Text-to-Audio
Transformers
musicgen
Inference Endpoints
mmomeni commited on
Commit
91330cc
1 Parent(s): 25948cc

Update config.json

Browse files
Files changed (1) hide show
  1. config.json +1 -290
config.json CHANGED
@@ -3,296 +3,7 @@
3
  "architectures": [
4
  "MusicgenForConditionalGeneration"
5
  ],
6
- "audio_encoder": {
7
- "_name_or_path": "facebook/encodec_32khz",
8
- "add_cross_attention": false,
9
- "architectures": [
10
- "EncodecModel"
11
- ],
12
- "audio_channels": 1,
13
- "bad_words_ids": null,
14
- "begin_suppress_tokens": null,
15
- "bos_token_id": null,
16
- "chunk_length_s": null,
17
- "chunk_size_feed_forward": 0,
18
- "codebook_dim": 128,
19
- "codebook_size": 2048,
20
- "compress": 2,
21
- "cross_attention_hidden_size": null,
22
- "decoder_start_token_id": null,
23
- "dilation_growth_rate": 2,
24
- "diversity_penalty": 0.0,
25
- "do_sample": false,
26
- "early_stopping": false,
27
- "encoder_no_repeat_ngram_size": 0,
28
- "eos_token_id": null,
29
- "exponential_decay_length_penalty": null,
30
- "finetuning_task": null,
31
- "forced_bos_token_id": null,
32
- "forced_eos_token_id": null,
33
- "hidden_size": 128,
34
- "id2label": {
35
- "0": "LABEL_0",
36
- "1": "LABEL_1"
37
- },
38
- "is_decoder": false,
39
- "is_encoder_decoder": false,
40
- "kernel_size": 7,
41
- "label2id": {
42
- "LABEL_0": 0,
43
- "LABEL_1": 1
44
- },
45
- "last_kernel_size": 7,
46
- "length_penalty": 1.0,
47
- "max_length": 20,
48
- "min_length": 0,
49
- "model_type": "encodec",
50
- "no_repeat_ngram_size": 0,
51
- "norm_type": "weight_norm",
52
- "normalize": false,
53
- "num_beam_groups": 1,
54
- "num_beams": 1,
55
- "num_filters": 64,
56
- "num_lstm_layers": 2,
57
- "num_residual_layers": 1,
58
- "num_return_sequences": 1,
59
- "output_attentions": false,
60
- "output_hidden_states": false,
61
- "output_scores": false,
62
- "overlap": null,
63
- "pad_mode": "reflect",
64
- "pad_token_id": null,
65
- "prefix": null,
66
- "problem_type": null,
67
- "pruned_heads": {},
68
- "remove_invalid_values": false,
69
- "repetition_penalty": 1.0,
70
- "residual_kernel_size": 3,
71
- "return_dict": true,
72
- "return_dict_in_generate": false,
73
- "sampling_rate": 32000,
74
- "sep_token_id": null,
75
- "suppress_tokens": null,
76
- "target_bandwidths": [
77
- 2.2
78
- ],
79
- "task_specific_params": null,
80
- "temperature": 1.0,
81
- "tf_legacy_loss": false,
82
- "tie_encoder_decoder": false,
83
- "tie_word_embeddings": true,
84
- "tokenizer_class": null,
85
- "top_k": 50,
86
- "top_p": 1.0,
87
- "torch_dtype": "float32",
88
- "torchscript": false,
89
- "transformers_version": "4.38.2",
90
- "trim_right_ratio": 1.0,
91
- "typical_p": 1.0,
92
- "upsampling_ratios": [
93
- 8,
94
- 5,
95
- 4,
96
- 4
97
- ],
98
- "use_bfloat16": false,
99
- "use_causal_conv": false,
100
- "use_conv_shortcut": false
101
- },
102
- "decoder": {
103
- "_name_or_path": "",
104
- "activation_dropout": 0.0,
105
- "activation_function": "gelu",
106
- "add_cross_attention": false,
107
- "architectures": null,
108
- "attention_dropout": 0.0,
109
- "bad_words_ids": null,
110
- "begin_suppress_tokens": null,
111
- "bos_token_id": 2048,
112
- "chunk_size_feed_forward": 0,
113
- "classifier_dropout": 0.0,
114
- "cross_attention_hidden_size": null,
115
- "decoder_start_token_id": null,
116
- "diversity_penalty": 0.0,
117
- "do_sample": false,
118
- "dropout": 0.1,
119
- "early_stopping": false,
120
- "encoder_no_repeat_ngram_size": 0,
121
- "eos_token_id": null,
122
- "exponential_decay_length_penalty": null,
123
- "ffn_dim": 4096,
124
- "finetuning_task": null,
125
- "forced_bos_token_id": null,
126
- "forced_eos_token_id": null,
127
- "hidden_size": 1024,
128
- "id2label": {
129
- "0": "LABEL_0",
130
- "1": "LABEL_1"
131
- },
132
- "initializer_factor": 0.02,
133
- "is_decoder": false,
134
- "is_encoder_decoder": false,
135
- "label2id": {
136
- "LABEL_0": 0,
137
- "LABEL_1": 1
138
- },
139
- "layerdrop": 0.0,
140
- "length_penalty": 1.0,
141
- "max_length": 20,
142
- "max_position_embeddings": 2048,
143
- "min_length": 0,
144
- "model_type": "musicgen_decoder",
145
- "no_repeat_ngram_size": 0,
146
- "num_attention_heads": 16,
147
- "num_beam_groups": 1,
148
- "num_beams": 1,
149
- "num_codebooks": 4,
150
- "num_hidden_layers": 24,
151
- "num_return_sequences": 1,
152
- "output_attentions": false,
153
- "output_hidden_states": false,
154
- "output_scores": false,
155
- "pad_token_id": 2048,
156
- "prefix": null,
157
- "problem_type": null,
158
- "pruned_heads": {},
159
- "remove_invalid_values": false,
160
- "repetition_penalty": 1.0,
161
- "return_dict": true,
162
- "return_dict_in_generate": false,
163
- "scale_embedding": false,
164
- "sep_token_id": null,
165
- "suppress_tokens": null,
166
- "task_specific_params": null,
167
- "temperature": 1.0,
168
- "tf_legacy_loss": false,
169
- "tie_encoder_decoder": false,
170
- "tie_word_embeddings": false,
171
- "tokenizer_class": null,
172
- "top_k": 50,
173
- "top_p": 1.0,
174
- "torch_dtype": null,
175
- "torchscript": false,
176
- "transformers_version": "4.38.2",
177
- "typical_p": 1.0,
178
- "use_bfloat16": false,
179
- "use_cache": true,
180
- "vocab_size": 2048
181
- },
182
- "is_encoder_decoder": true,
183
  "model_type": "musicgen",
184
- "text_encoder": {
185
- "_name_or_path": "t5-base",
186
- "add_cross_attention": false,
187
- "architectures": [
188
- "T5ForConditionalGeneration"
189
- ],
190
- "bad_words_ids": null,
191
- "begin_suppress_tokens": null,
192
- "bos_token_id": null,
193
- "chunk_size_feed_forward": 0,
194
- "cross_attention_hidden_size": null,
195
- "d_ff": 3072,
196
- "d_kv": 64,
197
- "d_model": 768,
198
- "decoder_start_token_id": 0,
199
- "dense_act_fn": "relu",
200
- "diversity_penalty": 0.0,
201
- "do_sample": false,
202
- "dropout_rate": 0.1,
203
- "early_stopping": false,
204
- "encoder_no_repeat_ngram_size": 0,
205
- "eos_token_id": 1,
206
- "exponential_decay_length_penalty": null,
207
- "feed_forward_proj": "relu",
208
- "finetuning_task": null,
209
- "forced_bos_token_id": null,
210
- "forced_eos_token_id": null,
211
- "id2label": {
212
- "0": "LABEL_0",
213
- "1": "LABEL_1"
214
- },
215
- "initializer_factor": 1.0,
216
- "is_decoder": false,
217
- "is_encoder_decoder": true,
218
- "is_gated_act": false,
219
- "label2id": {
220
- "LABEL_0": 0,
221
- "LABEL_1": 1
222
- },
223
- "layer_norm_epsilon": 1e-06,
224
- "length_penalty": 1.0,
225
- "max_length": 20,
226
- "min_length": 0,
227
- "model_type": "t5",
228
- "n_positions": 512,
229
- "no_repeat_ngram_size": 0,
230
- "num_beam_groups": 1,
231
- "num_beams": 1,
232
- "num_decoder_layers": 12,
233
- "num_heads": 12,
234
- "num_layers": 12,
235
- "num_return_sequences": 1,
236
- "output_attentions": false,
237
- "output_hidden_states": false,
238
- "output_past": true,
239
- "output_scores": false,
240
- "pad_token_id": 0,
241
- "prefix": null,
242
- "problem_type": null,
243
- "pruned_heads": {},
244
- "relative_attention_max_distance": 128,
245
- "relative_attention_num_buckets": 32,
246
- "remove_invalid_values": false,
247
- "repetition_penalty": 1.0,
248
- "return_dict": true,
249
- "return_dict_in_generate": false,
250
- "sep_token_id": null,
251
- "suppress_tokens": null,
252
- "task_specific_params": {
253
- "summarization": {
254
- "early_stopping": true,
255
- "length_penalty": 2.0,
256
- "max_length": 200,
257
- "min_length": 30,
258
- "no_repeat_ngram_size": 3,
259
- "num_beams": 4,
260
- "prefix": "summarize: "
261
- },
262
- "translation_en_to_de": {
263
- "early_stopping": true,
264
- "max_length": 300,
265
- "num_beams": 4,
266
- "prefix": "translate English to German: "
267
- },
268
- "translation_en_to_fr": {
269
- "early_stopping": true,
270
- "max_length": 300,
271
- "num_beams": 4,
272
- "prefix": "translate English to French: "
273
- },
274
- "translation_en_to_ro": {
275
- "early_stopping": true,
276
- "max_length": 300,
277
- "num_beams": 4,
278
- "prefix": "translate English to Romanian: "
279
- }
280
- },
281
- "temperature": 1.0,
282
- "tf_legacy_loss": false,
283
- "tie_encoder_decoder": false,
284
- "tie_word_embeddings": true,
285
- "tokenizer_class": null,
286
- "top_k": 50,
287
- "top_p": 1.0,
288
- "torch_dtype": null,
289
- "torchscript": false,
290
- "transformers_version": "4.38.2",
291
- "typical_p": 1.0,
292
- "use_bfloat16": false,
293
- "use_cache": true,
294
- "vocab_size": 32128
295
- },
296
  "torch_dtype": "float32",
297
- "transformers_version": "4.38.2"
298
  }
 
3
  "architectures": [
4
  "MusicgenForConditionalGeneration"
5
  ],
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6
  "model_type": "musicgen",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7
  "torch_dtype": "float32",
8
+ "transformers_version": null
9
  }