Avihu commited on
Commit
99a4df9
·
1 Parent(s): f272034

update encoder bpe vocab

Browse files
config.json CHANGED
@@ -1,84 +1,94 @@
1
  {
 
 
 
2
  "auto_map": {
3
  "AutoConfig": "configuration_granite_speech_nar.GraniteSpeechNarConfig",
4
  "AutoFeatureExtractor": "feature_extraction_granite_speech_nar.GraniteSpeechNarFeatureExtractor",
5
- "AutoProcessor": "processing_granite_speech_nar.GraniteSpeechNarProcessor",
6
- "AutoModel": "modeling_granite_speech_nar.GraniteSpeechNarForASR"
7
  },
8
- "architectures": [
9
- "GraniteSpeechNarForASR"
10
- ],
11
- "model_type": "granite_speech_nar",
12
- "torch_dtype": "bfloat16",
13
  "encoder_config": {
14
- "model_type": "granite_speech_nar_encoder",
15
- "input_dim": 160,
16
- "num_layers": 16,
17
- "hidden_dim": 1024,
 
 
 
 
18
  "feedforward_mult": 4,
 
 
 
 
 
19
  "num_heads": 8,
20
- "dim_head": 128,
21
  "output_dim": 348,
22
- "context_size": 200,
23
- "max_pos_emb": 512,
24
- "dropout": 0.1,
25
  "pred_dropout": 0.25,
26
- "conv_kernel_size": 15,
27
- "conv_expansion_factor": 2,
28
- "self_conditioning_layer": 8,
29
- "bpe_output_dim": 100353,
30
- "bpe_pooling_window": 4,
31
- "initializer_range": 0.02
32
  },
 
 
 
 
 
 
 
 
 
33
  "projector_config": {
34
- "model_type": "granite_speech_nar_projector",
 
 
 
35
  "encoder_dim": 1024,
 
 
36
  "llm_dim": 2048,
37
- "downsample_rate": 5,
 
 
38
  "num_encoder_layers": 4,
39
- "hidden_size": 2048,
40
  "num_heads": 32,
41
- "num_layers": 2,
42
- "dropout_prob": 0.1,
43
- "block_size": 15,
44
- "mlp_ratio": 2,
45
- "layernorm_eps": 1e-06,
46
- "attn_bias": true,
47
- "mlp_bias": true
48
  },
 
49
  "text_config": {
50
- "model_type": "granite",
51
- "vocab_size": 100352,
 
 
 
 
 
 
 
52
  "hidden_size": 2048,
 
53
  "intermediate_size": 4096,
54
- "num_hidden_layers": 40,
 
 
 
55
  "num_attention_heads": 16,
 
56
  "num_key_value_heads": 4,
57
- "hidden_act": "silu",
58
- "max_position_embeddings": 4096,
59
- "initializer_range": 0.1,
60
- "rms_norm_eps": 1e-05,
61
- "use_cache": true,
62
  "pad_token_id": 100256,
63
- "bos_token_id": 100257,
64
- "eos_token_id": 100257,
65
- "tie_word_embeddings": true,
66
  "rope_parameters": {
67
  "rope_theta": 10000,
68
  "rope_type": "default"
69
  },
70
- "attention_bias": false,
71
- "attention_dropout": 0.0,
72
- "mlp_bias": false,
73
- "embedding_multiplier": 12,
74
- "logits_scaling": 8,
75
- "residual_multiplier": 0.22,
76
- "attention_multiplier": 0.0078125
77
  },
78
- "encoder_layer_indices": [4, 8, 12, -1],
79
- "scale_projected_embeddings": true,
80
- "blank_token_id": 100257,
81
- "min_edit_sequence_length": 8,
82
- "ce_loss_lambda": 0.0,
83
- "encoder_ctc_loss_lambda": 0.0
84
  }
 
1
  {
2
+ "architectures": [
3
+ "GraniteSpeechNarForASR"
4
+ ],
5
  "auto_map": {
6
  "AutoConfig": "configuration_granite_speech_nar.GraniteSpeechNarConfig",
7
  "AutoFeatureExtractor": "feature_extraction_granite_speech_nar.GraniteSpeechNarFeatureExtractor",
8
+ "AutoModel": "modeling_granite_speech_nar.GraniteSpeechNarForASR",
9
+ "AutoProcessor": "processing_granite_speech_nar.GraniteSpeechNarProcessor"
10
  },
11
+ "blank_token_id": 100257,
12
+ "ce_loss_lambda": 0.02,
13
+ "dtype": "bfloat16",
 
 
14
  "encoder_config": {
15
+ "blank_token_id": 100257,
16
+ "bpe_output_dim": 100352,
17
+ "bpe_pooling_window": 4,
18
+ "context_size": 200,
19
+ "conv_expansion_factor": 2,
20
+ "conv_kernel_size": 15,
21
+ "dim_head": 128,
22
+ "dropout": 0.1,
23
  "feedforward_mult": 4,
24
+ "hidden_dim": 1024,
25
+ "initializer_range": 0.02,
26
+ "input_dim": 160,
27
+ "max_pos_emb": 512,
28
+ "model_type": "granite_speech_nar_encoder",
29
  "num_heads": 8,
30
+ "num_layers": 16,
31
  "output_dim": 348,
 
 
 
32
  "pred_dropout": 0.25,
33
+ "self_conditioning_layer": 8
 
 
 
 
 
34
  },
35
+ "encoder_ctc_loss_lambda": 0.8,
36
+ "encoder_layer_indices": [
37
+ 4,
38
+ 8,
39
+ 12,
40
+ -1
41
+ ],
42
+ "min_edit_sequence_length": 8,
43
+ "model_type": "granite_speech_nar",
44
  "projector_config": {
45
+ "attn_bias": true,
46
+ "block_size": 15,
47
+ "downsample_rate": 5,
48
+ "dropout_prob": 0.1,
49
  "encoder_dim": 1024,
50
+ "hidden_size": 2048,
51
+ "layernorm_eps": 1e-06,
52
  "llm_dim": 2048,
53
+ "mlp_bias": true,
54
+ "mlp_ratio": 2,
55
+ "model_type": "granite_speech_nar_projector",
56
  "num_encoder_layers": 4,
 
57
  "num_heads": 32,
58
+ "num_layers": 2
 
 
 
 
 
 
59
  },
60
+ "scale_projected_embeddings": true,
61
  "text_config": {
62
+ "_name_or_path": "ibm-granite/granite-4.0-1b-base",
63
+ "attention_bias": false,
64
+ "attention_dropout": 0.0,
65
+ "attention_multiplier": 0.0078125,
66
+ "bos_token_id": 100257,
67
+ "dtype": "bfloat16",
68
+ "embedding_multiplier": 12,
69
+ "eos_token_id": 100257,
70
+ "hidden_act": "silu",
71
  "hidden_size": 2048,
72
+ "initializer_range": 0.1,
73
  "intermediate_size": 4096,
74
+ "logits_scaling": 8,
75
+ "max_position_embeddings": 4096,
76
+ "mlp_bias": false,
77
+ "model_type": "granite",
78
  "num_attention_heads": 16,
79
+ "num_hidden_layers": 40,
80
  "num_key_value_heads": 4,
 
 
 
 
 
81
  "pad_token_id": 100256,
82
+ "residual_multiplier": 0.22,
83
+ "rms_norm_eps": 1e-05,
 
84
  "rope_parameters": {
85
  "rope_theta": 10000,
86
  "rope_type": "default"
87
  },
88
+ "tie_word_embeddings": true,
89
+ "use_cache": true,
90
+ "vocab_size": 100352
 
 
 
 
91
  },
92
+ "tie_word_embeddings": true,
93
+ "transformers_version": "5.8.0.dev0"
 
 
 
 
94
  }
configuration_granite_speech_nar.py CHANGED
@@ -40,7 +40,7 @@ class GraniteSpeechNarEncoderConfig(PreTrainedConfig):
40
  Layer index at which self-conditioning (mid-layer CTC feedback) is applied.
41
  Defaults to `num_layers // 2`.
42
  bpe_output_dim (`int`, *optional*):
43
- Vocabulary size for the BPE CTC head (shifted by +1 for blank). If None, BPE head is disabled.
44
  bpe_pooling_window (`int`, *optional*, defaults to 4):
45
  Window size for posterior-weighted pooling before the BPE CTC head.
46
 
@@ -78,6 +78,7 @@ class GraniteSpeechNarEncoderConfig(PreTrainedConfig):
78
  self_conditioning_layer: int | None = None
79
  bpe_output_dim: int | None = None
80
  bpe_pooling_window: int = 4
 
81
  initializer_range: float = 0.02
82
 
83
  def __post_init__(self, **kwargs):
@@ -208,6 +209,9 @@ class GraniteSpeechNarConfig(PreTrainedConfig):
208
  if self.blank_token_id is None:
209
  self.blank_token_id = self.text_config.eos_token_id
210
 
 
 
 
211
  super().__post_init__(**kwargs)
212
 
213
 
 
40
  Layer index at which self-conditioning (mid-layer CTC feedback) is applied.
41
  Defaults to `num_layers // 2`.
42
  bpe_output_dim (`int`, *optional*):
43
+ Vocabulary size for the BPE CTC head (same as LLM vocab, blank reuses eos_token_id). If None, BPE head is disabled.
44
  bpe_pooling_window (`int`, *optional*, defaults to 4):
45
  Window size for posterior-weighted pooling before the BPE CTC head.
46
 
 
78
  self_conditioning_layer: int | None = None
79
  bpe_output_dim: int | None = None
80
  bpe_pooling_window: int = 4
81
+ blank_token_id: int | None = None
82
  initializer_range: float = 0.02
83
 
84
  def __post_init__(self, **kwargs):
 
209
  if self.blank_token_id is None:
210
  self.blank_token_id = self.text_config.eos_token_id
211
 
212
+ # Propagate blank_token_id to encoder config
213
+ self.encoder_config.blank_token_id = self.blank_token_id
214
+
215
  super().__post_init__(**kwargs)
216
 
217
 
merges.txt DELETED
The diff for this file is too large to render. See raw diff
 
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:668b9fb26c417a4a8b78e3b99cb2fa3c52335f2cdcaafe99a9ad76f19df04fbb
3
- size 4509384522
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a187681b05e9598028b6177bba4588a27a76b97ab6840870877d69e1770a5094
3
+ size 4509382472
modeling_granite_speech_nar.py CHANGED
@@ -834,10 +834,10 @@ class GraniteSpeechNarCTCEncoder(GraniteSpeechNarPreTrainedModel):
834
  loss = (
835
  F.ctc_loss(
836
  log_probs.transpose(0, 1),
837
- labels + 1,
838
  lengths,
839
  label_lengths,
840
- blank=0,
841
  reduction="sum",
842
  zero_infinity=True,
843
  )
@@ -944,10 +944,11 @@ class GraniteSpeechNarForASR(GraniteSpeechNarPreTrainedModel):
944
  bpe_logits_flat: torch.Tensor,
945
  bpe_lengths: list[int],
946
  ) -> list[torch.Tensor]:
947
- """GPU CTC greedy decode: argmax -> unique_consecutive -> remove blank -> shift."""
 
948
  preds_flat = bpe_logits_flat.argmax(dim=-1)
949
  per_sample = preds_flat.split(bpe_lengths)
950
- return [(collapsed := torch.unique_consecutive(seq))[collapsed != 0] - 1 for seq in per_sample]
951
 
952
  def _add_insertion_slots(self, token_ids: torch.Tensor) -> torch.Tensor:
953
  """Insert blank tokens between each CTC token as editing slots for the LLM."""
 
834
  loss = (
835
  F.ctc_loss(
836
  log_probs.transpose(0, 1),
837
+ labels,
838
  lengths,
839
  label_lengths,
840
+ blank=self.config.blank_token_id,
841
  reduction="sum",
842
  zero_infinity=True,
843
  )
 
944
  bpe_logits_flat: torch.Tensor,
945
  bpe_lengths: list[int],
946
  ) -> list[torch.Tensor]:
947
+ """GPU CTC greedy decode: argmax -> unique_consecutive -> remove blank."""
948
+ blank_id = self.config.blank_token_id
949
  preds_flat = bpe_logits_flat.argmax(dim=-1)
950
  per_sample = preds_flat.split(bpe_lengths)
951
+ return [(collapsed := torch.unique_consecutive(seq))[collapsed != blank_id] for seq in per_sample]
952
 
953
  def _add_insertion_slots(self, token_ids: torch.Tensor) -> torch.Tensor:
954
  """Insert blank tokens between each CTC token as editing slots for the LLM."""
processing_granite_speech_nar.py CHANGED
@@ -26,7 +26,6 @@ if is_torch_available():
26
  class GraniteSpeechNarProcessor(ProcessorMixin):
27
  """Processor combining audio feature extraction and tokenizer for GraniteSpeechNar."""
28
 
29
- feature_extractor_class = "AutoFeatureExtractor"
30
  tokenizer_class = "AutoTokenizer"
31
 
32
  def __init__(self, feature_extractor: GraniteSpeechNarFeatureExtractor, tokenizer=None, **kwargs):
 
26
  class GraniteSpeechNarProcessor(ProcessorMixin):
27
  """Processor combining audio feature extraction and tokenizer for GraniteSpeechNar."""
28
 
 
29
  tokenizer_class = "AutoTokenizer"
30
 
31
  def __init__(self, feature_extractor: GraniteSpeechNarFeatureExtractor, tokenizer=None, **kwargs):
tokenizer.json CHANGED
@@ -888,7 +888,32 @@
888
  }
889
  ]
890
  },
891
- "post_processor": null,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
892
  "decoder": {
893
  "type": "ByteLevel",
894
  "add_prefix_space": true,
 
888
  }
889
  ]
890
  },
891
+ "post_processor": {
892
+ "type": "TemplateProcessing",
893
+ "single": [
894
+ {
895
+ "Sequence": {
896
+ "id": "A",
897
+ "type_id": 0
898
+ }
899
+ }
900
+ ],
901
+ "pair": [
902
+ {
903
+ "Sequence": {
904
+ "id": "A",
905
+ "type_id": 0
906
+ }
907
+ },
908
+ {
909
+ "Sequence": {
910
+ "id": "B",
911
+ "type_id": 1
912
+ }
913
+ }
914
+ ],
915
+ "special_tokens": {}
916
+ },
917
  "decoder": {
918
  "type": "ByteLevel",
919
  "add_prefix_space": true,
tokenizer_config.json CHANGED
@@ -1,783 +1,14 @@
1
  {
2
- "add_bos_token": false,
3
  "add_prefix_space": false,
4
- "added_tokens_decoder": {
5
- "100256": {
6
- "content": "<|pad|>",
7
- "lstrip": false,
8
- "normalized": false,
9
- "rstrip": false,
10
- "single_word": false,
11
- "special": true
12
- },
13
- "100257": {
14
- "content": "<|end_of_text|>",
15
- "lstrip": false,
16
- "normalized": false,
17
- "rstrip": false,
18
- "single_word": false,
19
- "special": true
20
- },
21
- "100258": {
22
- "content": "<|fim_prefix|>",
23
- "lstrip": false,
24
- "normalized": false,
25
- "rstrip": false,
26
- "single_word": false,
27
- "special": false
28
- },
29
- "100259": {
30
- "content": "<|fim_middle|>",
31
- "lstrip": false,
32
- "normalized": false,
33
- "rstrip": false,
34
- "single_word": false,
35
- "special": false
36
- },
37
- "100260": {
38
- "content": "<|fim_suffix|>",
39
- "lstrip": false,
40
- "normalized": false,
41
- "rstrip": false,
42
- "single_word": false,
43
- "special": false
44
- },
45
- "100261": {
46
- "content": "<|fim_pad|>",
47
- "lstrip": false,
48
- "normalized": false,
49
- "rstrip": false,
50
- "single_word": false,
51
- "special": false
52
- },
53
- "100262": {
54
- "content": "<|filename|>",
55
- "lstrip": false,
56
- "normalized": false,
57
- "rstrip": false,
58
- "single_word": false,
59
- "special": false
60
- },
61
- "100263": {
62
- "content": "<|reponame|>",
63
- "lstrip": false,
64
- "normalized": false,
65
- "rstrip": false,
66
- "single_word": false,
67
- "special": false
68
- },
69
- "100264": {
70
- "content": "<|start_of_role|>",
71
- "lstrip": false,
72
- "normalized": false,
73
- "rstrip": false,
74
- "single_word": false,
75
- "special": true
76
- },
77
- "100265": {
78
- "content": "<|end_of_role|>",
79
- "lstrip": false,
80
- "normalized": false,
81
- "rstrip": false,
82
- "single_word": false,
83
- "special": true
84
- },
85
- "100266": {
86
- "content": "<|unused_1|>",
87
- "lstrip": false,
88
- "normalized": false,
89
- "rstrip": false,
90
- "single_word": false,
91
- "special": true
92
- },
93
- "100267": {
94
- "content": "<|start_of_plugin|>",
95
- "lstrip": false,
96
- "normalized": false,
97
- "rstrip": false,
98
- "single_word": false,
99
- "special": true
100
- },
101
- "100268": {
102
- "content": "<|end_of_plugin|>",
103
- "lstrip": false,
104
- "normalized": false,
105
- "rstrip": false,
106
- "single_word": false,
107
- "special": true
108
- },
109
- "100269": {
110
- "content": "<|unk|>",
111
- "lstrip": false,
112
- "normalized": false,
113
- "rstrip": false,
114
- "single_word": false,
115
- "special": true
116
- },
117
- "100270": {
118
- "content": "<tool_call>",
119
- "lstrip": false,
120
- "normalized": false,
121
- "rstrip": false,
122
- "single_word": false,
123
- "special": false
124
- },
125
- "100271": {
126
- "content": "</tool_call>",
127
- "lstrip": false,
128
- "normalized": false,
129
- "rstrip": false,
130
- "single_word": false,
131
- "special": false
132
- },
133
- "100272": {
134
- "content": "<tool_response>",
135
- "lstrip": false,
136
- "normalized": false,
137
- "rstrip": false,
138
- "single_word": false,
139
- "special": false
140
- },
141
- "100273": {
142
- "content": "</tool_response>",
143
- "lstrip": false,
144
- "normalized": false,
145
- "rstrip": false,
146
- "single_word": false,
147
- "special": false
148
- },
149
- "100274": {
150
- "content": "<think>",
151
- "lstrip": false,
152
- "normalized": false,
153
- "rstrip": false,
154
- "single_word": false,
155
- "special": false
156
- },
157
- "100275": {
158
- "content": "</think>",
159
- "lstrip": false,
160
- "normalized": false,
161
- "rstrip": false,
162
- "single_word": false,
163
- "special": false
164
- },
165
- "100276": {
166
- "content": "<think_on>",
167
- "lstrip": false,
168
- "normalized": false,
169
- "rstrip": false,
170
- "single_word": false,
171
- "special": true
172
- },
173
- "100277": {
174
- "content": "<think_off>",
175
- "lstrip": false,
176
- "normalized": false,
177
- "rstrip": false,
178
- "single_word": false,
179
- "special": true
180
- },
181
- "100278": {
182
- "content": "<schema>",
183
- "lstrip": false,
184
- "normalized": false,
185
- "rstrip": false,
186
- "single_word": false,
187
- "special": true
188
- },
189
- "100279": {
190
- "content": "</schema>",
191
- "lstrip": false,
192
- "normalized": false,
193
- "rstrip": false,
194
- "single_word": false,
195
- "special": true
196
- },
197
- "100280": {
198
- "content": "<tools>",
199
- "lstrip": false,
200
- "normalized": false,
201
- "rstrip": false,
202
- "single_word": false,
203
- "special": true
204
- },
205
- "100281": {
206
- "content": "</tools>",
207
- "lstrip": false,
208
- "normalized": false,
209
- "rstrip": false,
210
- "single_word": false,
211
- "special": true
212
- },
213
- "100282": {
214
- "content": "<documents>",
215
- "lstrip": false,
216
- "normalized": false,
217
- "rstrip": false,
218
- "single_word": false,
219
- "special": true
220
- },
221
- "100283": {
222
- "content": "</documents>",
223
- "lstrip": false,
224
- "normalized": false,
225
- "rstrip": false,
226
- "single_word": false,
227
- "special": true
228
- },
229
- "100284": {
230
- "content": "<|unused_15|>",
231
- "lstrip": false,
232
- "normalized": false,
233
- "rstrip": false,
234
- "single_word": false,
235
- "special": true
236
- },
237
- "100285": {
238
- "content": "<|unused_16|>",
239
- "lstrip": false,
240
- "normalized": false,
241
- "rstrip": false,
242
- "single_word": false,
243
- "special": true
244
- },
245
- "100286": {
246
- "content": "<|unused_17|>",
247
- "lstrip": false,
248
- "normalized": false,
249
- "rstrip": false,
250
- "single_word": false,
251
- "special": true
252
- },
253
- "100287": {
254
- "content": "<|unused_18|>",
255
- "lstrip": false,
256
- "normalized": false,
257
- "rstrip": false,
258
- "single_word": false,
259
- "special": true
260
- },
261
- "100288": {
262
- "content": "<|unused_19|>",
263
- "lstrip": false,
264
- "normalized": false,
265
- "rstrip": false,
266
- "single_word": false,
267
- "special": true
268
- },
269
- "100289": {
270
- "content": "<|unused_20|>",
271
- "lstrip": false,
272
- "normalized": false,
273
- "rstrip": false,
274
- "single_word": false,
275
- "special": true
276
- },
277
- "100290": {
278
- "content": "<|unused_21|>",
279
- "lstrip": false,
280
- "normalized": false,
281
- "rstrip": false,
282
- "single_word": false,
283
- "special": true
284
- },
285
- "100291": {
286
- "content": "<|unused_22|>",
287
- "lstrip": false,
288
- "normalized": false,
289
- "rstrip": false,
290
- "single_word": false,
291
- "special": true
292
- },
293
- "100292": {
294
- "content": "<|unused_23|>",
295
- "lstrip": false,
296
- "normalized": false,
297
- "rstrip": false,
298
- "single_word": false,
299
- "special": true
300
- },
301
- "100293": {
302
- "content": "<|unused_24|>",
303
- "lstrip": false,
304
- "normalized": false,
305
- "rstrip": false,
306
- "single_word": false,
307
- "special": true
308
- },
309
- "100294": {
310
- "content": "<|unused_25|>",
311
- "lstrip": false,
312
- "normalized": false,
313
- "rstrip": false,
314
- "single_word": false,
315
- "special": true
316
- },
317
- "100295": {
318
- "content": "<|unused_26|>",
319
- "lstrip": false,
320
- "normalized": false,
321
- "rstrip": false,
322
- "single_word": false,
323
- "special": true
324
- },
325
- "100296": {
326
- "content": "<|unused_27|>",
327
- "lstrip": false,
328
- "normalized": false,
329
- "rstrip": false,
330
- "single_word": false,
331
- "special": true
332
- },
333
- "100297": {
334
- "content": "<|unused_28|>",
335
- "lstrip": false,
336
- "normalized": false,
337
- "rstrip": false,
338
- "single_word": false,
339
- "special": true
340
- },
341
- "100298": {
342
- "content": "<|unused_29|>",
343
- "lstrip": false,
344
- "normalized": false,
345
- "rstrip": false,
346
- "single_word": false,
347
- "special": true
348
- },
349
- "100299": {
350
- "content": "<|unused_30|>",
351
- "lstrip": false,
352
- "normalized": false,
353
- "rstrip": false,
354
- "single_word": false,
355
- "special": true
356
- },
357
- "100300": {
358
- "content": "<|unused_31|>",
359
- "lstrip": false,
360
- "normalized": false,
361
- "rstrip": false,
362
- "single_word": false,
363
- "special": true
364
- },
365
- "100301": {
366
- "content": "<|unused_32|>",
367
- "lstrip": false,
368
- "normalized": false,
369
- "rstrip": false,
370
- "single_word": false,
371
- "special": true
372
- },
373
- "100302": {
374
- "content": "<|unused_33|>",
375
- "lstrip": false,
376
- "normalized": false,
377
- "rstrip": false,
378
- "single_word": false,
379
- "special": true
380
- },
381
- "100303": {
382
- "content": "<|unused_34|>",
383
- "lstrip": false,
384
- "normalized": false,
385
- "rstrip": false,
386
- "single_word": false,
387
- "special": true
388
- },
389
- "100304": {
390
- "content": "<|unused_35|>",
391
- "lstrip": false,
392
- "normalized": false,
393
- "rstrip": false,
394
- "single_word": false,
395
- "special": true
396
- },
397
- "100305": {
398
- "content": "<|unused_36|>",
399
- "lstrip": false,
400
- "normalized": false,
401
- "rstrip": false,
402
- "single_word": false,
403
- "special": true
404
- },
405
- "100306": {
406
- "content": "<|unused_37|>",
407
- "lstrip": false,
408
- "normalized": false,
409
- "rstrip": false,
410
- "single_word": false,
411
- "special": true
412
- },
413
- "100307": {
414
- "content": "<|unused_38|>",
415
- "lstrip": false,
416
- "normalized": false,
417
- "rstrip": false,
418
- "single_word": false,
419
- "special": true
420
- },
421
- "100308": {
422
- "content": "<|unused_39|>",
423
- "lstrip": false,
424
- "normalized": false,
425
- "rstrip": false,
426
- "single_word": false,
427
- "special": true
428
- },
429
- "100309": {
430
- "content": "<|unused_40|>",
431
- "lstrip": false,
432
- "normalized": false,
433
- "rstrip": false,
434
- "single_word": false,
435
- "special": true
436
- },
437
- "100310": {
438
- "content": "<|unused_41|>",
439
- "lstrip": false,
440
- "normalized": false,
441
- "rstrip": false,
442
- "single_word": false,
443
- "special": true
444
- },
445
- "100311": {
446
- "content": "<|unused_42|>",
447
- "lstrip": false,
448
- "normalized": false,
449
- "rstrip": false,
450
- "single_word": false,
451
- "special": true
452
- },
453
- "100312": {
454
- "content": "<|unused_43|>",
455
- "lstrip": false,
456
- "normalized": false,
457
- "rstrip": false,
458
- "single_word": false,
459
- "special": true
460
- },
461
- "100313": {
462
- "content": "<|unused_44|>",
463
- "lstrip": false,
464
- "normalized": false,
465
- "rstrip": false,
466
- "single_word": false,
467
- "special": true
468
- },
469
- "100314": {
470
- "content": "<|unused_45|>",
471
- "lstrip": false,
472
- "normalized": false,
473
- "rstrip": false,
474
- "single_word": false,
475
- "special": true
476
- },
477
- "100315": {
478
- "content": "<|unused_46|>",
479
- "lstrip": false,
480
- "normalized": false,
481
- "rstrip": false,
482
- "single_word": false,
483
- "special": true
484
- },
485
- "100316": {
486
- "content": "<|unused_47|>",
487
- "lstrip": false,
488
- "normalized": false,
489
- "rstrip": false,
490
- "single_word": false,
491
- "special": true
492
- },
493
- "100317": {
494
- "content": "<|unused_48|>",
495
- "lstrip": false,
496
- "normalized": false,
497
- "rstrip": false,
498
- "single_word": false,
499
- "special": true
500
- },
501
- "100318": {
502
- "content": "<|unused_49|>",
503
- "lstrip": false,
504
- "normalized": false,
505
- "rstrip": false,
506
- "single_word": false,
507
- "special": true
508
- },
509
- "100319": {
510
- "content": "<|unused_50|>",
511
- "lstrip": false,
512
- "normalized": false,
513
- "rstrip": false,
514
- "single_word": false,
515
- "special": true
516
- },
517
- "100320": {
518
- "content": "<|unused_51|>",
519
- "lstrip": false,
520
- "normalized": false,
521
- "rstrip": false,
522
- "single_word": false,
523
- "special": true
524
- },
525
- "100321": {
526
- "content": "<|unused_52|>",
527
- "lstrip": false,
528
- "normalized": false,
529
- "rstrip": false,
530
- "single_word": false,
531
- "special": true
532
- },
533
- "100322": {
534
- "content": "<|unused_53|>",
535
- "lstrip": false,
536
- "normalized": false,
537
- "rstrip": false,
538
- "single_word": false,
539
- "special": true
540
- },
541
- "100323": {
542
- "content": "<|unused_54|>",
543
- "lstrip": false,
544
- "normalized": false,
545
- "rstrip": false,
546
- "single_word": false,
547
- "special": true
548
- },
549
- "100324": {
550
- "content": "<|unused_55|>",
551
- "lstrip": false,
552
- "normalized": false,
553
- "rstrip": false,
554
- "single_word": false,
555
- "special": true
556
- },
557
- "100325": {
558
- "content": "<|unused_56|>",
559
- "lstrip": false,
560
- "normalized": false,
561
- "rstrip": false,
562
- "single_word": false,
563
- "special": true
564
- },
565
- "100326": {
566
- "content": "<|unused_57|>",
567
- "lstrip": false,
568
- "normalized": false,
569
- "rstrip": false,
570
- "single_word": false,
571
- "special": true
572
- },
573
- "100327": {
574
- "content": "<|unused_58|>",
575
- "lstrip": false,
576
- "normalized": false,
577
- "rstrip": false,
578
- "single_word": false,
579
- "special": true
580
- },
581
- "100328": {
582
- "content": "<|unused_59|>",
583
- "lstrip": false,
584
- "normalized": false,
585
- "rstrip": false,
586
- "single_word": false,
587
- "special": true
588
- },
589
- "100329": {
590
- "content": "<|unused_60|>",
591
- "lstrip": false,
592
- "normalized": false,
593
- "rstrip": false,
594
- "single_word": false,
595
- "special": true
596
- },
597
- "100330": {
598
- "content": "<|unused_61|>",
599
- "lstrip": false,
600
- "normalized": false,
601
- "rstrip": false,
602
- "single_word": false,
603
- "special": true
604
- },
605
- "100331": {
606
- "content": "<|unused_62|>",
607
- "lstrip": false,
608
- "normalized": false,
609
- "rstrip": false,
610
- "single_word": false,
611
- "special": true
612
- },
613
- "100332": {
614
- "content": "<|unused_63|>",
615
- "lstrip": false,
616
- "normalized": false,
617
- "rstrip": false,
618
- "single_word": false,
619
- "special": true
620
- },
621
- "100333": {
622
- "content": "<|unused_64|>",
623
- "lstrip": false,
624
- "normalized": false,
625
- "rstrip": false,
626
- "single_word": false,
627
- "special": true
628
- },
629
- "100334": {
630
- "content": "<|unused_65|>",
631
- "lstrip": false,
632
- "normalized": false,
633
- "rstrip": false,
634
- "single_word": false,
635
- "special": true
636
- },
637
- "100335": {
638
- "content": "<|unused_66|>",
639
- "lstrip": false,
640
- "normalized": false,
641
- "rstrip": false,
642
- "single_word": false,
643
- "special": true
644
- },
645
- "100336": {
646
- "content": "<|unused_67|>",
647
- "lstrip": false,
648
- "normalized": false,
649
- "rstrip": false,
650
- "single_word": false,
651
- "special": true
652
- },
653
- "100337": {
654
- "content": "<|unused_68|>",
655
- "lstrip": false,
656
- "normalized": false,
657
- "rstrip": false,
658
- "single_word": false,
659
- "special": true
660
- },
661
- "100338": {
662
- "content": "<|unused_69|>",
663
- "lstrip": false,
664
- "normalized": false,
665
- "rstrip": false,
666
- "single_word": false,
667
- "special": true
668
- },
669
- "100339": {
670
- "content": "<|unused_70|>",
671
- "lstrip": false,
672
- "normalized": false,
673
- "rstrip": false,
674
- "single_word": false,
675
- "special": true
676
- },
677
- "100340": {
678
- "content": "<|unused_71|>",
679
- "lstrip": false,
680
- "normalized": false,
681
- "rstrip": false,
682
- "single_word": false,
683
- "special": true
684
- },
685
- "100341": {
686
- "content": "<|unused_72|>",
687
- "lstrip": false,
688
- "normalized": false,
689
- "rstrip": false,
690
- "single_word": false,
691
- "special": true
692
- },
693
- "100342": {
694
- "content": "<|unused_73|>",
695
- "lstrip": false,
696
- "normalized": false,
697
- "rstrip": false,
698
- "single_word": false,
699
- "special": true
700
- },
701
- "100343": {
702
- "content": "<|unused_74|>",
703
- "lstrip": false,
704
- "normalized": false,
705
- "rstrip": false,
706
- "single_word": false,
707
- "special": true
708
- },
709
- "100344": {
710
- "content": "<|unused_75|>",
711
- "lstrip": false,
712
- "normalized": false,
713
- "rstrip": false,
714
- "single_word": false,
715
- "special": true
716
- },
717
- "100345": {
718
- "content": "<|unused_76|>",
719
- "lstrip": false,
720
- "normalized": false,
721
- "rstrip": false,
722
- "single_word": false,
723
- "special": true
724
- },
725
- "100346": {
726
- "content": "<|unused_77|>",
727
- "lstrip": false,
728
- "normalized": false,
729
- "rstrip": false,
730
- "single_word": false,
731
- "special": true
732
- },
733
- "100347": {
734
- "content": "<|unused_78|>",
735
- "lstrip": false,
736
- "normalized": false,
737
- "rstrip": false,
738
- "single_word": false,
739
- "special": true
740
- },
741
- "100348": {
742
- "content": "<|unused_79|>",
743
- "lstrip": false,
744
- "normalized": false,
745
- "rstrip": false,
746
- "single_word": false,
747
- "special": true
748
- },
749
- "100349": {
750
- "content": "<|unused_80|>",
751
- "lstrip": false,
752
- "normalized": false,
753
- "rstrip": false,
754
- "single_word": false,
755
- "special": true
756
- },
757
- "100350": {
758
- "content": "<|unused_81|>",
759
- "lstrip": false,
760
- "normalized": false,
761
- "rstrip": false,
762
- "single_word": false,
763
- "special": true
764
- },
765
- "100351": {
766
- "content": "<|unused_82|>",
767
- "lstrip": false,
768
- "normalized": false,
769
- "rstrip": false,
770
- "single_word": false,
771
- "special": true
772
- }
773
- },
774
  "bos_token": "<|end_of_text|>",
775
  "clean_up_tokenization_spaces": false,
776
  "eos_token": "<|end_of_text|>",
777
- "extra_special_tokens": {},
 
778
  "model_max_length": 1000000000000000019884624838656,
779
  "pad_token": "<|pad|>",
780
  "padding_side": "left",
781
- "tokenizer_class": "GPT2Tokenizer",
782
  "unk_token": "<|unk|>"
783
  }
 
1
  {
 
2
  "add_prefix_space": false,
3
+ "backend": "tokenizers",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4
  "bos_token": "<|end_of_text|>",
5
  "clean_up_tokenization_spaces": false,
6
  "eos_token": "<|end_of_text|>",
7
+ "is_local": true,
8
+ "local_files_only": false,
9
  "model_max_length": 1000000000000000019884624838656,
10
  "pad_token": "<|pad|>",
11
  "padding_side": "left",
12
+ "tokenizer_class": "TokenizersBackend",
13
  "unk_token": "<|unk|>"
14
  }