hf-transformers-bot commited on
Commit
90c0668
·
verified ·
1 Parent(s): 924f515

Add tiny processor fixture for testing

Browse files
.gitattributes CHANGED
@@ -33,3 +33,6 @@ 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
37
+ static/mf_logo.png filter=lfs diff=lfs merge=lfs -text
38
+ static/mf_main.png filter=lfs diff=lfs merge=lfs -text
chat_template.jinja ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {% if messages[0]['role'] != 'system' %}<|im_start|>system
2
+ You are Music Flamingo, a multimodal assistant for language and music. On each turn you receive an audio clip which contains music and optional text, you will receive at least one or both; use your world knowledge and reasoning to help the user with any task. Interpret the entirety of the content any input music--regardlenss of whether the user calls it audio, music, or sound.<|im_end|>
3
+ {% endif %}{% for m in messages if m['content'] is not none %}<|im_start|>{{ m['role'] }}
4
+ {% if m['content'] is string %}{{ m['content'] }}{% else %}{% set audio = namespace(found=False) %}{% set text_buf = namespace(v='') %}{% for c in m['content'] %}{% if c.get('type') == 'audio' or 'audio' in c %}{% set audio.found = True %}{% elif c.get('type') == 'text' or 'text' in c %}{% set text_buf.v = text_buf.v + c['text'] %}{% endif %}{% endfor %}{% if audio.found %}{{ '<sound>' }}{% endif %}{{ text_buf.v }}{% endif %}<|im_end|>
5
+ {% endfor %}{% if add_generation_prompt %}<|im_start|>assistant
6
+ {% endif %}
config.json ADDED
@@ -0,0 +1,95 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "MusicFlamingoForConditionalGeneration"
4
+ ],
5
+ "audio_bos_token_id": 151670,
6
+ "audio_config": {
7
+ "activation_dropout": 0.0,
8
+ "activation_function": "gelu",
9
+ "attention_dropout": 0.0,
10
+ "dropout": 0.0,
11
+ "hidden_size": 1280,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 5120,
14
+ "layerdrop": 0.0,
15
+ "max_source_positions": 1500,
16
+ "model_type": "audioflamingo3_encoder",
17
+ "num_attention_heads": 20,
18
+ "num_hidden_layers": 32,
19
+ "num_mel_bins": 128,
20
+ "scale_embedding": false
21
+ },
22
+ "audio_eos_token_id": 151671,
23
+ "audio_frame_step": 0.01,
24
+ "audio_token_id": 151667,
25
+ "dtype": "bfloat16",
26
+ "head_dim": 1280,
27
+ "max_position_embeddings": 1200,
28
+ "model_type": "musicflamingo",
29
+ "projector_bias": true,
30
+ "projector_hidden_act": "gelu",
31
+ "rope_parameters": {
32
+ "partial_rotary_factor": 0.2,
33
+ "rope_theta": 1200,
34
+ "rope_type": "default"
35
+ },
36
+ "text_config": {
37
+ "attention_dropout": 0.0,
38
+ "bos_token_id": 151668,
39
+ "eos_token_id": 151645,
40
+ "hidden_act": "silu",
41
+ "hidden_size": 3584,
42
+ "initializer_range": 0.02,
43
+ "intermediate_size": 18944,
44
+ "layer_types": [
45
+ "full_attention",
46
+ "full_attention",
47
+ "full_attention",
48
+ "full_attention",
49
+ "full_attention",
50
+ "full_attention",
51
+ "full_attention",
52
+ "full_attention",
53
+ "full_attention",
54
+ "full_attention",
55
+ "full_attention",
56
+ "full_attention",
57
+ "full_attention",
58
+ "full_attention",
59
+ "full_attention",
60
+ "full_attention",
61
+ "full_attention",
62
+ "full_attention",
63
+ "full_attention",
64
+ "full_attention",
65
+ "full_attention",
66
+ "full_attention",
67
+ "full_attention",
68
+ "full_attention",
69
+ "full_attention",
70
+ "full_attention",
71
+ "full_attention",
72
+ "full_attention"
73
+ ],
74
+ "max_position_embeddings": 32768,
75
+ "max_window_layers": 28,
76
+ "model_max_length": 32768,
77
+ "model_type": "qwen2",
78
+ "num_attention_heads": 28,
79
+ "num_hidden_layers": 28,
80
+ "num_key_value_heads": 4,
81
+ "pad_token_id": 151669,
82
+ "rms_norm_eps": 1e-06,
83
+ "rope_parameters": {
84
+ "rope_theta": 1000000.0,
85
+ "rope_type": "default"
86
+ },
87
+ "sliding_window": null,
88
+ "tie_word_embeddings": false,
89
+ "use_cache": false,
90
+ "use_sliding_window": false,
91
+ "vocab_size": 151672
92
+ },
93
+ "transformers_version": "5.6.0.dev0",
94
+ "vocab_size": 500
95
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151668,
3
+ "eos_token_id": 151645,
4
+ "max_new_tokens": 2048,
5
+ "pad_token_id": 151669,
6
+ "transformers_version": "5.6.0.dev0"
7
+ }
processor_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "audio_bos_token": "<|sound_bos|>",
3
+ "audio_eos_token": "<|sound_eos|>",
4
+ "audio_token": "<sound>",
5
+ "feature_extractor": {
6
+ "chunk_length": 30,
7
+ "dither": 0.0,
8
+ "feature_extractor_type": "WhisperFeatureExtractor",
9
+ "feature_size": 128,
10
+ "hop_length": 160,
11
+ "n_fft": 400,
12
+ "n_samples": 480000,
13
+ "nb_max_frames": 3000,
14
+ "padding_side": "right",
15
+ "padding_value": 0.0,
16
+ "return_attention_mask": true,
17
+ "sampling_rate": 16000
18
+ },
19
+ "max_audio_len": 1200,
20
+ "processor_class": "MusicFlamingoProcessor"
21
+ }
static/NVIDIA OneWay Noncommercial License_22Mar2022 (academic).docx ADDED
Binary file (20.7 kB). View file
 
static/NVIDIA-OneWay-Noncommercial-License_22Mar2022-academic.docx ADDED
Binary file (20.7 kB). View file
 
tokenizer.json ADDED
@@ -0,0 +1,1792 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "1.0",
3
+ "truncation": null,
4
+ "padding": null,
5
+ "added_tokens": [
6
+ {
7
+ "id": 500,
8
+ "content": "<|endoftext|>",
9
+ "single_word": false,
10
+ "lstrip": false,
11
+ "rstrip": false,
12
+ "normalized": false,
13
+ "special": true
14
+ },
15
+ {
16
+ "id": 501,
17
+ "content": "<|im_start|>",
18
+ "single_word": false,
19
+ "lstrip": false,
20
+ "rstrip": false,
21
+ "normalized": false,
22
+ "special": true
23
+ },
24
+ {
25
+ "id": 502,
26
+ "content": "<|im_end|>",
27
+ "single_word": false,
28
+ "lstrip": false,
29
+ "rstrip": false,
30
+ "normalized": false,
31
+ "special": true
32
+ },
33
+ {
34
+ "id": 503,
35
+ "content": "<|object_ref_start|>",
36
+ "single_word": false,
37
+ "lstrip": false,
38
+ "rstrip": false,
39
+ "normalized": false,
40
+ "special": true
41
+ },
42
+ {
43
+ "id": 504,
44
+ "content": "<|object_ref_end|>",
45
+ "single_word": false,
46
+ "lstrip": false,
47
+ "rstrip": false,
48
+ "normalized": false,
49
+ "special": true
50
+ },
51
+ {
52
+ "id": 505,
53
+ "content": "<|box_start|>",
54
+ "single_word": false,
55
+ "lstrip": false,
56
+ "rstrip": false,
57
+ "normalized": false,
58
+ "special": true
59
+ },
60
+ {
61
+ "id": 506,
62
+ "content": "<|box_end|>",
63
+ "single_word": false,
64
+ "lstrip": false,
65
+ "rstrip": false,
66
+ "normalized": false,
67
+ "special": true
68
+ },
69
+ {
70
+ "id": 507,
71
+ "content": "<|quad_start|>",
72
+ "single_word": false,
73
+ "lstrip": false,
74
+ "rstrip": false,
75
+ "normalized": false,
76
+ "special": true
77
+ },
78
+ {
79
+ "id": 508,
80
+ "content": "<|quad_end|>",
81
+ "single_word": false,
82
+ "lstrip": false,
83
+ "rstrip": false,
84
+ "normalized": false,
85
+ "special": true
86
+ },
87
+ {
88
+ "id": 509,
89
+ "content": "<|vision_start|>",
90
+ "single_word": false,
91
+ "lstrip": false,
92
+ "rstrip": false,
93
+ "normalized": false,
94
+ "special": true
95
+ },
96
+ {
97
+ "id": 510,
98
+ "content": "<|vision_end|>",
99
+ "single_word": false,
100
+ "lstrip": false,
101
+ "rstrip": false,
102
+ "normalized": false,
103
+ "special": true
104
+ },
105
+ {
106
+ "id": 511,
107
+ "content": "<|vision_pad|>",
108
+ "single_word": false,
109
+ "lstrip": false,
110
+ "rstrip": false,
111
+ "normalized": false,
112
+ "special": true
113
+ },
114
+ {
115
+ "id": 512,
116
+ "content": "<|image_pad|>",
117
+ "single_word": false,
118
+ "lstrip": false,
119
+ "rstrip": false,
120
+ "normalized": false,
121
+ "special": true
122
+ },
123
+ {
124
+ "id": 513,
125
+ "content": "<|video_pad|>",
126
+ "single_word": false,
127
+ "lstrip": false,
128
+ "rstrip": false,
129
+ "normalized": false,
130
+ "special": true
131
+ },
132
+ {
133
+ "id": 514,
134
+ "content": "<tool_call>",
135
+ "single_word": false,
136
+ "lstrip": false,
137
+ "rstrip": false,
138
+ "normalized": false,
139
+ "special": false
140
+ },
141
+ {
142
+ "id": 515,
143
+ "content": "</tool_call>",
144
+ "single_word": false,
145
+ "lstrip": false,
146
+ "rstrip": false,
147
+ "normalized": false,
148
+ "special": false
149
+ },
150
+ {
151
+ "id": 516,
152
+ "content": "<|fim_prefix|>",
153
+ "single_word": false,
154
+ "lstrip": false,
155
+ "rstrip": false,
156
+ "normalized": false,
157
+ "special": false
158
+ },
159
+ {
160
+ "id": 517,
161
+ "content": "<|fim_middle|>",
162
+ "single_word": false,
163
+ "lstrip": false,
164
+ "rstrip": false,
165
+ "normalized": false,
166
+ "special": false
167
+ },
168
+ {
169
+ "id": 518,
170
+ "content": "<|fim_suffix|>",
171
+ "single_word": false,
172
+ "lstrip": false,
173
+ "rstrip": false,
174
+ "normalized": false,
175
+ "special": false
176
+ },
177
+ {
178
+ "id": 519,
179
+ "content": "<|fim_pad|>",
180
+ "single_word": false,
181
+ "lstrip": false,
182
+ "rstrip": false,
183
+ "normalized": false,
184
+ "special": false
185
+ },
186
+ {
187
+ "id": 520,
188
+ "content": "<|repo_name|>",
189
+ "single_word": false,
190
+ "lstrip": false,
191
+ "rstrip": false,
192
+ "normalized": false,
193
+ "special": false
194
+ },
195
+ {
196
+ "id": 521,
197
+ "content": "<|file_sep|>",
198
+ "single_word": false,
199
+ "lstrip": false,
200
+ "rstrip": false,
201
+ "normalized": false,
202
+ "special": false
203
+ },
204
+ {
205
+ "id": 522,
206
+ "content": "<vila/sentinel>",
207
+ "single_word": false,
208
+ "lstrip": false,
209
+ "rstrip": false,
210
+ "normalized": false,
211
+ "special": true
212
+ },
213
+ {
214
+ "id": 523,
215
+ "content": "<speech>",
216
+ "single_word": false,
217
+ "lstrip": false,
218
+ "rstrip": false,
219
+ "normalized": false,
220
+ "special": true
221
+ },
222
+ {
223
+ "id": 524,
224
+ "content": "<sound>",
225
+ "single_word": false,
226
+ "lstrip": false,
227
+ "rstrip": false,
228
+ "normalized": false,
229
+ "special": true
230
+ },
231
+ {
232
+ "id": 525,
233
+ "content": "[BOS]",
234
+ "single_word": false,
235
+ "lstrip": false,
236
+ "rstrip": false,
237
+ "normalized": false,
238
+ "special": true
239
+ },
240
+ {
241
+ "id": 526,
242
+ "content": "[PAD]",
243
+ "single_word": false,
244
+ "lstrip": false,
245
+ "rstrip": false,
246
+ "normalized": false,
247
+ "special": true
248
+ },
249
+ {
250
+ "id": 527,
251
+ "content": "<|sound_bos|>",
252
+ "single_word": false,
253
+ "lstrip": false,
254
+ "rstrip": false,
255
+ "normalized": false,
256
+ "special": true
257
+ },
258
+ {
259
+ "id": 528,
260
+ "content": "<|sound_eos|>",
261
+ "single_word": false,
262
+ "lstrip": false,
263
+ "rstrip": false,
264
+ "normalized": false,
265
+ "special": true
266
+ }
267
+ ],
268
+ "normalizer": {
269
+ "type": "NFC"
270
+ },
271
+ "pre_tokenizer": {
272
+ "type": "Sequence",
273
+ "pretokenizers": [
274
+ {
275
+ "type": "Split",
276
+ "pattern": {
277
+ "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+"
278
+ },
279
+ "behavior": "Isolated",
280
+ "invert": false
281
+ },
282
+ {
283
+ "type": "ByteLevel",
284
+ "add_prefix_space": false,
285
+ "trim_offsets": true,
286
+ "use_regex": false
287
+ }
288
+ ]
289
+ },
290
+ "post_processor": {
291
+ "type": "ByteLevel",
292
+ "add_prefix_space": false,
293
+ "trim_offsets": false,
294
+ "use_regex": false
295
+ },
296
+ "decoder": {
297
+ "type": "ByteLevel",
298
+ "add_prefix_space": true,
299
+ "trim_offsets": true,
300
+ "use_regex": true
301
+ },
302
+ "model": {
303
+ "type": "BPE",
304
+ "dropout": null,
305
+ "unk_token": null,
306
+ "continuing_subword_prefix": "",
307
+ "end_of_word_suffix": "",
308
+ "fuse_unk": false,
309
+ "byte_fallback": false,
310
+ "ignore_merges": false,
311
+ "vocab": {
312
+ "!": 0,
313
+ "\"": 1,
314
+ "#": 2,
315
+ "$": 3,
316
+ "%": 4,
317
+ "&": 5,
318
+ "'": 6,
319
+ "(": 7,
320
+ ")": 8,
321
+ "*": 9,
322
+ "+": 10,
323
+ ",": 11,
324
+ "-": 12,
325
+ ".": 13,
326
+ "/": 14,
327
+ "0": 15,
328
+ "1": 16,
329
+ "2": 17,
330
+ "3": 18,
331
+ "4": 19,
332
+ "5": 20,
333
+ "6": 21,
334
+ "7": 22,
335
+ "8": 23,
336
+ "9": 24,
337
+ ":": 25,
338
+ ";": 26,
339
+ "<": 27,
340
+ "=": 28,
341
+ ">": 29,
342
+ "?": 30,
343
+ "@": 31,
344
+ "A": 32,
345
+ "B": 33,
346
+ "C": 34,
347
+ "D": 35,
348
+ "E": 36,
349
+ "F": 37,
350
+ "G": 38,
351
+ "H": 39,
352
+ "I": 40,
353
+ "J": 41,
354
+ "K": 42,
355
+ "L": 43,
356
+ "M": 44,
357
+ "N": 45,
358
+ "O": 46,
359
+ "P": 47,
360
+ "Q": 48,
361
+ "R": 49,
362
+ "S": 50,
363
+ "T": 51,
364
+ "U": 52,
365
+ "V": 53,
366
+ "W": 54,
367
+ "X": 55,
368
+ "Y": 56,
369
+ "Z": 57,
370
+ "[": 58,
371
+ "\\": 59,
372
+ "]": 60,
373
+ "^": 61,
374
+ "_": 62,
375
+ "`": 63,
376
+ "a": 64,
377
+ "b": 65,
378
+ "c": 66,
379
+ "d": 67,
380
+ "e": 68,
381
+ "f": 69,
382
+ "g": 70,
383
+ "h": 71,
384
+ "i": 72,
385
+ "j": 73,
386
+ "k": 74,
387
+ "l": 75,
388
+ "m": 76,
389
+ "n": 77,
390
+ "o": 78,
391
+ "p": 79,
392
+ "q": 80,
393
+ "r": 81,
394
+ "s": 82,
395
+ "t": 83,
396
+ "u": 84,
397
+ "v": 85,
398
+ "w": 86,
399
+ "x": 87,
400
+ "y": 88,
401
+ "z": 89,
402
+ "{": 90,
403
+ "|": 91,
404
+ "}": 92,
405
+ "~": 93,
406
+ "¡": 94,
407
+ "¢": 95,
408
+ "£": 96,
409
+ "¤": 97,
410
+ "¥": 98,
411
+ "¦": 99,
412
+ "§": 100,
413
+ "¨": 101,
414
+ "©": 102,
415
+ "ª": 103,
416
+ "«": 104,
417
+ "¬": 105,
418
+ "®": 106,
419
+ "¯": 107,
420
+ "°": 108,
421
+ "±": 109,
422
+ "²": 110,
423
+ "³": 111,
424
+ "´": 112,
425
+ "µ": 113,
426
+ "¶": 114,
427
+ "·": 115,
428
+ "¸": 116,
429
+ "¹": 117,
430
+ "º": 118,
431
+ "»": 119,
432
+ "¼": 120,
433
+ "½": 121,
434
+ "¾": 122,
435
+ "¿": 123,
436
+ "À": 124,
437
+ "Á": 125,
438
+ "Â": 126,
439
+ "Ã": 127,
440
+ "Ä": 128,
441
+ "Å": 129,
442
+ "Æ": 130,
443
+ "Ç": 131,
444
+ "È": 132,
445
+ "É": 133,
446
+ "Ê": 134,
447
+ "Ë": 135,
448
+ "Ì": 136,
449
+ "Í": 137,
450
+ "Î": 138,
451
+ "Ï": 139,
452
+ "Ð": 140,
453
+ "Ñ": 141,
454
+ "Ò": 142,
455
+ "Ó": 143,
456
+ "Ô": 144,
457
+ "Õ": 145,
458
+ "Ö": 146,
459
+ "×": 147,
460
+ "Ø": 148,
461
+ "Ù": 149,
462
+ "Ú": 150,
463
+ "Û": 151,
464
+ "Ü": 152,
465
+ "Ý": 153,
466
+ "Þ": 154,
467
+ "ß": 155,
468
+ "à": 156,
469
+ "á": 157,
470
+ "â": 158,
471
+ "ã": 159,
472
+ "ä": 160,
473
+ "å": 161,
474
+ "æ": 162,
475
+ "ç": 163,
476
+ "è": 164,
477
+ "é": 165,
478
+ "ê": 166,
479
+ "ë": 167,
480
+ "ì": 168,
481
+ "í": 169,
482
+ "î": 170,
483
+ "ï": 171,
484
+ "ð": 172,
485
+ "ñ": 173,
486
+ "ò": 174,
487
+ "ó": 175,
488
+ "ô": 176,
489
+ "õ": 177,
490
+ "ö": 178,
491
+ "÷": 179,
492
+ "ø": 180,
493
+ "ù": 181,
494
+ "ú": 182,
495
+ "û": 183,
496
+ "ü": 184,
497
+ "ý": 185,
498
+ "þ": 186,
499
+ "ÿ": 187,
500
+ "Ā": 188,
501
+ "ā": 189,
502
+ "Ă": 190,
503
+ "ă": 191,
504
+ "Ą": 192,
505
+ "ą": 193,
506
+ "Ć": 194,
507
+ "ć": 195,
508
+ "Ĉ": 196,
509
+ "ĉ": 197,
510
+ "Ċ": 198,
511
+ "ċ": 199,
512
+ "Č": 200,
513
+ "č": 201,
514
+ "Ď": 202,
515
+ "ď": 203,
516
+ "Đ": 204,
517
+ "đ": 205,
518
+ "Ē": 206,
519
+ "ē": 207,
520
+ "Ĕ": 208,
521
+ "ĕ": 209,
522
+ "Ė": 210,
523
+ "ė": 211,
524
+ "Ę": 212,
525
+ "ę": 213,
526
+ "Ě": 214,
527
+ "ě": 215,
528
+ "Ĝ": 216,
529
+ "ĝ": 217,
530
+ "Ğ": 218,
531
+ "ğ": 219,
532
+ "Ġ": 220,
533
+ "ġ": 221,
534
+ "Ģ": 222,
535
+ "ģ": 223,
536
+ "Ĥ": 224,
537
+ "ĥ": 225,
538
+ "Ħ": 226,
539
+ "ħ": 227,
540
+ "Ĩ": 228,
541
+ "ĩ": 229,
542
+ "Ī": 230,
543
+ "ī": 231,
544
+ "Ĭ": 232,
545
+ "ĭ": 233,
546
+ "Į": 234,
547
+ "į": 235,
548
+ "İ": 236,
549
+ "ı": 237,
550
+ "IJ": 238,
551
+ "ij": 239,
552
+ "Ĵ": 240,
553
+ "ĵ": 241,
554
+ "Ķ": 242,
555
+ "ķ": 243,
556
+ "ĸ": 244,
557
+ "Ĺ": 245,
558
+ "ĺ": 246,
559
+ "Ļ": 247,
560
+ "ļ": 248,
561
+ "Ľ": 249,
562
+ "ľ": 250,
563
+ "Ŀ": 251,
564
+ "ŀ": 252,
565
+ "Ł": 253,
566
+ "ł": 254,
567
+ "Ń": 255,
568
+ "ĠĠ": 256,
569
+ "ĠĠĠĠ": 257,
570
+ "in": 258,
571
+ "Ġt": 259,
572
+ "ĠĠĠĠĠĠĠĠ": 260,
573
+ "er": 261,
574
+ "ĠĠĠ": 262,
575
+ "on": 263,
576
+ "Ġa": 264,
577
+ "re": 265,
578
+ "at": 266,
579
+ "st": 267,
580
+ "en": 268,
581
+ "or": 269,
582
+ "Ġth": 270,
583
+ "ĊĊ": 271,
584
+ "Ġc": 272,
585
+ "le": 273,
586
+ "Ġs": 274,
587
+ "it": 275,
588
+ "an": 276,
589
+ "ar": 277,
590
+ "al": 278,
591
+ "Ġthe": 279,
592
+ ";Ċ": 280,
593
+ "Ġp": 281,
594
+ "Ġf": 282,
595
+ "ou": 283,
596
+ "Ġ=": 284,
597
+ "is": 285,
598
+ "ĠĠĠĠĠĠĠ": 286,
599
+ "ing": 287,
600
+ "es": 288,
601
+ "Ġw": 289,
602
+ "ion": 290,
603
+ "ed": 291,
604
+ "ic": 292,
605
+ "Ġb": 293,
606
+ "Ġd": 294,
607
+ "et": 295,
608
+ "Ġm": 296,
609
+ "Ġo": 297,
610
+ "ĉĉ": 298,
611
+ "ro": 299,
612
+ "as": 300,
613
+ "el": 301,
614
+ "ct": 302,
615
+ "nd": 303,
616
+ "Ġin": 304,
617
+ "Ġh": 305,
618
+ "ent": 306,
619
+ "id": 307,
620
+ "Ġn": 308,
621
+ "am": 309,
622
+ "ĠĠĠĠĠĠĠĠĠĠĠ": 310,
623
+ "Ġto": 311,
624
+ "Ġre": 312,
625
+ "--": 313,
626
+ "Ġ{": 314,
627
+ "Ġof": 315,
628
+ "om": 316,
629
+ ");Ċ": 317,
630
+ "im": 318,
631
+ "čĊ": 319,
632
+ "Ġ(": 320,
633
+ "il": 321,
634
+ "//": 322,
635
+ "Ġand": 323,
636
+ "ur": 324,
637
+ "se": 325,
638
+ "Ġl": 326,
639
+ "ex": 327,
640
+ "ĠS": 328,
641
+ "ad": 329,
642
+ "Ġ\"": 330,
643
+ "ch": 331,
644
+ "ut": 332,
645
+ "if": 333,
646
+ "**": 334,
647
+ "Ġ}": 335,
648
+ "em": 336,
649
+ "ol": 337,
650
+ "ĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠ": 338,
651
+ "th": 339,
652
+ ")Ċ": 340,
653
+ "Ġ{Ċ": 341,
654
+ "Ġg": 342,
655
+ "ig": 343,
656
+ "iv": 344,
657
+ ",Ċ": 345,
658
+ "ce": 346,
659
+ "od": 347,
660
+ "Ġv": 348,
661
+ "ate": 349,
662
+ "ĠT": 350,
663
+ "ag": 351,
664
+ "ay": 352,
665
+ "Ġ*": 353,
666
+ "ot": 354,
667
+ "us": 355,
668
+ "ĠC": 356,
669
+ "Ġst": 357,
670
+ "ĠI": 358,
671
+ "un": 359,
672
+ "ul": 360,
673
+ "ue": 361,
674
+ "ĠA": 362,
675
+ "ow": 363,
676
+ "Ġ'": 364,
677
+ "ew": 365,
678
+ "Ġ<": 366,
679
+ "ation": 367,
680
+ "()": 368,
681
+ "Ġfor": 369,
682
+ "ab": 370,
683
+ "ort": 371,
684
+ "um": 372,
685
+ "ame": 373,
686
+ "Ġis": 374,
687
+ "pe": 375,
688
+ "tr": 376,
689
+ "ck": 377,
690
+ "âĢ": 378,
691
+ "Ġy": 379,
692
+ "ist": 380,
693
+ "----": 381,
694
+ ".ĊĊ": 382,
695
+ "he": 383,
696
+ "Ġe": 384,
697
+ "lo": 385,
698
+ "ĠM": 386,
699
+ "Ġbe": 387,
700
+ "ers": 388,
701
+ "Ġon": 389,
702
+ "Ġcon": 390,
703
+ "ap": 391,
704
+ "ub": 392,
705
+ "ĠP": 393,
706
+ "ĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠ": 394,
707
+ "ass": 395,
708
+ "int": 396,
709
+ ">Ċ": 397,
710
+ "ly": 398,
711
+ "urn": 399,
712
+ "Ġ$": 400,
713
+ ";ĊĊ": 401,
714
+ "av": 402,
715
+ "port": 403,
716
+ "ir": 404,
717
+ "->": 405,
718
+ "nt": 406,
719
+ "ction": 407,
720
+ "end": 408,
721
+ "Ġde": 409,
722
+ "ith": 410,
723
+ "out": 411,
724
+ "turn": 412,
725
+ "our": 413,
726
+ "ĠĠĠĠĠ": 414,
727
+ "lic": 415,
728
+ "res": 416,
729
+ "pt": 417,
730
+ "==": 418,
731
+ "Ġthis": 419,
732
+ "Ġwh": 420,
733
+ "Ġif": 421,
734
+ "ĠD": 422,
735
+ "ver": 423,
736
+ "age": 424,
737
+ "ĠB": 425,
738
+ "ht": 426,
739
+ "ext": 427,
740
+ "=\"": 428,
741
+ "Ġthat": 429,
742
+ "****": 430,
743
+ "ĠR": 431,
744
+ "Ġit": 432,
745
+ "ess": 433,
746
+ "ĠF": 434,
747
+ "Ġr": 435,
748
+ "os": 436,
749
+ "and": 437,
750
+ "Ġas": 438,
751
+ "ect": 439,
752
+ "ke": 440,
753
+ "rom": 441,
754
+ "Ġ//": 442,
755
+ "con": 443,
756
+ "ĠL": 444,
757
+ "(\"": 445,
758
+ "qu": 446,
759
+ "lass": 447,
760
+ "Ġwith": 448,
761
+ "iz": 449,
762
+ "de": 450,
763
+ "ĠN": 451,
764
+ "Ġal": 452,
765
+ "op": 453,
766
+ "up": 454,
767
+ "get": 455,
768
+ "Ġ}Ċ": 456,
769
+ "ile": 457,
770
+ "Ġan": 458,
771
+ "ata": 459,
772
+ "ore": 460,
773
+ "ri": 461,
774
+ "Ġpro": 462,
775
+ ";čĊ": 463,
776
+ "ĉĉĉĉ": 464,
777
+ "ter": 465,
778
+ "ain": 466,
779
+ "ĠW": 467,
780
+ "ĠE": 468,
781
+ "Ġcom": 469,
782
+ "Ġreturn": 470,
783
+ "art": 471,
784
+ "ĠH": 472,
785
+ "ack": 473,
786
+ "import": 474,
787
+ "ublic": 475,
788
+ "Ġor": 476,
789
+ "est": 477,
790
+ "ment": 478,
791
+ "ĠG": 479,
792
+ "able": 480,
793
+ "Ġ-": 481,
794
+ "ine": 482,
795
+ "ill": 483,
796
+ "ind": 484,
797
+ "ere": 485,
798
+ "::": 486,
799
+ "ity": 487,
800
+ "Ġ+": 488,
801
+ "Ġtr": 489,
802
+ "elf": 490,
803
+ "ight": 491,
804
+ "('": 492,
805
+ "orm": 493,
806
+ "ult": 494,
807
+ "str": 495,
808
+ "..": 496,
809
+ "\",": 497,
810
+ "Ġyou": 498,
811
+ "ype": 499
812
+ },
813
+ "merges": [
814
+ [
815
+ "Ġ",
816
+ "Ġ"
817
+ ],
818
+ [
819
+ "ĠĠ",
820
+ "ĠĠ"
821
+ ],
822
+ [
823
+ "i",
824
+ "n"
825
+ ],
826
+ [
827
+ "Ġ",
828
+ "t"
829
+ ],
830
+ [
831
+ "ĠĠĠĠ",
832
+ "ĠĠĠĠ"
833
+ ],
834
+ [
835
+ "e",
836
+ "r"
837
+ ],
838
+ [
839
+ "ĠĠ",
840
+ "Ġ"
841
+ ],
842
+ [
843
+ "o",
844
+ "n"
845
+ ],
846
+ [
847
+ "Ġ",
848
+ "a"
849
+ ],
850
+ [
851
+ "r",
852
+ "e"
853
+ ],
854
+ [
855
+ "a",
856
+ "t"
857
+ ],
858
+ [
859
+ "s",
860
+ "t"
861
+ ],
862
+ [
863
+ "e",
864
+ "n"
865
+ ],
866
+ [
867
+ "o",
868
+ "r"
869
+ ],
870
+ [
871
+ "Ġt",
872
+ "h"
873
+ ],
874
+ [
875
+ "Ċ",
876
+ "Ċ"
877
+ ],
878
+ [
879
+ "Ġ",
880
+ "c"
881
+ ],
882
+ [
883
+ "l",
884
+ "e"
885
+ ],
886
+ [
887
+ "Ġ",
888
+ "s"
889
+ ],
890
+ [
891
+ "i",
892
+ "t"
893
+ ],
894
+ [
895
+ "a",
896
+ "n"
897
+ ],
898
+ [
899
+ "a",
900
+ "r"
901
+ ],
902
+ [
903
+ "a",
904
+ "l"
905
+ ],
906
+ [
907
+ "Ġth",
908
+ "e"
909
+ ],
910
+ [
911
+ ";",
912
+ "Ċ"
913
+ ],
914
+ [
915
+ "Ġ",
916
+ "p"
917
+ ],
918
+ [
919
+ "Ġ",
920
+ "f"
921
+ ],
922
+ [
923
+ "o",
924
+ "u"
925
+ ],
926
+ [
927
+ "Ġ",
928
+ "="
929
+ ],
930
+ [
931
+ "i",
932
+ "s"
933
+ ],
934
+ [
935
+ "ĠĠĠĠ",
936
+ "ĠĠĠ"
937
+ ],
938
+ [
939
+ "in",
940
+ "g"
941
+ ],
942
+ [
943
+ "e",
944
+ "s"
945
+ ],
946
+ [
947
+ "Ġ",
948
+ "w"
949
+ ],
950
+ [
951
+ "i",
952
+ "on"
953
+ ],
954
+ [
955
+ "e",
956
+ "d"
957
+ ],
958
+ [
959
+ "i",
960
+ "c"
961
+ ],
962
+ [
963
+ "Ġ",
964
+ "b"
965
+ ],
966
+ [
967
+ "Ġ",
968
+ "d"
969
+ ],
970
+ [
971
+ "e",
972
+ "t"
973
+ ],
974
+ [
975
+ "Ġ",
976
+ "m"
977
+ ],
978
+ [
979
+ "Ġ",
980
+ "o"
981
+ ],
982
+ [
983
+ "ĉ",
984
+ "ĉ"
985
+ ],
986
+ [
987
+ "r",
988
+ "o"
989
+ ],
990
+ [
991
+ "a",
992
+ "s"
993
+ ],
994
+ [
995
+ "e",
996
+ "l"
997
+ ],
998
+ [
999
+ "c",
1000
+ "t"
1001
+ ],
1002
+ [
1003
+ "n",
1004
+ "d"
1005
+ ],
1006
+ [
1007
+ "Ġ",
1008
+ "in"
1009
+ ],
1010
+ [
1011
+ "Ġ",
1012
+ "h"
1013
+ ],
1014
+ [
1015
+ "en",
1016
+ "t"
1017
+ ],
1018
+ [
1019
+ "i",
1020
+ "d"
1021
+ ],
1022
+ [
1023
+ "Ġ",
1024
+ "n"
1025
+ ],
1026
+ [
1027
+ "a",
1028
+ "m"
1029
+ ],
1030
+ [
1031
+ "ĠĠĠĠĠĠĠĠ",
1032
+ "ĠĠĠ"
1033
+ ],
1034
+ [
1035
+ "Ġt",
1036
+ "o"
1037
+ ],
1038
+ [
1039
+ "Ġ",
1040
+ "re"
1041
+ ],
1042
+ [
1043
+ "-",
1044
+ "-"
1045
+ ],
1046
+ [
1047
+ "Ġ",
1048
+ "{"
1049
+ ],
1050
+ [
1051
+ "Ġo",
1052
+ "f"
1053
+ ],
1054
+ [
1055
+ "o",
1056
+ "m"
1057
+ ],
1058
+ [
1059
+ ")",
1060
+ ";Ċ"
1061
+ ],
1062
+ [
1063
+ "i",
1064
+ "m"
1065
+ ],
1066
+ [
1067
+ "č",
1068
+ "Ċ"
1069
+ ],
1070
+ [
1071
+ "Ġ",
1072
+ "("
1073
+ ],
1074
+ [
1075
+ "i",
1076
+ "l"
1077
+ ],
1078
+ [
1079
+ "/",
1080
+ "/"
1081
+ ],
1082
+ [
1083
+ "Ġa",
1084
+ "nd"
1085
+ ],
1086
+ [
1087
+ "u",
1088
+ "r"
1089
+ ],
1090
+ [
1091
+ "s",
1092
+ "e"
1093
+ ],
1094
+ [
1095
+ "Ġ",
1096
+ "l"
1097
+ ],
1098
+ [
1099
+ "e",
1100
+ "x"
1101
+ ],
1102
+ [
1103
+ "Ġ",
1104
+ "S"
1105
+ ],
1106
+ [
1107
+ "a",
1108
+ "d"
1109
+ ],
1110
+ [
1111
+ "Ġ",
1112
+ "\""
1113
+ ],
1114
+ [
1115
+ "c",
1116
+ "h"
1117
+ ],
1118
+ [
1119
+ "u",
1120
+ "t"
1121
+ ],
1122
+ [
1123
+ "i",
1124
+ "f"
1125
+ ],
1126
+ [
1127
+ "*",
1128
+ "*"
1129
+ ],
1130
+ [
1131
+ "Ġ",
1132
+ "}"
1133
+ ],
1134
+ [
1135
+ "e",
1136
+ "m"
1137
+ ],
1138
+ [
1139
+ "o",
1140
+ "l"
1141
+ ],
1142
+ [
1143
+ "ĠĠĠĠĠĠĠĠ",
1144
+ "ĠĠĠĠĠĠĠĠ"
1145
+ ],
1146
+ [
1147
+ "t",
1148
+ "h"
1149
+ ],
1150
+ [
1151
+ ")",
1152
+ "Ċ"
1153
+ ],
1154
+ [
1155
+ "Ġ{",
1156
+ "Ċ"
1157
+ ],
1158
+ [
1159
+ "Ġ",
1160
+ "g"
1161
+ ],
1162
+ [
1163
+ "i",
1164
+ "g"
1165
+ ],
1166
+ [
1167
+ "i",
1168
+ "v"
1169
+ ],
1170
+ [
1171
+ ",",
1172
+ "Ċ"
1173
+ ],
1174
+ [
1175
+ "c",
1176
+ "e"
1177
+ ],
1178
+ [
1179
+ "o",
1180
+ "d"
1181
+ ],
1182
+ [
1183
+ "Ġ",
1184
+ "v"
1185
+ ],
1186
+ [
1187
+ "at",
1188
+ "e"
1189
+ ],
1190
+ [
1191
+ "Ġ",
1192
+ "T"
1193
+ ],
1194
+ [
1195
+ "a",
1196
+ "g"
1197
+ ],
1198
+ [
1199
+ "a",
1200
+ "y"
1201
+ ],
1202
+ [
1203
+ "Ġ",
1204
+ "*"
1205
+ ],
1206
+ [
1207
+ "o",
1208
+ "t"
1209
+ ],
1210
+ [
1211
+ "u",
1212
+ "s"
1213
+ ],
1214
+ [
1215
+ "Ġ",
1216
+ "C"
1217
+ ],
1218
+ [
1219
+ "Ġ",
1220
+ "st"
1221
+ ],
1222
+ [
1223
+ "Ġ",
1224
+ "I"
1225
+ ],
1226
+ [
1227
+ "u",
1228
+ "n"
1229
+ ],
1230
+ [
1231
+ "u",
1232
+ "l"
1233
+ ],
1234
+ [
1235
+ "u",
1236
+ "e"
1237
+ ],
1238
+ [
1239
+ "Ġ",
1240
+ "A"
1241
+ ],
1242
+ [
1243
+ "o",
1244
+ "w"
1245
+ ],
1246
+ [
1247
+ "Ġ",
1248
+ "'"
1249
+ ],
1250
+ [
1251
+ "e",
1252
+ "w"
1253
+ ],
1254
+ [
1255
+ "Ġ",
1256
+ "<"
1257
+ ],
1258
+ [
1259
+ "at",
1260
+ "ion"
1261
+ ],
1262
+ [
1263
+ "(",
1264
+ ")"
1265
+ ],
1266
+ [
1267
+ "Ġf",
1268
+ "or"
1269
+ ],
1270
+ [
1271
+ "a",
1272
+ "b"
1273
+ ],
1274
+ [
1275
+ "or",
1276
+ "t"
1277
+ ],
1278
+ [
1279
+ "u",
1280
+ "m"
1281
+ ],
1282
+ [
1283
+ "am",
1284
+ "e"
1285
+ ],
1286
+ [
1287
+ "Ġ",
1288
+ "is"
1289
+ ],
1290
+ [
1291
+ "p",
1292
+ "e"
1293
+ ],
1294
+ [
1295
+ "t",
1296
+ "r"
1297
+ ],
1298
+ [
1299
+ "c",
1300
+ "k"
1301
+ ],
1302
+ [
1303
+ "â",
1304
+ "Ģ"
1305
+ ],
1306
+ [
1307
+ "Ġ",
1308
+ "y"
1309
+ ],
1310
+ [
1311
+ "i",
1312
+ "st"
1313
+ ],
1314
+ [
1315
+ "--",
1316
+ "--"
1317
+ ],
1318
+ [
1319
+ ".",
1320
+ "ĊĊ"
1321
+ ],
1322
+ [
1323
+ "h",
1324
+ "e"
1325
+ ],
1326
+ [
1327
+ "Ġ",
1328
+ "e"
1329
+ ],
1330
+ [
1331
+ "l",
1332
+ "o"
1333
+ ],
1334
+ [
1335
+ "Ġ",
1336
+ "M"
1337
+ ],
1338
+ [
1339
+ "Ġb",
1340
+ "e"
1341
+ ],
1342
+ [
1343
+ "er",
1344
+ "s"
1345
+ ],
1346
+ [
1347
+ "Ġ",
1348
+ "on"
1349
+ ],
1350
+ [
1351
+ "Ġc",
1352
+ "on"
1353
+ ],
1354
+ [
1355
+ "a",
1356
+ "p"
1357
+ ],
1358
+ [
1359
+ "u",
1360
+ "b"
1361
+ ],
1362
+ [
1363
+ "Ġ",
1364
+ "P"
1365
+ ],
1366
+ [
1367
+ "ĠĠĠĠĠĠĠĠ",
1368
+ "ĠĠĠĠĠĠĠ"
1369
+ ],
1370
+ [
1371
+ "as",
1372
+ "s"
1373
+ ],
1374
+ [
1375
+ "in",
1376
+ "t"
1377
+ ],
1378
+ [
1379
+ ">",
1380
+ "Ċ"
1381
+ ],
1382
+ [
1383
+ "l",
1384
+ "y"
1385
+ ],
1386
+ [
1387
+ "ur",
1388
+ "n"
1389
+ ],
1390
+ [
1391
+ "Ġ",
1392
+ "$"
1393
+ ],
1394
+ [
1395
+ ";",
1396
+ "ĊĊ"
1397
+ ],
1398
+ [
1399
+ "a",
1400
+ "v"
1401
+ ],
1402
+ [
1403
+ "p",
1404
+ "ort"
1405
+ ],
1406
+ [
1407
+ "i",
1408
+ "r"
1409
+ ],
1410
+ [
1411
+ "-",
1412
+ ">"
1413
+ ],
1414
+ [
1415
+ "n",
1416
+ "t"
1417
+ ],
1418
+ [
1419
+ "ct",
1420
+ "ion"
1421
+ ],
1422
+ [
1423
+ "en",
1424
+ "d"
1425
+ ],
1426
+ [
1427
+ "Ġd",
1428
+ "e"
1429
+ ],
1430
+ [
1431
+ "it",
1432
+ "h"
1433
+ ],
1434
+ [
1435
+ "ou",
1436
+ "t"
1437
+ ],
1438
+ [
1439
+ "t",
1440
+ "urn"
1441
+ ],
1442
+ [
1443
+ "ou",
1444
+ "r"
1445
+ ],
1446
+ [
1447
+ "ĠĠĠĠ",
1448
+ "Ġ"
1449
+ ],
1450
+ [
1451
+ "l",
1452
+ "ic"
1453
+ ],
1454
+ [
1455
+ "re",
1456
+ "s"
1457
+ ],
1458
+ [
1459
+ "p",
1460
+ "t"
1461
+ ],
1462
+ [
1463
+ "=",
1464
+ "="
1465
+ ],
1466
+ [
1467
+ "Ġth",
1468
+ "is"
1469
+ ],
1470
+ [
1471
+ "Ġw",
1472
+ "h"
1473
+ ],
1474
+ [
1475
+ "Ġ",
1476
+ "if"
1477
+ ],
1478
+ [
1479
+ "Ġ",
1480
+ "D"
1481
+ ],
1482
+ [
1483
+ "v",
1484
+ "er"
1485
+ ],
1486
+ [
1487
+ "ag",
1488
+ "e"
1489
+ ],
1490
+ [
1491
+ "Ġ",
1492
+ "B"
1493
+ ],
1494
+ [
1495
+ "h",
1496
+ "t"
1497
+ ],
1498
+ [
1499
+ "ex",
1500
+ "t"
1501
+ ],
1502
+ [
1503
+ "=",
1504
+ "\""
1505
+ ],
1506
+ [
1507
+ "Ġth",
1508
+ "at"
1509
+ ],
1510
+ [
1511
+ "**",
1512
+ "**"
1513
+ ],
1514
+ [
1515
+ "Ġ",
1516
+ "R"
1517
+ ],
1518
+ [
1519
+ "Ġ",
1520
+ "it"
1521
+ ],
1522
+ [
1523
+ "es",
1524
+ "s"
1525
+ ],
1526
+ [
1527
+ "Ġ",
1528
+ "F"
1529
+ ],
1530
+ [
1531
+ "Ġ",
1532
+ "r"
1533
+ ],
1534
+ [
1535
+ "o",
1536
+ "s"
1537
+ ],
1538
+ [
1539
+ "an",
1540
+ "d"
1541
+ ],
1542
+ [
1543
+ "Ġa",
1544
+ "s"
1545
+ ],
1546
+ [
1547
+ "e",
1548
+ "ct"
1549
+ ],
1550
+ [
1551
+ "k",
1552
+ "e"
1553
+ ],
1554
+ [
1555
+ "ro",
1556
+ "m"
1557
+ ],
1558
+ [
1559
+ "Ġ",
1560
+ "//"
1561
+ ],
1562
+ [
1563
+ "c",
1564
+ "on"
1565
+ ],
1566
+ [
1567
+ "Ġ",
1568
+ "L"
1569
+ ],
1570
+ [
1571
+ "(",
1572
+ "\""
1573
+ ],
1574
+ [
1575
+ "q",
1576
+ "u"
1577
+ ],
1578
+ [
1579
+ "l",
1580
+ "ass"
1581
+ ],
1582
+ [
1583
+ "Ġw",
1584
+ "ith"
1585
+ ],
1586
+ [
1587
+ "i",
1588
+ "z"
1589
+ ],
1590
+ [
1591
+ "d",
1592
+ "e"
1593
+ ],
1594
+ [
1595
+ "Ġ",
1596
+ "N"
1597
+ ],
1598
+ [
1599
+ "Ġa",
1600
+ "l"
1601
+ ],
1602
+ [
1603
+ "o",
1604
+ "p"
1605
+ ],
1606
+ [
1607
+ "u",
1608
+ "p"
1609
+ ],
1610
+ [
1611
+ "g",
1612
+ "et"
1613
+ ],
1614
+ [
1615
+ "Ġ}",
1616
+ "Ċ"
1617
+ ],
1618
+ [
1619
+ "i",
1620
+ "le"
1621
+ ],
1622
+ [
1623
+ "Ġa",
1624
+ "n"
1625
+ ],
1626
+ [
1627
+ "at",
1628
+ "a"
1629
+ ],
1630
+ [
1631
+ "o",
1632
+ "re"
1633
+ ],
1634
+ [
1635
+ "r",
1636
+ "i"
1637
+ ],
1638
+ [
1639
+ "Ġp",
1640
+ "ro"
1641
+ ],
1642
+ [
1643
+ ";",
1644
+ "čĊ"
1645
+ ],
1646
+ [
1647
+ "ĉĉ",
1648
+ "ĉĉ"
1649
+ ],
1650
+ [
1651
+ "t",
1652
+ "er"
1653
+ ],
1654
+ [
1655
+ "a",
1656
+ "in"
1657
+ ],
1658
+ [
1659
+ "Ġ",
1660
+ "W"
1661
+ ],
1662
+ [
1663
+ "Ġ",
1664
+ "E"
1665
+ ],
1666
+ [
1667
+ "Ġc",
1668
+ "om"
1669
+ ],
1670
+ [
1671
+ "Ġre",
1672
+ "turn"
1673
+ ],
1674
+ [
1675
+ "ar",
1676
+ "t"
1677
+ ],
1678
+ [
1679
+ "Ġ",
1680
+ "H"
1681
+ ],
1682
+ [
1683
+ "a",
1684
+ "ck"
1685
+ ],
1686
+ [
1687
+ "im",
1688
+ "port"
1689
+ ],
1690
+ [
1691
+ "ub",
1692
+ "lic"
1693
+ ],
1694
+ [
1695
+ "Ġ",
1696
+ "or"
1697
+ ],
1698
+ [
1699
+ "e",
1700
+ "st"
1701
+ ],
1702
+ [
1703
+ "m",
1704
+ "ent"
1705
+ ],
1706
+ [
1707
+ "Ġ",
1708
+ "G"
1709
+ ],
1710
+ [
1711
+ "ab",
1712
+ "le"
1713
+ ],
1714
+ [
1715
+ "Ġ",
1716
+ "-"
1717
+ ],
1718
+ [
1719
+ "in",
1720
+ "e"
1721
+ ],
1722
+ [
1723
+ "il",
1724
+ "l"
1725
+ ],
1726
+ [
1727
+ "in",
1728
+ "d"
1729
+ ],
1730
+ [
1731
+ "er",
1732
+ "e"
1733
+ ],
1734
+ [
1735
+ ":",
1736
+ ":"
1737
+ ],
1738
+ [
1739
+ "it",
1740
+ "y"
1741
+ ],
1742
+ [
1743
+ "Ġ",
1744
+ "+"
1745
+ ],
1746
+ [
1747
+ "Ġt",
1748
+ "r"
1749
+ ],
1750
+ [
1751
+ "el",
1752
+ "f"
1753
+ ],
1754
+ [
1755
+ "ig",
1756
+ "ht"
1757
+ ],
1758
+ [
1759
+ "(",
1760
+ "'"
1761
+ ],
1762
+ [
1763
+ "or",
1764
+ "m"
1765
+ ],
1766
+ [
1767
+ "ul",
1768
+ "t"
1769
+ ],
1770
+ [
1771
+ "st",
1772
+ "r"
1773
+ ],
1774
+ [
1775
+ ".",
1776
+ "."
1777
+ ],
1778
+ [
1779
+ "\"",
1780
+ ","
1781
+ ],
1782
+ [
1783
+ "Ġy",
1784
+ "ou"
1785
+ ],
1786
+ [
1787
+ "y",
1788
+ "pe"
1789
+ ]
1790
+ ]
1791
+ }
1792
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,255 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "backend": "tokenizers",
4
+ "bos_token": "[BOS]",
5
+ "clean_up_tokenization_spaces": false,
6
+ "eos_token": "<|im_end|>",
7
+ "errors": "replace",
8
+ "extra_special_tokens": [
9
+ "<|sound_bos|>",
10
+ "<|sound_eos|>"
11
+ ],
12
+ "is_local": true,
13
+ "legacy": false,
14
+ "model_max_length": 32768,
15
+ "pad_token": "[PAD]",
16
+ "padding_side": "right",
17
+ "processor_class": "MusicFlamingoProcessor",
18
+ "split_special_tokens": false,
19
+ "tokenizer_class": "Qwen2Tokenizer",
20
+ "unk_token": null,
21
+ "added_tokens_decoder": {
22
+ "500": {
23
+ "content": "<|endoftext|>",
24
+ "single_word": false,
25
+ "lstrip": false,
26
+ "rstrip": false,
27
+ "normalized": false,
28
+ "special": true
29
+ },
30
+ "501": {
31
+ "content": "<|im_start|>",
32
+ "single_word": false,
33
+ "lstrip": false,
34
+ "rstrip": false,
35
+ "normalized": false,
36
+ "special": true
37
+ },
38
+ "502": {
39
+ "content": "<|im_end|>",
40
+ "single_word": false,
41
+ "lstrip": false,
42
+ "rstrip": false,
43
+ "normalized": false,
44
+ "special": true
45
+ },
46
+ "503": {
47
+ "content": "<|object_ref_start|>",
48
+ "single_word": false,
49
+ "lstrip": false,
50
+ "rstrip": false,
51
+ "normalized": false,
52
+ "special": true
53
+ },
54
+ "504": {
55
+ "content": "<|object_ref_end|>",
56
+ "single_word": false,
57
+ "lstrip": false,
58
+ "rstrip": false,
59
+ "normalized": false,
60
+ "special": true
61
+ },
62
+ "505": {
63
+ "content": "<|box_start|>",
64
+ "single_word": false,
65
+ "lstrip": false,
66
+ "rstrip": false,
67
+ "normalized": false,
68
+ "special": true
69
+ },
70
+ "506": {
71
+ "content": "<|box_end|>",
72
+ "single_word": false,
73
+ "lstrip": false,
74
+ "rstrip": false,
75
+ "normalized": false,
76
+ "special": true
77
+ },
78
+ "507": {
79
+ "content": "<|quad_start|>",
80
+ "single_word": false,
81
+ "lstrip": false,
82
+ "rstrip": false,
83
+ "normalized": false,
84
+ "special": true
85
+ },
86
+ "508": {
87
+ "content": "<|quad_end|>",
88
+ "single_word": false,
89
+ "lstrip": false,
90
+ "rstrip": false,
91
+ "normalized": false,
92
+ "special": true
93
+ },
94
+ "509": {
95
+ "content": "<|vision_start|>",
96
+ "single_word": false,
97
+ "lstrip": false,
98
+ "rstrip": false,
99
+ "normalized": false,
100
+ "special": true
101
+ },
102
+ "510": {
103
+ "content": "<|vision_end|>",
104
+ "single_word": false,
105
+ "lstrip": false,
106
+ "rstrip": false,
107
+ "normalized": false,
108
+ "special": true
109
+ },
110
+ "511": {
111
+ "content": "<|vision_pad|>",
112
+ "single_word": false,
113
+ "lstrip": false,
114
+ "rstrip": false,
115
+ "normalized": false,
116
+ "special": true
117
+ },
118
+ "512": {
119
+ "content": "<|image_pad|>",
120
+ "single_word": false,
121
+ "lstrip": false,
122
+ "rstrip": false,
123
+ "normalized": false,
124
+ "special": true
125
+ },
126
+ "513": {
127
+ "content": "<|video_pad|>",
128
+ "single_word": false,
129
+ "lstrip": false,
130
+ "rstrip": false,
131
+ "normalized": false,
132
+ "special": true
133
+ },
134
+ "514": {
135
+ "content": "<tool_call>",
136
+ "single_word": false,
137
+ "lstrip": false,
138
+ "rstrip": false,
139
+ "normalized": false,
140
+ "special": false
141
+ },
142
+ "515": {
143
+ "content": "</tool_call>",
144
+ "single_word": false,
145
+ "lstrip": false,
146
+ "rstrip": false,
147
+ "normalized": false,
148
+ "special": false
149
+ },
150
+ "516": {
151
+ "content": "<|fim_prefix|>",
152
+ "single_word": false,
153
+ "lstrip": false,
154
+ "rstrip": false,
155
+ "normalized": false,
156
+ "special": false
157
+ },
158
+ "517": {
159
+ "content": "<|fim_middle|>",
160
+ "single_word": false,
161
+ "lstrip": false,
162
+ "rstrip": false,
163
+ "normalized": false,
164
+ "special": false
165
+ },
166
+ "518": {
167
+ "content": "<|fim_suffix|>",
168
+ "single_word": false,
169
+ "lstrip": false,
170
+ "rstrip": false,
171
+ "normalized": false,
172
+ "special": false
173
+ },
174
+ "519": {
175
+ "content": "<|fim_pad|>",
176
+ "single_word": false,
177
+ "lstrip": false,
178
+ "rstrip": false,
179
+ "normalized": false,
180
+ "special": false
181
+ },
182
+ "520": {
183
+ "content": "<|repo_name|>",
184
+ "single_word": false,
185
+ "lstrip": false,
186
+ "rstrip": false,
187
+ "normalized": false,
188
+ "special": false
189
+ },
190
+ "521": {
191
+ "content": "<|file_sep|>",
192
+ "single_word": false,
193
+ "lstrip": false,
194
+ "rstrip": false,
195
+ "normalized": false,
196
+ "special": false
197
+ },
198
+ "522": {
199
+ "content": "<vila/sentinel>",
200
+ "single_word": false,
201
+ "lstrip": false,
202
+ "rstrip": false,
203
+ "normalized": false,
204
+ "special": true
205
+ },
206
+ "523": {
207
+ "content": "<speech>",
208
+ "single_word": false,
209
+ "lstrip": false,
210
+ "rstrip": false,
211
+ "normalized": false,
212
+ "special": true
213
+ },
214
+ "524": {
215
+ "content": "<sound>",
216
+ "single_word": false,
217
+ "lstrip": false,
218
+ "rstrip": false,
219
+ "normalized": false,
220
+ "special": true
221
+ },
222
+ "525": {
223
+ "content": "[BOS]",
224
+ "single_word": false,
225
+ "lstrip": false,
226
+ "rstrip": false,
227
+ "normalized": false,
228
+ "special": true
229
+ },
230
+ "526": {
231
+ "content": "[PAD]",
232
+ "single_word": false,
233
+ "lstrip": false,
234
+ "rstrip": false,
235
+ "normalized": false,
236
+ "special": true
237
+ },
238
+ "527": {
239
+ "content": "<|sound_bos|>",
240
+ "single_word": false,
241
+ "lstrip": false,
242
+ "rstrip": false,
243
+ "normalized": false,
244
+ "special": true
245
+ },
246
+ "528": {
247
+ "content": "<|sound_eos|>",
248
+ "single_word": false,
249
+ "lstrip": false,
250
+ "rstrip": false,
251
+ "normalized": false,
252
+ "special": true
253
+ }
254
+ }
255
+ }