150
+ <dim>-1</dim>
151
+ </port>
152
+ <port id="1" precision="I32">
153
+ <dim>-1</dim>
154
+ </port>
155
+ <port id="2" precision="U8">
156
+ <dim>-1</dim>
157
+ </port>
158
+ </input>
159
+ <output>
160
+ <port id="3" precision="STRING" names="Result_170654,string_output">
161
+ <dim>-1</dim>
162
+ </port>
163
+ </output>
164
+ </layer>
165
+ <layer id="10" name="Result_170654" type="Result" version="opset1" output_names="Result_170654,string_output">
166
+ <input>
167
+ <port id="0" precision="STRING">
168
+ <dim>-1</dim>
169
+ </port>
170
+ </input>
171
+ </layer>
172
+ </layers>
173
+ <edges>
174
+ <edge from-layer="0" from-port="0" to-layer="1" to-port="0" />
175
+ <edge from-layer="1" from-port="1" to-layer="6" to-port="0" />
176
+ <edge from-layer="2" from-port="0" to-layer="6" to-port="1" />
177
+ <edge from-layer="3" from-port="0" to-layer="6" to-port="2" />
178
+ <edge from-layer="4" from-port="0" to-layer="6" to-port="3" />
179
+ <edge from-layer="5" from-port="0" to-layer="6" to-port="4" />
180
+ <edge from-layer="6" from-port="7" to-layer="7" to-port="2" />
181
+ <edge from-layer="6" from-port="9" to-layer="8" to-port="2" />
182
+ <edge from-layer="6" from-port="8" to-layer="7" to-port="3" />
183
+ <edge from-layer="6" from-port="6" to-layer="7" to-port="1" />
184
+ <edge from-layer="6" from-port="5" to-layer="7" to-port="0" />
185
+ <edge from-layer="7" from-port="4" to-layer="8" to-port="0" />
186
+ <edge from-layer="7" from-port="5" to-layer="8" to-port="1" />
187
+ <edge from-layer="8" from-port="3" to-layer="9" to-port="0" />
188
+ <edge from-layer="8" from-port="4" to-layer="9" to-port="1" />
189
+ <edge from-layer="8" from-port="5" to-layer="9" to-port="2" />
190
+ <edge from-layer="9" from-port="3" to-layer="10" to-port="0" />
191
+ </edges>
192
+ <rt_info>
193
+ <add_attention_mask value="True" />
194
+ <add_prefix_space />
195
+ <add_special_tokens value="True" />
196
+ <bos_token_id value="199999" />
197
+ <chat_template value="{% for message in messages %}{% if message['role'] == 'system' and 'tools' in message and message['tools'] is not none %}{{ '&lt;|' + message['role'] + '|>' + message['content'] + '&lt;|tool|>' + message['tools'] + '&lt;|/tool|>' + '&lt;|end|>' }}{% else %}{{ '&lt;|' + message['role'] + '|>' + message['content'] + '&lt;|end|>' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '&lt;|assistant|>' }}{% else %}{{ eos_token }}{% endif %}" />
198
+ <clean_up_tokenization_spaces />
199
+ <detokenizer_input_type value="i64" />
200
+ <eos_token_id value="199999" />
201
+ <handle_special_tokens_with_re />
202
+ <max_length />
203
+ <number_of_inputs value="1" />
204
+ <openvino_tokenizers_version value="2025.1.0.0-523-710ddf14de8" />
205
+ <openvino_version value="2025.1.0-18503-6fec06580ab-releases/2025/1" />
206
+ <original_tokenizer_class value="&lt;class 'transformers.models.gpt2.tokenization_gpt2_fast.GPT2TokenizerFast'>" />
207
+ <pad_token_id value="199999" />
208
+ <sentencepiece_version value="0.2.0" />
209
+ <skip_special_tokens value="True" />
210
+ <streaming_detokenizer value="False" />
211
+ <tiktoken_version value="0.9.0" />
212
+ <tokenizer_output_type value="i64" />
213
+ <tokenizers_version value="0.21.1" />
214
+ <transformers_version value="4.51.3" />
215
+ <use_max_padding value="False" />
216
+ <use_sentencepiece_backend value="False" />
217
+ <utf8_replace_mode value="replace" />
218
+ <with_detokenizer value="True" />
219
+ </rt_info>
220
+ </net>
openvino_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c379f7d44b0bc02b14f72d46aa2b4e6265d746bbd42a874ecc2dec639ba5313e
3
+ size 2228378220
openvino_model.xml ADDED
The diff for this file is too large to render. See raw diff
 
openvino_tokenizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:818537d6633196e2f45e51017a6320010ca3c06120460c14028a6c325f92f477
3
+ size 7602768
openvino_tokenizer.xml ADDED
@@ -0,0 +1,686 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ <?xml version="1.0"?>
2
+ <net name="tokenizer" version="11">
3
+ <layers>
4
+ <layer id="0" name="Parameter_170519" type="Parameter" version="opset1">
5
+ <data shape="?" element_type="string" />
6
+ <output>
7
+ <port id="0" precision="STRING" names="Parameter_170519">
8
+ <dim>-1</dim>
9
+ </port>
10
+ </output>
11
+ </layer>
12
+ <layer id="1" name="Constant_170525" type="Const" version="opset1">
13
+ <data element_type="i64" shape="" offset="0" size="8" />
14
+ <output>
15
+ <port id="0" precision="I64" />
16
+ </output>
17
+ </layer>
18
+ <layer id="2" name="StringTensorUnpack_170520" type="StringTensorUnpack" version="opset15">
19
+ <input>
20
+ <port id="0" precision="STRING">
21
+ <dim>-1</dim>
22
+ </port>
23
+ </input>
24
+ <output>
25
+ <port id="1" precision="I32">
26
+ <dim>-1</dim>
27
+ </port>
28
+ <port id="2" precision="I32">
29
+ <dim>-1</dim>
30
+ </port>
31
+ <port id="3" precision="U8">
32
+ <dim>-1</dim>
33
+ </port>
34
+ </output>
35
+ </layer>
36
+ <layer id="3" name="ShapeOf_170521" type="ShapeOf" version="opset3">
37
+ <data output_type="i64" />
38
+ <input>
39
+ <port id="0" precision="I32">
40
+ <dim>-1</dim>
41
+ </port>
42
+ </input>
43
+ <output>
44
+ <port id="1" precision="I64">
45
+ <dim>1</dim>
46
+ </port>
47
+ </output>
48
+ </layer>
49
+ <layer id="4" name="Constant_170522" type="Const" version="opset1">
50
+ <data element_type="i64" shape="" offset="0" size="8" />
51
+ <output>
52
+ <port id="0" precision="I64" />
53
+ </output>
54
+ </layer>
55
+ <layer id="5" name="Constant_170523" type="Const" version="opset1">
56
+ <data element_type="i64" shape="" offset="0" size="8" />
57
+ <output>
58
+ <port id="0" precision="I64" />
59
+ </output>
60
+ </layer>
61
+ <layer id="6" name="Gather_170524" type="Gather" version="opset8">
62
+ <data batch_dims="0" />
63
+ <input>
64
+ <port id="0" precision="I64">
65
+ <dim>1</dim>
66
+ </port>
67
+ <port id="1" precision="I64" />
68
+ <port id="2" precision="I64" />
69
+ </input>
70
+ <output>
71
+ <port id="3" precision="I64" />
72
+ </output>
73
+ </layer>
74
+ <layer id="7" name="Constant_170526" type="Const" version="opset1">
75
+ <data element_type="i64" shape="" offset="8" size="8" />
76
+ <output>
77
+ <port id="0" precision="I64" />
78
+ </output>
79
+ </layer>
80
+ <layer id="8" name="Range_170527" type="Range" version="opset4">
81
+ <data output_type="i32" />
82
+ <input>
83
+ <port id="0" precision="I64" />
84
+ <port id="1" precision="I64" />
85
+ <port id="2" precision="I64" />
86
+ </input>
87
+ <output>
88
+ <port id="3" precision="I32">
89
+ <dim>-1</dim>
90
+ </port>
91
+ </output>
92
+ </layer>
93
+ <layer id="9" name="Constant_170528" type="Const" version="opset1">
94
+ <data element_type="i64" shape="" offset="8" size="8" />
95
+ <output>
96
+ <port id="0" precision="I64" />
97
+ </output>
98
+ </layer>
99
+ <layer id="10" name="Constant_170529" type="Const" version="opset1">
100
+ <data element_type="i64" shape="" offset="8" size="8" />
101
+ <output>
102
+ <port id="0" precision="I64" />
103
+ </output>
104
+ </layer>
105
+ <layer id="11" name="Add_170530" type="Add" version="opset1">
106
+ <data auto_broadcast="numpy" />
107
+ <input>
108
+ <port id="0" precision="I64" />
109
+ <port id="1" precision="I64" />
110
+ </input>
111
+ <output>
112
+ <port id="2" precision="I64" />
113
+ </output>
114
+ </layer>
115
+ <layer id="12" name="Constant_170531" type="Const" version="opset1">
116
+ <data element_type="i64" shape="" offset="8" size="8" />
117
+ <output>
118
+ <port id="0" precision="I64" />
119
+ </output>
120
+ </layer>
121
+ <layer id="13" name="Range_170532" type="Range" version="opset4">
122
+ <data output_type="i32" />
123
+ <input>
124
+ <port id="0" precision="I64" />
125
+ <port id="1" precision="I64" />
126
+ <port id="2" precision="I64" />
127
+ </input>
128
+ <output>
129
+ <port id="3" precision="I32">
130
+ <dim>-1</dim>
131
+ </port>
132
+ </output>
133
+ </layer>
134
+ <layer id="14" name="Constant_170594" type="Const" version="opset1">
135
+ <data element_type="u8" shape="289" offset="16" size="289" />
136
+ <output>
137
+ <port id="0" precision="U8">
138
+ <dim>289</dim>
139
+ </port>
140
+ </output>
141
+ </layer>
142
+ <layer id="15" name="SpecialTokensSplit_170595" type="SpecialTokensSplit" version="extension">
143
+ <input>
144
+ <port id="0" precision="I32">
145
+ <dim>-1</dim>
146
+ </port>
147
+ <port id="1" precision="I32">
148
+ <dim>-1</dim>
149
+ </port>
150
+ <port id="2" precision="I32">
151
+ <dim>-1</dim>
152
+ </port>
153
+ <port id="3" precision="I32">
154
+ <dim>-1</dim>
155
+ </port>
156
+ <port id="4" precision="U8">
157
+ <dim>-1</dim>
158
+ </port>
159
+ <port id="5" precision="U8">
160
+ <dim>289</dim>
161
+ </port>
162
+ </input>
163
+ <output>
164
+ <port id="6" precision="I32">
165
+ <dim>-1</dim>
166
+ </port>
167
+ <port id="7" precision="I32">
168
+ <dim>-1</dim>
169
+ </port>
170
+ <port id="8" precision="I32">
171
+ <dim>-1</dim>
172
+ </port>
173
+ <port id="9" precision="I32">
174
+ <dim>-1</dim>
175
+ </port>
176
+ <port id="10" precision="U8">
177
+ <dim>-1</dim>
178
+ </port>
179
+ <port id="11" precision="BOOL">
180
+ <dim>-1</dim>
181
+ </port>
182
+ </output>
183
+ </layer>
184
+ <layer id="16" name="Constant_170597" type="Const" version="opset1">
185
+ <data element_type="u8" shape="274" offset="305" size="274" />
186
+ <output>
187
+ <port id="0" precision="U8">
188
+ <dim>274</dim>
189
+ </port>
190
+ </output>
191
+ </layer>
192
+ <layer id="17" name="RegexSplit_170598" type="RegexSplit" version="extension">
193
+ <data behaviour="remove" invert="true" max_splits="-1" />
194
+ <input>
195
+ <port id="0" precision="I32">
196
+ <dim>-1</dim>
197
+ </port>
198
+ <port id="1" precision="I32">
199
+ <dim>-1</dim>
200
+ </port>
201
+ <port id="2" precision="I32">
202
+ <dim>-1</dim>
203
+ </port>
204
+ <port id="3" precision="I32">
205
+ <dim>-1</dim>
206
+ </port>
207
+ <port id="4" precision="U8">
208
+ <dim>-1</dim>
209
+ </port>
210
+ <port id="5" precision="BOOL">
211
+ <dim>-1</dim>
212
+ </port>
213
+ <port id="6" precision="U8">
214
+ <dim>274</dim>
215
+ </port>
216
+ </input>
217
+ <output>
218
+ <port id="7" precision="I32">
219
+ <dim>-1</dim>
220
+ </port>
221
+ <port id="8" precision="I32">
222
+ <dim>-1</dim>
223
+ </port>
224
+ <port id="9" precision="I32">
225
+ <dim>-1</dim>
226
+ </port>
227
+ <port id="10" precision="I32">
228
+ <dim>-1</dim>
229
+ </port>
230
+ <port id="11" precision="U8">
231
+ <dim>-1</dim>
232
+ </port>
233
+ <port id="12" precision="BOOL">
234
+ <dim>-1</dim>
235
+ </port>
236
+ </output>
237
+ </layer>
238
+ <layer id="18" name="Constant_170600" type="Const" version="opset1">
239
+ <data element_type="i32" shape="200029" offset="579" size="800116" />
240
+ <output>
241
+ <port id="0" precision="I32">
242
+ <dim>200029</dim>
243
+ </port>
244
+ </output>
245
+ </layer>
246
+ <layer id="19" name="Constant_170602" type="Const" version="opset1">
247
+ <data element_type="i32" shape="200029" offset="800695" size="800116" />
248
+ <output>
249
+ <port id="0" precision="I32">
250
+ <dim>200029</dim>
251
+ </port>
252
+ </output>
253
+ </layer>
254
+ <layer id="20" name="Constant_170604" type="Const" version="opset1">
255
+ <data element_type="u8" shape="1398109" offset="1600811" size="1398109" />
256
+ <output>
257
+ <port id="0" precision="U8">
258
+ <dim>1398109</dim>
259
+ </port>
260
+ </output>
261
+ </layer>
262
+ <layer id="21" name="Constant_170612" type="Const" version="opset1">
263
+ <data element_type="i32" shape="199742" offset="2998920" size="798968" />
264
+ <output>
265
+ <port id="0" precision="I32">
266
+ <dim>199742</dim>
267
+ </port>
268
+ </output>
269
+ </layer>
270
+ <layer id="22" name="Constant_170614" type="Const" version="opset1">
271
+ <data element_type="i32" shape="199742" offset="3797888" size="798968" />
272
+ <output>
273
+ <port id="0" precision="I32">
274
+ <dim>199742</dim>
275
+ </port>
276
+ </output>
277
+ </layer>
278
+ <layer id="23" name="Constant_170616" type="Const" version="opset1">
279
+ <data element_type="u8" shape="718313" offset="4596856" size="718313" />
280
+ <output>
281
+ <port id="0" precision="U8">
282
+ <dim>718313</dim>
283
+ </port>
284
+ </output>
285
+ </layer>
286
+ <layer id="24" name="Constant_170618" type="Const" version="opset1">
287
+ <data element_type="i32" shape="199742" offset="5315169" size="798968" />
288
+ <output>
289
+ <port id="0" precision="I32">
290
+ <dim>199742</dim>
291
+ </port>
292
+ </output>
293
+ </layer>
294
+ <layer id="25" name="Constant_170620" type="Const" version="opset1">
295
+ <data element_type="i32" shape="199742" offset="6114137" size="798968" />
296
+ <output>
297
+ <port id="0" precision="I32">
298
+ <dim>199742</dim>
299
+ </port>
300
+ </output>
301
+ </layer>
302
+ <layer id="26" name="Constant_170622" type="Const" version="opset1">
303
+ <data element_type="u8" shape="679101" offset="6913105" size="679101" />
304
+ <output>
305
+ <port id="0" precision="U8">
306
+ <dim>679101</dim>
307
+ </port>
308
+ </output>
309
+ </layer>
310
+ <layer id="27" name="Constant_170606" type="Const" version="opset1">
311
+ <data element_type="i32" shape="432" offset="7592206" size="1728" />
312
+ <output>
313
+ <port id="0" precision="I32">
314
+ <dim>432</dim>
315
+ </port>
316
+ </output>
317
+ </layer>
318
+ <layer id="28" name="Constant_170608" type="Const" version="opset1">
319
+ <data element_type="i32" shape="432" offset="7593934" size="1728" />
320
+ <output>
321
+ <port id="0" precision="I32">
322
+ <dim>432</dim>
323
+ </port>
324
+ </output>
325
+ </layer>
326
+ <layer id="29" name="Constant_170610" type="Const" version="opset1">
327
+ <data element_type="u8" shape="5366" offset="7595662" size="5366" />
328
+ <output>
329
+ <port id="0" precision="U8">
330
+ <dim>5366</dim>
331
+ </port>
332
+ </output>
333
+ </layer>
334
+ <layer id="30" name="Constant_170623" type="Const" version="opset1">
335
+ <data element_type="i32" shape="432" offset="7601028" size="1728" />
336
+ <output>
337
+ <port id="0" precision="I32">
338
+ <dim>432</dim>
339
+ </port>
340
+ </output>
341
+ </layer>
342
+ <layer id="31" name="BPETokenizer_170624" type="BPETokenizer" version="extension">
343
+ <data unk_token="" fuse_unk="false" suffix_indicator="" end_suffix="" byte_fallback="false" cache_capacity="40003" />
344
+ <input>
345
+ <port id="0" precision="I32">
346
+ <dim>-1</dim>
347
+ </port>
348
+ <port id="1" precision="I32">
349
+ <dim>-1</dim>
350
+ </port>
351
+ <port id="2" precision="I32">
352
+ <dim>-1</dim>
353
+ </port>
354
+ <port id="3" precision="I32">
355
+ <dim>-1</dim>
356
+ </port>
357
+ <port id="4" precision="U8">
358
+ <dim>-1</dim>
359
+ </port>
360
+ <port id="5" precision="I32">
361
+ <dim>200029</dim>
362
+ </port>
363
+ <port id="6" precision="I32">
364
+ <dim>200029</dim>
365
+ </port>
366
+ <port id="7" precision="U8">
367
+ <dim>1398109</dim>
368
+ </port>
369
+ <port id="8" precision="I32">
370
+ <dim>199742</dim>
371
+ </port>
372
+ <port id="9" precision="I32">
373
+ <dim>199742</dim>
374
+ </port>
375
+ <port id="10" precision="U8">
376
+ <dim>718313</dim>
377
+ </port>
378
+ <port id="11" precision="I32">
379
+ <dim>199742</dim>
380
+ </port>
381
+ <port id="12" precision="I32">
382
+ <dim>199742</dim>
383
+ </port>
384
+ <port id="13" precision="U8">
385
+ <dim>679101</dim>
386
+ </port>
387
+ <port id="14" precision="I32">
388
+ <dim>432</dim>
389
+ </port>
390
+ <port id="15" precision="I32">
391
+ <dim>432</dim>
392
+ </port>
393
+ <port id="16" precision="U8">
394
+ <dim>5366</dim>
395
+ </port>
396
+ <port id="17" precision="I32">
397
+ <dim>432</dim>
398
+ </port>
399
+ </input>
400
+ <output>
401
+ <port id="18" precision="I32">
402
+ <dim>-1</dim>
403
+ </port>
404
+ <port id="19" precision="I32">
405
+ <dim>-1</dim>
406
+ </port>
407
+ <port id="20" precision="I32">
408
+ <dim>-1</dim>
409
+ </port>
410
+ </output>
411
+ </layer>
412
+ <layer id="32" name="Subtract_170625" type="Subtract" version="opset1">
413
+ <data auto_broadcast="numpy" />
414
+ <input>
415
+ <port id="0" precision="I32">
416
+ <dim>-1</dim>
417
+ </port>
418
+ <port id="1" precision="I32">
419
+ <dim>-1</dim>
420
+ </port>
421
+ </input>
422
+ <output>
423
+ <port id="2" precision="I32">
424
+ <dim>-1</dim>
425
+ </port>
426
+ </output>
427
+ </layer>
428
+ <layer id="33" name="Constant_170626" type="Const" version="opset1">
429
+ <data element_type="i32" shape="" offset="7602756" size="4" />
430
+ <output>
431
+ <port id="0" precision="I32" />
432
+ </output>
433
+ </layer>
434
+ <layer id="34" name="Minimum_170627" type="Minimum" version="opset1">
435
+ <data auto_broadcast="numpy" />
436
+ <input>
437
+ <port id="0" precision="I32">
438
+ <dim>-1</dim>
439
+ </port>
440
+ <port id="1" precision="I32" />
441
+ </input>
442
+ <output>
443
+ <port id="2" precision="I32">
444
+ <dim>-1</dim>
445
+ </port>
446
+ </output>
447
+ </layer>
448
+ <layer id="35" name="Subtract_170628" type="Subtract" version="opset1">
449
+ <data auto_broadcast="numpy" />
450
+ <input>
451
+ <port id="0" precision="I32">
452
+ <dim>-1</dim>
453
+ </port>
454
+ <port id="1" precision="I32">
455
+ <dim>-1</dim>
456
+ </port>
457
+ </input>
458
+ <output>
459
+ <port id="2" precision="I32">
460
+ <dim>-1</dim>
461
+ </port>
462
+ </output>
463
+ </layer>
464
+ <layer id="36" name="Subtract_170629" type="Subtract" version="opset1">
465
+ <data auto_broadcast="numpy" />
466
+ <input>
467
+ <port id="0" precision="I32">
468
+ <dim>-1</dim>
469
+ </port>
470
+ <port id="1" precision="I32">
471
+ <dim>-1</dim>
472
+ </port>
473
+ </input>
474
+ <output>
475
+ <port id="2" precision="I32">
476
+ <dim>-1</dim>
477
+ </port>
478
+ </output>
479
+ </layer>
480
+ <layer id="37" name="Constant_170630" type="Const" version="opset1">
481
+ <data element_type="i32" shape="" offset="7602760" size="4" />
482
+ <output>
483
+ <port id="0" precision="I32" />
484
+ </output>
485
+ </layer>
486
+ <layer id="38" name="ReduceMax_170631" type="ReduceMax" version="opset1">
487
+ <data keep_dims="false" />
488
+ <input>
489
+ <port id="0" precision="I32">
490
+ <dim>-1</dim>
491
+ </port>
492
+ <port id="1" precision="I32" />
493
+ </input>
494
+ <output>
495
+ <port id="2" precision="I32" />
496
+ </output>
497
+ </layer>
498
+ <layer id="39" name="Constant_170632" type="Const" version="opset1">
499
+ <data element_type="i32" shape="" offset="7602764" size="4" />
500
+ <output>
501
+ <port id="0" precision="I32" />
502
+ </output>
503
+ </layer>
504
+ <layer id="40" name="RaggedToDense_170633" type="RaggedToDense" version="extension">
505
+ <data pad_right="false" m_pad_max_length="false" />
506
+ <input>
507
+ <port id="0" precision="I32">
508
+ <dim>-1</dim>
509
+ </port>
510
+ <port id="1" precision="I32">
511
+ <dim>-1</dim>
512
+ </port>
513
+ <port id="2" precision="I32">
514
+ <dim>-1</dim>
515
+ </port>
516
+ <port id="3" precision="I32" />
517
+ <port id="4" precision="I32" />
518
+ </input>
519
+ <output>
520
+ <port id="5" precision="I32">
521
+ <dim>-1</dim>
522
+ <dim>-1</dim>
523
+ </port>
524
+ <port id="6" precision="BOOL">
525
+ <dim>-1</dim>
526
+ <dim>-1</dim>
527
+ </port>
528
+ </output>
529
+ </layer>
530
+ <layer id="41" name="Convert_170634" type="Convert" version="opset1">
531
+ <data destination_type="i32" />
532
+ <input>
533
+ <port id="0" precision="BOOL">
534
+ <dim>-1</dim>
535
+ <dim>-1</dim>
536
+ </port>
537
+ </input>
538
+ <output>
539
+ <port id="1" precision="I32">
540
+ <dim>-1</dim>
541
+ <dim>-1</dim>
542
+ </port>
543
+ </output>
544
+ </layer>
545
+ <layer id="42" name="Convert_170634.0" type="Convert" version="opset1">
546
+ <data destination_type="i64" />
547
+ <input>
548
+ <port id="0" precision="I32">
549
+ <dim>-1</dim>
550
+ <dim>-1</dim>
551
+ </port>
552
+ </input>
553
+ <output>
554
+ <port id="1" precision="I64" names="attention_mask">
555
+ <dim>-1</dim>
556
+ <dim>-1</dim>
557
+ </port>
558
+ </output>
559
+ </layer>
560
+ <layer id="44" name="RaggedToDense_170633.0" type="Convert" version="opset1">
561
+ <data destination_type="i64" />
562
+ <input>
563
+ <port id="0" precision="I32">
564
+ <dim>-1</dim>
565
+ <dim>-1</dim>
566
+ </port>
567
+ </input>
568
+ <output>
569
+ <port id="1" precision="I64" names="input_ids">
570
+ <dim>-1</dim>
571
+ <dim>-1</dim>
572
+ </port>
573
+ </output>
574
+ </layer>
575
+ <layer id="45" name="Result_170635" type="Result" version="opset1" output_names="input_ids">
576
+ <input>
577
+ <port id="0" precision="I64">
578
+ <dim>-1</dim>
579
+ <dim>-1</dim>
580
+ </port>
581
+ </input>
582
+ </layer>
583
+ <layer id="43" name="Result_170636" type="Result" version="opset1" output_names="attention_mask">
584
+ <input>
585
+ <port id="0" precision="I64">
586
+ <dim>-1</dim>
587
+ <dim>-1</dim>
588
+ </port>
589
+ </input>
590
+ </layer>
591
+ </layers>
592
+ <edges>
593
+ <edge from-layer="0" from-port="0" to-layer="2" to-port="0" />
594
+ <edge from-layer="1" from-port="0" to-layer="8" to-port="0" />
595
+ <edge from-layer="2" from-port="2" to-layer="15" to-port="3" />
596
+ <edge from-layer="2" from-port="3" to-layer="15" to-port="4" />
597
+ <edge from-layer="2" from-port="1" to-layer="15" to-port="2" />
598
+ <edge from-layer="2" from-port="1" to-layer="3" to-port="0" />
599
+ <edge from-layer="3" from-port="1" to-layer="6" to-port="0" />
600
+ <edge from-layer="4" from-port="0" to-layer="6" to-port="1" />
601
+ <edge from-layer="5" from-port="0" to-layer="6" to-port="2" />
602
+ <edge from-layer="6" from-port="3" to-layer="8" to-port="1" />
603
+ <edge from-layer="6" from-port="3" to-layer="11" to-port="0" />
604
+ <edge from-layer="7" from-port="0" to-layer="8" to-port="2" />
605
+ <edge from-layer="8" from-port="3" to-layer="15" to-port="0" />
606
+ <edge from-layer="9" from-port="0" to-layer="13" to-port="0" />
607
+ <edge from-layer="10" from-port="0" to-layer="11" to-port="1" />
608
+ <edge from-layer="11" from-port="2" to-layer="13" to-port="1" />
609
+ <edge from-layer="12" from-port="0" to-layer="13" to-port="2" />
610
+ <edge from-layer="13" from-port="3" to-layer="15" to-port="1" />
611
+ <edge from-layer="14" from-port="0" to-layer="15" to-port="5" />
612
+ <edge from-layer="15" from-port="6" to-layer="17" to-port="0" />
613
+ <edge from-layer="15" from-port="7" to-layer="17" to-port="1" />
614
+ <edge from-layer="15" from-port="8" to-layer="17" to-port="2" />
615
+ <edge from-layer="15" from-port="9" to-layer="17" to-port="3" />
616
+ <edge from-layer="15" from-port="10" to-layer="17" to-port="4" />
617
+ <edge from-layer="15" from-port="11" to-layer="17" to-port="5" />
618
+ <edge from-layer="16" from-port="0" to-layer="17" to-port="6" />
619
+ <edge from-layer="17" from-port="7" to-layer="31" to-port="0" />
620
+ <edge from-layer="17" from-port="8" to-layer="31" to-port="1" />
621
+ <edge from-layer="17" from-port="9" to-layer="31" to-port="2" />
622
+ <edge from-layer="17" from-port="10" to-layer="31" to-port="3" />
623
+ <edge from-layer="17" from-port="11" to-layer="31" to-port="4" />
624
+ <edge from-layer="18" from-port="0" to-layer="31" to-port="5" />
625
+ <edge from-layer="19" from-port="0" to-layer="31" to-port="6" />
626
+ <edge from-layer="20" from-port="0" to-layer="31" to-port="7" />
627
+ <edge from-layer="21" from-port="0" to-layer="31" to-port="8" />
628
+ <edge from-layer="22" from-port="0" to-layer="31" to-port="9" />
629
+ <edge from-layer="23" from-port="0" to-layer="31" to-port="10" />
630
+ <edge from-layer="24" from-port="0" to-layer="31" to-port="11" />
631
+ <edge from-layer="25" from-port="0" to-layer="31" to-port="12" />
632
+ <edge from-layer="26" from-port="0" to-layer="31" to-port="13" />
633
+ <edge from-layer="27" from-port="0" to-layer="31" to-port="14" />
634
+ <edge from-layer="28" from-port="0" to-layer="31" to-port="15" />
635
+ <edge from-layer="29" from-port="0" to-layer="31" to-port="16" />
636
+ <edge from-layer="30" from-port="0" to-layer="31" to-port="17" />
637
+ <edge from-layer="31" from-port="19" to-layer="35" to-port="0" />
638
+ <edge from-layer="31" from-port="20" to-layer="40" to-port="2" />
639
+ <edge from-layer="31" from-port="19" to-layer="40" to-port="1" />
640
+ <edge from-layer="31" from-port="19" to-layer="36" to-port="0" />
641
+ <edge from-layer="31" from-port="18" to-layer="32" to-port="1" />
642
+ <edge from-layer="31" from-port="19" to-layer="32" to-port="0" />
643
+ <edge from-layer="32" from-port="2" to-layer="34" to-port="0" />
644
+ <edge from-layer="33" from-port="0" to-layer="34" to-port="1" />
645
+ <edge from-layer="34" from-port="2" to-layer="35" to-port="1" />
646
+ <edge from-layer="35" from-port="2" to-layer="36" to-port="1" />
647
+ <edge from-layer="35" from-port="2" to-layer="40" to-port="0" />
648
+ <edge from-layer="36" from-port="2" to-layer="38" to-port="0" />
649
+ <edge from-layer="37" from-port="0" to-layer="38" to-port="1" />
650
+ <edge from-layer="38" from-port="2" to-layer="40" to-port="3" />
651
+ <edge from-layer="39" from-port="0" to-layer="40" to-port="4" />
652
+ <edge from-layer="40" from-port="6" to-layer="41" to-port="0" />
653
+ <edge from-layer="40" from-port="5" to-layer="44" to-port="0" />
654
+ <edge from-layer="41" from-port="1" to-layer="42" to-port="0" />
655
+ <edge from-layer="42" from-port="1" to-layer="43" to-port="0" />
656
+ <edge from-layer="44" from-port="1" to-layer="45" to-port="0" />
657
+ </edges>
658
+ <rt_info>
659
+ <add_attention_mask value="True" />
660
+ <add_prefix_space />
661
+ <add_special_tokens value="True" />
662
+ <bos_token_id value="199999" />
663
+ <chat_template value="{% for message in messages %}{% if message['role'] == 'system' and 'tools' in message and message['tools'] is not none %}{{ '&lt;|' + message['role'] + '|>' + message['content'] + '&lt;|tool|>' + message['tools'] + '&lt;|/tool|>' + '&lt;|end|>' }}{% else %}{{ '&lt;|' + message['role'] + '|>' + message['content'] + '&lt;|end|>' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '&lt;|assistant|>' }}{% else %}{{ eos_token }}{% endif %}" />
664
+ <clean_up_tokenization_spaces />
665
+ <detokenizer_input_type value="i64" />
666
+ <eos_token_id value="199999" />
667
+ <handle_special_tokens_with_re />
668
+ <max_length />
669
+ <number_of_inputs value="1" />
670
+ <openvino_tokenizers_version value="2025.1.0.0-523-710ddf14de8" />
671
+ <openvino_version value="2025.1.0-18503-6fec06580ab-releases/2025/1" />
672
+ <original_tokenizer_class value="&lt;class 'transformers.models.gpt2.tokenization_gpt2_fast.GPT2TokenizerFast'>" />
673
+ <pad_token_id value="199999" />
674
+ <sentencepiece_version value="0.2.0" />
675
+ <skip_special_tokens value="True" />
676
+ <streaming_detokenizer value="False" />
677
+ <tiktoken_version value="0.9.0" />
678
+ <tokenizer_output_type value="i64" />
679
+ <tokenizers_version value="0.21.1" />
680
+ <transformers_version value="4.51.3" />
681
+ <use_max_padding value="False" />
682
+ <use_sentencepiece_backend value="False" />
683
+ <utf8_replace_mode value="replace" />
684
+ <with_detokenizer value="True" />
685
+ </rt_info>
686
+ </net>
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|endoftext|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|endoftext|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<|endoftext|>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:382cc235b56c725945e149cc25f191da667c836655efd0857b004320e90e91ea
3
+ size 15524095
tokenizer_config.json ADDED
@@ -0,0 +1,112 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": false,
5
+ "added_tokens_decoder": {
6
+ "199999": {
7
+ "content": "<|endoftext|>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "200018": {
15
+ "content": "<|endofprompt|>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "200019": {
23
+ "content": "<|assistant|>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": true,
27
+ "single_word": false,
28
+ "special": true
29
+ },
30
+ "200020": {
31
+ "content": "<|end|>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": true,
35
+ "single_word": false,
36
+ "special": true
37
+ },
38
+ "200021": {
39
+ "content": "<|user|>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": true,
43
+ "single_word": false,
44
+ "special": true
45
+ },
46
+ "200022": {
47
+ "content": "<|system|>",
48
+ "lstrip": false,
49
+ "normalized": false,
50
+ "rstrip": true,
51
+ "single_word": false,
52
+ "special": true
53
+ },
54
+ "200023": {
55
+ "content": "<|tool|>",
56
+ "lstrip": false,
57
+ "normalized": false,
58
+ "rstrip": true,
59
+ "single_word": false,
60
+ "special": false
61
+ },
62
+ "200024": {
63
+ "content": "<|/tool|>",
64
+ "lstrip": false,
65
+ "normalized": false,
66
+ "rstrip": true,
67
+ "single_word": false,
68
+ "special": false
69
+ },
70
+ "200025": {
71
+ "content": "<|tool_call|>",
72
+ "lstrip": false,
73
+ "normalized": false,
74
+ "rstrip": true,
75
+ "single_word": false,
76
+ "special": false
77
+ },
78
+ "200026": {
79
+ "content": "<|/tool_call|>",
80
+ "lstrip": false,
81
+ "normalized": false,
82
+ "rstrip": true,
83
+ "single_word": false,
84
+ "special": false
85
+ },
86
+ "200027": {
87
+ "content": "<|tool_response|>",
88
+ "lstrip": false,
89
+ "normalized": false,
90
+ "rstrip": true,
91
+ "single_word": false,
92
+ "special": false
93
+ },
94
+ "200028": {
95
+ "content": "<|tag|>",
96
+ "lstrip": false,
97
+ "normalized": false,
98
+ "rstrip": true,
99
+ "single_word": false,
100
+ "special": true
101
+ }
102
+ },
103
+ "bos_token": "<|endoftext|>",
104
+ "chat_template": "{% for message in messages %}{% if message['role'] == 'system' and 'tools' in message and message['tools'] is not none %}{{ '<|' + message['role'] + '|>' + message['content'] + '<|tool|>' + message['tools'] + '<|/tool|>' + '<|end|>' }}{% else %}{{ '<|' + message['role'] + '|>' + message['content'] + '<|end|>' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>' }}{% else %}{{ eos_token }}{% endif %}",
105
+ "clean_up_tokenization_spaces": false,
106
+ "eos_token": "<|endoftext|>",
107
+ "extra_special_tokens": {},
108
+ "model_max_length": 131072,
109
+ "pad_token": "<|endoftext|>",
110
+ "tokenizer_class": "GPT2Tokenizer",
111
+ "unk_token": "<|endoftext|>"
112
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff