hf-transformers-bot commited on
Commit
7006d31
·
verified ·
1 Parent(s): 95d04bd

Add tiny processor fixture for testing

Browse files
chat_template.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "chat_template": "<|begin_of_text|>{% for message in messages %}{{message['role'].capitalize()}}{% if message['content'][0]['type'] == 'image' %}{{':'}}{% else %}{{': '}}{% endif %}{% for line in message['content'] %}{% if line['type'] == 'text' %}{{line['text']}}{% elif line['type'] == 'image' %}{{ '<image>' }}{% endif %}{% endfor %}<end_of_utterance>\n{% endfor %}{% if add_generation_prompt %}{{ 'Assistant:' }}{% endif %}"
3
+ }
config.json ADDED
@@ -0,0 +1,260 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Idefics3ForConditionalGeneration"
4
+ ],
5
+ "image_token_id": 128257,
6
+ "model_type": "idefics3",
7
+ "scale_factor": 2,
8
+ "text_config": {
9
+ "_flash_attn_2_enabled": true,
10
+ "_name_or_path": "None",
11
+ "add_cross_attention": false,
12
+ "architectures": [
13
+ "Idefics3ForVisionText2Text"
14
+ ],
15
+ "attention_bias": false,
16
+ "attention_dropout": 0.0,
17
+ "auto_map": {
18
+ "AutoConfig": "configuration_idefics3.Idefics3Config",
19
+ "AutoModelForCausalLM": "modeling_idefics3.Idefics3ForVisionText2Text"
20
+ },
21
+ "bad_words_ids": null,
22
+ "begin_suppress_tokens": null,
23
+ "bos_token_id": 128000,
24
+ "chunk_size_feed_forward": 0,
25
+ "cross_attention_hidden_size": null,
26
+ "decoder_start_token_id": null,
27
+ "diversity_penalty": 0.0,
28
+ "do_sample": false,
29
+ "early_stopping": false,
30
+ "encoder_no_repeat_ngram_size": 0,
31
+ "eos_token_id": [
32
+ 128001,
33
+ 128008,
34
+ 128009
35
+ ],
36
+ "exponential_decay_length_penalty": null,
37
+ "finetuning_task": null,
38
+ "forced_bos_token_id": null,
39
+ "forced_eos_token_id": null,
40
+ "hidden_act": "silu",
41
+ "hidden_size": 4096,
42
+ "id2label": {
43
+ "0": "LABEL_0",
44
+ "1": "LABEL_1"
45
+ },
46
+ "initializer_range": 0.02,
47
+ "intermediate_size": 14336,
48
+ "is_decoder": false,
49
+ "is_encoder_decoder": false,
50
+ "label2id": {
51
+ "LABEL_0": 0,
52
+ "LABEL_1": 1
53
+ },
54
+ "length_penalty": 1.0,
55
+ "max_length": 20,
56
+ "max_position_embeddings": 131072,
57
+ "min_length": 0,
58
+ "mlp_bias": false,
59
+ "model_type": "llama",
60
+ "neftune_noise_alpha": 0.0,
61
+ "no_repeat_ngram_size": 0,
62
+ "num_attention_heads": 32,
63
+ "num_beam_groups": 1,
64
+ "num_beams": 1,
65
+ "num_hidden_layers": 32,
66
+ "num_key_value_heads": 8,
67
+ "num_return_sequences": 1,
68
+ "output_attentions": false,
69
+ "output_hidden_states": false,
70
+ "output_scores": false,
71
+ "pad_token_id": 128002,
72
+ "perceiver_config": {
73
+ "_name_or_path": "",
74
+ "add_cross_attention": false,
75
+ "architectures": null,
76
+ "attention_dropout": 0.0,
77
+ "bad_words_ids": null,
78
+ "begin_suppress_tokens": null,
79
+ "bos_token_id": null,
80
+ "chunk_size_feed_forward": 0,
81
+ "cross_attention_hidden_size": null,
82
+ "decoder_start_token_id": null,
83
+ "diversity_penalty": 0.0,
84
+ "do_sample": false,
85
+ "early_stopping": false,
86
+ "encoder_no_repeat_ngram_size": 0,
87
+ "eos_token_id": null,
88
+ "exponential_decay_length_penalty": null,
89
+ "finetuning_task": null,
90
+ "forced_bos_token_id": null,
91
+ "forced_eos_token_id": null,
92
+ "hidden_act": "silu",
93
+ "id2label": {
94
+ "0": "LABEL_0",
95
+ "1": "LABEL_1"
96
+ },
97
+ "is_decoder": false,
98
+ "is_encoder_decoder": false,
99
+ "label2id": {
100
+ "LABEL_0": 0,
101
+ "LABEL_1": 1
102
+ },
103
+ "length_penalty": 1.0,
104
+ "max_length": 20,
105
+ "min_length": 0,
106
+ "model_type": "idefics3",
107
+ "no_repeat_ngram_size": 0,
108
+ "num_beam_groups": 1,
109
+ "num_beams": 1,
110
+ "num_key_value_heads": 1,
111
+ "num_return_sequences": 1,
112
+ "output_attentions": false,
113
+ "output_hidden_states": false,
114
+ "output_scores": false,
115
+ "pad_token_id": 128002,
116
+ "prefix": null,
117
+ "problem_type": null,
118
+ "pruned_heads": {},
119
+ "qk_layer_norms_perceiver": false,
120
+ "remove_invalid_values": false,
121
+ "repetition_penalty": 1.0,
122
+ "resampler_depth": 6,
123
+ "resampler_head_dim": 96,
124
+ "resampler_n_heads": 16,
125
+ "resampler_n_latents": 64,
126
+ "return_dict": true,
127
+ "return_dict_in_generate": false,
128
+ "sep_token_id": null,
129
+ "suppress_tokens": null,
130
+ "task_specific_params": null,
131
+ "temperature": 1.0,
132
+ "tf_legacy_loss": false,
133
+ "tie_encoder_decoder": false,
134
+ "tie_word_embeddings": true,
135
+ "tokenizer_class": null,
136
+ "top_k": 50,
137
+ "top_p": 1.0,
138
+ "torch_dtype": null,
139
+ "torchscript": false,
140
+ "transformers_version": "4.43.2",
141
+ "typical_p": 1.0,
142
+ "use_bfloat16": false
143
+ },
144
+ "prefix": null,
145
+ "pretraining_tp": 1,
146
+ "problem_type": null,
147
+ "pruned_heads": {},
148
+ "qk_layer_norms": false,
149
+ "remove_invalid_values": false,
150
+ "repetition_penalty": 1.0,
151
+ "return_dict": true,
152
+ "return_dict_in_generate": false,
153
+ "rms_norm_eps": 1e-05,
154
+ "rope_scaling": {
155
+ "factor": 8.0,
156
+ "high_freq_factor": 4.0,
157
+ "low_freq_factor": 1.0,
158
+ "original_max_position_embeddings": 8192,
159
+ "rope_type": "llama3"
160
+ },
161
+ "rope_theta": 500000.0,
162
+ "sep_token_id": null,
163
+ "suppress_tokens": null,
164
+ "task_specific_params": null,
165
+ "temperature": 1.0,
166
+ "tf_legacy_loss": false,
167
+ "tie_encoder_decoder": false,
168
+ "tie_word_embeddings": false,
169
+ "tokenizer_class": null,
170
+ "top_k": 50,
171
+ "top_p": 1.0,
172
+ "torch_dtype": "bfloat16",
173
+ "torchscript": false,
174
+ "typical_p": 1.0,
175
+ "use_bfloat16": false,
176
+ "use_cache": true,
177
+ "use_resampler": false,
178
+ "vocab_size": 128259
179
+ },
180
+ "tie_word_embeddings": false,
181
+ "torch_dtype": "bfloat16",
182
+ "transformers_version": "4.44.0.dev0",
183
+ "use_cache": true,
184
+ "vision_config": {
185
+ "_name_or_path": "",
186
+ "add_cross_attention": false,
187
+ "architectures": null,
188
+ "attention_dropout": 0.0,
189
+ "bad_words_ids": null,
190
+ "begin_suppress_tokens": null,
191
+ "bos_token_id": null,
192
+ "chunk_size_feed_forward": 0,
193
+ "cross_attention_hidden_size": null,
194
+ "decoder_start_token_id": null,
195
+ "diversity_penalty": 0.0,
196
+ "do_sample": false,
197
+ "early_stopping": false,
198
+ "encoder_no_repeat_ngram_size": 0,
199
+ "eos_token_id": null,
200
+ "exponential_decay_length_penalty": null,
201
+ "finetuning_task": null,
202
+ "forced_bos_token_id": null,
203
+ "forced_eos_token_id": null,
204
+ "hidden_act": "gelu_pytorch_tanh",
205
+ "hidden_size": 1152,
206
+ "id2label": {
207
+ "0": "LABEL_0",
208
+ "1": "LABEL_1"
209
+ },
210
+ "image_size": 364,
211
+ "initializer_range": 0.02,
212
+ "intermediate_size": 4304,
213
+ "is_decoder": false,
214
+ "is_encoder_decoder": false,
215
+ "label2id": {
216
+ "LABEL_0": 0,
217
+ "LABEL_1": 1
218
+ },
219
+ "layer_norm_eps": 1e-06,
220
+ "length_penalty": 1.0,
221
+ "max_length": 20,
222
+ "min_length": 0,
223
+ "model_type": "idefics3",
224
+ "no_repeat_ngram_size": 0,
225
+ "num_attention_heads": 16,
226
+ "num_beam_groups": 1,
227
+ "num_beams": 1,
228
+ "num_channels": 3,
229
+ "num_hidden_layers": 27,
230
+ "num_return_sequences": 1,
231
+ "old_vision_model_name": "/fsx/hugo/siglip-so400m-14-364-flash-attn2-navit",
232
+ "output_attentions": false,
233
+ "output_hidden_states": false,
234
+ "output_scores": false,
235
+ "pad_token_id": 128002,
236
+ "patch_size": 14,
237
+ "prefix": null,
238
+ "problem_type": null,
239
+ "pruned_heads": {},
240
+ "remove_invalid_values": false,
241
+ "repetition_penalty": 1.0,
242
+ "return_dict": true,
243
+ "return_dict_in_generate": false,
244
+ "sep_token_id": null,
245
+ "suppress_tokens": null,
246
+ "task_specific_params": null,
247
+ "temperature": 1.0,
248
+ "tf_legacy_loss": false,
249
+ "tie_encoder_decoder": false,
250
+ "tie_word_embeddings": true,
251
+ "tokenizer_class": null,
252
+ "top_k": 50,
253
+ "top_p": 1.0,
254
+ "torch_dtype": null,
255
+ "torchscript": false,
256
+ "typical_p": 1.0,
257
+ "use_bfloat16": false
258
+ },
259
+ "vocab_size": 500
260
+ }
generation_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 128000,
4
+ "eos_token_id": [
5
+ 128001,
6
+ 128008,
7
+ 128009,
8
+ 128258
9
+ ],
10
+ "pad_token_id": 128002,
11
+ "transformers_version": "4.44.0.dev0"
12
+ }
preprocessor_config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_convert_rgb": true,
3
+ "do_image_splitting": true,
4
+ "do_normalize": true,
5
+ "do_pad": true,
6
+ "do_rescale": true,
7
+ "do_resize": true,
8
+ "image_mean": [
9
+ 0.5,
10
+ 0.5,
11
+ 0.5
12
+ ],
13
+ "image_processor_type": "Idefics3ImageProcessor",
14
+ "image_std": [
15
+ 0.5,
16
+ 0.5,
17
+ 0.5
18
+ ],
19
+ "processor_class": "Idefics3Processor",
20
+ "resample": 1,
21
+ "rescale_factor": 0.00392156862745098,
22
+ "size": {
23
+ "longest_edge": 1456
24
+ }
25
+ }
tokenizer.json ADDED
@@ -0,0 +1,3241 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "1.0",
3
+ "truncation": null,
4
+ "padding": null,
5
+ "added_tokens": [
6
+ {
7
+ "id": 500,
8
+ "content": "<|begin_of_text|>",
9
+ "single_word": false,
10
+ "lstrip": false,
11
+ "rstrip": false,
12
+ "normalized": false,
13
+ "special": true
14
+ },
15
+ {
16
+ "id": 501,
17
+ "content": "<|end_of_text|>",
18
+ "single_word": false,
19
+ "lstrip": false,
20
+ "rstrip": false,
21
+ "normalized": false,
22
+ "special": true
23
+ },
24
+ {
25
+ "id": 502,
26
+ "content": "<|reserved_special_token_0|>",
27
+ "single_word": false,
28
+ "lstrip": false,
29
+ "rstrip": false,
30
+ "normalized": false,
31
+ "special": true
32
+ },
33
+ {
34
+ "id": 503,
35
+ "content": "<|reserved_special_token_1|>",
36
+ "single_word": false,
37
+ "lstrip": false,
38
+ "rstrip": false,
39
+ "normalized": false,
40
+ "special": true
41
+ },
42
+ {
43
+ "id": 504,
44
+ "content": "<|finetune_right_pad_id|>",
45
+ "single_word": false,
46
+ "lstrip": false,
47
+ "rstrip": false,
48
+ "normalized": false,
49
+ "special": true
50
+ },
51
+ {
52
+ "id": 505,
53
+ "content": "<|reserved_special_token_2|>",
54
+ "single_word": false,
55
+ "lstrip": false,
56
+ "rstrip": false,
57
+ "normalized": false,
58
+ "special": true
59
+ },
60
+ {
61
+ "id": 506,
62
+ "content": "<|start_header_id|>",
63
+ "single_word": false,
64
+ "lstrip": false,
65
+ "rstrip": false,
66
+ "normalized": false,
67
+ "special": true
68
+ },
69
+ {
70
+ "id": 507,
71
+ "content": "<|end_header_id|>",
72
+ "single_word": false,
73
+ "lstrip": false,
74
+ "rstrip": false,
75
+ "normalized": false,
76
+ "special": true
77
+ },
78
+ {
79
+ "id": 508,
80
+ "content": "<|eom_id|>",
81
+ "single_word": false,
82
+ "lstrip": false,
83
+ "rstrip": false,
84
+ "normalized": false,
85
+ "special": true
86
+ },
87
+ {
88
+ "id": 509,
89
+ "content": "<|eot_id|>",
90
+ "single_word": false,
91
+ "lstrip": false,
92
+ "rstrip": false,
93
+ "normalized": false,
94
+ "special": true
95
+ },
96
+ {
97
+ "id": 510,
98
+ "content": "<|python_tag|>",
99
+ "single_word": false,
100
+ "lstrip": false,
101
+ "rstrip": false,
102
+ "normalized": false,
103
+ "special": true
104
+ },
105
+ {
106
+ "id": 511,
107
+ "content": "<|reserved_special_token_3|>",
108
+ "single_word": false,
109
+ "lstrip": false,
110
+ "rstrip": false,
111
+ "normalized": false,
112
+ "special": true
113
+ },
114
+ {
115
+ "id": 512,
116
+ "content": "<|reserved_special_token_4|>",
117
+ "single_word": false,
118
+ "lstrip": false,
119
+ "rstrip": false,
120
+ "normalized": false,
121
+ "special": true
122
+ },
123
+ {
124
+ "id": 513,
125
+ "content": "<|reserved_special_token_5|>",
126
+ "single_word": false,
127
+ "lstrip": false,
128
+ "rstrip": false,
129
+ "normalized": false,
130
+ "special": true
131
+ },
132
+ {
133
+ "id": 514,
134
+ "content": "<|reserved_special_token_6|>",
135
+ "single_word": false,
136
+ "lstrip": false,
137
+ "rstrip": false,
138
+ "normalized": false,
139
+ "special": true
140
+ },
141
+ {
142
+ "id": 515,
143
+ "content": "<|reserved_special_token_7|>",
144
+ "single_word": false,
145
+ "lstrip": false,
146
+ "rstrip": false,
147
+ "normalized": false,
148
+ "special": true
149
+ },
150
+ {
151
+ "id": 516,
152
+ "content": "<|reserved_special_token_8|>",
153
+ "single_word": false,
154
+ "lstrip": false,
155
+ "rstrip": false,
156
+ "normalized": false,
157
+ "special": true
158
+ },
159
+ {
160
+ "id": 517,
161
+ "content": "<|reserved_special_token_9|>",
162
+ "single_word": false,
163
+ "lstrip": false,
164
+ "rstrip": false,
165
+ "normalized": false,
166
+ "special": true
167
+ },
168
+ {
169
+ "id": 518,
170
+ "content": "<|reserved_special_token_10|>",
171
+ "single_word": false,
172
+ "lstrip": false,
173
+ "rstrip": false,
174
+ "normalized": false,
175
+ "special": true
176
+ },
177
+ {
178
+ "id": 519,
179
+ "content": "<|reserved_special_token_11|>",
180
+ "single_word": false,
181
+ "lstrip": false,
182
+ "rstrip": false,
183
+ "normalized": false,
184
+ "special": true
185
+ },
186
+ {
187
+ "id": 520,
188
+ "content": "<|reserved_special_token_12|>",
189
+ "single_word": false,
190
+ "lstrip": false,
191
+ "rstrip": false,
192
+ "normalized": false,
193
+ "special": true
194
+ },
195
+ {
196
+ "id": 521,
197
+ "content": "<|reserved_special_token_13|>",
198
+ "single_word": false,
199
+ "lstrip": false,
200
+ "rstrip": false,
201
+ "normalized": false,
202
+ "special": true
203
+ },
204
+ {
205
+ "id": 522,
206
+ "content": "<|reserved_special_token_14|>",
207
+ "single_word": false,
208
+ "lstrip": false,
209
+ "rstrip": false,
210
+ "normalized": false,
211
+ "special": true
212
+ },
213
+ {
214
+ "id": 523,
215
+ "content": "<|reserved_special_token_15|>",
216
+ "single_word": false,
217
+ "lstrip": false,
218
+ "rstrip": false,
219
+ "normalized": false,
220
+ "special": true
221
+ },
222
+ {
223
+ "id": 524,
224
+ "content": "<|reserved_special_token_16|>",
225
+ "single_word": false,
226
+ "lstrip": false,
227
+ "rstrip": false,
228
+ "normalized": false,
229
+ "special": true
230
+ },
231
+ {
232
+ "id": 525,
233
+ "content": "<|reserved_special_token_17|>",
234
+ "single_word": false,
235
+ "lstrip": false,
236
+ "rstrip": false,
237
+ "normalized": false,
238
+ "special": true
239
+ },
240
+ {
241
+ "id": 526,
242
+ "content": "<|reserved_special_token_18|>",
243
+ "single_word": false,
244
+ "lstrip": false,
245
+ "rstrip": false,
246
+ "normalized": false,
247
+ "special": true
248
+ },
249
+ {
250
+ "id": 527,
251
+ "content": "<|reserved_special_token_19|>",
252
+ "single_word": false,
253
+ "lstrip": false,
254
+ "rstrip": false,
255
+ "normalized": false,
256
+ "special": true
257
+ },
258
+ {
259
+ "id": 528,
260
+ "content": "<|reserved_special_token_20|>",
261
+ "single_word": false,
262
+ "lstrip": false,
263
+ "rstrip": false,
264
+ "normalized": false,
265
+ "special": true
266
+ },
267
+ {
268
+ "id": 529,
269
+ "content": "<|reserved_special_token_21|>",
270
+ "single_word": false,
271
+ "lstrip": false,
272
+ "rstrip": false,
273
+ "normalized": false,
274
+ "special": true
275
+ },
276
+ {
277
+ "id": 530,
278
+ "content": "<|reserved_special_token_22|>",
279
+ "single_word": false,
280
+ "lstrip": false,
281
+ "rstrip": false,
282
+ "normalized": false,
283
+ "special": true
284
+ },
285
+ {
286
+ "id": 531,
287
+ "content": "<|reserved_special_token_23|>",
288
+ "single_word": false,
289
+ "lstrip": false,
290
+ "rstrip": false,
291
+ "normalized": false,
292
+ "special": true
293
+ },
294
+ {
295
+ "id": 532,
296
+ "content": "<|reserved_special_token_24|>",
297
+ "single_word": false,
298
+ "lstrip": false,
299
+ "rstrip": false,
300
+ "normalized": false,
301
+ "special": true
302
+ },
303
+ {
304
+ "id": 533,
305
+ "content": "<|reserved_special_token_25|>",
306
+ "single_word": false,
307
+ "lstrip": false,
308
+ "rstrip": false,
309
+ "normalized": false,
310
+ "special": true
311
+ },
312
+ {
313
+ "id": 534,
314
+ "content": "<|reserved_special_token_26|>",
315
+ "single_word": false,
316
+ "lstrip": false,
317
+ "rstrip": false,
318
+ "normalized": false,
319
+ "special": true
320
+ },
321
+ {
322
+ "id": 535,
323
+ "content": "<|reserved_special_token_27|>",
324
+ "single_word": false,
325
+ "lstrip": false,
326
+ "rstrip": false,
327
+ "normalized": false,
328
+ "special": true
329
+ },
330
+ {
331
+ "id": 536,
332
+ "content": "<|reserved_special_token_28|>",
333
+ "single_word": false,
334
+ "lstrip": false,
335
+ "rstrip": false,
336
+ "normalized": false,
337
+ "special": true
338
+ },
339
+ {
340
+ "id": 537,
341
+ "content": "<|reserved_special_token_29|>",
342
+ "single_word": false,
343
+ "lstrip": false,
344
+ "rstrip": false,
345
+ "normalized": false,
346
+ "special": true
347
+ },
348
+ {
349
+ "id": 538,
350
+ "content": "<|reserved_special_token_30|>",
351
+ "single_word": false,
352
+ "lstrip": false,
353
+ "rstrip": false,
354
+ "normalized": false,
355
+ "special": true
356
+ },
357
+ {
358
+ "id": 539,
359
+ "content": "<|reserved_special_token_31|>",
360
+ "single_word": false,
361
+ "lstrip": false,
362
+ "rstrip": false,
363
+ "normalized": false,
364
+ "special": true
365
+ },
366
+ {
367
+ "id": 540,
368
+ "content": "<|reserved_special_token_32|>",
369
+ "single_word": false,
370
+ "lstrip": false,
371
+ "rstrip": false,
372
+ "normalized": false,
373
+ "special": true
374
+ },
375
+ {
376
+ "id": 541,
377
+ "content": "<|reserved_special_token_33|>",
378
+ "single_word": false,
379
+ "lstrip": false,
380
+ "rstrip": false,
381
+ "normalized": false,
382
+ "special": true
383
+ },
384
+ {
385
+ "id": 542,
386
+ "content": "<|reserved_special_token_34|>",
387
+ "single_word": false,
388
+ "lstrip": false,
389
+ "rstrip": false,
390
+ "normalized": false,
391
+ "special": true
392
+ },
393
+ {
394
+ "id": 543,
395
+ "content": "<|reserved_special_token_35|>",
396
+ "single_word": false,
397
+ "lstrip": false,
398
+ "rstrip": false,
399
+ "normalized": false,
400
+ "special": true
401
+ },
402
+ {
403
+ "id": 544,
404
+ "content": "<|reserved_special_token_36|>",
405
+ "single_word": false,
406
+ "lstrip": false,
407
+ "rstrip": false,
408
+ "normalized": false,
409
+ "special": true
410
+ },
411
+ {
412
+ "id": 545,
413
+ "content": "<|reserved_special_token_37|>",
414
+ "single_word": false,
415
+ "lstrip": false,
416
+ "rstrip": false,
417
+ "normalized": false,
418
+ "special": true
419
+ },
420
+ {
421
+ "id": 546,
422
+ "content": "<|reserved_special_token_38|>",
423
+ "single_word": false,
424
+ "lstrip": false,
425
+ "rstrip": false,
426
+ "normalized": false,
427
+ "special": true
428
+ },
429
+ {
430
+ "id": 547,
431
+ "content": "<|reserved_special_token_39|>",
432
+ "single_word": false,
433
+ "lstrip": false,
434
+ "rstrip": false,
435
+ "normalized": false,
436
+ "special": true
437
+ },
438
+ {
439
+ "id": 548,
440
+ "content": "<|reserved_special_token_40|>",
441
+ "single_word": false,
442
+ "lstrip": false,
443
+ "rstrip": false,
444
+ "normalized": false,
445
+ "special": true
446
+ },
447
+ {
448
+ "id": 549,
449
+ "content": "<|reserved_special_token_41|>",
450
+ "single_word": false,
451
+ "lstrip": false,
452
+ "rstrip": false,
453
+ "normalized": false,
454
+ "special": true
455
+ },
456
+ {
457
+ "id": 550,
458
+ "content": "<|reserved_special_token_42|>",
459
+ "single_word": false,
460
+ "lstrip": false,
461
+ "rstrip": false,
462
+ "normalized": false,
463
+ "special": true
464
+ },
465
+ {
466
+ "id": 551,
467
+ "content": "<|reserved_special_token_43|>",
468
+ "single_word": false,
469
+ "lstrip": false,
470
+ "rstrip": false,
471
+ "normalized": false,
472
+ "special": true
473
+ },
474
+ {
475
+ "id": 552,
476
+ "content": "<|reserved_special_token_44|>",
477
+ "single_word": false,
478
+ "lstrip": false,
479
+ "rstrip": false,
480
+ "normalized": false,
481
+ "special": true
482
+ },
483
+ {
484
+ "id": 553,
485
+ "content": "<|reserved_special_token_45|>",
486
+ "single_word": false,
487
+ "lstrip": false,
488
+ "rstrip": false,
489
+ "normalized": false,
490
+ "special": true
491
+ },
492
+ {
493
+ "id": 554,
494
+ "content": "<|reserved_special_token_46|>",
495
+ "single_word": false,
496
+ "lstrip": false,
497
+ "rstrip": false,
498
+ "normalized": false,
499
+ "special": true
500
+ },
501
+ {
502
+ "id": 555,
503
+ "content": "<|reserved_special_token_47|>",
504
+ "single_word": false,
505
+ "lstrip": false,
506
+ "rstrip": false,
507
+ "normalized": false,
508
+ "special": true
509
+ },
510
+ {
511
+ "id": 556,
512
+ "content": "<|reserved_special_token_48|>",
513
+ "single_word": false,
514
+ "lstrip": false,
515
+ "rstrip": false,
516
+ "normalized": false,
517
+ "special": true
518
+ },
519
+ {
520
+ "id": 557,
521
+ "content": "<|reserved_special_token_49|>",
522
+ "single_word": false,
523
+ "lstrip": false,
524
+ "rstrip": false,
525
+ "normalized": false,
526
+ "special": true
527
+ },
528
+ {
529
+ "id": 558,
530
+ "content": "<|reserved_special_token_50|>",
531
+ "single_word": false,
532
+ "lstrip": false,
533
+ "rstrip": false,
534
+ "normalized": false,
535
+ "special": true
536
+ },
537
+ {
538
+ "id": 559,
539
+ "content": "<|reserved_special_token_51|>",
540
+ "single_word": false,
541
+ "lstrip": false,
542
+ "rstrip": false,
543
+ "normalized": false,
544
+ "special": true
545
+ },
546
+ {
547
+ "id": 560,
548
+ "content": "<|reserved_special_token_52|>",
549
+ "single_word": false,
550
+ "lstrip": false,
551
+ "rstrip": false,
552
+ "normalized": false,
553
+ "special": true
554
+ },
555
+ {
556
+ "id": 561,
557
+ "content": "<|reserved_special_token_53|>",
558
+ "single_word": false,
559
+ "lstrip": false,
560
+ "rstrip": false,
561
+ "normalized": false,
562
+ "special": true
563
+ },
564
+ {
565
+ "id": 562,
566
+ "content": "<|reserved_special_token_54|>",
567
+ "single_word": false,
568
+ "lstrip": false,
569
+ "rstrip": false,
570
+ "normalized": false,
571
+ "special": true
572
+ },
573
+ {
574
+ "id": 563,
575
+ "content": "<|reserved_special_token_55|>",
576
+ "single_word": false,
577
+ "lstrip": false,
578
+ "rstrip": false,
579
+ "normalized": false,
580
+ "special": true
581
+ },
582
+ {
583
+ "id": 564,
584
+ "content": "<|reserved_special_token_56|>",
585
+ "single_word": false,
586
+ "lstrip": false,
587
+ "rstrip": false,
588
+ "normalized": false,
589
+ "special": true
590
+ },
591
+ {
592
+ "id": 565,
593
+ "content": "<|reserved_special_token_57|>",
594
+ "single_word": false,
595
+ "lstrip": false,
596
+ "rstrip": false,
597
+ "normalized": false,
598
+ "special": true
599
+ },
600
+ {
601
+ "id": 566,
602
+ "content": "<|reserved_special_token_58|>",
603
+ "single_word": false,
604
+ "lstrip": false,
605
+ "rstrip": false,
606
+ "normalized": false,
607
+ "special": true
608
+ },
609
+ {
610
+ "id": 567,
611
+ "content": "<|reserved_special_token_59|>",
612
+ "single_word": false,
613
+ "lstrip": false,
614
+ "rstrip": false,
615
+ "normalized": false,
616
+ "special": true
617
+ },
618
+ {
619
+ "id": 568,
620
+ "content": "<|reserved_special_token_60|>",
621
+ "single_word": false,
622
+ "lstrip": false,
623
+ "rstrip": false,
624
+ "normalized": false,
625
+ "special": true
626
+ },
627
+ {
628
+ "id": 569,
629
+ "content": "<|reserved_special_token_61|>",
630
+ "single_word": false,
631
+ "lstrip": false,
632
+ "rstrip": false,
633
+ "normalized": false,
634
+ "special": true
635
+ },
636
+ {
637
+ "id": 570,
638
+ "content": "<|reserved_special_token_62|>",
639
+ "single_word": false,
640
+ "lstrip": false,
641
+ "rstrip": false,
642
+ "normalized": false,
643
+ "special": true
644
+ },
645
+ {
646
+ "id": 571,
647
+ "content": "<|reserved_special_token_63|>",
648
+ "single_word": false,
649
+ "lstrip": false,
650
+ "rstrip": false,
651
+ "normalized": false,
652
+ "special": true
653
+ },
654
+ {
655
+ "id": 572,
656
+ "content": "<|reserved_special_token_64|>",
657
+ "single_word": false,
658
+ "lstrip": false,
659
+ "rstrip": false,
660
+ "normalized": false,
661
+ "special": true
662
+ },
663
+ {
664
+ "id": 573,
665
+ "content": "<|reserved_special_token_65|>",
666
+ "single_word": false,
667
+ "lstrip": false,
668
+ "rstrip": false,
669
+ "normalized": false,
670
+ "special": true
671
+ },
672
+ {
673
+ "id": 574,
674
+ "content": "<|reserved_special_token_66|>",
675
+ "single_word": false,
676
+ "lstrip": false,
677
+ "rstrip": false,
678
+ "normalized": false,
679
+ "special": true
680
+ },
681
+ {
682
+ "id": 575,
683
+ "content": "<|reserved_special_token_67|>",
684
+ "single_word": false,
685
+ "lstrip": false,
686
+ "rstrip": false,
687
+ "normalized": false,
688
+ "special": true
689
+ },
690
+ {
691
+ "id": 576,
692
+ "content": "<|reserved_special_token_68|>",
693
+ "single_word": false,
694
+ "lstrip": false,
695
+ "rstrip": false,
696
+ "normalized": false,
697
+ "special": true
698
+ },
699
+ {
700
+ "id": 577,
701
+ "content": "<|reserved_special_token_69|>",
702
+ "single_word": false,
703
+ "lstrip": false,
704
+ "rstrip": false,
705
+ "normalized": false,
706
+ "special": true
707
+ },
708
+ {
709
+ "id": 578,
710
+ "content": "<|reserved_special_token_70|>",
711
+ "single_word": false,
712
+ "lstrip": false,
713
+ "rstrip": false,
714
+ "normalized": false,
715
+ "special": true
716
+ },
717
+ {
718
+ "id": 579,
719
+ "content": "<|reserved_special_token_71|>",
720
+ "single_word": false,
721
+ "lstrip": false,
722
+ "rstrip": false,
723
+ "normalized": false,
724
+ "special": true
725
+ },
726
+ {
727
+ "id": 580,
728
+ "content": "<|reserved_special_token_72|>",
729
+ "single_word": false,
730
+ "lstrip": false,
731
+ "rstrip": false,
732
+ "normalized": false,
733
+ "special": true
734
+ },
735
+ {
736
+ "id": 581,
737
+ "content": "<|reserved_special_token_73|>",
738
+ "single_word": false,
739
+ "lstrip": false,
740
+ "rstrip": false,
741
+ "normalized": false,
742
+ "special": true
743
+ },
744
+ {
745
+ "id": 582,
746
+ "content": "<|reserved_special_token_74|>",
747
+ "single_word": false,
748
+ "lstrip": false,
749
+ "rstrip": false,
750
+ "normalized": false,
751
+ "special": true
752
+ },
753
+ {
754
+ "id": 583,
755
+ "content": "<|reserved_special_token_75|>",
756
+ "single_word": false,
757
+ "lstrip": false,
758
+ "rstrip": false,
759
+ "normalized": false,
760
+ "special": true
761
+ },
762
+ {
763
+ "id": 584,
764
+ "content": "<|reserved_special_token_76|>",
765
+ "single_word": false,
766
+ "lstrip": false,
767
+ "rstrip": false,
768
+ "normalized": false,
769
+ "special": true
770
+ },
771
+ {
772
+ "id": 585,
773
+ "content": "<|reserved_special_token_77|>",
774
+ "single_word": false,
775
+ "lstrip": false,
776
+ "rstrip": false,
777
+ "normalized": false,
778
+ "special": true
779
+ },
780
+ {
781
+ "id": 586,
782
+ "content": "<|reserved_special_token_78|>",
783
+ "single_word": false,
784
+ "lstrip": false,
785
+ "rstrip": false,
786
+ "normalized": false,
787
+ "special": true
788
+ },
789
+ {
790
+ "id": 587,
791
+ "content": "<|reserved_special_token_79|>",
792
+ "single_word": false,
793
+ "lstrip": false,
794
+ "rstrip": false,
795
+ "normalized": false,
796
+ "special": true
797
+ },
798
+ {
799
+ "id": 588,
800
+ "content": "<|reserved_special_token_80|>",
801
+ "single_word": false,
802
+ "lstrip": false,
803
+ "rstrip": false,
804
+ "normalized": false,
805
+ "special": true
806
+ },
807
+ {
808
+ "id": 589,
809
+ "content": "<|reserved_special_token_81|>",
810
+ "single_word": false,
811
+ "lstrip": false,
812
+ "rstrip": false,
813
+ "normalized": false,
814
+ "special": true
815
+ },
816
+ {
817
+ "id": 590,
818
+ "content": "<|reserved_special_token_82|>",
819
+ "single_word": false,
820
+ "lstrip": false,
821
+ "rstrip": false,
822
+ "normalized": false,
823
+ "special": true
824
+ },
825
+ {
826
+ "id": 591,
827
+ "content": "<|reserved_special_token_83|>",
828
+ "single_word": false,
829
+ "lstrip": false,
830
+ "rstrip": false,
831
+ "normalized": false,
832
+ "special": true
833
+ },
834
+ {
835
+ "id": 592,
836
+ "content": "<|reserved_special_token_84|>",
837
+ "single_word": false,
838
+ "lstrip": false,
839
+ "rstrip": false,
840
+ "normalized": false,
841
+ "special": true
842
+ },
843
+ {
844
+ "id": 593,
845
+ "content": "<|reserved_special_token_85|>",
846
+ "single_word": false,
847
+ "lstrip": false,
848
+ "rstrip": false,
849
+ "normalized": false,
850
+ "special": true
851
+ },
852
+ {
853
+ "id": 594,
854
+ "content": "<|reserved_special_token_86|>",
855
+ "single_word": false,
856
+ "lstrip": false,
857
+ "rstrip": false,
858
+ "normalized": false,
859
+ "special": true
860
+ },
861
+ {
862
+ "id": 595,
863
+ "content": "<|reserved_special_token_87|>",
864
+ "single_word": false,
865
+ "lstrip": false,
866
+ "rstrip": false,
867
+ "normalized": false,
868
+ "special": true
869
+ },
870
+ {
871
+ "id": 596,
872
+ "content": "<|reserved_special_token_88|>",
873
+ "single_word": false,
874
+ "lstrip": false,
875
+ "rstrip": false,
876
+ "normalized": false,
877
+ "special": true
878
+ },
879
+ {
880
+ "id": 597,
881
+ "content": "<|reserved_special_token_89|>",
882
+ "single_word": false,
883
+ "lstrip": false,
884
+ "rstrip": false,
885
+ "normalized": false,
886
+ "special": true
887
+ },
888
+ {
889
+ "id": 598,
890
+ "content": "<|reserved_special_token_90|>",
891
+ "single_word": false,
892
+ "lstrip": false,
893
+ "rstrip": false,
894
+ "normalized": false,
895
+ "special": true
896
+ },
897
+ {
898
+ "id": 599,
899
+ "content": "<|reserved_special_token_91|>",
900
+ "single_word": false,
901
+ "lstrip": false,
902
+ "rstrip": false,
903
+ "normalized": false,
904
+ "special": true
905
+ },
906
+ {
907
+ "id": 600,
908
+ "content": "<|reserved_special_token_92|>",
909
+ "single_word": false,
910
+ "lstrip": false,
911
+ "rstrip": false,
912
+ "normalized": false,
913
+ "special": true
914
+ },
915
+ {
916
+ "id": 601,
917
+ "content": "<|reserved_special_token_93|>",
918
+ "single_word": false,
919
+ "lstrip": false,
920
+ "rstrip": false,
921
+ "normalized": false,
922
+ "special": true
923
+ },
924
+ {
925
+ "id": 602,
926
+ "content": "<|reserved_special_token_94|>",
927
+ "single_word": false,
928
+ "lstrip": false,
929
+ "rstrip": false,
930
+ "normalized": false,
931
+ "special": true
932
+ },
933
+ {
934
+ "id": 603,
935
+ "content": "<|reserved_special_token_95|>",
936
+ "single_word": false,
937
+ "lstrip": false,
938
+ "rstrip": false,
939
+ "normalized": false,
940
+ "special": true
941
+ },
942
+ {
943
+ "id": 604,
944
+ "content": "<|reserved_special_token_96|>",
945
+ "single_word": false,
946
+ "lstrip": false,
947
+ "rstrip": false,
948
+ "normalized": false,
949
+ "special": true
950
+ },
951
+ {
952
+ "id": 605,
953
+ "content": "<|reserved_special_token_97|>",
954
+ "single_word": false,
955
+ "lstrip": false,
956
+ "rstrip": false,
957
+ "normalized": false,
958
+ "special": true
959
+ },
960
+ {
961
+ "id": 606,
962
+ "content": "<|reserved_special_token_98|>",
963
+ "single_word": false,
964
+ "lstrip": false,
965
+ "rstrip": false,
966
+ "normalized": false,
967
+ "special": true
968
+ },
969
+ {
970
+ "id": 607,
971
+ "content": "<|reserved_special_token_99|>",
972
+ "single_word": false,
973
+ "lstrip": false,
974
+ "rstrip": false,
975
+ "normalized": false,
976
+ "special": true
977
+ },
978
+ {
979
+ "id": 608,
980
+ "content": "<|reserved_special_token_100|>",
981
+ "single_word": false,
982
+ "lstrip": false,
983
+ "rstrip": false,
984
+ "normalized": false,
985
+ "special": true
986
+ },
987
+ {
988
+ "id": 609,
989
+ "content": "<|reserved_special_token_101|>",
990
+ "single_word": false,
991
+ "lstrip": false,
992
+ "rstrip": false,
993
+ "normalized": false,
994
+ "special": true
995
+ },
996
+ {
997
+ "id": 610,
998
+ "content": "<|reserved_special_token_102|>",
999
+ "single_word": false,
1000
+ "lstrip": false,
1001
+ "rstrip": false,
1002
+ "normalized": false,
1003
+ "special": true
1004
+ },
1005
+ {
1006
+ "id": 611,
1007
+ "content": "<|reserved_special_token_103|>",
1008
+ "single_word": false,
1009
+ "lstrip": false,
1010
+ "rstrip": false,
1011
+ "normalized": false,
1012
+ "special": true
1013
+ },
1014
+ {
1015
+ "id": 612,
1016
+ "content": "<|reserved_special_token_104|>",
1017
+ "single_word": false,
1018
+ "lstrip": false,
1019
+ "rstrip": false,
1020
+ "normalized": false,
1021
+ "special": true
1022
+ },
1023
+ {
1024
+ "id": 613,
1025
+ "content": "<|reserved_special_token_105|>",
1026
+ "single_word": false,
1027
+ "lstrip": false,
1028
+ "rstrip": false,
1029
+ "normalized": false,
1030
+ "special": true
1031
+ },
1032
+ {
1033
+ "id": 614,
1034
+ "content": "<|reserved_special_token_106|>",
1035
+ "single_word": false,
1036
+ "lstrip": false,
1037
+ "rstrip": false,
1038
+ "normalized": false,
1039
+ "special": true
1040
+ },
1041
+ {
1042
+ "id": 615,
1043
+ "content": "<|reserved_special_token_107|>",
1044
+ "single_word": false,
1045
+ "lstrip": false,
1046
+ "rstrip": false,
1047
+ "normalized": false,
1048
+ "special": true
1049
+ },
1050
+ {
1051
+ "id": 616,
1052
+ "content": "<|reserved_special_token_108|>",
1053
+ "single_word": false,
1054
+ "lstrip": false,
1055
+ "rstrip": false,
1056
+ "normalized": false,
1057
+ "special": true
1058
+ },
1059
+ {
1060
+ "id": 617,
1061
+ "content": "<|reserved_special_token_109|>",
1062
+ "single_word": false,
1063
+ "lstrip": false,
1064
+ "rstrip": false,
1065
+ "normalized": false,
1066
+ "special": true
1067
+ },
1068
+ {
1069
+ "id": 618,
1070
+ "content": "<|reserved_special_token_110|>",
1071
+ "single_word": false,
1072
+ "lstrip": false,
1073
+ "rstrip": false,
1074
+ "normalized": false,
1075
+ "special": true
1076
+ },
1077
+ {
1078
+ "id": 619,
1079
+ "content": "<|reserved_special_token_111|>",
1080
+ "single_word": false,
1081
+ "lstrip": false,
1082
+ "rstrip": false,
1083
+ "normalized": false,
1084
+ "special": true
1085
+ },
1086
+ {
1087
+ "id": 620,
1088
+ "content": "<|reserved_special_token_112|>",
1089
+ "single_word": false,
1090
+ "lstrip": false,
1091
+ "rstrip": false,
1092
+ "normalized": false,
1093
+ "special": true
1094
+ },
1095
+ {
1096
+ "id": 621,
1097
+ "content": "<|reserved_special_token_113|>",
1098
+ "single_word": false,
1099
+ "lstrip": false,
1100
+ "rstrip": false,
1101
+ "normalized": false,
1102
+ "special": true
1103
+ },
1104
+ {
1105
+ "id": 622,
1106
+ "content": "<|reserved_special_token_114|>",
1107
+ "single_word": false,
1108
+ "lstrip": false,
1109
+ "rstrip": false,
1110
+ "normalized": false,
1111
+ "special": true
1112
+ },
1113
+ {
1114
+ "id": 623,
1115
+ "content": "<|reserved_special_token_115|>",
1116
+ "single_word": false,
1117
+ "lstrip": false,
1118
+ "rstrip": false,
1119
+ "normalized": false,
1120
+ "special": true
1121
+ },
1122
+ {
1123
+ "id": 624,
1124
+ "content": "<|reserved_special_token_116|>",
1125
+ "single_word": false,
1126
+ "lstrip": false,
1127
+ "rstrip": false,
1128
+ "normalized": false,
1129
+ "special": true
1130
+ },
1131
+ {
1132
+ "id": 625,
1133
+ "content": "<|reserved_special_token_117|>",
1134
+ "single_word": false,
1135
+ "lstrip": false,
1136
+ "rstrip": false,
1137
+ "normalized": false,
1138
+ "special": true
1139
+ },
1140
+ {
1141
+ "id": 626,
1142
+ "content": "<|reserved_special_token_118|>",
1143
+ "single_word": false,
1144
+ "lstrip": false,
1145
+ "rstrip": false,
1146
+ "normalized": false,
1147
+ "special": true
1148
+ },
1149
+ {
1150
+ "id": 627,
1151
+ "content": "<|reserved_special_token_119|>",
1152
+ "single_word": false,
1153
+ "lstrip": false,
1154
+ "rstrip": false,
1155
+ "normalized": false,
1156
+ "special": true
1157
+ },
1158
+ {
1159
+ "id": 628,
1160
+ "content": "<|reserved_special_token_120|>",
1161
+ "single_word": false,
1162
+ "lstrip": false,
1163
+ "rstrip": false,
1164
+ "normalized": false,
1165
+ "special": true
1166
+ },
1167
+ {
1168
+ "id": 629,
1169
+ "content": "<|reserved_special_token_121|>",
1170
+ "single_word": false,
1171
+ "lstrip": false,
1172
+ "rstrip": false,
1173
+ "normalized": false,
1174
+ "special": true
1175
+ },
1176
+ {
1177
+ "id": 630,
1178
+ "content": "<|reserved_special_token_122|>",
1179
+ "single_word": false,
1180
+ "lstrip": false,
1181
+ "rstrip": false,
1182
+ "normalized": false,
1183
+ "special": true
1184
+ },
1185
+ {
1186
+ "id": 631,
1187
+ "content": "<|reserved_special_token_123|>",
1188
+ "single_word": false,
1189
+ "lstrip": false,
1190
+ "rstrip": false,
1191
+ "normalized": false,
1192
+ "special": true
1193
+ },
1194
+ {
1195
+ "id": 632,
1196
+ "content": "<|reserved_special_token_124|>",
1197
+ "single_word": false,
1198
+ "lstrip": false,
1199
+ "rstrip": false,
1200
+ "normalized": false,
1201
+ "special": true
1202
+ },
1203
+ {
1204
+ "id": 633,
1205
+ "content": "<|reserved_special_token_125|>",
1206
+ "single_word": false,
1207
+ "lstrip": false,
1208
+ "rstrip": false,
1209
+ "normalized": false,
1210
+ "special": true
1211
+ },
1212
+ {
1213
+ "id": 634,
1214
+ "content": "<|reserved_special_token_126|>",
1215
+ "single_word": false,
1216
+ "lstrip": false,
1217
+ "rstrip": false,
1218
+ "normalized": false,
1219
+ "special": true
1220
+ },
1221
+ {
1222
+ "id": 635,
1223
+ "content": "<|reserved_special_token_127|>",
1224
+ "single_word": false,
1225
+ "lstrip": false,
1226
+ "rstrip": false,
1227
+ "normalized": false,
1228
+ "special": true
1229
+ },
1230
+ {
1231
+ "id": 636,
1232
+ "content": "<|reserved_special_token_128|>",
1233
+ "single_word": false,
1234
+ "lstrip": false,
1235
+ "rstrip": false,
1236
+ "normalized": false,
1237
+ "special": true
1238
+ },
1239
+ {
1240
+ "id": 637,
1241
+ "content": "<|reserved_special_token_129|>",
1242
+ "single_word": false,
1243
+ "lstrip": false,
1244
+ "rstrip": false,
1245
+ "normalized": false,
1246
+ "special": true
1247
+ },
1248
+ {
1249
+ "id": 638,
1250
+ "content": "<|reserved_special_token_130|>",
1251
+ "single_word": false,
1252
+ "lstrip": false,
1253
+ "rstrip": false,
1254
+ "normalized": false,
1255
+ "special": true
1256
+ },
1257
+ {
1258
+ "id": 639,
1259
+ "content": "<|reserved_special_token_131|>",
1260
+ "single_word": false,
1261
+ "lstrip": false,
1262
+ "rstrip": false,
1263
+ "normalized": false,
1264
+ "special": true
1265
+ },
1266
+ {
1267
+ "id": 640,
1268
+ "content": "<|reserved_special_token_132|>",
1269
+ "single_word": false,
1270
+ "lstrip": false,
1271
+ "rstrip": false,
1272
+ "normalized": false,
1273
+ "special": true
1274
+ },
1275
+ {
1276
+ "id": 641,
1277
+ "content": "<|reserved_special_token_133|>",
1278
+ "single_word": false,
1279
+ "lstrip": false,
1280
+ "rstrip": false,
1281
+ "normalized": false,
1282
+ "special": true
1283
+ },
1284
+ {
1285
+ "id": 642,
1286
+ "content": "<|reserved_special_token_134|>",
1287
+ "single_word": false,
1288
+ "lstrip": false,
1289
+ "rstrip": false,
1290
+ "normalized": false,
1291
+ "special": true
1292
+ },
1293
+ {
1294
+ "id": 643,
1295
+ "content": "<|reserved_special_token_135|>",
1296
+ "single_word": false,
1297
+ "lstrip": false,
1298
+ "rstrip": false,
1299
+ "normalized": false,
1300
+ "special": true
1301
+ },
1302
+ {
1303
+ "id": 644,
1304
+ "content": "<|reserved_special_token_136|>",
1305
+ "single_word": false,
1306
+ "lstrip": false,
1307
+ "rstrip": false,
1308
+ "normalized": false,
1309
+ "special": true
1310
+ },
1311
+ {
1312
+ "id": 645,
1313
+ "content": "<|reserved_special_token_137|>",
1314
+ "single_word": false,
1315
+ "lstrip": false,
1316
+ "rstrip": false,
1317
+ "normalized": false,
1318
+ "special": true
1319
+ },
1320
+ {
1321
+ "id": 646,
1322
+ "content": "<|reserved_special_token_138|>",
1323
+ "single_word": false,
1324
+ "lstrip": false,
1325
+ "rstrip": false,
1326
+ "normalized": false,
1327
+ "special": true
1328
+ },
1329
+ {
1330
+ "id": 647,
1331
+ "content": "<|reserved_special_token_139|>",
1332
+ "single_word": false,
1333
+ "lstrip": false,
1334
+ "rstrip": false,
1335
+ "normalized": false,
1336
+ "special": true
1337
+ },
1338
+ {
1339
+ "id": 648,
1340
+ "content": "<|reserved_special_token_140|>",
1341
+ "single_word": false,
1342
+ "lstrip": false,
1343
+ "rstrip": false,
1344
+ "normalized": false,
1345
+ "special": true
1346
+ },
1347
+ {
1348
+ "id": 649,
1349
+ "content": "<|reserved_special_token_141|>",
1350
+ "single_word": false,
1351
+ "lstrip": false,
1352
+ "rstrip": false,
1353
+ "normalized": false,
1354
+ "special": true
1355
+ },
1356
+ {
1357
+ "id": 650,
1358
+ "content": "<|reserved_special_token_142|>",
1359
+ "single_word": false,
1360
+ "lstrip": false,
1361
+ "rstrip": false,
1362
+ "normalized": false,
1363
+ "special": true
1364
+ },
1365
+ {
1366
+ "id": 651,
1367
+ "content": "<|reserved_special_token_143|>",
1368
+ "single_word": false,
1369
+ "lstrip": false,
1370
+ "rstrip": false,
1371
+ "normalized": false,
1372
+ "special": true
1373
+ },
1374
+ {
1375
+ "id": 652,
1376
+ "content": "<|reserved_special_token_144|>",
1377
+ "single_word": false,
1378
+ "lstrip": false,
1379
+ "rstrip": false,
1380
+ "normalized": false,
1381
+ "special": true
1382
+ },
1383
+ {
1384
+ "id": 653,
1385
+ "content": "<|reserved_special_token_145|>",
1386
+ "single_word": false,
1387
+ "lstrip": false,
1388
+ "rstrip": false,
1389
+ "normalized": false,
1390
+ "special": true
1391
+ },
1392
+ {
1393
+ "id": 654,
1394
+ "content": "<|reserved_special_token_146|>",
1395
+ "single_word": false,
1396
+ "lstrip": false,
1397
+ "rstrip": false,
1398
+ "normalized": false,
1399
+ "special": true
1400
+ },
1401
+ {
1402
+ "id": 655,
1403
+ "content": "<|reserved_special_token_147|>",
1404
+ "single_word": false,
1405
+ "lstrip": false,
1406
+ "rstrip": false,
1407
+ "normalized": false,
1408
+ "special": true
1409
+ },
1410
+ {
1411
+ "id": 656,
1412
+ "content": "<|reserved_special_token_148|>",
1413
+ "single_word": false,
1414
+ "lstrip": false,
1415
+ "rstrip": false,
1416
+ "normalized": false,
1417
+ "special": true
1418
+ },
1419
+ {
1420
+ "id": 657,
1421
+ "content": "<|reserved_special_token_149|>",
1422
+ "single_word": false,
1423
+ "lstrip": false,
1424
+ "rstrip": false,
1425
+ "normalized": false,
1426
+ "special": true
1427
+ },
1428
+ {
1429
+ "id": 658,
1430
+ "content": "<|reserved_special_token_150|>",
1431
+ "single_word": false,
1432
+ "lstrip": false,
1433
+ "rstrip": false,
1434
+ "normalized": false,
1435
+ "special": true
1436
+ },
1437
+ {
1438
+ "id": 659,
1439
+ "content": "<|reserved_special_token_151|>",
1440
+ "single_word": false,
1441
+ "lstrip": false,
1442
+ "rstrip": false,
1443
+ "normalized": false,
1444
+ "special": true
1445
+ },
1446
+ {
1447
+ "id": 660,
1448
+ "content": "<|reserved_special_token_152|>",
1449
+ "single_word": false,
1450
+ "lstrip": false,
1451
+ "rstrip": false,
1452
+ "normalized": false,
1453
+ "special": true
1454
+ },
1455
+ {
1456
+ "id": 661,
1457
+ "content": "<|reserved_special_token_153|>",
1458
+ "single_word": false,
1459
+ "lstrip": false,
1460
+ "rstrip": false,
1461
+ "normalized": false,
1462
+ "special": true
1463
+ },
1464
+ {
1465
+ "id": 662,
1466
+ "content": "<|reserved_special_token_154|>",
1467
+ "single_word": false,
1468
+ "lstrip": false,
1469
+ "rstrip": false,
1470
+ "normalized": false,
1471
+ "special": true
1472
+ },
1473
+ {
1474
+ "id": 663,
1475
+ "content": "<|reserved_special_token_155|>",
1476
+ "single_word": false,
1477
+ "lstrip": false,
1478
+ "rstrip": false,
1479
+ "normalized": false,
1480
+ "special": true
1481
+ },
1482
+ {
1483
+ "id": 664,
1484
+ "content": "<|reserved_special_token_156|>",
1485
+ "single_word": false,
1486
+ "lstrip": false,
1487
+ "rstrip": false,
1488
+ "normalized": false,
1489
+ "special": true
1490
+ },
1491
+ {
1492
+ "id": 665,
1493
+ "content": "<|reserved_special_token_157|>",
1494
+ "single_word": false,
1495
+ "lstrip": false,
1496
+ "rstrip": false,
1497
+ "normalized": false,
1498
+ "special": true
1499
+ },
1500
+ {
1501
+ "id": 666,
1502
+ "content": "<|reserved_special_token_158|>",
1503
+ "single_word": false,
1504
+ "lstrip": false,
1505
+ "rstrip": false,
1506
+ "normalized": false,
1507
+ "special": true
1508
+ },
1509
+ {
1510
+ "id": 667,
1511
+ "content": "<|reserved_special_token_159|>",
1512
+ "single_word": false,
1513
+ "lstrip": false,
1514
+ "rstrip": false,
1515
+ "normalized": false,
1516
+ "special": true
1517
+ },
1518
+ {
1519
+ "id": 668,
1520
+ "content": "<|reserved_special_token_160|>",
1521
+ "single_word": false,
1522
+ "lstrip": false,
1523
+ "rstrip": false,
1524
+ "normalized": false,
1525
+ "special": true
1526
+ },
1527
+ {
1528
+ "id": 669,
1529
+ "content": "<|reserved_special_token_161|>",
1530
+ "single_word": false,
1531
+ "lstrip": false,
1532
+ "rstrip": false,
1533
+ "normalized": false,
1534
+ "special": true
1535
+ },
1536
+ {
1537
+ "id": 670,
1538
+ "content": "<|reserved_special_token_162|>",
1539
+ "single_word": false,
1540
+ "lstrip": false,
1541
+ "rstrip": false,
1542
+ "normalized": false,
1543
+ "special": true
1544
+ },
1545
+ {
1546
+ "id": 671,
1547
+ "content": "<|reserved_special_token_163|>",
1548
+ "single_word": false,
1549
+ "lstrip": false,
1550
+ "rstrip": false,
1551
+ "normalized": false,
1552
+ "special": true
1553
+ },
1554
+ {
1555
+ "id": 672,
1556
+ "content": "<|reserved_special_token_164|>",
1557
+ "single_word": false,
1558
+ "lstrip": false,
1559
+ "rstrip": false,
1560
+ "normalized": false,
1561
+ "special": true
1562
+ },
1563
+ {
1564
+ "id": 673,
1565
+ "content": "<|reserved_special_token_165|>",
1566
+ "single_word": false,
1567
+ "lstrip": false,
1568
+ "rstrip": false,
1569
+ "normalized": false,
1570
+ "special": true
1571
+ },
1572
+ {
1573
+ "id": 674,
1574
+ "content": "<|reserved_special_token_166|>",
1575
+ "single_word": false,
1576
+ "lstrip": false,
1577
+ "rstrip": false,
1578
+ "normalized": false,
1579
+ "special": true
1580
+ },
1581
+ {
1582
+ "id": 675,
1583
+ "content": "<|reserved_special_token_167|>",
1584
+ "single_word": false,
1585
+ "lstrip": false,
1586
+ "rstrip": false,
1587
+ "normalized": false,
1588
+ "special": true
1589
+ },
1590
+ {
1591
+ "id": 676,
1592
+ "content": "<|reserved_special_token_168|>",
1593
+ "single_word": false,
1594
+ "lstrip": false,
1595
+ "rstrip": false,
1596
+ "normalized": false,
1597
+ "special": true
1598
+ },
1599
+ {
1600
+ "id": 677,
1601
+ "content": "<|reserved_special_token_169|>",
1602
+ "single_word": false,
1603
+ "lstrip": false,
1604
+ "rstrip": false,
1605
+ "normalized": false,
1606
+ "special": true
1607
+ },
1608
+ {
1609
+ "id": 678,
1610
+ "content": "<|reserved_special_token_170|>",
1611
+ "single_word": false,
1612
+ "lstrip": false,
1613
+ "rstrip": false,
1614
+ "normalized": false,
1615
+ "special": true
1616
+ },
1617
+ {
1618
+ "id": 679,
1619
+ "content": "<|reserved_special_token_171|>",
1620
+ "single_word": false,
1621
+ "lstrip": false,
1622
+ "rstrip": false,
1623
+ "normalized": false,
1624
+ "special": true
1625
+ },
1626
+ {
1627
+ "id": 680,
1628
+ "content": "<|reserved_special_token_172|>",
1629
+ "single_word": false,
1630
+ "lstrip": false,
1631
+ "rstrip": false,
1632
+ "normalized": false,
1633
+ "special": true
1634
+ },
1635
+ {
1636
+ "id": 681,
1637
+ "content": "<|reserved_special_token_173|>",
1638
+ "single_word": false,
1639
+ "lstrip": false,
1640
+ "rstrip": false,
1641
+ "normalized": false,
1642
+ "special": true
1643
+ },
1644
+ {
1645
+ "id": 682,
1646
+ "content": "<|reserved_special_token_174|>",
1647
+ "single_word": false,
1648
+ "lstrip": false,
1649
+ "rstrip": false,
1650
+ "normalized": false,
1651
+ "special": true
1652
+ },
1653
+ {
1654
+ "id": 683,
1655
+ "content": "<|reserved_special_token_175|>",
1656
+ "single_word": false,
1657
+ "lstrip": false,
1658
+ "rstrip": false,
1659
+ "normalized": false,
1660
+ "special": true
1661
+ },
1662
+ {
1663
+ "id": 684,
1664
+ "content": "<|reserved_special_token_176|>",
1665
+ "single_word": false,
1666
+ "lstrip": false,
1667
+ "rstrip": false,
1668
+ "normalized": false,
1669
+ "special": true
1670
+ },
1671
+ {
1672
+ "id": 685,
1673
+ "content": "<|reserved_special_token_177|>",
1674
+ "single_word": false,
1675
+ "lstrip": false,
1676
+ "rstrip": false,
1677
+ "normalized": false,
1678
+ "special": true
1679
+ },
1680
+ {
1681
+ "id": 686,
1682
+ "content": "<|reserved_special_token_178|>",
1683
+ "single_word": false,
1684
+ "lstrip": false,
1685
+ "rstrip": false,
1686
+ "normalized": false,
1687
+ "special": true
1688
+ },
1689
+ {
1690
+ "id": 687,
1691
+ "content": "<|reserved_special_token_179|>",
1692
+ "single_word": false,
1693
+ "lstrip": false,
1694
+ "rstrip": false,
1695
+ "normalized": false,
1696
+ "special": true
1697
+ },
1698
+ {
1699
+ "id": 688,
1700
+ "content": "<|reserved_special_token_180|>",
1701
+ "single_word": false,
1702
+ "lstrip": false,
1703
+ "rstrip": false,
1704
+ "normalized": false,
1705
+ "special": true
1706
+ },
1707
+ {
1708
+ "id": 689,
1709
+ "content": "<|reserved_special_token_181|>",
1710
+ "single_word": false,
1711
+ "lstrip": false,
1712
+ "rstrip": false,
1713
+ "normalized": false,
1714
+ "special": true
1715
+ },
1716
+ {
1717
+ "id": 690,
1718
+ "content": "<|reserved_special_token_182|>",
1719
+ "single_word": false,
1720
+ "lstrip": false,
1721
+ "rstrip": false,
1722
+ "normalized": false,
1723
+ "special": true
1724
+ },
1725
+ {
1726
+ "id": 691,
1727
+ "content": "<|reserved_special_token_183|>",
1728
+ "single_word": false,
1729
+ "lstrip": false,
1730
+ "rstrip": false,
1731
+ "normalized": false,
1732
+ "special": true
1733
+ },
1734
+ {
1735
+ "id": 692,
1736
+ "content": "<|reserved_special_token_184|>",
1737
+ "single_word": false,
1738
+ "lstrip": false,
1739
+ "rstrip": false,
1740
+ "normalized": false,
1741
+ "special": true
1742
+ },
1743
+ {
1744
+ "id": 693,
1745
+ "content": "<|reserved_special_token_185|>",
1746
+ "single_word": false,
1747
+ "lstrip": false,
1748
+ "rstrip": false,
1749
+ "normalized": false,
1750
+ "special": true
1751
+ },
1752
+ {
1753
+ "id": 694,
1754
+ "content": "<|reserved_special_token_186|>",
1755
+ "single_word": false,
1756
+ "lstrip": false,
1757
+ "rstrip": false,
1758
+ "normalized": false,
1759
+ "special": true
1760
+ },
1761
+ {
1762
+ "id": 695,
1763
+ "content": "<|reserved_special_token_187|>",
1764
+ "single_word": false,
1765
+ "lstrip": false,
1766
+ "rstrip": false,
1767
+ "normalized": false,
1768
+ "special": true
1769
+ },
1770
+ {
1771
+ "id": 696,
1772
+ "content": "<|reserved_special_token_188|>",
1773
+ "single_word": false,
1774
+ "lstrip": false,
1775
+ "rstrip": false,
1776
+ "normalized": false,
1777
+ "special": true
1778
+ },
1779
+ {
1780
+ "id": 697,
1781
+ "content": "<|reserved_special_token_189|>",
1782
+ "single_word": false,
1783
+ "lstrip": false,
1784
+ "rstrip": false,
1785
+ "normalized": false,
1786
+ "special": true
1787
+ },
1788
+ {
1789
+ "id": 698,
1790
+ "content": "<|reserved_special_token_190|>",
1791
+ "single_word": false,
1792
+ "lstrip": false,
1793
+ "rstrip": false,
1794
+ "normalized": false,
1795
+ "special": true
1796
+ },
1797
+ {
1798
+ "id": 699,
1799
+ "content": "<|reserved_special_token_191|>",
1800
+ "single_word": false,
1801
+ "lstrip": false,
1802
+ "rstrip": false,
1803
+ "normalized": false,
1804
+ "special": true
1805
+ },
1806
+ {
1807
+ "id": 700,
1808
+ "content": "<|reserved_special_token_192|>",
1809
+ "single_word": false,
1810
+ "lstrip": false,
1811
+ "rstrip": false,
1812
+ "normalized": false,
1813
+ "special": true
1814
+ },
1815
+ {
1816
+ "id": 701,
1817
+ "content": "<|reserved_special_token_193|>",
1818
+ "single_word": false,
1819
+ "lstrip": false,
1820
+ "rstrip": false,
1821
+ "normalized": false,
1822
+ "special": true
1823
+ },
1824
+ {
1825
+ "id": 702,
1826
+ "content": "<|reserved_special_token_194|>",
1827
+ "single_word": false,
1828
+ "lstrip": false,
1829
+ "rstrip": false,
1830
+ "normalized": false,
1831
+ "special": true
1832
+ },
1833
+ {
1834
+ "id": 703,
1835
+ "content": "<|reserved_special_token_195|>",
1836
+ "single_word": false,
1837
+ "lstrip": false,
1838
+ "rstrip": false,
1839
+ "normalized": false,
1840
+ "special": true
1841
+ },
1842
+ {
1843
+ "id": 704,
1844
+ "content": "<|reserved_special_token_196|>",
1845
+ "single_word": false,
1846
+ "lstrip": false,
1847
+ "rstrip": false,
1848
+ "normalized": false,
1849
+ "special": true
1850
+ },
1851
+ {
1852
+ "id": 705,
1853
+ "content": "<|reserved_special_token_197|>",
1854
+ "single_word": false,
1855
+ "lstrip": false,
1856
+ "rstrip": false,
1857
+ "normalized": false,
1858
+ "special": true
1859
+ },
1860
+ {
1861
+ "id": 706,
1862
+ "content": "<|reserved_special_token_198|>",
1863
+ "single_word": false,
1864
+ "lstrip": false,
1865
+ "rstrip": false,
1866
+ "normalized": false,
1867
+ "special": true
1868
+ },
1869
+ {
1870
+ "id": 707,
1871
+ "content": "<|reserved_special_token_199|>",
1872
+ "single_word": false,
1873
+ "lstrip": false,
1874
+ "rstrip": false,
1875
+ "normalized": false,
1876
+ "special": true
1877
+ },
1878
+ {
1879
+ "id": 708,
1880
+ "content": "<|reserved_special_token_200|>",
1881
+ "single_word": false,
1882
+ "lstrip": false,
1883
+ "rstrip": false,
1884
+ "normalized": false,
1885
+ "special": true
1886
+ },
1887
+ {
1888
+ "id": 709,
1889
+ "content": "<|reserved_special_token_201|>",
1890
+ "single_word": false,
1891
+ "lstrip": false,
1892
+ "rstrip": false,
1893
+ "normalized": false,
1894
+ "special": true
1895
+ },
1896
+ {
1897
+ "id": 710,
1898
+ "content": "<|reserved_special_token_202|>",
1899
+ "single_word": false,
1900
+ "lstrip": false,
1901
+ "rstrip": false,
1902
+ "normalized": false,
1903
+ "special": true
1904
+ },
1905
+ {
1906
+ "id": 711,
1907
+ "content": "<|reserved_special_token_203|>",
1908
+ "single_word": false,
1909
+ "lstrip": false,
1910
+ "rstrip": false,
1911
+ "normalized": false,
1912
+ "special": true
1913
+ },
1914
+ {
1915
+ "id": 712,
1916
+ "content": "<|reserved_special_token_204|>",
1917
+ "single_word": false,
1918
+ "lstrip": false,
1919
+ "rstrip": false,
1920
+ "normalized": false,
1921
+ "special": true
1922
+ },
1923
+ {
1924
+ "id": 713,
1925
+ "content": "<|reserved_special_token_205|>",
1926
+ "single_word": false,
1927
+ "lstrip": false,
1928
+ "rstrip": false,
1929
+ "normalized": false,
1930
+ "special": true
1931
+ },
1932
+ {
1933
+ "id": 714,
1934
+ "content": "<|reserved_special_token_206|>",
1935
+ "single_word": false,
1936
+ "lstrip": false,
1937
+ "rstrip": false,
1938
+ "normalized": false,
1939
+ "special": true
1940
+ },
1941
+ {
1942
+ "id": 715,
1943
+ "content": "<|reserved_special_token_207|>",
1944
+ "single_word": false,
1945
+ "lstrip": false,
1946
+ "rstrip": false,
1947
+ "normalized": false,
1948
+ "special": true
1949
+ },
1950
+ {
1951
+ "id": 716,
1952
+ "content": "<|reserved_special_token_208|>",
1953
+ "single_word": false,
1954
+ "lstrip": false,
1955
+ "rstrip": false,
1956
+ "normalized": false,
1957
+ "special": true
1958
+ },
1959
+ {
1960
+ "id": 717,
1961
+ "content": "<|reserved_special_token_209|>",
1962
+ "single_word": false,
1963
+ "lstrip": false,
1964
+ "rstrip": false,
1965
+ "normalized": false,
1966
+ "special": true
1967
+ },
1968
+ {
1969
+ "id": 718,
1970
+ "content": "<|reserved_special_token_210|>",
1971
+ "single_word": false,
1972
+ "lstrip": false,
1973
+ "rstrip": false,
1974
+ "normalized": false,
1975
+ "special": true
1976
+ },
1977
+ {
1978
+ "id": 719,
1979
+ "content": "<|reserved_special_token_211|>",
1980
+ "single_word": false,
1981
+ "lstrip": false,
1982
+ "rstrip": false,
1983
+ "normalized": false,
1984
+ "special": true
1985
+ },
1986
+ {
1987
+ "id": 720,
1988
+ "content": "<|reserved_special_token_212|>",
1989
+ "single_word": false,
1990
+ "lstrip": false,
1991
+ "rstrip": false,
1992
+ "normalized": false,
1993
+ "special": true
1994
+ },
1995
+ {
1996
+ "id": 721,
1997
+ "content": "<|reserved_special_token_213|>",
1998
+ "single_word": false,
1999
+ "lstrip": false,
2000
+ "rstrip": false,
2001
+ "normalized": false,
2002
+ "special": true
2003
+ },
2004
+ {
2005
+ "id": 722,
2006
+ "content": "<|reserved_special_token_214|>",
2007
+ "single_word": false,
2008
+ "lstrip": false,
2009
+ "rstrip": false,
2010
+ "normalized": false,
2011
+ "special": true
2012
+ },
2013
+ {
2014
+ "id": 723,
2015
+ "content": "<|reserved_special_token_215|>",
2016
+ "single_word": false,
2017
+ "lstrip": false,
2018
+ "rstrip": false,
2019
+ "normalized": false,
2020
+ "special": true
2021
+ },
2022
+ {
2023
+ "id": 724,
2024
+ "content": "<|reserved_special_token_216|>",
2025
+ "single_word": false,
2026
+ "lstrip": false,
2027
+ "rstrip": false,
2028
+ "normalized": false,
2029
+ "special": true
2030
+ },
2031
+ {
2032
+ "id": 725,
2033
+ "content": "<|reserved_special_token_217|>",
2034
+ "single_word": false,
2035
+ "lstrip": false,
2036
+ "rstrip": false,
2037
+ "normalized": false,
2038
+ "special": true
2039
+ },
2040
+ {
2041
+ "id": 726,
2042
+ "content": "<|reserved_special_token_218|>",
2043
+ "single_word": false,
2044
+ "lstrip": false,
2045
+ "rstrip": false,
2046
+ "normalized": false,
2047
+ "special": true
2048
+ },
2049
+ {
2050
+ "id": 727,
2051
+ "content": "<|reserved_special_token_219|>",
2052
+ "single_word": false,
2053
+ "lstrip": false,
2054
+ "rstrip": false,
2055
+ "normalized": false,
2056
+ "special": true
2057
+ },
2058
+ {
2059
+ "id": 728,
2060
+ "content": "<|reserved_special_token_220|>",
2061
+ "single_word": false,
2062
+ "lstrip": false,
2063
+ "rstrip": false,
2064
+ "normalized": false,
2065
+ "special": true
2066
+ },
2067
+ {
2068
+ "id": 729,
2069
+ "content": "<|reserved_special_token_221|>",
2070
+ "single_word": false,
2071
+ "lstrip": false,
2072
+ "rstrip": false,
2073
+ "normalized": false,
2074
+ "special": true
2075
+ },
2076
+ {
2077
+ "id": 730,
2078
+ "content": "<|reserved_special_token_222|>",
2079
+ "single_word": false,
2080
+ "lstrip": false,
2081
+ "rstrip": false,
2082
+ "normalized": false,
2083
+ "special": true
2084
+ },
2085
+ {
2086
+ "id": 731,
2087
+ "content": "<|reserved_special_token_223|>",
2088
+ "single_word": false,
2089
+ "lstrip": false,
2090
+ "rstrip": false,
2091
+ "normalized": false,
2092
+ "special": true
2093
+ },
2094
+ {
2095
+ "id": 732,
2096
+ "content": "<|reserved_special_token_224|>",
2097
+ "single_word": false,
2098
+ "lstrip": false,
2099
+ "rstrip": false,
2100
+ "normalized": false,
2101
+ "special": true
2102
+ },
2103
+ {
2104
+ "id": 733,
2105
+ "content": "<|reserved_special_token_225|>",
2106
+ "single_word": false,
2107
+ "lstrip": false,
2108
+ "rstrip": false,
2109
+ "normalized": false,
2110
+ "special": true
2111
+ },
2112
+ {
2113
+ "id": 734,
2114
+ "content": "<|reserved_special_token_226|>",
2115
+ "single_word": false,
2116
+ "lstrip": false,
2117
+ "rstrip": false,
2118
+ "normalized": false,
2119
+ "special": true
2120
+ },
2121
+ {
2122
+ "id": 735,
2123
+ "content": "<|reserved_special_token_227|>",
2124
+ "single_word": false,
2125
+ "lstrip": false,
2126
+ "rstrip": false,
2127
+ "normalized": false,
2128
+ "special": true
2129
+ },
2130
+ {
2131
+ "id": 736,
2132
+ "content": "<|reserved_special_token_228|>",
2133
+ "single_word": false,
2134
+ "lstrip": false,
2135
+ "rstrip": false,
2136
+ "normalized": false,
2137
+ "special": true
2138
+ },
2139
+ {
2140
+ "id": 737,
2141
+ "content": "<|reserved_special_token_229|>",
2142
+ "single_word": false,
2143
+ "lstrip": false,
2144
+ "rstrip": false,
2145
+ "normalized": false,
2146
+ "special": true
2147
+ },
2148
+ {
2149
+ "id": 738,
2150
+ "content": "<|reserved_special_token_230|>",
2151
+ "single_word": false,
2152
+ "lstrip": false,
2153
+ "rstrip": false,
2154
+ "normalized": false,
2155
+ "special": true
2156
+ },
2157
+ {
2158
+ "id": 739,
2159
+ "content": "<|reserved_special_token_231|>",
2160
+ "single_word": false,
2161
+ "lstrip": false,
2162
+ "rstrip": false,
2163
+ "normalized": false,
2164
+ "special": true
2165
+ },
2166
+ {
2167
+ "id": 740,
2168
+ "content": "<|reserved_special_token_232|>",
2169
+ "single_word": false,
2170
+ "lstrip": false,
2171
+ "rstrip": false,
2172
+ "normalized": false,
2173
+ "special": true
2174
+ },
2175
+ {
2176
+ "id": 741,
2177
+ "content": "<|reserved_special_token_233|>",
2178
+ "single_word": false,
2179
+ "lstrip": false,
2180
+ "rstrip": false,
2181
+ "normalized": false,
2182
+ "special": true
2183
+ },
2184
+ {
2185
+ "id": 742,
2186
+ "content": "<|reserved_special_token_234|>",
2187
+ "single_word": false,
2188
+ "lstrip": false,
2189
+ "rstrip": false,
2190
+ "normalized": false,
2191
+ "special": true
2192
+ },
2193
+ {
2194
+ "id": 743,
2195
+ "content": "<|reserved_special_token_235|>",
2196
+ "single_word": false,
2197
+ "lstrip": false,
2198
+ "rstrip": false,
2199
+ "normalized": false,
2200
+ "special": true
2201
+ },
2202
+ {
2203
+ "id": 744,
2204
+ "content": "<|reserved_special_token_236|>",
2205
+ "single_word": false,
2206
+ "lstrip": false,
2207
+ "rstrip": false,
2208
+ "normalized": false,
2209
+ "special": true
2210
+ },
2211
+ {
2212
+ "id": 745,
2213
+ "content": "<|reserved_special_token_237|>",
2214
+ "single_word": false,
2215
+ "lstrip": false,
2216
+ "rstrip": false,
2217
+ "normalized": false,
2218
+ "special": true
2219
+ },
2220
+ {
2221
+ "id": 746,
2222
+ "content": "<|reserved_special_token_238|>",
2223
+ "single_word": false,
2224
+ "lstrip": false,
2225
+ "rstrip": false,
2226
+ "normalized": false,
2227
+ "special": true
2228
+ },
2229
+ {
2230
+ "id": 747,
2231
+ "content": "<|reserved_special_token_239|>",
2232
+ "single_word": false,
2233
+ "lstrip": false,
2234
+ "rstrip": false,
2235
+ "normalized": false,
2236
+ "special": true
2237
+ },
2238
+ {
2239
+ "id": 748,
2240
+ "content": "<|reserved_special_token_240|>",
2241
+ "single_word": false,
2242
+ "lstrip": false,
2243
+ "rstrip": false,
2244
+ "normalized": false,
2245
+ "special": true
2246
+ },
2247
+ {
2248
+ "id": 749,
2249
+ "content": "<|reserved_special_token_241|>",
2250
+ "single_word": false,
2251
+ "lstrip": false,
2252
+ "rstrip": false,
2253
+ "normalized": false,
2254
+ "special": true
2255
+ },
2256
+ {
2257
+ "id": 750,
2258
+ "content": "<|reserved_special_token_242|>",
2259
+ "single_word": false,
2260
+ "lstrip": false,
2261
+ "rstrip": false,
2262
+ "normalized": false,
2263
+ "special": true
2264
+ },
2265
+ {
2266
+ "id": 751,
2267
+ "content": "<|reserved_special_token_243|>",
2268
+ "single_word": false,
2269
+ "lstrip": false,
2270
+ "rstrip": false,
2271
+ "normalized": false,
2272
+ "special": true
2273
+ },
2274
+ {
2275
+ "id": 752,
2276
+ "content": "<|reserved_special_token_244|>",
2277
+ "single_word": false,
2278
+ "lstrip": false,
2279
+ "rstrip": false,
2280
+ "normalized": false,
2281
+ "special": true
2282
+ },
2283
+ {
2284
+ "id": 753,
2285
+ "content": "<|reserved_special_token_245|>",
2286
+ "single_word": false,
2287
+ "lstrip": false,
2288
+ "rstrip": false,
2289
+ "normalized": false,
2290
+ "special": true
2291
+ },
2292
+ {
2293
+ "id": 754,
2294
+ "content": "<|reserved_special_token_246|>",
2295
+ "single_word": false,
2296
+ "lstrip": false,
2297
+ "rstrip": false,
2298
+ "normalized": false,
2299
+ "special": true
2300
+ },
2301
+ {
2302
+ "id": 755,
2303
+ "content": "<|reserved_special_token_247|>",
2304
+ "single_word": false,
2305
+ "lstrip": false,
2306
+ "rstrip": false,
2307
+ "normalized": false,
2308
+ "special": true
2309
+ },
2310
+ {
2311
+ "id": 756,
2312
+ "content": "<fake_token_around_image>",
2313
+ "single_word": false,
2314
+ "lstrip": false,
2315
+ "rstrip": false,
2316
+ "normalized": false,
2317
+ "special": true
2318
+ },
2319
+ {
2320
+ "id": 757,
2321
+ "content": "<image>",
2322
+ "single_word": false,
2323
+ "lstrip": false,
2324
+ "rstrip": false,
2325
+ "normalized": false,
2326
+ "special": true
2327
+ },
2328
+ {
2329
+ "id": 758,
2330
+ "content": "<end_of_utterance>",
2331
+ "single_word": false,
2332
+ "lstrip": false,
2333
+ "rstrip": false,
2334
+ "normalized": false,
2335
+ "special": true
2336
+ }
2337
+ ],
2338
+ "normalizer": null,
2339
+ "pre_tokenizer": {
2340
+ "type": "Sequence",
2341
+ "pretokenizers": [
2342
+ {
2343
+ "type": "Split",
2344
+ "pattern": {
2345
+ "Regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?\\p{L}+|\\p{N}{1,3}| ?[^\\s\\p{L}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+"
2346
+ },
2347
+ "behavior": "Isolated",
2348
+ "invert": false
2349
+ },
2350
+ {
2351
+ "type": "ByteLevel",
2352
+ "add_prefix_space": false,
2353
+ "trim_offsets": true,
2354
+ "use_regex": false
2355
+ }
2356
+ ]
2357
+ },
2358
+ "post_processor": {
2359
+ "type": "Sequence",
2360
+ "processors": [
2361
+ {
2362
+ "type": "ByteLevel",
2363
+ "add_prefix_space": true,
2364
+ "trim_offsets": false,
2365
+ "use_regex": true
2366
+ },
2367
+ {
2368
+ "type": "TemplateProcessing",
2369
+ "single": [
2370
+ {
2371
+ "SpecialToken": {
2372
+ "id": "<|begin_of_text|>",
2373
+ "type_id": 0
2374
+ }
2375
+ },
2376
+ {
2377
+ "Sequence": {
2378
+ "id": "A",
2379
+ "type_id": 0
2380
+ }
2381
+ }
2382
+ ],
2383
+ "pair": [
2384
+ {
2385
+ "SpecialToken": {
2386
+ "id": "<|begin_of_text|>",
2387
+ "type_id": 0
2388
+ }
2389
+ },
2390
+ {
2391
+ "Sequence": {
2392
+ "id": "A",
2393
+ "type_id": 0
2394
+ }
2395
+ },
2396
+ {
2397
+ "SpecialToken": {
2398
+ "id": "<|begin_of_text|>",
2399
+ "type_id": 1
2400
+ }
2401
+ },
2402
+ {
2403
+ "Sequence": {
2404
+ "id": "B",
2405
+ "type_id": 1
2406
+ }
2407
+ }
2408
+ ],
2409
+ "special_tokens": {
2410
+ "<|begin_of_text|>": {
2411
+ "id": "<|begin_of_text|>",
2412
+ "ids": [
2413
+ 128000
2414
+ ],
2415
+ "tokens": [
2416
+ "<|begin_of_text|>"
2417
+ ]
2418
+ }
2419
+ }
2420
+ }
2421
+ ]
2422
+ },
2423
+ "decoder": {
2424
+ "type": "ByteLevel",
2425
+ "add_prefix_space": true,
2426
+ "trim_offsets": true,
2427
+ "use_regex": true
2428
+ },
2429
+ "model": {
2430
+ "type": "BPE",
2431
+ "dropout": null,
2432
+ "unk_token": null,
2433
+ "continuing_subword_prefix": null,
2434
+ "end_of_word_suffix": null,
2435
+ "fuse_unk": false,
2436
+ "byte_fallback": false,
2437
+ "ignore_merges": true,
2438
+ "vocab": {
2439
+ "!": 0,
2440
+ "\"": 1,
2441
+ "#": 2,
2442
+ "$": 3,
2443
+ "%": 4,
2444
+ "&": 5,
2445
+ "'": 6,
2446
+ "(": 7,
2447
+ ")": 8,
2448
+ "*": 9,
2449
+ "+": 10,
2450
+ ",": 11,
2451
+ "-": 12,
2452
+ ".": 13,
2453
+ "/": 14,
2454
+ "0": 15,
2455
+ "1": 16,
2456
+ "2": 17,
2457
+ "3": 18,
2458
+ "4": 19,
2459
+ "5": 20,
2460
+ "6": 21,
2461
+ "7": 22,
2462
+ "8": 23,
2463
+ "9": 24,
2464
+ ":": 25,
2465
+ ";": 26,
2466
+ "<": 27,
2467
+ "=": 28,
2468
+ ">": 29,
2469
+ "?": 30,
2470
+ "@": 31,
2471
+ "A": 32,
2472
+ "B": 33,
2473
+ "C": 34,
2474
+ "D": 35,
2475
+ "E": 36,
2476
+ "F": 37,
2477
+ "G": 38,
2478
+ "H": 39,
2479
+ "I": 40,
2480
+ "J": 41,
2481
+ "K": 42,
2482
+ "L": 43,
2483
+ "M": 44,
2484
+ "N": 45,
2485
+ "O": 46,
2486
+ "P": 47,
2487
+ "Q": 48,
2488
+ "R": 49,
2489
+ "S": 50,
2490
+ "T": 51,
2491
+ "U": 52,
2492
+ "V": 53,
2493
+ "W": 54,
2494
+ "X": 55,
2495
+ "Y": 56,
2496
+ "Z": 57,
2497
+ "[": 58,
2498
+ "\\": 59,
2499
+ "]": 60,
2500
+ "^": 61,
2501
+ "_": 62,
2502
+ "`": 63,
2503
+ "a": 64,
2504
+ "b": 65,
2505
+ "c": 66,
2506
+ "d": 67,
2507
+ "e": 68,
2508
+ "f": 69,
2509
+ "g": 70,
2510
+ "h": 71,
2511
+ "i": 72,
2512
+ "j": 73,
2513
+ "k": 74,
2514
+ "l": 75,
2515
+ "m": 76,
2516
+ "n": 77,
2517
+ "o": 78,
2518
+ "p": 79,
2519
+ "q": 80,
2520
+ "r": 81,
2521
+ "s": 82,
2522
+ "t": 83,
2523
+ "u": 84,
2524
+ "v": 85,
2525
+ "w": 86,
2526
+ "x": 87,
2527
+ "y": 88,
2528
+ "z": 89,
2529
+ "{": 90,
2530
+ "|": 91,
2531
+ "}": 92,
2532
+ "~": 93,
2533
+ "¡": 94,
2534
+ "¢": 95,
2535
+ "£": 96,
2536
+ "¤": 97,
2537
+ "¥": 98,
2538
+ "¦": 99,
2539
+ "§": 100,
2540
+ "¨": 101,
2541
+ "©": 102,
2542
+ "ª": 103,
2543
+ "«": 104,
2544
+ "¬": 105,
2545
+ "®": 106,
2546
+ "¯": 107,
2547
+ "°": 108,
2548
+ "±": 109,
2549
+ "²": 110,
2550
+ "³": 111,
2551
+ "´": 112,
2552
+ "µ": 113,
2553
+ "¶": 114,
2554
+ "·": 115,
2555
+ "¸": 116,
2556
+ "¹": 117,
2557
+ "º": 118,
2558
+ "»": 119,
2559
+ "¼": 120,
2560
+ "½": 121,
2561
+ "¾": 122,
2562
+ "¿": 123,
2563
+ "À": 124,
2564
+ "Á": 125,
2565
+ "Â": 126,
2566
+ "Ã": 127,
2567
+ "Ä": 128,
2568
+ "Å": 129,
2569
+ "Æ": 130,
2570
+ "Ç": 131,
2571
+ "È": 132,
2572
+ "É": 133,
2573
+ "Ê": 134,
2574
+ "Ë": 135,
2575
+ "Ì": 136,
2576
+ "Í": 137,
2577
+ "Î": 138,
2578
+ "Ï": 139,
2579
+ "Ð": 140,
2580
+ "Ñ": 141,
2581
+ "Ò": 142,
2582
+ "Ó": 143,
2583
+ "Ô": 144,
2584
+ "Õ": 145,
2585
+ "Ö": 146,
2586
+ "×": 147,
2587
+ "Ø": 148,
2588
+ "Ù": 149,
2589
+ "Ú": 150,
2590
+ "Û": 151,
2591
+ "Ü": 152,
2592
+ "Ý": 153,
2593
+ "Þ": 154,
2594
+ "ß": 155,
2595
+ "à": 156,
2596
+ "á": 157,
2597
+ "â": 158,
2598
+ "ã": 159,
2599
+ "ä": 160,
2600
+ "å": 161,
2601
+ "æ": 162,
2602
+ "ç": 163,
2603
+ "è": 164,
2604
+ "é": 165,
2605
+ "ê": 166,
2606
+ "ë": 167,
2607
+ "ì": 168,
2608
+ "í": 169,
2609
+ "î": 170,
2610
+ "ï": 171,
2611
+ "ð": 172,
2612
+ "ñ": 173,
2613
+ "ò": 174,
2614
+ "ó": 175,
2615
+ "ô": 176,
2616
+ "õ": 177,
2617
+ "ö": 178,
2618
+ "÷": 179,
2619
+ "ø": 180,
2620
+ "ù": 181,
2621
+ "ú": 182,
2622
+ "û": 183,
2623
+ "ü": 184,
2624
+ "ý": 185,
2625
+ "þ": 186,
2626
+ "ÿ": 187,
2627
+ "Ā": 188,
2628
+ "ā": 189,
2629
+ "Ă": 190,
2630
+ "ă": 191,
2631
+ "Ą": 192,
2632
+ "ą": 193,
2633
+ "Ć": 194,
2634
+ "ć": 195,
2635
+ "Ĉ": 196,
2636
+ "ĉ": 197,
2637
+ "Ċ": 198,
2638
+ "ċ": 199,
2639
+ "Č": 200,
2640
+ "č": 201,
2641
+ "Ď": 202,
2642
+ "ď": 203,
2643
+ "Đ": 204,
2644
+ "đ": 205,
2645
+ "Ē": 206,
2646
+ "ē": 207,
2647
+ "Ĕ": 208,
2648
+ "ĕ": 209,
2649
+ "Ė": 210,
2650
+ "ė": 211,
2651
+ "Ę": 212,
2652
+ "ę": 213,
2653
+ "Ě": 214,
2654
+ "ě": 215,
2655
+ "Ĝ": 216,
2656
+ "ĝ": 217,
2657
+ "Ğ": 218,
2658
+ "ğ": 219,
2659
+ "Ġ": 220,
2660
+ "ġ": 221,
2661
+ "Ģ": 222,
2662
+ "ģ": 223,
2663
+ "Ĥ": 224,
2664
+ "ĥ": 225,
2665
+ "Ħ": 226,
2666
+ "ħ": 227,
2667
+ "Ĩ": 228,
2668
+ "ĩ": 229,
2669
+ "Ī": 230,
2670
+ "ī": 231,
2671
+ "Ĭ": 232,
2672
+ "ĭ": 233,
2673
+ "Į": 234,
2674
+ "į": 235,
2675
+ "İ": 236,
2676
+ "ı": 237,
2677
+ "IJ": 238,
2678
+ "ij": 239,
2679
+ "Ĵ": 240,
2680
+ "ĵ": 241,
2681
+ "Ķ": 242,
2682
+ "ķ": 243,
2683
+ "ĸ": 244,
2684
+ "Ĺ": 245,
2685
+ "ĺ": 246,
2686
+ "Ļ": 247,
2687
+ "ļ": 248,
2688
+ "Ľ": 249,
2689
+ "ľ": 250,
2690
+ "Ŀ": 251,
2691
+ "ŀ": 252,
2692
+ "Ł": 253,
2693
+ "ł": 254,
2694
+ "Ń": 255,
2695
+ "ĠĠ": 256,
2696
+ "ĠĠĠĠ": 257,
2697
+ "in": 258,
2698
+ "Ġt": 259,
2699
+ "ĠĠĠĠĠĠĠĠ": 260,
2700
+ "er": 261,
2701
+ "ĠĠĠ": 262,
2702
+ "on": 263,
2703
+ "Ġa": 264,
2704
+ "re": 265,
2705
+ "at": 266,
2706
+ "st": 267,
2707
+ "en": 268,
2708
+ "or": 269,
2709
+ "Ġth": 270,
2710
+ "ĊĊ": 271,
2711
+ "Ġc": 272,
2712
+ "le": 273,
2713
+ "Ġs": 274,
2714
+ "it": 275,
2715
+ "an": 276,
2716
+ "ar": 277,
2717
+ "al": 278,
2718
+ "Ġthe": 279,
2719
+ ";Ċ": 280,
2720
+ "Ġp": 281,
2721
+ "Ġf": 282,
2722
+ "ou": 283,
2723
+ "Ġ=": 284,
2724
+ "is": 285,
2725
+ "ĠĠĠĠĠĠĠ": 286,
2726
+ "ing": 287,
2727
+ "es": 288,
2728
+ "Ġw": 289,
2729
+ "ion": 290,
2730
+ "ed": 291,
2731
+ "ic": 292,
2732
+ "Ġb": 293,
2733
+ "Ġd": 294,
2734
+ "et": 295,
2735
+ "Ġm": 296,
2736
+ "Ġo": 297,
2737
+ "ĉĉ": 298,
2738
+ "ro": 299,
2739
+ "as": 300,
2740
+ "el": 301,
2741
+ "ct": 302,
2742
+ "nd": 303,
2743
+ "Ġin": 304,
2744
+ "Ġh": 305,
2745
+ "ent": 306,
2746
+ "id": 307,
2747
+ "Ġn": 308,
2748
+ "am": 309,
2749
+ "ĠĠĠĠĠĠĠĠĠĠĠ": 310,
2750
+ "Ġto": 311,
2751
+ "Ġre": 312,
2752
+ "--": 313,
2753
+ "Ġ{": 314,
2754
+ "Ġof": 315,
2755
+ "om": 316,
2756
+ ");Ċ": 317,
2757
+ "im": 318,
2758
+ "čĊ": 319,
2759
+ "Ġ(": 320,
2760
+ "il": 321,
2761
+ "//": 322,
2762
+ "Ġand": 323,
2763
+ "ur": 324,
2764
+ "se": 325,
2765
+ "Ġl": 326,
2766
+ "ex": 327,
2767
+ "ĠS": 328,
2768
+ "ad": 329,
2769
+ "Ġ\"": 330,
2770
+ "ch": 331,
2771
+ "ut": 332,
2772
+ "if": 333,
2773
+ "**": 334,
2774
+ "Ġ}": 335,
2775
+ "em": 336,
2776
+ "ol": 337,
2777
+ "ĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠ": 338,
2778
+ "th": 339,
2779
+ ")Ċ": 340,
2780
+ "Ġ{Ċ": 341,
2781
+ "Ġg": 342,
2782
+ "ig": 343,
2783
+ "iv": 344,
2784
+ ",Ċ": 345,
2785
+ "ce": 346,
2786
+ "od": 347,
2787
+ "Ġv": 348,
2788
+ "ate": 349,
2789
+ "ĠT": 350,
2790
+ "ag": 351,
2791
+ "ay": 352,
2792
+ "Ġ*": 353,
2793
+ "ot": 354,
2794
+ "us": 355,
2795
+ "ĠC": 356,
2796
+ "Ġst": 357,
2797
+ "ĠI": 358,
2798
+ "un": 359,
2799
+ "ul": 360,
2800
+ "ue": 361,
2801
+ "ĠA": 362,
2802
+ "ow": 363,
2803
+ "Ġ'": 364,
2804
+ "ew": 365,
2805
+ "Ġ<": 366,
2806
+ "ation": 367,
2807
+ "()": 368,
2808
+ "Ġfor": 369,
2809
+ "ab": 370,
2810
+ "ort": 371,
2811
+ "um": 372,
2812
+ "ame": 373,
2813
+ "Ġis": 374,
2814
+ "pe": 375,
2815
+ "tr": 376,
2816
+ "ck": 377,
2817
+ "âĢ": 378,
2818
+ "Ġy": 379,
2819
+ "ist": 380,
2820
+ "----": 381,
2821
+ ".ĊĊ": 382,
2822
+ "he": 383,
2823
+ "Ġe": 384,
2824
+ "lo": 385,
2825
+ "ĠM": 386,
2826
+ "Ġbe": 387,
2827
+ "ers": 388,
2828
+ "Ġon": 389,
2829
+ "Ġcon": 390,
2830
+ "ap": 391,
2831
+ "ub": 392,
2832
+ "ĠP": 393,
2833
+ "ĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠ": 394,
2834
+ "ass": 395,
2835
+ "int": 396,
2836
+ ">Ċ": 397,
2837
+ "ly": 398,
2838
+ "urn": 399,
2839
+ "Ġ$": 400,
2840
+ ";ĊĊ": 401,
2841
+ "av": 402,
2842
+ "port": 403,
2843
+ "ir": 404,
2844
+ "->": 405,
2845
+ "nt": 406,
2846
+ "ction": 407,
2847
+ "end": 408,
2848
+ "Ġde": 409,
2849
+ "00": 410,
2850
+ "ith": 411,
2851
+ "out": 412,
2852
+ "turn": 413,
2853
+ "our": 414,
2854
+ "ĠĠĠĠĠ": 415,
2855
+ "lic": 416,
2856
+ "res": 417,
2857
+ "pt": 418,
2858
+ "==": 419,
2859
+ "Ġthis": 420,
2860
+ "Ġwh": 421,
2861
+ "Ġif": 422,
2862
+ "ĠD": 423,
2863
+ "ver": 424,
2864
+ "age": 425,
2865
+ "ĠB": 426,
2866
+ "ht": 427,
2867
+ "ext": 428,
2868
+ "=\"": 429,
2869
+ "Ġthat": 430,
2870
+ "****": 431,
2871
+ "ĠR": 432,
2872
+ "Ġit": 433,
2873
+ "ess": 434,
2874
+ "ĠF": 435,
2875
+ "Ġr": 436,
2876
+ "os": 437,
2877
+ "and": 438,
2878
+ "Ġas": 439,
2879
+ "ect": 440,
2880
+ "ke": 441,
2881
+ "rom": 442,
2882
+ "Ġ//": 443,
2883
+ "con": 444,
2884
+ "ĠL": 445,
2885
+ "(\"": 446,
2886
+ "qu": 447,
2887
+ "lass": 448,
2888
+ "Ġwith": 449,
2889
+ "iz": 450,
2890
+ "de": 451,
2891
+ "ĠN": 452,
2892
+ "Ġal": 453,
2893
+ "op": 454,
2894
+ "up": 455,
2895
+ "get": 456,
2896
+ "Ġ}Ċ": 457,
2897
+ "ile": 458,
2898
+ "Ġan": 459,
2899
+ "ata": 460,
2900
+ "ore": 461,
2901
+ "ri": 462,
2902
+ "Ġpro": 463,
2903
+ ";čĊ": 464,
2904
+ "ĉĉĉĉ": 465,
2905
+ "ter": 466,
2906
+ "ain": 467,
2907
+ "ĠW": 468,
2908
+ "ĠE": 469,
2909
+ "Ġcom": 470,
2910
+ "Ġreturn": 471,
2911
+ "art": 472,
2912
+ "ĠH": 473,
2913
+ "ack": 474,
2914
+ "import": 475,
2915
+ "ublic": 476,
2916
+ "Ġor": 477,
2917
+ "est": 478,
2918
+ "ment": 479,
2919
+ "ĠG": 480,
2920
+ "able": 481,
2921
+ "Ġ-": 482,
2922
+ "ine": 483,
2923
+ "ill": 484,
2924
+ "ind": 485,
2925
+ "ere": 486,
2926
+ "::": 487,
2927
+ "ity": 488,
2928
+ "Ġ+": 489,
2929
+ "Ġtr": 490,
2930
+ "elf": 491,
2931
+ "ight": 492,
2932
+ "('": 493,
2933
+ "orm": 494,
2934
+ "ult": 495,
2935
+ "str": 496,
2936
+ "..": 497,
2937
+ "\",": 498,
2938
+ "Ġyou": 499
2939
+ },
2940
+ "merges": [
2941
+ "Ġ Ġ",
2942
+ "Ġ ĠĠĠ",
2943
+ "ĠĠ ĠĠ",
2944
+ "ĠĠĠ Ġ",
2945
+ "i n",
2946
+ "Ġ t",
2947
+ "Ġ ĠĠĠĠĠĠĠ",
2948
+ "ĠĠĠĠ ĠĠĠĠ",
2949
+ "ĠĠĠ ĠĠĠĠĠ",
2950
+ "ĠĠĠĠĠĠĠ Ġ",
2951
+ "ĠĠĠĠĠ ĠĠĠ",
2952
+ "e r",
2953
+ "Ġ ĠĠ",
2954
+ "ĠĠ Ġ",
2955
+ "o n",
2956
+ "Ġ a",
2957
+ "r e",
2958
+ "a t",
2959
+ "s t",
2960
+ "e n",
2961
+ "o r",
2962
+ "Ġ th",
2963
+ "Ġt h",
2964
+ "Ċ Ċ",
2965
+ "Ġ c",
2966
+ "l e",
2967
+ "Ġ s",
2968
+ "i t",
2969
+ "a n",
2970
+ "a r",
2971
+ "a l",
2972
+ "Ġt he",
2973
+ "Ġth e",
2974
+ "; Ċ",
2975
+ "Ġ p",
2976
+ "Ġ f",
2977
+ "o u",
2978
+ "Ġ =",
2979
+ "i s",
2980
+ "ĠĠ ĠĠĠĠĠ",
2981
+ "ĠĠĠĠ ĠĠĠ",
2982
+ "ĠĠĠ ĠĠĠĠ",
2983
+ "ĠĠĠĠĠ ĠĠ",
2984
+ "in g",
2985
+ "e s",
2986
+ "Ġ w",
2987
+ "i on",
2988
+ "e d",
2989
+ "i c",
2990
+ "Ġ b",
2991
+ "Ġ d",
2992
+ "e t",
2993
+ "Ġ m",
2994
+ "Ġ o",
2995
+ "ĉ ĉ",
2996
+ "r o",
2997
+ "a s",
2998
+ "e l",
2999
+ "c t",
3000
+ "n d",
3001
+ "Ġ in",
3002
+ "Ġ h",
3003
+ "e nt",
3004
+ "en t",
3005
+ "i d",
3006
+ "Ġ n",
3007
+ "a m",
3008
+ "ĠĠĠĠ ĠĠĠĠĠĠĠ",
3009
+ "ĠĠĠĠĠĠĠĠ ĠĠĠ",
3010
+ "ĠĠĠ ĠĠĠĠĠĠĠĠ",
3011
+ "ĠĠĠĠĠĠĠ ĠĠĠĠ",
3012
+ "Ġt o",
3013
+ "Ġ re",
3014
+ "Ġr e",
3015
+ "- -",
3016
+ "Ġ {",
3017
+ "Ġo f",
3018
+ "o m",
3019
+ ") ;Ċ",
3020
+ "i m",
3021
+ "č Ċ",
3022
+ "Ġ (",
3023
+ "i l",
3024
+ "/ /",
3025
+ "Ġ and",
3026
+ "Ġa nd",
3027
+ "Ġan d",
3028
+ "u r",
3029
+ "s e",
3030
+ "Ġ l",
3031
+ "e x",
3032
+ "Ġ S",
3033
+ "a d",
3034
+ "Ġ \"",
3035
+ "c h",
3036
+ "u t",
3037
+ "i f",
3038
+ "* *",
3039
+ "Ġ }",
3040
+ "e m",
3041
+ "o l",
3042
+ "Ġ ĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠ",
3043
+ "ĠĠĠĠĠĠĠĠ ĠĠĠĠĠĠĠĠ",
3044
+ "ĠĠĠĠĠĠĠĠĠĠĠ ĠĠĠĠĠ",
3045
+ "ĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠ Ġ",
3046
+ "ĠĠĠĠĠ ĠĠĠĠĠĠĠĠĠĠĠ",
3047
+ "t h",
3048
+ ") Ċ",
3049
+ "Ġ{ Ċ",
3050
+ "Ġ g",
3051
+ "i g",
3052
+ "i v",
3053
+ ", Ċ",
3054
+ "c e",
3055
+ "o d",
3056
+ "Ġ v",
3057
+ "at e",
3058
+ "Ġ T",
3059
+ "a g",
3060
+ "a y",
3061
+ "Ġ *",
3062
+ "o t",
3063
+ "u s",
3064
+ "Ġ C",
3065
+ "Ġ st",
3066
+ "Ġs t",
3067
+ "Ġ I",
3068
+ "u n",
3069
+ "u l",
3070
+ "u e",
3071
+ "Ġ A",
3072
+ "o w",
3073
+ "Ġ '",
3074
+ "e w",
3075
+ "Ġ <",
3076
+ "at ion",
3077
+ "( )",
3078
+ "Ġf or",
3079
+ "a b",
3080
+ "or t",
3081
+ "u m",
3082
+ "am e",
3083
+ "Ġ is",
3084
+ "p e",
3085
+ "t r",
3086
+ "c k",
3087
+ "â Ģ",
3088
+ "Ġ y",
3089
+ "i st",
3090
+ "is t",
3091
+ "-- --",
3092
+ ". ĊĊ",
3093
+ "h e",
3094
+ "Ġ e",
3095
+ "l o",
3096
+ "Ġ M",
3097
+ "Ġb e",
3098
+ "er s",
3099
+ "Ġ on",
3100
+ "Ġo n",
3101
+ "Ġ con",
3102
+ "Ġc on",
3103
+ "a p",
3104
+ "u b",
3105
+ "Ġ P",
3106
+ "ĠĠĠĠ ĠĠĠĠĠĠĠĠĠĠĠ",
3107
+ "ĠĠĠĠĠĠĠĠ ĠĠĠĠĠĠĠ",
3108
+ "ĠĠĠĠĠĠĠ ĠĠĠĠĠĠĠĠ",
3109
+ "ĠĠĠĠĠĠĠĠĠĠĠ ĠĠĠĠ",
3110
+ "as s",
3111
+ "i nt",
3112
+ "in t",
3113
+ "> Ċ",
3114
+ "l y",
3115
+ "ur n",
3116
+ "Ġ $",
3117
+ "; ĊĊ",
3118
+ ";Ċ Ċ",
3119
+ "a v",
3120
+ "p ort",
3121
+ "i r",
3122
+ "- >",
3123
+ "n t",
3124
+ "ct ion",
3125
+ "e nd",
3126
+ "en d",
3127
+ "Ġ de",
3128
+ "Ġd e",
3129
+ "0 0",
3130
+ "i th",
3131
+ "it h",
3132
+ "o ut",
3133
+ "ou t",
3134
+ "t urn",
3135
+ "o ur",
3136
+ "ou r",
3137
+ "Ġ ĠĠĠĠ",
3138
+ "ĠĠ ĠĠĠ",
3139
+ "ĠĠĠĠ Ġ",
3140
+ "ĠĠĠ ĠĠ",
3141
+ "l ic",
3142
+ "r es",
3143
+ "re s",
3144
+ "p t",
3145
+ "= =",
3146
+ "Ġth is",
3147
+ "Ġw h",
3148
+ "Ġ if",
3149
+ "Ġ D",
3150
+ "v er",
3151
+ "ag e",
3152
+ "Ġ B",
3153
+ "h t",
3154
+ "ex t",
3155
+ "= \"",
3156
+ "Ġth at",
3157
+ "** **",
3158
+ "Ġ R",
3159
+ "Ġ it",
3160
+ "es s",
3161
+ "Ġ F",
3162
+ "Ġ r",
3163
+ "o s",
3164
+ "a nd",
3165
+ "an d",
3166
+ "Ġ as",
3167
+ "Ġa s",
3168
+ "e ct",
3169
+ "k e",
3170
+ "r om",
3171
+ "ro m",
3172
+ "Ġ //",
3173
+ "c on",
3174
+ "Ġ L",
3175
+ "( \"",
3176
+ "q u",
3177
+ "l ass",
3178
+ "Ġw ith",
3179
+ "i z",
3180
+ "d e",
3181
+ "Ġ N",
3182
+ "Ġ al",
3183
+ "Ġa l",
3184
+ "o p",
3185
+ "u p",
3186
+ "g et",
3187
+ "Ġ} Ċ",
3188
+ "i le",
3189
+ "il e",
3190
+ "Ġ an",
3191
+ "Ġa n",
3192
+ "at a",
3193
+ "o re",
3194
+ "or e",
3195
+ "r i",
3196
+ "Ġp ro",
3197
+ "; čĊ",
3198
+ "ĉĉ ĉĉ",
3199
+ "t er",
3200
+ "a in",
3201
+ "Ġ W",
3202
+ "Ġ E",
3203
+ "Ġc om",
3204
+ "Ġre turn",
3205
+ "ar t",
3206
+ "Ġ H",
3207
+ "a ck",
3208
+ "im port",
3209
+ "ub lic",
3210
+ "Ġ or",
3211
+ "Ġo r",
3212
+ "e st",
3213
+ "es t",
3214
+ "m ent",
3215
+ "Ġ G",
3216
+ "ab le",
3217
+ "Ġ -",
3218
+ "in e",
3219
+ "il l",
3220
+ "i nd",
3221
+ "in d",
3222
+ "e re",
3223
+ "er e",
3224
+ ": :",
3225
+ "it y",
3226
+ "Ġ +",
3227
+ "Ġ tr",
3228
+ "Ġt r",
3229
+ "el f",
3230
+ "ig ht",
3231
+ "( '",
3232
+ "or m",
3233
+ "ul t",
3234
+ "s tr",
3235
+ "st r",
3236
+ ". .",
3237
+ "\" ,",
3238
+ "Ġy ou"
3239
+ ]
3240
+ }
3241
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,2097 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_eos_token": true,
3
+ "padding_side": "left",
4
+ "truncation_side": "left",
5
+ "added_tokens_decoder": {
6
+ "128000": {
7
+ "content": "<|begin_of_text|>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "128001": {
15
+ "content": "<|end_of_text|>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "128002": {
23
+ "content": "<|reserved_special_token_0|>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ },
30
+ "128003": {
31
+ "content": "<|reserved_special_token_1|>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": true
37
+ },
38
+ "128004": {
39
+ "content": "<|finetune_right_pad_id|>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": false,
43
+ "single_word": false,
44
+ "special": true
45
+ },
46
+ "128005": {
47
+ "content": "<|reserved_special_token_2|>",
48
+ "lstrip": false,
49
+ "normalized": false,
50
+ "rstrip": false,
51
+ "single_word": false,
52
+ "special": true
53
+ },
54
+ "128006": {
55
+ "content": "<|start_header_id|>",
56
+ "lstrip": false,
57
+ "normalized": false,
58
+ "rstrip": false,
59
+ "single_word": false,
60
+ "special": true
61
+ },
62
+ "128007": {
63
+ "content": "<|end_header_id|>",
64
+ "lstrip": false,
65
+ "normalized": false,
66
+ "rstrip": false,
67
+ "single_word": false,
68
+ "special": true
69
+ },
70
+ "128008": {
71
+ "content": "<|eom_id|>",
72
+ "lstrip": false,
73
+ "normalized": false,
74
+ "rstrip": false,
75
+ "single_word": false,
76
+ "special": true
77
+ },
78
+ "128009": {
79
+ "content": "<|eot_id|>",
80
+ "lstrip": false,
81
+ "normalized": false,
82
+ "rstrip": false,
83
+ "single_word": false,
84
+ "special": true
85
+ },
86
+ "128010": {
87
+ "content": "<|python_tag|>",
88
+ "lstrip": false,
89
+ "normalized": false,
90
+ "rstrip": false,
91
+ "single_word": false,
92
+ "special": true
93
+ },
94
+ "128011": {
95
+ "content": "<|reserved_special_token_3|>",
96
+ "lstrip": false,
97
+ "normalized": false,
98
+ "rstrip": false,
99
+ "single_word": false,
100
+ "special": true
101
+ },
102
+ "128012": {
103
+ "content": "<|reserved_special_token_4|>",
104
+ "lstrip": false,
105
+ "normalized": false,
106
+ "rstrip": false,
107
+ "single_word": false,
108
+ "special": true
109
+ },
110
+ "128013": {
111
+ "content": "<|reserved_special_token_5|>",
112
+ "lstrip": false,
113
+ "normalized": false,
114
+ "rstrip": false,
115
+ "single_word": false,
116
+ "special": true
117
+ },
118
+ "128014": {
119
+ "content": "<|reserved_special_token_6|>",
120
+ "lstrip": false,
121
+ "normalized": false,
122
+ "rstrip": false,
123
+ "single_word": false,
124
+ "special": true
125
+ },
126
+ "128015": {
127
+ "content": "<|reserved_special_token_7|>",
128
+ "lstrip": false,
129
+ "normalized": false,
130
+ "rstrip": false,
131
+ "single_word": false,
132
+ "special": true
133
+ },
134
+ "128016": {
135
+ "content": "<|reserved_special_token_8|>",
136
+ "lstrip": false,
137
+ "normalized": false,
138
+ "rstrip": false,
139
+ "single_word": false,
140
+ "special": true
141
+ },
142
+ "128017": {
143
+ "content": "<|reserved_special_token_9|>",
144
+ "lstrip": false,
145
+ "normalized": false,
146
+ "rstrip": false,
147
+ "single_word": false,
148
+ "special": true
149
+ },
150
+ "128018": {
151
+ "content": "<|reserved_special_token_10|>",
152
+ "lstrip": false,
153
+ "normalized": false,
154
+ "rstrip": false,
155
+ "single_word": false,
156
+ "special": true
157
+ },
158
+ "128019": {
159
+ "content": "<|reserved_special_token_11|>",
160
+ "lstrip": false,
161
+ "normalized": false,
162
+ "rstrip": false,
163
+ "single_word": false,
164
+ "special": true
165
+ },
166
+ "128020": {
167
+ "content": "<|reserved_special_token_12|>",
168
+ "lstrip": false,
169
+ "normalized": false,
170
+ "rstrip": false,
171
+ "single_word": false,
172
+ "special": true
173
+ },
174
+ "128021": {
175
+ "content": "<|reserved_special_token_13|>",
176
+ "lstrip": false,
177
+ "normalized": false,
178
+ "rstrip": false,
179
+ "single_word": false,
180
+ "special": true
181
+ },
182
+ "128022": {
183
+ "content": "<|reserved_special_token_14|>",
184
+ "lstrip": false,
185
+ "normalized": false,
186
+ "rstrip": false,
187
+ "single_word": false,
188
+ "special": true
189
+ },
190
+ "128023": {
191
+ "content": "<|reserved_special_token_15|>",
192
+ "lstrip": false,
193
+ "normalized": false,
194
+ "rstrip": false,
195
+ "single_word": false,
196
+ "special": true
197
+ },
198
+ "128024": {
199
+ "content": "<|reserved_special_token_16|>",
200
+ "lstrip": false,
201
+ "normalized": false,
202
+ "rstrip": false,
203
+ "single_word": false,
204
+ "special": true
205
+ },
206
+ "128025": {
207
+ "content": "<|reserved_special_token_17|>",
208
+ "lstrip": false,
209
+ "normalized": false,
210
+ "rstrip": false,
211
+ "single_word": false,
212
+ "special": true
213
+ },
214
+ "128026": {
215
+ "content": "<|reserved_special_token_18|>",
216
+ "lstrip": false,
217
+ "normalized": false,
218
+ "rstrip": false,
219
+ "single_word": false,
220
+ "special": true
221
+ },
222
+ "128027": {
223
+ "content": "<|reserved_special_token_19|>",
224
+ "lstrip": false,
225
+ "normalized": false,
226
+ "rstrip": false,
227
+ "single_word": false,
228
+ "special": true
229
+ },
230
+ "128028": {
231
+ "content": "<|reserved_special_token_20|>",
232
+ "lstrip": false,
233
+ "normalized": false,
234
+ "rstrip": false,
235
+ "single_word": false,
236
+ "special": true
237
+ },
238
+ "128029": {
239
+ "content": "<|reserved_special_token_21|>",
240
+ "lstrip": false,
241
+ "normalized": false,
242
+ "rstrip": false,
243
+ "single_word": false,
244
+ "special": true
245
+ },
246
+ "128030": {
247
+ "content": "<|reserved_special_token_22|>",
248
+ "lstrip": false,
249
+ "normalized": false,
250
+ "rstrip": false,
251
+ "single_word": false,
252
+ "special": true
253
+ },
254
+ "128031": {
255
+ "content": "<|reserved_special_token_23|>",
256
+ "lstrip": false,
257
+ "normalized": false,
258
+ "rstrip": false,
259
+ "single_word": false,
260
+ "special": true
261
+ },
262
+ "128032": {
263
+ "content": "<|reserved_special_token_24|>",
264
+ "lstrip": false,
265
+ "normalized": false,
266
+ "rstrip": false,
267
+ "single_word": false,
268
+ "special": true
269
+ },
270
+ "128033": {
271
+ "content": "<|reserved_special_token_25|>",
272
+ "lstrip": false,
273
+ "normalized": false,
274
+ "rstrip": false,
275
+ "single_word": false,
276
+ "special": true
277
+ },
278
+ "128034": {
279
+ "content": "<|reserved_special_token_26|>",
280
+ "lstrip": false,
281
+ "normalized": false,
282
+ "rstrip": false,
283
+ "single_word": false,
284
+ "special": true
285
+ },
286
+ "128035": {
287
+ "content": "<|reserved_special_token_27|>",
288
+ "lstrip": false,
289
+ "normalized": false,
290
+ "rstrip": false,
291
+ "single_word": false,
292
+ "special": true
293
+ },
294
+ "128036": {
295
+ "content": "<|reserved_special_token_28|>",
296
+ "lstrip": false,
297
+ "normalized": false,
298
+ "rstrip": false,
299
+ "single_word": false,
300
+ "special": true
301
+ },
302
+ "128037": {
303
+ "content": "<|reserved_special_token_29|>",
304
+ "lstrip": false,
305
+ "normalized": false,
306
+ "rstrip": false,
307
+ "single_word": false,
308
+ "special": true
309
+ },
310
+ "128038": {
311
+ "content": "<|reserved_special_token_30|>",
312
+ "lstrip": false,
313
+ "normalized": false,
314
+ "rstrip": false,
315
+ "single_word": false,
316
+ "special": true
317
+ },
318
+ "128039": {
319
+ "content": "<|reserved_special_token_31|>",
320
+ "lstrip": false,
321
+ "normalized": false,
322
+ "rstrip": false,
323
+ "single_word": false,
324
+ "special": true
325
+ },
326
+ "128040": {
327
+ "content": "<|reserved_special_token_32|>",
328
+ "lstrip": false,
329
+ "normalized": false,
330
+ "rstrip": false,
331
+ "single_word": false,
332
+ "special": true
333
+ },
334
+ "128041": {
335
+ "content": "<|reserved_special_token_33|>",
336
+ "lstrip": false,
337
+ "normalized": false,
338
+ "rstrip": false,
339
+ "single_word": false,
340
+ "special": true
341
+ },
342
+ "128042": {
343
+ "content": "<|reserved_special_token_34|>",
344
+ "lstrip": false,
345
+ "normalized": false,
346
+ "rstrip": false,
347
+ "single_word": false,
348
+ "special": true
349
+ },
350
+ "128043": {
351
+ "content": "<|reserved_special_token_35|>",
352
+ "lstrip": false,
353
+ "normalized": false,
354
+ "rstrip": false,
355
+ "single_word": false,
356
+ "special": true
357
+ },
358
+ "128044": {
359
+ "content": "<|reserved_special_token_36|>",
360
+ "lstrip": false,
361
+ "normalized": false,
362
+ "rstrip": false,
363
+ "single_word": false,
364
+ "special": true
365
+ },
366
+ "128045": {
367
+ "content": "<|reserved_special_token_37|>",
368
+ "lstrip": false,
369
+ "normalized": false,
370
+ "rstrip": false,
371
+ "single_word": false,
372
+ "special": true
373
+ },
374
+ "128046": {
375
+ "content": "<|reserved_special_token_38|>",
376
+ "lstrip": false,
377
+ "normalized": false,
378
+ "rstrip": false,
379
+ "single_word": false,
380
+ "special": true
381
+ },
382
+ "128047": {
383
+ "content": "<|reserved_special_token_39|>",
384
+ "lstrip": false,
385
+ "normalized": false,
386
+ "rstrip": false,
387
+ "single_word": false,
388
+ "special": true
389
+ },
390
+ "128048": {
391
+ "content": "<|reserved_special_token_40|>",
392
+ "lstrip": false,
393
+ "normalized": false,
394
+ "rstrip": false,
395
+ "single_word": false,
396
+ "special": true
397
+ },
398
+ "128049": {
399
+ "content": "<|reserved_special_token_41|>",
400
+ "lstrip": false,
401
+ "normalized": false,
402
+ "rstrip": false,
403
+ "single_word": false,
404
+ "special": true
405
+ },
406
+ "128050": {
407
+ "content": "<|reserved_special_token_42|>",
408
+ "lstrip": false,
409
+ "normalized": false,
410
+ "rstrip": false,
411
+ "single_word": false,
412
+ "special": true
413
+ },
414
+ "128051": {
415
+ "content": "<|reserved_special_token_43|>",
416
+ "lstrip": false,
417
+ "normalized": false,
418
+ "rstrip": false,
419
+ "single_word": false,
420
+ "special": true
421
+ },
422
+ "128052": {
423
+ "content": "<|reserved_special_token_44|>",
424
+ "lstrip": false,
425
+ "normalized": false,
426
+ "rstrip": false,
427
+ "single_word": false,
428
+ "special": true
429
+ },
430
+ "128053": {
431
+ "content": "<|reserved_special_token_45|>",
432
+ "lstrip": false,
433
+ "normalized": false,
434
+ "rstrip": false,
435
+ "single_word": false,
436
+ "special": true
437
+ },
438
+ "128054": {
439
+ "content": "<|reserved_special_token_46|>",
440
+ "lstrip": false,
441
+ "normalized": false,
442
+ "rstrip": false,
443
+ "single_word": false,
444
+ "special": true
445
+ },
446
+ "128055": {
447
+ "content": "<|reserved_special_token_47|>",
448
+ "lstrip": false,
449
+ "normalized": false,
450
+ "rstrip": false,
451
+ "single_word": false,
452
+ "special": true
453
+ },
454
+ "128056": {
455
+ "content": "<|reserved_special_token_48|>",
456
+ "lstrip": false,
457
+ "normalized": false,
458
+ "rstrip": false,
459
+ "single_word": false,
460
+ "special": true
461
+ },
462
+ "128057": {
463
+ "content": "<|reserved_special_token_49|>",
464
+ "lstrip": false,
465
+ "normalized": false,
466
+ "rstrip": false,
467
+ "single_word": false,
468
+ "special": true
469
+ },
470
+ "128058": {
471
+ "content": "<|reserved_special_token_50|>",
472
+ "lstrip": false,
473
+ "normalized": false,
474
+ "rstrip": false,
475
+ "single_word": false,
476
+ "special": true
477
+ },
478
+ "128059": {
479
+ "content": "<|reserved_special_token_51|>",
480
+ "lstrip": false,
481
+ "normalized": false,
482
+ "rstrip": false,
483
+ "single_word": false,
484
+ "special": true
485
+ },
486
+ "128060": {
487
+ "content": "<|reserved_special_token_52|>",
488
+ "lstrip": false,
489
+ "normalized": false,
490
+ "rstrip": false,
491
+ "single_word": false,
492
+ "special": true
493
+ },
494
+ "128061": {
495
+ "content": "<|reserved_special_token_53|>",
496
+ "lstrip": false,
497
+ "normalized": false,
498
+ "rstrip": false,
499
+ "single_word": false,
500
+ "special": true
501
+ },
502
+ "128062": {
503
+ "content": "<|reserved_special_token_54|>",
504
+ "lstrip": false,
505
+ "normalized": false,
506
+ "rstrip": false,
507
+ "single_word": false,
508
+ "special": true
509
+ },
510
+ "128063": {
511
+ "content": "<|reserved_special_token_55|>",
512
+ "lstrip": false,
513
+ "normalized": false,
514
+ "rstrip": false,
515
+ "single_word": false,
516
+ "special": true
517
+ },
518
+ "128064": {
519
+ "content": "<|reserved_special_token_56|>",
520
+ "lstrip": false,
521
+ "normalized": false,
522
+ "rstrip": false,
523
+ "single_word": false,
524
+ "special": true
525
+ },
526
+ "128065": {
527
+ "content": "<|reserved_special_token_57|>",
528
+ "lstrip": false,
529
+ "normalized": false,
530
+ "rstrip": false,
531
+ "single_word": false,
532
+ "special": true
533
+ },
534
+ "128066": {
535
+ "content": "<|reserved_special_token_58|>",
536
+ "lstrip": false,
537
+ "normalized": false,
538
+ "rstrip": false,
539
+ "single_word": false,
540
+ "special": true
541
+ },
542
+ "128067": {
543
+ "content": "<|reserved_special_token_59|>",
544
+ "lstrip": false,
545
+ "normalized": false,
546
+ "rstrip": false,
547
+ "single_word": false,
548
+ "special": true
549
+ },
550
+ "128068": {
551
+ "content": "<|reserved_special_token_60|>",
552
+ "lstrip": false,
553
+ "normalized": false,
554
+ "rstrip": false,
555
+ "single_word": false,
556
+ "special": true
557
+ },
558
+ "128069": {
559
+ "content": "<|reserved_special_token_61|>",
560
+ "lstrip": false,
561
+ "normalized": false,
562
+ "rstrip": false,
563
+ "single_word": false,
564
+ "special": true
565
+ },
566
+ "128070": {
567
+ "content": "<|reserved_special_token_62|>",
568
+ "lstrip": false,
569
+ "normalized": false,
570
+ "rstrip": false,
571
+ "single_word": false,
572
+ "special": true
573
+ },
574
+ "128071": {
575
+ "content": "<|reserved_special_token_63|>",
576
+ "lstrip": false,
577
+ "normalized": false,
578
+ "rstrip": false,
579
+ "single_word": false,
580
+ "special": true
581
+ },
582
+ "128072": {
583
+ "content": "<|reserved_special_token_64|>",
584
+ "lstrip": false,
585
+ "normalized": false,
586
+ "rstrip": false,
587
+ "single_word": false,
588
+ "special": true
589
+ },
590
+ "128073": {
591
+ "content": "<|reserved_special_token_65|>",
592
+ "lstrip": false,
593
+ "normalized": false,
594
+ "rstrip": false,
595
+ "single_word": false,
596
+ "special": true
597
+ },
598
+ "128074": {
599
+ "content": "<|reserved_special_token_66|>",
600
+ "lstrip": false,
601
+ "normalized": false,
602
+ "rstrip": false,
603
+ "single_word": false,
604
+ "special": true
605
+ },
606
+ "128075": {
607
+ "content": "<|reserved_special_token_67|>",
608
+ "lstrip": false,
609
+ "normalized": false,
610
+ "rstrip": false,
611
+ "single_word": false,
612
+ "special": true
613
+ },
614
+ "128076": {
615
+ "content": "<|reserved_special_token_68|>",
616
+ "lstrip": false,
617
+ "normalized": false,
618
+ "rstrip": false,
619
+ "single_word": false,
620
+ "special": true
621
+ },
622
+ "128077": {
623
+ "content": "<|reserved_special_token_69|>",
624
+ "lstrip": false,
625
+ "normalized": false,
626
+ "rstrip": false,
627
+ "single_word": false,
628
+ "special": true
629
+ },
630
+ "128078": {
631
+ "content": "<|reserved_special_token_70|>",
632
+ "lstrip": false,
633
+ "normalized": false,
634
+ "rstrip": false,
635
+ "single_word": false,
636
+ "special": true
637
+ },
638
+ "128079": {
639
+ "content": "<|reserved_special_token_71|>",
640
+ "lstrip": false,
641
+ "normalized": false,
642
+ "rstrip": false,
643
+ "single_word": false,
644
+ "special": true
645
+ },
646
+ "128080": {
647
+ "content": "<|reserved_special_token_72|>",
648
+ "lstrip": false,
649
+ "normalized": false,
650
+ "rstrip": false,
651
+ "single_word": false,
652
+ "special": true
653
+ },
654
+ "128081": {
655
+ "content": "<|reserved_special_token_73|>",
656
+ "lstrip": false,
657
+ "normalized": false,
658
+ "rstrip": false,
659
+ "single_word": false,
660
+ "special": true
661
+ },
662
+ "128082": {
663
+ "content": "<|reserved_special_token_74|>",
664
+ "lstrip": false,
665
+ "normalized": false,
666
+ "rstrip": false,
667
+ "single_word": false,
668
+ "special": true
669
+ },
670
+ "128083": {
671
+ "content": "<|reserved_special_token_75|>",
672
+ "lstrip": false,
673
+ "normalized": false,
674
+ "rstrip": false,
675
+ "single_word": false,
676
+ "special": true
677
+ },
678
+ "128084": {
679
+ "content": "<|reserved_special_token_76|>",
680
+ "lstrip": false,
681
+ "normalized": false,
682
+ "rstrip": false,
683
+ "single_word": false,
684
+ "special": true
685
+ },
686
+ "128085": {
687
+ "content": "<|reserved_special_token_77|>",
688
+ "lstrip": false,
689
+ "normalized": false,
690
+ "rstrip": false,
691
+ "single_word": false,
692
+ "special": true
693
+ },
694
+ "128086": {
695
+ "content": "<|reserved_special_token_78|>",
696
+ "lstrip": false,
697
+ "normalized": false,
698
+ "rstrip": false,
699
+ "single_word": false,
700
+ "special": true
701
+ },
702
+ "128087": {
703
+ "content": "<|reserved_special_token_79|>",
704
+ "lstrip": false,
705
+ "normalized": false,
706
+ "rstrip": false,
707
+ "single_word": false,
708
+ "special": true
709
+ },
710
+ "128088": {
711
+ "content": "<|reserved_special_token_80|>",
712
+ "lstrip": false,
713
+ "normalized": false,
714
+ "rstrip": false,
715
+ "single_word": false,
716
+ "special": true
717
+ },
718
+ "128089": {
719
+ "content": "<|reserved_special_token_81|>",
720
+ "lstrip": false,
721
+ "normalized": false,
722
+ "rstrip": false,
723
+ "single_word": false,
724
+ "special": true
725
+ },
726
+ "128090": {
727
+ "content": "<|reserved_special_token_82|>",
728
+ "lstrip": false,
729
+ "normalized": false,
730
+ "rstrip": false,
731
+ "single_word": false,
732
+ "special": true
733
+ },
734
+ "128091": {
735
+ "content": "<|reserved_special_token_83|>",
736
+ "lstrip": false,
737
+ "normalized": false,
738
+ "rstrip": false,
739
+ "single_word": false,
740
+ "special": true
741
+ },
742
+ "128092": {
743
+ "content": "<|reserved_special_token_84|>",
744
+ "lstrip": false,
745
+ "normalized": false,
746
+ "rstrip": false,
747
+ "single_word": false,
748
+ "special": true
749
+ },
750
+ "128093": {
751
+ "content": "<|reserved_special_token_85|>",
752
+ "lstrip": false,
753
+ "normalized": false,
754
+ "rstrip": false,
755
+ "single_word": false,
756
+ "special": true
757
+ },
758
+ "128094": {
759
+ "content": "<|reserved_special_token_86|>",
760
+ "lstrip": false,
761
+ "normalized": false,
762
+ "rstrip": false,
763
+ "single_word": false,
764
+ "special": true
765
+ },
766
+ "128095": {
767
+ "content": "<|reserved_special_token_87|>",
768
+ "lstrip": false,
769
+ "normalized": false,
770
+ "rstrip": false,
771
+ "single_word": false,
772
+ "special": true
773
+ },
774
+ "128096": {
775
+ "content": "<|reserved_special_token_88|>",
776
+ "lstrip": false,
777
+ "normalized": false,
778
+ "rstrip": false,
779
+ "single_word": false,
780
+ "special": true
781
+ },
782
+ "128097": {
783
+ "content": "<|reserved_special_token_89|>",
784
+ "lstrip": false,
785
+ "normalized": false,
786
+ "rstrip": false,
787
+ "single_word": false,
788
+ "special": true
789
+ },
790
+ "128098": {
791
+ "content": "<|reserved_special_token_90|>",
792
+ "lstrip": false,
793
+ "normalized": false,
794
+ "rstrip": false,
795
+ "single_word": false,
796
+ "special": true
797
+ },
798
+ "128099": {
799
+ "content": "<|reserved_special_token_91|>",
800
+ "lstrip": false,
801
+ "normalized": false,
802
+ "rstrip": false,
803
+ "single_word": false,
804
+ "special": true
805
+ },
806
+ "128100": {
807
+ "content": "<|reserved_special_token_92|>",
808
+ "lstrip": false,
809
+ "normalized": false,
810
+ "rstrip": false,
811
+ "single_word": false,
812
+ "special": true
813
+ },
814
+ "128101": {
815
+ "content": "<|reserved_special_token_93|>",
816
+ "lstrip": false,
817
+ "normalized": false,
818
+ "rstrip": false,
819
+ "single_word": false,
820
+ "special": true
821
+ },
822
+ "128102": {
823
+ "content": "<|reserved_special_token_94|>",
824
+ "lstrip": false,
825
+ "normalized": false,
826
+ "rstrip": false,
827
+ "single_word": false,
828
+ "special": true
829
+ },
830
+ "128103": {
831
+ "content": "<|reserved_special_token_95|>",
832
+ "lstrip": false,
833
+ "normalized": false,
834
+ "rstrip": false,
835
+ "single_word": false,
836
+ "special": true
837
+ },
838
+ "128104": {
839
+ "content": "<|reserved_special_token_96|>",
840
+ "lstrip": false,
841
+ "normalized": false,
842
+ "rstrip": false,
843
+ "single_word": false,
844
+ "special": true
845
+ },
846
+ "128105": {
847
+ "content": "<|reserved_special_token_97|>",
848
+ "lstrip": false,
849
+ "normalized": false,
850
+ "rstrip": false,
851
+ "single_word": false,
852
+ "special": true
853
+ },
854
+ "128106": {
855
+ "content": "<|reserved_special_token_98|>",
856
+ "lstrip": false,
857
+ "normalized": false,
858
+ "rstrip": false,
859
+ "single_word": false,
860
+ "special": true
861
+ },
862
+ "128107": {
863
+ "content": "<|reserved_special_token_99|>",
864
+ "lstrip": false,
865
+ "normalized": false,
866
+ "rstrip": false,
867
+ "single_word": false,
868
+ "special": true
869
+ },
870
+ "128108": {
871
+ "content": "<|reserved_special_token_100|>",
872
+ "lstrip": false,
873
+ "normalized": false,
874
+ "rstrip": false,
875
+ "single_word": false,
876
+ "special": true
877
+ },
878
+ "128109": {
879
+ "content": "<|reserved_special_token_101|>",
880
+ "lstrip": false,
881
+ "normalized": false,
882
+ "rstrip": false,
883
+ "single_word": false,
884
+ "special": true
885
+ },
886
+ "128110": {
887
+ "content": "<|reserved_special_token_102|>",
888
+ "lstrip": false,
889
+ "normalized": false,
890
+ "rstrip": false,
891
+ "single_word": false,
892
+ "special": true
893
+ },
894
+ "128111": {
895
+ "content": "<|reserved_special_token_103|>",
896
+ "lstrip": false,
897
+ "normalized": false,
898
+ "rstrip": false,
899
+ "single_word": false,
900
+ "special": true
901
+ },
902
+ "128112": {
903
+ "content": "<|reserved_special_token_104|>",
904
+ "lstrip": false,
905
+ "normalized": false,
906
+ "rstrip": false,
907
+ "single_word": false,
908
+ "special": true
909
+ },
910
+ "128113": {
911
+ "content": "<|reserved_special_token_105|>",
912
+ "lstrip": false,
913
+ "normalized": false,
914
+ "rstrip": false,
915
+ "single_word": false,
916
+ "special": true
917
+ },
918
+ "128114": {
919
+ "content": "<|reserved_special_token_106|>",
920
+ "lstrip": false,
921
+ "normalized": false,
922
+ "rstrip": false,
923
+ "single_word": false,
924
+ "special": true
925
+ },
926
+ "128115": {
927
+ "content": "<|reserved_special_token_107|>",
928
+ "lstrip": false,
929
+ "normalized": false,
930
+ "rstrip": false,
931
+ "single_word": false,
932
+ "special": true
933
+ },
934
+ "128116": {
935
+ "content": "<|reserved_special_token_108|>",
936
+ "lstrip": false,
937
+ "normalized": false,
938
+ "rstrip": false,
939
+ "single_word": false,
940
+ "special": true
941
+ },
942
+ "128117": {
943
+ "content": "<|reserved_special_token_109|>",
944
+ "lstrip": false,
945
+ "normalized": false,
946
+ "rstrip": false,
947
+ "single_word": false,
948
+ "special": true
949
+ },
950
+ "128118": {
951
+ "content": "<|reserved_special_token_110|>",
952
+ "lstrip": false,
953
+ "normalized": false,
954
+ "rstrip": false,
955
+ "single_word": false,
956
+ "special": true
957
+ },
958
+ "128119": {
959
+ "content": "<|reserved_special_token_111|>",
960
+ "lstrip": false,
961
+ "normalized": false,
962
+ "rstrip": false,
963
+ "single_word": false,
964
+ "special": true
965
+ },
966
+ "128120": {
967
+ "content": "<|reserved_special_token_112|>",
968
+ "lstrip": false,
969
+ "normalized": false,
970
+ "rstrip": false,
971
+ "single_word": false,
972
+ "special": true
973
+ },
974
+ "128121": {
975
+ "content": "<|reserved_special_token_113|>",
976
+ "lstrip": false,
977
+ "normalized": false,
978
+ "rstrip": false,
979
+ "single_word": false,
980
+ "special": true
981
+ },
982
+ "128122": {
983
+ "content": "<|reserved_special_token_114|>",
984
+ "lstrip": false,
985
+ "normalized": false,
986
+ "rstrip": false,
987
+ "single_word": false,
988
+ "special": true
989
+ },
990
+ "128123": {
991
+ "content": "<|reserved_special_token_115|>",
992
+ "lstrip": false,
993
+ "normalized": false,
994
+ "rstrip": false,
995
+ "single_word": false,
996
+ "special": true
997
+ },
998
+ "128124": {
999
+ "content": "<|reserved_special_token_116|>",
1000
+ "lstrip": false,
1001
+ "normalized": false,
1002
+ "rstrip": false,
1003
+ "single_word": false,
1004
+ "special": true
1005
+ },
1006
+ "128125": {
1007
+ "content": "<|reserved_special_token_117|>",
1008
+ "lstrip": false,
1009
+ "normalized": false,
1010
+ "rstrip": false,
1011
+ "single_word": false,
1012
+ "special": true
1013
+ },
1014
+ "128126": {
1015
+ "content": "<|reserved_special_token_118|>",
1016
+ "lstrip": false,
1017
+ "normalized": false,
1018
+ "rstrip": false,
1019
+ "single_word": false,
1020
+ "special": true
1021
+ },
1022
+ "128127": {
1023
+ "content": "<|reserved_special_token_119|>",
1024
+ "lstrip": false,
1025
+ "normalized": false,
1026
+ "rstrip": false,
1027
+ "single_word": false,
1028
+ "special": true
1029
+ },
1030
+ "128128": {
1031
+ "content": "<|reserved_special_token_120|>",
1032
+ "lstrip": false,
1033
+ "normalized": false,
1034
+ "rstrip": false,
1035
+ "single_word": false,
1036
+ "special": true
1037
+ },
1038
+ "128129": {
1039
+ "content": "<|reserved_special_token_121|>",
1040
+ "lstrip": false,
1041
+ "normalized": false,
1042
+ "rstrip": false,
1043
+ "single_word": false,
1044
+ "special": true
1045
+ },
1046
+ "128130": {
1047
+ "content": "<|reserved_special_token_122|>",
1048
+ "lstrip": false,
1049
+ "normalized": false,
1050
+ "rstrip": false,
1051
+ "single_word": false,
1052
+ "special": true
1053
+ },
1054
+ "128131": {
1055
+ "content": "<|reserved_special_token_123|>",
1056
+ "lstrip": false,
1057
+ "normalized": false,
1058
+ "rstrip": false,
1059
+ "single_word": false,
1060
+ "special": true
1061
+ },
1062
+ "128132": {
1063
+ "content": "<|reserved_special_token_124|>",
1064
+ "lstrip": false,
1065
+ "normalized": false,
1066
+ "rstrip": false,
1067
+ "single_word": false,
1068
+ "special": true
1069
+ },
1070
+ "128133": {
1071
+ "content": "<|reserved_special_token_125|>",
1072
+ "lstrip": false,
1073
+ "normalized": false,
1074
+ "rstrip": false,
1075
+ "single_word": false,
1076
+ "special": true
1077
+ },
1078
+ "128134": {
1079
+ "content": "<|reserved_special_token_126|>",
1080
+ "lstrip": false,
1081
+ "normalized": false,
1082
+ "rstrip": false,
1083
+ "single_word": false,
1084
+ "special": true
1085
+ },
1086
+ "128135": {
1087
+ "content": "<|reserved_special_token_127|>",
1088
+ "lstrip": false,
1089
+ "normalized": false,
1090
+ "rstrip": false,
1091
+ "single_word": false,
1092
+ "special": true
1093
+ },
1094
+ "128136": {
1095
+ "content": "<|reserved_special_token_128|>",
1096
+ "lstrip": false,
1097
+ "normalized": false,
1098
+ "rstrip": false,
1099
+ "single_word": false,
1100
+ "special": true
1101
+ },
1102
+ "128137": {
1103
+ "content": "<|reserved_special_token_129|>",
1104
+ "lstrip": false,
1105
+ "normalized": false,
1106
+ "rstrip": false,
1107
+ "single_word": false,
1108
+ "special": true
1109
+ },
1110
+ "128138": {
1111
+ "content": "<|reserved_special_token_130|>",
1112
+ "lstrip": false,
1113
+ "normalized": false,
1114
+ "rstrip": false,
1115
+ "single_word": false,
1116
+ "special": true
1117
+ },
1118
+ "128139": {
1119
+ "content": "<|reserved_special_token_131|>",
1120
+ "lstrip": false,
1121
+ "normalized": false,
1122
+ "rstrip": false,
1123
+ "single_word": false,
1124
+ "special": true
1125
+ },
1126
+ "128140": {
1127
+ "content": "<|reserved_special_token_132|>",
1128
+ "lstrip": false,
1129
+ "normalized": false,
1130
+ "rstrip": false,
1131
+ "single_word": false,
1132
+ "special": true
1133
+ },
1134
+ "128141": {
1135
+ "content": "<|reserved_special_token_133|>",
1136
+ "lstrip": false,
1137
+ "normalized": false,
1138
+ "rstrip": false,
1139
+ "single_word": false,
1140
+ "special": true
1141
+ },
1142
+ "128142": {
1143
+ "content": "<|reserved_special_token_134|>",
1144
+ "lstrip": false,
1145
+ "normalized": false,
1146
+ "rstrip": false,
1147
+ "single_word": false,
1148
+ "special": true
1149
+ },
1150
+ "128143": {
1151
+ "content": "<|reserved_special_token_135|>",
1152
+ "lstrip": false,
1153
+ "normalized": false,
1154
+ "rstrip": false,
1155
+ "single_word": false,
1156
+ "special": true
1157
+ },
1158
+ "128144": {
1159
+ "content": "<|reserved_special_token_136|>",
1160
+ "lstrip": false,
1161
+ "normalized": false,
1162
+ "rstrip": false,
1163
+ "single_word": false,
1164
+ "special": true
1165
+ },
1166
+ "128145": {
1167
+ "content": "<|reserved_special_token_137|>",
1168
+ "lstrip": false,
1169
+ "normalized": false,
1170
+ "rstrip": false,
1171
+ "single_word": false,
1172
+ "special": true
1173
+ },
1174
+ "128146": {
1175
+ "content": "<|reserved_special_token_138|>",
1176
+ "lstrip": false,
1177
+ "normalized": false,
1178
+ "rstrip": false,
1179
+ "single_word": false,
1180
+ "special": true
1181
+ },
1182
+ "128147": {
1183
+ "content": "<|reserved_special_token_139|>",
1184
+ "lstrip": false,
1185
+ "normalized": false,
1186
+ "rstrip": false,
1187
+ "single_word": false,
1188
+ "special": true
1189
+ },
1190
+ "128148": {
1191
+ "content": "<|reserved_special_token_140|>",
1192
+ "lstrip": false,
1193
+ "normalized": false,
1194
+ "rstrip": false,
1195
+ "single_word": false,
1196
+ "special": true
1197
+ },
1198
+ "128149": {
1199
+ "content": "<|reserved_special_token_141|>",
1200
+ "lstrip": false,
1201
+ "normalized": false,
1202
+ "rstrip": false,
1203
+ "single_word": false,
1204
+ "special": true
1205
+ },
1206
+ "128150": {
1207
+ "content": "<|reserved_special_token_142|>",
1208
+ "lstrip": false,
1209
+ "normalized": false,
1210
+ "rstrip": false,
1211
+ "single_word": false,
1212
+ "special": true
1213
+ },
1214
+ "128151": {
1215
+ "content": "<|reserved_special_token_143|>",
1216
+ "lstrip": false,
1217
+ "normalized": false,
1218
+ "rstrip": false,
1219
+ "single_word": false,
1220
+ "special": true
1221
+ },
1222
+ "128152": {
1223
+ "content": "<|reserved_special_token_144|>",
1224
+ "lstrip": false,
1225
+ "normalized": false,
1226
+ "rstrip": false,
1227
+ "single_word": false,
1228
+ "special": true
1229
+ },
1230
+ "128153": {
1231
+ "content": "<|reserved_special_token_145|>",
1232
+ "lstrip": false,
1233
+ "normalized": false,
1234
+ "rstrip": false,
1235
+ "single_word": false,
1236
+ "special": true
1237
+ },
1238
+ "128154": {
1239
+ "content": "<|reserved_special_token_146|>",
1240
+ "lstrip": false,
1241
+ "normalized": false,
1242
+ "rstrip": false,
1243
+ "single_word": false,
1244
+ "special": true
1245
+ },
1246
+ "128155": {
1247
+ "content": "<|reserved_special_token_147|>",
1248
+ "lstrip": false,
1249
+ "normalized": false,
1250
+ "rstrip": false,
1251
+ "single_word": false,
1252
+ "special": true
1253
+ },
1254
+ "128156": {
1255
+ "content": "<|reserved_special_token_148|>",
1256
+ "lstrip": false,
1257
+ "normalized": false,
1258
+ "rstrip": false,
1259
+ "single_word": false,
1260
+ "special": true
1261
+ },
1262
+ "128157": {
1263
+ "content": "<|reserved_special_token_149|>",
1264
+ "lstrip": false,
1265
+ "normalized": false,
1266
+ "rstrip": false,
1267
+ "single_word": false,
1268
+ "special": true
1269
+ },
1270
+ "128158": {
1271
+ "content": "<|reserved_special_token_150|>",
1272
+ "lstrip": false,
1273
+ "normalized": false,
1274
+ "rstrip": false,
1275
+ "single_word": false,
1276
+ "special": true
1277
+ },
1278
+ "128159": {
1279
+ "content": "<|reserved_special_token_151|>",
1280
+ "lstrip": false,
1281
+ "normalized": false,
1282
+ "rstrip": false,
1283
+ "single_word": false,
1284
+ "special": true
1285
+ },
1286
+ "128160": {
1287
+ "content": "<|reserved_special_token_152|>",
1288
+ "lstrip": false,
1289
+ "normalized": false,
1290
+ "rstrip": false,
1291
+ "single_word": false,
1292
+ "special": true
1293
+ },
1294
+ "128161": {
1295
+ "content": "<|reserved_special_token_153|>",
1296
+ "lstrip": false,
1297
+ "normalized": false,
1298
+ "rstrip": false,
1299
+ "single_word": false,
1300
+ "special": true
1301
+ },
1302
+ "128162": {
1303
+ "content": "<|reserved_special_token_154|>",
1304
+ "lstrip": false,
1305
+ "normalized": false,
1306
+ "rstrip": false,
1307
+ "single_word": false,
1308
+ "special": true
1309
+ },
1310
+ "128163": {
1311
+ "content": "<|reserved_special_token_155|>",
1312
+ "lstrip": false,
1313
+ "normalized": false,
1314
+ "rstrip": false,
1315
+ "single_word": false,
1316
+ "special": true
1317
+ },
1318
+ "128164": {
1319
+ "content": "<|reserved_special_token_156|>",
1320
+ "lstrip": false,
1321
+ "normalized": false,
1322
+ "rstrip": false,
1323
+ "single_word": false,
1324
+ "special": true
1325
+ },
1326
+ "128165": {
1327
+ "content": "<|reserved_special_token_157|>",
1328
+ "lstrip": false,
1329
+ "normalized": false,
1330
+ "rstrip": false,
1331
+ "single_word": false,
1332
+ "special": true
1333
+ },
1334
+ "128166": {
1335
+ "content": "<|reserved_special_token_158|>",
1336
+ "lstrip": false,
1337
+ "normalized": false,
1338
+ "rstrip": false,
1339
+ "single_word": false,
1340
+ "special": true
1341
+ },
1342
+ "128167": {
1343
+ "content": "<|reserved_special_token_159|>",
1344
+ "lstrip": false,
1345
+ "normalized": false,
1346
+ "rstrip": false,
1347
+ "single_word": false,
1348
+ "special": true
1349
+ },
1350
+ "128168": {
1351
+ "content": "<|reserved_special_token_160|>",
1352
+ "lstrip": false,
1353
+ "normalized": false,
1354
+ "rstrip": false,
1355
+ "single_word": false,
1356
+ "special": true
1357
+ },
1358
+ "128169": {
1359
+ "content": "<|reserved_special_token_161|>",
1360
+ "lstrip": false,
1361
+ "normalized": false,
1362
+ "rstrip": false,
1363
+ "single_word": false,
1364
+ "special": true
1365
+ },
1366
+ "128170": {
1367
+ "content": "<|reserved_special_token_162|>",
1368
+ "lstrip": false,
1369
+ "normalized": false,
1370
+ "rstrip": false,
1371
+ "single_word": false,
1372
+ "special": true
1373
+ },
1374
+ "128171": {
1375
+ "content": "<|reserved_special_token_163|>",
1376
+ "lstrip": false,
1377
+ "normalized": false,
1378
+ "rstrip": false,
1379
+ "single_word": false,
1380
+ "special": true
1381
+ },
1382
+ "128172": {
1383
+ "content": "<|reserved_special_token_164|>",
1384
+ "lstrip": false,
1385
+ "normalized": false,
1386
+ "rstrip": false,
1387
+ "single_word": false,
1388
+ "special": true
1389
+ },
1390
+ "128173": {
1391
+ "content": "<|reserved_special_token_165|>",
1392
+ "lstrip": false,
1393
+ "normalized": false,
1394
+ "rstrip": false,
1395
+ "single_word": false,
1396
+ "special": true
1397
+ },
1398
+ "128174": {
1399
+ "content": "<|reserved_special_token_166|>",
1400
+ "lstrip": false,
1401
+ "normalized": false,
1402
+ "rstrip": false,
1403
+ "single_word": false,
1404
+ "special": true
1405
+ },
1406
+ "128175": {
1407
+ "content": "<|reserved_special_token_167|>",
1408
+ "lstrip": false,
1409
+ "normalized": false,
1410
+ "rstrip": false,
1411
+ "single_word": false,
1412
+ "special": true
1413
+ },
1414
+ "128176": {
1415
+ "content": "<|reserved_special_token_168|>",
1416
+ "lstrip": false,
1417
+ "normalized": false,
1418
+ "rstrip": false,
1419
+ "single_word": false,
1420
+ "special": true
1421
+ },
1422
+ "128177": {
1423
+ "content": "<|reserved_special_token_169|>",
1424
+ "lstrip": false,
1425
+ "normalized": false,
1426
+ "rstrip": false,
1427
+ "single_word": false,
1428
+ "special": true
1429
+ },
1430
+ "128178": {
1431
+ "content": "<|reserved_special_token_170|>",
1432
+ "lstrip": false,
1433
+ "normalized": false,
1434
+ "rstrip": false,
1435
+ "single_word": false,
1436
+ "special": true
1437
+ },
1438
+ "128179": {
1439
+ "content": "<|reserved_special_token_171|>",
1440
+ "lstrip": false,
1441
+ "normalized": false,
1442
+ "rstrip": false,
1443
+ "single_word": false,
1444
+ "special": true
1445
+ },
1446
+ "128180": {
1447
+ "content": "<|reserved_special_token_172|>",
1448
+ "lstrip": false,
1449
+ "normalized": false,
1450
+ "rstrip": false,
1451
+ "single_word": false,
1452
+ "special": true
1453
+ },
1454
+ "128181": {
1455
+ "content": "<|reserved_special_token_173|>",
1456
+ "lstrip": false,
1457
+ "normalized": false,
1458
+ "rstrip": false,
1459
+ "single_word": false,
1460
+ "special": true
1461
+ },
1462
+ "128182": {
1463
+ "content": "<|reserved_special_token_174|>",
1464
+ "lstrip": false,
1465
+ "normalized": false,
1466
+ "rstrip": false,
1467
+ "single_word": false,
1468
+ "special": true
1469
+ },
1470
+ "128183": {
1471
+ "content": "<|reserved_special_token_175|>",
1472
+ "lstrip": false,
1473
+ "normalized": false,
1474
+ "rstrip": false,
1475
+ "single_word": false,
1476
+ "special": true
1477
+ },
1478
+ "128184": {
1479
+ "content": "<|reserved_special_token_176|>",
1480
+ "lstrip": false,
1481
+ "normalized": false,
1482
+ "rstrip": false,
1483
+ "single_word": false,
1484
+ "special": true
1485
+ },
1486
+ "128185": {
1487
+ "content": "<|reserved_special_token_177|>",
1488
+ "lstrip": false,
1489
+ "normalized": false,
1490
+ "rstrip": false,
1491
+ "single_word": false,
1492
+ "special": true
1493
+ },
1494
+ "128186": {
1495
+ "content": "<|reserved_special_token_178|>",
1496
+ "lstrip": false,
1497
+ "normalized": false,
1498
+ "rstrip": false,
1499
+ "single_word": false,
1500
+ "special": true
1501
+ },
1502
+ "128187": {
1503
+ "content": "<|reserved_special_token_179|>",
1504
+ "lstrip": false,
1505
+ "normalized": false,
1506
+ "rstrip": false,
1507
+ "single_word": false,
1508
+ "special": true
1509
+ },
1510
+ "128188": {
1511
+ "content": "<|reserved_special_token_180|>",
1512
+ "lstrip": false,
1513
+ "normalized": false,
1514
+ "rstrip": false,
1515
+ "single_word": false,
1516
+ "special": true
1517
+ },
1518
+ "128189": {
1519
+ "content": "<|reserved_special_token_181|>",
1520
+ "lstrip": false,
1521
+ "normalized": false,
1522
+ "rstrip": false,
1523
+ "single_word": false,
1524
+ "special": true
1525
+ },
1526
+ "128190": {
1527
+ "content": "<|reserved_special_token_182|>",
1528
+ "lstrip": false,
1529
+ "normalized": false,
1530
+ "rstrip": false,
1531
+ "single_word": false,
1532
+ "special": true
1533
+ },
1534
+ "128191": {
1535
+ "content": "<|reserved_special_token_183|>",
1536
+ "lstrip": false,
1537
+ "normalized": false,
1538
+ "rstrip": false,
1539
+ "single_word": false,
1540
+ "special": true
1541
+ },
1542
+ "128192": {
1543
+ "content": "<|reserved_special_token_184|>",
1544
+ "lstrip": false,
1545
+ "normalized": false,
1546
+ "rstrip": false,
1547
+ "single_word": false,
1548
+ "special": true
1549
+ },
1550
+ "128193": {
1551
+ "content": "<|reserved_special_token_185|>",
1552
+ "lstrip": false,
1553
+ "normalized": false,
1554
+ "rstrip": false,
1555
+ "single_word": false,
1556
+ "special": true
1557
+ },
1558
+ "128194": {
1559
+ "content": "<|reserved_special_token_186|>",
1560
+ "lstrip": false,
1561
+ "normalized": false,
1562
+ "rstrip": false,
1563
+ "single_word": false,
1564
+ "special": true
1565
+ },
1566
+ "128195": {
1567
+ "content": "<|reserved_special_token_187|>",
1568
+ "lstrip": false,
1569
+ "normalized": false,
1570
+ "rstrip": false,
1571
+ "single_word": false,
1572
+ "special": true
1573
+ },
1574
+ "128196": {
1575
+ "content": "<|reserved_special_token_188|>",
1576
+ "lstrip": false,
1577
+ "normalized": false,
1578
+ "rstrip": false,
1579
+ "single_word": false,
1580
+ "special": true
1581
+ },
1582
+ "128197": {
1583
+ "content": "<|reserved_special_token_189|>",
1584
+ "lstrip": false,
1585
+ "normalized": false,
1586
+ "rstrip": false,
1587
+ "single_word": false,
1588
+ "special": true
1589
+ },
1590
+ "128198": {
1591
+ "content": "<|reserved_special_token_190|>",
1592
+ "lstrip": false,
1593
+ "normalized": false,
1594
+ "rstrip": false,
1595
+ "single_word": false,
1596
+ "special": true
1597
+ },
1598
+ "128199": {
1599
+ "content": "<|reserved_special_token_191|>",
1600
+ "lstrip": false,
1601
+ "normalized": false,
1602
+ "rstrip": false,
1603
+ "single_word": false,
1604
+ "special": true
1605
+ },
1606
+ "128200": {
1607
+ "content": "<|reserved_special_token_192|>",
1608
+ "lstrip": false,
1609
+ "normalized": false,
1610
+ "rstrip": false,
1611
+ "single_word": false,
1612
+ "special": true
1613
+ },
1614
+ "128201": {
1615
+ "content": "<|reserved_special_token_193|>",
1616
+ "lstrip": false,
1617
+ "normalized": false,
1618
+ "rstrip": false,
1619
+ "single_word": false,
1620
+ "special": true
1621
+ },
1622
+ "128202": {
1623
+ "content": "<|reserved_special_token_194|>",
1624
+ "lstrip": false,
1625
+ "normalized": false,
1626
+ "rstrip": false,
1627
+ "single_word": false,
1628
+ "special": true
1629
+ },
1630
+ "128203": {
1631
+ "content": "<|reserved_special_token_195|>",
1632
+ "lstrip": false,
1633
+ "normalized": false,
1634
+ "rstrip": false,
1635
+ "single_word": false,
1636
+ "special": true
1637
+ },
1638
+ "128204": {
1639
+ "content": "<|reserved_special_token_196|>",
1640
+ "lstrip": false,
1641
+ "normalized": false,
1642
+ "rstrip": false,
1643
+ "single_word": false,
1644
+ "special": true
1645
+ },
1646
+ "128205": {
1647
+ "content": "<|reserved_special_token_197|>",
1648
+ "lstrip": false,
1649
+ "normalized": false,
1650
+ "rstrip": false,
1651
+ "single_word": false,
1652
+ "special": true
1653
+ },
1654
+ "128206": {
1655
+ "content": "<|reserved_special_token_198|>",
1656
+ "lstrip": false,
1657
+ "normalized": false,
1658
+ "rstrip": false,
1659
+ "single_word": false,
1660
+ "special": true
1661
+ },
1662
+ "128207": {
1663
+ "content": "<|reserved_special_token_199|>",
1664
+ "lstrip": false,
1665
+ "normalized": false,
1666
+ "rstrip": false,
1667
+ "single_word": false,
1668
+ "special": true
1669
+ },
1670
+ "128208": {
1671
+ "content": "<|reserved_special_token_200|>",
1672
+ "lstrip": false,
1673
+ "normalized": false,
1674
+ "rstrip": false,
1675
+ "single_word": false,
1676
+ "special": true
1677
+ },
1678
+ "128209": {
1679
+ "content": "<|reserved_special_token_201|>",
1680
+ "lstrip": false,
1681
+ "normalized": false,
1682
+ "rstrip": false,
1683
+ "single_word": false,
1684
+ "special": true
1685
+ },
1686
+ "128210": {
1687
+ "content": "<|reserved_special_token_202|>",
1688
+ "lstrip": false,
1689
+ "normalized": false,
1690
+ "rstrip": false,
1691
+ "single_word": false,
1692
+ "special": true
1693
+ },
1694
+ "128211": {
1695
+ "content": "<|reserved_special_token_203|>",
1696
+ "lstrip": false,
1697
+ "normalized": false,
1698
+ "rstrip": false,
1699
+ "single_word": false,
1700
+ "special": true
1701
+ },
1702
+ "128212": {
1703
+ "content": "<|reserved_special_token_204|>",
1704
+ "lstrip": false,
1705
+ "normalized": false,
1706
+ "rstrip": false,
1707
+ "single_word": false,
1708
+ "special": true
1709
+ },
1710
+ "128213": {
1711
+ "content": "<|reserved_special_token_205|>",
1712
+ "lstrip": false,
1713
+ "normalized": false,
1714
+ "rstrip": false,
1715
+ "single_word": false,
1716
+ "special": true
1717
+ },
1718
+ "128214": {
1719
+ "content": "<|reserved_special_token_206|>",
1720
+ "lstrip": false,
1721
+ "normalized": false,
1722
+ "rstrip": false,
1723
+ "single_word": false,
1724
+ "special": true
1725
+ },
1726
+ "128215": {
1727
+ "content": "<|reserved_special_token_207|>",
1728
+ "lstrip": false,
1729
+ "normalized": false,
1730
+ "rstrip": false,
1731
+ "single_word": false,
1732
+ "special": true
1733
+ },
1734
+ "128216": {
1735
+ "content": "<|reserved_special_token_208|>",
1736
+ "lstrip": false,
1737
+ "normalized": false,
1738
+ "rstrip": false,
1739
+ "single_word": false,
1740
+ "special": true
1741
+ },
1742
+ "128217": {
1743
+ "content": "<|reserved_special_token_209|>",
1744
+ "lstrip": false,
1745
+ "normalized": false,
1746
+ "rstrip": false,
1747
+ "single_word": false,
1748
+ "special": true
1749
+ },
1750
+ "128218": {
1751
+ "content": "<|reserved_special_token_210|>",
1752
+ "lstrip": false,
1753
+ "normalized": false,
1754
+ "rstrip": false,
1755
+ "single_word": false,
1756
+ "special": true
1757
+ },
1758
+ "128219": {
1759
+ "content": "<|reserved_special_token_211|>",
1760
+ "lstrip": false,
1761
+ "normalized": false,
1762
+ "rstrip": false,
1763
+ "single_word": false,
1764
+ "special": true
1765
+ },
1766
+ "128220": {
1767
+ "content": "<|reserved_special_token_212|>",
1768
+ "lstrip": false,
1769
+ "normalized": false,
1770
+ "rstrip": false,
1771
+ "single_word": false,
1772
+ "special": true
1773
+ },
1774
+ "128221": {
1775
+ "content": "<|reserved_special_token_213|>",
1776
+ "lstrip": false,
1777
+ "normalized": false,
1778
+ "rstrip": false,
1779
+ "single_word": false,
1780
+ "special": true
1781
+ },
1782
+ "128222": {
1783
+ "content": "<|reserved_special_token_214|>",
1784
+ "lstrip": false,
1785
+ "normalized": false,
1786
+ "rstrip": false,
1787
+ "single_word": false,
1788
+ "special": true
1789
+ },
1790
+ "128223": {
1791
+ "content": "<|reserved_special_token_215|>",
1792
+ "lstrip": false,
1793
+ "normalized": false,
1794
+ "rstrip": false,
1795
+ "single_word": false,
1796
+ "special": true
1797
+ },
1798
+ "128224": {
1799
+ "content": "<|reserved_special_token_216|>",
1800
+ "lstrip": false,
1801
+ "normalized": false,
1802
+ "rstrip": false,
1803
+ "single_word": false,
1804
+ "special": true
1805
+ },
1806
+ "128225": {
1807
+ "content": "<|reserved_special_token_217|>",
1808
+ "lstrip": false,
1809
+ "normalized": false,
1810
+ "rstrip": false,
1811
+ "single_word": false,
1812
+ "special": true
1813
+ },
1814
+ "128226": {
1815
+ "content": "<|reserved_special_token_218|>",
1816
+ "lstrip": false,
1817
+ "normalized": false,
1818
+ "rstrip": false,
1819
+ "single_word": false,
1820
+ "special": true
1821
+ },
1822
+ "128227": {
1823
+ "content": "<|reserved_special_token_219|>",
1824
+ "lstrip": false,
1825
+ "normalized": false,
1826
+ "rstrip": false,
1827
+ "single_word": false,
1828
+ "special": true
1829
+ },
1830
+ "128228": {
1831
+ "content": "<|reserved_special_token_220|>",
1832
+ "lstrip": false,
1833
+ "normalized": false,
1834
+ "rstrip": false,
1835
+ "single_word": false,
1836
+ "special": true
1837
+ },
1838
+ "128229": {
1839
+ "content": "<|reserved_special_token_221|>",
1840
+ "lstrip": false,
1841
+ "normalized": false,
1842
+ "rstrip": false,
1843
+ "single_word": false,
1844
+ "special": true
1845
+ },
1846
+ "128230": {
1847
+ "content": "<|reserved_special_token_222|>",
1848
+ "lstrip": false,
1849
+ "normalized": false,
1850
+ "rstrip": false,
1851
+ "single_word": false,
1852
+ "special": true
1853
+ },
1854
+ "128231": {
1855
+ "content": "<|reserved_special_token_223|>",
1856
+ "lstrip": false,
1857
+ "normalized": false,
1858
+ "rstrip": false,
1859
+ "single_word": false,
1860
+ "special": true
1861
+ },
1862
+ "128232": {
1863
+ "content": "<|reserved_special_token_224|>",
1864
+ "lstrip": false,
1865
+ "normalized": false,
1866
+ "rstrip": false,
1867
+ "single_word": false,
1868
+ "special": true
1869
+ },
1870
+ "128233": {
1871
+ "content": "<|reserved_special_token_225|>",
1872
+ "lstrip": false,
1873
+ "normalized": false,
1874
+ "rstrip": false,
1875
+ "single_word": false,
1876
+ "special": true
1877
+ },
1878
+ "128234": {
1879
+ "content": "<|reserved_special_token_226|>",
1880
+ "lstrip": false,
1881
+ "normalized": false,
1882
+ "rstrip": false,
1883
+ "single_word": false,
1884
+ "special": true
1885
+ },
1886
+ "128235": {
1887
+ "content": "<|reserved_special_token_227|>",
1888
+ "lstrip": false,
1889
+ "normalized": false,
1890
+ "rstrip": false,
1891
+ "single_word": false,
1892
+ "special": true
1893
+ },
1894
+ "128236": {
1895
+ "content": "<|reserved_special_token_228|>",
1896
+ "lstrip": false,
1897
+ "normalized": false,
1898
+ "rstrip": false,
1899
+ "single_word": false,
1900
+ "special": true
1901
+ },
1902
+ "128237": {
1903
+ "content": "<|reserved_special_token_229|>",
1904
+ "lstrip": false,
1905
+ "normalized": false,
1906
+ "rstrip": false,
1907
+ "single_word": false,
1908
+ "special": true
1909
+ },
1910
+ "128238": {
1911
+ "content": "<|reserved_special_token_230|>",
1912
+ "lstrip": false,
1913
+ "normalized": false,
1914
+ "rstrip": false,
1915
+ "single_word": false,
1916
+ "special": true
1917
+ },
1918
+ "128239": {
1919
+ "content": "<|reserved_special_token_231|>",
1920
+ "lstrip": false,
1921
+ "normalized": false,
1922
+ "rstrip": false,
1923
+ "single_word": false,
1924
+ "special": true
1925
+ },
1926
+ "128240": {
1927
+ "content": "<|reserved_special_token_232|>",
1928
+ "lstrip": false,
1929
+ "normalized": false,
1930
+ "rstrip": false,
1931
+ "single_word": false,
1932
+ "special": true
1933
+ },
1934
+ "128241": {
1935
+ "content": "<|reserved_special_token_233|>",
1936
+ "lstrip": false,
1937
+ "normalized": false,
1938
+ "rstrip": false,
1939
+ "single_word": false,
1940
+ "special": true
1941
+ },
1942
+ "128242": {
1943
+ "content": "<|reserved_special_token_234|>",
1944
+ "lstrip": false,
1945
+ "normalized": false,
1946
+ "rstrip": false,
1947
+ "single_word": false,
1948
+ "special": true
1949
+ },
1950
+ "128243": {
1951
+ "content": "<|reserved_special_token_235|>",
1952
+ "lstrip": false,
1953
+ "normalized": false,
1954
+ "rstrip": false,
1955
+ "single_word": false,
1956
+ "special": true
1957
+ },
1958
+ "128244": {
1959
+ "content": "<|reserved_special_token_236|>",
1960
+ "lstrip": false,
1961
+ "normalized": false,
1962
+ "rstrip": false,
1963
+ "single_word": false,
1964
+ "special": true
1965
+ },
1966
+ "128245": {
1967
+ "content": "<|reserved_special_token_237|>",
1968
+ "lstrip": false,
1969
+ "normalized": false,
1970
+ "rstrip": false,
1971
+ "single_word": false,
1972
+ "special": true
1973
+ },
1974
+ "128246": {
1975
+ "content": "<|reserved_special_token_238|>",
1976
+ "lstrip": false,
1977
+ "normalized": false,
1978
+ "rstrip": false,
1979
+ "single_word": false,
1980
+ "special": true
1981
+ },
1982
+ "128247": {
1983
+ "content": "<|reserved_special_token_239|>",
1984
+ "lstrip": false,
1985
+ "normalized": false,
1986
+ "rstrip": false,
1987
+ "single_word": false,
1988
+ "special": true
1989
+ },
1990
+ "128248": {
1991
+ "content": "<|reserved_special_token_240|>",
1992
+ "lstrip": false,
1993
+ "normalized": false,
1994
+ "rstrip": false,
1995
+ "single_word": false,
1996
+ "special": true
1997
+ },
1998
+ "128249": {
1999
+ "content": "<|reserved_special_token_241|>",
2000
+ "lstrip": false,
2001
+ "normalized": false,
2002
+ "rstrip": false,
2003
+ "single_word": false,
2004
+ "special": true
2005
+ },
2006
+ "128250": {
2007
+ "content": "<|reserved_special_token_242|>",
2008
+ "lstrip": false,
2009
+ "normalized": false,
2010
+ "rstrip": false,
2011
+ "single_word": false,
2012
+ "special": true
2013
+ },
2014
+ "128251": {
2015
+ "content": "<|reserved_special_token_243|>",
2016
+ "lstrip": false,
2017
+ "normalized": false,
2018
+ "rstrip": false,
2019
+ "single_word": false,
2020
+ "special": true
2021
+ },
2022
+ "128252": {
2023
+ "content": "<|reserved_special_token_244|>",
2024
+ "lstrip": false,
2025
+ "normalized": false,
2026
+ "rstrip": false,
2027
+ "single_word": false,
2028
+ "special": true
2029
+ },
2030
+ "128253": {
2031
+ "content": "<|reserved_special_token_245|>",
2032
+ "lstrip": false,
2033
+ "normalized": false,
2034
+ "rstrip": false,
2035
+ "single_word": false,
2036
+ "special": true
2037
+ },
2038
+ "128254": {
2039
+ "content": "<|reserved_special_token_246|>",
2040
+ "lstrip": false,
2041
+ "normalized": false,
2042
+ "rstrip": false,
2043
+ "single_word": false,
2044
+ "special": true
2045
+ },
2046
+ "128255": {
2047
+ "content": "<|reserved_special_token_247|>",
2048
+ "lstrip": false,
2049
+ "normalized": false,
2050
+ "rstrip": false,
2051
+ "single_word": false,
2052
+ "special": true
2053
+ },
2054
+ "128256": {
2055
+ "content": "<fake_token_around_image>",
2056
+ "lstrip": false,
2057
+ "normalized": false,
2058
+ "rstrip": false,
2059
+ "single_word": false,
2060
+ "special": true
2061
+ },
2062
+ "128257": {
2063
+ "content": "<image>",
2064
+ "lstrip": false,
2065
+ "normalized": false,
2066
+ "rstrip": false,
2067
+ "single_word": false,
2068
+ "special": true
2069
+ },
2070
+ "128258": {
2071
+ "content": "<end_of_utterance>",
2072
+ "lstrip": false,
2073
+ "normalized": false,
2074
+ "rstrip": false,
2075
+ "single_word": false,
2076
+ "special": true
2077
+ }
2078
+ },
2079
+ "additional_special_tokens": [
2080
+ "<fake_token_around_image>",
2081
+ "<image>",
2082
+ "<end_of_utterance>"
2083
+ ],
2084
+ "bos_token": "<|begin_of_text|>",
2085
+ "chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}",
2086
+ "clean_up_tokenization_spaces": true,
2087
+ "eos_token": "<|end_of_text|>",
2088
+ "legacy": false,
2089
+ "model_input_names": [
2090
+ "input_ids",
2091
+ "attention_mask"
2092
+ ],
2093
+ "model_max_length": 131072,
2094
+ "pad_token": "<|reserved_special_token_0|>",
2095
+ "processor_class": "Idefics3Processor",
2096
+ "tokenizer_class": "PreTrainedTokenizerFast"
2097
+ }