RuaYiii patrickvonplaten commited on
Commit
160ccb2
0 Parent(s):

Duplicate from facebook/musicgen-large

Browse files

Co-authored-by: Patrick von Platen <patrickvonplaten@users.noreply.huggingface.co>

.gitattributes ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ *.7z filter=lfs diff=lfs merge=lfs -text
2
+ *.arrow filter=lfs diff=lfs merge=lfs -text
3
+ *.bin filter=lfs diff=lfs merge=lfs -text
4
+ *.bz2 filter=lfs diff=lfs merge=lfs -text
5
+ *.ckpt filter=lfs diff=lfs merge=lfs -text
6
+ *.ftz filter=lfs diff=lfs merge=lfs -text
7
+ *.gz filter=lfs diff=lfs merge=lfs -text
8
+ *.h5 filter=lfs diff=lfs merge=lfs -text
9
+ *.joblib filter=lfs diff=lfs merge=lfs -text
10
+ *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
+ *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
+ *.model filter=lfs diff=lfs merge=lfs -text
13
+ *.msgpack filter=lfs diff=lfs merge=lfs -text
14
+ *.npy filter=lfs diff=lfs merge=lfs -text
15
+ *.npz filter=lfs diff=lfs merge=lfs -text
16
+ *.onnx filter=lfs diff=lfs merge=lfs -text
17
+ *.ot filter=lfs diff=lfs merge=lfs -text
18
+ *.parquet filter=lfs diff=lfs merge=lfs -text
19
+ *.pb filter=lfs diff=lfs merge=lfs -text
20
+ *.pickle filter=lfs diff=lfs merge=lfs -text
21
+ *.pkl filter=lfs diff=lfs merge=lfs -text
22
+ *.pt filter=lfs diff=lfs merge=lfs -text
23
+ *.pth filter=lfs diff=lfs merge=lfs -text
24
+ *.rar filter=lfs diff=lfs merge=lfs -text
25
+ *.safetensors filter=lfs diff=lfs merge=lfs -text
26
+ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
+ *.tar.* filter=lfs diff=lfs merge=lfs -text
28
+ *.tflite filter=lfs diff=lfs merge=lfs -text
29
+ *.tgz filter=lfs diff=lfs merge=lfs -text
30
+ *.wasm filter=lfs diff=lfs merge=lfs -text
31
+ *.xz filter=lfs diff=lfs merge=lfs -text
32
+ *.zip filter=lfs diff=lfs merge=lfs -text
33
+ *.zst filter=lfs diff=lfs merge=lfs -text
34
+ *tfevents* filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,221 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ inference: false
3
+ tags:
4
+ - musicgen
5
+ license: cc-by-nc-4.0
6
+ duplicated_from: facebook/musicgen-large
7
+ ---
8
+
9
+ # MusicGen - Large - 3.3B
10
+
11
+ MusicGen is a text-to-music model capable of genreating high-quality music samples conditioned on text descriptions or audio prompts.
12
+ It is a single stage auto-regressive Transformer model trained over a 32kHz EnCodec tokenizer with 4 codebooks sampled at 50 Hz.
13
+ Unlike existing methods, like MusicLM, MusicGen doesn't require a self-supervised semantic representation, and it generates all 4 codebooks in one pass.
14
+ By introducing a small delay between the codebooks, we show we can predict them in parallel, thus having only 50 auto-regressive steps per second of audio.
15
+
16
+ MusicGen was published in [Simple and Controllable Music Generation](https://arxiv.org/abs/2306.05284) by *Jade Copet, Felix Kreuk, Itai Gat, Tal Remez, David Kant, Gabriel Synnaeve, Yossi Adi, Alexandre Défossez*.
17
+
18
+ Four checkpoints are released:
19
+ - [small](https://huggingface.co/facebook/musicgen-small)
20
+ - [medium](https://huggingface.co/facebook/musicgen-medium)
21
+ - [**large** (this checkpoint)](https://huggingface.co/facebook/musicgen-large)
22
+ - [melody](https://huggingface.co/facebook/musicgen-melody)
23
+
24
+ ## Example
25
+
26
+ Try out MusicGen yourself!
27
+
28
+ * Audiocraft Colab:
29
+
30
+ <a target="_blank" href="https://colab.research.google.com/drive/1fxGqfg96RBUvGxZ1XXN07s3DthrKUl4-?usp=sharing">
31
+ <img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/>
32
+ </a>
33
+
34
+ * Hugging Face Colab:
35
+
36
+ <a target="_blank" href="https://colab.research.google.com/github/sanchit-gandhi/notebooks/blob/main/MusicGen.ipynb">
37
+ <img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/>
38
+ </a>
39
+
40
+ * Hugging Face Demo:
41
+
42
+ <a target="_blank" href="https://huggingface.co/spaces/facebook/MusicGen">
43
+ <img src="https://huggingface.co/datasets/huggingface/badges/raw/main/open-in-hf-spaces-sm.svg" alt="Open in HuggingFace"/>
44
+ </a>
45
+
46
+ ## 🤗 Transformers Usage
47
+
48
+ You can run MusicGen locally with the 🤗 Transformers library from version 4.31.0 onwards.
49
+
50
+ 1. First install the 🤗 [Transformers library](https://github.com/huggingface/transformers) from main:
51
+
52
+ ```
53
+ pip install git+https://github.com/huggingface/transformers.git
54
+ ```
55
+
56
+ 2. Run the following Python code to generate text-conditional audio samples:
57
+
58
+ ```py
59
+ from transformers import AutoProcessor, MusicgenForConditionalGeneration
60
+
61
+
62
+ processor = AutoProcessor.from_pretrained("facebook/musicgen-large")
63
+ model = MusicgenForConditionalGeneration.from_pretrained("facebook/musicgen-large")
64
+
65
+ inputs = processor(
66
+ text=["80s pop track with bassy drums and synth", "90s rock song with loud guitars and heavy drums"],
67
+ padding=True,
68
+ return_tensors="pt",
69
+ )
70
+
71
+ audio_values = model.generate(**inputs, max_new_tokens=256)
72
+ ```
73
+
74
+ 3. Listen to the audio samples either in an ipynb notebook:
75
+
76
+ ```py
77
+ from IPython.display import Audio
78
+
79
+ sampling_rate = model.config.audio_encoder.sampling_rate
80
+ Audio(audio_values[0].numpy(), rate=sampling_rate)
81
+ ```
82
+
83
+ Or save them as a `.wav` file using a third-party library, e.g. `scipy`:
84
+
85
+ ```py
86
+ import scipy
87
+
88
+ sampling_rate = model.config.audio_encoder.sampling_rate
89
+ scipy.io.wavfile.write("musicgen_out.wav", rate=sampling_rate, data=audio_values[0, 0].numpy())
90
+ ```
91
+
92
+ For more details on using the MusicGen model for inference using the 🤗 Transformers library, refer to the [MusicGen docs](https://huggingface.co/docs/transformers/model_doc/musicgen).
93
+
94
+ ## Audiocraft Usage
95
+
96
+ You can also run MusicGen locally through the original [Audiocraft library]((https://github.com/facebookresearch/audiocraft):
97
+
98
+ 1. First install the [`audiocraft` library](https://github.com/facebookresearch/audiocraft)
99
+ ```
100
+ pip install git+https://github.com/facebookresearch/audiocraft.git
101
+ ```
102
+
103
+ 2. Make sure to have [`ffmpeg`](https://ffmpeg.org/download.html) installed:
104
+ ```
105
+ apt get install ffmpeg
106
+ ```
107
+
108
+ 3. Run the following Python code:
109
+
110
+ ```py
111
+ from audiocraft.models import MusicGen
112
+ from audiocraft.data.audio import audio_write
113
+
114
+ model = MusicGen.get_pretrained("large")
115
+ model.set_generation_params(duration=8) # generate 8 seconds.
116
+
117
+ descriptions = ["happy rock", "energetic EDM"]
118
+
119
+ wav = model.generate(descriptions) # generates 2 samples.
120
+
121
+ for idx, one_wav in enumerate(wav):
122
+ # Will save under {idx}.wav, with loudness normalization at -14 db LUFS.
123
+ audio_write(f'{idx}', one_wav.cpu(), model.sample_rate, strategy="loudness")
124
+ ```
125
+
126
+ ## Model details
127
+
128
+ **Organization developing the model:** The FAIR team of Meta AI.
129
+
130
+ **Model date:** MusicGen was trained between April 2023 and May 2023.
131
+
132
+ **Model version:** This is the version 1 of the model.
133
+
134
+ **Model type:** MusicGen consists of an EnCodec model for audio tokenization, an auto-regressive language model based on the transformer architecture for music modeling. The model comes in different sizes: 300M, 1.5B and 3.3B parameters ; and two variants: a model trained for text-to-music generation task and a model trained for melody-guided music generation.
135
+
136
+ **Paper or resources for more information:** More information can be found in the paper [Simple and Controllable Music Generation](https://arxiv.org/abs/2306.05284).
137
+
138
+ **Citation details:**
139
+ ```
140
+ @misc{copet2023simple,
141
+ title={Simple and Controllable Music Generation},
142
+ author={Jade Copet and Felix Kreuk and Itai Gat and Tal Remez and David Kant and Gabriel Synnaeve and Yossi Adi and Alexandre Défossez},
143
+ year={2023},
144
+ eprint={2306.05284},
145
+ archivePrefix={arXiv},
146
+ primaryClass={cs.SD}
147
+ }
148
+ ```
149
+
150
+ **License:** Code is released under MIT, model weights are released under CC-BY-NC 4.0.
151
+
152
+ **Where to send questions or comments about the model:** Questions and comments about MusicGen can be sent via the [Github repository](https://github.com/facebookresearch/audiocraft) of the project, or by opening an issue.
153
+
154
+ ## Intended use
155
+ **Primary intended use:** The primary use of MusicGen is research on AI-based music generation, including:
156
+
157
+ - Research efforts, such as probing and better understanding the limitations of generative models to further improve the state of science
158
+ - Generation of music guided by text or melody to understand current abilities of generative AI models by machine learning amateurs
159
+
160
+ **Primary intended users:** The primary intended users of the model are researchers in audio, machine learning and artificial intelligence, as well as amateur seeking to better understand those models.
161
+
162
+ **Out-of-scope use cases:** The model should not be used on downstream applications without further risk evaluation and mitigation. The model should not be used to intentionally create or disseminate music pieces that create hostile or alienating environments for people. This includes generating music that people would foreseeably find disturbing, distressing, or offensive; or content that propagates historical or current stereotypes.
163
+
164
+ ## Metrics
165
+
166
+ **Models performance measures:** We used the following objective measure to evaluate the model on a standard music benchmark:
167
+
168
+ - Frechet Audio Distance computed on features extracted from a pre-trained audio classifier (VGGish)
169
+ - Kullback-Leibler Divergence on label distributions extracted from a pre-trained audio classifier (PaSST)
170
+ - CLAP Score between audio embedding and text embedding extracted from a pre-trained CLAP model
171
+
172
+ Additionally, we run qualitative studies with human participants, evaluating the performance of the model with the following axes:
173
+
174
+ - Overall quality of the music samples;
175
+ - Text relevance to the provided text input;
176
+ - Adherence to the melody for melody-guided music generation.
177
+
178
+ More details on performance measures and human studies can be found in the paper.
179
+
180
+ **Decision thresholds:** Not applicable.
181
+
182
+ ## Evaluation datasets
183
+
184
+ The model was evaluated on the [MusicCaps benchmark](https://www.kaggle.com/datasets/googleai/musiccaps) and on an in-domain held-out evaluation set, with no artist overlap with the training set.
185
+
186
+ ## Training datasets
187
+
188
+ The model was trained on licensed data using the following sources: the [Meta Music Initiative Sound Collection](https://www.fb.com/sound), [Shutterstock music collection](https://www.shutterstock.com/music) and the [Pond5 music collection](https://www.pond5.com/). See the paper for more details about the training set and corresponding preprocessing.
189
+
190
+ ## Evaluation results
191
+
192
+ Below are the objective metrics obtained on MusicCaps with the released model. Note that for the publicly released models, we had all the datasets go through a state-of-the-art music source separation method, namely using the open source [Hybrid Transformer for Music Source Separation](https://github.com/facebookresearch/demucs) (HT-Demucs), in order to keep only the instrumental part. This explains the difference in objective metrics with the models used in the paper.
193
+
194
+ | Model | Frechet Audio Distance | KLD | Text Consistency | Chroma Cosine Similarity |
195
+ |---|---|---|---|---|
196
+ | facebook/musicgen-small | 4.88 | 1.42 | 0.27 | - |
197
+ | facebook/musicgen-medium | 5.14 | 1.38 | 0.28 | - |
198
+ | **facebook/musicgen-large** | 5.48 | 1.37 | 0.28 | - |
199
+ | facebook/musicgen-melody | 4.93 | 1.41 | 0.27 | 0.44 |
200
+
201
+ More information can be found in the paper [Simple and Controllable Music Generation](https://arxiv.org/abs/2306.05284), in the Results section.
202
+
203
+ ## Limitations and biases
204
+
205
+ **Data:** The data sources used to train the model are created by music professionals and covered by legal agreements with the right holders. The model is trained on 20K hours of data, we believe that scaling the model on larger datasets can further improve the performance of the model.
206
+
207
+ **Mitigations:** Vocals have been removed from the data source using corresponding tags, and then using a state-of-the-art music source separation method, namely using the open source [Hybrid Transformer for Music Source Separation](https://github.com/facebookresearch/demucs) (HT-Demucs).
208
+
209
+ **Limitations:**
210
+
211
+ - The model is not able to generate realistic vocals.
212
+ - The model has been trained with English descriptions and will not perform as well in other languages.
213
+ - The model does not perform equally well for all music styles and cultures.
214
+ - The model sometimes generates end of songs, collapsing to silence.
215
+ - It is sometimes difficult to assess what types of text descriptions provide the best generations. Prompt engineering may be required to obtain satisfying results.
216
+
217
+ **Biases:** The source of data is potentially lacking diversity and all music cultures are not equally represented in the dataset. The model may not perform equally well on the wide variety of music genres that exists. The generated samples from the model will reflect the biases from the training data. Further work on this model should include methods for balanced and just representations of cultures, for example, by scaling the training data to be both diverse and inclusive.
218
+
219
+ **Risks and harms:** Biases and limitations of the model may lead to generation of samples that may be considered as biased, inappropriate or offensive. We believe that providing the code to reproduce the research and train new models will allow to broaden the application to new and more representative data.
220
+
221
+ **Use cases:** Users must be aware of the biases, limitations and risks of the model. MusicGen is a model developed for artificial intelligence research on controllable music generation. As such, it should not be used for downstream applications without further investigation and mitigation of risks.
compression_state_dict.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37d256b525d4117f8bbf790ab448a8e9f4746cd401900fe1ae72e154b1513a30
3
+ size 236001935
config.json ADDED
@@ -0,0 +1,298 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_commit_hash": null,
3
+ "architectures": [
4
+ "MusicgenForConditionalGeneration"
5
+ ],
6
+ "audio_encoder": {
7
+ "_name_or_path": "facebook/encodec_32khz",
8
+ "add_cross_attention": false,
9
+ "architectures": [
10
+ "EncodecModel"
11
+ ],
12
+ "audio_channels": 1,
13
+ "bad_words_ids": null,
14
+ "begin_suppress_tokens": null,
15
+ "bos_token_id": null,
16
+ "chunk_length_s": null,
17
+ "chunk_size_feed_forward": 0,
18
+ "codebook_dim": 128,
19
+ "codebook_size": 2048,
20
+ "compress": 2,
21
+ "cross_attention_hidden_size": null,
22
+ "decoder_start_token_id": null,
23
+ "dilation_growth_rate": 2,
24
+ "diversity_penalty": 0.0,
25
+ "do_sample": false,
26
+ "early_stopping": false,
27
+ "encoder_no_repeat_ngram_size": 0,
28
+ "eos_token_id": null,
29
+ "exponential_decay_length_penalty": null,
30
+ "finetuning_task": null,
31
+ "forced_bos_token_id": null,
32
+ "forced_eos_token_id": null,
33
+ "hidden_size": 128,
34
+ "id2label": {
35
+ "0": "LABEL_0",
36
+ "1": "LABEL_1"
37
+ },
38
+ "is_decoder": false,
39
+ "is_encoder_decoder": false,
40
+ "kernel_size": 7,
41
+ "label2id": {
42
+ "LABEL_0": 0,
43
+ "LABEL_1": 1
44
+ },
45
+ "last_kernel_size": 7,
46
+ "length_penalty": 1.0,
47
+ "max_length": 20,
48
+ "min_length": 0,
49
+ "model_type": "encodec",
50
+ "no_repeat_ngram_size": 0,
51
+ "norm_type": "weight_norm",
52
+ "normalize": false,
53
+ "num_beam_groups": 1,
54
+ "num_beams": 1,
55
+ "num_filters": 64,
56
+ "num_lstm_layers": 2,
57
+ "num_residual_layers": 1,
58
+ "num_return_sequences": 1,
59
+ "output_attentions": false,
60
+ "output_hidden_states": false,
61
+ "output_scores": false,
62
+ "overlap": null,
63
+ "pad_mode": "reflect",
64
+ "pad_token_id": null,
65
+ "prefix": null,
66
+ "problem_type": null,
67
+ "pruned_heads": {},
68
+ "remove_invalid_values": false,
69
+ "repetition_penalty": 1.0,
70
+ "residual_kernel_size": 3,
71
+ "return_dict": true,
72
+ "return_dict_in_generate": false,
73
+ "sampling_rate": 32000,
74
+ "sep_token_id": null,
75
+ "suppress_tokens": null,
76
+ "target_bandwidths": [
77
+ 2.2
78
+ ],
79
+ "task_specific_params": null,
80
+ "temperature": 1.0,
81
+ "tf_legacy_loss": false,
82
+ "tie_encoder_decoder": false,
83
+ "tie_word_embeddings": true,
84
+ "tokenizer_class": null,
85
+ "top_k": 50,
86
+ "top_p": 1.0,
87
+ "torch_dtype": "float32",
88
+ "torchscript": false,
89
+ "transformers_version": "4.31.0.dev0",
90
+ "trim_right_ratio": 1.0,
91
+ "typical_p": 1.0,
92
+ "upsampling_ratios": [
93
+ 8,
94
+ 5,
95
+ 4,
96
+ 4
97
+ ],
98
+ "use_bfloat16": false,
99
+ "use_causal_conv": false,
100
+ "use_conv_shortcut": false
101
+ },
102
+ "decoder": {
103
+ "_name_or_path": "",
104
+ "activation_dropout": 0.0,
105
+ "activation_function": "gelu",
106
+ "add_cross_attention": false,
107
+ "architectures": null,
108
+ "attention_dropout": 0.0,
109
+ "bad_words_ids": null,
110
+ "begin_suppress_tokens": null,
111
+ "bos_token_id": 2048,
112
+ "chunk_size_feed_forward": 0,
113
+ "classifier_dropout": 0.0,
114
+ "cross_attention_hidden_size": null,
115
+ "decoder_start_token_id": null,
116
+ "diversity_penalty": 0.0,
117
+ "do_sample": false,
118
+ "dropout": 0.1,
119
+ "early_stopping": false,
120
+ "encoder_no_repeat_ngram_size": 0,
121
+ "eos_token_id": null,
122
+ "exponential_decay_length_penalty": null,
123
+ "ffn_dim": 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_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
+ "transformers_version": "4.31.0.dev0",
177
+ "typical_p": 1.0,
178
+ "use_bfloat16": false,
179
+ "use_cache": true,
180
+ "vocab_size": 2048
181
+ },
182
+ "is_encoder_decoder": true,
183
+ "model_type": "musicgen",
184
+ "text_encoder": {
185
+ "_name_or_path": "t5-base",
186
+ "add_cross_attention": false,
187
+ "architectures": [
188
+ "T5ForConditionalGeneration"
189
+ ],
190
+ "bad_words_ids": null,
191
+ "begin_suppress_tokens": null,
192
+ "bos_token_id": null,
193
+ "chunk_size_feed_forward": 0,
194
+ "cross_attention_hidden_size": null,
195
+ "d_ff": 3072,
196
+ "d_kv": 64,
197
+ "d_model": 768,
198
+ "decoder_start_token_id": 0,
199
+ "dense_act_fn": "relu",
200
+ "diversity_penalty": 0.0,
201
+ "do_sample": false,
202
+ "dropout_rate": 0.1,
203
+ "early_stopping": false,
204
+ "encoder_no_repeat_ngram_size": 0,
205
+ "eos_token_id": 1,
206
+ "exponential_decay_length_penalty": null,
207
+ "feed_forward_proj": "relu",
208
+ "finetuning_task": null,
209
+ "forced_bos_token_id": null,
210
+ "forced_eos_token_id": null,
211
+ "id2label": {
212
+ "0": "LABEL_0",
213
+ "1": "LABEL_1"
214
+ },
215
+ "initializer_factor": 1.0,
216
+ "is_decoder": false,
217
+ "is_encoder_decoder": true,
218
+ "is_gated_act": false,
219
+ "label2id": {
220
+ "LABEL_0": 0,
221
+ "LABEL_1": 1
222
+ },
223
+ "layer_norm_epsilon": 1e-06,
224
+ "length_penalty": 1.0,
225
+ "max_length": 20,
226
+ "min_length": 0,
227
+ "model_type": "t5",
228
+ "n_positions": 512,
229
+ "no_repeat_ngram_size": 0,
230
+ "num_beam_groups": 1,
231
+ "num_beams": 1,
232
+ "num_decoder_layers": 12,
233
+ "num_heads": 12,
234
+ "num_layers": 12,
235
+ "num_return_sequences": 1,
236
+ "output_attentions": false,
237
+ "output_hidden_states": false,
238
+ "output_past": true,
239
+ "output_scores": false,
240
+ "pad_token_id": 0,
241
+ "prefix": null,
242
+ "problem_type": null,
243
+ "pruned_heads": {},
244
+ "relative_attention_max_distance": 128,
245
+ "relative_attention_num_buckets": 32,
246
+ "remove_invalid_values": false,
247
+ "repetition_penalty": 1.0,
248
+ "return_dict": true,
249
+ "return_dict_in_generate": false,
250
+ "sep_token_id": null,
251
+ "suppress_tokens": null,
252
+ "task_specific_params": {
253
+ "summarization": {
254
+ "early_stopping": true,
255
+ "length_penalty": 2.0,
256
+ "max_length": 200,
257
+ "min_length": 30,
258
+ "no_repeat_ngram_size": 3,
259
+ "num_beams": 4,
260
+ "prefix": "summarize: "
261
+ },
262
+ "translation_en_to_de": {
263
+ "early_stopping": true,
264
+ "max_length": 300,
265
+ "num_beams": 4,
266
+ "prefix": "translate English to German: "
267
+ },
268
+ "translation_en_to_fr": {
269
+ "early_stopping": true,
270
+ "max_length": 300,
271
+ "num_beams": 4,
272
+ "prefix": "translate English to French: "
273
+ },
274
+ "translation_en_to_ro": {
275
+ "early_stopping": true,
276
+ "max_length": 300,
277
+ "num_beams": 4,
278
+ "prefix": "translate English to Romanian: "
279
+ }
280
+ },
281
+ "temperature": 1.0,
282
+ "tf_legacy_loss": false,
283
+ "tie_encoder_decoder": false,
284
+ "tie_word_embeddings": true,
285
+ "tokenizer_class": null,
286
+ "top_k": 50,
287
+ "top_p": 1.0,
288
+ "torch_dtype": null,
289
+ "torchscript": false,
290
+ "transformers_version": "4.31.0.dev0",
291
+ "typical_p": 1.0,
292
+ "use_bfloat16": false,
293
+ "use_cache": true,
294
+ "vocab_size": 32128
295
+ },
296
+ "torch_dtype": "float32",
297
+ "transformers_version": null
298
+ }
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": "4.31.0.dev0"
10
+ }
preprocessor_config.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "chunk_length_s": null,
3
+ "feature_extractor_type": "EncodecFeatureExtractor",
4
+ "feature_size": 1,
5
+ "overlap": null,
6
+ "padding_side": "left",
7
+ "padding_value": 0.0,
8
+ "processor_class": "MusicgenProcessor",
9
+ "return_attention_mask": true,
10
+ "sampling_rate": 32000
11
+ }
pytorch_model-00001-of-00002.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7ed8a0d95eff206263d1ae62955a7b8a7dab11a6b55e953887aea6ed54f85bd
3
+ size 9987827539
pytorch_model-00002-of-00002.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9923d2947297a9883404abfd4041a32cf486c763d36e00eb4f178823bf6bdac
3
+ size 3731608779
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,1004 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 13719079192
4
+ },
5
+ "weight_map": {
6
+ "audio_encoder.decoder.layers.0.conv.bias": "pytorch_model-00001-of-00002.bin",
7
+ "audio_encoder.decoder.layers.0.conv.weight_g": "pytorch_model-00001-of-00002.bin",
8
+ "audio_encoder.decoder.layers.0.conv.weight_v": "pytorch_model-00001-of-00002.bin",
9
+ "audio_encoder.decoder.layers.1.lstm.bias_hh_l0": "pytorch_model-00001-of-00002.bin",
10
+ "audio_encoder.decoder.layers.1.lstm.bias_hh_l1": "pytorch_model-00001-of-00002.bin",
11
+ "audio_encoder.decoder.layers.1.lstm.bias_ih_l0": "pytorch_model-00001-of-00002.bin",
12
+ "audio_encoder.decoder.layers.1.lstm.bias_ih_l1": "pytorch_model-00001-of-00002.bin",
13
+ "audio_encoder.decoder.layers.1.lstm.weight_hh_l0": "pytorch_model-00001-of-00002.bin",
14
+ "audio_encoder.decoder.layers.1.lstm.weight_hh_l1": "pytorch_model-00001-of-00002.bin",
15
+ "audio_encoder.decoder.layers.1.lstm.weight_ih_l0": "pytorch_model-00001-of-00002.bin",
16
+ "audio_encoder.decoder.layers.1.lstm.weight_ih_l1": "pytorch_model-00001-of-00002.bin",
17
+ "audio_encoder.decoder.layers.10.block.1.conv.bias": "pytorch_model-00001-of-00002.bin",
18
+ "audio_encoder.decoder.layers.10.block.1.conv.weight_g": "pytorch_model-00001-of-00002.bin",
19
+ "audio_encoder.decoder.layers.10.block.1.conv.weight_v": "pytorch_model-00001-of-00002.bin",
20
+ "audio_encoder.decoder.layers.10.block.3.conv.bias": "pytorch_model-00001-of-00002.bin",
21
+ "audio_encoder.decoder.layers.10.block.3.conv.weight_g": "pytorch_model-00001-of-00002.bin",
22
+ "audio_encoder.decoder.layers.10.block.3.conv.weight_v": "pytorch_model-00001-of-00002.bin",
23
+ "audio_encoder.decoder.layers.12.conv.bias": "pytorch_model-00001-of-00002.bin",
24
+ "audio_encoder.decoder.layers.12.conv.weight_g": "pytorch_model-00001-of-00002.bin",
25
+ "audio_encoder.decoder.layers.12.conv.weight_v": "pytorch_model-00001-of-00002.bin",
26
+ "audio_encoder.decoder.layers.13.block.1.conv.bias": "pytorch_model-00001-of-00002.bin",
27
+ "audio_encoder.decoder.layers.13.block.1.conv.weight_g": "pytorch_model-00001-of-00002.bin",
28
+ "audio_encoder.decoder.layers.13.block.1.conv.weight_v": "pytorch_model-00001-of-00002.bin",
29
+ "audio_encoder.decoder.layers.13.block.3.conv.bias": "pytorch_model-00001-of-00002.bin",
30
+ "audio_encoder.decoder.layers.13.block.3.conv.weight_g": "pytorch_model-00001-of-00002.bin",
31
+ "audio_encoder.decoder.layers.13.block.3.conv.weight_v": "pytorch_model-00001-of-00002.bin",
32
+ "audio_encoder.decoder.layers.15.conv.bias": "pytorch_model-00001-of-00002.bin",
33
+ "audio_encoder.decoder.layers.15.conv.weight_g": "pytorch_model-00001-of-00002.bin",
34
+ "audio_encoder.decoder.layers.15.conv.weight_v": "pytorch_model-00001-of-00002.bin",
35
+ "audio_encoder.decoder.layers.3.conv.bias": "pytorch_model-00001-of-00002.bin",
36
+ "audio_encoder.decoder.layers.3.conv.weight_g": "pytorch_model-00001-of-00002.bin",
37
+ "audio_encoder.decoder.layers.3.conv.weight_v": "pytorch_model-00001-of-00002.bin",
38
+ "audio_encoder.decoder.layers.4.block.1.conv.bias": "pytorch_model-00001-of-00002.bin",
39
+ "audio_encoder.decoder.layers.4.block.1.conv.weight_g": "pytorch_model-00001-of-00002.bin",
40
+ "audio_encoder.decoder.layers.4.block.1.conv.weight_v": "pytorch_model-00001-of-00002.bin",
41
+ "audio_encoder.decoder.layers.4.block.3.conv.bias": "pytorch_model-00001-of-00002.bin",
42
+ "audio_encoder.decoder.layers.4.block.3.conv.weight_g": "pytorch_model-00001-of-00002.bin",
43
+ "audio_encoder.decoder.layers.4.block.3.conv.weight_v": "pytorch_model-00001-of-00002.bin",
44
+ "audio_encoder.decoder.layers.6.conv.bias": "pytorch_model-00001-of-00002.bin",
45
+ "audio_encoder.decoder.layers.6.conv.weight_g": "pytorch_model-00001-of-00002.bin",
46
+ "audio_encoder.decoder.layers.6.conv.weight_v": "pytorch_model-00001-of-00002.bin",
47
+ "audio_encoder.decoder.layers.7.block.1.conv.bias": "pytorch_model-00001-of-00002.bin",
48
+ "audio_encoder.decoder.layers.7.block.1.conv.weight_g": "pytorch_model-00001-of-00002.bin",
49
+ "audio_encoder.decoder.layers.7.block.1.conv.weight_v": "pytorch_model-00001-of-00002.bin",
50
+ "audio_encoder.decoder.layers.7.block.3.conv.bias": "pytorch_model-00001-of-00002.bin",
51
+ "audio_encoder.decoder.layers.7.block.3.conv.weight_g": "pytorch_model-00001-of-00002.bin",
52
+ "audio_encoder.decoder.layers.7.block.3.conv.weight_v": "pytorch_model-00001-of-00002.bin",
53
+ "audio_encoder.decoder.layers.9.conv.bias": "pytorch_model-00001-of-00002.bin",
54
+ "audio_encoder.decoder.layers.9.conv.weight_g": "pytorch_model-00001-of-00002.bin",
55
+ "audio_encoder.decoder.layers.9.conv.weight_v": "pytorch_model-00001-of-00002.bin",
56
+ "audio_encoder.encoder.layers.0.conv.bias": "pytorch_model-00001-of-00002.bin",
57
+ "audio_encoder.encoder.layers.0.conv.weight_g": "pytorch_model-00001-of-00002.bin",
58
+ "audio_encoder.encoder.layers.0.conv.weight_v": "pytorch_model-00001-of-00002.bin",
59
+ "audio_encoder.encoder.layers.1.block.1.conv.bias": "pytorch_model-00001-of-00002.bin",
60
+ "audio_encoder.encoder.layers.1.block.1.conv.weight_g": "pytorch_model-00001-of-00002.bin",
61
+ "audio_encoder.encoder.layers.1.block.1.conv.weight_v": "pytorch_model-00001-of-00002.bin",
62
+ "audio_encoder.encoder.layers.1.block.3.conv.bias": "pytorch_model-00001-of-00002.bin",
63
+ "audio_encoder.encoder.layers.1.block.3.conv.weight_g": "pytorch_model-00001-of-00002.bin",
64
+ "audio_encoder.encoder.layers.1.block.3.conv.weight_v": "pytorch_model-00001-of-00002.bin",
65
+ "audio_encoder.encoder.layers.10.block.1.conv.bias": "pytorch_model-00001-of-00002.bin",
66
+ "audio_encoder.encoder.layers.10.block.1.conv.weight_g": "pytorch_model-00001-of-00002.bin",
67
+ "audio_encoder.encoder.layers.10.block.1.conv.weight_v": "pytorch_model-00001-of-00002.bin",
68
+ "audio_encoder.encoder.layers.10.block.3.conv.bias": "pytorch_model-00001-of-00002.bin",
69
+ "audio_encoder.encoder.layers.10.block.3.conv.weight_g": "pytorch_model-00001-of-00002.bin",
70
+ "audio_encoder.encoder.layers.10.block.3.conv.weight_v": "pytorch_model-00001-of-00002.bin",
71
+ "audio_encoder.encoder.layers.12.conv.bias": "pytorch_model-00001-of-00002.bin",
72
+ "audio_encoder.encoder.layers.12.conv.weight_g": "pytorch_model-00001-of-00002.bin",
73
+ "audio_encoder.encoder.layers.12.conv.weight_v": "pytorch_model-00001-of-00002.bin",
74
+ "audio_encoder.encoder.layers.13.lstm.bias_hh_l0": "pytorch_model-00001-of-00002.bin",
75
+ "audio_encoder.encoder.layers.13.lstm.bias_hh_l1": "pytorch_model-00001-of-00002.bin",
76
+ "audio_encoder.encoder.layers.13.lstm.bias_ih_l0": "pytorch_model-00001-of-00002.bin",
77
+ "audio_encoder.encoder.layers.13.lstm.bias_ih_l1": "pytorch_model-00001-of-00002.bin",
78
+ "audio_encoder.encoder.layers.13.lstm.weight_hh_l0": "pytorch_model-00001-of-00002.bin",
79
+ "audio_encoder.encoder.layers.13.lstm.weight_hh_l1": "pytorch_model-00001-of-00002.bin",
80
+ "audio_encoder.encoder.layers.13.lstm.weight_ih_l0": "pytorch_model-00001-of-00002.bin",
81
+ "audio_encoder.encoder.layers.13.lstm.weight_ih_l1": "pytorch_model-00001-of-00002.bin",
82
+ "audio_encoder.encoder.layers.15.conv.bias": "pytorch_model-00001-of-00002.bin",
83
+ "audio_encoder.encoder.layers.15.conv.weight_g": "pytorch_model-00001-of-00002.bin",
84
+ "audio_encoder.encoder.layers.15.conv.weight_v": "pytorch_model-00001-of-00002.bin",
85
+ "audio_encoder.encoder.layers.3.conv.bias": "pytorch_model-00001-of-00002.bin",
86
+ "audio_encoder.encoder.layers.3.conv.weight_g": "pytorch_model-00001-of-00002.bin",
87
+ "audio_encoder.encoder.layers.3.conv.weight_v": "pytorch_model-00001-of-00002.bin",
88
+ "audio_encoder.encoder.layers.4.block.1.conv.bias": "pytorch_model-00001-of-00002.bin",
89
+ "audio_encoder.encoder.layers.4.block.1.conv.weight_g": "pytorch_model-00001-of-00002.bin",
90
+ "audio_encoder.encoder.layers.4.block.1.conv.weight_v": "pytorch_model-00001-of-00002.bin",
91
+ "audio_encoder.encoder.layers.4.block.3.conv.bias": "pytorch_model-00001-of-00002.bin",
92
+ "audio_encoder.encoder.layers.4.block.3.conv.weight_g": "pytorch_model-00001-of-00002.bin",
93
+ "audio_encoder.encoder.layers.4.block.3.conv.weight_v": "pytorch_model-00001-of-00002.bin",
94
+ "audio_encoder.encoder.layers.6.conv.bias": "pytorch_model-00001-of-00002.bin",
95
+ "audio_encoder.encoder.layers.6.conv.weight_g": "pytorch_model-00001-of-00002.bin",
96
+ "audio_encoder.encoder.layers.6.conv.weight_v": "pytorch_model-00001-of-00002.bin",
97
+ "audio_encoder.encoder.layers.7.block.1.conv.bias": "pytorch_model-00001-of-00002.bin",
98
+ "audio_encoder.encoder.layers.7.block.1.conv.weight_g": "pytorch_model-00001-of-00002.bin",
99
+ "audio_encoder.encoder.layers.7.block.1.conv.weight_v": "pytorch_model-00001-of-00002.bin",
100
+ "audio_encoder.encoder.layers.7.block.3.conv.bias": "pytorch_model-00001-of-00002.bin",
101
+ "audio_encoder.encoder.layers.7.block.3.conv.weight_g": "pytorch_model-00001-of-00002.bin",
102
+ "audio_encoder.encoder.layers.7.block.3.conv.weight_v": "pytorch_model-00001-of-00002.bin",
103
+ "audio_encoder.encoder.layers.9.conv.bias": "pytorch_model-00001-of-00002.bin",
104
+ "audio_encoder.encoder.layers.9.conv.weight_g": "pytorch_model-00001-of-00002.bin",
105
+ "audio_encoder.encoder.layers.9.conv.weight_v": "pytorch_model-00001-of-00002.bin",
106
+ "audio_encoder.quantizer.layers.0.codebook.cluster_size": "pytorch_model-00001-of-00002.bin",
107
+ "audio_encoder.quantizer.layers.0.codebook.embed": "pytorch_model-00001-of-00002.bin",
108
+ "audio_encoder.quantizer.layers.0.codebook.embed_avg": "pytorch_model-00001-of-00002.bin",
109
+ "audio_encoder.quantizer.layers.0.codebook.inited": "pytorch_model-00001-of-00002.bin",
110
+ "audio_encoder.quantizer.layers.1.codebook.cluster_size": "pytorch_model-00001-of-00002.bin",
111
+ "audio_encoder.quantizer.layers.1.codebook.embed": "pytorch_model-00001-of-00002.bin",
112
+ "audio_encoder.quantizer.layers.1.codebook.embed_avg": "pytorch_model-00001-of-00002.bin",
113
+ "audio_encoder.quantizer.layers.1.codebook.inited": "pytorch_model-00001-of-00002.bin",
114
+ "audio_encoder.quantizer.layers.2.codebook.cluster_size": "pytorch_model-00001-of-00002.bin",
115
+ "audio_encoder.quantizer.layers.2.codebook.embed": "pytorch_model-00001-of-00002.bin",
116
+ "audio_encoder.quantizer.layers.2.codebook.embed_avg": "pytorch_model-00001-of-00002.bin",
117
+ "audio_encoder.quantizer.layers.2.codebook.inited": "pytorch_model-00001-of-00002.bin",
118
+ "audio_encoder.quantizer.layers.3.codebook.cluster_size": "pytorch_model-00001-of-00002.bin",
119
+ "audio_encoder.quantizer.layers.3.codebook.embed": "pytorch_model-00001-of-00002.bin",
120
+ "audio_encoder.quantizer.layers.3.codebook.embed_avg": "pytorch_model-00001-of-00002.bin",
121
+ "audio_encoder.quantizer.layers.3.codebook.inited": "pytorch_model-00001-of-00002.bin",
122
+ "decoder.lm_heads.0.weight": "pytorch_model-00002-of-00002.bin",
123
+ "decoder.lm_heads.1.weight": "pytorch_model-00002-of-00002.bin",
124
+ "decoder.lm_heads.2.weight": "pytorch_model-00002-of-00002.bin",
125
+ "decoder.lm_heads.3.weight": "pytorch_model-00002-of-00002.bin",
126
+ "decoder.model.decoder.embed_positions.weights": "pytorch_model-00001-of-00002.bin",
127
+ "decoder.model.decoder.embed_tokens.0.weight": "pytorch_model-00001-of-00002.bin",
128
+ "decoder.model.decoder.embed_tokens.1.weight": "pytorch_model-00001-of-00002.bin",
129
+ "decoder.model.decoder.embed_tokens.2.weight": "pytorch_model-00001-of-00002.bin",
130
+ "decoder.model.decoder.embed_tokens.3.weight": "pytorch_model-00001-of-00002.bin",
131
+ "decoder.model.decoder.layer_norm.bias": "pytorch_model-00002-of-00002.bin",
132
+ "decoder.model.decoder.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
133
+ "decoder.model.decoder.layers.0.encoder_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
134
+ "decoder.model.decoder.layers.0.encoder_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
135
+ "decoder.model.decoder.layers.0.encoder_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
136
+ "decoder.model.decoder.layers.0.encoder_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
137
+ "decoder.model.decoder.layers.0.encoder_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
138
+ "decoder.model.decoder.layers.0.encoder_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
139
+ "decoder.model.decoder.layers.0.fc1.weight": "pytorch_model-00001-of-00002.bin",
140
+ "decoder.model.decoder.layers.0.fc2.weight": "pytorch_model-00001-of-00002.bin",
141
+ "decoder.model.decoder.layers.0.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
142
+ "decoder.model.decoder.layers.0.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
143
+ "decoder.model.decoder.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
144
+ "decoder.model.decoder.layers.0.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
145
+ "decoder.model.decoder.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
146
+ "decoder.model.decoder.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
147
+ "decoder.model.decoder.layers.0.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
148
+ "decoder.model.decoder.layers.0.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
149
+ "decoder.model.decoder.layers.1.encoder_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
150
+ "decoder.model.decoder.layers.1.encoder_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
151
+ "decoder.model.decoder.layers.1.encoder_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
152
+ "decoder.model.decoder.layers.1.encoder_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
153
+ "decoder.model.decoder.layers.1.encoder_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
154
+ "decoder.model.decoder.layers.1.encoder_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
155
+ "decoder.model.decoder.layers.1.fc1.weight": "pytorch_model-00001-of-00002.bin",
156
+ "decoder.model.decoder.layers.1.fc2.weight": "pytorch_model-00001-of-00002.bin",
157
+ "decoder.model.decoder.layers.1.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
158
+ "decoder.model.decoder.layers.1.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
159
+ "decoder.model.decoder.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
160
+ "decoder.model.decoder.layers.1.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
161
+ "decoder.model.decoder.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
162
+ "decoder.model.decoder.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
163
+ "decoder.model.decoder.layers.1.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
164
+ "decoder.model.decoder.layers.1.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
165
+ "decoder.model.decoder.layers.10.encoder_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
166
+ "decoder.model.decoder.layers.10.encoder_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
167
+ "decoder.model.decoder.layers.10.encoder_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
168
+ "decoder.model.decoder.layers.10.encoder_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
169
+ "decoder.model.decoder.layers.10.encoder_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
170
+ "decoder.model.decoder.layers.10.encoder_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
171
+ "decoder.model.decoder.layers.10.fc1.weight": "pytorch_model-00001-of-00002.bin",
172
+ "decoder.model.decoder.layers.10.fc2.weight": "pytorch_model-00001-of-00002.bin",
173
+ "decoder.model.decoder.layers.10.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
174
+ "decoder.model.decoder.layers.10.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
175
+ "decoder.model.decoder.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
176
+ "decoder.model.decoder.layers.10.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
177
+ "decoder.model.decoder.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
178
+ "decoder.model.decoder.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
179
+ "decoder.model.decoder.layers.10.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
180
+ "decoder.model.decoder.layers.10.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
181
+ "decoder.model.decoder.layers.11.encoder_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
182
+ "decoder.model.decoder.layers.11.encoder_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
183
+ "decoder.model.decoder.layers.11.encoder_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
184
+ "decoder.model.decoder.layers.11.encoder_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
185
+ "decoder.model.decoder.layers.11.encoder_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
186
+ "decoder.model.decoder.layers.11.encoder_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
187
+ "decoder.model.decoder.layers.11.fc1.weight": "pytorch_model-00001-of-00002.bin",
188
+ "decoder.model.decoder.layers.11.fc2.weight": "pytorch_model-00001-of-00002.bin",
189
+ "decoder.model.decoder.layers.11.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
190
+ "decoder.model.decoder.layers.11.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
191
+ "decoder.model.decoder.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
192
+ "decoder.model.decoder.layers.11.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
193
+ "decoder.model.decoder.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
194
+ "decoder.model.decoder.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
195
+ "decoder.model.decoder.layers.11.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
196
+ "decoder.model.decoder.layers.11.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
197
+ "decoder.model.decoder.layers.12.encoder_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
198
+ "decoder.model.decoder.layers.12.encoder_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
199
+ "decoder.model.decoder.layers.12.encoder_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
200
+ "decoder.model.decoder.layers.12.encoder_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
201
+ "decoder.model.decoder.layers.12.encoder_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
202
+ "decoder.model.decoder.layers.12.encoder_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
203
+ "decoder.model.decoder.layers.12.fc1.weight": "pytorch_model-00001-of-00002.bin",
204
+ "decoder.model.decoder.layers.12.fc2.weight": "pytorch_model-00001-of-00002.bin",
205
+ "decoder.model.decoder.layers.12.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
206
+ "decoder.model.decoder.layers.12.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
207
+ "decoder.model.decoder.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
208
+ "decoder.model.decoder.layers.12.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
209
+ "decoder.model.decoder.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
210
+ "decoder.model.decoder.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
211
+ "decoder.model.decoder.layers.12.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
212
+ "decoder.model.decoder.layers.12.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
213
+ "decoder.model.decoder.layers.13.encoder_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
214
+ "decoder.model.decoder.layers.13.encoder_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
215
+ "decoder.model.decoder.layers.13.encoder_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
216
+ "decoder.model.decoder.layers.13.encoder_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
217
+ "decoder.model.decoder.layers.13.encoder_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
218
+ "decoder.model.decoder.layers.13.encoder_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
219
+ "decoder.model.decoder.layers.13.fc1.weight": "pytorch_model-00001-of-00002.bin",
220
+ "decoder.model.decoder.layers.13.fc2.weight": "pytorch_model-00001-of-00002.bin",
221
+ "decoder.model.decoder.layers.13.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
222
+ "decoder.model.decoder.layers.13.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
223
+ "decoder.model.decoder.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
224
+ "decoder.model.decoder.layers.13.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
225
+ "decoder.model.decoder.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
226
+ "decoder.model.decoder.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
227
+ "decoder.model.decoder.layers.13.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
228
+ "decoder.model.decoder.layers.13.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
229
+ "decoder.model.decoder.layers.14.encoder_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
230
+ "decoder.model.decoder.layers.14.encoder_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
231
+ "decoder.model.decoder.layers.14.encoder_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
232
+ "decoder.model.decoder.layers.14.encoder_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
233
+ "decoder.model.decoder.layers.14.encoder_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
234
+ "decoder.model.decoder.layers.14.encoder_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
235
+ "decoder.model.decoder.layers.14.fc1.weight": "pytorch_model-00001-of-00002.bin",
236
+ "decoder.model.decoder.layers.14.fc2.weight": "pytorch_model-00001-of-00002.bin",
237
+ "decoder.model.decoder.layers.14.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
238
+ "decoder.model.decoder.layers.14.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
239
+ "decoder.model.decoder.layers.14.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
240
+ "decoder.model.decoder.layers.14.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
241
+ "decoder.model.decoder.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
242
+ "decoder.model.decoder.layers.14.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
243
+ "decoder.model.decoder.layers.14.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
244
+ "decoder.model.decoder.layers.14.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
245
+ "decoder.model.decoder.layers.15.encoder_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
246
+ "decoder.model.decoder.layers.15.encoder_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
247
+ "decoder.model.decoder.layers.15.encoder_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
248
+ "decoder.model.decoder.layers.15.encoder_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
249
+ "decoder.model.decoder.layers.15.encoder_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
250
+ "decoder.model.decoder.layers.15.encoder_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
251
+ "decoder.model.decoder.layers.15.fc1.weight": "pytorch_model-00001-of-00002.bin",
252
+ "decoder.model.decoder.layers.15.fc2.weight": "pytorch_model-00001-of-00002.bin",
253
+ "decoder.model.decoder.layers.15.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
254
+ "decoder.model.decoder.layers.15.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
255
+ "decoder.model.decoder.layers.15.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
256
+ "decoder.model.decoder.layers.15.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
257
+ "decoder.model.decoder.layers.15.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
258
+ "decoder.model.decoder.layers.15.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
259
+ "decoder.model.decoder.layers.15.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
260
+ "decoder.model.decoder.layers.15.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
261
+ "decoder.model.decoder.layers.16.encoder_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
262
+ "decoder.model.decoder.layers.16.encoder_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
263
+ "decoder.model.decoder.layers.16.encoder_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
264
+ "decoder.model.decoder.layers.16.encoder_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
265
+ "decoder.model.decoder.layers.16.encoder_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
266
+ "decoder.model.decoder.layers.16.encoder_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
267
+ "decoder.model.decoder.layers.16.fc1.weight": "pytorch_model-00001-of-00002.bin",
268
+ "decoder.model.decoder.layers.16.fc2.weight": "pytorch_model-00001-of-00002.bin",
269
+ "decoder.model.decoder.layers.16.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
270
+ "decoder.model.decoder.layers.16.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
271
+ "decoder.model.decoder.layers.16.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
272
+ "decoder.model.decoder.layers.16.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
273
+ "decoder.model.decoder.layers.16.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
274
+ "decoder.model.decoder.layers.16.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
275
+ "decoder.model.decoder.layers.16.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
276
+ "decoder.model.decoder.layers.16.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
277
+ "decoder.model.decoder.layers.17.encoder_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
278
+ "decoder.model.decoder.layers.17.encoder_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
279
+ "decoder.model.decoder.layers.17.encoder_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
280
+ "decoder.model.decoder.layers.17.encoder_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
281
+ "decoder.model.decoder.layers.17.encoder_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
282
+ "decoder.model.decoder.layers.17.encoder_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
283
+ "decoder.model.decoder.layers.17.fc1.weight": "pytorch_model-00001-of-00002.bin",
284
+ "decoder.model.decoder.layers.17.fc2.weight": "pytorch_model-00001-of-00002.bin",
285
+ "decoder.model.decoder.layers.17.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
286
+ "decoder.model.decoder.layers.17.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
287
+ "decoder.model.decoder.layers.17.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
288
+ "decoder.model.decoder.layers.17.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
289
+ "decoder.model.decoder.layers.17.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
290
+ "decoder.model.decoder.layers.17.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
291
+ "decoder.model.decoder.layers.17.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
292
+ "decoder.model.decoder.layers.17.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
293
+ "decoder.model.decoder.layers.18.encoder_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
294
+ "decoder.model.decoder.layers.18.encoder_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
295
+ "decoder.model.decoder.layers.18.encoder_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
296
+ "decoder.model.decoder.layers.18.encoder_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
297
+ "decoder.model.decoder.layers.18.encoder_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
298
+ "decoder.model.decoder.layers.18.encoder_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
299
+ "decoder.model.decoder.layers.18.fc1.weight": "pytorch_model-00001-of-00002.bin",
300
+ "decoder.model.decoder.layers.18.fc2.weight": "pytorch_model-00001-of-00002.bin",
301
+ "decoder.model.decoder.layers.18.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
302
+ "decoder.model.decoder.layers.18.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
303
+ "decoder.model.decoder.layers.18.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
304
+ "decoder.model.decoder.layers.18.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
305
+ "decoder.model.decoder.layers.18.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
306
+ "decoder.model.decoder.layers.18.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
307
+ "decoder.model.decoder.layers.18.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
308
+ "decoder.model.decoder.layers.18.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
309
+ "decoder.model.decoder.layers.19.encoder_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
310
+ "decoder.model.decoder.layers.19.encoder_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
311
+ "decoder.model.decoder.layers.19.encoder_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
312
+ "decoder.model.decoder.layers.19.encoder_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
313
+ "decoder.model.decoder.layers.19.encoder_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
314
+ "decoder.model.decoder.layers.19.encoder_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
315
+ "decoder.model.decoder.layers.19.fc1.weight": "pytorch_model-00001-of-00002.bin",
316
+ "decoder.model.decoder.layers.19.fc2.weight": "pytorch_model-00001-of-00002.bin",
317
+ "decoder.model.decoder.layers.19.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
318
+ "decoder.model.decoder.layers.19.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
319
+ "decoder.model.decoder.layers.19.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
320
+ "decoder.model.decoder.layers.19.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
321
+ "decoder.model.decoder.layers.19.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
322
+ "decoder.model.decoder.layers.19.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
323
+ "decoder.model.decoder.layers.19.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
324
+ "decoder.model.decoder.layers.19.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
325
+ "decoder.model.decoder.layers.2.encoder_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
326
+ "decoder.model.decoder.layers.2.encoder_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
327
+ "decoder.model.decoder.layers.2.encoder_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
328
+ "decoder.model.decoder.layers.2.encoder_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
329
+ "decoder.model.decoder.layers.2.encoder_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
330
+ "decoder.model.decoder.layers.2.encoder_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
331
+ "decoder.model.decoder.layers.2.fc1.weight": "pytorch_model-00001-of-00002.bin",
332
+ "decoder.model.decoder.layers.2.fc2.weight": "pytorch_model-00001-of-00002.bin",
333
+ "decoder.model.decoder.layers.2.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
334
+ "decoder.model.decoder.layers.2.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
335
+ "decoder.model.decoder.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
336
+ "decoder.model.decoder.layers.2.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
337
+ "decoder.model.decoder.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
338
+ "decoder.model.decoder.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
339
+ "decoder.model.decoder.layers.2.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
340
+ "decoder.model.decoder.layers.2.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
341
+ "decoder.model.decoder.layers.20.encoder_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
342
+ "decoder.model.decoder.layers.20.encoder_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
343
+ "decoder.model.decoder.layers.20.encoder_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
344
+ "decoder.model.decoder.layers.20.encoder_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
345
+ "decoder.model.decoder.layers.20.encoder_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
346
+ "decoder.model.decoder.layers.20.encoder_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
347
+ "decoder.model.decoder.layers.20.fc1.weight": "pytorch_model-00001-of-00002.bin",
348
+ "decoder.model.decoder.layers.20.fc2.weight": "pytorch_model-00001-of-00002.bin",
349
+ "decoder.model.decoder.layers.20.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
350
+ "decoder.model.decoder.layers.20.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
351
+ "decoder.model.decoder.layers.20.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
352
+ "decoder.model.decoder.layers.20.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
353
+ "decoder.model.decoder.layers.20.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
354
+ "decoder.model.decoder.layers.20.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
355
+ "decoder.model.decoder.layers.20.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
356
+ "decoder.model.decoder.layers.20.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
357
+ "decoder.model.decoder.layers.21.encoder_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
358
+ "decoder.model.decoder.layers.21.encoder_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
359
+ "decoder.model.decoder.layers.21.encoder_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
360
+ "decoder.model.decoder.layers.21.encoder_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
361
+ "decoder.model.decoder.layers.21.encoder_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
362
+ "decoder.model.decoder.layers.21.encoder_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
363
+ "decoder.model.decoder.layers.21.fc1.weight": "pytorch_model-00001-of-00002.bin",
364
+ "decoder.model.decoder.layers.21.fc2.weight": "pytorch_model-00001-of-00002.bin",
365
+ "decoder.model.decoder.layers.21.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
366
+ "decoder.model.decoder.layers.21.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
367
+ "decoder.model.decoder.layers.21.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
368
+ "decoder.model.decoder.layers.21.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
369
+ "decoder.model.decoder.layers.21.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
370
+ "decoder.model.decoder.layers.21.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
371
+ "decoder.model.decoder.layers.21.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
372
+ "decoder.model.decoder.layers.21.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
373
+ "decoder.model.decoder.layers.22.encoder_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
374
+ "decoder.model.decoder.layers.22.encoder_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
375
+ "decoder.model.decoder.layers.22.encoder_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
376
+ "decoder.model.decoder.layers.22.encoder_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
377
+ "decoder.model.decoder.layers.22.encoder_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
378
+ "decoder.model.decoder.layers.22.encoder_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
379
+ "decoder.model.decoder.layers.22.fc1.weight": "pytorch_model-00001-of-00002.bin",
380
+ "decoder.model.decoder.layers.22.fc2.weight": "pytorch_model-00001-of-00002.bin",
381
+ "decoder.model.decoder.layers.22.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
382
+ "decoder.model.decoder.layers.22.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
383
+ "decoder.model.decoder.layers.22.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
384
+ "decoder.model.decoder.layers.22.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
385
+ "decoder.model.decoder.layers.22.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
386
+ "decoder.model.decoder.layers.22.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
387
+ "decoder.model.decoder.layers.22.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
388
+ "decoder.model.decoder.layers.22.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
389
+ "decoder.model.decoder.layers.23.encoder_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
390
+ "decoder.model.decoder.layers.23.encoder_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
391
+ "decoder.model.decoder.layers.23.encoder_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
392
+ "decoder.model.decoder.layers.23.encoder_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
393
+ "decoder.model.decoder.layers.23.encoder_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
394
+ "decoder.model.decoder.layers.23.encoder_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
395
+ "decoder.model.decoder.layers.23.fc1.weight": "pytorch_model-00001-of-00002.bin",
396
+ "decoder.model.decoder.layers.23.fc2.weight": "pytorch_model-00001-of-00002.bin",
397
+ "decoder.model.decoder.layers.23.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
398
+ "decoder.model.decoder.layers.23.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
399
+ "decoder.model.decoder.layers.23.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
400
+ "decoder.model.decoder.layers.23.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
401
+ "decoder.model.decoder.layers.23.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
402
+ "decoder.model.decoder.layers.23.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
403
+ "decoder.model.decoder.layers.23.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
404
+ "decoder.model.decoder.layers.23.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
405
+ "decoder.model.decoder.layers.24.encoder_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
406
+ "decoder.model.decoder.layers.24.encoder_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
407
+ "decoder.model.decoder.layers.24.encoder_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
408
+ "decoder.model.decoder.layers.24.encoder_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
409
+ "decoder.model.decoder.layers.24.encoder_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
410
+ "decoder.model.decoder.layers.24.encoder_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
411
+ "decoder.model.decoder.layers.24.fc1.weight": "pytorch_model-00001-of-00002.bin",
412
+ "decoder.model.decoder.layers.24.fc2.weight": "pytorch_model-00001-of-00002.bin",
413
+ "decoder.model.decoder.layers.24.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
414
+ "decoder.model.decoder.layers.24.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
415
+ "decoder.model.decoder.layers.24.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
416
+ "decoder.model.decoder.layers.24.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
417
+ "decoder.model.decoder.layers.24.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
418
+ "decoder.model.decoder.layers.24.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
419
+ "decoder.model.decoder.layers.24.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
420
+ "decoder.model.decoder.layers.24.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
421
+ "decoder.model.decoder.layers.25.encoder_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
422
+ "decoder.model.decoder.layers.25.encoder_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
423
+ "decoder.model.decoder.layers.25.encoder_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
424
+ "decoder.model.decoder.layers.25.encoder_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
425
+ "decoder.model.decoder.layers.25.encoder_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
426
+ "decoder.model.decoder.layers.25.encoder_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
427
+ "decoder.model.decoder.layers.25.fc1.weight": "pytorch_model-00001-of-00002.bin",
428
+ "decoder.model.decoder.layers.25.fc2.weight": "pytorch_model-00001-of-00002.bin",
429
+ "decoder.model.decoder.layers.25.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
430
+ "decoder.model.decoder.layers.25.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
431
+ "decoder.model.decoder.layers.25.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
432
+ "decoder.model.decoder.layers.25.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
433
+ "decoder.model.decoder.layers.25.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
434
+ "decoder.model.decoder.layers.25.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
435
+ "decoder.model.decoder.layers.25.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
436
+ "decoder.model.decoder.layers.25.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
437
+ "decoder.model.decoder.layers.26.encoder_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
438
+ "decoder.model.decoder.layers.26.encoder_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
439
+ "decoder.model.decoder.layers.26.encoder_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
440
+ "decoder.model.decoder.layers.26.encoder_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
441
+ "decoder.model.decoder.layers.26.encoder_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
442
+ "decoder.model.decoder.layers.26.encoder_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
443
+ "decoder.model.decoder.layers.26.fc1.weight": "pytorch_model-00001-of-00002.bin",
444
+ "decoder.model.decoder.layers.26.fc2.weight": "pytorch_model-00001-of-00002.bin",
445
+ "decoder.model.decoder.layers.26.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
446
+ "decoder.model.decoder.layers.26.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
447
+ "decoder.model.decoder.layers.26.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
448
+ "decoder.model.decoder.layers.26.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
449
+ "decoder.model.decoder.layers.26.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
450
+ "decoder.model.decoder.layers.26.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
451
+ "decoder.model.decoder.layers.26.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
452
+ "decoder.model.decoder.layers.26.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
453
+ "decoder.model.decoder.layers.27.encoder_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
454
+ "decoder.model.decoder.layers.27.encoder_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
455
+ "decoder.model.decoder.layers.27.encoder_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
456
+ "decoder.model.decoder.layers.27.encoder_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
457
+ "decoder.model.decoder.layers.27.encoder_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
458
+ "decoder.model.decoder.layers.27.encoder_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
459
+ "decoder.model.decoder.layers.27.fc1.weight": "pytorch_model-00001-of-00002.bin",
460
+ "decoder.model.decoder.layers.27.fc2.weight": "pytorch_model-00001-of-00002.bin",
461
+ "decoder.model.decoder.layers.27.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
462
+ "decoder.model.decoder.layers.27.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
463
+ "decoder.model.decoder.layers.27.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
464
+ "decoder.model.decoder.layers.27.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
465
+ "decoder.model.decoder.layers.27.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
466
+ "decoder.model.decoder.layers.27.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
467
+ "decoder.model.decoder.layers.27.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
468
+ "decoder.model.decoder.layers.27.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
469
+ "decoder.model.decoder.layers.28.encoder_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
470
+ "decoder.model.decoder.layers.28.encoder_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
471
+ "decoder.model.decoder.layers.28.encoder_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
472
+ "decoder.model.decoder.layers.28.encoder_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
473
+ "decoder.model.decoder.layers.28.encoder_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
474
+ "decoder.model.decoder.layers.28.encoder_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
475
+ "decoder.model.decoder.layers.28.fc1.weight": "pytorch_model-00001-of-00002.bin",
476
+ "decoder.model.decoder.layers.28.fc2.weight": "pytorch_model-00001-of-00002.bin",
477
+ "decoder.model.decoder.layers.28.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
478
+ "decoder.model.decoder.layers.28.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
479
+ "decoder.model.decoder.layers.28.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
480
+ "decoder.model.decoder.layers.28.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
481
+ "decoder.model.decoder.layers.28.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
482
+ "decoder.model.decoder.layers.28.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
483
+ "decoder.model.decoder.layers.28.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
484
+ "decoder.model.decoder.layers.28.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
485
+ "decoder.model.decoder.layers.29.encoder_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
486
+ "decoder.model.decoder.layers.29.encoder_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
487
+ "decoder.model.decoder.layers.29.encoder_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
488
+ "decoder.model.decoder.layers.29.encoder_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
489
+ "decoder.model.decoder.layers.29.encoder_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
490
+ "decoder.model.decoder.layers.29.encoder_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
491
+ "decoder.model.decoder.layers.29.fc1.weight": "pytorch_model-00001-of-00002.bin",
492
+ "decoder.model.decoder.layers.29.fc2.weight": "pytorch_model-00001-of-00002.bin",
493
+ "decoder.model.decoder.layers.29.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
494
+ "decoder.model.decoder.layers.29.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
495
+ "decoder.model.decoder.layers.29.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
496
+ "decoder.model.decoder.layers.29.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
497
+ "decoder.model.decoder.layers.29.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
498
+ "decoder.model.decoder.layers.29.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
499
+ "decoder.model.decoder.layers.29.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
500
+ "decoder.model.decoder.layers.29.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
501
+ "decoder.model.decoder.layers.3.encoder_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
502
+ "decoder.model.decoder.layers.3.encoder_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
503
+ "decoder.model.decoder.layers.3.encoder_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
504
+ "decoder.model.decoder.layers.3.encoder_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
505
+ "decoder.model.decoder.layers.3.encoder_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
506
+ "decoder.model.decoder.layers.3.encoder_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
507
+ "decoder.model.decoder.layers.3.fc1.weight": "pytorch_model-00001-of-00002.bin",
508
+ "decoder.model.decoder.layers.3.fc2.weight": "pytorch_model-00001-of-00002.bin",
509
+ "decoder.model.decoder.layers.3.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
510
+ "decoder.model.decoder.layers.3.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
511
+ "decoder.model.decoder.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
512
+ "decoder.model.decoder.layers.3.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
513
+ "decoder.model.decoder.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
514
+ "decoder.model.decoder.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
515
+ "decoder.model.decoder.layers.3.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
516
+ "decoder.model.decoder.layers.3.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
517
+ "decoder.model.decoder.layers.30.encoder_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
518
+ "decoder.model.decoder.layers.30.encoder_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
519
+ "decoder.model.decoder.layers.30.encoder_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
520
+ "decoder.model.decoder.layers.30.encoder_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
521
+ "decoder.model.decoder.layers.30.encoder_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
522
+ "decoder.model.decoder.layers.30.encoder_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
523
+ "decoder.model.decoder.layers.30.fc1.weight": "pytorch_model-00001-of-00002.bin",
524
+ "decoder.model.decoder.layers.30.fc2.weight": "pytorch_model-00001-of-00002.bin",
525
+ "decoder.model.decoder.layers.30.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
526
+ "decoder.model.decoder.layers.30.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
527
+ "decoder.model.decoder.layers.30.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
528
+ "decoder.model.decoder.layers.30.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
529
+ "decoder.model.decoder.layers.30.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
530
+ "decoder.model.decoder.layers.30.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
531
+ "decoder.model.decoder.layers.30.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
532
+ "decoder.model.decoder.layers.30.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
533
+ "decoder.model.decoder.layers.31.encoder_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
534
+ "decoder.model.decoder.layers.31.encoder_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
535
+ "decoder.model.decoder.layers.31.encoder_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
536
+ "decoder.model.decoder.layers.31.encoder_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
537
+ "decoder.model.decoder.layers.31.encoder_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
538
+ "decoder.model.decoder.layers.31.encoder_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
539
+ "decoder.model.decoder.layers.31.fc1.weight": "pytorch_model-00001-of-00002.bin",
540
+ "decoder.model.decoder.layers.31.fc2.weight": "pytorch_model-00001-of-00002.bin",
541
+ "decoder.model.decoder.layers.31.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
542
+ "decoder.model.decoder.layers.31.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
543
+ "decoder.model.decoder.layers.31.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
544
+ "decoder.model.decoder.layers.31.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
545
+ "decoder.model.decoder.layers.31.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
546
+ "decoder.model.decoder.layers.31.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
547
+ "decoder.model.decoder.layers.31.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
548
+ "decoder.model.decoder.layers.31.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
549
+ "decoder.model.decoder.layers.32.encoder_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
550
+ "decoder.model.decoder.layers.32.encoder_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
551
+ "decoder.model.decoder.layers.32.encoder_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
552
+ "decoder.model.decoder.layers.32.encoder_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
553
+ "decoder.model.decoder.layers.32.encoder_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
554
+ "decoder.model.decoder.layers.32.encoder_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
555
+ "decoder.model.decoder.layers.32.fc1.weight": "pytorch_model-00001-of-00002.bin",
556
+ "decoder.model.decoder.layers.32.fc2.weight": "pytorch_model-00001-of-00002.bin",
557
+ "decoder.model.decoder.layers.32.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
558
+ "decoder.model.decoder.layers.32.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
559
+ "decoder.model.decoder.layers.32.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
560
+ "decoder.model.decoder.layers.32.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
561
+ "decoder.model.decoder.layers.32.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
562
+ "decoder.model.decoder.layers.32.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
563
+ "decoder.model.decoder.layers.32.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
564
+ "decoder.model.decoder.layers.32.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
565
+ "decoder.model.decoder.layers.33.encoder_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
566
+ "decoder.model.decoder.layers.33.encoder_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
567
+ "decoder.model.decoder.layers.33.encoder_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
568
+ "decoder.model.decoder.layers.33.encoder_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
569
+ "decoder.model.decoder.layers.33.encoder_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
570
+ "decoder.model.decoder.layers.33.encoder_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
571
+ "decoder.model.decoder.layers.33.fc1.weight": "pytorch_model-00001-of-00002.bin",
572
+ "decoder.model.decoder.layers.33.fc2.weight": "pytorch_model-00001-of-00002.bin",
573
+ "decoder.model.decoder.layers.33.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
574
+ "decoder.model.decoder.layers.33.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
575
+ "decoder.model.decoder.layers.33.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
576
+ "decoder.model.decoder.layers.33.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
577
+ "decoder.model.decoder.layers.33.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
578
+ "decoder.model.decoder.layers.33.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
579
+ "decoder.model.decoder.layers.33.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
580
+ "decoder.model.decoder.layers.33.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
581
+ "decoder.model.decoder.layers.34.encoder_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
582
+ "decoder.model.decoder.layers.34.encoder_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
583
+ "decoder.model.decoder.layers.34.encoder_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
584
+ "decoder.model.decoder.layers.34.encoder_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
585
+ "decoder.model.decoder.layers.34.encoder_attn_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
586
+ "decoder.model.decoder.layers.34.encoder_attn_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
587
+ "decoder.model.decoder.layers.34.fc1.weight": "pytorch_model-00002-of-00002.bin",
588
+ "decoder.model.decoder.layers.34.fc2.weight": "pytorch_model-00002-of-00002.bin",
589
+ "decoder.model.decoder.layers.34.final_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
590
+ "decoder.model.decoder.layers.34.final_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
591
+ "decoder.model.decoder.layers.34.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
592
+ "decoder.model.decoder.layers.34.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
593
+ "decoder.model.decoder.layers.34.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
594
+ "decoder.model.decoder.layers.34.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
595
+ "decoder.model.decoder.layers.34.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
596
+ "decoder.model.decoder.layers.34.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
597
+ "decoder.model.decoder.layers.35.encoder_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
598
+ "decoder.model.decoder.layers.35.encoder_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
599
+ "decoder.model.decoder.layers.35.encoder_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
600
+ "decoder.model.decoder.layers.35.encoder_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
601
+ "decoder.model.decoder.layers.35.encoder_attn_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
602
+ "decoder.model.decoder.layers.35.encoder_attn_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
603
+ "decoder.model.decoder.layers.35.fc1.weight": "pytorch_model-00002-of-00002.bin",
604
+ "decoder.model.decoder.layers.35.fc2.weight": "pytorch_model-00002-of-00002.bin",
605
+ "decoder.model.decoder.layers.35.final_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
606
+ "decoder.model.decoder.layers.35.final_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
607
+ "decoder.model.decoder.layers.35.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
608
+ "decoder.model.decoder.layers.35.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
609
+ "decoder.model.decoder.layers.35.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
610
+ "decoder.model.decoder.layers.35.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
611
+ "decoder.model.decoder.layers.35.self_attn_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
612
+ "decoder.model.decoder.layers.35.self_attn_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
613
+ "decoder.model.decoder.layers.36.encoder_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
614
+ "decoder.model.decoder.layers.36.encoder_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
615
+ "decoder.model.decoder.layers.36.encoder_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
616
+ "decoder.model.decoder.layers.36.encoder_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
617
+ "decoder.model.decoder.layers.36.encoder_attn_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
618
+ "decoder.model.decoder.layers.36.encoder_attn_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
619
+ "decoder.model.decoder.layers.36.fc1.weight": "pytorch_model-00002-of-00002.bin",
620
+ "decoder.model.decoder.layers.36.fc2.weight": "pytorch_model-00002-of-00002.bin",
621
+ "decoder.model.decoder.layers.36.final_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
622
+ "decoder.model.decoder.layers.36.final_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
623
+ "decoder.model.decoder.layers.36.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
624
+ "decoder.model.decoder.layers.36.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
625
+ "decoder.model.decoder.layers.36.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
626
+ "decoder.model.decoder.layers.36.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
627
+ "decoder.model.decoder.layers.36.self_attn_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
628
+ "decoder.model.decoder.layers.36.self_attn_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
629
+ "decoder.model.decoder.layers.37.encoder_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
630
+ "decoder.model.decoder.layers.37.encoder_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
631
+ "decoder.model.decoder.layers.37.encoder_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
632
+ "decoder.model.decoder.layers.37.encoder_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
633
+ "decoder.model.decoder.layers.37.encoder_attn_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
634
+ "decoder.model.decoder.layers.37.encoder_attn_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
635
+ "decoder.model.decoder.layers.37.fc1.weight": "pytorch_model-00002-of-00002.bin",
636
+ "decoder.model.decoder.layers.37.fc2.weight": "pytorch_model-00002-of-00002.bin",
637
+ "decoder.model.decoder.layers.37.final_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
638
+ "decoder.model.decoder.layers.37.final_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
639
+ "decoder.model.decoder.layers.37.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
640
+ "decoder.model.decoder.layers.37.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
641
+ "decoder.model.decoder.layers.37.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
642
+ "decoder.model.decoder.layers.37.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
643
+ "decoder.model.decoder.layers.37.self_attn_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
644
+ "decoder.model.decoder.layers.37.self_attn_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
645
+ "decoder.model.decoder.layers.38.encoder_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
646
+ "decoder.model.decoder.layers.38.encoder_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
647
+ "decoder.model.decoder.layers.38.encoder_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
648
+ "decoder.model.decoder.layers.38.encoder_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
649
+ "decoder.model.decoder.layers.38.encoder_attn_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
650
+ "decoder.model.decoder.layers.38.encoder_attn_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
651
+ "decoder.model.decoder.layers.38.fc1.weight": "pytorch_model-00002-of-00002.bin",
652
+ "decoder.model.decoder.layers.38.fc2.weight": "pytorch_model-00002-of-00002.bin",
653
+ "decoder.model.decoder.layers.38.final_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
654
+ "decoder.model.decoder.layers.38.final_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
655
+ "decoder.model.decoder.layers.38.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
656
+ "decoder.model.decoder.layers.38.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
657
+ "decoder.model.decoder.layers.38.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
658
+ "decoder.model.decoder.layers.38.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
659
+ "decoder.model.decoder.layers.38.self_attn_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
660
+ "decoder.model.decoder.layers.38.self_attn_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
661
+ "decoder.model.decoder.layers.39.encoder_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
662
+ "decoder.model.decoder.layers.39.encoder_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
663
+ "decoder.model.decoder.layers.39.encoder_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
664
+ "decoder.model.decoder.layers.39.encoder_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
665
+ "decoder.model.decoder.layers.39.encoder_attn_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
666
+ "decoder.model.decoder.layers.39.encoder_attn_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
667
+ "decoder.model.decoder.layers.39.fc1.weight": "pytorch_model-00002-of-00002.bin",
668
+ "decoder.model.decoder.layers.39.fc2.weight": "pytorch_model-00002-of-00002.bin",
669
+ "decoder.model.decoder.layers.39.final_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
670
+ "decoder.model.decoder.layers.39.final_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
671
+ "decoder.model.decoder.layers.39.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
672
+ "decoder.model.decoder.layers.39.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
673
+ "decoder.model.decoder.layers.39.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
674
+ "decoder.model.decoder.layers.39.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
675
+ "decoder.model.decoder.layers.39.self_attn_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
676
+ "decoder.model.decoder.layers.39.self_attn_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
677
+ "decoder.model.decoder.layers.4.encoder_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
678
+ "decoder.model.decoder.layers.4.encoder_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
679
+ "decoder.model.decoder.layers.4.encoder_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
680
+ "decoder.model.decoder.layers.4.encoder_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
681
+ "decoder.model.decoder.layers.4.encoder_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
682
+ "decoder.model.decoder.layers.4.encoder_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
683
+ "decoder.model.decoder.layers.4.fc1.weight": "pytorch_model-00001-of-00002.bin",
684
+ "decoder.model.decoder.layers.4.fc2.weight": "pytorch_model-00001-of-00002.bin",
685
+ "decoder.model.decoder.layers.4.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
686
+ "decoder.model.decoder.layers.4.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
687
+ "decoder.model.decoder.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
688
+ "decoder.model.decoder.layers.4.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
689
+ "decoder.model.decoder.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
690
+ "decoder.model.decoder.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
691
+ "decoder.model.decoder.layers.4.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
692
+ "decoder.model.decoder.layers.4.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
693
+ "decoder.model.decoder.layers.40.encoder_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
694
+ "decoder.model.decoder.layers.40.encoder_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
695
+ "decoder.model.decoder.layers.40.encoder_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
696
+ "decoder.model.decoder.layers.40.encoder_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
697
+ "decoder.model.decoder.layers.40.encoder_attn_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
698
+ "decoder.model.decoder.layers.40.encoder_attn_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
699
+ "decoder.model.decoder.layers.40.fc1.weight": "pytorch_model-00002-of-00002.bin",
700
+ "decoder.model.decoder.layers.40.fc2.weight": "pytorch_model-00002-of-00002.bin",
701
+ "decoder.model.decoder.layers.40.final_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
702
+ "decoder.model.decoder.layers.40.final_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
703
+ "decoder.model.decoder.layers.40.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
704
+ "decoder.model.decoder.layers.40.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
705
+ "decoder.model.decoder.layers.40.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
706
+ "decoder.model.decoder.layers.40.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
707
+ "decoder.model.decoder.layers.40.self_attn_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
708
+ "decoder.model.decoder.layers.40.self_attn_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
709
+ "decoder.model.decoder.layers.41.encoder_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
710
+ "decoder.model.decoder.layers.41.encoder_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
711
+ "decoder.model.decoder.layers.41.encoder_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
712
+ "decoder.model.decoder.layers.41.encoder_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
713
+ "decoder.model.decoder.layers.41.encoder_attn_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
714
+ "decoder.model.decoder.layers.41.encoder_attn_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
715
+ "decoder.model.decoder.layers.41.fc1.weight": "pytorch_model-00002-of-00002.bin",
716
+ "decoder.model.decoder.layers.41.fc2.weight": "pytorch_model-00002-of-00002.bin",
717
+ "decoder.model.decoder.layers.41.final_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
718
+ "decoder.model.decoder.layers.41.final_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
719
+ "decoder.model.decoder.layers.41.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
720
+ "decoder.model.decoder.layers.41.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
721
+ "decoder.model.decoder.layers.41.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
722
+ "decoder.model.decoder.layers.41.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
723
+ "decoder.model.decoder.layers.41.self_attn_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
724
+ "decoder.model.decoder.layers.41.self_attn_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
725
+ "decoder.model.decoder.layers.42.encoder_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
726
+ "decoder.model.decoder.layers.42.encoder_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
727
+ "decoder.model.decoder.layers.42.encoder_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
728
+ "decoder.model.decoder.layers.42.encoder_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
729
+ "decoder.model.decoder.layers.42.encoder_attn_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
730
+ "decoder.model.decoder.layers.42.encoder_attn_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
731
+ "decoder.model.decoder.layers.42.fc1.weight": "pytorch_model-00002-of-00002.bin",
732
+ "decoder.model.decoder.layers.42.fc2.weight": "pytorch_model-00002-of-00002.bin",
733
+ "decoder.model.decoder.layers.42.final_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
734
+ "decoder.model.decoder.layers.42.final_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
735
+ "decoder.model.decoder.layers.42.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
736
+ "decoder.model.decoder.layers.42.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
737
+ "decoder.model.decoder.layers.42.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
738
+ "decoder.model.decoder.layers.42.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
739
+ "decoder.model.decoder.layers.42.self_attn_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
740
+ "decoder.model.decoder.layers.42.self_attn_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
741
+ "decoder.model.decoder.layers.43.encoder_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
742
+ "decoder.model.decoder.layers.43.encoder_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
743
+ "decoder.model.decoder.layers.43.encoder_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
744
+ "decoder.model.decoder.layers.43.encoder_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
745
+ "decoder.model.decoder.layers.43.encoder_attn_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
746
+ "decoder.model.decoder.layers.43.encoder_attn_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
747
+ "decoder.model.decoder.layers.43.fc1.weight": "pytorch_model-00002-of-00002.bin",
748
+ "decoder.model.decoder.layers.43.fc2.weight": "pytorch_model-00002-of-00002.bin",
749
+ "decoder.model.decoder.layers.43.final_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
750
+ "decoder.model.decoder.layers.43.final_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
751
+ "decoder.model.decoder.layers.43.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
752
+ "decoder.model.decoder.layers.43.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
753
+ "decoder.model.decoder.layers.43.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
754
+ "decoder.model.decoder.layers.43.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
755
+ "decoder.model.decoder.layers.43.self_attn_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
756
+ "decoder.model.decoder.layers.43.self_attn_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
757
+ "decoder.model.decoder.layers.44.encoder_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
758
+ "decoder.model.decoder.layers.44.encoder_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
759
+ "decoder.model.decoder.layers.44.encoder_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
760
+ "decoder.model.decoder.layers.44.encoder_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
761
+ "decoder.model.decoder.layers.44.encoder_attn_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
762
+ "decoder.model.decoder.layers.44.encoder_attn_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
763
+ "decoder.model.decoder.layers.44.fc1.weight": "pytorch_model-00002-of-00002.bin",
764
+ "decoder.model.decoder.layers.44.fc2.weight": "pytorch_model-00002-of-00002.bin",
765
+ "decoder.model.decoder.layers.44.final_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
766
+ "decoder.model.decoder.layers.44.final_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
767
+ "decoder.model.decoder.layers.44.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
768
+ "decoder.model.decoder.layers.44.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
769
+ "decoder.model.decoder.layers.44.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
770
+ "decoder.model.decoder.layers.44.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
771
+ "decoder.model.decoder.layers.44.self_attn_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
772
+ "decoder.model.decoder.layers.44.self_attn_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
773
+ "decoder.model.decoder.layers.45.encoder_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
774
+ "decoder.model.decoder.layers.45.encoder_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
775
+ "decoder.model.decoder.layers.45.encoder_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
776
+ "decoder.model.decoder.layers.45.encoder_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
777
+ "decoder.model.decoder.layers.45.encoder_attn_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
778
+ "decoder.model.decoder.layers.45.encoder_attn_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
779
+ "decoder.model.decoder.layers.45.fc1.weight": "pytorch_model-00002-of-00002.bin",
780
+ "decoder.model.decoder.layers.45.fc2.weight": "pytorch_model-00002-of-00002.bin",
781
+ "decoder.model.decoder.layers.45.final_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
782
+ "decoder.model.decoder.layers.45.final_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
783
+ "decoder.model.decoder.layers.45.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
784
+ "decoder.model.decoder.layers.45.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
785
+ "decoder.model.decoder.layers.45.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
786
+ "decoder.model.decoder.layers.45.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
787
+ "decoder.model.decoder.layers.45.self_attn_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
788
+ "decoder.model.decoder.layers.45.self_attn_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
789
+ "decoder.model.decoder.layers.46.encoder_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
790
+ "decoder.model.decoder.layers.46.encoder_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
791
+ "decoder.model.decoder.layers.46.encoder_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
792
+ "decoder.model.decoder.layers.46.encoder_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
793
+ "decoder.model.decoder.layers.46.encoder_attn_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
794
+ "decoder.model.decoder.layers.46.encoder_attn_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
795
+ "decoder.model.decoder.layers.46.fc1.weight": "pytorch_model-00002-of-00002.bin",
796
+ "decoder.model.decoder.layers.46.fc2.weight": "pytorch_model-00002-of-00002.bin",
797
+ "decoder.model.decoder.layers.46.final_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
798
+ "decoder.model.decoder.layers.46.final_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
799
+ "decoder.model.decoder.layers.46.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
800
+ "decoder.model.decoder.layers.46.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
801
+ "decoder.model.decoder.layers.46.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
802
+ "decoder.model.decoder.layers.46.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
803
+ "decoder.model.decoder.layers.46.self_attn_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
804
+ "decoder.model.decoder.layers.46.self_attn_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
805
+ "decoder.model.decoder.layers.47.encoder_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
806
+ "decoder.model.decoder.layers.47.encoder_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
807
+ "decoder.model.decoder.layers.47.encoder_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
808
+ "decoder.model.decoder.layers.47.encoder_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
809
+ "decoder.model.decoder.layers.47.encoder_attn_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
810
+ "decoder.model.decoder.layers.47.encoder_attn_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
811
+ "decoder.model.decoder.layers.47.fc1.weight": "pytorch_model-00002-of-00002.bin",
812
+ "decoder.model.decoder.layers.47.fc2.weight": "pytorch_model-00002-of-00002.bin",
813
+ "decoder.model.decoder.layers.47.final_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
814
+ "decoder.model.decoder.layers.47.final_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
815
+ "decoder.model.decoder.layers.47.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
816
+ "decoder.model.decoder.layers.47.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
817
+ "decoder.model.decoder.layers.47.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
818
+ "decoder.model.decoder.layers.47.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
819
+ "decoder.model.decoder.layers.47.self_attn_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
820
+ "decoder.model.decoder.layers.47.self_attn_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
821
+ "decoder.model.decoder.layers.5.encoder_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
822
+ "decoder.model.decoder.layers.5.encoder_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
823
+ "decoder.model.decoder.layers.5.encoder_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
824
+ "decoder.model.decoder.layers.5.encoder_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
825
+ "decoder.model.decoder.layers.5.encoder_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
826
+ "decoder.model.decoder.layers.5.encoder_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
827
+ "decoder.model.decoder.layers.5.fc1.weight": "pytorch_model-00001-of-00002.bin",
828
+ "decoder.model.decoder.layers.5.fc2.weight": "pytorch_model-00001-of-00002.bin",
829
+ "decoder.model.decoder.layers.5.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
830
+ "decoder.model.decoder.layers.5.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
831
+ "decoder.model.decoder.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
832
+ "decoder.model.decoder.layers.5.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
833
+ "decoder.model.decoder.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
834
+ "decoder.model.decoder.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
835
+ "decoder.model.decoder.layers.5.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
836
+ "decoder.model.decoder.layers.5.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
837
+ "decoder.model.decoder.layers.6.encoder_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
838
+ "decoder.model.decoder.layers.6.encoder_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
839
+ "decoder.model.decoder.layers.6.encoder_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
840
+ "decoder.model.decoder.layers.6.encoder_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
841
+ "decoder.model.decoder.layers.6.encoder_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
842
+ "decoder.model.decoder.layers.6.encoder_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
843
+ "decoder.model.decoder.layers.6.fc1.weight": "pytorch_model-00001-of-00002.bin",
844
+ "decoder.model.decoder.layers.6.fc2.weight": "pytorch_model-00001-of-00002.bin",
845
+ "decoder.model.decoder.layers.6.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
846
+ "decoder.model.decoder.layers.6.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
847
+ "decoder.model.decoder.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
848
+ "decoder.model.decoder.layers.6.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
849
+ "decoder.model.decoder.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
850
+ "decoder.model.decoder.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
851
+ "decoder.model.decoder.layers.6.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
852
+ "decoder.model.decoder.layers.6.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
853
+ "decoder.model.decoder.layers.7.encoder_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
854
+ "decoder.model.decoder.layers.7.encoder_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
855
+ "decoder.model.decoder.layers.7.encoder_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
856
+ "decoder.model.decoder.layers.7.encoder_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
857
+ "decoder.model.decoder.layers.7.encoder_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
858
+ "decoder.model.decoder.layers.7.encoder_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
859
+ "decoder.model.decoder.layers.7.fc1.weight": "pytorch_model-00001-of-00002.bin",
860
+ "decoder.model.decoder.layers.7.fc2.weight": "pytorch_model-00001-of-00002.bin",
861
+ "decoder.model.decoder.layers.7.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
862
+ "decoder.model.decoder.layers.7.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
863
+ "decoder.model.decoder.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
864
+ "decoder.model.decoder.layers.7.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
865
+ "decoder.model.decoder.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
866
+ "decoder.model.decoder.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
867
+ "decoder.model.decoder.layers.7.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
868
+ "decoder.model.decoder.layers.7.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
869
+ "decoder.model.decoder.layers.8.encoder_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
870
+ "decoder.model.decoder.layers.8.encoder_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
871
+ "decoder.model.decoder.layers.8.encoder_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
872
+ "decoder.model.decoder.layers.8.encoder_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
873
+ "decoder.model.decoder.layers.8.encoder_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
874
+ "decoder.model.decoder.layers.8.encoder_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
875
+ "decoder.model.decoder.layers.8.fc1.weight": "pytorch_model-00001-of-00002.bin",
876
+ "decoder.model.decoder.layers.8.fc2.weight": "pytorch_model-00001-of-00002.bin",
877
+ "decoder.model.decoder.layers.8.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
878
+ "decoder.model.decoder.layers.8.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
879
+ "decoder.model.decoder.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
880
+ "decoder.model.decoder.layers.8.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
881
+ "decoder.model.decoder.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
882
+ "decoder.model.decoder.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
883
+ "decoder.model.decoder.layers.8.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
884
+ "decoder.model.decoder.layers.8.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
885
+ "decoder.model.decoder.layers.9.encoder_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
886
+ "decoder.model.decoder.layers.9.encoder_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
887
+ "decoder.model.decoder.layers.9.encoder_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
888
+ "decoder.model.decoder.layers.9.encoder_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
889
+ "decoder.model.decoder.layers.9.encoder_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
890
+ "decoder.model.decoder.layers.9.encoder_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
891
+ "decoder.model.decoder.layers.9.fc1.weight": "pytorch_model-00001-of-00002.bin",
892
+ "decoder.model.decoder.layers.9.fc2.weight": "pytorch_model-00001-of-00002.bin",
893
+ "decoder.model.decoder.layers.9.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
894
+ "decoder.model.decoder.layers.9.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
895
+ "decoder.model.decoder.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
896
+ "decoder.model.decoder.layers.9.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
897
+ "decoder.model.decoder.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
898
+ "decoder.model.decoder.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
899
+ "decoder.model.decoder.layers.9.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
900
+ "decoder.model.decoder.layers.9.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
901
+ "enc_to_dec_proj.bias": "pytorch_model-00002-of-00002.bin",
902
+ "enc_to_dec_proj.weight": "pytorch_model-00002-of-00002.bin",
903
+ "text_encoder.encoder.block.0.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
904
+ "text_encoder.encoder.block.0.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
905
+ "text_encoder.encoder.block.0.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
906
+ "text_encoder.encoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "pytorch_model-00001-of-00002.bin",
907
+ "text_encoder.encoder.block.0.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
908
+ "text_encoder.encoder.block.0.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
909
+ "text_encoder.encoder.block.0.layer.1.DenseReluDense.wi.weight": "pytorch_model-00001-of-00002.bin",
910
+ "text_encoder.encoder.block.0.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
911
+ "text_encoder.encoder.block.0.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
912
+ "text_encoder.encoder.block.1.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
913
+ "text_encoder.encoder.block.1.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
914
+ "text_encoder.encoder.block.1.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
915
+ "text_encoder.encoder.block.1.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
916
+ "text_encoder.encoder.block.1.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
917
+ "text_encoder.encoder.block.1.layer.1.DenseReluDense.wi.weight": "pytorch_model-00001-of-00002.bin",
918
+ "text_encoder.encoder.block.1.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
919
+ "text_encoder.encoder.block.1.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
920
+ "text_encoder.encoder.block.10.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
921
+ "text_encoder.encoder.block.10.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
922
+ "text_encoder.encoder.block.10.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
923
+ "text_encoder.encoder.block.10.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
924
+ "text_encoder.encoder.block.10.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
925
+ "text_encoder.encoder.block.10.layer.1.DenseReluDense.wi.weight": "pytorch_model-00001-of-00002.bin",
926
+ "text_encoder.encoder.block.10.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
927
+ "text_encoder.encoder.block.10.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
928
+ "text_encoder.encoder.block.11.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
929
+ "text_encoder.encoder.block.11.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
930
+ "text_encoder.encoder.block.11.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
931
+ "text_encoder.encoder.block.11.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
932
+ "text_encoder.encoder.block.11.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
933
+ "text_encoder.encoder.block.11.layer.1.DenseReluDense.wi.weight": "pytorch_model-00001-of-00002.bin",
934
+ "text_encoder.encoder.block.11.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
935
+ "text_encoder.encoder.block.11.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
936
+ "text_encoder.encoder.block.2.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
937
+ "text_encoder.encoder.block.2.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
938
+ "text_encoder.encoder.block.2.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
939
+ "text_encoder.encoder.block.2.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
940
+ "text_encoder.encoder.block.2.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
941
+ "text_encoder.encoder.block.2.layer.1.DenseReluDense.wi.weight": "pytorch_model-00001-of-00002.bin",
942
+ "text_encoder.encoder.block.2.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
943
+ "text_encoder.encoder.block.2.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
944
+ "text_encoder.encoder.block.3.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
945
+ "text_encoder.encoder.block.3.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
946
+ "text_encoder.encoder.block.3.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
947
+ "text_encoder.encoder.block.3.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
948
+ "text_encoder.encoder.block.3.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
949
+ "text_encoder.encoder.block.3.layer.1.DenseReluDense.wi.weight": "pytorch_model-00001-of-00002.bin",
950
+ "text_encoder.encoder.block.3.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
951
+ "text_encoder.encoder.block.3.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
952
+ "text_encoder.encoder.block.4.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
953
+ "text_encoder.encoder.block.4.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
954
+ "text_encoder.encoder.block.4.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
955
+ "text_encoder.encoder.block.4.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
956
+ "text_encoder.encoder.block.4.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
957
+ "text_encoder.encoder.block.4.layer.1.DenseReluDense.wi.weight": "pytorch_model-00001-of-00002.bin",
958
+ "text_encoder.encoder.block.4.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
959
+ "text_encoder.encoder.block.4.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
960
+ "text_encoder.encoder.block.5.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
961
+ "text_encoder.encoder.block.5.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
962
+ "text_encoder.encoder.block.5.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
963
+ "text_encoder.encoder.block.5.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
964
+ "text_encoder.encoder.block.5.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
965
+ "text_encoder.encoder.block.5.layer.1.DenseReluDense.wi.weight": "pytorch_model-00001-of-00002.bin",
966
+ "text_encoder.encoder.block.5.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
967
+ "text_encoder.encoder.block.5.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
968
+ "text_encoder.encoder.block.6.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
969
+ "text_encoder.encoder.block.6.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
970
+ "text_encoder.encoder.block.6.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
971
+ "text_encoder.encoder.block.6.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
972
+ "text_encoder.encoder.block.6.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
973
+ "text_encoder.encoder.block.6.layer.1.DenseReluDense.wi.weight": "pytorch_model-00001-of-00002.bin",
974
+ "text_encoder.encoder.block.6.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
975
+ "text_encoder.encoder.block.6.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
976
+ "text_encoder.encoder.block.7.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
977
+ "text_encoder.encoder.block.7.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
978
+ "text_encoder.encoder.block.7.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
979
+ "text_encoder.encoder.block.7.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
980
+ "text_encoder.encoder.block.7.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
981
+ "text_encoder.encoder.block.7.layer.1.DenseReluDense.wi.weight": "pytorch_model-00001-of-00002.bin",
982
+ "text_encoder.encoder.block.7.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
983
+ "text_encoder.encoder.block.7.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
984
+ "text_encoder.encoder.block.8.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
985
+ "text_encoder.encoder.block.8.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
986
+ "text_encoder.encoder.block.8.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
987
+ "text_encoder.encoder.block.8.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
988
+ "text_encoder.encoder.block.8.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
989
+ "text_encoder.encoder.block.8.layer.1.DenseReluDense.wi.weight": "pytorch_model-00001-of-00002.bin",
990
+ "text_encoder.encoder.block.8.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
991
+ "text_encoder.encoder.block.8.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
992
+ "text_encoder.encoder.block.9.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
993
+ "text_encoder.encoder.block.9.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
994
+ "text_encoder.encoder.block.9.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
995
+ "text_encoder.encoder.block.9.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
996
+ "text_encoder.encoder.block.9.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
997
+ "text_encoder.encoder.block.9.layer.1.DenseReluDense.wi.weight": "pytorch_model-00001-of-00002.bin",
998
+ "text_encoder.encoder.block.9.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
999
+ "text_encoder.encoder.block.9.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
1000
+ "text_encoder.encoder.embed_tokens.weight": "pytorch_model-00001-of-00002.bin",
1001
+ "text_encoder.encoder.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
1002
+ "text_encoder.shared.weight": "pytorch_model-00001-of-00002.bin"
1003
+ }
1004
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,107 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<extra_id_0>",
4
+ "<extra_id_1>",
5
+ "<extra_id_2>",
6
+ "<extra_id_3>",
7
+ "<extra_id_4>",
8
+ "<extra_id_5>",
9
+ "<extra_id_6>",
10
+ "<extra_id_7>",
11
+ "<extra_id_8>",
12
+ "<extra_id_9>",
13
+ "<extra_id_10>",
14
+ "<extra_id_11>",
15
+ "<extra_id_12>",
16
+ "<extra_id_13>",
17
+ "<extra_id_14>",
18
+ "<extra_id_15>",
19
+ "<extra_id_16>",
20
+ "<extra_id_17>",
21
+ "<extra_id_18>",
22
+ "<extra_id_19>",
23
+ "<extra_id_20>",
24
+ "<extra_id_21>",
25
+ "<extra_id_22>",
26
+ "<extra_id_23>",
27
+ "<extra_id_24>",
28
+ "<extra_id_25>",
29
+ "<extra_id_26>",
30
+ "<extra_id_27>",
31
+ "<extra_id_28>",
32
+ "<extra_id_29>",
33
+ "<extra_id_30>",
34
+ "<extra_id_31>",
35
+ "<extra_id_32>",
36
+ "<extra_id_33>",
37
+ "<extra_id_34>",
38
+ "<extra_id_35>",
39
+ "<extra_id_36>",
40
+ "<extra_id_37>",
41
+ "<extra_id_38>",
42
+ "<extra_id_39>",
43
+ "<extra_id_40>",
44
+ "<extra_id_41>",
45
+ "<extra_id_42>",
46
+ "<extra_id_43>",
47
+ "<extra_id_44>",
48
+ "<extra_id_45>",
49
+ "<extra_id_46>",
50
+ "<extra_id_47>",
51
+ "<extra_id_48>",
52
+ "<extra_id_49>",
53
+ "<extra_id_50>",
54
+ "<extra_id_51>",
55
+ "<extra_id_52>",
56
+ "<extra_id_53>",
57
+ "<extra_id_54>",
58
+ "<extra_id_55>",
59
+ "<extra_id_56>",
60
+ "<extra_id_57>",
61
+ "<extra_id_58>",
62
+ "<extra_id_59>",
63
+ "<extra_id_60>",
64
+ "<extra_id_61>",
65
+ "<extra_id_62>",
66
+ "<extra_id_63>",
67
+ "<extra_id_64>",
68
+ "<extra_id_65>",
69
+ "<extra_id_66>",
70
+ "<extra_id_67>",
71
+ "<extra_id_68>",
72
+ "<extra_id_69>",
73
+ "<extra_id_70>",
74
+ "<extra_id_71>",
75
+ "<extra_id_72>",
76
+ "<extra_id_73>",
77
+ "<extra_id_74>",
78
+ "<extra_id_75>",
79
+ "<extra_id_76>",
80
+ "<extra_id_77>",
81
+ "<extra_id_78>",
82
+ "<extra_id_79>",
83
+ "<extra_id_80>",
84
+ "<extra_id_81>",
85
+ "<extra_id_82>",
86
+ "<extra_id_83>",
87
+ "<extra_id_84>",
88
+ "<extra_id_85>",
89
+ "<extra_id_86>",
90
+ "<extra_id_87>",
91
+ "<extra_id_88>",
92
+ "<extra_id_89>",
93
+ "<extra_id_90>",
94
+ "<extra_id_91>",
95
+ "<extra_id_92>",
96
+ "<extra_id_93>",
97
+ "<extra_id_94>",
98
+ "<extra_id_95>",
99
+ "<extra_id_96>",
100
+ "<extra_id_97>",
101
+ "<extra_id_98>",
102
+ "<extra_id_99>"
103
+ ],
104
+ "eos_token": "</s>",
105
+ "pad_token": "<pad>",
106
+ "unk_token": "<unk>"
107
+ }
spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
3
+ size 791656
state_dict.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f0cf17b5e65c5dd8ba71767371c377f174e4ce1db44bc4d6657825769f26ffd
3
+ size 6514108999
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,112 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<extra_id_0>",
4
+ "<extra_id_1>",
5
+ "<extra_id_2>",
6
+ "<extra_id_3>",
7
+ "<extra_id_4>",
8
+ "<extra_id_5>",
9
+ "<extra_id_6>",
10
+ "<extra_id_7>",
11
+ "<extra_id_8>",
12
+ "<extra_id_9>",
13
+ "<extra_id_10>",
14
+ "<extra_id_11>",
15
+ "<extra_id_12>",
16
+ "<extra_id_13>",
17
+ "<extra_id_14>",
18
+ "<extra_id_15>",
19
+ "<extra_id_16>",
20
+ "<extra_id_17>",
21
+ "<extra_id_18>",
22
+ "<extra_id_19>",
23
+ "<extra_id_20>",
24
+ "<extra_id_21>",
25
+ "<extra_id_22>",
26
+ "<extra_id_23>",
27
+ "<extra_id_24>",
28
+ "<extra_id_25>",
29
+ "<extra_id_26>",
30
+ "<extra_id_27>",
31
+ "<extra_id_28>",
32
+ "<extra_id_29>",
33
+ "<extra_id_30>",
34
+ "<extra_id_31>",
35
+ "<extra_id_32>",
36
+ "<extra_id_33>",
37
+ "<extra_id_34>",
38
+ "<extra_id_35>",
39
+ "<extra_id_36>",
40
+ "<extra_id_37>",
41
+ "<extra_id_38>",
42
+ "<extra_id_39>",
43
+ "<extra_id_40>",
44
+ "<extra_id_41>",
45
+ "<extra_id_42>",
46
+ "<extra_id_43>",
47
+ "<extra_id_44>",
48
+ "<extra_id_45>",
49
+ "<extra_id_46>",
50
+ "<extra_id_47>",
51
+ "<extra_id_48>",
52
+ "<extra_id_49>",
53
+ "<extra_id_50>",
54
+ "<extra_id_51>",
55
+ "<extra_id_52>",
56
+ "<extra_id_53>",
57
+ "<extra_id_54>",
58
+ "<extra_id_55>",
59
+ "<extra_id_56>",
60
+ "<extra_id_57>",
61
+ "<extra_id_58>",
62
+ "<extra_id_59>",
63
+ "<extra_id_60>",
64
+ "<extra_id_61>",
65
+ "<extra_id_62>",
66
+ "<extra_id_63>",
67
+ "<extra_id_64>",
68
+ "<extra_id_65>",
69
+ "<extra_id_66>",
70
+ "<extra_id_67>",
71
+ "<extra_id_68>",
72
+ "<extra_id_69>",
73
+ "<extra_id_70>",
74
+ "<extra_id_71>",
75
+ "<extra_id_72>",
76
+ "<extra_id_73>",
77
+ "<extra_id_74>",
78
+ "<extra_id_75>",
79
+ "<extra_id_76>",
80
+ "<extra_id_77>",
81
+ "<extra_id_78>",
82
+ "<extra_id_79>",
83
+ "<extra_id_80>",
84
+ "<extra_id_81>",
85
+ "<extra_id_82>",
86
+ "<extra_id_83>",
87
+ "<extra_id_84>",
88
+ "<extra_id_85>",
89
+ "<extra_id_86>",
90
+ "<extra_id_87>",
91
+ "<extra_id_88>",
92
+ "<extra_id_89>",
93
+ "<extra_id_90>",
94
+ "<extra_id_91>",
95
+ "<extra_id_92>",
96
+ "<extra_id_93>",
97
+ "<extra_id_94>",
98
+ "<extra_id_95>",
99
+ "<extra_id_96>",
100
+ "<extra_id_97>",
101
+ "<extra_id_98>",
102
+ "<extra_id_99>"
103
+ ],
104
+ "clean_up_tokenization_spaces": true,
105
+ "eos_token": "</s>",
106
+ "extra_ids": 100,
107
+ "model_max_length": 512,
108
+ "pad_token": "<pad>",
109
+ "processor_class": "MusicgenProcessor",
110
+ "tokenizer_class": "T5Tokenizer",
111
+ "unk_token": "<unk>"
112
+ }