Hugging Face's logo

ylacombe
/
musicgen-melody-punk-lora

Text-to-Audio
PEFT
Safetensors
musicgen_melody
ylacombe/tiny-punk
Generated from Trainer
Model card Files Community
ylacombe HF staff commited on
Commit
339487e
•
1 Parent(s): f58acad

Model save

Browse files
Files changed (18) hide show
  1. README.md +57 -0
  2. adapter_config.json +46 -0
  3. adapter_model.safetensors +3 -0
  4. all_results.json +15 -0
  5. config.json +299 -0
  6. eval_results.json +9 -0
  7. generation_config.json +9 -0
  8. model-00001-of-00002.safetensors +3 -0
  9. model-00002-of-00002.safetensors +3 -0
  10. model.safetensors.index.json +717 -0
  11. preprocessor_config.json +17 -0
  12. special_tokens_map.json +125 -0
  13. spiece.model +3 -0
  14. tokenizer.json +0 -0
  15. tokenizer_config.json +942 -0
  16. train_results.json +9 -0
  17. trainer_state.json +30 -0
  18. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: cc-by-nc-4.0
3
+ library_name: peft
4
+ tags:
5
+ - generated_from_trainer
6
+ base_model: facebook/musicgen-melody
7
+ model-index:
8
+ - name: musicgen-melody-punk-lora
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ # musicgen-melody-punk-lora
16
+
17
+ This model is a fine-tuned version of [facebook/musicgen-melody](https://huggingface.co/facebook/musicgen-melody) on an unknown dataset.
18
+
19
+ ## Model description
20
+
21
+ More information needed
22
+
23
+ ## Intended uses & limitations
24
+
25
+ More information needed
26
+
27
+ ## Training and evaluation data
28
+
29
+ More information needed
30
+
31
+ ## Training procedure
32
+
33
+ ### Training hyperparameters
34
+
35
+ The following hyperparameters were used during training:
36
+ - learning_rate: 0.0002
37
+ - train_batch_size: 2
38
+ - eval_batch_size: 1
39
+ - seed: 456
40
+ - gradient_accumulation_steps: 8
41
+ - total_train_batch_size: 16
42
+ - optimizer: Adam with betas=(0.9,0.99) and epsilon=1e-08
43
+ - lr_scheduler_type: linear
44
+ - num_epochs: 4
45
+ - mixed_precision_training: Native AMP
46
+
47
+ ### Training results
48
+
49
+
50
+
51
+ ### Framework versions
52
+
53
+ - PEFT 0.10.0
54
+ - Transformers 4.40.0.dev0
55
+ - Pytorch 2.1.2+cu121
56
+ - Datasets 2.18.0
57
+ - Tokenizers 0.19.1
adapter_config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": {
4
+ "base_model_class": "MusicgenMelodyForConditionalGeneration",
5
+ "parent_library": "transformers.models.musicgen_melody.modeling_musicgen_melody"
6
+ },
7
+ "base_model_name_or_path": "facebook/musicgen-melody",
8
+ "bias": "none",
9
+ "fan_in_fan_out": false,
10
+ "inference_mode": true,
11
+ "init_lora_weights": true,
12
+ "layer_replication": null,
13
+ "layers_pattern": null,
14
+ "layers_to_transform": null,
15
+ "loftq_config": {},
16
+ "lora_alpha": 16,
17
+ "lora_dropout": 0.05,
18
+ "megatron_config": null,
19
+ "megatron_core": "megatron.core",
20
+ "modules_to_save": null,
21
+ "peft_type": "LORA",
22
+ "r": 16,
23
+ "rank_pattern": {},
24
+ "revision": null,
25
+ "target_modules": [
26
+ "enc_to_dec_proj",
27
+ "out_proj",
28
+ "fc2",
29
+ "lm_heads.3",
30
+ "lm_heads.2",
31
+ "embed_tokens.0",
32
+ "lm_heads.1",
33
+ "q_proj",
34
+ "k_proj",
35
+ "fc1",
36
+ "embed_tokens.2",
37
+ "embed_tokens.3",
38
+ "v_proj",
39
+ "lm_heads.0",
40
+ "audio_enc_to_dec_proj",
41
+ "embed_tokens.1"
42
+ ],
43
+ "task_type": null,
44
+ "use_dora": false,
45
+ "use_rslora": false
46
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78b66138da22e547a9045f9b37fbf37b27e087670b0dc0350582fa254d5ee26b
3
+ size 87103456
all_results.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.764705882352941,
3
+ "eval_clap": 0.3365415632724762,
4
+ "eval_loss": 4.704524993896484,
5
+ "eval_runtime": 147.6762,
6
+ "eval_samples": 5,
7
+ "eval_samples_per_second": 0.034,
8
+ "eval_steps_per_second": 0.034,
9
+ "total_flos": 59875624258368.0,
10
+ "train_loss": 8.819526672363281,
11
+ "train_runtime": 269.5748,
12
+ "train_samples": 33,
13
+ "train_samples_per_second": 0.49,
14
+ "train_steps_per_second": 0.03
15
+ }
config.json ADDED
@@ -0,0 +1,299 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/musicgen-melody-large",
3
+ "architectures": [
4
+ "MusicgenMelodyForConditionalGeneration"
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
+ "chroma_length": 235,
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
+ "audio_channels": 1,
110
+ "bad_words_ids": null,
111
+ "begin_suppress_tokens": null,
112
+ "bos_token_id": 2048,
113
+ "chunk_size_feed_forward": 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": 8192,
124
+ "finetuning_task": null,
125
+ "forced_bos_token_id": null,
126
+ "forced_eos_token_id": null,
127
+ "hidden_size": 2048,
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_melody_decoder",
145
+ "no_repeat_ngram_size": 0,
146
+ "num_attention_heads": 32,
147
+ "num_beam_groups": 1,
148
+ "num_beams": 1,
149
+ "num_codebooks": 4,
150
+ "num_hidden_layers": 48,
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
+ "typical_p": 1.0,
177
+ "use_bfloat16": false,
178
+ "use_cache": true,
179
+ "vocab_size": 2048
180
+ },
181
+ "decoder_start_token_id": 2048,
182
+ "model_type": "musicgen_melody",
183
+ "num_chroma": 12,
184
+ "pad_token_id": 2048,
185
+ "text_encoder": {
186
+ "_name_or_path": "t5-base",
187
+ "add_cross_attention": false,
188
+ "architectures": [
189
+ "T5ForConditionalGeneration"
190
+ ],
191
+ "bad_words_ids": null,
192
+ "begin_suppress_tokens": null,
193
+ "bos_token_id": null,
194
+ "chunk_size_feed_forward": 0,
195
+ "classifier_dropout": 0.0,
196
+ "cross_attention_hidden_size": null,
197
+ "d_ff": 3072,
198
+ "d_kv": 64,
199
+ "d_model": 768,
200
+ "decoder_start_token_id": 0,
201
+ "dense_act_fn": "relu",
202
+ "diversity_penalty": 0.0,
203
+ "do_sample": false,
204
+ "dropout_rate": 0.1,
205
+ "early_stopping": false,
206
+ "encoder_no_repeat_ngram_size": 0,
207
+ "eos_token_id": 1,
208
+ "exponential_decay_length_penalty": null,
209
+ "feed_forward_proj": "relu",
210
+ "finetuning_task": null,
211
+ "forced_bos_token_id": null,
212
+ "forced_eos_token_id": null,
213
+ "id2label": {
214
+ "0": "LABEL_0",
215
+ "1": "LABEL_1"
216
+ },
217
+ "initializer_factor": 1.0,
218
+ "is_decoder": false,
219
+ "is_encoder_decoder": true,
220
+ "is_gated_act": false,
221
+ "label2id": {
222
+ "LABEL_0": 0,
223
+ "LABEL_1": 1
224
+ },
225
+ "layer_norm_epsilon": 1e-06,
226
+ "length_penalty": 1.0,
227
+ "max_length": 20,
228
+ "min_length": 0,
229
+ "model_type": "t5",
230
+ "n_positions": 512,
231
+ "no_repeat_ngram_size": 0,
232
+ "num_beam_groups": 1,
233
+ "num_beams": 1,
234
+ "num_decoder_layers": 12,
235
+ "num_heads": 12,
236
+ "num_layers": 12,
237
+ "num_return_sequences": 1,
238
+ "output_attentions": false,
239
+ "output_hidden_states": false,
240
+ "output_past": true,
241
+ "output_scores": false,
242
+ "pad_token_id": 0,
243
+ "prefix": null,
244
+ "problem_type": null,
245
+ "pruned_heads": {},
246
+ "relative_attention_max_distance": 128,
247
+ "relative_attention_num_buckets": 32,
248
+ "remove_invalid_values": false,
249
+ "repetition_penalty": 1.0,
250
+ "return_dict": true,
251
+ "return_dict_in_generate": false,
252
+ "sep_token_id": null,
253
+ "suppress_tokens": null,
254
+ "task_specific_params": {
255
+ "summarization": {
256
+ "early_stopping": true,
257
+ "length_penalty": 2.0,
258
+ "max_length": 200,
259
+ "min_length": 30,
260
+ "no_repeat_ngram_size": 3,
261
+ "num_beams": 4,
262
+ "prefix": "summarize: "
263
+ },
264
+ "translation_en_to_de": {
265
+ "early_stopping": true,
266
+ "max_length": 300,
267
+ "num_beams": 4,
268
+ "prefix": "translate English to German: "
269
+ },
270
+ "translation_en_to_fr": {
271
+ "early_stopping": true,
272
+ "max_length": 300,
273
+ "num_beams": 4,
274
+ "prefix": "translate English to French: "
275
+ },
276
+ "translation_en_to_ro": {
277
+ "early_stopping": true,
278
+ "max_length": 300,
279
+ "num_beams": 4,
280
+ "prefix": "translate English to Romanian: "
281
+ }
282
+ },
283
+ "temperature": 1.0,
284
+ "tf_legacy_loss": false,
285
+ "tie_encoder_decoder": false,
286
+ "tie_word_embeddings": true,
287
+ "tokenizer_class": null,
288
+ "top_k": 50,
289
+ "top_p": 1.0,
290
+ "torch_dtype": null,
291
+ "torchscript": false,
292
+ "typical_p": 1.0,
293
+ "use_bfloat16": false,
294
+ "use_cache": true,
295
+ "vocab_size": 32128
296
+ },
297
+ "torch_dtype": "float32",
298
+ "transformers_version": "4.40.0.dev0"
299
+ }
eval_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.764705882352941,
3
+ "eval_clap": 0.3365415632724762,
4
+ "eval_loss": 4.704524993896484,
5
+ "eval_runtime": 147.6762,
6
+ "eval_samples": 5,
7
+ "eval_samples_per_second": 0.034,
8
+ "eval_steps_per_second": 0.034
9
+ }
generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 2048,
3
+ "decoder_start_token_id": 2048,
4
+ "do_sample": true,
5
+ "guidance_scale": 3.0,
6
+ "max_length": 1500,
7
+ "pad_token_id": 2048,
8
+ "transformers_version": "4.40.0.dev0"
9
+ }
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6610b21d2b0da10c212aa63ddaa43b9d9578c2606a5fcc6f10e818f4b39be3e
3
+ size 4966269512
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bdf7b00866034c7908b8bcff3b69ddeba3743235afb667a529411a6370a161d0
3
+ size 1263380400
model.safetensors.index.json ADDED
@@ -0,0 +1,717 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 6229559576
4
+ },
5
+ "weight_map": {
6
+ "audio_enc_to_dec_proj.bias": "model-00002-of-00002.safetensors",
7
+ "audio_enc_to_dec_proj.weight": "model-00002-of-00002.safetensors",
8
+ "audio_encoder.decoder.layers.0.conv.bias": "model-00001-of-00002.safetensors",
9
+ "audio_encoder.decoder.layers.0.conv.weight_g": "model-00001-of-00002.safetensors",
10
+ "audio_encoder.decoder.layers.0.conv.weight_v": "model-00001-of-00002.safetensors",
11
+ "audio_encoder.decoder.layers.1.lstm.bias_hh_l0": "model-00001-of-00002.safetensors",
12
+ "audio_encoder.decoder.layers.1.lstm.bias_hh_l1": "model-00001-of-00002.safetensors",
13
+ "audio_encoder.decoder.layers.1.lstm.bias_ih_l0": "model-00001-of-00002.safetensors",
14
+ "audio_encoder.decoder.layers.1.lstm.bias_ih_l1": "model-00001-of-00002.safetensors",
15
+ "audio_encoder.decoder.layers.1.lstm.weight_hh_l0": "model-00001-of-00002.safetensors",
16
+ "audio_encoder.decoder.layers.1.lstm.weight_hh_l1": "model-00001-of-00002.safetensors",
17
+ "audio_encoder.decoder.layers.1.lstm.weight_ih_l0": "model-00001-of-00002.safetensors",
18
+ "audio_encoder.decoder.layers.1.lstm.weight_ih_l1": "model-00001-of-00002.safetensors",
19
+ "audio_encoder.decoder.layers.10.block.1.conv.bias": "model-00001-of-00002.safetensors",
20
+ "audio_encoder.decoder.layers.10.block.1.conv.weight_g": "model-00001-of-00002.safetensors",
21
+ "audio_encoder.decoder.layers.10.block.1.conv.weight_v": "model-00001-of-00002.safetensors",
22
+ "audio_encoder.decoder.layers.10.block.3.conv.bias": "model-00001-of-00002.safetensors",
23
+ "audio_encoder.decoder.layers.10.block.3.conv.weight_g": "model-00001-of-00002.safetensors",
24
+ "audio_encoder.decoder.layers.10.block.3.conv.weight_v": "model-00001-of-00002.safetensors",
25
+ "audio_encoder.decoder.layers.12.conv.bias": "model-00001-of-00002.safetensors",
26
+ "audio_encoder.decoder.layers.12.conv.weight_g": "model-00001-of-00002.safetensors",
27
+ "audio_encoder.decoder.layers.12.conv.weight_v": "model-00001-of-00002.safetensors",
28
+ "audio_encoder.decoder.layers.13.block.1.conv.bias": "model-00001-of-00002.safetensors",
29
+ "audio_encoder.decoder.layers.13.block.1.conv.weight_g": "model-00001-of-00002.safetensors",
30
+ "audio_encoder.decoder.layers.13.block.1.conv.weight_v": "model-00001-of-00002.safetensors",
31
+ "audio_encoder.decoder.layers.13.block.3.conv.bias": "model-00001-of-00002.safetensors",
32
+ "audio_encoder.decoder.layers.13.block.3.conv.weight_g": "model-00001-of-00002.safetensors",
33
+ "audio_encoder.decoder.layers.13.block.3.conv.weight_v": "model-00001-of-00002.safetensors",
34
+ "audio_encoder.decoder.layers.15.conv.bias": "model-00001-of-00002.safetensors",
35
+ "audio_encoder.decoder.layers.15.conv.weight_g": "model-00001-of-00002.safetensors",
36
+ "audio_encoder.decoder.layers.15.conv.weight_v": "model-00001-of-00002.safetensors",
37
+ "audio_encoder.decoder.layers.3.conv.bias": "model-00001-of-00002.safetensors",
38
+ "audio_encoder.decoder.layers.3.conv.weight_g": "model-00001-of-00002.safetensors",
39
+ "audio_encoder.decoder.layers.3.conv.weight_v": "model-00001-of-00002.safetensors",
40
+ "audio_encoder.decoder.layers.4.block.1.conv.bias": "model-00001-of-00002.safetensors",
41
+ "audio_encoder.decoder.layers.4.block.1.conv.weight_g": "model-00001-of-00002.safetensors",
42
+ "audio_encoder.decoder.layers.4.block.1.conv.weight_v": "model-00001-of-00002.safetensors",
43
+ "audio_encoder.decoder.layers.4.block.3.conv.bias": "model-00001-of-00002.safetensors",
44
+ "audio_encoder.decoder.layers.4.block.3.conv.weight_g": "model-00001-of-00002.safetensors",
45
+ "audio_encoder.decoder.layers.4.block.3.conv.weight_v": "model-00001-of-00002.safetensors",
46
+ "audio_encoder.decoder.layers.6.conv.bias": "model-00001-of-00002.safetensors",
47
+ "audio_encoder.decoder.layers.6.conv.weight_g": "model-00001-of-00002.safetensors",
48
+ "audio_encoder.decoder.layers.6.conv.weight_v": "model-00001-of-00002.safetensors",
49
+ "audio_encoder.decoder.layers.7.block.1.conv.bias": "model-00001-of-00002.safetensors",
50
+ "audio_encoder.decoder.layers.7.block.1.conv.weight_g": "model-00001-of-00002.safetensors",
51
+ "audio_encoder.decoder.layers.7.block.1.conv.weight_v": "model-00001-of-00002.safetensors",
52
+ "audio_encoder.decoder.layers.7.block.3.conv.bias": "model-00001-of-00002.safetensors",
53
+ "audio_encoder.decoder.layers.7.block.3.conv.weight_g": "model-00001-of-00002.safetensors",
54
+ "audio_encoder.decoder.layers.7.block.3.conv.weight_v": "model-00001-of-00002.safetensors",
55
+ "audio_encoder.decoder.layers.9.conv.bias": "model-00001-of-00002.safetensors",
56
+ "audio_encoder.decoder.layers.9.conv.weight_g": "model-00001-of-00002.safetensors",
57
+ "audio_encoder.decoder.layers.9.conv.weight_v": "model-00001-of-00002.safetensors",
58
+ "audio_encoder.encoder.layers.0.conv.bias": "model-00001-of-00002.safetensors",
59
+ "audio_encoder.encoder.layers.0.conv.weight_g": "model-00001-of-00002.safetensors",
60
+ "audio_encoder.encoder.layers.0.conv.weight_v": "model-00001-of-00002.safetensors",
61
+ "audio_encoder.encoder.layers.1.block.1.conv.bias": "model-00001-of-00002.safetensors",
62
+ "audio_encoder.encoder.layers.1.block.1.conv.weight_g": "model-00001-of-00002.safetensors",
63
+ "audio_encoder.encoder.layers.1.block.1.conv.weight_v": "model-00001-of-00002.safetensors",
64
+ "audio_encoder.encoder.layers.1.block.3.conv.bias": "model-00001-of-00002.safetensors",
65
+ "audio_encoder.encoder.layers.1.block.3.conv.weight_g": "model-00001-of-00002.safetensors",
66
+ "audio_encoder.encoder.layers.1.block.3.conv.weight_v": "model-00001-of-00002.safetensors",
67
+ "audio_encoder.encoder.layers.10.block.1.conv.bias": "model-00001-of-00002.safetensors",
68
+ "audio_encoder.encoder.layers.10.block.1.conv.weight_g": "model-00001-of-00002.safetensors",
69
+ "audio_encoder.encoder.layers.10.block.1.conv.weight_v": "model-00001-of-00002.safetensors",
70
+ "audio_encoder.encoder.layers.10.block.3.conv.bias": "model-00001-of-00002.safetensors",
71
+ "audio_encoder.encoder.layers.10.block.3.conv.weight_g": "model-00001-of-00002.safetensors",
72
+ "audio_encoder.encoder.layers.10.block.3.conv.weight_v": "model-00001-of-00002.safetensors",
73
+ "audio_encoder.encoder.layers.12.conv.bias": "model-00001-of-00002.safetensors",
74
+ "audio_encoder.encoder.layers.12.conv.weight_g": "model-00001-of-00002.safetensors",
75
+ "audio_encoder.encoder.layers.12.conv.weight_v": "model-00001-of-00002.safetensors",
76
+ "audio_encoder.encoder.layers.13.lstm.bias_hh_l0": "model-00001-of-00002.safetensors",
77
+ "audio_encoder.encoder.layers.13.lstm.bias_hh_l1": "model-00001-of-00002.safetensors",
78
+ "audio_encoder.encoder.layers.13.lstm.bias_ih_l0": "model-00001-of-00002.safetensors",
79
+ "audio_encoder.encoder.layers.13.lstm.bias_ih_l1": "model-00001-of-00002.safetensors",
80
+ "audio_encoder.encoder.layers.13.lstm.weight_hh_l0": "model-00001-of-00002.safetensors",
81
+ "audio_encoder.encoder.layers.13.lstm.weight_hh_l1": "model-00001-of-00002.safetensors",
82
+ "audio_encoder.encoder.layers.13.lstm.weight_ih_l0": "model-00001-of-00002.safetensors",
83
+ "audio_encoder.encoder.layers.13.lstm.weight_ih_l1": "model-00001-of-00002.safetensors",
84
+ "audio_encoder.encoder.layers.15.conv.bias": "model-00001-of-00002.safetensors",
85
+ "audio_encoder.encoder.layers.15.conv.weight_g": "model-00001-of-00002.safetensors",
86
+ "audio_encoder.encoder.layers.15.conv.weight_v": "model-00001-of-00002.safetensors",
87
+ "audio_encoder.encoder.layers.3.conv.bias": "model-00001-of-00002.safetensors",
88
+ "audio_encoder.encoder.layers.3.conv.weight_g": "model-00001-of-00002.safetensors",
89
+ "audio_encoder.encoder.layers.3.conv.weight_v": "model-00001-of-00002.safetensors",
90
+ "audio_encoder.encoder.layers.4.block.1.conv.bias": "model-00001-of-00002.safetensors",
91
+ "audio_encoder.encoder.layers.4.block.1.conv.weight_g": "model-00001-of-00002.safetensors",
92
+ "audio_encoder.encoder.layers.4.block.1.conv.weight_v": "model-00001-of-00002.safetensors",
93
+ "audio_encoder.encoder.layers.4.block.3.conv.bias": "model-00001-of-00002.safetensors",
94
+ "audio_encoder.encoder.layers.4.block.3.conv.weight_g": "model-00001-of-00002.safetensors",
95
+ "audio_encoder.encoder.layers.4.block.3.conv.weight_v": "model-00001-of-00002.safetensors",
96
+ "audio_encoder.encoder.layers.6.conv.bias": "model-00001-of-00002.safetensors",
97
+ "audio_encoder.encoder.layers.6.conv.weight_g": "model-00001-of-00002.safetensors",
98
+ "audio_encoder.encoder.layers.6.conv.weight_v": "model-00001-of-00002.safetensors",
99
+ "audio_encoder.encoder.layers.7.block.1.conv.bias": "model-00001-of-00002.safetensors",
100
+ "audio_encoder.encoder.layers.7.block.1.conv.weight_g": "model-00001-of-00002.safetensors",
101
+ "audio_encoder.encoder.layers.7.block.1.conv.weight_v": "model-00001-of-00002.safetensors",
102
+ "audio_encoder.encoder.layers.7.block.3.conv.bias": "model-00001-of-00002.safetensors",
103
+ "audio_encoder.encoder.layers.7.block.3.conv.weight_g": "model-00001-of-00002.safetensors",
104
+ "audio_encoder.encoder.layers.7.block.3.conv.weight_v": "model-00001-of-00002.safetensors",
105
+ "audio_encoder.encoder.layers.9.conv.bias": "model-00001-of-00002.safetensors",
106
+ "audio_encoder.encoder.layers.9.conv.weight_g": "model-00001-of-00002.safetensors",
107
+ "audio_encoder.encoder.layers.9.conv.weight_v": "model-00001-of-00002.safetensors",
108
+ "audio_encoder.quantizer.layers.0.codebook.cluster_size": "model-00001-of-00002.safetensors",
109
+ "audio_encoder.quantizer.layers.0.codebook.embed": "model-00001-of-00002.safetensors",
110
+ "audio_encoder.quantizer.layers.0.codebook.embed_avg": "model-00001-of-00002.safetensors",
111
+ "audio_encoder.quantizer.layers.0.codebook.inited": "model-00001-of-00002.safetensors",
112
+ "audio_encoder.quantizer.layers.1.codebook.cluster_size": "model-00001-of-00002.safetensors",
113
+ "audio_encoder.quantizer.layers.1.codebook.embed": "model-00001-of-00002.safetensors",
114
+ "audio_encoder.quantizer.layers.1.codebook.embed_avg": "model-00001-of-00002.safetensors",
115
+ "audio_encoder.quantizer.layers.1.codebook.inited": "model-00001-of-00002.safetensors",
116
+ "audio_encoder.quantizer.layers.2.codebook.cluster_size": "model-00001-of-00002.safetensors",
117
+ "audio_encoder.quantizer.layers.2.codebook.embed": "model-00001-of-00002.safetensors",
118
+ "audio_encoder.quantizer.layers.2.codebook.embed_avg": "model-00001-of-00002.safetensors",
119
+ "audio_encoder.quantizer.layers.2.codebook.inited": "model-00001-of-00002.safetensors",
120
+ "audio_encoder.quantizer.layers.3.codebook.cluster_size": "model-00001-of-00002.safetensors",
121
+ "audio_encoder.quantizer.layers.3.codebook.embed": "model-00001-of-00002.safetensors",
122
+ "audio_encoder.quantizer.layers.3.codebook.embed_avg": "model-00001-of-00002.safetensors",
123
+ "audio_encoder.quantizer.layers.3.codebook.inited": "model-00001-of-00002.safetensors",
124
+ "decoder.lm_heads.0.weight": "model-00002-of-00002.safetensors",
125
+ "decoder.lm_heads.1.weight": "model-00002-of-00002.safetensors",
126
+ "decoder.lm_heads.2.weight": "model-00002-of-00002.safetensors",
127
+ "decoder.lm_heads.3.weight": "model-00002-of-00002.safetensors",
128
+ "decoder.model.decoder.embed_positions.weights": "model-00001-of-00002.safetensors",
129
+ "decoder.model.decoder.embed_tokens.0.weight": "model-00001-of-00002.safetensors",
130
+ "decoder.model.decoder.embed_tokens.1.weight": "model-00001-of-00002.safetensors",
131
+ "decoder.model.decoder.embed_tokens.2.weight": "model-00001-of-00002.safetensors",
132
+ "decoder.model.decoder.embed_tokens.3.weight": "model-00001-of-00002.safetensors",
133
+ "decoder.model.decoder.layer_norm.bias": "model-00002-of-00002.safetensors",
134
+ "decoder.model.decoder.layer_norm.weight": "model-00002-of-00002.safetensors",
135
+ "decoder.model.decoder.layers.0.fc1.weight": "model-00001-of-00002.safetensors",
136
+ "decoder.model.decoder.layers.0.fc2.weight": "model-00001-of-00002.safetensors",
137
+ "decoder.model.decoder.layers.0.final_layer_norm.bias": "model-00001-of-00002.safetensors",
138
+ "decoder.model.decoder.layers.0.final_layer_norm.weight": "model-00001-of-00002.safetensors",
139
+ "decoder.model.decoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
140
+ "decoder.model.decoder.layers.0.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
141
+ "decoder.model.decoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
142
+ "decoder.model.decoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
143
+ "decoder.model.decoder.layers.0.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
144
+ "decoder.model.decoder.layers.0.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
145
+ "decoder.model.decoder.layers.1.fc1.weight": "model-00001-of-00002.safetensors",
146
+ "decoder.model.decoder.layers.1.fc2.weight": "model-00001-of-00002.safetensors",
147
+ "decoder.model.decoder.layers.1.final_layer_norm.bias": "model-00001-of-00002.safetensors",
148
+ "decoder.model.decoder.layers.1.final_layer_norm.weight": "model-00001-of-00002.safetensors",
149
+ "decoder.model.decoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
150
+ "decoder.model.decoder.layers.1.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
151
+ "decoder.model.decoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
152
+ "decoder.model.decoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
153
+ "decoder.model.decoder.layers.1.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
154
+ "decoder.model.decoder.layers.1.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
155
+ "decoder.model.decoder.layers.10.fc1.weight": "model-00001-of-00002.safetensors",
156
+ "decoder.model.decoder.layers.10.fc2.weight": "model-00001-of-00002.safetensors",
157
+ "decoder.model.decoder.layers.10.final_layer_norm.bias": "model-00001-of-00002.safetensors",
158
+ "decoder.model.decoder.layers.10.final_layer_norm.weight": "model-00001-of-00002.safetensors",
159
+ "decoder.model.decoder.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
160
+ "decoder.model.decoder.layers.10.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
161
+ "decoder.model.decoder.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
162
+ "decoder.model.decoder.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
163
+ "decoder.model.decoder.layers.10.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
164
+ "decoder.model.decoder.layers.10.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
165
+ "decoder.model.decoder.layers.11.fc1.weight": "model-00001-of-00002.safetensors",
166
+ "decoder.model.decoder.layers.11.fc2.weight": "model-00001-of-00002.safetensors",
167
+ "decoder.model.decoder.layers.11.final_layer_norm.bias": "model-00001-of-00002.safetensors",
168
+ "decoder.model.decoder.layers.11.final_layer_norm.weight": "model-00001-of-00002.safetensors",
169
+ "decoder.model.decoder.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
170
+ "decoder.model.decoder.layers.11.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
171
+ "decoder.model.decoder.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
172
+ "decoder.model.decoder.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
173
+ "decoder.model.decoder.layers.11.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
174
+ "decoder.model.decoder.layers.11.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
175
+ "decoder.model.decoder.layers.12.fc1.weight": "model-00001-of-00002.safetensors",
176
+ "decoder.model.decoder.layers.12.fc2.weight": "model-00001-of-00002.safetensors",
177
+ "decoder.model.decoder.layers.12.final_layer_norm.bias": "model-00001-of-00002.safetensors",
178
+ "decoder.model.decoder.layers.12.final_layer_norm.weight": "model-00001-of-00002.safetensors",
179
+ "decoder.model.decoder.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
180
+ "decoder.model.decoder.layers.12.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
181
+ "decoder.model.decoder.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
182
+ "decoder.model.decoder.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
183
+ "decoder.model.decoder.layers.12.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
184
+ "decoder.model.decoder.layers.12.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
185
+ "decoder.model.decoder.layers.13.fc1.weight": "model-00001-of-00002.safetensors",
186
+ "decoder.model.decoder.layers.13.fc2.weight": "model-00001-of-00002.safetensors",
187
+ "decoder.model.decoder.layers.13.final_layer_norm.bias": "model-00001-of-00002.safetensors",
188
+ "decoder.model.decoder.layers.13.final_layer_norm.weight": "model-00001-of-00002.safetensors",
189
+ "decoder.model.decoder.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
190
+ "decoder.model.decoder.layers.13.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
191
+ "decoder.model.decoder.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
192
+ "decoder.model.decoder.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
193
+ "decoder.model.decoder.layers.13.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
194
+ "decoder.model.decoder.layers.13.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
195
+ "decoder.model.decoder.layers.14.fc1.weight": "model-00001-of-00002.safetensors",
196
+ "decoder.model.decoder.layers.14.fc2.weight": "model-00001-of-00002.safetensors",
197
+ "decoder.model.decoder.layers.14.final_layer_norm.bias": "model-00001-of-00002.safetensors",
198
+ "decoder.model.decoder.layers.14.final_layer_norm.weight": "model-00001-of-00002.safetensors",
199
+ "decoder.model.decoder.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
200
+ "decoder.model.decoder.layers.14.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
201
+ "decoder.model.decoder.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
202
+ "decoder.model.decoder.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
203
+ "decoder.model.decoder.layers.14.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
204
+ "decoder.model.decoder.layers.14.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
205
+ "decoder.model.decoder.layers.15.fc1.weight": "model-00001-of-00002.safetensors",
206
+ "decoder.model.decoder.layers.15.fc2.weight": "model-00001-of-00002.safetensors",
207
+ "decoder.model.decoder.layers.15.final_layer_norm.bias": "model-00001-of-00002.safetensors",
208
+ "decoder.model.decoder.layers.15.final_layer_norm.weight": "model-00001-of-00002.safetensors",
209
+ "decoder.model.decoder.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
210
+ "decoder.model.decoder.layers.15.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
211
+ "decoder.model.decoder.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
212
+ "decoder.model.decoder.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
213
+ "decoder.model.decoder.layers.15.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
214
+ "decoder.model.decoder.layers.15.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
215
+ "decoder.model.decoder.layers.16.fc1.weight": "model-00001-of-00002.safetensors",
216
+ "decoder.model.decoder.layers.16.fc2.weight": "model-00001-of-00002.safetensors",
217
+ "decoder.model.decoder.layers.16.final_layer_norm.bias": "model-00001-of-00002.safetensors",
218
+ "decoder.model.decoder.layers.16.final_layer_norm.weight": "model-00001-of-00002.safetensors",
219
+ "decoder.model.decoder.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
220
+ "decoder.model.decoder.layers.16.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
221
+ "decoder.model.decoder.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
222
+ "decoder.model.decoder.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
223
+ "decoder.model.decoder.layers.16.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
224
+ "decoder.model.decoder.layers.16.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
225
+ "decoder.model.decoder.layers.17.fc1.weight": "model-00001-of-00002.safetensors",
226
+ "decoder.model.decoder.layers.17.fc2.weight": "model-00001-of-00002.safetensors",
227
+ "decoder.model.decoder.layers.17.final_layer_norm.bias": "model-00001-of-00002.safetensors",
228
+ "decoder.model.decoder.layers.17.final_layer_norm.weight": "model-00001-of-00002.safetensors",
229
+ "decoder.model.decoder.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
230
+ "decoder.model.decoder.layers.17.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
231
+ "decoder.model.decoder.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
232
+ "decoder.model.decoder.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
233
+ "decoder.model.decoder.layers.17.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
234
+ "decoder.model.decoder.layers.17.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
235
+ "decoder.model.decoder.layers.18.fc1.weight": "model-00001-of-00002.safetensors",
236
+ "decoder.model.decoder.layers.18.fc2.weight": "model-00001-of-00002.safetensors",
237
+ "decoder.model.decoder.layers.18.final_layer_norm.bias": "model-00001-of-00002.safetensors",
238
+ "decoder.model.decoder.layers.18.final_layer_norm.weight": "model-00001-of-00002.safetensors",
239
+ "decoder.model.decoder.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
240
+ "decoder.model.decoder.layers.18.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
241
+ "decoder.model.decoder.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
242
+ "decoder.model.decoder.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
243
+ "decoder.model.decoder.layers.18.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
244
+ "decoder.model.decoder.layers.18.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
245
+ "decoder.model.decoder.layers.19.fc1.weight": "model-00001-of-00002.safetensors",
246
+ "decoder.model.decoder.layers.19.fc2.weight": "model-00001-of-00002.safetensors",
247
+ "decoder.model.decoder.layers.19.final_layer_norm.bias": "model-00001-of-00002.safetensors",
248
+ "decoder.model.decoder.layers.19.final_layer_norm.weight": "model-00001-of-00002.safetensors",
249
+ "decoder.model.decoder.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
250
+ "decoder.model.decoder.layers.19.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
251
+ "decoder.model.decoder.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
252
+ "decoder.model.decoder.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
253
+ "decoder.model.decoder.layers.19.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
254
+ "decoder.model.decoder.layers.19.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
255
+ "decoder.model.decoder.layers.2.fc1.weight": "model-00001-of-00002.safetensors",
256
+ "decoder.model.decoder.layers.2.fc2.weight": "model-00001-of-00002.safetensors",
257
+ "decoder.model.decoder.layers.2.final_layer_norm.bias": "model-00001-of-00002.safetensors",
258
+ "decoder.model.decoder.layers.2.final_layer_norm.weight": "model-00001-of-00002.safetensors",
259
+ "decoder.model.decoder.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
260
+ "decoder.model.decoder.layers.2.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
261
+ "decoder.model.decoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
262
+ "decoder.model.decoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
263
+ "decoder.model.decoder.layers.2.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
264
+ "decoder.model.decoder.layers.2.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
265
+ "decoder.model.decoder.layers.20.fc1.weight": "model-00001-of-00002.safetensors",
266
+ "decoder.model.decoder.layers.20.fc2.weight": "model-00001-of-00002.safetensors",
267
+ "decoder.model.decoder.layers.20.final_layer_norm.bias": "model-00001-of-00002.safetensors",
268
+ "decoder.model.decoder.layers.20.final_layer_norm.weight": "model-00001-of-00002.safetensors",
269
+ "decoder.model.decoder.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
270
+ "decoder.model.decoder.layers.20.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
271
+ "decoder.model.decoder.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
272
+ "decoder.model.decoder.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
273
+ "decoder.model.decoder.layers.20.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
274
+ "decoder.model.decoder.layers.20.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
275
+ "decoder.model.decoder.layers.21.fc1.weight": "model-00001-of-00002.safetensors",
276
+ "decoder.model.decoder.layers.21.fc2.weight": "model-00001-of-00002.safetensors",
277
+ "decoder.model.decoder.layers.21.final_layer_norm.bias": "model-00001-of-00002.safetensors",
278
+ "decoder.model.decoder.layers.21.final_layer_norm.weight": "model-00001-of-00002.safetensors",
279
+ "decoder.model.decoder.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
280
+ "decoder.model.decoder.layers.21.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
281
+ "decoder.model.decoder.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
282
+ "decoder.model.decoder.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
283
+ "decoder.model.decoder.layers.21.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
284
+ "decoder.model.decoder.layers.21.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
285
+ "decoder.model.decoder.layers.22.fc1.weight": "model-00001-of-00002.safetensors",
286
+ "decoder.model.decoder.layers.22.fc2.weight": "model-00001-of-00002.safetensors",
287
+ "decoder.model.decoder.layers.22.final_layer_norm.bias": "model-00001-of-00002.safetensors",
288
+ "decoder.model.decoder.layers.22.final_layer_norm.weight": "model-00001-of-00002.safetensors",
289
+ "decoder.model.decoder.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
290
+ "decoder.model.decoder.layers.22.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
291
+ "decoder.model.decoder.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
292
+ "decoder.model.decoder.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
293
+ "decoder.model.decoder.layers.22.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
294
+ "decoder.model.decoder.layers.22.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
295
+ "decoder.model.decoder.layers.23.fc1.weight": "model-00001-of-00002.safetensors",
296
+ "decoder.model.decoder.layers.23.fc2.weight": "model-00001-of-00002.safetensors",
297
+ "decoder.model.decoder.layers.23.final_layer_norm.bias": "model-00001-of-00002.safetensors",
298
+ "decoder.model.decoder.layers.23.final_layer_norm.weight": "model-00001-of-00002.safetensors",
299
+ "decoder.model.decoder.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
300
+ "decoder.model.decoder.layers.23.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
301
+ "decoder.model.decoder.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
302
+ "decoder.model.decoder.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
303
+ "decoder.model.decoder.layers.23.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
304
+ "decoder.model.decoder.layers.23.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
305
+ "decoder.model.decoder.layers.24.fc1.weight": "model-00001-of-00002.safetensors",
306
+ "decoder.model.decoder.layers.24.fc2.weight": "model-00001-of-00002.safetensors",
307
+ "decoder.model.decoder.layers.24.final_layer_norm.bias": "model-00001-of-00002.safetensors",
308
+ "decoder.model.decoder.layers.24.final_layer_norm.weight": "model-00001-of-00002.safetensors",
309
+ "decoder.model.decoder.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
310
+ "decoder.model.decoder.layers.24.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
311
+ "decoder.model.decoder.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
312
+ "decoder.model.decoder.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
313
+ "decoder.model.decoder.layers.24.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
314
+ "decoder.model.decoder.layers.24.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
315
+ "decoder.model.decoder.layers.25.fc1.weight": "model-00001-of-00002.safetensors",
316
+ "decoder.model.decoder.layers.25.fc2.weight": "model-00001-of-00002.safetensors",
317
+ "decoder.model.decoder.layers.25.final_layer_norm.bias": "model-00001-of-00002.safetensors",
318
+ "decoder.model.decoder.layers.25.final_layer_norm.weight": "model-00001-of-00002.safetensors",
319
+ "decoder.model.decoder.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
320
+ "decoder.model.decoder.layers.25.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
321
+ "decoder.model.decoder.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
322
+ "decoder.model.decoder.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
323
+ "decoder.model.decoder.layers.25.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
324
+ "decoder.model.decoder.layers.25.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
325
+ "decoder.model.decoder.layers.26.fc1.weight": "model-00001-of-00002.safetensors",
326
+ "decoder.model.decoder.layers.26.fc2.weight": "model-00001-of-00002.safetensors",
327
+ "decoder.model.decoder.layers.26.final_layer_norm.bias": "model-00001-of-00002.safetensors",
328
+ "decoder.model.decoder.layers.26.final_layer_norm.weight": "model-00001-of-00002.safetensors",
329
+ "decoder.model.decoder.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
330
+ "decoder.model.decoder.layers.26.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
331
+ "decoder.model.decoder.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
332
+ "decoder.model.decoder.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
333
+ "decoder.model.decoder.layers.26.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
334
+ "decoder.model.decoder.layers.26.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
335
+ "decoder.model.decoder.layers.27.fc1.weight": "model-00001-of-00002.safetensors",
336
+ "decoder.model.decoder.layers.27.fc2.weight": "model-00001-of-00002.safetensors",
337
+ "decoder.model.decoder.layers.27.final_layer_norm.bias": "model-00001-of-00002.safetensors",
338
+ "decoder.model.decoder.layers.27.final_layer_norm.weight": "model-00001-of-00002.safetensors",
339
+ "decoder.model.decoder.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
340
+ "decoder.model.decoder.layers.27.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
341
+ "decoder.model.decoder.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
342
+ "decoder.model.decoder.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
343
+ "decoder.model.decoder.layers.27.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
344
+ "decoder.model.decoder.layers.27.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
345
+ "decoder.model.decoder.layers.28.fc1.weight": "model-00001-of-00002.safetensors",
346
+ "decoder.model.decoder.layers.28.fc2.weight": "model-00001-of-00002.safetensors",
347
+ "decoder.model.decoder.layers.28.final_layer_norm.bias": "model-00001-of-00002.safetensors",
348
+ "decoder.model.decoder.layers.28.final_layer_norm.weight": "model-00001-of-00002.safetensors",
349
+ "decoder.model.decoder.layers.28.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
350
+ "decoder.model.decoder.layers.28.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
351
+ "decoder.model.decoder.layers.28.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
352
+ "decoder.model.decoder.layers.28.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
353
+ "decoder.model.decoder.layers.28.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
354
+ "decoder.model.decoder.layers.28.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
355
+ "decoder.model.decoder.layers.29.fc1.weight": "model-00001-of-00002.safetensors",
356
+ "decoder.model.decoder.layers.29.fc2.weight": "model-00001-of-00002.safetensors",
357
+ "decoder.model.decoder.layers.29.final_layer_norm.bias": "model-00001-of-00002.safetensors",
358
+ "decoder.model.decoder.layers.29.final_layer_norm.weight": "model-00001-of-00002.safetensors",
359
+ "decoder.model.decoder.layers.29.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
360
+ "decoder.model.decoder.layers.29.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
361
+ "decoder.model.decoder.layers.29.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
362
+ "decoder.model.decoder.layers.29.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
363
+ "decoder.model.decoder.layers.29.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
364
+ "decoder.model.decoder.layers.29.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
365
+ "decoder.model.decoder.layers.3.fc1.weight": "model-00001-of-00002.safetensors",
366
+ "decoder.model.decoder.layers.3.fc2.weight": "model-00001-of-00002.safetensors",
367
+ "decoder.model.decoder.layers.3.final_layer_norm.bias": "model-00001-of-00002.safetensors",
368
+ "decoder.model.decoder.layers.3.final_layer_norm.weight": "model-00001-of-00002.safetensors",
369
+ "decoder.model.decoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
370
+ "decoder.model.decoder.layers.3.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
371
+ "decoder.model.decoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
372
+ "decoder.model.decoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
373
+ "decoder.model.decoder.layers.3.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
374
+ "decoder.model.decoder.layers.3.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
375
+ "decoder.model.decoder.layers.30.fc1.weight": "model-00001-of-00002.safetensors",
376
+ "decoder.model.decoder.layers.30.fc2.weight": "model-00001-of-00002.safetensors",
377
+ "decoder.model.decoder.layers.30.final_layer_norm.bias": "model-00001-of-00002.safetensors",
378
+ "decoder.model.decoder.layers.30.final_layer_norm.weight": "model-00001-of-00002.safetensors",
379
+ "decoder.model.decoder.layers.30.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
380
+ "decoder.model.decoder.layers.30.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
381
+ "decoder.model.decoder.layers.30.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
382
+ "decoder.model.decoder.layers.30.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
383
+ "decoder.model.decoder.layers.30.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
384
+ "decoder.model.decoder.layers.30.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
385
+ "decoder.model.decoder.layers.31.fc1.weight": "model-00001-of-00002.safetensors",
386
+ "decoder.model.decoder.layers.31.fc2.weight": "model-00001-of-00002.safetensors",
387
+ "decoder.model.decoder.layers.31.final_layer_norm.bias": "model-00001-of-00002.safetensors",
388
+ "decoder.model.decoder.layers.31.final_layer_norm.weight": "model-00001-of-00002.safetensors",
389
+ "decoder.model.decoder.layers.31.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
390
+ "decoder.model.decoder.layers.31.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
391
+ "decoder.model.decoder.layers.31.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
392
+ "decoder.model.decoder.layers.31.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
393
+ "decoder.model.decoder.layers.31.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
394
+ "decoder.model.decoder.layers.31.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
395
+ "decoder.model.decoder.layers.32.fc1.weight": "model-00001-of-00002.safetensors",
396
+ "decoder.model.decoder.layers.32.fc2.weight": "model-00001-of-00002.safetensors",
397
+ "decoder.model.decoder.layers.32.final_layer_norm.bias": "model-00001-of-00002.safetensors",
398
+ "decoder.model.decoder.layers.32.final_layer_norm.weight": "model-00001-of-00002.safetensors",
399
+ "decoder.model.decoder.layers.32.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
400
+ "decoder.model.decoder.layers.32.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
401
+ "decoder.model.decoder.layers.32.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
402
+ "decoder.model.decoder.layers.32.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
403
+ "decoder.model.decoder.layers.32.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
404
+ "decoder.model.decoder.layers.32.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
405
+ "decoder.model.decoder.layers.33.fc1.weight": "model-00001-of-00002.safetensors",
406
+ "decoder.model.decoder.layers.33.fc2.weight": "model-00001-of-00002.safetensors",
407
+ "decoder.model.decoder.layers.33.final_layer_norm.bias": "model-00001-of-00002.safetensors",
408
+ "decoder.model.decoder.layers.33.final_layer_norm.weight": "model-00001-of-00002.safetensors",
409
+ "decoder.model.decoder.layers.33.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
410
+ "decoder.model.decoder.layers.33.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
411
+ "decoder.model.decoder.layers.33.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
412
+ "decoder.model.decoder.layers.33.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
413
+ "decoder.model.decoder.layers.33.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
414
+ "decoder.model.decoder.layers.33.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
415
+ "decoder.model.decoder.layers.34.fc1.weight": "model-00001-of-00002.safetensors",
416
+ "decoder.model.decoder.layers.34.fc2.weight": "model-00001-of-00002.safetensors",
417
+ "decoder.model.decoder.layers.34.final_layer_norm.bias": "model-00001-of-00002.safetensors",
418
+ "decoder.model.decoder.layers.34.final_layer_norm.weight": "model-00001-of-00002.safetensors",
419
+ "decoder.model.decoder.layers.34.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
420
+ "decoder.model.decoder.layers.34.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
421
+ "decoder.model.decoder.layers.34.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
422
+ "decoder.model.decoder.layers.34.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
423
+ "decoder.model.decoder.layers.34.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
424
+ "decoder.model.decoder.layers.34.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
425
+ "decoder.model.decoder.layers.35.fc1.weight": "model-00001-of-00002.safetensors",
426
+ "decoder.model.decoder.layers.35.fc2.weight": "model-00001-of-00002.safetensors",
427
+ "decoder.model.decoder.layers.35.final_layer_norm.bias": "model-00001-of-00002.safetensors",
428
+ "decoder.model.decoder.layers.35.final_layer_norm.weight": "model-00001-of-00002.safetensors",
429
+ "decoder.model.decoder.layers.35.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
430
+ "decoder.model.decoder.layers.35.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
431
+ "decoder.model.decoder.layers.35.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
432
+ "decoder.model.decoder.layers.35.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
433
+ "decoder.model.decoder.layers.35.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
434
+ "decoder.model.decoder.layers.35.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
435
+ "decoder.model.decoder.layers.36.fc1.weight": "model-00001-of-00002.safetensors",
436
+ "decoder.model.decoder.layers.36.fc2.weight": "model-00001-of-00002.safetensors",
437
+ "decoder.model.decoder.layers.36.final_layer_norm.bias": "model-00001-of-00002.safetensors",
438
+ "decoder.model.decoder.layers.36.final_layer_norm.weight": "model-00001-of-00002.safetensors",
439
+ "decoder.model.decoder.layers.36.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
440
+ "decoder.model.decoder.layers.36.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
441
+ "decoder.model.decoder.layers.36.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
442
+ "decoder.model.decoder.layers.36.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
443
+ "decoder.model.decoder.layers.36.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
444
+ "decoder.model.decoder.layers.36.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
445
+ "decoder.model.decoder.layers.37.fc1.weight": "model-00002-of-00002.safetensors",
446
+ "decoder.model.decoder.layers.37.fc2.weight": "model-00002-of-00002.safetensors",
447
+ "decoder.model.decoder.layers.37.final_layer_norm.bias": "model-00002-of-00002.safetensors",
448
+ "decoder.model.decoder.layers.37.final_layer_norm.weight": "model-00002-of-00002.safetensors",
449
+ "decoder.model.decoder.layers.37.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
450
+ "decoder.model.decoder.layers.37.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
451
+ "decoder.model.decoder.layers.37.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
452
+ "decoder.model.decoder.layers.37.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
453
+ "decoder.model.decoder.layers.37.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
454
+ "decoder.model.decoder.layers.37.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
455
+ "decoder.model.decoder.layers.38.fc1.weight": "model-00002-of-00002.safetensors",
456
+ "decoder.model.decoder.layers.38.fc2.weight": "model-00002-of-00002.safetensors",
457
+ "decoder.model.decoder.layers.38.final_layer_norm.bias": "model-00002-of-00002.safetensors",
458
+ "decoder.model.decoder.layers.38.final_layer_norm.weight": "model-00002-of-00002.safetensors",
459
+ "decoder.model.decoder.layers.38.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
460
+ "decoder.model.decoder.layers.38.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
461
+ "decoder.model.decoder.layers.38.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
462
+ "decoder.model.decoder.layers.38.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
463
+ "decoder.model.decoder.layers.38.self_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
464
+ "decoder.model.decoder.layers.38.self_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
465
+ "decoder.model.decoder.layers.39.fc1.weight": "model-00002-of-00002.safetensors",
466
+ "decoder.model.decoder.layers.39.fc2.weight": "model-00002-of-00002.safetensors",
467
+ "decoder.model.decoder.layers.39.final_layer_norm.bias": "model-00002-of-00002.safetensors",
468
+ "decoder.model.decoder.layers.39.final_layer_norm.weight": "model-00002-of-00002.safetensors",
469
+ "decoder.model.decoder.layers.39.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
470
+ "decoder.model.decoder.layers.39.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
471
+ "decoder.model.decoder.layers.39.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
472
+ "decoder.model.decoder.layers.39.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
473
+ "decoder.model.decoder.layers.39.self_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
474
+ "decoder.model.decoder.layers.39.self_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
475
+ "decoder.model.decoder.layers.4.fc1.weight": "model-00001-of-00002.safetensors",
476
+ "decoder.model.decoder.layers.4.fc2.weight": "model-00001-of-00002.safetensors",
477
+ "decoder.model.decoder.layers.4.final_layer_norm.bias": "model-00001-of-00002.safetensors",
478
+ "decoder.model.decoder.layers.4.final_layer_norm.weight": "model-00001-of-00002.safetensors",
479
+ "decoder.model.decoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
480
+ "decoder.model.decoder.layers.4.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
481
+ "decoder.model.decoder.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
482
+ "decoder.model.decoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
483
+ "decoder.model.decoder.layers.4.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
484
+ "decoder.model.decoder.layers.4.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
485
+ "decoder.model.decoder.layers.40.fc1.weight": "model-00002-of-00002.safetensors",
486
+ "decoder.model.decoder.layers.40.fc2.weight": "model-00002-of-00002.safetensors",
487
+ "decoder.model.decoder.layers.40.final_layer_norm.bias": "model-00002-of-00002.safetensors",
488
+ "decoder.model.decoder.layers.40.final_layer_norm.weight": "model-00002-of-00002.safetensors",
489
+ "decoder.model.decoder.layers.40.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
490
+ "decoder.model.decoder.layers.40.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
491
+ "decoder.model.decoder.layers.40.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
492
+ "decoder.model.decoder.layers.40.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
493
+ "decoder.model.decoder.layers.40.self_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
494
+ "decoder.model.decoder.layers.40.self_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
495
+ "decoder.model.decoder.layers.41.fc1.weight": "model-00002-of-00002.safetensors",
496
+ "decoder.model.decoder.layers.41.fc2.weight": "model-00002-of-00002.safetensors",
497
+ "decoder.model.decoder.layers.41.final_layer_norm.bias": "model-00002-of-00002.safetensors",
498
+ "decoder.model.decoder.layers.41.final_layer_norm.weight": "model-00002-of-00002.safetensors",
499
+ "decoder.model.decoder.layers.41.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
500
+ "decoder.model.decoder.layers.41.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
501
+ "decoder.model.decoder.layers.41.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
502
+ "decoder.model.decoder.layers.41.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
503
+ "decoder.model.decoder.layers.41.self_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
504
+ "decoder.model.decoder.layers.41.self_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
505
+ "decoder.model.decoder.layers.42.fc1.weight": "model-00002-of-00002.safetensors",
506
+ "decoder.model.decoder.layers.42.fc2.weight": "model-00002-of-00002.safetensors",
507
+ "decoder.model.decoder.layers.42.final_layer_norm.bias": "model-00002-of-00002.safetensors",
508
+ "decoder.model.decoder.layers.42.final_layer_norm.weight": "model-00002-of-00002.safetensors",
509
+ "decoder.model.decoder.layers.42.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
510
+ "decoder.model.decoder.layers.42.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
511
+ "decoder.model.decoder.layers.42.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
512
+ "decoder.model.decoder.layers.42.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
513
+ "decoder.model.decoder.layers.42.self_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
514
+ "decoder.model.decoder.layers.42.self_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
515
+ "decoder.model.decoder.layers.43.fc1.weight": "model-00002-of-00002.safetensors",
516
+ "decoder.model.decoder.layers.43.fc2.weight": "model-00002-of-00002.safetensors",
517
+ "decoder.model.decoder.layers.43.final_layer_norm.bias": "model-00002-of-00002.safetensors",
518
+ "decoder.model.decoder.layers.43.final_layer_norm.weight": "model-00002-of-00002.safetensors",
519
+ "decoder.model.decoder.layers.43.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
520
+ "decoder.model.decoder.layers.43.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
521
+ "decoder.model.decoder.layers.43.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
522
+ "decoder.model.decoder.layers.43.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
523
+ "decoder.model.decoder.layers.43.self_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
524
+ "decoder.model.decoder.layers.43.self_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
525
+ "decoder.model.decoder.layers.44.fc1.weight": "model-00002-of-00002.safetensors",
526
+ "decoder.model.decoder.layers.44.fc2.weight": "model-00002-of-00002.safetensors",
527
+ "decoder.model.decoder.layers.44.final_layer_norm.bias": "model-00002-of-00002.safetensors",
528
+ "decoder.model.decoder.layers.44.final_layer_norm.weight": "model-00002-of-00002.safetensors",
529
+ "decoder.model.decoder.layers.44.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
530
+ "decoder.model.decoder.layers.44.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
531
+ "decoder.model.decoder.layers.44.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
532
+ "decoder.model.decoder.layers.44.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
533
+ "decoder.model.decoder.layers.44.self_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
534
+ "decoder.model.decoder.layers.44.self_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
535
+ "decoder.model.decoder.layers.45.fc1.weight": "model-00002-of-00002.safetensors",
536
+ "decoder.model.decoder.layers.45.fc2.weight": "model-00002-of-00002.safetensors",
537
+ "decoder.model.decoder.layers.45.final_layer_norm.bias": "model-00002-of-00002.safetensors",
538
+ "decoder.model.decoder.layers.45.final_layer_norm.weight": "model-00002-of-00002.safetensors",
539
+ "decoder.model.decoder.layers.45.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
540
+ "decoder.model.decoder.layers.45.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
541
+ "decoder.model.decoder.layers.45.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
542
+ "decoder.model.decoder.layers.45.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
543
+ "decoder.model.decoder.layers.45.self_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
544
+ "decoder.model.decoder.layers.45.self_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
545
+ "decoder.model.decoder.layers.46.fc1.weight": "model-00002-of-00002.safetensors",
546
+ "decoder.model.decoder.layers.46.fc2.weight": "model-00002-of-00002.safetensors",
547
+ "decoder.model.decoder.layers.46.final_layer_norm.bias": "model-00002-of-00002.safetensors",
548
+ "decoder.model.decoder.layers.46.final_layer_norm.weight": "model-00002-of-00002.safetensors",
549
+ "decoder.model.decoder.layers.46.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
550
+ "decoder.model.decoder.layers.46.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
551
+ "decoder.model.decoder.layers.46.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
552
+ "decoder.model.decoder.layers.46.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
553
+ "decoder.model.decoder.layers.46.self_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
554
+ "decoder.model.decoder.layers.46.self_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
555
+ "decoder.model.decoder.layers.47.fc1.weight": "model-00002-of-00002.safetensors",
556
+ "decoder.model.decoder.layers.47.fc2.weight": "model-00002-of-00002.safetensors",
557
+ "decoder.model.decoder.layers.47.final_layer_norm.bias": "model-00002-of-00002.safetensors",
558
+ "decoder.model.decoder.layers.47.final_layer_norm.weight": "model-00002-of-00002.safetensors",
559
+ "decoder.model.decoder.layers.47.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
560
+ "decoder.model.decoder.layers.47.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
561
+ "decoder.model.decoder.layers.47.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
562
+ "decoder.model.decoder.layers.47.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
563
+ "decoder.model.decoder.layers.47.self_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
564
+ "decoder.model.decoder.layers.47.self_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
565
+ "decoder.model.decoder.layers.5.fc1.weight": "model-00001-of-00002.safetensors",
566
+ "decoder.model.decoder.layers.5.fc2.weight": "model-00001-of-00002.safetensors",
567
+ "decoder.model.decoder.layers.5.final_layer_norm.bias": "model-00001-of-00002.safetensors",
568
+ "decoder.model.decoder.layers.5.final_layer_norm.weight": "model-00001-of-00002.safetensors",
569
+ "decoder.model.decoder.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
570
+ "decoder.model.decoder.layers.5.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
571
+ "decoder.model.decoder.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
572
+ "decoder.model.decoder.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
573
+ "decoder.model.decoder.layers.5.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
574
+ "decoder.model.decoder.layers.5.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
575
+ "decoder.model.decoder.layers.6.fc1.weight": "model-00001-of-00002.safetensors",
576
+ "decoder.model.decoder.layers.6.fc2.weight": "model-00001-of-00002.safetensors",
577
+ "decoder.model.decoder.layers.6.final_layer_norm.bias": "model-00001-of-00002.safetensors",
578
+ "decoder.model.decoder.layers.6.final_layer_norm.weight": "model-00001-of-00002.safetensors",
579
+ "decoder.model.decoder.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
580
+ "decoder.model.decoder.layers.6.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
581
+ "decoder.model.decoder.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
582
+ "decoder.model.decoder.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
583
+ "decoder.model.decoder.layers.6.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
584
+ "decoder.model.decoder.layers.6.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
585
+ "decoder.model.decoder.layers.7.fc1.weight": "model-00001-of-00002.safetensors",
586
+ "decoder.model.decoder.layers.7.fc2.weight": "model-00001-of-00002.safetensors",
587
+ "decoder.model.decoder.layers.7.final_layer_norm.bias": "model-00001-of-00002.safetensors",
588
+ "decoder.model.decoder.layers.7.final_layer_norm.weight": "model-00001-of-00002.safetensors",
589
+ "decoder.model.decoder.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
590
+ "decoder.model.decoder.layers.7.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
591
+ "decoder.model.decoder.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
592
+ "decoder.model.decoder.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
593
+ "decoder.model.decoder.layers.7.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
594
+ "decoder.model.decoder.layers.7.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
595
+ "decoder.model.decoder.layers.8.fc1.weight": "model-00001-of-00002.safetensors",
596
+ "decoder.model.decoder.layers.8.fc2.weight": "model-00001-of-00002.safetensors",
597
+ "decoder.model.decoder.layers.8.final_layer_norm.bias": "model-00001-of-00002.safetensors",
598
+ "decoder.model.decoder.layers.8.final_layer_norm.weight": "model-00001-of-00002.safetensors",
599
+ "decoder.model.decoder.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
600
+ "decoder.model.decoder.layers.8.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
601
+ "decoder.model.decoder.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
602
+ "decoder.model.decoder.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
603
+ "decoder.model.decoder.layers.8.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
604
+ "decoder.model.decoder.layers.8.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
605
+ "decoder.model.decoder.layers.9.fc1.weight": "model-00001-of-00002.safetensors",
606
+ "decoder.model.decoder.layers.9.fc2.weight": "model-00001-of-00002.safetensors",
607
+ "decoder.model.decoder.layers.9.final_layer_norm.bias": "model-00001-of-00002.safetensors",
608
+ "decoder.model.decoder.layers.9.final_layer_norm.weight": "model-00001-of-00002.safetensors",
609
+ "decoder.model.decoder.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
610
+ "decoder.model.decoder.layers.9.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
611
+ "decoder.model.decoder.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
612
+ "decoder.model.decoder.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
613
+ "decoder.model.decoder.layers.9.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
614
+ "decoder.model.decoder.layers.9.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
615
+ "enc_to_dec_proj.bias": "model-00002-of-00002.safetensors",
616
+ "enc_to_dec_proj.weight": "model-00002-of-00002.safetensors",
617
+ "text_encoder.encoder.block.0.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
618
+ "text_encoder.encoder.block.0.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
619
+ "text_encoder.encoder.block.0.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
620
+ "text_encoder.encoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "model-00001-of-00002.safetensors",
621
+ "text_encoder.encoder.block.0.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
622
+ "text_encoder.encoder.block.0.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
623
+ "text_encoder.encoder.block.0.layer.1.DenseReluDense.wi.weight": "model-00001-of-00002.safetensors",
624
+ "text_encoder.encoder.block.0.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
625
+ "text_encoder.encoder.block.0.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
626
+ "text_encoder.encoder.block.1.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
627
+ "text_encoder.encoder.block.1.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
628
+ "text_encoder.encoder.block.1.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
629
+ "text_encoder.encoder.block.1.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
630
+ "text_encoder.encoder.block.1.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
631
+ "text_encoder.encoder.block.1.layer.1.DenseReluDense.wi.weight": "model-00001-of-00002.safetensors",
632
+ "text_encoder.encoder.block.1.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
633
+ "text_encoder.encoder.block.1.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
634
+ "text_encoder.encoder.block.10.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
635
+ "text_encoder.encoder.block.10.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
636
+ "text_encoder.encoder.block.10.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
637
+ "text_encoder.encoder.block.10.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
638
+ "text_encoder.encoder.block.10.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
639
+ "text_encoder.encoder.block.10.layer.1.DenseReluDense.wi.weight": "model-00001-of-00002.safetensors",
640
+ "text_encoder.encoder.block.10.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
641
+ "text_encoder.encoder.block.10.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
642
+ "text_encoder.encoder.block.11.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
643
+ "text_encoder.encoder.block.11.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
644
+ "text_encoder.encoder.block.11.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
645
+ "text_encoder.encoder.block.11.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
646
+ "text_encoder.encoder.block.11.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
647
+ "text_encoder.encoder.block.11.layer.1.DenseReluDense.wi.weight": "model-00001-of-00002.safetensors",
648
+ "text_encoder.encoder.block.11.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
649
+ "text_encoder.encoder.block.11.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
650
+ "text_encoder.encoder.block.2.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
651
+ "text_encoder.encoder.block.2.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
652
+ "text_encoder.encoder.block.2.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
653
+ "text_encoder.encoder.block.2.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
654
+ "text_encoder.encoder.block.2.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
655
+ "text_encoder.encoder.block.2.layer.1.DenseReluDense.wi.weight": "model-00001-of-00002.safetensors",
656
+ "text_encoder.encoder.block.2.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
657
+ "text_encoder.encoder.block.2.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
658
+ "text_encoder.encoder.block.3.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
659
+ "text_encoder.encoder.block.3.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
660
+ "text_encoder.encoder.block.3.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
661
+ "text_encoder.encoder.block.3.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
662
+ "text_encoder.encoder.block.3.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
663
+ "text_encoder.encoder.block.3.layer.1.DenseReluDense.wi.weight": "model-00001-of-00002.safetensors",
664
+ "text_encoder.encoder.block.3.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
665
+ "text_encoder.encoder.block.3.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
666
+ "text_encoder.encoder.block.4.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
667
+ "text_encoder.encoder.block.4.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
668
+ "text_encoder.encoder.block.4.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
669
+ "text_encoder.encoder.block.4.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
670
+ "text_encoder.encoder.block.4.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
671
+ "text_encoder.encoder.block.4.layer.1.DenseReluDense.wi.weight": "model-00001-of-00002.safetensors",
672
+ "text_encoder.encoder.block.4.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
673
+ "text_encoder.encoder.block.4.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
674
+ "text_encoder.encoder.block.5.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
675
+ "text_encoder.encoder.block.5.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
676
+ "text_encoder.encoder.block.5.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
677
+ "text_encoder.encoder.block.5.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
678
+ "text_encoder.encoder.block.5.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
679
+ "text_encoder.encoder.block.5.layer.1.DenseReluDense.wi.weight": "model-00001-of-00002.safetensors",
680
+ "text_encoder.encoder.block.5.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
681
+ "text_encoder.encoder.block.5.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
682
+ "text_encoder.encoder.block.6.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
683
+ "text_encoder.encoder.block.6.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
684
+ "text_encoder.encoder.block.6.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
685
+ "text_encoder.encoder.block.6.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
686
+ "text_encoder.encoder.block.6.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
687
+ "text_encoder.encoder.block.6.layer.1.DenseReluDense.wi.weight": "model-00001-of-00002.safetensors",
688
+ "text_encoder.encoder.block.6.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
689
+ "text_encoder.encoder.block.6.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
690
+ "text_encoder.encoder.block.7.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
691
+ "text_encoder.encoder.block.7.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
692
+ "text_encoder.encoder.block.7.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
693
+ "text_encoder.encoder.block.7.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
694
+ "text_encoder.encoder.block.7.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
695
+ "text_encoder.encoder.block.7.layer.1.DenseReluDense.wi.weight": "model-00001-of-00002.safetensors",
696
+ "text_encoder.encoder.block.7.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
697
+ "text_encoder.encoder.block.7.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
698
+ "text_encoder.encoder.block.8.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
699
+ "text_encoder.encoder.block.8.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
700
+ "text_encoder.encoder.block.8.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
701
+ "text_encoder.encoder.block.8.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
702
+ "text_encoder.encoder.block.8.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
703
+ "text_encoder.encoder.block.8.layer.1.DenseReluDense.wi.weight": "model-00001-of-00002.safetensors",
704
+ "text_encoder.encoder.block.8.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
705
+ "text_encoder.encoder.block.8.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
706
+ "text_encoder.encoder.block.9.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
707
+ "text_encoder.encoder.block.9.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
708
+ "text_encoder.encoder.block.9.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
709
+ "text_encoder.encoder.block.9.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
710
+ "text_encoder.encoder.block.9.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
711
+ "text_encoder.encoder.block.9.layer.1.DenseReluDense.wi.weight": "model-00001-of-00002.safetensors",
712
+ "text_encoder.encoder.block.9.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
713
+ "text_encoder.encoder.block.9.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
714
+ "text_encoder.encoder.final_layer_norm.weight": "model-00001-of-00002.safetensors",
715
+ "text_encoder.shared.weight": "model-00001-of-00002.safetensors"
716
+ }
717
+ }
preprocessor_config.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "chunk_length": 30,
3
+ "feature_extractor_type": "MusicgenMelodyFeatureExtractor",
4
+ "feature_size": 12,
5
+ "hop_length": 4096,
6
+ "n_fft": 16384,
7
+ "n_samples": 960000,
8
+ "padding_side": "right",
9
+ "padding_value": 0.0,
10
+ "processor_class": "MusicgenMelodyProcessor",
11
+ "return_attention_mask": false,
12
+ "sampling_rate": 32000,
13
+ "stem_indices": [
14
+ 3,
15
+ 2
16
+ ]
17
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,125 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": {
105
+ "content": "</s>",
106
+ "lstrip": false,
107
+ "normalized": false,
108
+ "rstrip": false,
109
+ "single_word": false
110
+ },
111
+ "pad_token": {
112
+ "content": "<pad>",
113
+ "lstrip": false,
114
+ "normalized": false,
115
+ "rstrip": false,
116
+ "single_word": false
117
+ },
118
+ "unk_token": {
119
+ "content": "<unk>",
120
+ "lstrip": false,
121
+ "normalized": false,
122
+ "rstrip": false,
123
+ "single_word": false
124
+ }
125
+ }
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 +1,942 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<pad>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "</s>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "<unk>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "32000": {
28
+ "content": "<extra_id_99>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "32001": {
36
+ "content": "<extra_id_98>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "32002": {
44
+ "content": "<extra_id_97>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "32003": {
52
+ "content": "<extra_id_96>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "32004": {
60
+ "content": "<extra_id_95>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "32005": {
68
+ "content": "<extra_id_94>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "32006": {
76
+ "content": "<extra_id_93>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "32007": {
84
+ "content": "<extra_id_92>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "32008": {
92
+ "content": "<extra_id_91>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "32009": {
100
+ "content": "<extra_id_90>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "32010": {
108
+ "content": "<extra_id_89>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "32011": {
116
+ "content": "<extra_id_88>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "32012": {
124
+ "content": "<extra_id_87>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "32013": {
132
+ "content": "<extra_id_86>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "32014": {
140
+ "content": "<extra_id_85>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "32015": {
148
+ "content": "<extra_id_84>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "32016": {
156
+ "content": "<extra_id_83>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "32017": {
164
+ "content": "<extra_id_82>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "32018": {
172
+ "content": "<extra_id_81>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "32019": {
180
+ "content": "<extra_id_80>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "32020": {
188
+ "content": "<extra_id_79>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "32021": {
196
+ "content": "<extra_id_78>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "32022": {
204
+ "content": "<extra_id_77>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "32023": {
212
+ "content": "<extra_id_76>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "32024": {
220
+ "content": "<extra_id_75>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "32025": {
228
+ "content": "<extra_id_74>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "32026": {
236
+ "content": "<extra_id_73>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "32027": {
244
+ "content": "<extra_id_72>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "32028": {
252
+ "content": "<extra_id_71>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "32029": {
260
+ "content": "<extra_id_70>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "32030": {
268
+ "content": "<extra_id_69>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "32031": {
276
+ "content": "<extra_id_68>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "32032": {
284
+ "content": "<extra_id_67>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "32033": {
292
+ "content": "<extra_id_66>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "32034": {
300
+ "content": "<extra_id_65>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "32035": {
308
+ "content": "<extra_id_64>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "32036": {
316
+ "content": "<extra_id_63>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "32037": {
324
+ "content": "<extra_id_62>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "32038": {
332
+ "content": "<extra_id_61>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "32039": {
340
+ "content": "<extra_id_60>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "32040": {
348
+ "content": "<extra_id_59>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "32041": {
356
+ "content": "<extra_id_58>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "32042": {
364
+ "content": "<extra_id_57>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "32043": {
372
+ "content": "<extra_id_56>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "32044": {
380
+ "content": "<extra_id_55>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "32045": {
388
+ "content": "<extra_id_54>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "32046": {
396
+ "content": "<extra_id_53>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "32047": {
404
+ "content": "<extra_id_52>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "32048": {
412
+ "content": "<extra_id_51>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "32049": {
420
+ "content": "<extra_id_50>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "32050": {
428
+ "content": "<extra_id_49>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "32051": {
436
+ "content": "<extra_id_48>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "32052": {
444
+ "content": "<extra_id_47>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "32053": {
452
+ "content": "<extra_id_46>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "32054": {
460
+ "content": "<extra_id_45>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "32055": {
468
+ "content": "<extra_id_44>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "32056": {
476
+ "content": "<extra_id_43>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "32057": {
484
+ "content": "<extra_id_42>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "32058": {
492
+ "content": "<extra_id_41>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "32059": {
500
+ "content": "<extra_id_40>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "32060": {
508
+ "content": "<extra_id_39>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "32061": {
516
+ "content": "<extra_id_38>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "32062": {
524
+ "content": "<extra_id_37>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "32063": {
532
+ "content": "<extra_id_36>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "32064": {
540
+ "content": "<extra_id_35>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "32065": {
548
+ "content": "<extra_id_34>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "32066": {
556
+ "content": "<extra_id_33>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "32067": {
564
+ "content": "<extra_id_32>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "32068": {
572
+ "content": "<extra_id_31>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "32069": {
580
+ "content": "<extra_id_30>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "32070": {
588
+ "content": "<extra_id_29>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "32071": {
596
+ "content": "<extra_id_28>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "32072": {
604
+ "content": "<extra_id_27>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "32073": {
612
+ "content": "<extra_id_26>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "32074": {
620
+ "content": "<extra_id_25>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "32075": {
628
+ "content": "<extra_id_24>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "32076": {
636
+ "content": "<extra_id_23>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "32077": {
644
+ "content": "<extra_id_22>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "32078": {
652
+ "content": "<extra_id_21>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "32079": {
660
+ "content": "<extra_id_20>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "32080": {
668
+ "content": "<extra_id_19>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "32081": {
676
+ "content": "<extra_id_18>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "32082": {
684
+ "content": "<extra_id_17>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "32083": {
692
+ "content": "<extra_id_16>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "32084": {
700
+ "content": "<extra_id_15>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "32085": {
708
+ "content": "<extra_id_14>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "32086": {
716
+ "content": "<extra_id_13>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "32087": {
724
+ "content": "<extra_id_12>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "32088": {
732
+ "content": "<extra_id_11>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "32089": {
740
+ "content": "<extra_id_10>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "32090": {
748
+ "content": "<extra_id_9>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "32091": {
756
+ "content": "<extra_id_8>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "32092": {
764
+ "content": "<extra_id_7>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "32093": {
772
+ "content": "<extra_id_6>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "32094": {
780
+ "content": "<extra_id_5>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "32095": {
788
+ "content": "<extra_id_4>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "32096": {
796
+ "content": "<extra_id_3>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "32097": {
804
+ "content": "<extra_id_2>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "32098": {
812
+ "content": "<extra_id_1>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "32099": {
820
+ "content": "<extra_id_0>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ }
827
+ },
828
+ "additional_special_tokens": [
829
+ "<extra_id_0>",
830
+ "<extra_id_1>",
831
+ "<extra_id_2>",
832
+ "<extra_id_3>",
833
+ "<extra_id_4>",
834
+ "<extra_id_5>",
835
+ "<extra_id_6>",
836
+ "<extra_id_7>",
837
+ "<extra_id_8>",
838
+ "<extra_id_9>",
839
+ "<extra_id_10>",
840
+ "<extra_id_11>",
841
+ "<extra_id_12>",
842
+ "<extra_id_13>",
843
+ "<extra_id_14>",
844
+ "<extra_id_15>",
845
+ "<extra_id_16>",
846
+ "<extra_id_17>",
847
+ "<extra_id_18>",
848
+ "<extra_id_19>",
849
+ "<extra_id_20>",
850
+ "<extra_id_21>",
851
+ "<extra_id_22>",
852
+ "<extra_id_23>",
853
+ "<extra_id_24>",
854
+ "<extra_id_25>",
855
+ "<extra_id_26>",
856
+ "<extra_id_27>",
857
+ "<extra_id_28>",
858
+ "<extra_id_29>",
859
+ "<extra_id_30>",
860
+ "<extra_id_31>",
861
+ "<extra_id_32>",
862
+ "<extra_id_33>",
863
+ "<extra_id_34>",
864
+ "<extra_id_35>",
865
+ "<extra_id_36>",
866
+ "<extra_id_37>",
867
+ "<extra_id_38>",
868
+ "<extra_id_39>",
869
+ "<extra_id_40>",
870
+ "<extra_id_41>",
871
+ "<extra_id_42>",
872
+ "<extra_id_43>",
873
+ "<extra_id_44>",
874
+ "<extra_id_45>",
875
+ "<extra_id_46>",
876
+ "<extra_id_47>",
877
+ "<extra_id_48>",
878
+ "<extra_id_49>",
879
+ "<extra_id_50>",
880
+ "<extra_id_51>",
881
+ "<extra_id_52>",
882
+ "<extra_id_53>",
883
+ "<extra_id_54>",
884
+ "<extra_id_55>",
885
+ "<extra_id_56>",
886
+ "<extra_id_57>",
887
+ "<extra_id_58>",
888
+ "<extra_id_59>",
889
+ "<extra_id_60>",
890
+ "<extra_id_61>",
891
+ "<extra_id_62>",
892
+ "<extra_id_63>",
893
+ "<extra_id_64>",
894
+ "<extra_id_65>",
895
+ "<extra_id_66>",
896
+ "<extra_id_67>",
897
+ "<extra_id_68>",
898
+ "<extra_id_69>",
899
+ "<extra_id_70>",
900
+ "<extra_id_71>",
901
+ "<extra_id_72>",
902
+ "<extra_id_73>",
903
+ "<extra_id_74>",
904
+ "<extra_id_75>",
905
+ "<extra_id_76>",
906
+ "<extra_id_77>",
907
+ "<extra_id_78>",
908
+ "<extra_id_79>",
909
+ "<extra_id_80>",
910
+ "<extra_id_81>",
911
+ "<extra_id_82>",
912
+ "<extra_id_83>",
913
+ "<extra_id_84>",
914
+ "<extra_id_85>",
915
+ "<extra_id_86>",
916
+ "<extra_id_87>",
917
+ "<extra_id_88>",
918
+ "<extra_id_89>",
919
+ "<extra_id_90>",
920
+ "<extra_id_91>",
921
+ "<extra_id_92>",
922
+ "<extra_id_93>",
923
+ "<extra_id_94>",
924
+ "<extra_id_95>",
925
+ "<extra_id_96>",
926
+ "<extra_id_97>",
927
+ "<extra_id_98>",
928
+ "<extra_id_99>"
929
+ ],
930
+ "clean_up_tokenization_spaces": true,
931
+ "eos_token": "</s>",
932
+ "extra_ids": 100,
933
+ "max_length": null,
934
+ "model_max_length": 512,
935
+ "pad_to_multiple_of": null,
936
+ "pad_token": "<pad>",
937
+ "pad_token_type_id": 0,
938
+ "padding_side": "right",
939
+ "processor_class": "MusicgenMelodyProcessor",
940
+ "tokenizer_class": "T5Tokenizer",
941
+ "unk_token": "<unk>"
942
+ }
train_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.764705882352941,
3
+ "total_flos": 59875624258368.0,
4
+ "train_loss": 8.819526672363281,
5
+ "train_runtime": 269.5748,
6
+ "train_samples": 33,
7
+ "train_samples_per_second": 0.49,
8
+ "train_steps_per_second": 0.03
9
+ }
trainer_state.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.764705882352941,
5
+ "eval_steps": 100,
6
+ "global_step": 8,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 3.764705882352941,
13
+ "step": 8,
14
+ "total_flos": 59875624258368.0,
15
+ "train_loss": 8.819526672363281,
16
+ "train_runtime": 269.5748,
17
+ "train_samples_per_second": 0.49,
18
+ "train_steps_per_second": 0.03
19
+ }
20
+ ],
21
+ "logging_steps": 25,
22
+ "max_steps": 8,
23
+ "num_input_tokens_seen": 0,
24
+ "num_train_epochs": 4,
25
+ "save_steps": 500,
26
+ "total_flos": 59875624258368.0,
27
+ "train_batch_size": 2,
28
+ "trial_name": null,
29
+ "trial_params": null
30
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1ccac7c14909717b76ae18f6c6e89f17008eafe9462a646abafd7de11fc3992
3
+ size 5112