hf-transformers-bot commited on
Commit
46d1c84
·
verified ·
1 Parent(s): 3ee8a61

Add tiny processor fixture for testing

Browse files
.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
chat_template.jinja ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {% for message in messages %}{{'<|im_start|>' + message['role'] + '
2
+ '}}{% if message['content'] is string %}{{ message['content'] }}{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' %}{{ '<IMG_CONTEXT>
3
+ ' }}{% elif content['type'] == 'video' %}{{ '<video>
4
+ ' }}{% elif content['type'] == 'text' %}{{ content['text'] }}{% endif %}{% endfor %}{% endif %}{{'<|im_end|>
5
+ '}}{% endfor %}{% if add_generation_prompt %}{{'<|im_start|>assistant
6
+ ' }}{% endif %}
config.json ADDED
@@ -0,0 +1,80 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "InternVLForConditionalGeneration"
4
+ ],
5
+ "downsample_ratio": 0.5,
6
+ "image_seq_length": 256,
7
+ "image_token_id": 151667,
8
+ "model_type": "internvl",
9
+ "projector_hidden_act": "gelu",
10
+ "text_config": {
11
+ "architectures": [
12
+ "Qwen2ForCausalLM"
13
+ ],
14
+ "attention_dropout": 0.0,
15
+ "bos_token_id": 151643,
16
+ "eos_token_id": 151645,
17
+ "hidden_act": "silu",
18
+ "hidden_size": 896,
19
+ "initializer_range": 0.02,
20
+ "intermediate_size": 4864,
21
+ "max_position_embeddings": 32768,
22
+ "max_window_layers": 70,
23
+ "model_type": "qwen2",
24
+ "num_attention_heads": 14,
25
+ "num_hidden_layers": 24,
26
+ "num_key_value_heads": 2,
27
+ "rms_norm_eps": 1e-06,
28
+ "rope_scaling": {
29
+ "factor": 2.0,
30
+ "rope_type": "dynamic",
31
+ "type": "dynamic"
32
+ },
33
+ "rope_theta": 1000000.0,
34
+ "sliding_window": null,
35
+ "torch_dtype": "bfloat16",
36
+ "use_cache": true,
37
+ "use_sliding_window": false,
38
+ "vocab_size": 151674
39
+ },
40
+ "torch_dtype": "bfloat16",
41
+ "transformers_version": "4.52.0.dev0",
42
+ "vision_config": {
43
+ "architectures": [
44
+ "InternVisionModel"
45
+ ],
46
+ "attention_bias": true,
47
+ "attention_dropout": 0.0,
48
+ "dropout": 0.0,
49
+ "hidden_act": "gelu",
50
+ "hidden_dropout_prob": 0.0,
51
+ "hidden_size": 1024,
52
+ "image_size": [
53
+ 448,
54
+ 448
55
+ ],
56
+ "initializer_factor": 0.1,
57
+ "initializer_range": 1e-10,
58
+ "intermediate_size": 4096,
59
+ "layer_norm_eps": 1e-06,
60
+ "layer_scale_init_value": 0.1,
61
+ "model_type": "internvl_vision",
62
+ "norm_type": "layer_norm",
63
+ "num_attention_heads": 16,
64
+ "num_channels": 3,
65
+ "num_hidden_layers": 24,
66
+ "patch_size": [
67
+ 14,
68
+ 14
69
+ ],
70
+ "projection_dropout": 0.0,
71
+ "torch_dtype": "bfloat16",
72
+ "use_absolute_position_embeddings": true,
73
+ "use_mask_token": false,
74
+ "use_mean_pooling": true,
75
+ "use_qk_norm": false
76
+ },
77
+ "vision_feature_layer": -1,
78
+ "vision_feature_select_strategy": "default",
79
+ "vocab_size": 500
80
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 151643,
4
+ "eos_token_id": 151645,
5
+ "transformers_version": "4.52.0.dev0"
6
+ }
preprocessor_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "crop_size": null,
3
+ "crop_to_patches": false,
4
+ "data_format": "channels_first",
5
+ "default_to_square": true,
6
+ "device": null,
7
+ "do_center_crop": null,
8
+ "do_convert_rgb": true,
9
+ "do_normalize": true,
10
+ "do_rescale": true,
11
+ "do_resize": true,
12
+ "image_mean": [
13
+ 0.485,
14
+ 0.456,
15
+ 0.406
16
+ ],
17
+ "image_processor_type": "GotOcr2ImageProcessorFast",
18
+ "image_std": [
19
+ 0.229,
20
+ 0.224,
21
+ 0.225
22
+ ],
23
+ "input_data_format": null,
24
+ "max_patches": 12,
25
+ "min_patches": 1,
26
+ "processor_class": "InternVLProcessor",
27
+ "resample": 3,
28
+ "rescale_factor": 0.00392156862745098,
29
+ "return_tensors": null,
30
+ "size": {
31
+ "height": 448,
32
+ "width": 448
33
+ }
34
+ }
processor_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "image_seq_length": 256,
3
+ "processor_class": "InternVLProcessor"
4
+ }
tokenizer.json ADDED
@@ -0,0 +1,1819 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "1.0",
3
+ "truncation": null,
4
+ "padding": null,
5
+ "added_tokens": [
6
+ {
7
+ "id": 500,
8
+ "content": "<|endoftext|>",
9
+ "single_word": false,
10
+ "lstrip": false,
11
+ "rstrip": false,
12
+ "normalized": false,
13
+ "special": true
14
+ },
15
+ {
16
+ "id": 501,
17
+ "content": "<|im_start|>",
18
+ "single_word": false,
19
+ "lstrip": false,
20
+ "rstrip": false,
21
+ "normalized": false,
22
+ "special": true
23
+ },
24
+ {
25
+ "id": 502,
26
+ "content": "<|im_end|>",
27
+ "single_word": false,
28
+ "lstrip": false,
29
+ "rstrip": false,
30
+ "normalized": false,
31
+ "special": true
32
+ },
33
+ {
34
+ "id": 503,
35
+ "content": "<|object_ref_start|>",
36
+ "single_word": false,
37
+ "lstrip": false,
38
+ "rstrip": false,
39
+ "normalized": false,
40
+ "special": true
41
+ },
42
+ {
43
+ "id": 504,
44
+ "content": "<|object_ref_end|>",
45
+ "single_word": false,
46
+ "lstrip": false,
47
+ "rstrip": false,
48
+ "normalized": false,
49
+ "special": true
50
+ },
51
+ {
52
+ "id": 505,
53
+ "content": "<|box_start|>",
54
+ "single_word": false,
55
+ "lstrip": false,
56
+ "rstrip": false,
57
+ "normalized": false,
58
+ "special": true
59
+ },
60
+ {
61
+ "id": 506,
62
+ "content": "<|box_end|>",
63
+ "single_word": false,
64
+ "lstrip": false,
65
+ "rstrip": false,
66
+ "normalized": false,
67
+ "special": true
68
+ },
69
+ {
70
+ "id": 507,
71
+ "content": "<|quad_start|>",
72
+ "single_word": false,
73
+ "lstrip": false,
74
+ "rstrip": false,
75
+ "normalized": false,
76
+ "special": true
77
+ },
78
+ {
79
+ "id": 508,
80
+ "content": "<|quad_end|>",
81
+ "single_word": false,
82
+ "lstrip": false,
83
+ "rstrip": false,
84
+ "normalized": false,
85
+ "special": true
86
+ },
87
+ {
88
+ "id": 509,
89
+ "content": "<|vision_start|>",
90
+ "single_word": false,
91
+ "lstrip": false,
92
+ "rstrip": false,
93
+ "normalized": false,
94
+ "special": true
95
+ },
96
+ {
97
+ "id": 510,
98
+ "content": "<|vision_end|>",
99
+ "single_word": false,
100
+ "lstrip": false,
101
+ "rstrip": false,
102
+ "normalized": false,
103
+ "special": true
104
+ },
105
+ {
106
+ "id": 511,
107
+ "content": "<|vision_pad|>",
108
+ "single_word": false,
109
+ "lstrip": false,
110
+ "rstrip": false,
111
+ "normalized": false,
112
+ "special": true
113
+ },
114
+ {
115
+ "id": 512,
116
+ "content": "<|image_pad|>",
117
+ "single_word": false,
118
+ "lstrip": false,
119
+ "rstrip": false,
120
+ "normalized": false,
121
+ "special": true
122
+ },
123
+ {
124
+ "id": 513,
125
+ "content": "<|video_pad|>",
126
+ "single_word": false,
127
+ "lstrip": false,
128
+ "rstrip": false,
129
+ "normalized": false,
130
+ "special": true
131
+ },
132
+ {
133
+ "id": 514,
134
+ "content": "<tool_call>",
135
+ "single_word": false,
136
+ "lstrip": false,
137
+ "rstrip": false,
138
+ "normalized": false,
139
+ "special": false
140
+ },
141
+ {
142
+ "id": 515,
143
+ "content": "</tool_call>",
144
+ "single_word": false,
145
+ "lstrip": false,
146
+ "rstrip": false,
147
+ "normalized": false,
148
+ "special": false
149
+ },
150
+ {
151
+ "id": 516,
152
+ "content": "<|fim_prefix|>",
153
+ "single_word": false,
154
+ "lstrip": false,
155
+ "rstrip": false,
156
+ "normalized": false,
157
+ "special": false
158
+ },
159
+ {
160
+ "id": 517,
161
+ "content": "<|fim_middle|>",
162
+ "single_word": false,
163
+ "lstrip": false,
164
+ "rstrip": false,
165
+ "normalized": false,
166
+ "special": false
167
+ },
168
+ {
169
+ "id": 518,
170
+ "content": "<|fim_suffix|>",
171
+ "single_word": false,
172
+ "lstrip": false,
173
+ "rstrip": false,
174
+ "normalized": false,
175
+ "special": false
176
+ },
177
+ {
178
+ "id": 519,
179
+ "content": "<|fim_pad|>",
180
+ "single_word": false,
181
+ "lstrip": false,
182
+ "rstrip": false,
183
+ "normalized": false,
184
+ "special": false
185
+ },
186
+ {
187
+ "id": 520,
188
+ "content": "<|repo_name|>",
189
+ "single_word": false,
190
+ "lstrip": false,
191
+ "rstrip": false,
192
+ "normalized": false,
193
+ "special": false
194
+ },
195
+ {
196
+ "id": 521,
197
+ "content": "<|file_sep|>",
198
+ "single_word": false,
199
+ "lstrip": false,
200
+ "rstrip": false,
201
+ "normalized": false,
202
+ "special": false
203
+ },
204
+ {
205
+ "id": 522,
206
+ "content": "<img>",
207
+ "single_word": false,
208
+ "lstrip": false,
209
+ "rstrip": false,
210
+ "normalized": false,
211
+ "special": true
212
+ },
213
+ {
214
+ "id": 523,
215
+ "content": "</img>",
216
+ "single_word": false,
217
+ "lstrip": false,
218
+ "rstrip": false,
219
+ "normalized": false,
220
+ "special": true
221
+ },
222
+ {
223
+ "id": 524,
224
+ "content": "<IMG_CONTEXT>",
225
+ "single_word": false,
226
+ "lstrip": false,
227
+ "rstrip": false,
228
+ "normalized": false,
229
+ "special": true
230
+ },
231
+ {
232
+ "id": 525,
233
+ "content": "<quad>",
234
+ "single_word": false,
235
+ "lstrip": false,
236
+ "rstrip": false,
237
+ "normalized": false,
238
+ "special": true
239
+ },
240
+ {
241
+ "id": 526,
242
+ "content": "</quad>",
243
+ "single_word": false,
244
+ "lstrip": false,
245
+ "rstrip": false,
246
+ "normalized": false,
247
+ "special": true
248
+ },
249
+ {
250
+ "id": 527,
251
+ "content": "<ref>",
252
+ "single_word": false,
253
+ "lstrip": false,
254
+ "rstrip": false,
255
+ "normalized": false,
256
+ "special": true
257
+ },
258
+ {
259
+ "id": 528,
260
+ "content": "</ref>",
261
+ "single_word": false,
262
+ "lstrip": false,
263
+ "rstrip": false,
264
+ "normalized": false,
265
+ "special": true
266
+ },
267
+ {
268
+ "id": 529,
269
+ "content": "<box>",
270
+ "single_word": false,
271
+ "lstrip": false,
272
+ "rstrip": false,
273
+ "normalized": false,
274
+ "special": true
275
+ },
276
+ {
277
+ "id": 530,
278
+ "content": "</box>",
279
+ "single_word": false,
280
+ "lstrip": false,
281
+ "rstrip": false,
282
+ "normalized": false,
283
+ "special": true
284
+ },
285
+ {
286
+ "id": 531,
287
+ "content": "<video>",
288
+ "single_word": false,
289
+ "lstrip": false,
290
+ "rstrip": false,
291
+ "normalized": false,
292
+ "special": true
293
+ }
294
+ ],
295
+ "normalizer": {
296
+ "type": "NFC"
297
+ },
298
+ "pre_tokenizer": {
299
+ "type": "Sequence",
300
+ "pretokenizers": [
301
+ {
302
+ "type": "Split",
303
+ "pattern": {
304
+ "Regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?\\p{L}+|\\p{N}| ?[^\\s\\p{L}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+"
305
+ },
306
+ "behavior": "Isolated",
307
+ "invert": false
308
+ },
309
+ {
310
+ "type": "ByteLevel",
311
+ "add_prefix_space": false,
312
+ "trim_offsets": false,
313
+ "use_regex": false
314
+ }
315
+ ]
316
+ },
317
+ "post_processor": {
318
+ "type": "ByteLevel",
319
+ "add_prefix_space": false,
320
+ "trim_offsets": false,
321
+ "use_regex": false
322
+ },
323
+ "decoder": {
324
+ "type": "ByteLevel",
325
+ "add_prefix_space": false,
326
+ "trim_offsets": false,
327
+ "use_regex": false
328
+ },
329
+ "model": {
330
+ "type": "BPE",
331
+ "dropout": null,
332
+ "unk_token": null,
333
+ "continuing_subword_prefix": "",
334
+ "end_of_word_suffix": "",
335
+ "fuse_unk": false,
336
+ "byte_fallback": false,
337
+ "ignore_merges": false,
338
+ "vocab": {
339
+ "!": 0,
340
+ "\"": 1,
341
+ "#": 2,
342
+ "$": 3,
343
+ "%": 4,
344
+ "&": 5,
345
+ "'": 6,
346
+ "(": 7,
347
+ ")": 8,
348
+ "*": 9,
349
+ "+": 10,
350
+ ",": 11,
351
+ "-": 12,
352
+ ".": 13,
353
+ "/": 14,
354
+ "0": 15,
355
+ "1": 16,
356
+ "2": 17,
357
+ "3": 18,
358
+ "4": 19,
359
+ "5": 20,
360
+ "6": 21,
361
+ "7": 22,
362
+ "8": 23,
363
+ "9": 24,
364
+ ":": 25,
365
+ ";": 26,
366
+ "<": 27,
367
+ "=": 28,
368
+ ">": 29,
369
+ "?": 30,
370
+ "@": 31,
371
+ "A": 32,
372
+ "B": 33,
373
+ "C": 34,
374
+ "D": 35,
375
+ "E": 36,
376
+ "F": 37,
377
+ "G": 38,
378
+ "H": 39,
379
+ "I": 40,
380
+ "J": 41,
381
+ "K": 42,
382
+ "L": 43,
383
+ "M": 44,
384
+ "N": 45,
385
+ "O": 46,
386
+ "P": 47,
387
+ "Q": 48,
388
+ "R": 49,
389
+ "S": 50,
390
+ "T": 51,
391
+ "U": 52,
392
+ "V": 53,
393
+ "W": 54,
394
+ "X": 55,
395
+ "Y": 56,
396
+ "Z": 57,
397
+ "[": 58,
398
+ "\\": 59,
399
+ "]": 60,
400
+ "^": 61,
401
+ "_": 62,
402
+ "`": 63,
403
+ "a": 64,
404
+ "b": 65,
405
+ "c": 66,
406
+ "d": 67,
407
+ "e": 68,
408
+ "f": 69,
409
+ "g": 70,
410
+ "h": 71,
411
+ "i": 72,
412
+ "j": 73,
413
+ "k": 74,
414
+ "l": 75,
415
+ "m": 76,
416
+ "n": 77,
417
+ "o": 78,
418
+ "p": 79,
419
+ "q": 80,
420
+ "r": 81,
421
+ "s": 82,
422
+ "t": 83,
423
+ "u": 84,
424
+ "v": 85,
425
+ "w": 86,
426
+ "x": 87,
427
+ "y": 88,
428
+ "z": 89,
429
+ "{": 90,
430
+ "|": 91,
431
+ "}": 92,
432
+ "~": 93,
433
+ "¡": 94,
434
+ "¢": 95,
435
+ "£": 96,
436
+ "¤": 97,
437
+ "¥": 98,
438
+ "¦": 99,
439
+ "§": 100,
440
+ "¨": 101,
441
+ "©": 102,
442
+ "ª": 103,
443
+ "«": 104,
444
+ "¬": 105,
445
+ "®": 106,
446
+ "¯": 107,
447
+ "°": 108,
448
+ "±": 109,
449
+ "²": 110,
450
+ "³": 111,
451
+ "´": 112,
452
+ "µ": 113,
453
+ "¶": 114,
454
+ "·": 115,
455
+ "¸": 116,
456
+ "¹": 117,
457
+ "º": 118,
458
+ "»": 119,
459
+ "¼": 120,
460
+ "½": 121,
461
+ "¾": 122,
462
+ "¿": 123,
463
+ "À": 124,
464
+ "Á": 125,
465
+ "Â": 126,
466
+ "Ã": 127,
467
+ "Ä": 128,
468
+ "Å": 129,
469
+ "Æ": 130,
470
+ "Ç": 131,
471
+ "È": 132,
472
+ "É": 133,
473
+ "Ê": 134,
474
+ "Ë": 135,
475
+ "Ì": 136,
476
+ "Í": 137,
477
+ "Î": 138,
478
+ "Ï": 139,
479
+ "Ð": 140,
480
+ "Ñ": 141,
481
+ "Ò": 142,
482
+ "Ó": 143,
483
+ "Ô": 144,
484
+ "Õ": 145,
485
+ "Ö": 146,
486
+ "×": 147,
487
+ "Ø": 148,
488
+ "Ù": 149,
489
+ "Ú": 150,
490
+ "Û": 151,
491
+ "Ü": 152,
492
+ "Ý": 153,
493
+ "Þ": 154,
494
+ "ß": 155,
495
+ "à": 156,
496
+ "á": 157,
497
+ "â": 158,
498
+ "ã": 159,
499
+ "ä": 160,
500
+ "å": 161,
501
+ "æ": 162,
502
+ "ç": 163,
503
+ "è": 164,
504
+ "é": 165,
505
+ "ê": 166,
506
+ "ë": 167,
507
+ "ì": 168,
508
+ "í": 169,
509
+ "î": 170,
510
+ "ï": 171,
511
+ "ð": 172,
512
+ "ñ": 173,
513
+ "ò": 174,
514
+ "ó": 175,
515
+ "ô": 176,
516
+ "õ": 177,
517
+ "ö": 178,
518
+ "÷": 179,
519
+ "ø": 180,
520
+ "ù": 181,
521
+ "ú": 182,
522
+ "û": 183,
523
+ "ü": 184,
524
+ "ý": 185,
525
+ "þ": 186,
526
+ "ÿ": 187,
527
+ "Ā": 188,
528
+ "ā": 189,
529
+ "Ă": 190,
530
+ "ă": 191,
531
+ "Ą": 192,
532
+ "ą": 193,
533
+ "Ć": 194,
534
+ "ć": 195,
535
+ "Ĉ": 196,
536
+ "ĉ": 197,
537
+ "Ċ": 198,
538
+ "ċ": 199,
539
+ "Č": 200,
540
+ "č": 201,
541
+ "Ď": 202,
542
+ "ď": 203,
543
+ "Đ": 204,
544
+ "đ": 205,
545
+ "Ē": 206,
546
+ "ē": 207,
547
+ "Ĕ": 208,
548
+ "ĕ": 209,
549
+ "Ė": 210,
550
+ "ė": 211,
551
+ "Ę": 212,
552
+ "ę": 213,
553
+ "Ě": 214,
554
+ "ě": 215,
555
+ "Ĝ": 216,
556
+ "ĝ": 217,
557
+ "Ğ": 218,
558
+ "ğ": 219,
559
+ "Ġ": 220,
560
+ "ġ": 221,
561
+ "Ģ": 222,
562
+ "ģ": 223,
563
+ "Ĥ": 224,
564
+ "ĥ": 225,
565
+ "Ħ": 226,
566
+ "ħ": 227,
567
+ "Ĩ": 228,
568
+ "ĩ": 229,
569
+ "Ī": 230,
570
+ "ī": 231,
571
+ "Ĭ": 232,
572
+ "ĭ": 233,
573
+ "Į": 234,
574
+ "į": 235,
575
+ "İ": 236,
576
+ "ı": 237,
577
+ "IJ": 238,
578
+ "ij": 239,
579
+ "Ĵ": 240,
580
+ "ĵ": 241,
581
+ "Ķ": 242,
582
+ "ķ": 243,
583
+ "ĸ": 244,
584
+ "Ĺ": 245,
585
+ "ĺ": 246,
586
+ "Ļ": 247,
587
+ "ļ": 248,
588
+ "Ľ": 249,
589
+ "ľ": 250,
590
+ "Ŀ": 251,
591
+ "ŀ": 252,
592
+ "Ł": 253,
593
+ "ł": 254,
594
+ "Ń": 255,
595
+ "ĠĠ": 256,
596
+ "ĠĠĠĠ": 257,
597
+ "in": 258,
598
+ "Ġt": 259,
599
+ "ĠĠĠĠĠĠĠĠ": 260,
600
+ "er": 261,
601
+ "ĠĠĠ": 262,
602
+ "on": 263,
603
+ "Ġa": 264,
604
+ "re": 265,
605
+ "at": 266,
606
+ "st": 267,
607
+ "en": 268,
608
+ "or": 269,
609
+ "Ġth": 270,
610
+ "ĊĊ": 271,
611
+ "Ġc": 272,
612
+ "le": 273,
613
+ "Ġs": 274,
614
+ "it": 275,
615
+ "an": 276,
616
+ "ar": 277,
617
+ "al": 278,
618
+ "Ġthe": 279,
619
+ ";Ċ": 280,
620
+ "Ġp": 281,
621
+ "Ġf": 282,
622
+ "ou": 283,
623
+ "Ġ=": 284,
624
+ "is": 285,
625
+ "ĠĠĠĠĠĠĠ": 286,
626
+ "ing": 287,
627
+ "es": 288,
628
+ "Ġw": 289,
629
+ "ion": 290,
630
+ "ed": 291,
631
+ "ic": 292,
632
+ "Ġb": 293,
633
+ "Ġd": 294,
634
+ "et": 295,
635
+ "Ġm": 296,
636
+ "Ġo": 297,
637
+ "ĉĉ": 298,
638
+ "ro": 299,
639
+ "as": 300,
640
+ "el": 301,
641
+ "ct": 302,
642
+ "nd": 303,
643
+ "Ġin": 304,
644
+ "Ġh": 305,
645
+ "ent": 306,
646
+ "id": 307,
647
+ "Ġn": 308,
648
+ "am": 309,
649
+ "ĠĠĠĠĠĠĠĠĠĠĠ": 310,
650
+ "Ġto": 311,
651
+ "Ġre": 312,
652
+ "--": 313,
653
+ "Ġ{": 314,
654
+ "Ġof": 315,
655
+ "om": 316,
656
+ ");Ċ": 317,
657
+ "im": 318,
658
+ "čĊ": 319,
659
+ "Ġ(": 320,
660
+ "il": 321,
661
+ "//": 322,
662
+ "Ġand": 323,
663
+ "ur": 324,
664
+ "se": 325,
665
+ "Ġl": 326,
666
+ "ex": 327,
667
+ "ĠS": 328,
668
+ "ad": 329,
669
+ "Ġ\"": 330,
670
+ "ch": 331,
671
+ "ut": 332,
672
+ "if": 333,
673
+ "**": 334,
674
+ "Ġ}": 335,
675
+ "em": 336,
676
+ "ol": 337,
677
+ "ĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠ": 338,
678
+ "th": 339,
679
+ ")Ċ": 340,
680
+ "Ġ{Ċ": 341,
681
+ "Ġg": 342,
682
+ "ig": 343,
683
+ "iv": 344,
684
+ ",Ċ": 345,
685
+ "ce": 346,
686
+ "od": 347,
687
+ "Ġv": 348,
688
+ "ate": 349,
689
+ "ĠT": 350,
690
+ "ag": 351,
691
+ "ay": 352,
692
+ "Ġ*": 353,
693
+ "ot": 354,
694
+ "us": 355,
695
+ "ĠC": 356,
696
+ "Ġst": 357,
697
+ "ĠI": 358,
698
+ "un": 359,
699
+ "ul": 360,
700
+ "ue": 361,
701
+ "ĠA": 362,
702
+ "ow": 363,
703
+ "Ġ'": 364,
704
+ "ew": 365,
705
+ "Ġ<": 366,
706
+ "ation": 367,
707
+ "()": 368,
708
+ "Ġfor": 369,
709
+ "ab": 370,
710
+ "ort": 371,
711
+ "um": 372,
712
+ "ame": 373,
713
+ "Ġis": 374,
714
+ "pe": 375,
715
+ "tr": 376,
716
+ "ck": 377,
717
+ "âĢ": 378,
718
+ "Ġy": 379,
719
+ "ist": 380,
720
+ "----": 381,
721
+ ".ĊĊ": 382,
722
+ "he": 383,
723
+ "Ġe": 384,
724
+ "lo": 385,
725
+ "ĠM": 386,
726
+ "Ġbe": 387,
727
+ "ers": 388,
728
+ "Ġon": 389,
729
+ "Ġcon": 390,
730
+ "ap": 391,
731
+ "ub": 392,
732
+ "ĠP": 393,
733
+ "ĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠ": 394,
734
+ "ass": 395,
735
+ "int": 396,
736
+ ">Ċ": 397,
737
+ "ly": 398,
738
+ "urn": 399,
739
+ "Ġ$": 400,
740
+ ";ĊĊ": 401,
741
+ "av": 402,
742
+ "port": 403,
743
+ "ir": 404,
744
+ "->": 405,
745
+ "nt": 406,
746
+ "ction": 407,
747
+ "end": 408,
748
+ "Ġde": 409,
749
+ "ith": 410,
750
+ "out": 411,
751
+ "turn": 412,
752
+ "our": 413,
753
+ "ĠĠĠĠĠ": 414,
754
+ "lic": 415,
755
+ "res": 416,
756
+ "pt": 417,
757
+ "==": 418,
758
+ "Ġthis": 419,
759
+ "Ġwh": 420,
760
+ "Ġif": 421,
761
+ "ĠD": 422,
762
+ "ver": 423,
763
+ "age": 424,
764
+ "ĠB": 425,
765
+ "ht": 426,
766
+ "ext": 427,
767
+ "=\"": 428,
768
+ "Ġthat": 429,
769
+ "****": 430,
770
+ "ĠR": 431,
771
+ "Ġit": 432,
772
+ "ess": 433,
773
+ "ĠF": 434,
774
+ "Ġr": 435,
775
+ "os": 436,
776
+ "and": 437,
777
+ "Ġas": 438,
778
+ "ect": 439,
779
+ "ke": 440,
780
+ "rom": 441,
781
+ "Ġ//": 442,
782
+ "con": 443,
783
+ "ĠL": 444,
784
+ "(\"": 445,
785
+ "qu": 446,
786
+ "lass": 447,
787
+ "Ġwith": 448,
788
+ "iz": 449,
789
+ "de": 450,
790
+ "ĠN": 451,
791
+ "Ġal": 452,
792
+ "op": 453,
793
+ "up": 454,
794
+ "get": 455,
795
+ "Ġ}Ċ": 456,
796
+ "ile": 457,
797
+ "Ġan": 458,
798
+ "ata": 459,
799
+ "ore": 460,
800
+ "ri": 461,
801
+ "Ġpro": 462,
802
+ ";čĊ": 463,
803
+ "ĉĉĉĉ": 464,
804
+ "ter": 465,
805
+ "ain": 466,
806
+ "ĠW": 467,
807
+ "ĠE": 468,
808
+ "Ġcom": 469,
809
+ "Ġreturn": 470,
810
+ "art": 471,
811
+ "ĠH": 472,
812
+ "ack": 473,
813
+ "import": 474,
814
+ "ublic": 475,
815
+ "Ġor": 476,
816
+ "est": 477,
817
+ "ment": 478,
818
+ "ĠG": 479,
819
+ "able": 480,
820
+ "Ġ-": 481,
821
+ "ine": 482,
822
+ "ill": 483,
823
+ "ind": 484,
824
+ "ere": 485,
825
+ "::": 486,
826
+ "ity": 487,
827
+ "Ġ+": 488,
828
+ "Ġtr": 489,
829
+ "elf": 490,
830
+ "ight": 491,
831
+ "('": 492,
832
+ "orm": 493,
833
+ "ult": 494,
834
+ "str": 495,
835
+ "..": 496,
836
+ "\",": 497,
837
+ "Ġyou": 498,
838
+ "ype": 499
839
+ },
840
+ "merges": [
841
+ [
842
+ "Ġ",
843
+ "Ġ"
844
+ ],
845
+ [
846
+ "ĠĠ",
847
+ "ĠĠ"
848
+ ],
849
+ [
850
+ "i",
851
+ "n"
852
+ ],
853
+ [
854
+ "Ġ",
855
+ "t"
856
+ ],
857
+ [
858
+ "ĠĠĠĠ",
859
+ "ĠĠĠĠ"
860
+ ],
861
+ [
862
+ "e",
863
+ "r"
864
+ ],
865
+ [
866
+ "ĠĠ",
867
+ "Ġ"
868
+ ],
869
+ [
870
+ "o",
871
+ "n"
872
+ ],
873
+ [
874
+ "Ġ",
875
+ "a"
876
+ ],
877
+ [
878
+ "r",
879
+ "e"
880
+ ],
881
+ [
882
+ "a",
883
+ "t"
884
+ ],
885
+ [
886
+ "s",
887
+ "t"
888
+ ],
889
+ [
890
+ "e",
891
+ "n"
892
+ ],
893
+ [
894
+ "o",
895
+ "r"
896
+ ],
897
+ [
898
+ "Ġt",
899
+ "h"
900
+ ],
901
+ [
902
+ "Ċ",
903
+ "Ċ"
904
+ ],
905
+ [
906
+ "Ġ",
907
+ "c"
908
+ ],
909
+ [
910
+ "l",
911
+ "e"
912
+ ],
913
+ [
914
+ "Ġ",
915
+ "s"
916
+ ],
917
+ [
918
+ "i",
919
+ "t"
920
+ ],
921
+ [
922
+ "a",
923
+ "n"
924
+ ],
925
+ [
926
+ "a",
927
+ "r"
928
+ ],
929
+ [
930
+ "a",
931
+ "l"
932
+ ],
933
+ [
934
+ "Ġth",
935
+ "e"
936
+ ],
937
+ [
938
+ ";",
939
+ "Ċ"
940
+ ],
941
+ [
942
+ "Ġ",
943
+ "p"
944
+ ],
945
+ [
946
+ "Ġ",
947
+ "f"
948
+ ],
949
+ [
950
+ "o",
951
+ "u"
952
+ ],
953
+ [
954
+ "Ġ",
955
+ "="
956
+ ],
957
+ [
958
+ "i",
959
+ "s"
960
+ ],
961
+ [
962
+ "ĠĠĠĠ",
963
+ "ĠĠĠ"
964
+ ],
965
+ [
966
+ "in",
967
+ "g"
968
+ ],
969
+ [
970
+ "e",
971
+ "s"
972
+ ],
973
+ [
974
+ "Ġ",
975
+ "w"
976
+ ],
977
+ [
978
+ "i",
979
+ "on"
980
+ ],
981
+ [
982
+ "e",
983
+ "d"
984
+ ],
985
+ [
986
+ "i",
987
+ "c"
988
+ ],
989
+ [
990
+ "Ġ",
991
+ "b"
992
+ ],
993
+ [
994
+ "Ġ",
995
+ "d"
996
+ ],
997
+ [
998
+ "e",
999
+ "t"
1000
+ ],
1001
+ [
1002
+ "Ġ",
1003
+ "m"
1004
+ ],
1005
+ [
1006
+ "Ġ",
1007
+ "o"
1008
+ ],
1009
+ [
1010
+ "ĉ",
1011
+ "ĉ"
1012
+ ],
1013
+ [
1014
+ "r",
1015
+ "o"
1016
+ ],
1017
+ [
1018
+ "a",
1019
+ "s"
1020
+ ],
1021
+ [
1022
+ "e",
1023
+ "l"
1024
+ ],
1025
+ [
1026
+ "c",
1027
+ "t"
1028
+ ],
1029
+ [
1030
+ "n",
1031
+ "d"
1032
+ ],
1033
+ [
1034
+ "Ġ",
1035
+ "in"
1036
+ ],
1037
+ [
1038
+ "Ġ",
1039
+ "h"
1040
+ ],
1041
+ [
1042
+ "en",
1043
+ "t"
1044
+ ],
1045
+ [
1046
+ "i",
1047
+ "d"
1048
+ ],
1049
+ [
1050
+ "Ġ",
1051
+ "n"
1052
+ ],
1053
+ [
1054
+ "a",
1055
+ "m"
1056
+ ],
1057
+ [
1058
+ "ĠĠĠĠĠĠĠĠ",
1059
+ "ĠĠĠ"
1060
+ ],
1061
+ [
1062
+ "Ġt",
1063
+ "o"
1064
+ ],
1065
+ [
1066
+ "Ġ",
1067
+ "re"
1068
+ ],
1069
+ [
1070
+ "-",
1071
+ "-"
1072
+ ],
1073
+ [
1074
+ "Ġ",
1075
+ "{"
1076
+ ],
1077
+ [
1078
+ "Ġo",
1079
+ "f"
1080
+ ],
1081
+ [
1082
+ "o",
1083
+ "m"
1084
+ ],
1085
+ [
1086
+ ")",
1087
+ ";Ċ"
1088
+ ],
1089
+ [
1090
+ "i",
1091
+ "m"
1092
+ ],
1093
+ [
1094
+ "č",
1095
+ "Ċ"
1096
+ ],
1097
+ [
1098
+ "Ġ",
1099
+ "("
1100
+ ],
1101
+ [
1102
+ "i",
1103
+ "l"
1104
+ ],
1105
+ [
1106
+ "/",
1107
+ "/"
1108
+ ],
1109
+ [
1110
+ "Ġa",
1111
+ "nd"
1112
+ ],
1113
+ [
1114
+ "u",
1115
+ "r"
1116
+ ],
1117
+ [
1118
+ "s",
1119
+ "e"
1120
+ ],
1121
+ [
1122
+ "Ġ",
1123
+ "l"
1124
+ ],
1125
+ [
1126
+ "e",
1127
+ "x"
1128
+ ],
1129
+ [
1130
+ "Ġ",
1131
+ "S"
1132
+ ],
1133
+ [
1134
+ "a",
1135
+ "d"
1136
+ ],
1137
+ [
1138
+ "Ġ",
1139
+ "\""
1140
+ ],
1141
+ [
1142
+ "c",
1143
+ "h"
1144
+ ],
1145
+ [
1146
+ "u",
1147
+ "t"
1148
+ ],
1149
+ [
1150
+ "i",
1151
+ "f"
1152
+ ],
1153
+ [
1154
+ "*",
1155
+ "*"
1156
+ ],
1157
+ [
1158
+ "Ġ",
1159
+ "}"
1160
+ ],
1161
+ [
1162
+ "e",
1163
+ "m"
1164
+ ],
1165
+ [
1166
+ "o",
1167
+ "l"
1168
+ ],
1169
+ [
1170
+ "ĠĠĠĠĠĠĠĠ",
1171
+ "ĠĠĠĠĠĠĠĠ"
1172
+ ],
1173
+ [
1174
+ "t",
1175
+ "h"
1176
+ ],
1177
+ [
1178
+ ")",
1179
+ "Ċ"
1180
+ ],
1181
+ [
1182
+ "Ġ{",
1183
+ "Ċ"
1184
+ ],
1185
+ [
1186
+ "Ġ",
1187
+ "g"
1188
+ ],
1189
+ [
1190
+ "i",
1191
+ "g"
1192
+ ],
1193
+ [
1194
+ "i",
1195
+ "v"
1196
+ ],
1197
+ [
1198
+ ",",
1199
+ "Ċ"
1200
+ ],
1201
+ [
1202
+ "c",
1203
+ "e"
1204
+ ],
1205
+ [
1206
+ "o",
1207
+ "d"
1208
+ ],
1209
+ [
1210
+ "Ġ",
1211
+ "v"
1212
+ ],
1213
+ [
1214
+ "at",
1215
+ "e"
1216
+ ],
1217
+ [
1218
+ "Ġ",
1219
+ "T"
1220
+ ],
1221
+ [
1222
+ "a",
1223
+ "g"
1224
+ ],
1225
+ [
1226
+ "a",
1227
+ "y"
1228
+ ],
1229
+ [
1230
+ "Ġ",
1231
+ "*"
1232
+ ],
1233
+ [
1234
+ "o",
1235
+ "t"
1236
+ ],
1237
+ [
1238
+ "u",
1239
+ "s"
1240
+ ],
1241
+ [
1242
+ "Ġ",
1243
+ "C"
1244
+ ],
1245
+ [
1246
+ "Ġ",
1247
+ "st"
1248
+ ],
1249
+ [
1250
+ "Ġ",
1251
+ "I"
1252
+ ],
1253
+ [
1254
+ "u",
1255
+ "n"
1256
+ ],
1257
+ [
1258
+ "u",
1259
+ "l"
1260
+ ],
1261
+ [
1262
+ "u",
1263
+ "e"
1264
+ ],
1265
+ [
1266
+ "Ġ",
1267
+ "A"
1268
+ ],
1269
+ [
1270
+ "o",
1271
+ "w"
1272
+ ],
1273
+ [
1274
+ "Ġ",
1275
+ "'"
1276
+ ],
1277
+ [
1278
+ "e",
1279
+ "w"
1280
+ ],
1281
+ [
1282
+ "Ġ",
1283
+ "<"
1284
+ ],
1285
+ [
1286
+ "at",
1287
+ "ion"
1288
+ ],
1289
+ [
1290
+ "(",
1291
+ ")"
1292
+ ],
1293
+ [
1294
+ "Ġf",
1295
+ "or"
1296
+ ],
1297
+ [
1298
+ "a",
1299
+ "b"
1300
+ ],
1301
+ [
1302
+ "or",
1303
+ "t"
1304
+ ],
1305
+ [
1306
+ "u",
1307
+ "m"
1308
+ ],
1309
+ [
1310
+ "am",
1311
+ "e"
1312
+ ],
1313
+ [
1314
+ "Ġ",
1315
+ "is"
1316
+ ],
1317
+ [
1318
+ "p",
1319
+ "e"
1320
+ ],
1321
+ [
1322
+ "t",
1323
+ "r"
1324
+ ],
1325
+ [
1326
+ "c",
1327
+ "k"
1328
+ ],
1329
+ [
1330
+ "â",
1331
+ "Ģ"
1332
+ ],
1333
+ [
1334
+ "Ġ",
1335
+ "y"
1336
+ ],
1337
+ [
1338
+ "i",
1339
+ "st"
1340
+ ],
1341
+ [
1342
+ "--",
1343
+ "--"
1344
+ ],
1345
+ [
1346
+ ".",
1347
+ "ĊĊ"
1348
+ ],
1349
+ [
1350
+ "h",
1351
+ "e"
1352
+ ],
1353
+ [
1354
+ "Ġ",
1355
+ "e"
1356
+ ],
1357
+ [
1358
+ "l",
1359
+ "o"
1360
+ ],
1361
+ [
1362
+ "Ġ",
1363
+ "M"
1364
+ ],
1365
+ [
1366
+ "Ġb",
1367
+ "e"
1368
+ ],
1369
+ [
1370
+ "er",
1371
+ "s"
1372
+ ],
1373
+ [
1374
+ "Ġ",
1375
+ "on"
1376
+ ],
1377
+ [
1378
+ "Ġc",
1379
+ "on"
1380
+ ],
1381
+ [
1382
+ "a",
1383
+ "p"
1384
+ ],
1385
+ [
1386
+ "u",
1387
+ "b"
1388
+ ],
1389
+ [
1390
+ "Ġ",
1391
+ "P"
1392
+ ],
1393
+ [
1394
+ "ĠĠĠĠĠĠĠĠ",
1395
+ "ĠĠĠĠĠĠĠ"
1396
+ ],
1397
+ [
1398
+ "as",
1399
+ "s"
1400
+ ],
1401
+ [
1402
+ "in",
1403
+ "t"
1404
+ ],
1405
+ [
1406
+ ">",
1407
+ "Ċ"
1408
+ ],
1409
+ [
1410
+ "l",
1411
+ "y"
1412
+ ],
1413
+ [
1414
+ "ur",
1415
+ "n"
1416
+ ],
1417
+ [
1418
+ "Ġ",
1419
+ "$"
1420
+ ],
1421
+ [
1422
+ ";",
1423
+ "ĊĊ"
1424
+ ],
1425
+ [
1426
+ "a",
1427
+ "v"
1428
+ ],
1429
+ [
1430
+ "p",
1431
+ "ort"
1432
+ ],
1433
+ [
1434
+ "i",
1435
+ "r"
1436
+ ],
1437
+ [
1438
+ "-",
1439
+ ">"
1440
+ ],
1441
+ [
1442
+ "n",
1443
+ "t"
1444
+ ],
1445
+ [
1446
+ "ct",
1447
+ "ion"
1448
+ ],
1449
+ [
1450
+ "en",
1451
+ "d"
1452
+ ],
1453
+ [
1454
+ "Ġd",
1455
+ "e"
1456
+ ],
1457
+ [
1458
+ "it",
1459
+ "h"
1460
+ ],
1461
+ [
1462
+ "ou",
1463
+ "t"
1464
+ ],
1465
+ [
1466
+ "t",
1467
+ "urn"
1468
+ ],
1469
+ [
1470
+ "ou",
1471
+ "r"
1472
+ ],
1473
+ [
1474
+ "ĠĠĠĠ",
1475
+ "Ġ"
1476
+ ],
1477
+ [
1478
+ "l",
1479
+ "ic"
1480
+ ],
1481
+ [
1482
+ "re",
1483
+ "s"
1484
+ ],
1485
+ [
1486
+ "p",
1487
+ "t"
1488
+ ],
1489
+ [
1490
+ "=",
1491
+ "="
1492
+ ],
1493
+ [
1494
+ "Ġth",
1495
+ "is"
1496
+ ],
1497
+ [
1498
+ "Ġw",
1499
+ "h"
1500
+ ],
1501
+ [
1502
+ "Ġ",
1503
+ "if"
1504
+ ],
1505
+ [
1506
+ "Ġ",
1507
+ "D"
1508
+ ],
1509
+ [
1510
+ "v",
1511
+ "er"
1512
+ ],
1513
+ [
1514
+ "ag",
1515
+ "e"
1516
+ ],
1517
+ [
1518
+ "Ġ",
1519
+ "B"
1520
+ ],
1521
+ [
1522
+ "h",
1523
+ "t"
1524
+ ],
1525
+ [
1526
+ "ex",
1527
+ "t"
1528
+ ],
1529
+ [
1530
+ "=",
1531
+ "\""
1532
+ ],
1533
+ [
1534
+ "Ġth",
1535
+ "at"
1536
+ ],
1537
+ [
1538
+ "**",
1539
+ "**"
1540
+ ],
1541
+ [
1542
+ "Ġ",
1543
+ "R"
1544
+ ],
1545
+ [
1546
+ "Ġ",
1547
+ "it"
1548
+ ],
1549
+ [
1550
+ "es",
1551
+ "s"
1552
+ ],
1553
+ [
1554
+ "Ġ",
1555
+ "F"
1556
+ ],
1557
+ [
1558
+ "Ġ",
1559
+ "r"
1560
+ ],
1561
+ [
1562
+ "o",
1563
+ "s"
1564
+ ],
1565
+ [
1566
+ "an",
1567
+ "d"
1568
+ ],
1569
+ [
1570
+ "Ġa",
1571
+ "s"
1572
+ ],
1573
+ [
1574
+ "e",
1575
+ "ct"
1576
+ ],
1577
+ [
1578
+ "k",
1579
+ "e"
1580
+ ],
1581
+ [
1582
+ "ro",
1583
+ "m"
1584
+ ],
1585
+ [
1586
+ "Ġ",
1587
+ "//"
1588
+ ],
1589
+ [
1590
+ "c",
1591
+ "on"
1592
+ ],
1593
+ [
1594
+ "Ġ",
1595
+ "L"
1596
+ ],
1597
+ [
1598
+ "(",
1599
+ "\""
1600
+ ],
1601
+ [
1602
+ "q",
1603
+ "u"
1604
+ ],
1605
+ [
1606
+ "l",
1607
+ "ass"
1608
+ ],
1609
+ [
1610
+ "Ġw",
1611
+ "ith"
1612
+ ],
1613
+ [
1614
+ "i",
1615
+ "z"
1616
+ ],
1617
+ [
1618
+ "d",
1619
+ "e"
1620
+ ],
1621
+ [
1622
+ "Ġ",
1623
+ "N"
1624
+ ],
1625
+ [
1626
+ "Ġa",
1627
+ "l"
1628
+ ],
1629
+ [
1630
+ "o",
1631
+ "p"
1632
+ ],
1633
+ [
1634
+ "u",
1635
+ "p"
1636
+ ],
1637
+ [
1638
+ "g",
1639
+ "et"
1640
+ ],
1641
+ [
1642
+ "Ġ}",
1643
+ "Ċ"
1644
+ ],
1645
+ [
1646
+ "i",
1647
+ "le"
1648
+ ],
1649
+ [
1650
+ "Ġa",
1651
+ "n"
1652
+ ],
1653
+ [
1654
+ "at",
1655
+ "a"
1656
+ ],
1657
+ [
1658
+ "o",
1659
+ "re"
1660
+ ],
1661
+ [
1662
+ "r",
1663
+ "i"
1664
+ ],
1665
+ [
1666
+ "Ġp",
1667
+ "ro"
1668
+ ],
1669
+ [
1670
+ ";",
1671
+ "čĊ"
1672
+ ],
1673
+ [
1674
+ "ĉĉ",
1675
+ "ĉĉ"
1676
+ ],
1677
+ [
1678
+ "t",
1679
+ "er"
1680
+ ],
1681
+ [
1682
+ "a",
1683
+ "in"
1684
+ ],
1685
+ [
1686
+ "Ġ",
1687
+ "W"
1688
+ ],
1689
+ [
1690
+ "Ġ",
1691
+ "E"
1692
+ ],
1693
+ [
1694
+ "Ġc",
1695
+ "om"
1696
+ ],
1697
+ [
1698
+ "Ġre",
1699
+ "turn"
1700
+ ],
1701
+ [
1702
+ "ar",
1703
+ "t"
1704
+ ],
1705
+ [
1706
+ "Ġ",
1707
+ "H"
1708
+ ],
1709
+ [
1710
+ "a",
1711
+ "ck"
1712
+ ],
1713
+ [
1714
+ "im",
1715
+ "port"
1716
+ ],
1717
+ [
1718
+ "ub",
1719
+ "lic"
1720
+ ],
1721
+ [
1722
+ "Ġ",
1723
+ "or"
1724
+ ],
1725
+ [
1726
+ "e",
1727
+ "st"
1728
+ ],
1729
+ [
1730
+ "m",
1731
+ "ent"
1732
+ ],
1733
+ [
1734
+ "Ġ",
1735
+ "G"
1736
+ ],
1737
+ [
1738
+ "ab",
1739
+ "le"
1740
+ ],
1741
+ [
1742
+ "Ġ",
1743
+ "-"
1744
+ ],
1745
+ [
1746
+ "in",
1747
+ "e"
1748
+ ],
1749
+ [
1750
+ "il",
1751
+ "l"
1752
+ ],
1753
+ [
1754
+ "in",
1755
+ "d"
1756
+ ],
1757
+ [
1758
+ "er",
1759
+ "e"
1760
+ ],
1761
+ [
1762
+ ":",
1763
+ ":"
1764
+ ],
1765
+ [
1766
+ "it",
1767
+ "y"
1768
+ ],
1769
+ [
1770
+ "Ġ",
1771
+ "+"
1772
+ ],
1773
+ [
1774
+ "Ġt",
1775
+ "r"
1776
+ ],
1777
+ [
1778
+ "el",
1779
+ "f"
1780
+ ],
1781
+ [
1782
+ "ig",
1783
+ "ht"
1784
+ ],
1785
+ [
1786
+ "(",
1787
+ "'"
1788
+ ],
1789
+ [
1790
+ "or",
1791
+ "m"
1792
+ ],
1793
+ [
1794
+ "ul",
1795
+ "t"
1796
+ ],
1797
+ [
1798
+ "st",
1799
+ "r"
1800
+ ],
1801
+ [
1802
+ ".",
1803
+ "."
1804
+ ],
1805
+ [
1806
+ "\"",
1807
+ ","
1808
+ ],
1809
+ [
1810
+ "Ġy",
1811
+ "ou"
1812
+ ],
1813
+ [
1814
+ "y",
1815
+ "pe"
1816
+ ]
1817
+ ]
1818
+ }
1819
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,306 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ },
181
+ "151665": {
182
+ "content": "<img>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": true
188
+ },
189
+ "151666": {
190
+ "content": "</img>",
191
+ "lstrip": false,
192
+ "normalized": false,
193
+ "rstrip": false,
194
+ "single_word": false,
195
+ "special": true
196
+ },
197
+ "151667": {
198
+ "content": "<IMG_CONTEXT>",
199
+ "lstrip": false,
200
+ "normalized": false,
201
+ "rstrip": false,
202
+ "single_word": false,
203
+ "special": true
204
+ },
205
+ "151668": {
206
+ "content": "<quad>",
207
+ "lstrip": false,
208
+ "normalized": false,
209
+ "rstrip": false,
210
+ "single_word": false,
211
+ "special": true
212
+ },
213
+ "151669": {
214
+ "content": "</quad>",
215
+ "lstrip": false,
216
+ "normalized": false,
217
+ "rstrip": false,
218
+ "single_word": false,
219
+ "special": true
220
+ },
221
+ "151670": {
222
+ "content": "<ref>",
223
+ "lstrip": false,
224
+ "normalized": false,
225
+ "rstrip": false,
226
+ "single_word": false,
227
+ "special": true
228
+ },
229
+ "151671": {
230
+ "content": "</ref>",
231
+ "lstrip": false,
232
+ "normalized": false,
233
+ "rstrip": false,
234
+ "single_word": false,
235
+ "special": true
236
+ },
237
+ "151672": {
238
+ "content": "<box>",
239
+ "lstrip": false,
240
+ "normalized": false,
241
+ "rstrip": false,
242
+ "single_word": false,
243
+ "special": true
244
+ },
245
+ "151673": {
246
+ "content": "</box>",
247
+ "lstrip": false,
248
+ "normalized": false,
249
+ "rstrip": false,
250
+ "single_word": false,
251
+ "special": true
252
+ },
253
+ "151674": {
254
+ "content": "<video>",
255
+ "lstrip": false,
256
+ "normalized": false,
257
+ "rstrip": false,
258
+ "single_word": false,
259
+ "special": true
260
+ }
261
+ },
262
+ "additional_special_tokens": [
263
+ "<|im_start|>",
264
+ "<|im_end|>",
265
+ "<|object_ref_start|>",
266
+ "<|object_ref_end|>",
267
+ "<|box_start|>",
268
+ "<|box_end|>",
269
+ "<|quad_start|>",
270
+ "<|quad_end|>",
271
+ "<|vision_start|>",
272
+ "<|vision_end|>",
273
+ "<|vision_pad|>",
274
+ "<|image_pad|>",
275
+ "<|video_pad|>",
276
+ "<img>",
277
+ "</img>",
278
+ "<IMG_CONTEXT>",
279
+ "<quad>",
280
+ "</quad>",
281
+ "<ref>",
282
+ "</ref>",
283
+ "<box>",
284
+ "</box>"
285
+ ],
286
+ "bos_token": null,
287
+ "clean_up_tokenization_spaces": false,
288
+ "context_image_token": "<IMG_CONTEXT>",
289
+ "end_image_token": "</img>",
290
+ "eos_token": "<|im_end|>",
291
+ "errors": "replace",
292
+ "extra_special_tokens": {
293
+ "context_image_token": "<IMG_CONTEXT>",
294
+ "end_image_token": "</img>",
295
+ "start_image_token": "<img>",
296
+ "video_token": "<video>"
297
+ },
298
+ "model_max_length": 8192,
299
+ "pad_token": "<|endoftext|>",
300
+ "return_token_type_ids": false,
301
+ "split_special_tokens": false,
302
+ "start_image_token": "<img>",
303
+ "tokenizer_class": "Qwen2Tokenizer",
304
+ "unk_token": null,
305
+ "video_token": "<video>"
306
+ }