Hugging Face's logo

fakezeta
/
Phi-3-mini-128k-instruct-ov-int8

Text Generation
Transformers
OpenVINO
phi3
conversational
custom_code
Inference Endpoints
Model card Files Community
fakezeta commited on
Commit
37e7447
•
1 Parent(s): ad5357c

Upload 13 files

Browse files

converted with transformers 4.41.2

Files changed (12) hide show
  1. added_tokens.json +6 -33
  2. config.json +5 -3
  3. generation_config.json +11 -0
  4. openvino_detokenizer.bin +3 -0
  5. openvino_detokenizer.xml +97 -0
  6. openvino_model.bin +2 -2
  7. openvino_model.xml +0 -0
  8. openvino_tokenizer.bin +3 -0
  9. openvino_tokenizer.xml +231 -0
  10. special_tokens_map.json +0 -3
  11. tokenizer.json +7 -249
  12. tokenizer_config.json +7 -226
added_tokens.json CHANGED
@@ -1,40 +1,13 @@
1
  {
2
- "<|/code|>": 32014,
3
- "<|/data|>": 32033,
4
- "<|/inst|>": 32037,
5
- "<|/query|>": 32031,
6
- "<|/sys|>": 32035,
7
- "<|assistant_mask|>": 32017,
8
  "<|assistant|>": 32001,
9
- "<|calc|>": 32012,
10
- "<|code|>": 32013,
11
- "<|continue|>": 32009,
12
- "<|data|>": 32032,
13
- "<|diff_marker|>": 32025,
14
- "<|disc_sep|>": 32029,
15
- "<|disc_start|>": 32028,
16
- "<|disc_thread|><|query|>": 32030,
17
  "<|endoftext|>": 32000,
18
  "<|end|>": 32007,
19
- "<|fim_middle|>": 32021,
20
- "<|fim_prefix|>": 32020,
21
- "<|fim_suffix|>": 32022,
22
- "<|function_call|>": 32005,
23
- "<|function_list|>": 32011,
24
- "<|function_output|>": 32003,
25
- "<|ghissue|>": 32026,
26
- "<|ghreview|>": 32027,
27
- "<|inst|>": 32036,
28
- "<|ipynb_marker|>": 32024,
29
- "<|message|>": 32019,
30
- "<|meta_start|>": 32023,
31
- "<|raw|>": 32008,
32
- "<|resource|>": 32016,
33
- "<|start|>": 32018,
34
- "<|step|>": 32002,
35
- "<|summary|>": 32015,
36
  "<|system|>": 32006,
37
- "<|sys|>": 32034,
38
- "<|tag|>": 32004,
39
  "<|user|>": 32010
40
  }
 
1
  {
 
 
 
 
 
 
2
  "<|assistant|>": 32001,
 
 
 
 
 
 
 
 
3
  "<|endoftext|>": 32000,
4
  "<|end|>": 32007,
5
+ "<|placeholder1|>": 32002,
6
+ "<|placeholder2|>": 32003,
7
+ "<|placeholder3|>": 32004,
8
+ "<|placeholder4|>": 32005,
9
+ "<|placeholder5|>": 32008,
10
+ "<|placeholder6|>": 32009,
 
 
 
 
 
 
 
 
 
 
 
11
  "<|system|>": 32006,
 
 
12
  "<|user|>": 32010
13
  }
config.json CHANGED
@@ -3,10 +3,13 @@
3
  "architectures": [
4
  "Phi3ForCausalLM"
5
  ],
 
6
  "attention_dropout": 0.0,
7
  "auto_map": {
8
  "AutoConfig": "microsoft/Phi-3-mini-128k-instruct--configuration_phi3.Phi3Config",
9
- "AutoModelForCausalLM": "microsoft/Phi-3-mini-128k-instruct--modeling_phi3.Phi3ForCausalLM"
 
 
10
  },
11
  "bos_token_id": 1,
12
  "embd_pdrop": 0.0,
@@ -130,8 +133,7 @@
130
  "rope_theta": 10000.0,
131
  "sliding_window": 262144,
132
  "tie_word_embeddings": false,
133
- "torch_dtype": "bfloat16",
134
- "transformers_version": "4.39.3",
135
  "use_cache": true,
136
  "vocab_size": 32064
137
  }
 
3
  "architectures": [
4
  "Phi3ForCausalLM"
5
  ],
6
+ "attention_bias": false,
7
  "attention_dropout": 0.0,
8
  "auto_map": {
9
  "AutoConfig": "microsoft/Phi-3-mini-128k-instruct--configuration_phi3.Phi3Config",
10
+ "AutoModelForCausalLM": "microsoft/Phi-3-mini-128k-instruct--modeling_phi3.Phi3ForCausalLM",
11
+ "AutoModelForSequenceClassification": "microsoft/Phi-3-mini-128k-instruct--modeling_phi3.Phi3ForSequenceClassification",
12
+ "AutoModelForTokenClassification": "microsoft/Phi-3-mini-128k-instruct--modeling_phi3.Phi3ForTokenClassification"
13
  },
14
  "bos_token_id": 1,
15
  "embd_pdrop": 0.0,
 
133
  "rope_theta": 10000.0,
134
  "sliding_window": 262144,
135
  "tie_word_embeddings": false,
136
+ "transformers_version": "4.41.2",
 
137
  "use_cache": true,
138
  "vocab_size": 32064
139
  }
generation_config.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": [
5
+ 32000,
6
+ 32001,
7
+ 32007
8
+ ],
9
+ "pad_token_id": 32000,
10
+ "transformers_version": "4.41.2"
11
+ }
openvino_detokenizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34f54bcfdecf199ed7333d7748c8e357c9d98b26c0c5800c7e0809e48edd74d3
3
+ size 499991
openvino_detokenizer.xml ADDED
@@ -0,0 +1,97 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ <?xml version="1.0"?>
2
+ <net name="detokenizer" version="11">
3
+ <layers>
4
+ <layer id="0" name="Parameter_223611" type="Parameter" version="opset1">
5
+ <data shape="?,?" element_type="i64" />
6
+ <output>
7
+ <port id="0" precision="I64" names="Parameter_223611">
8
+ <dim>-1</dim>
9
+ <dim>-1</dim>
10
+ </port>
11
+ </output>
12
+ </layer>
13
+ <layer id="1" name="Constant_223591" type="Const" version="opset1">
14
+ <data element_type="u8" shape="499991" offset="0" size="499991" />
15
+ <output>
16
+ <port id="0" precision="U8">
17
+ <dim>499991</dim>
18
+ </port>
19
+ </output>
20
+ </layer>
21
+ <layer id="2" name="Convert_223621" 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_223612" type="SentencepieceDetokenizer" version="extension">
37
+ <input>
38
+ <port id="0" precision="U8">
39
+ <dim>499991</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_223613" 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_223614" 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
+ <eos_token_id value="32000" />
96
+ </rt_info>
97
+ </net>
openvino_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:316d9768ef95819dc00f5e8a931c362a86e7d3ef00090b981f0361edee20b616
3
- size 3824519400
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe106009a626adda0ec04910de67d7e71003c82ab2b34bd56525855788fef175
3
+ size 3824919028
openvino_model.xml CHANGED
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 sha256:46097e0534935f1aec4cbac2c90e565ec51a8513fcd53b841231849403e5e122
3
+ size 499981
openvino_tokenizer.xml ADDED
@@ -0,0 +1,231 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ <?xml version="1.0"?>
2
+ <net name="tokenizer" version="11">
3
+ <layers>
4
+ <layer id="0" name="string_input" type="Parameter" version="opset1">
5
+ <data shape="?" element_type="string" />
6
+ <output>
7
+ <port id="0" precision="STRING" names="string_input">
8
+ <dim>-1</dim>
9
+ </port>
10
+ </output>
11
+ </layer>
12
+ <layer id="1" name="Constant_223597" type="Const" version="opset1">
13
+ <data element_type="i32" shape="" offset="0" size="4" />
14
+ <output>
15
+ <port id="0" precision="I32" />
16
+ </output>
17
+ </layer>
18
+ <layer id="2" name="Constant_223590" type="Const" version="opset1">
19
+ <data element_type="u8" shape="499969" offset="4" size="499969" />
20
+ <output>
21
+ <port id="0" precision="U8">
22
+ <dim>499969</dim>
23
+ </port>
24
+ </output>
25
+ </layer>
26
+ <layer id="3" name="SentencepieceTokenizer_223593" type="SentencepieceTokenizer" version="extension">
27
+ <data nbest_size="0" alpha="0" add_bos="true" add_eos="false" reverse="false" />
28
+ <input>
29
+ <port id="0" precision="U8">
30
+ <dim>499969</dim>
31
+ </port>
32
+ <port id="1" precision="STRING">
33
+ <dim>-1</dim>
34
+ </port>
35
+ </input>
36
+ <output>
37
+ <port id="2" precision="I64">
38
+ <dim>-1</dim>
39
+ <dim>2</dim>
40
+ </port>
41
+ <port id="3" precision="I32">
42
+ <dim>-1</dim>
43
+ </port>
44
+ <port id="4" precision="I64">
45
+ <dim>2</dim>
46
+ </port>
47
+ </output>
48
+ </layer>
49
+ <layer id="4" name="Broadcast_223598" type="Broadcast" version="opset3">
50
+ <data mode="numpy" />
51
+ <input>
52
+ <port id="0" precision="I32" />
53
+ <port id="1" precision="I64">
54
+ <dim>2</dim>
55
+ </port>
56
+ </input>
57
+ <output>
58
+ <port id="2" precision="I32">
59
+ <dim>-1</dim>
60
+ <dim>-1</dim>
61
+ </port>
62
+ </output>
63
+ </layer>
64
+ <layer id="5" name="Constant_223599" type="Const" version="opset1">
65
+ <data element_type="i32" shape="" offset="499973" size="4" />
66
+ <output>
67
+ <port id="0" precision="I32" />
68
+ </output>
69
+ </layer>
70
+ <layer id="6" name="ShapeOf_223600" type="ShapeOf" version="opset3">
71
+ <data output_type="i64" />
72
+ <input>
73
+ <port id="0" precision="I32">
74
+ <dim>-1</dim>
75
+ </port>
76
+ </input>
77
+ <output>
78
+ <port id="1" precision="I64">
79
+ <dim>1</dim>
80
+ </port>
81
+ </output>
82
+ </layer>
83
+ <layer id="7" name="Broadcast_223601" type="Broadcast" version="opset3">
84
+ <data mode="numpy" />
85
+ <input>
86
+ <port id="0" precision="I32" />
87
+ <port id="1" precision="I64">
88
+ <dim>1</dim>
89
+ </port>
90
+ </input>
91
+ <output>
92
+ <port id="2" precision="I32">
93
+ <dim>-1</dim>
94
+ </port>
95
+ </output>
96
+ </layer>
97
+ <layer id="8" name="ScatterNDUpdate_223605" type="ScatterNDUpdate" version="opset4">
98
+ <input>
99
+ <port id="0" precision="I32">
100
+ <dim>-1</dim>
101
+ <dim>-1</dim>
102
+ </port>
103
+ <port id="1" precision="I64">
104
+ <dim>-1</dim>
105
+ <dim>2</dim>
106
+ </port>
107
+ <port id="2" precision="I32">
108
+ <dim>-1</dim>
109
+ </port>
110
+ </input>
111
+ <output>
112
+ <port id="3" precision="I32">
113
+ <dim>-1</dim>
114
+ <dim>-1</dim>
115
+ </port>
116
+ </output>
117
+ </layer>
118
+ <layer id="9" name="ScatterNDUpdate_223605" type="Convert" version="opset1">
119
+ <data destination_type="i64" />
120
+ <input>
121
+ <port id="0" precision="I32">
122
+ <dim>-1</dim>
123
+ <dim>-1</dim>
124
+ </port>
125
+ </input>
126
+ <output>
127
+ <port id="1" precision="I64" names="attention_mask">
128
+ <dim>-1</dim>
129
+ <dim>-1</dim>
130
+ </port>
131
+ </output>
132
+ </layer>
133
+ <layer id="11" name="Constant_223594" type="Const" version="opset1">
134
+ <data element_type="i32" shape="" offset="499977" size="4" />
135
+ <output>
136
+ <port id="0" precision="I32" />
137
+ </output>
138
+ </layer>
139
+ <layer id="12" name="Broadcast_223595" type="Broadcast" version="opset3">
140
+ <data mode="numpy" />
141
+ <input>
142
+ <port id="0" precision="I32" />
143
+ <port id="1" precision="I64">
144
+ <dim>2</dim>
145
+ </port>
146
+ </input>
147
+ <output>
148
+ <port id="2" precision="I32">
149
+ <dim>-1</dim>
150
+ <dim>-1</dim>
151
+ </port>
152
+ </output>
153
+ </layer>
154
+ <layer id="13" name="ScatterNDUpdate_223596" type="ScatterNDUpdate" version="opset4">
155
+ <input>
156
+ <port id="0" precision="I32">
157
+ <dim>-1</dim>
158
+ <dim>-1</dim>
159
+ </port>
160
+ <port id="1" precision="I64">
161
+ <dim>-1</dim>
162
+ <dim>2</dim>
163
+ </port>
164
+ <port id="2" precision="I32">
165
+ <dim>-1</dim>
166
+ </port>
167
+ </input>
168
+ <output>
169
+ <port id="3" precision="I32">
170
+ <dim>-1</dim>
171
+ <dim>-1</dim>
172
+ </port>
173
+ </output>
174
+ </layer>
175
+ <layer id="14" name="ScatterNDUpdate_223596" type="Convert" version="opset1">
176
+ <data destination_type="i64" />
177
+ <input>
178
+ <port id="0" precision="I32">
179
+ <dim>-1</dim>
180
+ <dim>-1</dim>
181
+ </port>
182
+ </input>
183
+ <output>
184
+ <port id="1" precision="I64" names="input_ids">
185
+ <dim>-1</dim>
186
+ <dim>-1</dim>
187
+ </port>
188
+ </output>
189
+ </layer>
190
+ <layer id="15" name="Result_223606" type="Result" version="opset1">
191
+ <input>
192
+ <port id="0" precision="I64">
193
+ <dim>-1</dim>
194
+ <dim>-1</dim>
195
+ </port>
196
+ </input>
197
+ </layer>
198
+ <layer id="10" name="Result_223607" type="Result" version="opset1">
199
+ <input>
200
+ <port id="0" precision="I64">
201
+ <dim>-1</dim>
202
+ <dim>-1</dim>
203
+ </port>
204
+ </input>
205
+ </layer>
206
+ </layers>
207
+ <edges>
208
+ <edge from-layer="0" from-port="0" to-layer="3" to-port="1" />
209
+ <edge from-layer="1" from-port="0" to-layer="4" to-port="0" />
210
+ <edge from-layer="2" from-port="0" to-layer="3" to-port="0" />
211
+ <edge from-layer="3" from-port="4" to-layer="4" to-port="1" />
212
+ <edge from-layer="3" from-port="3" to-layer="6" to-port="0" />
213
+ <edge from-layer="3" from-port="2" to-layer="8" to-port="1" />
214
+ <edge from-layer="3" from-port="3" to-layer="13" to-port="2" />
215
+ <edge from-layer="3" from-port="2" to-layer="13" to-port="1" />
216
+ <edge from-layer="3" from-port="4" to-layer="12" to-port="1" />
217
+ <edge from-layer="4" from-port="2" to-layer="8" to-port="0" />
218
+ <edge from-layer="5" from-port="0" to-layer="7" to-port="0" />
219
+ <edge from-layer="6" from-port="1" to-layer="7" to-port="1" />
220
+ <edge from-layer="7" from-port="2" to-layer="8" to-port="2" />
221
+ <edge from-layer="8" from-port="3" to-layer="9" to-port="0" />
222
+ <edge from-layer="9" from-port="1" to-layer="10" to-port="0" />
223
+ <edge from-layer="11" from-port="0" to-layer="12" to-port="0" />
224
+ <edge from-layer="12" from-port="2" to-layer="13" to-port="0" />
225
+ <edge from-layer="13" from-port="3" to-layer="14" to-port="0" />
226
+ <edge from-layer="14" from-port="1" to-layer="15" to-port="0" />
227
+ </edges>
228
+ <rt_info>
229
+ <eos_token_id value="32000" />
230
+ </rt_info>
231
+ </net>
special_tokens_map.json CHANGED
@@ -1,7 +1,4 @@
1
  {
2
- "additional_special_tokens": [
3
- "<|/inst|>"
4
- ],
5
  "bos_token": {
6
  "content": "<s>",
7
  "lstrip": false,
 
1
  {
 
 
 
2
  "bos_token": {
3
  "content": "<s>",
4
  "lstrip": false,
tokenizer.json CHANGED
@@ -50,7 +50,7 @@
50
  },
51
  {
52
  "id": 32002,
53
- "content": "<|step|>",
54
  "single_word": false,
55
  "lstrip": false,
56
  "rstrip": true,
@@ -59,7 +59,7 @@
59
  },
60
  {
61
  "id": 32003,
62
- "content": "<|function_output|>",
63
  "single_word": false,
64
  "lstrip": false,
65
  "rstrip": true,
@@ -68,7 +68,7 @@
68
  },
69
  {
70
  "id": 32004,
71
- "content": "<|tag|>",
72
  "single_word": false,
73
  "lstrip": false,
74
  "rstrip": true,
@@ -77,7 +77,7 @@
77
  },
78
  {
79
  "id": 32005,
80
- "content": "<|function_call|>",
81
  "single_word": false,
82
  "lstrip": false,
83
  "rstrip": true,
@@ -104,7 +104,7 @@
104
  },
105
  {
106
  "id": 32008,
107
- "content": "<|raw|>",
108
  "single_word": false,
109
  "lstrip": false,
110
  "rstrip": true,
@@ -113,7 +113,7 @@
113
  },
114
  {
115
  "id": 32009,
116
- "content": "<|continue|>",
117
  "single_word": false,
118
  "lstrip": false,
119
  "rstrip": true,
@@ -128,249 +128,6 @@
128
  "rstrip": true,
129
  "normalized": false,
130
  "special": true
131
- },
132
- {
133
- "id": 32011,
134
- "content": "<|function_list|>",
135
- "single_word": false,
136
- "lstrip": false,
137
- "rstrip": true,
138
- "normalized": false,
139
- "special": true
140
- },
141
- {
142
- "id": 32012,
143
- "content": "<|calc|>",
144
- "single_word": false,
145
- "lstrip": false,
146
- "rstrip": true,
147
- "normalized": false,
148
- "special": true
149
- },
150
- {
151
- "id": 32013,
152
- "content": "<|code|>",
153
- "single_word": false,
154
- "lstrip": false,
155
- "rstrip": true,
156
- "normalized": false,
157
- "special": true
158
- },
159
- {
160
- "id": 32014,
161
- "content": "<|/code|>",
162
- "single_word": false,
163
- "lstrip": false,
164
- "rstrip": true,
165
- "normalized": false,
166
- "special": true
167
- },
168
- {
169
- "id": 32015,
170
- "content": "<|summary|>",
171
- "single_word": false,
172
- "lstrip": false,
173
- "rstrip": true,
174
- "normalized": false,
175
- "special": true
176
- },
177
- {
178
- "id": 32016,
179
- "content": "<|resource|>",
180
- "single_word": false,
181
- "lstrip": false,
182
- "rstrip": true,
183
- "normalized": false,
184
- "special": true
185
- },
186
- {
187
- "id": 32017,
188
- "content": "<|assistant_mask|>",
189
- "single_word": false,
190
- "lstrip": false,
191
- "rstrip": true,
192
- "normalized": false,
193
- "special": true
194
- },
195
- {
196
- "id": 32018,
197
- "content": "<|start|>",
198
- "single_word": false,
199
- "lstrip": false,
200
- "rstrip": true,
201
- "normalized": false,
202
- "special": true
203
- },
204
- {
205
- "id": 32019,
206
- "content": "<|message|>",
207
- "single_word": false,
208
- "lstrip": false,
209
- "rstrip": true,
210
- "normalized": false,
211
- "special": true
212
- },
213
- {
214
- "id": 32020,
215
- "content": "<|fim_prefix|>",
216
- "single_word": false,
217
- "lstrip": false,
218
- "rstrip": true,
219
- "normalized": false,
220
- "special": true
221
- },
222
- {
223
- "id": 32021,
224
- "content": "<|fim_middle|>",
225
- "single_word": false,
226
- "lstrip": false,
227
- "rstrip": true,
228
- "normalized": false,
229
- "special": true
230
- },
231
- {
232
- "id": 32022,
233
- "content": "<|fim_suffix|>",
234
- "single_word": false,
235
- "lstrip": false,
236
- "rstrip": true,
237
- "normalized": false,
238
- "special": true
239
- },
240
- {
241
- "id": 32023,
242
- "content": "<|meta_start|>",
243
- "single_word": false,
244
- "lstrip": false,
245
- "rstrip": true,
246
- "normalized": false,
247
- "special": true
248
- },
249
- {
250
- "id": 32024,
251
- "content": "<|ipynb_marker|>",
252
- "single_word": false,
253
- "lstrip": false,
254
- "rstrip": true,
255
- "normalized": false,
256
- "special": true
257
- },
258
- {
259
- "id": 32025,
260
- "content": "<|diff_marker|>",
261
- "single_word": false,
262
- "lstrip": false,
263
- "rstrip": true,
264
- "normalized": false,
265
- "special": true
266
- },
267
- {
268
- "id": 32026,
269
- "content": "<|ghissue|>",
270
- "single_word": false,
271
- "lstrip": false,
272
- "rstrip": true,
273
- "normalized": false,
274
- "special": true
275
- },
276
- {
277
- "id": 32027,
278
- "content": "<|ghreview|>",
279
- "single_word": false,
280
- "lstrip": false,
281
- "rstrip": true,
282
- "normalized": false,
283
- "special": true
284
- },
285
- {
286
- "id": 32028,
287
- "content": "<|disc_start|>",
288
- "single_word": false,
289
- "lstrip": false,
290
- "rstrip": true,
291
- "normalized": false,
292
- "special": true
293
- },
294
- {
295
- "id": 32029,
296
- "content": "<|disc_sep|>",
297
- "single_word": false,
298
- "lstrip": false,
299
- "rstrip": true,
300
- "normalized": false,
301
- "special": true
302
- },
303
- {
304
- "id": 32030,
305
- "content": "<|disc_thread|><|query|>",
306
- "single_word": false,
307
- "lstrip": false,
308
- "rstrip": true,
309
- "normalized": false,
310
- "special": true
311
- },
312
- {
313
- "id": 32031,
314
- "content": "<|/query|>",
315
- "single_word": false,
316
- "lstrip": false,
317
- "rstrip": true,
318
- "normalized": false,
319
- "special": true
320
- },
321
- {
322
- "id": 32032,
323
- "content": "<|data|>",
324
- "single_word": false,
325
- "lstrip": false,
326
- "rstrip": true,
327
- "normalized": false,
328
- "special": true
329
- },
330
- {
331
- "id": 32033,
332
- "content": "<|/data|>",
333
- "single_word": false,
334
- "lstrip": false,
335
- "rstrip": true,
336
- "normalized": false,
337
- "special": true
338
- },
339
- {
340
- "id": 32034,
341
- "content": "<|sys|>",
342
- "single_word": false,
343
- "lstrip": false,
344
- "rstrip": true,
345
- "normalized": false,
346
- "special": true
347
- },
348
- {
349
- "id": 32035,
350
- "content": "<|/sys|>",
351
- "single_word": false,
352
- "lstrip": false,
353
- "rstrip": true,
354
- "normalized": false,
355
- "special": true
356
- },
357
- {
358
- "id": 32036,
359
- "content": "<|inst|>",
360
- "single_word": false,
361
- "lstrip": false,
362
- "rstrip": true,
363
- "normalized": false,
364
- "special": true
365
- },
366
- {
367
- "id": 32037,
368
- "content": "<|/inst|>",
369
- "single_word": false,
370
- "lstrip": false,
371
- "rstrip": true,
372
- "normalized": false,
373
- "special": true
374
  }
375
  ],
376
  "normalizer": {
@@ -476,6 +233,7 @@
476
  "end_of_word_suffix": null,
477
  "fuse_unk": true,
478
  "byte_fallback": true,
 
479
  "vocab": {
480
  "<unk>": 0,
481
  "<s>": 1,
 
50
  },
51
  {
52
  "id": 32002,
53
+ "content": "<|placeholder1|>",
54
  "single_word": false,
55
  "lstrip": false,
56
  "rstrip": true,
 
59
  },
60
  {
61
  "id": 32003,
62
+ "content": "<|placeholder2|>",
63
  "single_word": false,
64
  "lstrip": false,
65
  "rstrip": true,
 
68
  },
69
  {
70
  "id": 32004,
71
+ "content": "<|placeholder3|>",
72
  "single_word": false,
73
  "lstrip": false,
74
  "rstrip": true,
 
77
  },
78
  {
79
  "id": 32005,
80
+ "content": "<|placeholder4|>",
81
  "single_word": false,
82
  "lstrip": false,
83
  "rstrip": true,
 
104
  },
105
  {
106
  "id": 32008,
107
+ "content": "<|placeholder5|>",
108
  "single_word": false,
109
  "lstrip": false,
110
  "rstrip": true,
 
113
  },
114
  {
115
  "id": 32009,
116
+ "content": "<|placeholder6|>",
117
  "single_word": false,
118
  "lstrip": false,
119
  "rstrip": true,
 
128
  "rstrip": true,
129
  "normalized": false,
130
  "special": true
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
131
  }
132
  ],
133
  "normalizer": {
 
233
  "end_of_word_suffix": null,
234
  "fuse_unk": true,
235
  "byte_fallback": true,
236
+ "ignore_merges": false,
237
  "vocab": {
238
  "<unk>": 0,
239
  "<s>": 1,
tokenizer_config.json CHANGED
@@ -43,7 +43,7 @@
43
  "special": true
44
  },
45
  "32002": {
46
- "content": "<|step|>",
47
  "lstrip": false,
48
  "normalized": false,
49
  "rstrip": true,
@@ -51,7 +51,7 @@
51
  "special": true
52
  },
53
  "32003": {
54
- "content": "<|function_output|>",
55
  "lstrip": false,
56
  "normalized": false,
57
  "rstrip": true,
@@ -59,7 +59,7 @@
59
  "special": true
60
  },
61
  "32004": {
62
- "content": "<|tag|>",
63
  "lstrip": false,
64
  "normalized": false,
65
  "rstrip": true,
@@ -67,7 +67,7 @@
67
  "special": true
68
  },
69
  "32005": {
70
- "content": "<|function_call|>",
71
  "lstrip": false,
72
  "normalized": false,
73
  "rstrip": true,
@@ -91,7 +91,7 @@
91
  "special": true
92
  },
93
  "32008": {
94
- "content": "<|raw|>",
95
  "lstrip": false,
96
  "normalized": false,
97
  "rstrip": true,
@@ -99,7 +99,7 @@
99
  "special": true
100
  },
101
  "32009": {
102
- "content": "<|continue|>",
103
  "lstrip": false,
104
  "normalized": false,
105
  "rstrip": true,
@@ -113,229 +113,10 @@
113
  "rstrip": true,
114
  "single_word": false,
115
  "special": true
116
- },
117
- "32011": {
118
- "content": "<|function_list|>",
119
- "lstrip": false,
120
- "normalized": false,
121
- "rstrip": true,
122
- "single_word": false,
123
- "special": true
124
- },
125
- "32012": {
126
- "content": "<|calc|>",
127
- "lstrip": false,
128
- "normalized": false,
129
- "rstrip": true,
130
- "single_word": false,
131
- "special": true
132
- },
133
- "32013": {
134
- "content": "<|code|>",
135
- "lstrip": false,
136
- "normalized": false,
137
- "rstrip": true,
138
- "single_word": false,
139
- "special": true
140
- },
141
- "32014": {
142
- "content": "<|/code|>",
143
- "lstrip": false,
144
- "normalized": false,
145
- "rstrip": true,
146
- "single_word": false,
147
- "special": true
148
- },
149
- "32015": {
150
- "content": "<|summary|>",
151
- "lstrip": false,
152
- "normalized": false,
153
- "rstrip": true,
154
- "single_word": false,
155
- "special": true
156
- },
157
- "32016": {
158
- "content": "<|resource|>",
159
- "lstrip": false,
160
- "normalized": false,
161
- "rstrip": true,
162
- "single_word": false,
163
- "special": true
164
- },
165
- "32017": {
166
- "content": "<|assistant_mask|>",
167
- "lstrip": false,
168
- "normalized": false,
169
- "rstrip": true,
170
- "single_word": false,
171
- "special": true
172
- },
173
- "32018": {
174
- "content": "<|start|>",
175
- "lstrip": false,
176
- "normalized": false,
177
- "rstrip": true,
178
- "single_word": false,
179
- "special": true
180
- },
181
- "32019": {
182
- "content": "<|message|>",
183
- "lstrip": false,
184
- "normalized": false,
185
- "rstrip": true,
186
- "single_word": false,
187
- "special": true
188
- },
189
- "32020": {
190
- "content": "<|fim_prefix|>",
191
- "lstrip": false,
192
- "normalized": false,
193
- "rstrip": true,
194
- "single_word": false,
195
- "special": true
196
- },
197
- "32021": {
198
- "content": "<|fim_middle|>",
199
- "lstrip": false,
200
- "normalized": false,
201
- "rstrip": true,
202
- "single_word": false,
203
- "special": true
204
- },
205
- "32022": {
206
- "content": "<|fim_suffix|>",
207
- "lstrip": false,
208
- "normalized": false,
209
- "rstrip": true,
210
- "single_word": false,
211
- "special": true
212
- },
213
- "32023": {
214
- "content": "<|meta_start|>",
215
- "lstrip": false,
216
- "normalized": false,
217
- "rstrip": true,
218
- "single_word": false,
219
- "special": true
220
- },
221
- "32024": {
222
- "content": "<|ipynb_marker|>",
223
- "lstrip": false,
224
- "normalized": false,
225
- "rstrip": true,
226
- "single_word": false,
227
- "special": true
228
- },
229
- "32025": {
230
- "content": "<|diff_marker|>",
231
- "lstrip": false,
232
- "normalized": false,
233
- "rstrip": true,
234
- "single_word": false,
235
- "special": true
236
- },
237
- "32026": {
238
- "content": "<|ghissue|>",
239
- "lstrip": false,
240
- "normalized": false,
241
- "rstrip": true,
242
- "single_word": false,
243
- "special": true
244
- },
245
- "32027": {
246
- "content": "<|ghreview|>",
247
- "lstrip": false,
248
- "normalized": false,
249
- "rstrip": true,
250
- "single_word": false,
251
- "special": true
252
- },
253
- "32028": {
254
- "content": "<|disc_start|>",
255
- "lstrip": false,
256
- "normalized": false,
257
- "rstrip": true,
258
- "single_word": false,
259
- "special": true
260
- },
261
- "32029": {
262
- "content": "<|disc_sep|>",
263
- "lstrip": false,
264
- "normalized": false,
265
- "rstrip": true,
266
- "single_word": false,
267
- "special": true
268
- },
269
- "32030": {
270
- "content": "<|disc_thread|><|query|>",
271
- "lstrip": false,
272
- "normalized": false,
273
- "rstrip": true,
274
- "single_word": false,
275
- "special": true
276
- },
277
- "32031": {
278
- "content": "<|/query|>",
279
- "lstrip": false,
280
- "normalized": false,
281
- "rstrip": true,
282
- "single_word": false,
283
- "special": true
284
- },
285
- "32032": {
286
- "content": "<|data|>",
287
- "lstrip": false,
288
- "normalized": false,
289
- "rstrip": true,
290
- "single_word": false,
291
- "special": true
292
- },
293
- "32033": {
294
- "content": "<|/data|>",
295
- "lstrip": false,
296
- "normalized": false,
297
- "rstrip": true,
298
- "single_word": false,
299
- "special": true
300
- },
301
- "32034": {
302
- "content": "<|sys|>",
303
- "lstrip": false,
304
- "normalized": false,
305
- "rstrip": true,
306
- "single_word": false,
307
- "special": true
308
- },
309
- "32035": {
310
- "content": "<|/sys|>",
311
- "lstrip": false,
312
- "normalized": false,
313
- "rstrip": true,
314
- "single_word": false,
315
- "special": true
316
- },
317
- "32036": {
318
- "content": "<|inst|>",
319
- "lstrip": false,
320
- "normalized": false,
321
- "rstrip": true,
322
- "single_word": false,
323
- "special": true
324
- },
325
- "32037": {
326
- "content": "<|/inst|>",
327
- "lstrip": false,
328
- "normalized": false,
329
- "rstrip": true,
330
- "single_word": false,
331
- "special": true
332
  }
333
  },
334
- "additional_special_tokens": [
335
- "<|/inst|>"
336
- ],
337
  "bos_token": "<s>",
338
- "chat_template": "{{ bos_token }}{% for message in messages %}{{'<|' + message['role'] + '|>' + '\n' + message['content'] + '<|end|>\n' }}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>\n' }}{% else %}{{ eos_token }}{% endif %}",
339
  "clean_up_tokenization_spaces": false,
340
  "eos_token": "<|endoftext|>",
341
  "legacy": false,
 
43
  "special": true
44
  },
45
  "32002": {
46
+ "content": "<|placeholder1|>",
47
  "lstrip": false,
48
  "normalized": false,
49
  "rstrip": true,
 
51
  "special": true
52
  },
53
  "32003": {
54
+ "content": "<|placeholder2|>",
55
  "lstrip": false,
56
  "normalized": false,
57
  "rstrip": true,
 
59
  "special": true
60
  },
61
  "32004": {
62
+ "content": "<|placeholder3|>",
63
  "lstrip": false,
64
  "normalized": false,
65
  "rstrip": true,
 
67
  "special": true
68
  },
69
  "32005": {
70
+ "content": "<|placeholder4|>",
71
  "lstrip": false,
72
  "normalized": false,
73
  "rstrip": true,
 
91
  "special": true
92
  },
93
  "32008": {
94
+ "content": "<|placeholder5|>",
95
  "lstrip": false,
96
  "normalized": false,
97
  "rstrip": true,
 
99
  "special": true
100
  },
101
  "32009": {
102
+ "content": "<|placeholder6|>",
103
  "lstrip": false,
104
  "normalized": false,
105
  "rstrip": true,
 
113
  "rstrip": true,
114
  "single_word": false,
115
  "special": true
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
116
  }
117
  },
 
 
 
118
  "bos_token": "<s>",
119
+ "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') %}{{'<|user|>' + '\n' + message['content'] + '<|end|>' + '\n' + '<|assistant|>' + '\n'}}{% elif (message['role'] == 'assistant') %}{{message['content'] + '<|end|>' + '\n'}}{% endif %}{% endfor %}",
120
  "clean_up_tokenization_spaces": false,
121
  "eos_token": "<|endoftext|>",
122
  "legacy": false,