ylacombe HF staff commited on
Commit
2f73ad7
1 Parent(s): 9e81020

Upload MusicgenMelodyForConditionalGeneration

Browse files
README.md CHANGED
@@ -1,8 +1,8 @@
1
  ---
2
- inference: false
3
  tags:
4
  - musicgen
5
- license: cc-by-nc-4.0
6
  ---
7
 
8
  # MusicGen - Melody - Large 3.3B
 
1
  ---
2
+ license: cc-by-nc-4.0
3
  tags:
4
  - musicgen
5
+ inference: false
6
  ---
7
 
8
  # MusicGen - Melody - Large 3.3B
config.json ADDED
@@ -0,0 +1,296 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "MusicgenMelodyForConditionalGeneration"
4
+ ],
5
+ "audio_encoder": {
6
+ "_name_or_path": "facebook/encodec_32khz",
7
+ "add_cross_attention": false,
8
+ "architectures": [
9
+ "EncodecModel"
10
+ ],
11
+ "audio_channels": 1,
12
+ "bad_words_ids": null,
13
+ "begin_suppress_tokens": null,
14
+ "bos_token_id": null,
15
+ "chunk_length_s": null,
16
+ "chunk_size_feed_forward": 0,
17
+ "codebook_dim": 128,
18
+ "codebook_size": 2048,
19
+ "compress": 2,
20
+ "cross_attention_hidden_size": null,
21
+ "decoder_start_token_id": null,
22
+ "dilation_growth_rate": 2,
23
+ "diversity_penalty": 0.0,
24
+ "do_sample": false,
25
+ "early_stopping": false,
26
+ "encoder_no_repeat_ngram_size": 0,
27
+ "eos_token_id": null,
28
+ "exponential_decay_length_penalty": null,
29
+ "finetuning_task": null,
30
+ "forced_bos_token_id": null,
31
+ "forced_eos_token_id": null,
32
+ "hidden_size": 128,
33
+ "id2label": {
34
+ "0": "LABEL_0",
35
+ "1": "LABEL_1"
36
+ },
37
+ "is_decoder": false,
38
+ "is_encoder_decoder": false,
39
+ "kernel_size": 7,
40
+ "label2id": {
41
+ "LABEL_0": 0,
42
+ "LABEL_1": 1
43
+ },
44
+ "last_kernel_size": 7,
45
+ "length_penalty": 1.0,
46
+ "max_length": 20,
47
+ "min_length": 0,
48
+ "model_type": "encodec",
49
+ "no_repeat_ngram_size": 0,
50
+ "norm_type": "weight_norm",
51
+ "normalize": false,
52
+ "num_beam_groups": 1,
53
+ "num_beams": 1,
54
+ "num_filters": 64,
55
+ "num_lstm_layers": 2,
56
+ "num_residual_layers": 1,
57
+ "num_return_sequences": 1,
58
+ "output_attentions": false,
59
+ "output_hidden_states": false,
60
+ "output_scores": false,
61
+ "overlap": null,
62
+ "pad_mode": "reflect",
63
+ "pad_token_id": null,
64
+ "prefix": null,
65
+ "problem_type": null,
66
+ "pruned_heads": {},
67
+ "remove_invalid_values": false,
68
+ "repetition_penalty": 1.0,
69
+ "residual_kernel_size": 3,
70
+ "return_dict": true,
71
+ "return_dict_in_generate": false,
72
+ "sampling_rate": 32000,
73
+ "sep_token_id": null,
74
+ "suppress_tokens": null,
75
+ "target_bandwidths": [
76
+ 2.2
77
+ ],
78
+ "task_specific_params": null,
79
+ "temperature": 1.0,
80
+ "tf_legacy_loss": false,
81
+ "tie_encoder_decoder": false,
82
+ "tie_word_embeddings": true,
83
+ "tokenizer_class": null,
84
+ "top_k": 50,
85
+ "top_p": 1.0,
86
+ "torch_dtype": "float32",
87
+ "torchscript": false,
88
+ "trim_right_ratio": 1.0,
89
+ "typical_p": 1.0,
90
+ "upsampling_ratios": [
91
+ 8,
92
+ 5,
93
+ 4,
94
+ 4
95
+ ],
96
+ "use_bfloat16": false,
97
+ "use_causal_conv": false,
98
+ "use_conv_shortcut": false
99
+ },
100
+ "chroma_length": 235,
101
+ "decoder": {
102
+ "_name_or_path": "",
103
+ "activation_dropout": 0.0,
104
+ "activation_function": "gelu",
105
+ "add_cross_attention": false,
106
+ "architectures": null,
107
+ "attention_dropout": 0.0,
108
+ "audio_channels": 1,
109
+ "bad_words_ids": null,
110
+ "begin_suppress_tokens": null,
111
+ "bos_token_id": 2048,
112
+ "chunk_size_feed_forward": 0,
113
+ "cross_attention_hidden_size": null,
114
+ "decoder_start_token_id": null,
115
+ "diversity_penalty": 0.0,
116
+ "do_sample": false,
117
+ "dropout": 0.1,
118
+ "early_stopping": false,
119
+ "encoder_no_repeat_ngram_size": 0,
120
+ "eos_token_id": null,
121
+ "exponential_decay_length_penalty": null,
122
+ "ffn_dim": 8192,
123
+ "finetuning_task": null,
124
+ "forced_bos_token_id": null,
125
+ "forced_eos_token_id": null,
126
+ "hidden_size": 2048,
127
+ "id2label": {
128
+ "0": "LABEL_0",
129
+ "1": "LABEL_1"
130
+ },
131
+ "initializer_factor": 0.02,
132
+ "is_decoder": false,
133
+ "is_encoder_decoder": false,
134
+ "label2id": {
135
+ "LABEL_0": 0,
136
+ "LABEL_1": 1
137
+ },
138
+ "layerdrop": 0.0,
139
+ "length_penalty": 1.0,
140
+ "max_length": 20,
141
+ "max_position_embeddings": 2048,
142
+ "min_length": 0,
143
+ "model_type": "musicgen_melody_decoder",
144
+ "no_repeat_ngram_size": 0,
145
+ "num_attention_heads": 32,
146
+ "num_beam_groups": 1,
147
+ "num_beams": 1,
148
+ "num_codebooks": 4,
149
+ "num_hidden_layers": 48,
150
+ "num_return_sequences": 1,
151
+ "output_attentions": false,
152
+ "output_hidden_states": false,
153
+ "output_scores": false,
154
+ "pad_token_id": 2048,
155
+ "prefix": null,
156
+ "problem_type": null,
157
+ "pruned_heads": {},
158
+ "remove_invalid_values": false,
159
+ "repetition_penalty": 1.0,
160
+ "return_dict": true,
161
+ "return_dict_in_generate": false,
162
+ "scale_embedding": false,
163
+ "sep_token_id": null,
164
+ "suppress_tokens": null,
165
+ "task_specific_params": null,
166
+ "temperature": 1.0,
167
+ "tf_legacy_loss": false,
168
+ "tie_encoder_decoder": false,
169
+ "tie_word_embeddings": false,
170
+ "tokenizer_class": null,
171
+ "top_k": 50,
172
+ "top_p": 1.0,
173
+ "torch_dtype": null,
174
+ "torchscript": false,
175
+ "typical_p": 1.0,
176
+ "use_bfloat16": false,
177
+ "use_cache": true,
178
+ "vocab_size": 2048
179
+ },
180
+ "model_type": "musicgen_melody",
181
+ "num_chroma": 12,
182
+ "text_encoder": {
183
+ "_name_or_path": "t5-base",
184
+ "add_cross_attention": false,
185
+ "architectures": [
186
+ "T5ForConditionalGeneration"
187
+ ],
188
+ "bad_words_ids": null,
189
+ "begin_suppress_tokens": null,
190
+ "bos_token_id": null,
191
+ "chunk_size_feed_forward": 0,
192
+ "classifier_dropout": 0.0,
193
+ "cross_attention_hidden_size": null,
194
+ "d_ff": 3072,
195
+ "d_kv": 64,
196
+ "d_model": 768,
197
+ "decoder_start_token_id": 0,
198
+ "dense_act_fn": "relu",
199
+ "diversity_penalty": 0.0,
200
+ "do_sample": false,
201
+ "dropout_rate": 0.1,
202
+ "early_stopping": false,
203
+ "encoder_no_repeat_ngram_size": 0,
204
+ "eos_token_id": 1,
205
+ "exponential_decay_length_penalty": null,
206
+ "feed_forward_proj": "relu",
207
+ "finetuning_task": null,
208
+ "forced_bos_token_id": null,
209
+ "forced_eos_token_id": null,
210
+ "id2label": {
211
+ "0": "LABEL_0",
212
+ "1": "LABEL_1"
213
+ },
214
+ "initializer_factor": 1.0,
215
+ "is_decoder": false,
216
+ "is_encoder_decoder": true,
217
+ "is_gated_act": false,
218
+ "label2id": {
219
+ "LABEL_0": 0,
220
+ "LABEL_1": 1
221
+ },
222
+ "layer_norm_epsilon": 1e-06,
223
+ "length_penalty": 1.0,
224
+ "max_length": 20,
225
+ "min_length": 0,
226
+ "model_type": "t5",
227
+ "n_positions": 512,
228
+ "no_repeat_ngram_size": 0,
229
+ "num_beam_groups": 1,
230
+ "num_beams": 1,
231
+ "num_decoder_layers": 12,
232
+ "num_heads": 12,
233
+ "num_layers": 12,
234
+ "num_return_sequences": 1,
235
+ "output_attentions": false,
236
+ "output_hidden_states": false,
237
+ "output_past": true,
238
+ "output_scores": false,
239
+ "pad_token_id": 0,
240
+ "prefix": null,
241
+ "problem_type": null,
242
+ "pruned_heads": {},
243
+ "relative_attention_max_distance": 128,
244
+ "relative_attention_num_buckets": 32,
245
+ "remove_invalid_values": false,
246
+ "repetition_penalty": 1.0,
247
+ "return_dict": true,
248
+ "return_dict_in_generate": false,
249
+ "sep_token_id": null,
250
+ "suppress_tokens": null,
251
+ "task_specific_params": {
252
+ "summarization": {
253
+ "early_stopping": true,
254
+ "length_penalty": 2.0,
255
+ "max_length": 200,
256
+ "min_length": 30,
257
+ "no_repeat_ngram_size": 3,
258
+ "num_beams": 4,
259
+ "prefix": "summarize: "
260
+ },
261
+ "translation_en_to_de": {
262
+ "early_stopping": true,
263
+ "max_length": 300,
264
+ "num_beams": 4,
265
+ "prefix": "translate English to German: "
266
+ },
267
+ "translation_en_to_fr": {
268
+ "early_stopping": true,
269
+ "max_length": 300,
270
+ "num_beams": 4,
271
+ "prefix": "translate English to French: "
272
+ },
273
+ "translation_en_to_ro": {
274
+ "early_stopping": true,
275
+ "max_length": 300,
276
+ "num_beams": 4,
277
+ "prefix": "translate English to Romanian: "
278
+ }
279
+ },
280
+ "temperature": 1.0,
281
+ "tf_legacy_loss": false,
282
+ "tie_encoder_decoder": false,
283
+ "tie_word_embeddings": true,
284
+ "tokenizer_class": null,
285
+ "top_k": 50,
286
+ "top_p": 1.0,
287
+ "torch_dtype": null,
288
+ "torchscript": false,
289
+ "typical_p": 1.0,
290
+ "use_bfloat16": false,
291
+ "use_cache": true,
292
+ "vocab_size": 32128
293
+ },
294
+ "torch_dtype": "float32",
295
+ "transformers_version": "4.38.0.dev0"
296
+ }
generation_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 2048,
4
+ "decoder_start_token_id": 2048,
5
+ "do_sample": true,
6
+ "guidance_scale": 3.0,
7
+ "max_length": 1500,
8
+ "pad_token_id": 2048,
9
+ "transformers_version": "4.38.0.dev0"
10
+ }
model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a38e3ed0a1a1e9927278e20a2cb5e56bfce019b98f78295c99b9a747d9bda699
3
+ size 4986994376
model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff7f57ef40b093d1f69851ecde50f57eb89904aa2abd02912868447b73b212b8
3
+ size 4966890568
model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5aace972db765f0d5c9c7ba88119b1c1e7aae9fed43d226522f596af65c1ccf
3
+ size 543379288
model.safetensors.index.json ADDED
@@ -0,0 +1,717 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 10497173784
4
+ },
5
+ "weight_map": {
6
+ "audio_enc_to_dec_proj.bias": "model-00003-of-00003.safetensors",
7
+ "audio_enc_to_dec_proj.weight": "model-00003-of-00003.safetensors",
8
+ "audio_encoder.decoder.layers.0.conv.bias": "model-00001-of-00003.safetensors",
9
+ "audio_encoder.decoder.layers.0.conv.weight_g": "model-00001-of-00003.safetensors",
10
+ "audio_encoder.decoder.layers.0.conv.weight_v": "model-00001-of-00003.safetensors",
11
+ "audio_encoder.decoder.layers.1.lstm.bias_hh_l0": "model-00001-of-00003.safetensors",
12
+ "audio_encoder.decoder.layers.1.lstm.bias_hh_l1": "model-00001-of-00003.safetensors",
13
+ "audio_encoder.decoder.layers.1.lstm.bias_ih_l0": "model-00001-of-00003.safetensors",
14
+ "audio_encoder.decoder.layers.1.lstm.bias_ih_l1": "model-00001-of-00003.safetensors",
15
+ "audio_encoder.decoder.layers.1.lstm.weight_hh_l0": "model-00001-of-00003.safetensors",
16
+ "audio_encoder.decoder.layers.1.lstm.weight_hh_l1": "model-00001-of-00003.safetensors",
17
+ "audio_encoder.decoder.layers.1.lstm.weight_ih_l0": "model-00001-of-00003.safetensors",
18
+ "audio_encoder.decoder.layers.1.lstm.weight_ih_l1": "model-00001-of-00003.safetensors",
19
+ "audio_encoder.decoder.layers.10.block.1.conv.bias": "model-00001-of-00003.safetensors",
20
+ "audio_encoder.decoder.layers.10.block.1.conv.weight_g": "model-00001-of-00003.safetensors",
21
+ "audio_encoder.decoder.layers.10.block.1.conv.weight_v": "model-00001-of-00003.safetensors",
22
+ "audio_encoder.decoder.layers.10.block.3.conv.bias": "model-00001-of-00003.safetensors",
23
+ "audio_encoder.decoder.layers.10.block.3.conv.weight_g": "model-00001-of-00003.safetensors",
24
+ "audio_encoder.decoder.layers.10.block.3.conv.weight_v": "model-00001-of-00003.safetensors",
25
+ "audio_encoder.decoder.layers.12.conv.bias": "model-00001-of-00003.safetensors",
26
+ "audio_encoder.decoder.layers.12.conv.weight_g": "model-00001-of-00003.safetensors",
27
+ "audio_encoder.decoder.layers.12.conv.weight_v": "model-00001-of-00003.safetensors",
28
+ "audio_encoder.decoder.layers.13.block.1.conv.bias": "model-00001-of-00003.safetensors",
29
+ "audio_encoder.decoder.layers.13.block.1.conv.weight_g": "model-00001-of-00003.safetensors",
30
+ "audio_encoder.decoder.layers.13.block.1.conv.weight_v": "model-00001-of-00003.safetensors",
31
+ "audio_encoder.decoder.layers.13.block.3.conv.bias": "model-00001-of-00003.safetensors",
32
+ "audio_encoder.decoder.layers.13.block.3.conv.weight_g": "model-00001-of-00003.safetensors",
33
+ "audio_encoder.decoder.layers.13.block.3.conv.weight_v": "model-00001-of-00003.safetensors",
34
+ "audio_encoder.decoder.layers.15.conv.bias": "model-00001-of-00003.safetensors",
35
+ "audio_encoder.decoder.layers.15.conv.weight_g": "model-00001-of-00003.safetensors",
36
+ "audio_encoder.decoder.layers.15.conv.weight_v": "model-00001-of-00003.safetensors",
37
+ "audio_encoder.decoder.layers.3.conv.bias": "model-00001-of-00003.safetensors",
38
+ "audio_encoder.decoder.layers.3.conv.weight_g": "model-00001-of-00003.safetensors",
39
+ "audio_encoder.decoder.layers.3.conv.weight_v": "model-00001-of-00003.safetensors",
40
+ "audio_encoder.decoder.layers.4.block.1.conv.bias": "model-00001-of-00003.safetensors",
41
+ "audio_encoder.decoder.layers.4.block.1.conv.weight_g": "model-00001-of-00003.safetensors",
42
+ "audio_encoder.decoder.layers.4.block.1.conv.weight_v": "model-00001-of-00003.safetensors",
43
+ "audio_encoder.decoder.layers.4.block.3.conv.bias": "model-00001-of-00003.safetensors",
44
+ "audio_encoder.decoder.layers.4.block.3.conv.weight_g": "model-00001-of-00003.safetensors",
45
+ "audio_encoder.decoder.layers.4.block.3.conv.weight_v": "model-00001-of-00003.safetensors",
46
+ "audio_encoder.decoder.layers.6.conv.bias": "model-00001-of-00003.safetensors",
47
+ "audio_encoder.decoder.layers.6.conv.weight_g": "model-00001-of-00003.safetensors",
48
+ "audio_encoder.decoder.layers.6.conv.weight_v": "model-00001-of-00003.safetensors",
49
+ "audio_encoder.decoder.layers.7.block.1.conv.bias": "model-00001-of-00003.safetensors",
50
+ "audio_encoder.decoder.layers.7.block.1.conv.weight_g": "model-00001-of-00003.safetensors",
51
+ "audio_encoder.decoder.layers.7.block.1.conv.weight_v": "model-00001-of-00003.safetensors",
52
+ "audio_encoder.decoder.layers.7.block.3.conv.bias": "model-00001-of-00003.safetensors",
53
+ "audio_encoder.decoder.layers.7.block.3.conv.weight_g": "model-00001-of-00003.safetensors",
54
+ "audio_encoder.decoder.layers.7.block.3.conv.weight_v": "model-00001-of-00003.safetensors",
55
+ "audio_encoder.decoder.layers.9.conv.bias": "model-00001-of-00003.safetensors",
56
+ "audio_encoder.decoder.layers.9.conv.weight_g": "model-00001-of-00003.safetensors",
57
+ "audio_encoder.decoder.layers.9.conv.weight_v": "model-00001-of-00003.safetensors",
58
+ "audio_encoder.encoder.layers.0.conv.bias": "model-00001-of-00003.safetensors",
59
+ "audio_encoder.encoder.layers.0.conv.weight_g": "model-00001-of-00003.safetensors",
60
+ "audio_encoder.encoder.layers.0.conv.weight_v": "model-00001-of-00003.safetensors",
61
+ "audio_encoder.encoder.layers.1.block.1.conv.bias": "model-00001-of-00003.safetensors",
62
+ "audio_encoder.encoder.layers.1.block.1.conv.weight_g": "model-00001-of-00003.safetensors",
63
+ "audio_encoder.encoder.layers.1.block.1.conv.weight_v": "model-00001-of-00003.safetensors",
64
+ "audio_encoder.encoder.layers.1.block.3.conv.bias": "model-00001-of-00003.safetensors",
65
+ "audio_encoder.encoder.layers.1.block.3.conv.weight_g": "model-00001-of-00003.safetensors",
66
+ "audio_encoder.encoder.layers.1.block.3.conv.weight_v": "model-00001-of-00003.safetensors",
67
+ "audio_encoder.encoder.layers.10.block.1.conv.bias": "model-00001-of-00003.safetensors",
68
+ "audio_encoder.encoder.layers.10.block.1.conv.weight_g": "model-00001-of-00003.safetensors",
69
+ "audio_encoder.encoder.layers.10.block.1.conv.weight_v": "model-00001-of-00003.safetensors",
70
+ "audio_encoder.encoder.layers.10.block.3.conv.bias": "model-00001-of-00003.safetensors",
71
+ "audio_encoder.encoder.layers.10.block.3.conv.weight_g": "model-00001-of-00003.safetensors",
72
+ "audio_encoder.encoder.layers.10.block.3.conv.weight_v": "model-00001-of-00003.safetensors",
73
+ "audio_encoder.encoder.layers.12.conv.bias": "model-00001-of-00003.safetensors",
74
+ "audio_encoder.encoder.layers.12.conv.weight_g": "model-00001-of-00003.safetensors",
75
+ "audio_encoder.encoder.layers.12.conv.weight_v": "model-00001-of-00003.safetensors",
76
+ "audio_encoder.encoder.layers.13.lstm.bias_hh_l0": "model-00001-of-00003.safetensors",
77
+ "audio_encoder.encoder.layers.13.lstm.bias_hh_l1": "model-00001-of-00003.safetensors",
78
+ "audio_encoder.encoder.layers.13.lstm.bias_ih_l0": "model-00001-of-00003.safetensors",
79
+ "audio_encoder.encoder.layers.13.lstm.bias_ih_l1": "model-00001-of-00003.safetensors",
80
+ "audio_encoder.encoder.layers.13.lstm.weight_hh_l0": "model-00001-of-00003.safetensors",
81
+ "audio_encoder.encoder.layers.13.lstm.weight_hh_l1": "model-00001-of-00003.safetensors",
82
+ "audio_encoder.encoder.layers.13.lstm.weight_ih_l0": "model-00001-of-00003.safetensors",
83
+ "audio_encoder.encoder.layers.13.lstm.weight_ih_l1": "model-00001-of-00003.safetensors",
84
+ "audio_encoder.encoder.layers.15.conv.bias": "model-00001-of-00003.safetensors",
85
+ "audio_encoder.encoder.layers.15.conv.weight_g": "model-00001-of-00003.safetensors",
86
+ "audio_encoder.encoder.layers.15.conv.weight_v": "model-00001-of-00003.safetensors",
87
+ "audio_encoder.encoder.layers.3.conv.bias": "model-00001-of-00003.safetensors",
88
+ "audio_encoder.encoder.layers.3.conv.weight_g": "model-00001-of-00003.safetensors",
89
+ "audio_encoder.encoder.layers.3.conv.weight_v": "model-00001-of-00003.safetensors",
90
+ "audio_encoder.encoder.layers.4.block.1.conv.bias": "model-00001-of-00003.safetensors",
91
+ "audio_encoder.encoder.layers.4.block.1.conv.weight_g": "model-00001-of-00003.safetensors",
92
+ "audio_encoder.encoder.layers.4.block.1.conv.weight_v": "model-00001-of-00003.safetensors",
93
+ "audio_encoder.encoder.layers.4.block.3.conv.bias": "model-00001-of-00003.safetensors",
94
+ "audio_encoder.encoder.layers.4.block.3.conv.weight_g": "model-00001-of-00003.safetensors",
95
+ "audio_encoder.encoder.layers.4.block.3.conv.weight_v": "model-00001-of-00003.safetensors",
96
+ "audio_encoder.encoder.layers.6.conv.bias": "model-00001-of-00003.safetensors",
97
+ "audio_encoder.encoder.layers.6.conv.weight_g": "model-00001-of-00003.safetensors",
98
+ "audio_encoder.encoder.layers.6.conv.weight_v": "model-00001-of-00003.safetensors",
99
+ "audio_encoder.encoder.layers.7.block.1.conv.bias": "model-00001-of-00003.safetensors",
100
+ "audio_encoder.encoder.layers.7.block.1.conv.weight_g": "model-00001-of-00003.safetensors",
101
+ "audio_encoder.encoder.layers.7.block.1.conv.weight_v": "model-00001-of-00003.safetensors",
102
+ "audio_encoder.encoder.layers.7.block.3.conv.bias": "model-00001-of-00003.safetensors",
103
+ "audio_encoder.encoder.layers.7.block.3.conv.weight_g": "model-00001-of-00003.safetensors",
104
+ "audio_encoder.encoder.layers.7.block.3.conv.weight_v": "model-00001-of-00003.safetensors",
105
+ "audio_encoder.encoder.layers.9.conv.bias": "model-00001-of-00003.safetensors",
106
+ "audio_encoder.encoder.layers.9.conv.weight_g": "model-00001-of-00003.safetensors",
107
+ "audio_encoder.encoder.layers.9.conv.weight_v": "model-00001-of-00003.safetensors",
108
+ "audio_encoder.quantizer.layers.0.codebook.cluster_size": "model-00001-of-00003.safetensors",
109
+ "audio_encoder.quantizer.layers.0.codebook.embed": "model-00001-of-00003.safetensors",
110
+ "audio_encoder.quantizer.layers.0.codebook.embed_avg": "model-00001-of-00003.safetensors",
111
+ "audio_encoder.quantizer.layers.0.codebook.inited": "model-00001-of-00003.safetensors",
112
+ "audio_encoder.quantizer.layers.1.codebook.cluster_size": "model-00001-of-00003.safetensors",
113
+ "audio_encoder.quantizer.layers.1.codebook.embed": "model-00001-of-00003.safetensors",
114
+ "audio_encoder.quantizer.layers.1.codebook.embed_avg": "model-00001-of-00003.safetensors",
115
+ "audio_encoder.quantizer.layers.1.codebook.inited": "model-00001-of-00003.safetensors",
116
+ "audio_encoder.quantizer.layers.2.codebook.cluster_size": "model-00001-of-00003.safetensors",
117
+ "audio_encoder.quantizer.layers.2.codebook.embed": "model-00001-of-00003.safetensors",
118
+ "audio_encoder.quantizer.layers.2.codebook.embed_avg": "model-00001-of-00003.safetensors",
119
+ "audio_encoder.quantizer.layers.2.codebook.inited": "model-00001-of-00003.safetensors",
120
+ "audio_encoder.quantizer.layers.3.codebook.cluster_size": "model-00001-of-00003.safetensors",
121
+ "audio_encoder.quantizer.layers.3.codebook.embed": "model-00001-of-00003.safetensors",
122
+ "audio_encoder.quantizer.layers.3.codebook.embed_avg": "model-00001-of-00003.safetensors",
123
+ "audio_encoder.quantizer.layers.3.codebook.inited": "model-00001-of-00003.safetensors",
124
+ "decoder.lm_heads.0.weight": "model-00003-of-00003.safetensors",
125
+ "decoder.lm_heads.1.weight": "model-00003-of-00003.safetensors",
126
+ "decoder.lm_heads.2.weight": "model-00003-of-00003.safetensors",
127
+ "decoder.lm_heads.3.weight": "model-00003-of-00003.safetensors",
128
+ "decoder.model.decoder.embed_positions.weights": "model-00001-of-00003.safetensors",
129
+ "decoder.model.decoder.embed_tokens.0.weight": "model-00001-of-00003.safetensors",
130
+ "decoder.model.decoder.embed_tokens.1.weight": "model-00001-of-00003.safetensors",
131
+ "decoder.model.decoder.embed_tokens.2.weight": "model-00001-of-00003.safetensors",
132
+ "decoder.model.decoder.embed_tokens.3.weight": "model-00001-of-00003.safetensors",
133
+ "decoder.model.decoder.layer_norm.bias": "model-00003-of-00003.safetensors",
134
+ "decoder.model.decoder.layer_norm.weight": "model-00003-of-00003.safetensors",
135
+ "decoder.model.decoder.layers.0.fc1.weight": "model-00001-of-00003.safetensors",
136
+ "decoder.model.decoder.layers.0.fc2.weight": "model-00001-of-00003.safetensors",
137
+ "decoder.model.decoder.layers.0.final_layer_norm.bias": "model-00001-of-00003.safetensors",
138
+ "decoder.model.decoder.layers.0.final_layer_norm.weight": "model-00001-of-00003.safetensors",
139
+ "decoder.model.decoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
140
+ "decoder.model.decoder.layers.0.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
141
+ "decoder.model.decoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
142
+ "decoder.model.decoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
143
+ "decoder.model.decoder.layers.0.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
144
+ "decoder.model.decoder.layers.0.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
145
+ "decoder.model.decoder.layers.1.fc1.weight": "model-00001-of-00003.safetensors",
146
+ "decoder.model.decoder.layers.1.fc2.weight": "model-00001-of-00003.safetensors",
147
+ "decoder.model.decoder.layers.1.final_layer_norm.bias": "model-00001-of-00003.safetensors",
148
+ "decoder.model.decoder.layers.1.final_layer_norm.weight": "model-00001-of-00003.safetensors",
149
+ "decoder.model.decoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
150
+ "decoder.model.decoder.layers.1.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
151
+ "decoder.model.decoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
152
+ "decoder.model.decoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
153
+ "decoder.model.decoder.layers.1.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
154
+ "decoder.model.decoder.layers.1.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
155
+ "decoder.model.decoder.layers.10.fc1.weight": "model-00001-of-00003.safetensors",
156
+ "decoder.model.decoder.layers.10.fc2.weight": "model-00001-of-00003.safetensors",
157
+ "decoder.model.decoder.layers.10.final_layer_norm.bias": "model-00001-of-00003.safetensors",
158
+ "decoder.model.decoder.layers.10.final_layer_norm.weight": "model-00001-of-00003.safetensors",
159
+ "decoder.model.decoder.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
160
+ "decoder.model.decoder.layers.10.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
161
+ "decoder.model.decoder.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
162
+ "decoder.model.decoder.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
163
+ "decoder.model.decoder.layers.10.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
164
+ "decoder.model.decoder.layers.10.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
165
+ "decoder.model.decoder.layers.11.fc1.weight": "model-00001-of-00003.safetensors",
166
+ "decoder.model.decoder.layers.11.fc2.weight": "model-00001-of-00003.safetensors",
167
+ "decoder.model.decoder.layers.11.final_layer_norm.bias": "model-00001-of-00003.safetensors",
168
+ "decoder.model.decoder.layers.11.final_layer_norm.weight": "model-00001-of-00003.safetensors",
169
+ "decoder.model.decoder.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
170
+ "decoder.model.decoder.layers.11.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
171
+ "decoder.model.decoder.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
172
+ "decoder.model.decoder.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
173
+ "decoder.model.decoder.layers.11.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
174
+ "decoder.model.decoder.layers.11.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
175
+ "decoder.model.decoder.layers.12.fc1.weight": "model-00001-of-00003.safetensors",
176
+ "decoder.model.decoder.layers.12.fc2.weight": "model-00001-of-00003.safetensors",
177
+ "decoder.model.decoder.layers.12.final_layer_norm.bias": "model-00001-of-00003.safetensors",
178
+ "decoder.model.decoder.layers.12.final_layer_norm.weight": "model-00001-of-00003.safetensors",
179
+ "decoder.model.decoder.layers.12.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
180
+ "decoder.model.decoder.layers.12.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
181
+ "decoder.model.decoder.layers.12.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
182
+ "decoder.model.decoder.layers.12.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
183
+ "decoder.model.decoder.layers.12.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
184
+ "decoder.model.decoder.layers.12.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
185
+ "decoder.model.decoder.layers.13.fc1.weight": "model-00001-of-00003.safetensors",
186
+ "decoder.model.decoder.layers.13.fc2.weight": "model-00001-of-00003.safetensors",
187
+ "decoder.model.decoder.layers.13.final_layer_norm.bias": "model-00001-of-00003.safetensors",
188
+ "decoder.model.decoder.layers.13.final_layer_norm.weight": "model-00001-of-00003.safetensors",
189
+ "decoder.model.decoder.layers.13.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
190
+ "decoder.model.decoder.layers.13.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
191
+ "decoder.model.decoder.layers.13.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
192
+ "decoder.model.decoder.layers.13.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
193
+ "decoder.model.decoder.layers.13.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
194
+ "decoder.model.decoder.layers.13.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
195
+ "decoder.model.decoder.layers.14.fc1.weight": "model-00001-of-00003.safetensors",
196
+ "decoder.model.decoder.layers.14.fc2.weight": "model-00001-of-00003.safetensors",
197
+ "decoder.model.decoder.layers.14.final_layer_norm.bias": "model-00001-of-00003.safetensors",
198
+ "decoder.model.decoder.layers.14.final_layer_norm.weight": "model-00001-of-00003.safetensors",
199
+ "decoder.model.decoder.layers.14.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
200
+ "decoder.model.decoder.layers.14.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
201
+ "decoder.model.decoder.layers.14.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
202
+ "decoder.model.decoder.layers.14.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
203
+ "decoder.model.decoder.layers.14.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
204
+ "decoder.model.decoder.layers.14.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
205
+ "decoder.model.decoder.layers.15.fc1.weight": "model-00001-of-00003.safetensors",
206
+ "decoder.model.decoder.layers.15.fc2.weight": "model-00001-of-00003.safetensors",
207
+ "decoder.model.decoder.layers.15.final_layer_norm.bias": "model-00001-of-00003.safetensors",
208
+ "decoder.model.decoder.layers.15.final_layer_norm.weight": "model-00001-of-00003.safetensors",
209
+ "decoder.model.decoder.layers.15.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
210
+ "decoder.model.decoder.layers.15.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
211
+ "decoder.model.decoder.layers.15.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
212
+ "decoder.model.decoder.layers.15.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
213
+ "decoder.model.decoder.layers.15.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
214
+ "decoder.model.decoder.layers.15.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
215
+ "decoder.model.decoder.layers.16.fc1.weight": "model-00001-of-00003.safetensors",
216
+ "decoder.model.decoder.layers.16.fc2.weight": "model-00001-of-00003.safetensors",
217
+ "decoder.model.decoder.layers.16.final_layer_norm.bias": "model-00001-of-00003.safetensors",
218
+ "decoder.model.decoder.layers.16.final_layer_norm.weight": "model-00001-of-00003.safetensors",
219
+ "decoder.model.decoder.layers.16.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
220
+ "decoder.model.decoder.layers.16.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
221
+ "decoder.model.decoder.layers.16.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
222
+ "decoder.model.decoder.layers.16.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
223
+ "decoder.model.decoder.layers.16.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
224
+ "decoder.model.decoder.layers.16.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
225
+ "decoder.model.decoder.layers.17.fc1.weight": "model-00001-of-00003.safetensors",
226
+ "decoder.model.decoder.layers.17.fc2.weight": "model-00001-of-00003.safetensors",
227
+ "decoder.model.decoder.layers.17.final_layer_norm.bias": "model-00001-of-00003.safetensors",
228
+ "decoder.model.decoder.layers.17.final_layer_norm.weight": "model-00001-of-00003.safetensors",
229
+ "decoder.model.decoder.layers.17.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
230
+ "decoder.model.decoder.layers.17.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
231
+ "decoder.model.decoder.layers.17.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
232
+ "decoder.model.decoder.layers.17.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
233
+ "decoder.model.decoder.layers.17.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
234
+ "decoder.model.decoder.layers.17.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
235
+ "decoder.model.decoder.layers.18.fc1.weight": "model-00001-of-00003.safetensors",
236
+ "decoder.model.decoder.layers.18.fc2.weight": "model-00001-of-00003.safetensors",
237
+ "decoder.model.decoder.layers.18.final_layer_norm.bias": "model-00001-of-00003.safetensors",
238
+ "decoder.model.decoder.layers.18.final_layer_norm.weight": "model-00001-of-00003.safetensors",
239
+ "decoder.model.decoder.layers.18.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
240
+ "decoder.model.decoder.layers.18.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
241
+ "decoder.model.decoder.layers.18.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
242
+ "decoder.model.decoder.layers.18.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
243
+ "decoder.model.decoder.layers.18.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
244
+ "decoder.model.decoder.layers.18.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
245
+ "decoder.model.decoder.layers.19.fc1.weight": "model-00001-of-00003.safetensors",
246
+ "decoder.model.decoder.layers.19.fc2.weight": "model-00001-of-00003.safetensors",
247
+ "decoder.model.decoder.layers.19.final_layer_norm.bias": "model-00001-of-00003.safetensors",
248
+ "decoder.model.decoder.layers.19.final_layer_norm.weight": "model-00001-of-00003.safetensors",
249
+ "decoder.model.decoder.layers.19.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
250
+ "decoder.model.decoder.layers.19.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
251
+ "decoder.model.decoder.layers.19.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
252
+ "decoder.model.decoder.layers.19.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
253
+ "decoder.model.decoder.layers.19.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
254
+ "decoder.model.decoder.layers.19.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
255
+ "decoder.model.decoder.layers.2.fc1.weight": "model-00001-of-00003.safetensors",
256
+ "decoder.model.decoder.layers.2.fc2.weight": "model-00001-of-00003.safetensors",
257
+ "decoder.model.decoder.layers.2.final_layer_norm.bias": "model-00001-of-00003.safetensors",
258
+ "decoder.model.decoder.layers.2.final_layer_norm.weight": "model-00001-of-00003.safetensors",
259
+ "decoder.model.decoder.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
260
+ "decoder.model.decoder.layers.2.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
261
+ "decoder.model.decoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
262
+ "decoder.model.decoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
263
+ "decoder.model.decoder.layers.2.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
264
+ "decoder.model.decoder.layers.2.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
265
+ "decoder.model.decoder.layers.20.fc1.weight": "model-00001-of-00003.safetensors",
266
+ "decoder.model.decoder.layers.20.fc2.weight": "model-00001-of-00003.safetensors",
267
+ "decoder.model.decoder.layers.20.final_layer_norm.bias": "model-00001-of-00003.safetensors",
268
+ "decoder.model.decoder.layers.20.final_layer_norm.weight": "model-00001-of-00003.safetensors",
269
+ "decoder.model.decoder.layers.20.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
270
+ "decoder.model.decoder.layers.20.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
271
+ "decoder.model.decoder.layers.20.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
272
+ "decoder.model.decoder.layers.20.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
273
+ "decoder.model.decoder.layers.20.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
274
+ "decoder.model.decoder.layers.20.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
275
+ "decoder.model.decoder.layers.21.fc1.weight": "model-00002-of-00003.safetensors",
276
+ "decoder.model.decoder.layers.21.fc2.weight": "model-00002-of-00003.safetensors",
277
+ "decoder.model.decoder.layers.21.final_layer_norm.bias": "model-00002-of-00003.safetensors",
278
+ "decoder.model.decoder.layers.21.final_layer_norm.weight": "model-00002-of-00003.safetensors",
279
+ "decoder.model.decoder.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
280
+ "decoder.model.decoder.layers.21.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
281
+ "decoder.model.decoder.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
282
+ "decoder.model.decoder.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
283
+ "decoder.model.decoder.layers.21.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
284
+ "decoder.model.decoder.layers.21.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
285
+ "decoder.model.decoder.layers.22.fc1.weight": "model-00002-of-00003.safetensors",
286
+ "decoder.model.decoder.layers.22.fc2.weight": "model-00002-of-00003.safetensors",
287
+ "decoder.model.decoder.layers.22.final_layer_norm.bias": "model-00002-of-00003.safetensors",
288
+ "decoder.model.decoder.layers.22.final_layer_norm.weight": "model-00002-of-00003.safetensors",
289
+ "decoder.model.decoder.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
290
+ "decoder.model.decoder.layers.22.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
291
+ "decoder.model.decoder.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
292
+ "decoder.model.decoder.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
293
+ "decoder.model.decoder.layers.22.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
294
+ "decoder.model.decoder.layers.22.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
295
+ "decoder.model.decoder.layers.23.fc1.weight": "model-00002-of-00003.safetensors",
296
+ "decoder.model.decoder.layers.23.fc2.weight": "model-00002-of-00003.safetensors",
297
+ "decoder.model.decoder.layers.23.final_layer_norm.bias": "model-00002-of-00003.safetensors",
298
+ "decoder.model.decoder.layers.23.final_layer_norm.weight": "model-00002-of-00003.safetensors",
299
+ "decoder.model.decoder.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
300
+ "decoder.model.decoder.layers.23.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
301
+ "decoder.model.decoder.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
302
+ "decoder.model.decoder.layers.23.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
303
+ "decoder.model.decoder.layers.23.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
304
+ "decoder.model.decoder.layers.23.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
305
+ "decoder.model.decoder.layers.24.fc1.weight": "model-00002-of-00003.safetensors",
306
+ "decoder.model.decoder.layers.24.fc2.weight": "model-00002-of-00003.safetensors",
307
+ "decoder.model.decoder.layers.24.final_layer_norm.bias": "model-00002-of-00003.safetensors",
308
+ "decoder.model.decoder.layers.24.final_layer_norm.weight": "model-00002-of-00003.safetensors",
309
+ "decoder.model.decoder.layers.24.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
310
+ "decoder.model.decoder.layers.24.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
311
+ "decoder.model.decoder.layers.24.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
312
+ "decoder.model.decoder.layers.24.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
313
+ "decoder.model.decoder.layers.24.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
314
+ "decoder.model.decoder.layers.24.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
315
+ "decoder.model.decoder.layers.25.fc1.weight": "model-00002-of-00003.safetensors",
316
+ "decoder.model.decoder.layers.25.fc2.weight": "model-00002-of-00003.safetensors",
317
+ "decoder.model.decoder.layers.25.final_layer_norm.bias": "model-00002-of-00003.safetensors",
318
+ "decoder.model.decoder.layers.25.final_layer_norm.weight": "model-00002-of-00003.safetensors",
319
+ "decoder.model.decoder.layers.25.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
320
+ "decoder.model.decoder.layers.25.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
321
+ "decoder.model.decoder.layers.25.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
322
+ "decoder.model.decoder.layers.25.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
323
+ "decoder.model.decoder.layers.25.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
324
+ "decoder.model.decoder.layers.25.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
325
+ "decoder.model.decoder.layers.26.fc1.weight": "model-00002-of-00003.safetensors",
326
+ "decoder.model.decoder.layers.26.fc2.weight": "model-00002-of-00003.safetensors",
327
+ "decoder.model.decoder.layers.26.final_layer_norm.bias": "model-00002-of-00003.safetensors",
328
+ "decoder.model.decoder.layers.26.final_layer_norm.weight": "model-00002-of-00003.safetensors",
329
+ "decoder.model.decoder.layers.26.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
330
+ "decoder.model.decoder.layers.26.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
331
+ "decoder.model.decoder.layers.26.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
332
+ "decoder.model.decoder.layers.26.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
333
+ "decoder.model.decoder.layers.26.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
334
+ "decoder.model.decoder.layers.26.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
335
+ "decoder.model.decoder.layers.27.fc1.weight": "model-00002-of-00003.safetensors",
336
+ "decoder.model.decoder.layers.27.fc2.weight": "model-00002-of-00003.safetensors",
337
+ "decoder.model.decoder.layers.27.final_layer_norm.bias": "model-00002-of-00003.safetensors",
338
+ "decoder.model.decoder.layers.27.final_layer_norm.weight": "model-00002-of-00003.safetensors",
339
+ "decoder.model.decoder.layers.27.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
340
+ "decoder.model.decoder.layers.27.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
341
+ "decoder.model.decoder.layers.27.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
342
+ "decoder.model.decoder.layers.27.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
343
+ "decoder.model.decoder.layers.27.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
344
+ "decoder.model.decoder.layers.27.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
345
+ "decoder.model.decoder.layers.28.fc1.weight": "model-00002-of-00003.safetensors",
346
+ "decoder.model.decoder.layers.28.fc2.weight": "model-00002-of-00003.safetensors",
347
+ "decoder.model.decoder.layers.28.final_layer_norm.bias": "model-00002-of-00003.safetensors",
348
+ "decoder.model.decoder.layers.28.final_layer_norm.weight": "model-00002-of-00003.safetensors",
349
+ "decoder.model.decoder.layers.28.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
350
+ "decoder.model.decoder.layers.28.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
351
+ "decoder.model.decoder.layers.28.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
352
+ "decoder.model.decoder.layers.28.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
353
+ "decoder.model.decoder.layers.28.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
354
+ "decoder.model.decoder.layers.28.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
355
+ "decoder.model.decoder.layers.29.fc1.weight": "model-00002-of-00003.safetensors",
356
+ "decoder.model.decoder.layers.29.fc2.weight": "model-00002-of-00003.safetensors",
357
+ "decoder.model.decoder.layers.29.final_layer_norm.bias": "model-00002-of-00003.safetensors",
358
+ "decoder.model.decoder.layers.29.final_layer_norm.weight": "model-00002-of-00003.safetensors",
359
+ "decoder.model.decoder.layers.29.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
360
+ "decoder.model.decoder.layers.29.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
361
+ "decoder.model.decoder.layers.29.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
362
+ "decoder.model.decoder.layers.29.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
363
+ "decoder.model.decoder.layers.29.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
364
+ "decoder.model.decoder.layers.29.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
365
+ "decoder.model.decoder.layers.3.fc1.weight": "model-00001-of-00003.safetensors",
366
+ "decoder.model.decoder.layers.3.fc2.weight": "model-00001-of-00003.safetensors",
367
+ "decoder.model.decoder.layers.3.final_layer_norm.bias": "model-00001-of-00003.safetensors",
368
+ "decoder.model.decoder.layers.3.final_layer_norm.weight": "model-00001-of-00003.safetensors",
369
+ "decoder.model.decoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
370
+ "decoder.model.decoder.layers.3.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
371
+ "decoder.model.decoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
372
+ "decoder.model.decoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
373
+ "decoder.model.decoder.layers.3.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
374
+ "decoder.model.decoder.layers.3.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
375
+ "decoder.model.decoder.layers.30.fc1.weight": "model-00002-of-00003.safetensors",
376
+ "decoder.model.decoder.layers.30.fc2.weight": "model-00002-of-00003.safetensors",
377
+ "decoder.model.decoder.layers.30.final_layer_norm.bias": "model-00002-of-00003.safetensors",
378
+ "decoder.model.decoder.layers.30.final_layer_norm.weight": "model-00002-of-00003.safetensors",
379
+ "decoder.model.decoder.layers.30.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
380
+ "decoder.model.decoder.layers.30.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
381
+ "decoder.model.decoder.layers.30.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
382
+ "decoder.model.decoder.layers.30.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
383
+ "decoder.model.decoder.layers.30.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
384
+ "decoder.model.decoder.layers.30.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
385
+ "decoder.model.decoder.layers.31.fc1.weight": "model-00002-of-00003.safetensors",
386
+ "decoder.model.decoder.layers.31.fc2.weight": "model-00002-of-00003.safetensors",
387
+ "decoder.model.decoder.layers.31.final_layer_norm.bias": "model-00002-of-00003.safetensors",
388
+ "decoder.model.decoder.layers.31.final_layer_norm.weight": "model-00002-of-00003.safetensors",
389
+ "decoder.model.decoder.layers.31.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
390
+ "decoder.model.decoder.layers.31.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
391
+ "decoder.model.decoder.layers.31.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
392
+ "decoder.model.decoder.layers.31.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
393
+ "decoder.model.decoder.layers.31.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
394
+ "decoder.model.decoder.layers.31.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
395
+ "decoder.model.decoder.layers.32.fc1.weight": "model-00002-of-00003.safetensors",
396
+ "decoder.model.decoder.layers.32.fc2.weight": "model-00002-of-00003.safetensors",
397
+ "decoder.model.decoder.layers.32.final_layer_norm.bias": "model-00002-of-00003.safetensors",
398
+ "decoder.model.decoder.layers.32.final_layer_norm.weight": "model-00002-of-00003.safetensors",
399
+ "decoder.model.decoder.layers.32.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
400
+ "decoder.model.decoder.layers.32.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
401
+ "decoder.model.decoder.layers.32.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
402
+ "decoder.model.decoder.layers.32.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
403
+ "decoder.model.decoder.layers.32.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
404
+ "decoder.model.decoder.layers.32.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
405
+ "decoder.model.decoder.layers.33.fc1.weight": "model-00002-of-00003.safetensors",
406
+ "decoder.model.decoder.layers.33.fc2.weight": "model-00002-of-00003.safetensors",
407
+ "decoder.model.decoder.layers.33.final_layer_norm.bias": "model-00002-of-00003.safetensors",
408
+ "decoder.model.decoder.layers.33.final_layer_norm.weight": "model-00002-of-00003.safetensors",
409
+ "decoder.model.decoder.layers.33.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
410
+ "decoder.model.decoder.layers.33.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
411
+ "decoder.model.decoder.layers.33.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
412
+ "decoder.model.decoder.layers.33.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
413
+ "decoder.model.decoder.layers.33.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
414
+ "decoder.model.decoder.layers.33.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
415
+ "decoder.model.decoder.layers.34.fc1.weight": "model-00002-of-00003.safetensors",
416
+ "decoder.model.decoder.layers.34.fc2.weight": "model-00002-of-00003.safetensors",
417
+ "decoder.model.decoder.layers.34.final_layer_norm.bias": "model-00002-of-00003.safetensors",
418
+ "decoder.model.decoder.layers.34.final_layer_norm.weight": "model-00002-of-00003.safetensors",
419
+ "decoder.model.decoder.layers.34.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
420
+ "decoder.model.decoder.layers.34.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
421
+ "decoder.model.decoder.layers.34.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
422
+ "decoder.model.decoder.layers.34.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
423
+ "decoder.model.decoder.layers.34.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
424
+ "decoder.model.decoder.layers.34.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
425
+ "decoder.model.decoder.layers.35.fc1.weight": "model-00002-of-00003.safetensors",
426
+ "decoder.model.decoder.layers.35.fc2.weight": "model-00002-of-00003.safetensors",
427
+ "decoder.model.decoder.layers.35.final_layer_norm.bias": "model-00002-of-00003.safetensors",
428
+ "decoder.model.decoder.layers.35.final_layer_norm.weight": "model-00002-of-00003.safetensors",
429
+ "decoder.model.decoder.layers.35.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
430
+ "decoder.model.decoder.layers.35.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
431
+ "decoder.model.decoder.layers.35.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
432
+ "decoder.model.decoder.layers.35.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
433
+ "decoder.model.decoder.layers.35.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
434
+ "decoder.model.decoder.layers.35.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
435
+ "decoder.model.decoder.layers.36.fc1.weight": "model-00002-of-00003.safetensors",
436
+ "decoder.model.decoder.layers.36.fc2.weight": "model-00002-of-00003.safetensors",
437
+ "decoder.model.decoder.layers.36.final_layer_norm.bias": "model-00002-of-00003.safetensors",
438
+ "decoder.model.decoder.layers.36.final_layer_norm.weight": "model-00002-of-00003.safetensors",
439
+ "decoder.model.decoder.layers.36.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
440
+ "decoder.model.decoder.layers.36.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
441
+ "decoder.model.decoder.layers.36.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
442
+ "decoder.model.decoder.layers.36.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
443
+ "decoder.model.decoder.layers.36.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
444
+ "decoder.model.decoder.layers.36.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
445
+ "decoder.model.decoder.layers.37.fc1.weight": "model-00002-of-00003.safetensors",
446
+ "decoder.model.decoder.layers.37.fc2.weight": "model-00002-of-00003.safetensors",
447
+ "decoder.model.decoder.layers.37.final_layer_norm.bias": "model-00002-of-00003.safetensors",
448
+ "decoder.model.decoder.layers.37.final_layer_norm.weight": "model-00002-of-00003.safetensors",
449
+ "decoder.model.decoder.layers.37.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
450
+ "decoder.model.decoder.layers.37.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
451
+ "decoder.model.decoder.layers.37.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
452
+ "decoder.model.decoder.layers.37.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
453
+ "decoder.model.decoder.layers.37.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
454
+ "decoder.model.decoder.layers.37.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
455
+ "decoder.model.decoder.layers.38.fc1.weight": "model-00002-of-00003.safetensors",
456
+ "decoder.model.decoder.layers.38.fc2.weight": "model-00002-of-00003.safetensors",
457
+ "decoder.model.decoder.layers.38.final_layer_norm.bias": "model-00002-of-00003.safetensors",
458
+ "decoder.model.decoder.layers.38.final_layer_norm.weight": "model-00002-of-00003.safetensors",
459
+ "decoder.model.decoder.layers.38.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
460
+ "decoder.model.decoder.layers.38.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
461
+ "decoder.model.decoder.layers.38.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
462
+ "decoder.model.decoder.layers.38.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
463
+ "decoder.model.decoder.layers.38.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
464
+ "decoder.model.decoder.layers.38.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
465
+ "decoder.model.decoder.layers.39.fc1.weight": "model-00002-of-00003.safetensors",
466
+ "decoder.model.decoder.layers.39.fc2.weight": "model-00002-of-00003.safetensors",
467
+ "decoder.model.decoder.layers.39.final_layer_norm.bias": "model-00002-of-00003.safetensors",
468
+ "decoder.model.decoder.layers.39.final_layer_norm.weight": "model-00002-of-00003.safetensors",
469
+ "decoder.model.decoder.layers.39.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
470
+ "decoder.model.decoder.layers.39.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
471
+ "decoder.model.decoder.layers.39.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
472
+ "decoder.model.decoder.layers.39.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
473
+ "decoder.model.decoder.layers.39.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
474
+ "decoder.model.decoder.layers.39.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
475
+ "decoder.model.decoder.layers.4.fc1.weight": "model-00001-of-00003.safetensors",
476
+ "decoder.model.decoder.layers.4.fc2.weight": "model-00001-of-00003.safetensors",
477
+ "decoder.model.decoder.layers.4.final_layer_norm.bias": "model-00001-of-00003.safetensors",
478
+ "decoder.model.decoder.layers.4.final_layer_norm.weight": "model-00001-of-00003.safetensors",
479
+ "decoder.model.decoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
480
+ "decoder.model.decoder.layers.4.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
481
+ "decoder.model.decoder.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
482
+ "decoder.model.decoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
483
+ "decoder.model.decoder.layers.4.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
484
+ "decoder.model.decoder.layers.4.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
485
+ "decoder.model.decoder.layers.40.fc1.weight": "model-00002-of-00003.safetensors",
486
+ "decoder.model.decoder.layers.40.fc2.weight": "model-00002-of-00003.safetensors",
487
+ "decoder.model.decoder.layers.40.final_layer_norm.bias": "model-00002-of-00003.safetensors",
488
+ "decoder.model.decoder.layers.40.final_layer_norm.weight": "model-00002-of-00003.safetensors",
489
+ "decoder.model.decoder.layers.40.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
490
+ "decoder.model.decoder.layers.40.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
491
+ "decoder.model.decoder.layers.40.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
492
+ "decoder.model.decoder.layers.40.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
493
+ "decoder.model.decoder.layers.40.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
494
+ "decoder.model.decoder.layers.40.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
495
+ "decoder.model.decoder.layers.41.fc1.weight": "model-00002-of-00003.safetensors",
496
+ "decoder.model.decoder.layers.41.fc2.weight": "model-00002-of-00003.safetensors",
497
+ "decoder.model.decoder.layers.41.final_layer_norm.bias": "model-00002-of-00003.safetensors",
498
+ "decoder.model.decoder.layers.41.final_layer_norm.weight": "model-00002-of-00003.safetensors",
499
+ "decoder.model.decoder.layers.41.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
500
+ "decoder.model.decoder.layers.41.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
501
+ "decoder.model.decoder.layers.41.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
502
+ "decoder.model.decoder.layers.41.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
503
+ "decoder.model.decoder.layers.41.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
504
+ "decoder.model.decoder.layers.41.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
505
+ "decoder.model.decoder.layers.42.fc1.weight": "model-00002-of-00003.safetensors",
506
+ "decoder.model.decoder.layers.42.fc2.weight": "model-00002-of-00003.safetensors",
507
+ "decoder.model.decoder.layers.42.final_layer_norm.bias": "model-00002-of-00003.safetensors",
508
+ "decoder.model.decoder.layers.42.final_layer_norm.weight": "model-00002-of-00003.safetensors",
509
+ "decoder.model.decoder.layers.42.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
510
+ "decoder.model.decoder.layers.42.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
511
+ "decoder.model.decoder.layers.42.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
512
+ "decoder.model.decoder.layers.42.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
513
+ "decoder.model.decoder.layers.42.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
514
+ "decoder.model.decoder.layers.42.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
515
+ "decoder.model.decoder.layers.43.fc1.weight": "model-00002-of-00003.safetensors",
516
+ "decoder.model.decoder.layers.43.fc2.weight": "model-00002-of-00003.safetensors",
517
+ "decoder.model.decoder.layers.43.final_layer_norm.bias": "model-00002-of-00003.safetensors",
518
+ "decoder.model.decoder.layers.43.final_layer_norm.weight": "model-00002-of-00003.safetensors",
519
+ "decoder.model.decoder.layers.43.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
520
+ "decoder.model.decoder.layers.43.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
521
+ "decoder.model.decoder.layers.43.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
522
+ "decoder.model.decoder.layers.43.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
523
+ "decoder.model.decoder.layers.43.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
524
+ "decoder.model.decoder.layers.43.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
525
+ "decoder.model.decoder.layers.44.fc1.weight": "model-00002-of-00003.safetensors",
526
+ "decoder.model.decoder.layers.44.fc2.weight": "model-00002-of-00003.safetensors",
527
+ "decoder.model.decoder.layers.44.final_layer_norm.bias": "model-00002-of-00003.safetensors",
528
+ "decoder.model.decoder.layers.44.final_layer_norm.weight": "model-00002-of-00003.safetensors",
529
+ "decoder.model.decoder.layers.44.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
530
+ "decoder.model.decoder.layers.44.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
531
+ "decoder.model.decoder.layers.44.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
532
+ "decoder.model.decoder.layers.44.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
533
+ "decoder.model.decoder.layers.44.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
534
+ "decoder.model.decoder.layers.44.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
535
+ "decoder.model.decoder.layers.45.fc1.weight": "model-00002-of-00003.safetensors",
536
+ "decoder.model.decoder.layers.45.fc2.weight": "model-00003-of-00003.safetensors",
537
+ "decoder.model.decoder.layers.45.final_layer_norm.bias": "model-00003-of-00003.safetensors",
538
+ "decoder.model.decoder.layers.45.final_layer_norm.weight": "model-00003-of-00003.safetensors",
539
+ "decoder.model.decoder.layers.45.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
540
+ "decoder.model.decoder.layers.45.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
541
+ "decoder.model.decoder.layers.45.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
542
+ "decoder.model.decoder.layers.45.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
543
+ "decoder.model.decoder.layers.45.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
544
+ "decoder.model.decoder.layers.45.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
545
+ "decoder.model.decoder.layers.46.fc1.weight": "model-00003-of-00003.safetensors",
546
+ "decoder.model.decoder.layers.46.fc2.weight": "model-00003-of-00003.safetensors",
547
+ "decoder.model.decoder.layers.46.final_layer_norm.bias": "model-00003-of-00003.safetensors",
548
+ "decoder.model.decoder.layers.46.final_layer_norm.weight": "model-00003-of-00003.safetensors",
549
+ "decoder.model.decoder.layers.46.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
550
+ "decoder.model.decoder.layers.46.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
551
+ "decoder.model.decoder.layers.46.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
552
+ "decoder.model.decoder.layers.46.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
553
+ "decoder.model.decoder.layers.46.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
554
+ "decoder.model.decoder.layers.46.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
555
+ "decoder.model.decoder.layers.47.fc1.weight": "model-00003-of-00003.safetensors",
556
+ "decoder.model.decoder.layers.47.fc2.weight": "model-00003-of-00003.safetensors",
557
+ "decoder.model.decoder.layers.47.final_layer_norm.bias": "model-00003-of-00003.safetensors",
558
+ "decoder.model.decoder.layers.47.final_layer_norm.weight": "model-00003-of-00003.safetensors",
559
+ "decoder.model.decoder.layers.47.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
560
+ "decoder.model.decoder.layers.47.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
561
+ "decoder.model.decoder.layers.47.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
562
+ "decoder.model.decoder.layers.47.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
563
+ "decoder.model.decoder.layers.47.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
564
+ "decoder.model.decoder.layers.47.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
565
+ "decoder.model.decoder.layers.5.fc1.weight": "model-00001-of-00003.safetensors",
566
+ "decoder.model.decoder.layers.5.fc2.weight": "model-00001-of-00003.safetensors",
567
+ "decoder.model.decoder.layers.5.final_layer_norm.bias": "model-00001-of-00003.safetensors",
568
+ "decoder.model.decoder.layers.5.final_layer_norm.weight": "model-00001-of-00003.safetensors",
569
+ "decoder.model.decoder.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
570
+ "decoder.model.decoder.layers.5.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
571
+ "decoder.model.decoder.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
572
+ "decoder.model.decoder.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
573
+ "decoder.model.decoder.layers.5.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
574
+ "decoder.model.decoder.layers.5.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
575
+ "decoder.model.decoder.layers.6.fc1.weight": "model-00001-of-00003.safetensors",
576
+ "decoder.model.decoder.layers.6.fc2.weight": "model-00001-of-00003.safetensors",
577
+ "decoder.model.decoder.layers.6.final_layer_norm.bias": "model-00001-of-00003.safetensors",
578
+ "decoder.model.decoder.layers.6.final_layer_norm.weight": "model-00001-of-00003.safetensors",
579
+ "decoder.model.decoder.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
580
+ "decoder.model.decoder.layers.6.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
581
+ "decoder.model.decoder.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
582
+ "decoder.model.decoder.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
583
+ "decoder.model.decoder.layers.6.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
584
+ "decoder.model.decoder.layers.6.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
585
+ "decoder.model.decoder.layers.7.fc1.weight": "model-00001-of-00003.safetensors",
586
+ "decoder.model.decoder.layers.7.fc2.weight": "model-00001-of-00003.safetensors",
587
+ "decoder.model.decoder.layers.7.final_layer_norm.bias": "model-00001-of-00003.safetensors",
588
+ "decoder.model.decoder.layers.7.final_layer_norm.weight": "model-00001-of-00003.safetensors",
589
+ "decoder.model.decoder.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
590
+ "decoder.model.decoder.layers.7.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
591
+ "decoder.model.decoder.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
592
+ "decoder.model.decoder.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
593
+ "decoder.model.decoder.layers.7.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
594
+ "decoder.model.decoder.layers.7.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
595
+ "decoder.model.decoder.layers.8.fc1.weight": "model-00001-of-00003.safetensors",
596
+ "decoder.model.decoder.layers.8.fc2.weight": "model-00001-of-00003.safetensors",
597
+ "decoder.model.decoder.layers.8.final_layer_norm.bias": "model-00001-of-00003.safetensors",
598
+ "decoder.model.decoder.layers.8.final_layer_norm.weight": "model-00001-of-00003.safetensors",
599
+ "decoder.model.decoder.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
600
+ "decoder.model.decoder.layers.8.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
601
+ "decoder.model.decoder.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
602
+ "decoder.model.decoder.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
603
+ "decoder.model.decoder.layers.8.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
604
+ "decoder.model.decoder.layers.8.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
605
+ "decoder.model.decoder.layers.9.fc1.weight": "model-00001-of-00003.safetensors",
606
+ "decoder.model.decoder.layers.9.fc2.weight": "model-00001-of-00003.safetensors",
607
+ "decoder.model.decoder.layers.9.final_layer_norm.bias": "model-00001-of-00003.safetensors",
608
+ "decoder.model.decoder.layers.9.final_layer_norm.weight": "model-00001-of-00003.safetensors",
609
+ "decoder.model.decoder.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
610
+ "decoder.model.decoder.layers.9.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
611
+ "decoder.model.decoder.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
612
+ "decoder.model.decoder.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
613
+ "decoder.model.decoder.layers.9.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
614
+ "decoder.model.decoder.layers.9.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
615
+ "enc_to_dec_proj.bias": "model-00003-of-00003.safetensors",
616
+ "enc_to_dec_proj.weight": "model-00003-of-00003.safetensors",
617
+ "text_encoder.encoder.block.0.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
618
+ "text_encoder.encoder.block.0.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
619
+ "text_encoder.encoder.block.0.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
620
+ "text_encoder.encoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "model-00001-of-00003.safetensors",
621
+ "text_encoder.encoder.block.0.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
622
+ "text_encoder.encoder.block.0.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
623
+ "text_encoder.encoder.block.0.layer.1.DenseReluDense.wi.weight": "model-00001-of-00003.safetensors",
624
+ "text_encoder.encoder.block.0.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
625
+ "text_encoder.encoder.block.0.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
626
+ "text_encoder.encoder.block.1.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
627
+ "text_encoder.encoder.block.1.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
628
+ "text_encoder.encoder.block.1.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
629
+ "text_encoder.encoder.block.1.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
630
+ "text_encoder.encoder.block.1.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
631
+ "text_encoder.encoder.block.1.layer.1.DenseReluDense.wi.weight": "model-00001-of-00003.safetensors",
632
+ "text_encoder.encoder.block.1.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
633
+ "text_encoder.encoder.block.1.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
634
+ "text_encoder.encoder.block.10.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
635
+ "text_encoder.encoder.block.10.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
636
+ "text_encoder.encoder.block.10.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
637
+ "text_encoder.encoder.block.10.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
638
+ "text_encoder.encoder.block.10.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
639
+ "text_encoder.encoder.block.10.layer.1.DenseReluDense.wi.weight": "model-00001-of-00003.safetensors",
640
+ "text_encoder.encoder.block.10.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
641
+ "text_encoder.encoder.block.10.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
642
+ "text_encoder.encoder.block.11.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
643
+ "text_encoder.encoder.block.11.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
644
+ "text_encoder.encoder.block.11.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
645
+ "text_encoder.encoder.block.11.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
646
+ "text_encoder.encoder.block.11.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
647
+ "text_encoder.encoder.block.11.layer.1.DenseReluDense.wi.weight": "model-00001-of-00003.safetensors",
648
+ "text_encoder.encoder.block.11.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
649
+ "text_encoder.encoder.block.11.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
650
+ "text_encoder.encoder.block.2.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
651
+ "text_encoder.encoder.block.2.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
652
+ "text_encoder.encoder.block.2.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
653
+ "text_encoder.encoder.block.2.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
654
+ "text_encoder.encoder.block.2.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
655
+ "text_encoder.encoder.block.2.layer.1.DenseReluDense.wi.weight": "model-00001-of-00003.safetensors",
656
+ "text_encoder.encoder.block.2.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
657
+ "text_encoder.encoder.block.2.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
658
+ "text_encoder.encoder.block.3.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
659
+ "text_encoder.encoder.block.3.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
660
+ "text_encoder.encoder.block.3.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
661
+ "text_encoder.encoder.block.3.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
662
+ "text_encoder.encoder.block.3.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
663
+ "text_encoder.encoder.block.3.layer.1.DenseReluDense.wi.weight": "model-00001-of-00003.safetensors",
664
+ "text_encoder.encoder.block.3.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
665
+ "text_encoder.encoder.block.3.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
666
+ "text_encoder.encoder.block.4.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
667
+ "text_encoder.encoder.block.4.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
668
+ "text_encoder.encoder.block.4.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
669
+ "text_encoder.encoder.block.4.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
670
+ "text_encoder.encoder.block.4.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
671
+ "text_encoder.encoder.block.4.layer.1.DenseReluDense.wi.weight": "model-00001-of-00003.safetensors",
672
+ "text_encoder.encoder.block.4.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
673
+ "text_encoder.encoder.block.4.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
674
+ "text_encoder.encoder.block.5.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
675
+ "text_encoder.encoder.block.5.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
676
+ "text_encoder.encoder.block.5.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
677
+ "text_encoder.encoder.block.5.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
678
+ "text_encoder.encoder.block.5.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
679
+ "text_encoder.encoder.block.5.layer.1.DenseReluDense.wi.weight": "model-00001-of-00003.safetensors",
680
+ "text_encoder.encoder.block.5.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
681
+ "text_encoder.encoder.block.5.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
682
+ "text_encoder.encoder.block.6.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
683
+ "text_encoder.encoder.block.6.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
684
+ "text_encoder.encoder.block.6.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
685
+ "text_encoder.encoder.block.6.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
686
+ "text_encoder.encoder.block.6.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
687
+ "text_encoder.encoder.block.6.layer.1.DenseReluDense.wi.weight": "model-00001-of-00003.safetensors",
688
+ "text_encoder.encoder.block.6.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
689
+ "text_encoder.encoder.block.6.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
690
+ "text_encoder.encoder.block.7.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
691
+ "text_encoder.encoder.block.7.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
692
+ "text_encoder.encoder.block.7.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
693
+ "text_encoder.encoder.block.7.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
694
+ "text_encoder.encoder.block.7.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
695
+ "text_encoder.encoder.block.7.layer.1.DenseReluDense.wi.weight": "model-00001-of-00003.safetensors",
696
+ "text_encoder.encoder.block.7.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
697
+ "text_encoder.encoder.block.7.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
698
+ "text_encoder.encoder.block.8.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
699
+ "text_encoder.encoder.block.8.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
700
+ "text_encoder.encoder.block.8.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
701
+ "text_encoder.encoder.block.8.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
702
+ "text_encoder.encoder.block.8.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
703
+ "text_encoder.encoder.block.8.layer.1.DenseReluDense.wi.weight": "model-00001-of-00003.safetensors",
704
+ "text_encoder.encoder.block.8.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
705
+ "text_encoder.encoder.block.8.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
706
+ "text_encoder.encoder.block.9.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
707
+ "text_encoder.encoder.block.9.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
708
+ "text_encoder.encoder.block.9.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
709
+ "text_encoder.encoder.block.9.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
710
+ "text_encoder.encoder.block.9.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
711
+ "text_encoder.encoder.block.9.layer.1.DenseReluDense.wi.weight": "model-00001-of-00003.safetensors",
712
+ "text_encoder.encoder.block.9.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
713
+ "text_encoder.encoder.block.9.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
714
+ "text_encoder.encoder.final_layer_norm.weight": "model-00001-of-00003.safetensors",
715
+ "text_encoder.shared.weight": "model-00001-of-00003.safetensors"
716
+ }
717
+ }