Hugging Face's logo

LunaFox
/
Breeze-TTS-2-mlx-4bit

Text-to-Speech
MLX
Safetensors
English
Chinese
breeze_tts
speech-generation
voice-clone
voice-design
voice-direction
4-bit precision
Model card Files
xet
 Community
LunaFox commited on
Commit
13fdc32
·
verified ·
1 Parent(s): 85ac9b7

Upload folder using huggingface_hub

Browse files
Files changed (12) hide show
  1. .gitattributes +1 -0
  2. audio_tokenizer/config.json +94 -0
  3. audio_tokenizer/configuration.json +1 -0
  4. audio_tokenizer/model.safetensors +3 -0
  5. audio_tokenizer/preprocessor_config.json +10 -0
  6. config.json +451 -0
  7. generation_config.json +13 -0
  8. model.safetensors +3 -0
  9. model.safetensors.index.json +0 -0
  10. special_tokens_map.json +51 -0
  11. tokenizer.json +3 -0
  12. tokenizer_config.json +0 -0
.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
audio_tokenizer/config.json ADDED
@@ -0,0 +1,94 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3TTSTokenizerV2Model"
4
+ ],
5
+ "model_type": "qwen3_tts_tokenizer_12hz",
6
+ "encoder_valid_num_quantizers": 16,
7
+ "input_sample_rate": 24000,
8
+ "output_sample_rate": 24000,
9
+ "decode_upsample_rate": 1920,
10
+ "encode_downsample_rate": 1920,
11
+ "decoder_config": {
12
+ "attention_bias": false,
13
+ "attention_dropout": 0.0,
14
+ "latent_dim": 1024,
15
+ "codebook_dim": 512,
16
+ "codebook_size": 2048,
17
+ "decoder_dim": 1536,
18
+ "hidden_act": "silu",
19
+ "hidden_size": 512,
20
+ "intermediate_size": 1024,
21
+ "layer_scale_initial_scale": 0.01,
22
+ "max_position_embeddings": 8000,
23
+ "head_dim": 64,
24
+ "num_attention_heads": 16,
25
+ "num_hidden_layers": 8,
26
+ "num_key_value_heads": 16,
27
+ "num_quantizers": 16,
28
+ "num_semantic_quantizers": 1,
29
+ "rms_norm_eps": 1e-05,
30
+ "rope_theta": 10000,
31
+ "semantic_codebook_size": 4096,
32
+ "sliding_window": 72,
33
+ "upsample_rates": [
34
+ 8,
35
+ 5,
36
+ 4,
37
+ 3
38
+ ],
39
+ "upsampling_ratios": [
40
+ 2,
41
+ 2
42
+ ],
43
+ "vector_quantization_hidden_dimension": 512
44
+ },
45
+ "encoder_config": {
46
+ "_frame_rate": 12.5,
47
+ "attention_bias": false,
48
+ "attention_dropout": 0.0,
49
+ "audio_channels": 1,
50
+ "codebook_dim": 256,
51
+ "codebook_size": 2048,
52
+ "compress": 2,
53
+ "dilation_growth_rate": 2,
54
+ "dtype": "float32",
55
+ "head_dim": 64,
56
+ "hidden_act": "gelu",
57
+ "hidden_size": 512,
58
+ "initializer_range": 0.02,
59
+ "intermediate_size": 2048,
60
+ "kernel_size": 7,
61
+ "last_kernel_size": 3,
62
+ "layer_scale_initial_scale": 0.01,
63
+ "max_position_embeddings": 8000,
64
+ "norm_eps": 1e-05,
65
+ "normalize": false,
66
+ "num_attention_heads": 8,
67
+ "num_filters": 64,
68
+ "num_hidden_layers": 8,
69
+ "num_key_value_heads": 8,
70
+ "num_quantizers": 32,
71
+ "num_residual_layers": 1,
72
+ "num_semantic_quantizers": 1,
73
+ "pad_mode": "constant",
74
+ "residual_kernel_size": 3,
75
+ "rope_theta": 10000.0,
76
+ "sampling_rate": 24000,
77
+ "sliding_window": 250,
78
+ "transformers_version": "4.57.0.dev0",
79
+ "trim_right_ratio": 1.0,
80
+ "upsample_groups": 512,
81
+ "upsampling_ratios": [
82
+ 8,
83
+ 6,
84
+ 5,
85
+ 4
86
+ ],
87
+ "use_cache": false,
88
+ "use_causal_conv": true,
89
+ "use_conv_shortcut": false,
90
+ "use_streaming": false,
91
+ "vector_quantization_hidden_dimension": 256
92
+ },
93
+ "transformers_version": "4.57.3"
94
+ }
audio_tokenizer/configuration.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"framework": "pytorch", "task": "feature-extraction", "allow_remote": true}
audio_tokenizer/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:836b7b357f5ea43e889936a3709af68dfe3751881acefe4ecf0dbd30ba571258
3
+ size 682293092
audio_tokenizer/preprocessor_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "chunk_length_s": null,
3
+ "feature_extractor_type": "EncodecFeatureExtractor",
4
+ "feature_size": 1,
5
+ "overlap": null,
6
+ "padding_side": "right",
7
+ "padding_value": 0.0,
8
+ "return_attention_mask": true,
9
+ "sampling_rate": 24000
10
+ }
config.json ADDED
@@ -0,0 +1,451 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BreezeForConditionalGeneration"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "audio_embed_size": 2048,
8
+ "audio_eos_token_id": 262145,
9
+ "audio_num_codebooks": 16,
10
+ "audio_token_id": 262144,
11
+ "audio_vocab_size": 2051,
12
+ "backbone_config": {
13
+ "architectures": [
14
+ "Qwen3ForCausalLM"
15
+ ],
16
+ "attention_bias": false,
17
+ "attention_dropout": 0.0,
18
+ "bos_token_id": 151643,
19
+ "eos_token_id": 151645,
20
+ "head_dim": 128,
21
+ "hidden_act": "silu",
22
+ "hidden_size": 2048,
23
+ "initializer_range": 0.02,
24
+ "intermediate_size": 6144,
25
+ "max_position_embeddings": 40960,
26
+ "max_window_layers": 28,
27
+ "model_type": "qwen3",
28
+ "num_attention_heads": 16,
29
+ "num_hidden_layers": 28,
30
+ "num_key_value_heads": 8,
31
+ "rms_norm_eps": 1e-06,
32
+ "rope_scaling": null,
33
+ "rope_theta": 1000000,
34
+ "sliding_window": null,
35
+ "tie_word_embeddings": true,
36
+ "torch_dtype": "bfloat16",
37
+ "transformers_version": "4.51.0",
38
+ "use_cache": true,
39
+ "use_sliding_window": false,
40
+ "vocab_size": 151936
41
+ },
42
+ "backbone_flavor": "llama-1B",
43
+ "backbone_model_name_or_path": null,
44
+ "backbone_model_type": "qwen3",
45
+ "bos_token_id": 2,
46
+ "codebook_eos_token_id": 0,
47
+ "codebook_pad_token_id": 2050,
48
+ "codec_config": {
49
+ "_frame_rate": 12.5,
50
+ "_name_or_path": "kyutai/mimi",
51
+ "architectures": [
52
+ "MimiModel"
53
+ ],
54
+ "attention_bias": false,
55
+ "attention_dropout": 0.0,
56
+ "audio_channels": 1,
57
+ "codebook_dim": 256,
58
+ "codebook_size": 2048,
59
+ "compress": 2,
60
+ "dilation_growth_rate": 2,
61
+ "dtype": "bfloat16",
62
+ "head_dim": 64,
63
+ "hidden_act": "gelu",
64
+ "hidden_size": 512,
65
+ "initializer_range": 0.02,
66
+ "intermediate_size": 2048,
67
+ "kernel_size": 7,
68
+ "last_kernel_size": 3,
69
+ "layer_scale_initial_scale": 0.01,
70
+ "max_position_embeddings": 8000,
71
+ "model_type": "mimi",
72
+ "norm_eps": 1e-05,
73
+ "normalize": false,
74
+ "num_attention_heads": 8,
75
+ "num_filters": 64,
76
+ "num_hidden_layers": 8,
77
+ "num_key_value_heads": 8,
78
+ "num_quantizers": 32,
79
+ "num_residual_layers": 1,
80
+ "num_semantic_quantizers": 1,
81
+ "pad_mode": "constant",
82
+ "residual_kernel_size": 3,
83
+ "rope_theta": 10000.0,
84
+ "sampling_rate": 24000,
85
+ "sliding_window": 250,
86
+ "trim_right_ratio": 1.0,
87
+ "upsample_groups": 512,
88
+ "upsampling_ratios": [
89
+ 8,
90
+ 6,
91
+ 5,
92
+ 4
93
+ ],
94
+ "use_cache": false,
95
+ "use_causal_conv": true,
96
+ "use_conv_shortcut": false,
97
+ "use_streaming": false,
98
+ "vector_quantization_hidden_dimension": 256
99
+ },
100
+ "decoder_flavor": "llama-100M",
101
+ "depth_decoder_config": {
102
+ "attention_bias": false,
103
+ "attention_dropout": 0.0,
104
+ "audio_embed_size": 2048,
105
+ "backbone_hidden_size": 2048,
106
+ "codebook_loss_weights": [
107
+ 3
108
+ ],
109
+ "dtype": "bfloat16",
110
+ "head_dim": 128,
111
+ "hidden_act": "silu",
112
+ "hidden_size": 1024,
113
+ "initializer_range": 0.02,
114
+ "intermediate_size": 8192,
115
+ "max_position_embeddings": 33,
116
+ "mlp_bias": false,
117
+ "model_type": "breeze_depth_decoder_model",
118
+ "num_attention_heads": 8,
119
+ "num_codebooks": 16,
120
+ "num_hidden_layers": 12,
121
+ "num_key_value_heads": 2,
122
+ "rms_norm_eps": 1e-05,
123
+ "rope_scaling": {
124
+ "factor": 32.0,
125
+ "high_freq_factor": 0.0078125,
126
+ "low_freq_factor": 0.001953125,
127
+ "original_max_position_embeddings": 16,
128
+ "rope_type": "llama3"
129
+ },
130
+ "rope_theta": 500000,
131
+ "use_cache": true,
132
+ "vocab_size": 2051
133
+ },
134
+ "depth_header_loss_weight": 1.0,
135
+ "dtype": "bfloat16",
136
+ "eos_token_id": 1,
137
+ "head_dim": 128,
138
+ "hidden_act": "silu",
139
+ "hidden_size": 2048,
140
+ "initializer_range": 0.02,
141
+ "intermediate_size": 6144,
142
+ "max_position_embeddings": 2048,
143
+ "mlp_bias": false,
144
+ "model_type": "breeze_tts",
145
+ "num_attention_heads": 16,
146
+ "num_codebooks": 16,
147
+ "num_hidden_layers": 28,
148
+ "num_key_value_heads": 8,
149
+ "pad_token_id": 0,
150
+ "quantization": {
151
+ "group_size": 32,
152
+ "bits": 4,
153
+ "mode": "mxfp4"
154
+ },
155
+ "quantization_config": {
156
+ "group_size": 32,
157
+ "bits": 4,
158
+ "mode": "mxfp4"
159
+ },
160
+ "rms_norm_eps": 1e-05,
161
+ "rope_scaling": {
162
+ "factor": 32.0,
163
+ "high_freq_factor": 0.5,
164
+ "low_freq_factor": 0.125,
165
+ "original_max_position_embeddings": 1024,
166
+ "rope_type": "llama3"
167
+ },
168
+ "rope_theta": 500000,
169
+ "text_encoder_bucket_max_length_ratio": 4.0,
170
+ "text_encoder_config": {
171
+ "add_cross_attention": false,
172
+ "architectures": [
173
+ "T5Gemma2TextEncoder"
174
+ ],
175
+ "attention_bias": false,
176
+ "attention_dropout": 0.0,
177
+ "attn_logit_softcapping": null,
178
+ "bad_words_ids": null,
179
+ "begin_suppress_tokens": null,
180
+ "bos_token_id": 2,
181
+ "chunk_size_feed_forward": 0,
182
+ "cross_attention_hidden_size": null,
183
+ "decoder_start_token_id": null,
184
+ "diversity_penalty": 0.0,
185
+ "do_sample": false,
186
+ "dropout_rate": 0.0,
187
+ "dtype": "bfloat16",
188
+ "early_stopping": false,
189
+ "encoder_no_repeat_ngram_size": 0,
190
+ "eoi_token_index": 256000,
191
+ "eos_token_id": 1,
192
+ "exponential_decay_length_penalty": null,
193
+ "final_logit_softcapping": null,
194
+ "finetuning_task": null,
195
+ "forced_bos_token_id": null,
196
+ "forced_eos_token_id": null,
197
+ "head_dim": 256,
198
+ "hidden_activation": "gelu_pytorch_tanh",
199
+ "hidden_size": 1152,
200
+ "id2label": {
201
+ "0": "LABEL_0",
202
+ "1": "LABEL_1"
203
+ },
204
+ "initializer_range": 0.02,
205
+ "intermediate_size": 6912,
206
+ "is_decoder": false,
207
+ "is_encoder_decoder": false,
208
+ "label2id": {
209
+ "LABEL_0": 0,
210
+ "LABEL_1": 1
211
+ },
212
+ "layer_types": [
213
+ "sliding_attention",
214
+ "sliding_attention",
215
+ "sliding_attention",
216
+ "sliding_attention",
217
+ "sliding_attention",
218
+ "full_attention",
219
+ "sliding_attention",
220
+ "sliding_attention",
221
+ "sliding_attention",
222
+ "sliding_attention",
223
+ "sliding_attention",
224
+ "full_attention",
225
+ "sliding_attention",
226
+ "sliding_attention",
227
+ "sliding_attention",
228
+ "sliding_attention",
229
+ "sliding_attention",
230
+ "full_attention",
231
+ "sliding_attention",
232
+ "sliding_attention",
233
+ "sliding_attention",
234
+ "sliding_attention",
235
+ "sliding_attention",
236
+ "full_attention",
237
+ "sliding_attention",
238
+ "sliding_attention"
239
+ ],
240
+ "length_penalty": 1.0,
241
+ "max_length": 20,
242
+ "max_position_embeddings": 32768,
243
+ "min_length": 0,
244
+ "model_type": "t5gemma2_text",
245
+ "no_repeat_ngram_size": 0,
246
+ "num_attention_heads": 4,
247
+ "num_beam_groups": 1,
248
+ "num_beams": 1,
249
+ "num_hidden_layers": 26,
250
+ "num_key_value_heads": 1,
251
+ "num_return_sequences": 1,
252
+ "output_attentions": false,
253
+ "output_hidden_states": false,
254
+ "output_scores": false,
255
+ "pad_token_id": 0,
256
+ "preferred_attn_implementation": "flash_attention_2",
257
+ "prefix": null,
258
+ "problem_type": null,
259
+ "pruned_heads": {},
260
+ "query_pre_attn_scalar": 256,
261
+ "remove_invalid_values": false,
262
+ "repetition_penalty": 1.0,
263
+ "requires_grad": false,
264
+ "return_dict": true,
265
+ "return_dict_in_generate": false,
266
+ "rms_norm_eps": 1e-06,
267
+ "rope_parameters": {
268
+ "full_attention": {
269
+ "factor": 8.0,
270
+ "rope_theta": 1000000,
271
+ "rope_type": "linear"
272
+ },
273
+ "sliding_attention": {
274
+ "rope_theta": 10000,
275
+ "rope_type": "default"
276
+ }
277
+ },
278
+ "sep_token_id": null,
279
+ "sliding_window": 512,
280
+ "suppress_tokens": null,
281
+ "task_specific_params": null,
282
+ "temperature": 1.0,
283
+ "tf_legacy_loss": false,
284
+ "tie_encoder_decoder": false,
285
+ "tie_word_embeddings": true,
286
+ "tokenizer_class": null,
287
+ "top_k": 50,
288
+ "top_p": 1.0,
289
+ "torchscript": false,
290
+ "typical_p": 1.0,
291
+ "use_bfloat16": false,
292
+ "use_bidirectional_attention": false,
293
+ "use_cache": true,
294
+ "vocab_size": 262158
295
+ },
296
+ "text_encoder_lora_config": {
297
+ "alpha": 16.0,
298
+ "dropout": 0.05,
299
+ "enabled": false,
300
+ "freeze_base_model": true,
301
+ "layers": [
302
+ 0,
303
+ 1,
304
+ 2,
305
+ 3,
306
+ 4,
307
+ 5,
308
+ 6,
309
+ 7,
310
+ 8,
311
+ 9,
312
+ 10,
313
+ 11,
314
+ 12,
315
+ 13,
316
+ 14,
317
+ 15,
318
+ 16,
319
+ 17,
320
+ 18,
321
+ 19,
322
+ 20,
323
+ 21,
324
+ 22,
325
+ 23,
326
+ 24,
327
+ 25
328
+ ],
329
+ "merged_into_base": true,
330
+ "rank": 8,
331
+ "target_modules": [
332
+ "q_proj",
333
+ "v_proj",
334
+ "o_proj"
335
+ ]
336
+ },
337
+ "text_encoder_proj_type": "linear",
338
+ "text_encoder_special_tokens_config": {
339
+ "enabled": false,
340
+ "freeze_base_embeddings": true,
341
+ "initializer_token_ids": {
342
+ "<ins_bos>": [
343
+ 236820,
344
+ 22768,
345
+ 236813
346
+ ],
347
+ "<ins_eos>": [
348
+ 954,
349
+ 22768,
350
+ 236813
351
+ ],
352
+ "[S0]": [
353
+ 262146
354
+ ],
355
+ "[S1]": [
356
+ 262147
357
+ ],
358
+ "[S2]": [
359
+ 262148
360
+ ],
361
+ "[S3]": [
362
+ 262149
363
+ ],
364
+ "[S4]": [
365
+ 262150
366
+ ],
367
+ "[S5]": [
368
+ 262151
369
+ ],
370
+ "[S6]": [
371
+ 262152
372
+ ],
373
+ "[S7]": [
374
+ 262153
375
+ ],
376
+ "[S8]": [
377
+ 262154
378
+ ],
379
+ "[S9]": [
380
+ 262155
381
+ ]
382
+ },
383
+ "initializers": {
384
+ "<ins_bos>": "<instruction>",
385
+ "<ins_eos>": "</instruction>",
386
+ "[S0]": "[S0]",
387
+ "[S1]": "[S1]",
388
+ "[S2]": "[S2]",
389
+ "[S3]": "[S3]",
390
+ "[S4]": "[S4]",
391
+ "[S5]": "[S5]",
392
+ "[S6]": "[S6]",
393
+ "[S7]": "[S7]",
394
+ "[S8]": "[S8]",
395
+ "[S9]": "[S9]"
396
+ },
397
+ "instruction_tokens": {
398
+ "bos": "<ins_bos>",
399
+ "eos": "<ins_eos>"
400
+ },
401
+ "merged_into_base": true,
402
+ "num_added_tokens": 12,
403
+ "speaker_tokens": [
404
+ "[S0]",
405
+ "[S1]",
406
+ "[S2]",
407
+ "[S3]",
408
+ "[S4]",
409
+ "[S5]",
410
+ "[S6]",
411
+ "[S7]",
412
+ "[S8]",
413
+ "[S9]"
414
+ ],
415
+ "token_ids": {
416
+ "<ins_bos>": 262156,
417
+ "<ins_eos>": 262157,
418
+ "[S0]": 262146,
419
+ "[S1]": 262147,
420
+ "[S2]": 262148,
421
+ "[S3]": 262149,
422
+ "[S4]": 262150,
423
+ "[S5]": 262151,
424
+ "[S6]": 262152,
425
+ "[S7]": 262153,
426
+ "[S8]": 262154,
427
+ "[S9]": 262155
428
+ },
429
+ "tokens": [
430
+ "[S0]",
431
+ "[S1]",
432
+ "[S2]",
433
+ "[S3]",
434
+ "[S4]",
435
+ "[S5]",
436
+ "[S6]",
437
+ "[S7]",
438
+ "[S8]",
439
+ "[S9]",
440
+ "<ins_bos>",
441
+ "<ins_eos>"
442
+ ],
443
+ "trainable": true
444
+ },
445
+ "text_vocab_size": 262158,
446
+ "tie_codebooks_embeddings": true,
447
+ "tie_word_embeddings": false,
448
+ "transformers_version": "4.57.3",
449
+ "use_cache": true,
450
+ "vocab_size": 2051
451
+ }
generation_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 2,
3
+ "depth_decoder_do_sample": true,
4
+ "depth_decoder_temperature": 0.9,
5
+ "do_sample": true,
6
+ "eos_token_id": [
7
+ 1
8
+ ],
9
+ "max_new_tokens": 750,
10
+ "pad_token_id": 0,
11
+ "temperature": 0.9,
12
+ "transformers_version": "4.57.3"
13
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8499e75e043b16d0734897869a124198aca2fa88436eb83c855d58a39fdac0a
3
+ size 2325487160
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "[S0]",
4
+ "[S1]",
5
+ "[S2]",
6
+ "[S3]",
7
+ "[S4]",
8
+ "[S5]",
9
+ "[S6]",
10
+ "[S7]",
11
+ "[S8]",
12
+ "[S9]",
13
+ "<ins_bos>",
14
+ "<ins_eos>"
15
+ ],
16
+ "bos_token": {
17
+ "content": "<bos>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "eos_token": {
24
+ "content": "<eos>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "mask_token": {
31
+ "content": "<mask>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "pad_token": {
38
+ "content": "<pad>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "<unk>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d3ec9ac3eb2392389b9f5112e85d8b43316494addb587ba7b7a9d61eac23af96
3
+ size 33386945
tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff