hf-transformers-bot commited on
Commit
271d330
·
verified ·
1 Parent(s): 5030d7e

Add tiny processor fixture for testing

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
chat_template.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}"
3
+ }
config.json ADDED
@@ -0,0 +1,220 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "ColQwen2ForRetrieval"
4
+ ],
5
+ "embedding_dim": 128,
6
+ "initializer_range": 0.02,
7
+ "is_composition": false,
8
+ "model_type": "colqwen2",
9
+ "torch_dtype": "bfloat16",
10
+ "transformers_version": "4.53.0.dev0",
11
+ "vlm_config": {
12
+ "_name_or_path": "Qwen/Qwen2-VL-2B-Instruct",
13
+ "attention_dropout": 0.0,
14
+ "bos_token_id": 151643,
15
+ "eos_token_id": 151645,
16
+ "hidden_act": "silu",
17
+ "hidden_size": 1536,
18
+ "image_token_id": 151655,
19
+ "initializer_range": 0.02,
20
+ "intermediate_size": 8960,
21
+ "max_position_embeddings": 32768,
22
+ "max_window_layers": 28,
23
+ "model_type": "qwen2_vl",
24
+ "num_attention_heads": 12,
25
+ "num_hidden_layers": 28,
26
+ "num_key_value_heads": 2,
27
+ "rms_norm_eps": 1e-06,
28
+ "rope_scaling": {
29
+ "mrope_section": [
30
+ 16,
31
+ 24,
32
+ 24
33
+ ],
34
+ "rope_type": "default",
35
+ "type": "default"
36
+ },
37
+ "rope_theta": 1000000.0,
38
+ "sliding_window": 32768,
39
+ "text_config": {
40
+ "_name_or_path": "vidore/colqwen2-base",
41
+ "add_cross_attention": false,
42
+ "architectures": [
43
+ "ColQwen2"
44
+ ],
45
+ "attention_dropout": 0.0,
46
+ "bad_words_ids": null,
47
+ "begin_suppress_tokens": null,
48
+ "bos_token_id": 151643,
49
+ "chunk_size_feed_forward": 0,
50
+ "cross_attention_hidden_size": null,
51
+ "decoder_start_token_id": null,
52
+ "diversity_penalty": 0.0,
53
+ "do_sample": false,
54
+ "early_stopping": false,
55
+ "encoder_no_repeat_ngram_size": 0,
56
+ "eos_token_id": 151645,
57
+ "exponential_decay_length_penalty": null,
58
+ "finetuning_task": null,
59
+ "forced_bos_token_id": null,
60
+ "forced_eos_token_id": null,
61
+ "hidden_act": "silu",
62
+ "hidden_size": 1536,
63
+ "id2label": {
64
+ "0": "LABEL_0",
65
+ "1": "LABEL_1"
66
+ },
67
+ "image_token_id": null,
68
+ "initializer_range": 0.02,
69
+ "intermediate_size": 8960,
70
+ "is_decoder": false,
71
+ "is_encoder_decoder": false,
72
+ "label2id": {
73
+ "LABEL_0": 0,
74
+ "LABEL_1": 1
75
+ },
76
+ "length_penalty": 1.0,
77
+ "max_length": 20,
78
+ "max_position_embeddings": 32768,
79
+ "max_window_layers": 28,
80
+ "min_length": 0,
81
+ "model_type": "qwen2_vl_text",
82
+ "no_repeat_ngram_size": 0,
83
+ "num_attention_heads": 12,
84
+ "num_beam_groups": 1,
85
+ "num_beams": 1,
86
+ "num_hidden_layers": 28,
87
+ "num_key_value_heads": 2,
88
+ "num_return_sequences": 1,
89
+ "output_attentions": false,
90
+ "output_hidden_states": false,
91
+ "output_scores": false,
92
+ "pad_token_id": null,
93
+ "prefix": null,
94
+ "problem_type": null,
95
+ "pruned_heads": {},
96
+ "remove_invalid_values": false,
97
+ "repetition_penalty": 1.0,
98
+ "return_dict": true,
99
+ "return_dict_in_generate": false,
100
+ "rms_norm_eps": 1e-06,
101
+ "rope_scaling": {
102
+ "mrope_section": [
103
+ 16,
104
+ 24,
105
+ 24
106
+ ],
107
+ "rope_type": "default",
108
+ "type": "default"
109
+ },
110
+ "rope_theta": 1000000.0,
111
+ "sep_token_id": null,
112
+ "sliding_window": 32768,
113
+ "suppress_tokens": null,
114
+ "task_specific_params": null,
115
+ "temperature": 1.0,
116
+ "tf_legacy_loss": false,
117
+ "tie_encoder_decoder": false,
118
+ "tie_word_embeddings": true,
119
+ "tokenizer_class": null,
120
+ "top_k": 50,
121
+ "top_p": 1.0,
122
+ "torch_dtype": "bfloat16",
123
+ "torchscript": false,
124
+ "typical_p": 1.0,
125
+ "use_bfloat16": false,
126
+ "use_cache": true,
127
+ "use_sliding_window": false,
128
+ "video_token_id": null,
129
+ "vision_end_token_id": 151653,
130
+ "vision_start_token_id": 151652,
131
+ "vision_token_id": 151654,
132
+ "vocab_size": 151936
133
+ },
134
+ "torch_dtype": "bfloat16",
135
+ "use_cache": true,
136
+ "use_sliding_window": false,
137
+ "video_token_id": 151656,
138
+ "vision_config": {
139
+ "_name_or_path": "",
140
+ "add_cross_attention": false,
141
+ "architectures": null,
142
+ "bad_words_ids": null,
143
+ "begin_suppress_tokens": null,
144
+ "bos_token_id": null,
145
+ "chunk_size_feed_forward": 0,
146
+ "cross_attention_hidden_size": null,
147
+ "decoder_start_token_id": null,
148
+ "depth": 32,
149
+ "diversity_penalty": 0.0,
150
+ "do_sample": false,
151
+ "early_stopping": false,
152
+ "embed_dim": 1280,
153
+ "encoder_no_repeat_ngram_size": 0,
154
+ "eos_token_id": null,
155
+ "exponential_decay_length_penalty": null,
156
+ "finetuning_task": null,
157
+ "forced_bos_token_id": null,
158
+ "forced_eos_token_id": null,
159
+ "hidden_act": "quick_gelu",
160
+ "hidden_size": 1536,
161
+ "id2label": {
162
+ "0": "LABEL_0",
163
+ "1": "LABEL_1"
164
+ },
165
+ "in_channels": 3,
166
+ "in_chans": 3,
167
+ "initializer_range": 0.02,
168
+ "is_decoder": false,
169
+ "is_encoder_decoder": false,
170
+ "label2id": {
171
+ "LABEL_0": 0,
172
+ "LABEL_1": 1
173
+ },
174
+ "length_penalty": 1.0,
175
+ "max_length": 20,
176
+ "min_length": 0,
177
+ "mlp_ratio": 4,
178
+ "model_type": "qwen2_vl",
179
+ "no_repeat_ngram_size": 0,
180
+ "num_beam_groups": 1,
181
+ "num_beams": 1,
182
+ "num_heads": 16,
183
+ "num_return_sequences": 1,
184
+ "output_attentions": false,
185
+ "output_hidden_states": false,
186
+ "output_scores": false,
187
+ "pad_token_id": null,
188
+ "patch_size": 14,
189
+ "prefix": null,
190
+ "problem_type": null,
191
+ "pruned_heads": {},
192
+ "remove_invalid_values": false,
193
+ "repetition_penalty": 1.0,
194
+ "return_dict": true,
195
+ "return_dict_in_generate": false,
196
+ "sep_token_id": null,
197
+ "spatial_merge_size": 2,
198
+ "spatial_patch_size": 14,
199
+ "suppress_tokens": null,
200
+ "task_specific_params": null,
201
+ "temperature": 1.0,
202
+ "temporal_patch_size": 2,
203
+ "tf_legacy_loss": false,
204
+ "tie_encoder_decoder": false,
205
+ "tie_word_embeddings": true,
206
+ "tokenizer_class": null,
207
+ "top_k": 50,
208
+ "top_p": 1.0,
209
+ "torch_dtype": null,
210
+ "torchscript": false,
211
+ "typical_p": 1.0,
212
+ "use_bfloat16": false
213
+ },
214
+ "vision_end_token_id": 151653,
215
+ "vision_start_token_id": 151652,
216
+ "vision_token_id": 151654,
217
+ "vocab_size": 151936
218
+ },
219
+ "vocab_size": 500
220
+ }
generation_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 151645,
6
+ 151643
7
+ ],
8
+ "pad_token_id": 151643,
9
+ "temperature": 0.01,
10
+ "top_k": 1,
11
+ "top_p": 0.001,
12
+ "transformers_version": "4.46.3"
13
+ }
preprocessor_config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_convert_rgb": true,
3
+ "do_normalize": true,
4
+ "do_rescale": true,
5
+ "do_resize": true,
6
+ "image_mean": [
7
+ 0.48145466,
8
+ 0.4578275,
9
+ 0.40821073
10
+ ],
11
+ "image_processor_type": "Qwen2VLImageProcessor",
12
+ "image_std": [
13
+ 0.26862954,
14
+ 0.26130258,
15
+ 0.27577711
16
+ ],
17
+ "max_pixels": 602112,
18
+ "merge_size": 2,
19
+ "min_pixels": 3136,
20
+ "patch_size": 14,
21
+ "processor_class": "ColQwen2Processor",
22
+ "resample": 3,
23
+ "rescale_factor": 0.00392156862745098,
24
+ "size": {
25
+ "max_pixels": 602112,
26
+ "min_pixels": 3136,
27
+ "longest_edge": 602112,
28
+ "shortest_edge": 3136
29
+ },
30
+ "temporal_patch_size": 2
31
+ }
tokenizer.json ADDED
@@ -0,0 +1,1657 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "1.0",
3
+ "truncation": null,
4
+ "padding": null,
5
+ "added_tokens": [
6
+ {
7
+ "id": 500,
8
+ "content": "<|endoftext|>",
9
+ "single_word": false,
10
+ "lstrip": false,
11
+ "rstrip": false,
12
+ "normalized": false,
13
+ "special": true
14
+ },
15
+ {
16
+ "id": 501,
17
+ "content": "<|im_start|>",
18
+ "single_word": false,
19
+ "lstrip": false,
20
+ "rstrip": false,
21
+ "normalized": false,
22
+ "special": true
23
+ },
24
+ {
25
+ "id": 502,
26
+ "content": "<|im_end|>",
27
+ "single_word": false,
28
+ "lstrip": false,
29
+ "rstrip": false,
30
+ "normalized": false,
31
+ "special": true
32
+ },
33
+ {
34
+ "id": 503,
35
+ "content": "<|object_ref_start|>",
36
+ "single_word": false,
37
+ "lstrip": false,
38
+ "rstrip": false,
39
+ "normalized": false,
40
+ "special": true
41
+ },
42
+ {
43
+ "id": 504,
44
+ "content": "<|object_ref_end|>",
45
+ "single_word": false,
46
+ "lstrip": false,
47
+ "rstrip": false,
48
+ "normalized": false,
49
+ "special": true
50
+ },
51
+ {
52
+ "id": 505,
53
+ "content": "<|box_start|>",
54
+ "single_word": false,
55
+ "lstrip": false,
56
+ "rstrip": false,
57
+ "normalized": false,
58
+ "special": true
59
+ },
60
+ {
61
+ "id": 506,
62
+ "content": "<|box_end|>",
63
+ "single_word": false,
64
+ "lstrip": false,
65
+ "rstrip": false,
66
+ "normalized": false,
67
+ "special": true
68
+ },
69
+ {
70
+ "id": 507,
71
+ "content": "<|quad_start|>",
72
+ "single_word": false,
73
+ "lstrip": false,
74
+ "rstrip": false,
75
+ "normalized": false,
76
+ "special": true
77
+ },
78
+ {
79
+ "id": 508,
80
+ "content": "<|quad_end|>",
81
+ "single_word": false,
82
+ "lstrip": false,
83
+ "rstrip": false,
84
+ "normalized": false,
85
+ "special": true
86
+ },
87
+ {
88
+ "id": 509,
89
+ "content": "<|vision_start|>",
90
+ "single_word": false,
91
+ "lstrip": false,
92
+ "rstrip": false,
93
+ "normalized": false,
94
+ "special": true
95
+ },
96
+ {
97
+ "id": 510,
98
+ "content": "<|vision_end|>",
99
+ "single_word": false,
100
+ "lstrip": false,
101
+ "rstrip": false,
102
+ "normalized": false,
103
+ "special": true
104
+ },
105
+ {
106
+ "id": 511,
107
+ "content": "<|vision_pad|>",
108
+ "single_word": false,
109
+ "lstrip": false,
110
+ "rstrip": false,
111
+ "normalized": false,
112
+ "special": true
113
+ },
114
+ {
115
+ "id": 512,
116
+ "content": "<|image_pad|>",
117
+ "single_word": false,
118
+ "lstrip": false,
119
+ "rstrip": false,
120
+ "normalized": false,
121
+ "special": true
122
+ },
123
+ {
124
+ "id": 513,
125
+ "content": "<|video_pad|>",
126
+ "single_word": false,
127
+ "lstrip": false,
128
+ "rstrip": false,
129
+ "normalized": false,
130
+ "special": true
131
+ }
132
+ ],
133
+ "normalizer": {
134
+ "type": "NFC"
135
+ },
136
+ "pre_tokenizer": {
137
+ "type": "Sequence",
138
+ "pretokenizers": [
139
+ {
140
+ "type": "Split",
141
+ "pattern": {
142
+ "Regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?\\p{L}+|\\p{N}| ?[^\\s\\p{L}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+"
143
+ },
144
+ "behavior": "Isolated",
145
+ "invert": false
146
+ },
147
+ {
148
+ "type": "ByteLevel",
149
+ "add_prefix_space": false,
150
+ "trim_offsets": false,
151
+ "use_regex": false
152
+ }
153
+ ]
154
+ },
155
+ "post_processor": {
156
+ "type": "ByteLevel",
157
+ "add_prefix_space": false,
158
+ "trim_offsets": false,
159
+ "use_regex": false
160
+ },
161
+ "decoder": {
162
+ "type": "ByteLevel",
163
+ "add_prefix_space": false,
164
+ "trim_offsets": false,
165
+ "use_regex": false
166
+ },
167
+ "model": {
168
+ "type": "BPE",
169
+ "dropout": null,
170
+ "unk_token": null,
171
+ "continuing_subword_prefix": "",
172
+ "end_of_word_suffix": "",
173
+ "fuse_unk": false,
174
+ "byte_fallback": false,
175
+ "ignore_merges": false,
176
+ "vocab": {
177
+ "!": 0,
178
+ "\"": 1,
179
+ "#": 2,
180
+ "$": 3,
181
+ "%": 4,
182
+ "&": 5,
183
+ "'": 6,
184
+ "(": 7,
185
+ ")": 8,
186
+ "*": 9,
187
+ "+": 10,
188
+ ",": 11,
189
+ "-": 12,
190
+ ".": 13,
191
+ "/": 14,
192
+ "0": 15,
193
+ "1": 16,
194
+ "2": 17,
195
+ "3": 18,
196
+ "4": 19,
197
+ "5": 20,
198
+ "6": 21,
199
+ "7": 22,
200
+ "8": 23,
201
+ "9": 24,
202
+ ":": 25,
203
+ ";": 26,
204
+ "<": 27,
205
+ "=": 28,
206
+ ">": 29,
207
+ "?": 30,
208
+ "@": 31,
209
+ "A": 32,
210
+ "B": 33,
211
+ "C": 34,
212
+ "D": 35,
213
+ "E": 36,
214
+ "F": 37,
215
+ "G": 38,
216
+ "H": 39,
217
+ "I": 40,
218
+ "J": 41,
219
+ "K": 42,
220
+ "L": 43,
221
+ "M": 44,
222
+ "N": 45,
223
+ "O": 46,
224
+ "P": 47,
225
+ "Q": 48,
226
+ "R": 49,
227
+ "S": 50,
228
+ "T": 51,
229
+ "U": 52,
230
+ "V": 53,
231
+ "W": 54,
232
+ "X": 55,
233
+ "Y": 56,
234
+ "Z": 57,
235
+ "[": 58,
236
+ "\\": 59,
237
+ "]": 60,
238
+ "^": 61,
239
+ "_": 62,
240
+ "`": 63,
241
+ "a": 64,
242
+ "b": 65,
243
+ "c": 66,
244
+ "d": 67,
245
+ "e": 68,
246
+ "f": 69,
247
+ "g": 70,
248
+ "h": 71,
249
+ "i": 72,
250
+ "j": 73,
251
+ "k": 74,
252
+ "l": 75,
253
+ "m": 76,
254
+ "n": 77,
255
+ "o": 78,
256
+ "p": 79,
257
+ "q": 80,
258
+ "r": 81,
259
+ "s": 82,
260
+ "t": 83,
261
+ "u": 84,
262
+ "v": 85,
263
+ "w": 86,
264
+ "x": 87,
265
+ "y": 88,
266
+ "z": 89,
267
+ "{": 90,
268
+ "|": 91,
269
+ "}": 92,
270
+ "~": 93,
271
+ "¡": 94,
272
+ "¢": 95,
273
+ "£": 96,
274
+ "¤": 97,
275
+ "¥": 98,
276
+ "¦": 99,
277
+ "§": 100,
278
+ "¨": 101,
279
+ "©": 102,
280
+ "ª": 103,
281
+ "«": 104,
282
+ "¬": 105,
283
+ "®": 106,
284
+ "¯": 107,
285
+ "°": 108,
286
+ "±": 109,
287
+ "²": 110,
288
+ "³": 111,
289
+ "´": 112,
290
+ "µ": 113,
291
+ "¶": 114,
292
+ "·": 115,
293
+ "¸": 116,
294
+ "¹": 117,
295
+ "º": 118,
296
+ "»": 119,
297
+ "¼": 120,
298
+ "½": 121,
299
+ "¾": 122,
300
+ "¿": 123,
301
+ "À": 124,
302
+ "Á": 125,
303
+ "Â": 126,
304
+ "Ã": 127,
305
+ "Ä": 128,
306
+ "Å": 129,
307
+ "Æ": 130,
308
+ "Ç": 131,
309
+ "È": 132,
310
+ "É": 133,
311
+ "Ê": 134,
312
+ "Ë": 135,
313
+ "Ì": 136,
314
+ "Í": 137,
315
+ "Î": 138,
316
+ "Ï": 139,
317
+ "Ð": 140,
318
+ "Ñ": 141,
319
+ "Ò": 142,
320
+ "Ó": 143,
321
+ "Ô": 144,
322
+ "Õ": 145,
323
+ "Ö": 146,
324
+ "×": 147,
325
+ "Ø": 148,
326
+ "Ù": 149,
327
+ "Ú": 150,
328
+ "Û": 151,
329
+ "Ü": 152,
330
+ "Ý": 153,
331
+ "Þ": 154,
332
+ "ß": 155,
333
+ "à": 156,
334
+ "á": 157,
335
+ "â": 158,
336
+ "ã": 159,
337
+ "ä": 160,
338
+ "å": 161,
339
+ "æ": 162,
340
+ "ç": 163,
341
+ "è": 164,
342
+ "é": 165,
343
+ "ê": 166,
344
+ "ë": 167,
345
+ "ì": 168,
346
+ "í": 169,
347
+ "î": 170,
348
+ "ï": 171,
349
+ "ð": 172,
350
+ "ñ": 173,
351
+ "ò": 174,
352
+ "ó": 175,
353
+ "ô": 176,
354
+ "õ": 177,
355
+ "ö": 178,
356
+ "÷": 179,
357
+ "ø": 180,
358
+ "ù": 181,
359
+ "ú": 182,
360
+ "û": 183,
361
+ "ü": 184,
362
+ "ý": 185,
363
+ "þ": 186,
364
+ "ÿ": 187,
365
+ "Ā": 188,
366
+ "ā": 189,
367
+ "Ă": 190,
368
+ "ă": 191,
369
+ "Ą": 192,
370
+ "ą": 193,
371
+ "Ć": 194,
372
+ "ć": 195,
373
+ "Ĉ": 196,
374
+ "ĉ": 197,
375
+ "Ċ": 198,
376
+ "ċ": 199,
377
+ "Č": 200,
378
+ "č": 201,
379
+ "Ď": 202,
380
+ "ď": 203,
381
+ "Đ": 204,
382
+ "đ": 205,
383
+ "Ē": 206,
384
+ "ē": 207,
385
+ "Ĕ": 208,
386
+ "ĕ": 209,
387
+ "Ė": 210,
388
+ "ė": 211,
389
+ "Ę": 212,
390
+ "ę": 213,
391
+ "Ě": 214,
392
+ "ě": 215,
393
+ "Ĝ": 216,
394
+ "ĝ": 217,
395
+ "Ğ": 218,
396
+ "ğ": 219,
397
+ "Ġ": 220,
398
+ "ġ": 221,
399
+ "Ģ": 222,
400
+ "ģ": 223,
401
+ "Ĥ": 224,
402
+ "ĥ": 225,
403
+ "Ħ": 226,
404
+ "ħ": 227,
405
+ "Ĩ": 228,
406
+ "ĩ": 229,
407
+ "Ī": 230,
408
+ "ī": 231,
409
+ "Ĭ": 232,
410
+ "ĭ": 233,
411
+ "Į": 234,
412
+ "į": 235,
413
+ "İ": 236,
414
+ "ı": 237,
415
+ "IJ": 238,
416
+ "ij": 239,
417
+ "Ĵ": 240,
418
+ "ĵ": 241,
419
+ "Ķ": 242,
420
+ "ķ": 243,
421
+ "ĸ": 244,
422
+ "Ĺ": 245,
423
+ "ĺ": 246,
424
+ "Ļ": 247,
425
+ "ļ": 248,
426
+ "Ľ": 249,
427
+ "ľ": 250,
428
+ "Ŀ": 251,
429
+ "ŀ": 252,
430
+ "Ł": 253,
431
+ "ł": 254,
432
+ "Ń": 255,
433
+ "ĠĠ": 256,
434
+ "ĠĠĠĠ": 257,
435
+ "in": 258,
436
+ "Ġt": 259,
437
+ "ĠĠĠĠĠĠĠĠ": 260,
438
+ "er": 261,
439
+ "ĠĠĠ": 262,
440
+ "on": 263,
441
+ "Ġa": 264,
442
+ "re": 265,
443
+ "at": 266,
444
+ "st": 267,
445
+ "en": 268,
446
+ "or": 269,
447
+ "Ġth": 270,
448
+ "ĊĊ": 271,
449
+ "Ġc": 272,
450
+ "le": 273,
451
+ "Ġs": 274,
452
+ "it": 275,
453
+ "an": 276,
454
+ "ar": 277,
455
+ "al": 278,
456
+ "Ġthe": 279,
457
+ ";Ċ": 280,
458
+ "Ġp": 281,
459
+ "Ġf": 282,
460
+ "ou": 283,
461
+ "Ġ=": 284,
462
+ "is": 285,
463
+ "ĠĠĠĠĠĠĠ": 286,
464
+ "ing": 287,
465
+ "es": 288,
466
+ "Ġw": 289,
467
+ "ion": 290,
468
+ "ed": 291,
469
+ "ic": 292,
470
+ "Ġb": 293,
471
+ "Ġd": 294,
472
+ "et": 295,
473
+ "Ġm": 296,
474
+ "Ġo": 297,
475
+ "ĉĉ": 298,
476
+ "ro": 299,
477
+ "as": 300,
478
+ "el": 301,
479
+ "ct": 302,
480
+ "nd": 303,
481
+ "Ġin": 304,
482
+ "Ġh": 305,
483
+ "ent": 306,
484
+ "id": 307,
485
+ "Ġn": 308,
486
+ "am": 309,
487
+ "ĠĠĠĠĠĠĠĠĠĠĠ": 310,
488
+ "Ġto": 311,
489
+ "Ġre": 312,
490
+ "--": 313,
491
+ "Ġ{": 314,
492
+ "Ġof": 315,
493
+ "om": 316,
494
+ ");Ċ": 317,
495
+ "im": 318,
496
+ "čĊ": 319,
497
+ "Ġ(": 320,
498
+ "il": 321,
499
+ "//": 322,
500
+ "Ġand": 323,
501
+ "ur": 324,
502
+ "se": 325,
503
+ "Ġl": 326,
504
+ "ex": 327,
505
+ "ĠS": 328,
506
+ "ad": 329,
507
+ "Ġ\"": 330,
508
+ "ch": 331,
509
+ "ut": 332,
510
+ "if": 333,
511
+ "**": 334,
512
+ "Ġ}": 335,
513
+ "em": 336,
514
+ "ol": 337,
515
+ "ĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠ": 338,
516
+ "th": 339,
517
+ ")Ċ": 340,
518
+ "Ġ{Ċ": 341,
519
+ "Ġg": 342,
520
+ "ig": 343,
521
+ "iv": 344,
522
+ ",Ċ": 345,
523
+ "ce": 346,
524
+ "od": 347,
525
+ "Ġv": 348,
526
+ "ate": 349,
527
+ "ĠT": 350,
528
+ "ag": 351,
529
+ "ay": 352,
530
+ "Ġ*": 353,
531
+ "ot": 354,
532
+ "us": 355,
533
+ "ĠC": 356,
534
+ "Ġst": 357,
535
+ "ĠI": 358,
536
+ "un": 359,
537
+ "ul": 360,
538
+ "ue": 361,
539
+ "ĠA": 362,
540
+ "ow": 363,
541
+ "Ġ'": 364,
542
+ "ew": 365,
543
+ "Ġ<": 366,
544
+ "ation": 367,
545
+ "()": 368,
546
+ "Ġfor": 369,
547
+ "ab": 370,
548
+ "ort": 371,
549
+ "um": 372,
550
+ "ame": 373,
551
+ "Ġis": 374,
552
+ "pe": 375,
553
+ "tr": 376,
554
+ "ck": 377,
555
+ "âĢ": 378,
556
+ "Ġy": 379,
557
+ "ist": 380,
558
+ "----": 381,
559
+ ".ĊĊ": 382,
560
+ "he": 383,
561
+ "Ġe": 384,
562
+ "lo": 385,
563
+ "ĠM": 386,
564
+ "Ġbe": 387,
565
+ "ers": 388,
566
+ "Ġon": 389,
567
+ "Ġcon": 390,
568
+ "ap": 391,
569
+ "ub": 392,
570
+ "ĠP": 393,
571
+ "ĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠ": 394,
572
+ "ass": 395,
573
+ "int": 396,
574
+ ">Ċ": 397,
575
+ "ly": 398,
576
+ "urn": 399,
577
+ "Ġ$": 400,
578
+ ";ĊĊ": 401,
579
+ "av": 402,
580
+ "port": 403,
581
+ "ir": 404,
582
+ "->": 405,
583
+ "nt": 406,
584
+ "ction": 407,
585
+ "end": 408,
586
+ "Ġde": 409,
587
+ "ith": 410,
588
+ "out": 411,
589
+ "turn": 412,
590
+ "our": 413,
591
+ "ĠĠĠĠĠ": 414,
592
+ "lic": 415,
593
+ "res": 416,
594
+ "pt": 417,
595
+ "==": 418,
596
+ "Ġthis": 419,
597
+ "Ġwh": 420,
598
+ "Ġif": 421,
599
+ "ĠD": 422,
600
+ "ver": 423,
601
+ "age": 424,
602
+ "ĠB": 425,
603
+ "ht": 426,
604
+ "ext": 427,
605
+ "=\"": 428,
606
+ "Ġthat": 429,
607
+ "****": 430,
608
+ "ĠR": 431,
609
+ "Ġit": 432,
610
+ "ess": 433,
611
+ "ĠF": 434,
612
+ "Ġr": 435,
613
+ "os": 436,
614
+ "and": 437,
615
+ "Ġas": 438,
616
+ "ect": 439,
617
+ "ke": 440,
618
+ "rom": 441,
619
+ "Ġ//": 442,
620
+ "con": 443,
621
+ "ĠL": 444,
622
+ "(\"": 445,
623
+ "qu": 446,
624
+ "lass": 447,
625
+ "Ġwith": 448,
626
+ "iz": 449,
627
+ "de": 450,
628
+ "ĠN": 451,
629
+ "Ġal": 452,
630
+ "op": 453,
631
+ "up": 454,
632
+ "get": 455,
633
+ "Ġ}Ċ": 456,
634
+ "ile": 457,
635
+ "Ġan": 458,
636
+ "ata": 459,
637
+ "ore": 460,
638
+ "ri": 461,
639
+ "Ġpro": 462,
640
+ ";čĊ": 463,
641
+ "ĉĉĉĉ": 464,
642
+ "ter": 465,
643
+ "ain": 466,
644
+ "ĠW": 467,
645
+ "ĠE": 468,
646
+ "Ġcom": 469,
647
+ "Ġreturn": 470,
648
+ "art": 471,
649
+ "ĠH": 472,
650
+ "ack": 473,
651
+ "import": 474,
652
+ "ublic": 475,
653
+ "Ġor": 476,
654
+ "est": 477,
655
+ "ment": 478,
656
+ "ĠG": 479,
657
+ "able": 480,
658
+ "Ġ-": 481,
659
+ "ine": 482,
660
+ "ill": 483,
661
+ "ind": 484,
662
+ "ere": 485,
663
+ "::": 486,
664
+ "ity": 487,
665
+ "Ġ+": 488,
666
+ "Ġtr": 489,
667
+ "elf": 490,
668
+ "ight": 491,
669
+ "('": 492,
670
+ "orm": 493,
671
+ "ult": 494,
672
+ "str": 495,
673
+ "..": 496,
674
+ "\",": 497,
675
+ "Ġyou": 498,
676
+ "ype": 499
677
+ },
678
+ "merges": [
679
+ [
680
+ "Ġ",
681
+ "Ġ"
682
+ ],
683
+ [
684
+ "ĠĠ",
685
+ "ĠĠ"
686
+ ],
687
+ [
688
+ "i",
689
+ "n"
690
+ ],
691
+ [
692
+ "Ġ",
693
+ "t"
694
+ ],
695
+ [
696
+ "ĠĠĠĠ",
697
+ "ĠĠĠĠ"
698
+ ],
699
+ [
700
+ "e",
701
+ "r"
702
+ ],
703
+ [
704
+ "ĠĠ",
705
+ "Ġ"
706
+ ],
707
+ [
708
+ "o",
709
+ "n"
710
+ ],
711
+ [
712
+ "Ġ",
713
+ "a"
714
+ ],
715
+ [
716
+ "r",
717
+ "e"
718
+ ],
719
+ [
720
+ "a",
721
+ "t"
722
+ ],
723
+ [
724
+ "s",
725
+ "t"
726
+ ],
727
+ [
728
+ "e",
729
+ "n"
730
+ ],
731
+ [
732
+ "o",
733
+ "r"
734
+ ],
735
+ [
736
+ "Ġt",
737
+ "h"
738
+ ],
739
+ [
740
+ "Ċ",
741
+ "Ċ"
742
+ ],
743
+ [
744
+ "Ġ",
745
+ "c"
746
+ ],
747
+ [
748
+ "l",
749
+ "e"
750
+ ],
751
+ [
752
+ "Ġ",
753
+ "s"
754
+ ],
755
+ [
756
+ "i",
757
+ "t"
758
+ ],
759
+ [
760
+ "a",
761
+ "n"
762
+ ],
763
+ [
764
+ "a",
765
+ "r"
766
+ ],
767
+ [
768
+ "a",
769
+ "l"
770
+ ],
771
+ [
772
+ "Ġth",
773
+ "e"
774
+ ],
775
+ [
776
+ ";",
777
+ "Ċ"
778
+ ],
779
+ [
780
+ "Ġ",
781
+ "p"
782
+ ],
783
+ [
784
+ "Ġ",
785
+ "f"
786
+ ],
787
+ [
788
+ "o",
789
+ "u"
790
+ ],
791
+ [
792
+ "Ġ",
793
+ "="
794
+ ],
795
+ [
796
+ "i",
797
+ "s"
798
+ ],
799
+ [
800
+ "ĠĠĠĠ",
801
+ "ĠĠĠ"
802
+ ],
803
+ [
804
+ "in",
805
+ "g"
806
+ ],
807
+ [
808
+ "e",
809
+ "s"
810
+ ],
811
+ [
812
+ "Ġ",
813
+ "w"
814
+ ],
815
+ [
816
+ "i",
817
+ "on"
818
+ ],
819
+ [
820
+ "e",
821
+ "d"
822
+ ],
823
+ [
824
+ "i",
825
+ "c"
826
+ ],
827
+ [
828
+ "Ġ",
829
+ "b"
830
+ ],
831
+ [
832
+ "Ġ",
833
+ "d"
834
+ ],
835
+ [
836
+ "e",
837
+ "t"
838
+ ],
839
+ [
840
+ "Ġ",
841
+ "m"
842
+ ],
843
+ [
844
+ "Ġ",
845
+ "o"
846
+ ],
847
+ [
848
+ "ĉ",
849
+ "ĉ"
850
+ ],
851
+ [
852
+ "r",
853
+ "o"
854
+ ],
855
+ [
856
+ "a",
857
+ "s"
858
+ ],
859
+ [
860
+ "e",
861
+ "l"
862
+ ],
863
+ [
864
+ "c",
865
+ "t"
866
+ ],
867
+ [
868
+ "n",
869
+ "d"
870
+ ],
871
+ [
872
+ "Ġ",
873
+ "in"
874
+ ],
875
+ [
876
+ "Ġ",
877
+ "h"
878
+ ],
879
+ [
880
+ "en",
881
+ "t"
882
+ ],
883
+ [
884
+ "i",
885
+ "d"
886
+ ],
887
+ [
888
+ "Ġ",
889
+ "n"
890
+ ],
891
+ [
892
+ "a",
893
+ "m"
894
+ ],
895
+ [
896
+ "ĠĠĠĠĠĠĠĠ",
897
+ "ĠĠĠ"
898
+ ],
899
+ [
900
+ "Ġt",
901
+ "o"
902
+ ],
903
+ [
904
+ "Ġ",
905
+ "re"
906
+ ],
907
+ [
908
+ "-",
909
+ "-"
910
+ ],
911
+ [
912
+ "Ġ",
913
+ "{"
914
+ ],
915
+ [
916
+ "Ġo",
917
+ "f"
918
+ ],
919
+ [
920
+ "o",
921
+ "m"
922
+ ],
923
+ [
924
+ ")",
925
+ ";Ċ"
926
+ ],
927
+ [
928
+ "i",
929
+ "m"
930
+ ],
931
+ [
932
+ "č",
933
+ "Ċ"
934
+ ],
935
+ [
936
+ "Ġ",
937
+ "("
938
+ ],
939
+ [
940
+ "i",
941
+ "l"
942
+ ],
943
+ [
944
+ "/",
945
+ "/"
946
+ ],
947
+ [
948
+ "Ġa",
949
+ "nd"
950
+ ],
951
+ [
952
+ "u",
953
+ "r"
954
+ ],
955
+ [
956
+ "s",
957
+ "e"
958
+ ],
959
+ [
960
+ "Ġ",
961
+ "l"
962
+ ],
963
+ [
964
+ "e",
965
+ "x"
966
+ ],
967
+ [
968
+ "Ġ",
969
+ "S"
970
+ ],
971
+ [
972
+ "a",
973
+ "d"
974
+ ],
975
+ [
976
+ "Ġ",
977
+ "\""
978
+ ],
979
+ [
980
+ "c",
981
+ "h"
982
+ ],
983
+ [
984
+ "u",
985
+ "t"
986
+ ],
987
+ [
988
+ "i",
989
+ "f"
990
+ ],
991
+ [
992
+ "*",
993
+ "*"
994
+ ],
995
+ [
996
+ "Ġ",
997
+ "}"
998
+ ],
999
+ [
1000
+ "e",
1001
+ "m"
1002
+ ],
1003
+ [
1004
+ "o",
1005
+ "l"
1006
+ ],
1007
+ [
1008
+ "ĠĠĠĠĠĠĠĠ",
1009
+ "ĠĠĠĠĠĠĠĠ"
1010
+ ],
1011
+ [
1012
+ "t",
1013
+ "h"
1014
+ ],
1015
+ [
1016
+ ")",
1017
+ "Ċ"
1018
+ ],
1019
+ [
1020
+ "Ġ{",
1021
+ "Ċ"
1022
+ ],
1023
+ [
1024
+ "Ġ",
1025
+ "g"
1026
+ ],
1027
+ [
1028
+ "i",
1029
+ "g"
1030
+ ],
1031
+ [
1032
+ "i",
1033
+ "v"
1034
+ ],
1035
+ [
1036
+ ",",
1037
+ "Ċ"
1038
+ ],
1039
+ [
1040
+ "c",
1041
+ "e"
1042
+ ],
1043
+ [
1044
+ "o",
1045
+ "d"
1046
+ ],
1047
+ [
1048
+ "Ġ",
1049
+ "v"
1050
+ ],
1051
+ [
1052
+ "at",
1053
+ "e"
1054
+ ],
1055
+ [
1056
+ "Ġ",
1057
+ "T"
1058
+ ],
1059
+ [
1060
+ "a",
1061
+ "g"
1062
+ ],
1063
+ [
1064
+ "a",
1065
+ "y"
1066
+ ],
1067
+ [
1068
+ "Ġ",
1069
+ "*"
1070
+ ],
1071
+ [
1072
+ "o",
1073
+ "t"
1074
+ ],
1075
+ [
1076
+ "u",
1077
+ "s"
1078
+ ],
1079
+ [
1080
+ "Ġ",
1081
+ "C"
1082
+ ],
1083
+ [
1084
+ "Ġ",
1085
+ "st"
1086
+ ],
1087
+ [
1088
+ "Ġ",
1089
+ "I"
1090
+ ],
1091
+ [
1092
+ "u",
1093
+ "n"
1094
+ ],
1095
+ [
1096
+ "u",
1097
+ "l"
1098
+ ],
1099
+ [
1100
+ "u",
1101
+ "e"
1102
+ ],
1103
+ [
1104
+ "Ġ",
1105
+ "A"
1106
+ ],
1107
+ [
1108
+ "o",
1109
+ "w"
1110
+ ],
1111
+ [
1112
+ "Ġ",
1113
+ "'"
1114
+ ],
1115
+ [
1116
+ "e",
1117
+ "w"
1118
+ ],
1119
+ [
1120
+ "Ġ",
1121
+ "<"
1122
+ ],
1123
+ [
1124
+ "at",
1125
+ "ion"
1126
+ ],
1127
+ [
1128
+ "(",
1129
+ ")"
1130
+ ],
1131
+ [
1132
+ "Ġf",
1133
+ "or"
1134
+ ],
1135
+ [
1136
+ "a",
1137
+ "b"
1138
+ ],
1139
+ [
1140
+ "or",
1141
+ "t"
1142
+ ],
1143
+ [
1144
+ "u",
1145
+ "m"
1146
+ ],
1147
+ [
1148
+ "am",
1149
+ "e"
1150
+ ],
1151
+ [
1152
+ "Ġ",
1153
+ "is"
1154
+ ],
1155
+ [
1156
+ "p",
1157
+ "e"
1158
+ ],
1159
+ [
1160
+ "t",
1161
+ "r"
1162
+ ],
1163
+ [
1164
+ "c",
1165
+ "k"
1166
+ ],
1167
+ [
1168
+ "â",
1169
+ "Ģ"
1170
+ ],
1171
+ [
1172
+ "Ġ",
1173
+ "y"
1174
+ ],
1175
+ [
1176
+ "i",
1177
+ "st"
1178
+ ],
1179
+ [
1180
+ "--",
1181
+ "--"
1182
+ ],
1183
+ [
1184
+ ".",
1185
+ "ĊĊ"
1186
+ ],
1187
+ [
1188
+ "h",
1189
+ "e"
1190
+ ],
1191
+ [
1192
+ "Ġ",
1193
+ "e"
1194
+ ],
1195
+ [
1196
+ "l",
1197
+ "o"
1198
+ ],
1199
+ [
1200
+ "Ġ",
1201
+ "M"
1202
+ ],
1203
+ [
1204
+ "Ġb",
1205
+ "e"
1206
+ ],
1207
+ [
1208
+ "er",
1209
+ "s"
1210
+ ],
1211
+ [
1212
+ "Ġ",
1213
+ "on"
1214
+ ],
1215
+ [
1216
+ "Ġc",
1217
+ "on"
1218
+ ],
1219
+ [
1220
+ "a",
1221
+ "p"
1222
+ ],
1223
+ [
1224
+ "u",
1225
+ "b"
1226
+ ],
1227
+ [
1228
+ "Ġ",
1229
+ "P"
1230
+ ],
1231
+ [
1232
+ "ĠĠĠĠĠĠĠĠ",
1233
+ "ĠĠĠĠĠĠĠ"
1234
+ ],
1235
+ [
1236
+ "as",
1237
+ "s"
1238
+ ],
1239
+ [
1240
+ "in",
1241
+ "t"
1242
+ ],
1243
+ [
1244
+ ">",
1245
+ "Ċ"
1246
+ ],
1247
+ [
1248
+ "l",
1249
+ "y"
1250
+ ],
1251
+ [
1252
+ "ur",
1253
+ "n"
1254
+ ],
1255
+ [
1256
+ "Ġ",
1257
+ "$"
1258
+ ],
1259
+ [
1260
+ ";",
1261
+ "ĊĊ"
1262
+ ],
1263
+ [
1264
+ "a",
1265
+ "v"
1266
+ ],
1267
+ [
1268
+ "p",
1269
+ "ort"
1270
+ ],
1271
+ [
1272
+ "i",
1273
+ "r"
1274
+ ],
1275
+ [
1276
+ "-",
1277
+ ">"
1278
+ ],
1279
+ [
1280
+ "n",
1281
+ "t"
1282
+ ],
1283
+ [
1284
+ "ct",
1285
+ "ion"
1286
+ ],
1287
+ [
1288
+ "en",
1289
+ "d"
1290
+ ],
1291
+ [
1292
+ "Ġd",
1293
+ "e"
1294
+ ],
1295
+ [
1296
+ "it",
1297
+ "h"
1298
+ ],
1299
+ [
1300
+ "ou",
1301
+ "t"
1302
+ ],
1303
+ [
1304
+ "t",
1305
+ "urn"
1306
+ ],
1307
+ [
1308
+ "ou",
1309
+ "r"
1310
+ ],
1311
+ [
1312
+ "ĠĠĠĠ",
1313
+ "Ġ"
1314
+ ],
1315
+ [
1316
+ "l",
1317
+ "ic"
1318
+ ],
1319
+ [
1320
+ "re",
1321
+ "s"
1322
+ ],
1323
+ [
1324
+ "p",
1325
+ "t"
1326
+ ],
1327
+ [
1328
+ "=",
1329
+ "="
1330
+ ],
1331
+ [
1332
+ "Ġth",
1333
+ "is"
1334
+ ],
1335
+ [
1336
+ "Ġw",
1337
+ "h"
1338
+ ],
1339
+ [
1340
+ "Ġ",
1341
+ "if"
1342
+ ],
1343
+ [
1344
+ "Ġ",
1345
+ "D"
1346
+ ],
1347
+ [
1348
+ "v",
1349
+ "er"
1350
+ ],
1351
+ [
1352
+ "ag",
1353
+ "e"
1354
+ ],
1355
+ [
1356
+ "Ġ",
1357
+ "B"
1358
+ ],
1359
+ [
1360
+ "h",
1361
+ "t"
1362
+ ],
1363
+ [
1364
+ "ex",
1365
+ "t"
1366
+ ],
1367
+ [
1368
+ "=",
1369
+ "\""
1370
+ ],
1371
+ [
1372
+ "Ġth",
1373
+ "at"
1374
+ ],
1375
+ [
1376
+ "**",
1377
+ "**"
1378
+ ],
1379
+ [
1380
+ "Ġ",
1381
+ "R"
1382
+ ],
1383
+ [
1384
+ "Ġ",
1385
+ "it"
1386
+ ],
1387
+ [
1388
+ "es",
1389
+ "s"
1390
+ ],
1391
+ [
1392
+ "Ġ",
1393
+ "F"
1394
+ ],
1395
+ [
1396
+ "Ġ",
1397
+ "r"
1398
+ ],
1399
+ [
1400
+ "o",
1401
+ "s"
1402
+ ],
1403
+ [
1404
+ "an",
1405
+ "d"
1406
+ ],
1407
+ [
1408
+ "Ġa",
1409
+ "s"
1410
+ ],
1411
+ [
1412
+ "e",
1413
+ "ct"
1414
+ ],
1415
+ [
1416
+ "k",
1417
+ "e"
1418
+ ],
1419
+ [
1420
+ "ro",
1421
+ "m"
1422
+ ],
1423
+ [
1424
+ "Ġ",
1425
+ "//"
1426
+ ],
1427
+ [
1428
+ "c",
1429
+ "on"
1430
+ ],
1431
+ [
1432
+ "Ġ",
1433
+ "L"
1434
+ ],
1435
+ [
1436
+ "(",
1437
+ "\""
1438
+ ],
1439
+ [
1440
+ "q",
1441
+ "u"
1442
+ ],
1443
+ [
1444
+ "l",
1445
+ "ass"
1446
+ ],
1447
+ [
1448
+ "Ġw",
1449
+ "ith"
1450
+ ],
1451
+ [
1452
+ "i",
1453
+ "z"
1454
+ ],
1455
+ [
1456
+ "d",
1457
+ "e"
1458
+ ],
1459
+ [
1460
+ "Ġ",
1461
+ "N"
1462
+ ],
1463
+ [
1464
+ "Ġa",
1465
+ "l"
1466
+ ],
1467
+ [
1468
+ "o",
1469
+ "p"
1470
+ ],
1471
+ [
1472
+ "u",
1473
+ "p"
1474
+ ],
1475
+ [
1476
+ "g",
1477
+ "et"
1478
+ ],
1479
+ [
1480
+ "Ġ}",
1481
+ "Ċ"
1482
+ ],
1483
+ [
1484
+ "i",
1485
+ "le"
1486
+ ],
1487
+ [
1488
+ "Ġa",
1489
+ "n"
1490
+ ],
1491
+ [
1492
+ "at",
1493
+ "a"
1494
+ ],
1495
+ [
1496
+ "o",
1497
+ "re"
1498
+ ],
1499
+ [
1500
+ "r",
1501
+ "i"
1502
+ ],
1503
+ [
1504
+ "Ġp",
1505
+ "ro"
1506
+ ],
1507
+ [
1508
+ ";",
1509
+ "čĊ"
1510
+ ],
1511
+ [
1512
+ "ĉĉ",
1513
+ "ĉĉ"
1514
+ ],
1515
+ [
1516
+ "t",
1517
+ "er"
1518
+ ],
1519
+ [
1520
+ "a",
1521
+ "in"
1522
+ ],
1523
+ [
1524
+ "Ġ",
1525
+ "W"
1526
+ ],
1527
+ [
1528
+ "Ġ",
1529
+ "E"
1530
+ ],
1531
+ [
1532
+ "Ġc",
1533
+ "om"
1534
+ ],
1535
+ [
1536
+ "Ġre",
1537
+ "turn"
1538
+ ],
1539
+ [
1540
+ "ar",
1541
+ "t"
1542
+ ],
1543
+ [
1544
+ "Ġ",
1545
+ "H"
1546
+ ],
1547
+ [
1548
+ "a",
1549
+ "ck"
1550
+ ],
1551
+ [
1552
+ "im",
1553
+ "port"
1554
+ ],
1555
+ [
1556
+ "ub",
1557
+ "lic"
1558
+ ],
1559
+ [
1560
+ "Ġ",
1561
+ "or"
1562
+ ],
1563
+ [
1564
+ "e",
1565
+ "st"
1566
+ ],
1567
+ [
1568
+ "m",
1569
+ "ent"
1570
+ ],
1571
+ [
1572
+ "Ġ",
1573
+ "G"
1574
+ ],
1575
+ [
1576
+ "ab",
1577
+ "le"
1578
+ ],
1579
+ [
1580
+ "Ġ",
1581
+ "-"
1582
+ ],
1583
+ [
1584
+ "in",
1585
+ "e"
1586
+ ],
1587
+ [
1588
+ "il",
1589
+ "l"
1590
+ ],
1591
+ [
1592
+ "in",
1593
+ "d"
1594
+ ],
1595
+ [
1596
+ "er",
1597
+ "e"
1598
+ ],
1599
+ [
1600
+ ":",
1601
+ ":"
1602
+ ],
1603
+ [
1604
+ "it",
1605
+ "y"
1606
+ ],
1607
+ [
1608
+ "Ġ",
1609
+ "+"
1610
+ ],
1611
+ [
1612
+ "Ġt",
1613
+ "r"
1614
+ ],
1615
+ [
1616
+ "el",
1617
+ "f"
1618
+ ],
1619
+ [
1620
+ "ig",
1621
+ "ht"
1622
+ ],
1623
+ [
1624
+ "(",
1625
+ "'"
1626
+ ],
1627
+ [
1628
+ "or",
1629
+ "m"
1630
+ ],
1631
+ [
1632
+ "ul",
1633
+ "t"
1634
+ ],
1635
+ [
1636
+ "st",
1637
+ "r"
1638
+ ],
1639
+ [
1640
+ ".",
1641
+ "."
1642
+ ],
1643
+ [
1644
+ "\"",
1645
+ ","
1646
+ ],
1647
+ [
1648
+ "Ġy",
1649
+ "ou"
1650
+ ],
1651
+ [
1652
+ "y",
1653
+ "pe"
1654
+ ]
1655
+ ]
1656
+ }
1657
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,144 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "151643": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "151644": {
13
+ "content": "<|im_start|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "151645": {
21
+ "content": "<|im_end|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "151646": {
29
+ "content": "<|object_ref_start|>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "151647": {
37
+ "content": "<|object_ref_end|>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "151648": {
45
+ "content": "<|box_start|>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "151649": {
53
+ "content": "<|box_end|>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "151650": {
61
+ "content": "<|quad_start|>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "151651": {
69
+ "content": "<|quad_end|>",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "151652": {
77
+ "content": "<|vision_start|>",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "151653": {
85
+ "content": "<|vision_end|>",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "151654": {
93
+ "content": "<|vision_pad|>",
94
+ "lstrip": false,
95
+ "normalized": false,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "151655": {
101
+ "content": "<|image_pad|>",
102
+ "lstrip": false,
103
+ "normalized": false,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "151656": {
109
+ "content": "<|video_pad|>",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": true
115
+ }
116
+ },
117
+ "additional_special_tokens": [
118
+ "<|im_start|>",
119
+ "<|im_end|>",
120
+ "<|object_ref_start|>",
121
+ "<|object_ref_end|>",
122
+ "<|box_start|>",
123
+ "<|box_end|>",
124
+ "<|quad_start|>",
125
+ "<|quad_end|>",
126
+ "<|vision_start|>",
127
+ "<|vision_end|>",
128
+ "<|vision_pad|>",
129
+ "<|image_pad|>",
130
+ "<|video_pad|>"
131
+ ],
132
+ "bos_token": null,
133
+ "chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}",
134
+ "clean_up_tokenization_spaces": false,
135
+ "eos_token": "<|im_end|>",
136
+ "errors": "replace",
137
+ "model_max_length": 32768,
138
+ "pad_token": "<|endoftext|>",
139
+ "padding_side": "left",
140
+ "processor_class": "ColQwen2Processor",
141
+ "split_special_tokens": false,
142
+ "tokenizer_class": "Qwen2Tokenizer",
143
+ "unk_token": null
144
+ }