hf-transformers-bot commited on
Commit
b71611b
1 Parent(s): e38c43a

Upload tiny models for MusicgenForConditionalGeneration

Browse files
config.json ADDED
@@ -0,0 +1,264 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "MusicgenForConditionalGeneration"
4
+ ],
5
+ "audio_encoder": {
6
+ "_name_or_path": "",
7
+ "add_cross_attention": false,
8
+ "architectures": null,
9
+ "audio_channels": 1,
10
+ "bad_words_ids": null,
11
+ "begin_suppress_tokens": null,
12
+ "bos_token_id": null,
13
+ "chunk_length_s": null,
14
+ "chunk_size_feed_forward": 0,
15
+ "codebook_dim": 99,
16
+ "codebook_size": 128,
17
+ "compress": 1,
18
+ "cross_attention_hidden_size": null,
19
+ "decoder_start_token_id": null,
20
+ "dilation_growth_rate": 2,
21
+ "diversity_penalty": 0.0,
22
+ "do_sample": false,
23
+ "early_stopping": false,
24
+ "encoder_no_repeat_ngram_size": 0,
25
+ "eos_token_id": null,
26
+ "exponential_decay_length_penalty": null,
27
+ "finetuning_task": null,
28
+ "forced_bos_token_id": null,
29
+ "forced_eos_token_id": null,
30
+ "hidden_size": 99,
31
+ "id2label": {
32
+ "0": "LABEL_0",
33
+ "1": "LABEL_1"
34
+ },
35
+ "is_decoder": false,
36
+ "is_encoder_decoder": false,
37
+ "kernel_size": 7,
38
+ "label2id": {
39
+ "LABEL_0": 0,
40
+ "LABEL_1": 1
41
+ },
42
+ "last_kernel_size": 7,
43
+ "length_penalty": 1.0,
44
+ "max_length": 20,
45
+ "min_length": 0,
46
+ "model_type": "encodec",
47
+ "no_repeat_ngram_size": 0,
48
+ "norm_type": "weight_norm",
49
+ "normalize": false,
50
+ "num_beam_groups": 1,
51
+ "num_beams": 1,
52
+ "num_filters": 4,
53
+ "num_lstm_layers": 2,
54
+ "num_residual_layers": 1,
55
+ "num_return_sequences": 1,
56
+ "output_attentions": false,
57
+ "output_hidden_states": false,
58
+ "output_scores": false,
59
+ "overlap": null,
60
+ "pad_mode": "reflect",
61
+ "pad_token_id": null,
62
+ "prefix": null,
63
+ "problem_type": null,
64
+ "pruned_heads": {},
65
+ "remove_invalid_values": false,
66
+ "repetition_penalty": 1.0,
67
+ "residual_kernel_size": 3,
68
+ "return_dict": true,
69
+ "return_dict_in_generate": false,
70
+ "sampling_rate": 24000,
71
+ "sep_token_id": null,
72
+ "suppress_tokens": null,
73
+ "target_bandwidths": [
74
+ 1.5,
75
+ 3.0,
76
+ 6.0,
77
+ 12.0,
78
+ 24.0
79
+ ],
80
+ "task_specific_params": null,
81
+ "temperature": 1.0,
82
+ "tf_legacy_loss": false,
83
+ "tie_encoder_decoder": false,
84
+ "tie_word_embeddings": true,
85
+ "tokenizer_class": null,
86
+ "top_k": 50,
87
+ "top_p": 1.0,
88
+ "torch_dtype": null,
89
+ "torchscript": false,
90
+ "trim_right_ratio": 1.0,
91
+ "typical_p": 1.0,
92
+ "upsampling_ratios": [
93
+ 8,
94
+ 5,
95
+ 4,
96
+ 2
97
+ ],
98
+ "use_bfloat16": false,
99
+ "use_causal_conv": true,
100
+ "use_conv_shortcut": true
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": 99,
112
+ "chunk_size_feed_forward": 0,
113
+ "cross_attention_hidden_size": null,
114
+ "decoder_start_token_id": 99,
115
+ "diversity_penalty": 0.0,
116
+ "do_sample": false,
117
+ "dropout": 0.1,
118
+ "early_stopping": false,
119
+ "encoder_no_repeat_ngram_size": 0,
120
+ "eos_token_id": null,
121
+ "exponential_decay_length_penalty": null,
122
+ "ffn_dim": 4,
123
+ "finetuning_task": null,
124
+ "forced_bos_token_id": null,
125
+ "forced_eos_token_id": null,
126
+ "hidden_size": 16,
127
+ "id2label": {
128
+ "0": "LABEL_0",
129
+ "1": "LABEL_1"
130
+ },
131
+ "initializer_factor": 0.02,
132
+ "is_decoder": false,
133
+ "is_encoder_decoder": false,
134
+ "label2id": {
135
+ "LABEL_0": 0,
136
+ "LABEL_1": 1
137
+ },
138
+ "layerdrop": 0.0,
139
+ "length_penalty": 1.0,
140
+ "max_length": 20,
141
+ "max_position_embeddings": 2048,
142
+ "min_length": 0,
143
+ "model_type": "musicgen_decoder",
144
+ "no_repeat_ngram_size": 0,
145
+ "num_attention_heads": 4,
146
+ "num_beam_groups": 1,
147
+ "num_beams": 1,
148
+ "num_codebooks": 4,
149
+ "num_hidden_layers": 2,
150
+ "num_return_sequences": 1,
151
+ "output_attentions": false,
152
+ "output_hidden_states": false,
153
+ "output_scores": false,
154
+ "pad_token_id": 99,
155
+ "prefix": null,
156
+ "problem_type": null,
157
+ "pruned_heads": {},
158
+ "remove_invalid_values": false,
159
+ "repetition_penalty": 1.0,
160
+ "return_dict": true,
161
+ "return_dict_in_generate": false,
162
+ "scale_embedding": false,
163
+ "sep_token_id": null,
164
+ "suppress_tokens": null,
165
+ "task_specific_params": null,
166
+ "temperature": 1.0,
167
+ "tf_legacy_loss": false,
168
+ "tie_encoder_decoder": false,
169
+ "tie_word_embeddings": false,
170
+ "tokenizer_class": null,
171
+ "top_k": 50,
172
+ "top_p": 1.0,
173
+ "torch_dtype": null,
174
+ "torchscript": false,
175
+ "typical_p": 1.0,
176
+ "use_bfloat16": false,
177
+ "use_cache": true,
178
+ "vocab_size": 99
179
+ },
180
+ "is_encoder_decoder": true,
181
+ "model_type": "musicgen",
182
+ "text_encoder": {
183
+ "_name_or_path": "",
184
+ "add_cross_attention": false,
185
+ "architectures": null,
186
+ "bad_words_ids": null,
187
+ "begin_suppress_tokens": null,
188
+ "bos_token_id": null,
189
+ "chunk_size_feed_forward": 0,
190
+ "classifier_dropout": 0.0,
191
+ "cross_attention_hidden_size": null,
192
+ "d_ff": 4,
193
+ "d_kv": 64,
194
+ "d_model": 16,
195
+ "decoder_start_token_id": null,
196
+ "dense_act_fn": "relu",
197
+ "diversity_penalty": 0.0,
198
+ "do_sample": false,
199
+ "dropout_rate": 0.1,
200
+ "early_stopping": false,
201
+ "encoder_no_repeat_ngram_size": 0,
202
+ "eos_token_id": 1,
203
+ "exponential_decay_length_penalty": null,
204
+ "feed_forward_proj": "relu",
205
+ "finetuning_task": null,
206
+ "forced_bos_token_id": null,
207
+ "forced_eos_token_id": null,
208
+ "id2label": {
209
+ "0": "LABEL_0",
210
+ "1": "LABEL_1"
211
+ },
212
+ "initializer_factor": 1.0,
213
+ "is_decoder": false,
214
+ "is_encoder_decoder": true,
215
+ "is_gated_act": false,
216
+ "label2id": {
217
+ "LABEL_0": 0,
218
+ "LABEL_1": 1
219
+ },
220
+ "layer_norm_epsilon": 1e-06,
221
+ "length_penalty": 1.0,
222
+ "max_length": 20,
223
+ "min_length": 0,
224
+ "model_type": "t5",
225
+ "no_repeat_ngram_size": 0,
226
+ "num_beam_groups": 1,
227
+ "num_beams": 1,
228
+ "num_decoder_layers": 2,
229
+ "num_heads": 4,
230
+ "num_layers": 2,
231
+ "num_return_sequences": 1,
232
+ "output_attentions": false,
233
+ "output_hidden_states": false,
234
+ "output_scores": false,
235
+ "pad_token_id": 0,
236
+ "prefix": null,
237
+ "problem_type": null,
238
+ "pruned_heads": {},
239
+ "relative_attention_max_distance": 128,
240
+ "relative_attention_num_buckets": 32,
241
+ "remove_invalid_values": false,
242
+ "repetition_penalty": 1.0,
243
+ "return_dict": true,
244
+ "return_dict_in_generate": false,
245
+ "sep_token_id": null,
246
+ "suppress_tokens": null,
247
+ "task_specific_params": null,
248
+ "temperature": 1.0,
249
+ "tf_legacy_loss": false,
250
+ "tie_encoder_decoder": false,
251
+ "tie_word_embeddings": true,
252
+ "tokenizer_class": null,
253
+ "top_k": 50,
254
+ "top_p": 1.0,
255
+ "torch_dtype": null,
256
+ "torchscript": false,
257
+ "typical_p": 1.0,
258
+ "use_bfloat16": false,
259
+ "use_cache": true,
260
+ "vocab_size": 99
261
+ },
262
+ "torch_dtype": "float32",
263
+ "transformers_version": "4.32.0.dev0"
264
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 99,
4
+ "decoder_start_token_id": 99,
5
+ "pad_token_id": 99,
6
+ "transformers_version": "4.32.0.dev0"
7
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27e5470ddc84bcaad00aeecf13d057453e3445385e9075a910f422a06f0378d8
3
+ size 4963125
special_tokens_map.json ADDED
@@ -0,0 +1,107 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<extra_id_0>",
4
+ "<extra_id_1>",
5
+ "<extra_id_2>",
6
+ "<extra_id_3>",
7
+ "<extra_id_4>",
8
+ "<extra_id_5>",
9
+ "<extra_id_6>",
10
+ "<extra_id_7>",
11
+ "<extra_id_8>",
12
+ "<extra_id_9>",
13
+ "<extra_id_10>",
14
+ "<extra_id_11>",
15
+ "<extra_id_12>",
16
+ "<extra_id_13>",
17
+ "<extra_id_14>",
18
+ "<extra_id_15>",
19
+ "<extra_id_16>",
20
+ "<extra_id_17>",
21
+ "<extra_id_18>",
22
+ "<extra_id_19>",
23
+ "<extra_id_20>",
24
+ "<extra_id_21>",
25
+ "<extra_id_22>",
26
+ "<extra_id_23>",
27
+ "<extra_id_24>",
28
+ "<extra_id_25>",
29
+ "<extra_id_26>",
30
+ "<extra_id_27>",
31
+ "<extra_id_28>",
32
+ "<extra_id_29>",
33
+ "<extra_id_30>",
34
+ "<extra_id_31>",
35
+ "<extra_id_32>",
36
+ "<extra_id_33>",
37
+ "<extra_id_34>",
38
+ "<extra_id_35>",
39
+ "<extra_id_36>",
40
+ "<extra_id_37>",
41
+ "<extra_id_38>",
42
+ "<extra_id_39>",
43
+ "<extra_id_40>",
44
+ "<extra_id_41>",
45
+ "<extra_id_42>",
46
+ "<extra_id_43>",
47
+ "<extra_id_44>",
48
+ "<extra_id_45>",
49
+ "<extra_id_46>",
50
+ "<extra_id_47>",
51
+ "<extra_id_48>",
52
+ "<extra_id_49>",
53
+ "<extra_id_50>",
54
+ "<extra_id_51>",
55
+ "<extra_id_52>",
56
+ "<extra_id_53>",
57
+ "<extra_id_54>",
58
+ "<extra_id_55>",
59
+ "<extra_id_56>",
60
+ "<extra_id_57>",
61
+ "<extra_id_58>",
62
+ "<extra_id_59>",
63
+ "<extra_id_60>",
64
+ "<extra_id_61>",
65
+ "<extra_id_62>",
66
+ "<extra_id_63>",
67
+ "<extra_id_64>",
68
+ "<extra_id_65>",
69
+ "<extra_id_66>",
70
+ "<extra_id_67>",
71
+ "<extra_id_68>",
72
+ "<extra_id_69>",
73
+ "<extra_id_70>",
74
+ "<extra_id_71>",
75
+ "<extra_id_72>",
76
+ "<extra_id_73>",
77
+ "<extra_id_74>",
78
+ "<extra_id_75>",
79
+ "<extra_id_76>",
80
+ "<extra_id_77>",
81
+ "<extra_id_78>",
82
+ "<extra_id_79>",
83
+ "<extra_id_80>",
84
+ "<extra_id_81>",
85
+ "<extra_id_82>",
86
+ "<extra_id_83>",
87
+ "<extra_id_84>",
88
+ "<extra_id_85>",
89
+ "<extra_id_86>",
90
+ "<extra_id_87>",
91
+ "<extra_id_88>",
92
+ "<extra_id_89>",
93
+ "<extra_id_90>",
94
+ "<extra_id_91>",
95
+ "<extra_id_92>",
96
+ "<extra_id_93>",
97
+ "<extra_id_94>",
98
+ "<extra_id_95>",
99
+ "<extra_id_96>",
100
+ "<extra_id_97>",
101
+ "<extra_id_98>",
102
+ "<extra_id_99>"
103
+ ],
104
+ "eos_token": "</s>",
105
+ "pad_token": "<pad>",
106
+ "unk_token": "<unk>"
107
+ }
spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
3
+ size 791656
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,113 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<extra_id_0>",
4
+ "<extra_id_1>",
5
+ "<extra_id_2>",
6
+ "<extra_id_3>",
7
+ "<extra_id_4>",
8
+ "<extra_id_5>",
9
+ "<extra_id_6>",
10
+ "<extra_id_7>",
11
+ "<extra_id_8>",
12
+ "<extra_id_9>",
13
+ "<extra_id_10>",
14
+ "<extra_id_11>",
15
+ "<extra_id_12>",
16
+ "<extra_id_13>",
17
+ "<extra_id_14>",
18
+ "<extra_id_15>",
19
+ "<extra_id_16>",
20
+ "<extra_id_17>",
21
+ "<extra_id_18>",
22
+ "<extra_id_19>",
23
+ "<extra_id_20>",
24
+ "<extra_id_21>",
25
+ "<extra_id_22>",
26
+ "<extra_id_23>",
27
+ "<extra_id_24>",
28
+ "<extra_id_25>",
29
+ "<extra_id_26>",
30
+ "<extra_id_27>",
31
+ "<extra_id_28>",
32
+ "<extra_id_29>",
33
+ "<extra_id_30>",
34
+ "<extra_id_31>",
35
+ "<extra_id_32>",
36
+ "<extra_id_33>",
37
+ "<extra_id_34>",
38
+ "<extra_id_35>",
39
+ "<extra_id_36>",
40
+ "<extra_id_37>",
41
+ "<extra_id_38>",
42
+ "<extra_id_39>",
43
+ "<extra_id_40>",
44
+ "<extra_id_41>",
45
+ "<extra_id_42>",
46
+ "<extra_id_43>",
47
+ "<extra_id_44>",
48
+ "<extra_id_45>",
49
+ "<extra_id_46>",
50
+ "<extra_id_47>",
51
+ "<extra_id_48>",
52
+ "<extra_id_49>",
53
+ "<extra_id_50>",
54
+ "<extra_id_51>",
55
+ "<extra_id_52>",
56
+ "<extra_id_53>",
57
+ "<extra_id_54>",
58
+ "<extra_id_55>",
59
+ "<extra_id_56>",
60
+ "<extra_id_57>",
61
+ "<extra_id_58>",
62
+ "<extra_id_59>",
63
+ "<extra_id_60>",
64
+ "<extra_id_61>",
65
+ "<extra_id_62>",
66
+ "<extra_id_63>",
67
+ "<extra_id_64>",
68
+ "<extra_id_65>",
69
+ "<extra_id_66>",
70
+ "<extra_id_67>",
71
+ "<extra_id_68>",
72
+ "<extra_id_69>",
73
+ "<extra_id_70>",
74
+ "<extra_id_71>",
75
+ "<extra_id_72>",
76
+ "<extra_id_73>",
77
+ "<extra_id_74>",
78
+ "<extra_id_75>",
79
+ "<extra_id_76>",
80
+ "<extra_id_77>",
81
+ "<extra_id_78>",
82
+ "<extra_id_79>",
83
+ "<extra_id_80>",
84
+ "<extra_id_81>",
85
+ "<extra_id_82>",
86
+ "<extra_id_83>",
87
+ "<extra_id_84>",
88
+ "<extra_id_85>",
89
+ "<extra_id_86>",
90
+ "<extra_id_87>",
91
+ "<extra_id_88>",
92
+ "<extra_id_89>",
93
+ "<extra_id_90>",
94
+ "<extra_id_91>",
95
+ "<extra_id_92>",
96
+ "<extra_id_93>",
97
+ "<extra_id_94>",
98
+ "<extra_id_95>",
99
+ "<extra_id_96>",
100
+ "<extra_id_97>",
101
+ "<extra_id_98>",
102
+ "<extra_id_99>"
103
+ ],
104
+ "clean_up_tokenization_spaces": true,
105
+ "eos_token": "</s>",
106
+ "extra_ids": 100,
107
+ "legacy": true,
108
+ "model_max_length": 512,
109
+ "pad_token": "<pad>",
110
+ "sp_model_kwargs": {},
111
+ "tokenizer_class": "T5Tokenizer",
112
+ "unk_token": "<unk>"
113
+ }