pharoAIsanders420 commited on
Commit
320a25d
1 Parent(s): 219ce45

Upload 9 files

Browse files
build_delay_pattern_mask.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4426d3771049f337d647700b57da35b6a0efe71b45c5a4ff232b5c541e0929f5
3
+ size 35354
config.json ADDED
@@ -0,0 +1,295 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "pharoAIsanders420/musicgen-tiny-jungle",
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
+ "trim_right_ratio": 1.0,
90
+ "typical_p": 1.0,
91
+ "upsampling_ratios": [
92
+ 8,
93
+ 5,
94
+ 4,
95
+ 4
96
+ ],
97
+ "use_bfloat16": false,
98
+ "use_causal_conv": false,
99
+ "use_conv_shortcut": false
100
+ },
101
+ "decoder": {
102
+ "_name_or_path": "",
103
+ "activation_dropout": 0.0,
104
+ "activation_function": "gelu",
105
+ "add_cross_attention": false,
106
+ "architectures": null,
107
+ "attention_dropout": 0.0,
108
+ "audio_channels": 1,
109
+ "bad_words_ids": null,
110
+ "begin_suppress_tokens": null,
111
+ "bos_token_id": 2048,
112
+ "chunk_size_feed_forward": 0,
113
+ "cross_attention_hidden_size": null,
114
+ "decoder_start_token_id": null,
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": 8192,
123
+ "finetuning_task": null,
124
+ "forced_bos_token_id": null,
125
+ "forced_eos_token_id": null,
126
+ "hidden_size": 2048,
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": 2,
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": 2048,
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": 2048
179
+ },
180
+ "is_encoder_decoder": true,
181
+ "model_type": "musicgen",
182
+ "text_encoder": {
183
+ "_name_or_path": "google-t5/t5-base",
184
+ "add_cross_attention": false,
185
+ "architectures": [
186
+ "T5ForConditionalGeneration"
187
+ ],
188
+ "bad_words_ids": null,
189
+ "begin_suppress_tokens": null,
190
+ "bos_token_id": null,
191
+ "chunk_size_feed_forward": 0,
192
+ "classifier_dropout": 0.0,
193
+ "cross_attention_hidden_size": null,
194
+ "d_ff": 3072,
195
+ "d_kv": 64,
196
+ "d_model": 768,
197
+ "decoder_start_token_id": 0,
198
+ "dense_act_fn": "relu",
199
+ "diversity_penalty": 0.0,
200
+ "do_sample": false,
201
+ "dropout_rate": 0.1,
202
+ "early_stopping": false,
203
+ "encoder_no_repeat_ngram_size": 0,
204
+ "eos_token_id": 1,
205
+ "exponential_decay_length_penalty": null,
206
+ "feed_forward_proj": "relu",
207
+ "finetuning_task": null,
208
+ "forced_bos_token_id": null,
209
+ "forced_eos_token_id": null,
210
+ "id2label": {
211
+ "0": "LABEL_0",
212
+ "1": "LABEL_1"
213
+ },
214
+ "initializer_factor": 1.0,
215
+ "is_decoder": false,
216
+ "is_encoder_decoder": true,
217
+ "is_gated_act": false,
218
+ "label2id": {
219
+ "LABEL_0": 0,
220
+ "LABEL_1": 1
221
+ },
222
+ "layer_norm_epsilon": 1e-06,
223
+ "length_penalty": 1.0,
224
+ "max_length": 20,
225
+ "min_length": 0,
226
+ "model_type": "t5",
227
+ "n_positions": 512,
228
+ "no_repeat_ngram_size": 0,
229
+ "num_beam_groups": 1,
230
+ "num_beams": 1,
231
+ "num_decoder_layers": 12,
232
+ "num_heads": 12,
233
+ "num_layers": 12,
234
+ "num_return_sequences": 1,
235
+ "output_attentions": false,
236
+ "output_hidden_states": false,
237
+ "output_past": true,
238
+ "output_scores": false,
239
+ "pad_token_id": 0,
240
+ "prefix": null,
241
+ "problem_type": null,
242
+ "pruned_heads": {},
243
+ "relative_attention_max_distance": 128,
244
+ "relative_attention_num_buckets": 32,
245
+ "remove_invalid_values": false,
246
+ "repetition_penalty": 1.0,
247
+ "return_dict": true,
248
+ "return_dict_in_generate": false,
249
+ "sep_token_id": null,
250
+ "suppress_tokens": null,
251
+ "task_specific_params": {
252
+ "summarization": {
253
+ "early_stopping": true,
254
+ "length_penalty": 2.0,
255
+ "max_length": 200,
256
+ "min_length": 30,
257
+ "no_repeat_ngram_size": 3,
258
+ "num_beams": 4,
259
+ "prefix": "summarize: "
260
+ },
261
+ "translation_en_to_de": {
262
+ "early_stopping": true,
263
+ "max_length": 300,
264
+ "num_beams": 4,
265
+ "prefix": "translate English to German: "
266
+ },
267
+ "translation_en_to_fr": {
268
+ "early_stopping": true,
269
+ "max_length": 300,
270
+ "num_beams": 4,
271
+ "prefix": "translate English to French: "
272
+ },
273
+ "translation_en_to_ro": {
274
+ "early_stopping": true,
275
+ "max_length": 300,
276
+ "num_beams": 4,
277
+ "prefix": "translate English to Romanian: "
278
+ }
279
+ },
280
+ "temperature": 1.0,
281
+ "tf_legacy_loss": false,
282
+ "tie_encoder_decoder": false,
283
+ "tie_word_embeddings": true,
284
+ "tokenizer_class": null,
285
+ "top_k": 50,
286
+ "top_p": 1.0,
287
+ "torch_dtype": null,
288
+ "torchscript": false,
289
+ "typical_p": 1.0,
290
+ "use_bfloat16": false,
291
+ "use_cache": true,
292
+ "vocab_size": 32128
293
+ },
294
+ "transformers_version": "4.39.3"
295
+ }
decoder_model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ea1913aaa4f7410c8217160aa43e04d24a5def0b9b21a893f481d96300d7ca8
3
+ size 694425570
decoder_model_merged.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:17a744d8c7377456505438206d9f0d0df4d6499455c8617669a0c21bde5cd1d3
3
+ size 694532018
decoder_with_past_model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ea4ca943ebd610bb86a8e0ba00abd650bb91fa2070a78ce419e8b6c0fe0b490
3
+ size 620993470
encodec_decode.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6a9a1da30ca2f31d6d2468d3b431065186b8588ffb6a1b4955593ea8f5562e1
3
+ size 118034595
generation_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 2048,
4
+ "decoder_start_token_id": 2048,
5
+ "do_sample": true,
6
+ "guidance_scale": 3.0,
7
+ "max_length": 1500,
8
+ "pad_token_id": 2048,
9
+ "transformers_version": "4.39.3"
10
+ }
preprocessor_config.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "chunk_length_s": null,
3
+ "feature_extractor_type": "EncodecFeatureExtractor",
4
+ "feature_size": 1,
5
+ "overlap": null,
6
+ "padding_side": "left",
7
+ "padding_value": 0.0,
8
+ "processor_class": "MusicgenProcessor",
9
+ "return_attention_mask": true,
10
+ "sampling_rate": 32000
11
+ }
text_encoder.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55c7354455489649217e3fcc0777259fdfdc67f89dce8d92f543812e2228dd0e
3
+ size 438689759