pere commited on
Commit
a9cf983
1 Parent(s): e57378e

Commit from model create scripts

Browse files
.gitattributes CHANGED
@@ -25,3 +25,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
25
  *.zip filter=lfs diff=lfs merge=lfs -text
26
  *.zstandard filter=lfs diff=lfs merge=lfs -text
27
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
25
  *.zip filter=lfs diff=lfs merge=lfs -text
26
  *.zstandard filter=lfs diff=lfs merge=lfs -text
27
  *tfevents* filter=lfs diff=lfs merge=lfs -text
28
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
config.gin ADDED
@@ -0,0 +1,152 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ from __gin__ import dynamic_registration
2
+ import __main__ as train_script
3
+ import seqio
4
+ import t5.data.mixtures
5
+ from t5x import adafactor
6
+ from t5x.examples.t5 import network
7
+ from t5x import gin_utils
8
+ from t5x import models
9
+ from t5x import partitioning
10
+ from t5x import trainer
11
+ from t5x import utils
12
+ import tasks
13
+
14
+ # Macros:
15
+ # ==============================================================================
16
+ BATCH_SIZE = 128
17
+ DROPOUT_RATE = 0.0
18
+ INITIAL_CHECKPOINT_PATH = \
19
+ 'gs://nb-t5x-us-central2/norwegian_NCC_plus_English_t5x_xl/checkpoint_1500000'
20
+ LABEL_SMOOTHING = 0.0
21
+ LOSS_NORMALIZING_FACTOR = None
22
+ MIXTURE_OR_TASK_MODULE = None
23
+ MIXTURE_OR_TASK_NAME = 'balanced_bokmaal_nynorsk_span_corruption_stream'
24
+ MODEL = @models.EncoderDecoderModel()
25
+ MODEL_DIR = \
26
+ 'gs://nb-t5x-us-central2/norwegian_NCC_plus_English_pluss200k_balanced_bokmaal_nynorsk_t5x_xl'
27
+ OPTIMIZER = @adafactor.Adafactor()
28
+ RANDOM_SEED = None
29
+ SHUFFLE_TRAIN_EXAMPLES = True
30
+ TASK_FEATURE_LENGTHS = {'inputs': 512, 'targets': 512}
31
+ TRAIN_STEPS = 1700000
32
+ USE_CACHED_TASKS = True
33
+ USE_HARDWARE_RNG = False
34
+ VOCABULARY = @seqio.SentencePieceVocabulary()
35
+ Z_LOSS = 0.0001
36
+
37
+ # Parameters for adafactor.Adafactor:
38
+ # ==============================================================================
39
+ adafactor.Adafactor.decay_rate = 0.8
40
+ adafactor.Adafactor.logical_factor_rules = \
41
+ @adafactor.standard_logical_factor_rules()
42
+ adafactor.Adafactor.step_offset = 0
43
+
44
+ # Parameters for utils.CheckpointConfig:
45
+ # ==============================================================================
46
+ utils.CheckpointConfig.restore = @utils.RestoreCheckpointConfig()
47
+ utils.CheckpointConfig.save = @utils.SaveCheckpointConfig()
48
+
49
+ # Parameters for utils.create_learning_rate_scheduler:
50
+ # ==============================================================================
51
+ utils.create_learning_rate_scheduler.base_learning_rate = 0.5
52
+ utils.create_learning_rate_scheduler.factors = 'constant * rsqrt_decay'
53
+ utils.create_learning_rate_scheduler.warmup_steps = 10000
54
+
55
+ # Parameters for train/utils.DatasetConfig:
56
+ # ==============================================================================
57
+ train/utils.DatasetConfig.batch_size = %BATCH_SIZE
58
+ train/utils.DatasetConfig.mixture_or_task_name = %MIXTURE_OR_TASK_NAME
59
+ train/utils.DatasetConfig.module = %MIXTURE_OR_TASK_MODULE
60
+ train/utils.DatasetConfig.pack = True
61
+ train/utils.DatasetConfig.seed = None
62
+ train/utils.DatasetConfig.shuffle = %SHUFFLE_TRAIN_EXAMPLES
63
+ train/utils.DatasetConfig.split = 'train'
64
+ train/utils.DatasetConfig.task_feature_lengths = %TASK_FEATURE_LENGTHS
65
+ train/utils.DatasetConfig.use_cached = %USE_CACHED_TASKS
66
+
67
+ # Parameters for train_eval/utils.DatasetConfig:
68
+ # ==============================================================================
69
+ train_eval/utils.DatasetConfig.batch_size = %BATCH_SIZE
70
+ train_eval/utils.DatasetConfig.mixture_or_task_name = %MIXTURE_OR_TASK_NAME
71
+ train_eval/utils.DatasetConfig.module = %MIXTURE_OR_TASK_MODULE
72
+ train_eval/utils.DatasetConfig.pack = True
73
+ train_eval/utils.DatasetConfig.seed = 42
74
+ train_eval/utils.DatasetConfig.shuffle = False
75
+ train_eval/utils.DatasetConfig.split = 'validation'
76
+ train_eval/utils.DatasetConfig.task_feature_lengths = %TASK_FEATURE_LENGTHS
77
+ train_eval/utils.DatasetConfig.use_cached = %USE_CACHED_TASKS
78
+
79
+ # Parameters for models.EncoderDecoderModel:
80
+ # ==============================================================================
81
+ models.EncoderDecoderModel.input_vocabulary = %VOCABULARY
82
+ models.EncoderDecoderModel.label_smoothing = %LABEL_SMOOTHING
83
+ models.EncoderDecoderModel.loss_normalizing_factor = %LOSS_NORMALIZING_FACTOR
84
+ models.EncoderDecoderModel.module = @network.Transformer()
85
+ models.EncoderDecoderModel.optimizer_def = %OPTIMIZER
86
+ models.EncoderDecoderModel.output_vocabulary = %VOCABULARY
87
+ models.EncoderDecoderModel.z_loss = %Z_LOSS
88
+
89
+ # Parameters for partitioning.PjitPartitioner:
90
+ # ==============================================================================
91
+ partitioning.PjitPartitioner.logical_axis_rules = \
92
+ @partitioning.standard_logical_axis_rules()
93
+ partitioning.PjitPartitioner.model_parallel_submesh = None
94
+ partitioning.PjitPartitioner.num_partitions = 2
95
+
96
+ # Parameters for utils.RestoreCheckpointConfig:
97
+ # ==============================================================================
98
+ utils.RestoreCheckpointConfig.dtype = 'float32'
99
+ utils.RestoreCheckpointConfig.mode = 'specific'
100
+ utils.RestoreCheckpointConfig.path = %INITIAL_CHECKPOINT_PATH
101
+
102
+ # Parameters for utils.SaveCheckpointConfig:
103
+ # ==============================================================================
104
+ utils.SaveCheckpointConfig.dtype = 'float32'
105
+ utils.SaveCheckpointConfig.keep = 3
106
+ utils.SaveCheckpointConfig.period = 5000
107
+ utils.SaveCheckpointConfig.save_dataset = False
108
+
109
+ # Parameters for seqio.SentencePieceVocabulary:
110
+ # ==============================================================================
111
+ seqio.SentencePieceVocabulary.sentencepiece_model_file = \
112
+ 'gs://t5-data/vocabs/mc4.250000.100extra/sentencepiece.model'
113
+
114
+ # Parameters for network.T5Config:
115
+ # ==============================================================================
116
+ network.T5Config.dropout_rate = %DROPOUT_RATE
117
+ network.T5Config.dtype = 'bfloat16'
118
+ network.T5Config.emb_dim = 2048
119
+ network.T5Config.head_dim = 64
120
+ network.T5Config.logits_via_embedding = False
121
+ network.T5Config.mlp_activations = ('gelu', 'linear')
122
+ network.T5Config.mlp_dim = 5120
123
+ network.T5Config.num_decoder_layers = 24
124
+ network.T5Config.num_encoder_layers = 24
125
+ network.T5Config.num_heads = 32
126
+ network.T5Config.vocab_size = 250112
127
+
128
+ # Parameters for train_script.train:
129
+ # ==============================================================================
130
+ train_script.train.checkpoint_cfg = @utils.CheckpointConfig()
131
+ train_script.train.eval_period = 1000
132
+ train_script.train.eval_steps = 20
133
+ train_script.train.infer_eval_dataset_cfg = None
134
+ train_script.train.model = %MODEL
135
+ train_script.train.model_dir = %MODEL_DIR
136
+ train_script.train.partitioner = @partitioning.PjitPartitioner()
137
+ train_script.train.random_seed = %RANDOM_SEED
138
+ train_script.train.summarize_config_fn = @gin_utils.summarize_gin_config
139
+ train_script.train.total_steps = %TRAIN_STEPS
140
+ train_script.train.train_dataset_cfg = @train/utils.DatasetConfig()
141
+ train_script.train.train_eval_dataset_cfg = @train_eval/utils.DatasetConfig()
142
+ train_script.train.trainer_cls = @trainer.Trainer
143
+ train_script.train.use_hardware_rng = %USE_HARDWARE_RNG
144
+
145
+ # Parameters for trainer.Trainer:
146
+ # ==============================================================================
147
+ trainer.Trainer.learning_rate_fn = @utils.create_learning_rate_scheduler()
148
+ trainer.Trainer.num_microbatches = None
149
+
150
+ # Parameters for network.Transformer:
151
+ # ==============================================================================
152
+ network.Transformer.config = @network.T5Config()
config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/home/patrick/t5/mt5-xl",
3
+ "architectures": [
4
+ "T5ForConditionalGeneration"
5
+ ],
6
+ "d_ff": 5120,
7
+ "d_kv": 64,
8
+ "d_model": 2048,
9
+ "decoder_start_token_id": 0,
10
+ "dropout_rate": 0.1,
11
+ "eos_token_id": 1,
12
+ "feed_forward_proj": "gated-gelu",
13
+ "initializer_factor": 1.0,
14
+ "is_encoder_decoder": true,
15
+ "layer_norm_epsilon": 1e-06,
16
+ "model_type": "t5",
17
+ "num_decoder_layers": 24,
18
+ "num_heads": 32,
19
+ "num_layers": 24,
20
+ "output_past": true,
21
+ "pad_token_id": 0,
22
+ "relative_attention_max_distance": 128,
23
+ "relative_attention_num_buckets": 32,
24
+ "tie_word_embeddings": false,
25
+ "tokenizer_class": "T5Tokenizer",
26
+ "torch_dtype": "float32",
27
+ "transformers_version": "4.19.2",
28
+ "use_cache": true,
29
+ "vocab_size": 250112
30
+ }
flax_model.msgpack ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca44b7e9b54129df79b8aac50022cc0fabe31a88185d22e7964e5463f6f32c37
3
+ size 14970502847
model-info.txt ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model-00001-of-00003.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f0ee79777f4ee858447c3095c2689bab575e67a0ed7d0bd554637afb80ecd17
3
+ size 6679907079
pytorch_model-00002-of-00003.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e680c611fc57b2853a35dd8eca0282efb5b4efaf3536016566410dc20705c88d
3
+ size 8290756867
pytorch_model-00003-of-00003.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c4f14928be592de3270967364aa66120cc73409dc0812e82f509b3a1b915374
3
+ size 2048918251
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,567 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 19068313600
4
+ },
5
+ "weight_map": {
6
+ "decoder.block.0.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00003.bin",
7
+ "decoder.block.0.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00003.bin",
8
+ "decoder.block.0.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00003.bin",
9
+ "decoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "pytorch_model-00002-of-00003.bin",
10
+ "decoder.block.0.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00003.bin",
11
+ "decoder.block.0.layer.0.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
12
+ "decoder.block.0.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00003.bin",
13
+ "decoder.block.0.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00003.bin",
14
+ "decoder.block.0.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00003.bin",
15
+ "decoder.block.0.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00003.bin",
16
+ "decoder.block.0.layer.1.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
17
+ "decoder.block.0.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00003.bin",
18
+ "decoder.block.0.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00003.bin",
19
+ "decoder.block.0.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00003.bin",
20
+ "decoder.block.0.layer.2.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
21
+ "decoder.block.1.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00003.bin",
22
+ "decoder.block.1.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00003.bin",
23
+ "decoder.block.1.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00003.bin",
24
+ "decoder.block.1.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00003.bin",
25
+ "decoder.block.1.layer.0.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
26
+ "decoder.block.1.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00003.bin",
27
+ "decoder.block.1.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00003.bin",
28
+ "decoder.block.1.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00003.bin",
29
+ "decoder.block.1.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00003.bin",
30
+ "decoder.block.1.layer.1.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
31
+ "decoder.block.1.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00003.bin",
32
+ "decoder.block.1.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00003.bin",
33
+ "decoder.block.1.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00003.bin",
34
+ "decoder.block.1.layer.2.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
35
+ "decoder.block.10.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00003.bin",
36
+ "decoder.block.10.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00003.bin",
37
+ "decoder.block.10.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00003.bin",
38
+ "decoder.block.10.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00003.bin",
39
+ "decoder.block.10.layer.0.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
40
+ "decoder.block.10.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00003.bin",
41
+ "decoder.block.10.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00003.bin",
42
+ "decoder.block.10.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00003.bin",
43
+ "decoder.block.10.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00003.bin",
44
+ "decoder.block.10.layer.1.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
45
+ "decoder.block.10.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00003.bin",
46
+ "decoder.block.10.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00003.bin",
47
+ "decoder.block.10.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00003.bin",
48
+ "decoder.block.10.layer.2.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
49
+ "decoder.block.11.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00003.bin",
50
+ "decoder.block.11.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00003.bin",
51
+ "decoder.block.11.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00003.bin",
52
+ "decoder.block.11.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00003.bin",
53
+ "decoder.block.11.layer.0.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
54
+ "decoder.block.11.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00003.bin",
55
+ "decoder.block.11.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00003.bin",
56
+ "decoder.block.11.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00003.bin",
57
+ "decoder.block.11.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00003.bin",
58
+ "decoder.block.11.layer.1.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
59
+ "decoder.block.11.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00003.bin",
60
+ "decoder.block.11.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00003.bin",
61
+ "decoder.block.11.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00003.bin",
62
+ "decoder.block.11.layer.2.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
63
+ "decoder.block.12.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00003.bin",
64
+ "decoder.block.12.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00003.bin",
65
+ "decoder.block.12.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00003.bin",
66
+ "decoder.block.12.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00003.bin",
67
+ "decoder.block.12.layer.0.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
68
+ "decoder.block.12.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00003.bin",
69
+ "decoder.block.12.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00003.bin",
70
+ "decoder.block.12.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00003.bin",
71
+ "decoder.block.12.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00003.bin",
72
+ "decoder.block.12.layer.1.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
73
+ "decoder.block.12.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00003.bin",
74
+ "decoder.block.12.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00003.bin",
75
+ "decoder.block.12.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00003.bin",
76
+ "decoder.block.12.layer.2.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
77
+ "decoder.block.13.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00003.bin",
78
+ "decoder.block.13.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00003.bin",
79
+ "decoder.block.13.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00003.bin",
80
+ "decoder.block.13.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00003.bin",
81
+ "decoder.block.13.layer.0.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
82
+ "decoder.block.13.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00003.bin",
83
+ "decoder.block.13.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00003.bin",
84
+ "decoder.block.13.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00003.bin",
85
+ "decoder.block.13.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00003.bin",
86
+ "decoder.block.13.layer.1.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
87
+ "decoder.block.13.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00003.bin",
88
+ "decoder.block.13.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00003.bin",
89
+ "decoder.block.13.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00003.bin",
90
+ "decoder.block.13.layer.2.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
91
+ "decoder.block.14.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00003.bin",
92
+ "decoder.block.14.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00003.bin",
93
+ "decoder.block.14.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00003.bin",
94
+ "decoder.block.14.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00003.bin",
95
+ "decoder.block.14.layer.0.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
96
+ "decoder.block.14.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00003.bin",
97
+ "decoder.block.14.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00003.bin",
98
+ "decoder.block.14.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00003.bin",
99
+ "decoder.block.14.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00003.bin",
100
+ "decoder.block.14.layer.1.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
101
+ "decoder.block.14.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00003.bin",
102
+ "decoder.block.14.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00003.bin",
103
+ "decoder.block.14.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00003.bin",
104
+ "decoder.block.14.layer.2.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
105
+ "decoder.block.15.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00003.bin",
106
+ "decoder.block.15.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00003.bin",
107
+ "decoder.block.15.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00003.bin",
108
+ "decoder.block.15.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00003.bin",
109
+ "decoder.block.15.layer.0.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
110
+ "decoder.block.15.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00003.bin",
111
+ "decoder.block.15.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00003.bin",
112
+ "decoder.block.15.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00003.bin",
113
+ "decoder.block.15.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00003.bin",
114
+ "decoder.block.15.layer.1.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
115
+ "decoder.block.15.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00003.bin",
116
+ "decoder.block.15.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00003.bin",
117
+ "decoder.block.15.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00003.bin",
118
+ "decoder.block.15.layer.2.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
119
+ "decoder.block.16.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00003.bin",
120
+ "decoder.block.16.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00003.bin",
121
+ "decoder.block.16.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00003.bin",
122
+ "decoder.block.16.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00003.bin",
123
+ "decoder.block.16.layer.0.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
124
+ "decoder.block.16.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00003.bin",
125
+ "decoder.block.16.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00003.bin",
126
+ "decoder.block.16.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00003.bin",
127
+ "decoder.block.16.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00003.bin",
128
+ "decoder.block.16.layer.1.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
129
+ "decoder.block.16.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00003.bin",
130
+ "decoder.block.16.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00003.bin",
131
+ "decoder.block.16.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00003.bin",
132
+ "decoder.block.16.layer.2.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
133
+ "decoder.block.17.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00003.bin",
134
+ "decoder.block.17.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00003.bin",
135
+ "decoder.block.17.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00003.bin",
136
+ "decoder.block.17.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00003.bin",
137
+ "decoder.block.17.layer.0.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
138
+ "decoder.block.17.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00003.bin",
139
+ "decoder.block.17.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00003.bin",
140
+ "decoder.block.17.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00003.bin",
141
+ "decoder.block.17.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00003.bin",
142
+ "decoder.block.17.layer.1.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
143
+ "decoder.block.17.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00003.bin",
144
+ "decoder.block.17.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00003.bin",
145
+ "decoder.block.17.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00003.bin",
146
+ "decoder.block.17.layer.2.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
147
+ "decoder.block.18.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00003.bin",
148
+ "decoder.block.18.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00003.bin",
149
+ "decoder.block.18.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00003.bin",
150
+ "decoder.block.18.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00003.bin",
151
+ "decoder.block.18.layer.0.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
152
+ "decoder.block.18.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00003.bin",
153
+ "decoder.block.18.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00003.bin",
154
+ "decoder.block.18.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00003.bin",
155
+ "decoder.block.18.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00003.bin",
156
+ "decoder.block.18.layer.1.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
157
+ "decoder.block.18.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00003.bin",
158
+ "decoder.block.18.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00003.bin",
159
+ "decoder.block.18.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00003.bin",
160
+ "decoder.block.18.layer.2.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
161
+ "decoder.block.19.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00003.bin",
162
+ "decoder.block.19.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00003.bin",
163
+ "decoder.block.19.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00003.bin",
164
+ "decoder.block.19.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00003.bin",
165
+ "decoder.block.19.layer.0.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
166
+ "decoder.block.19.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00003.bin",
167
+ "decoder.block.19.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00003.bin",
168
+ "decoder.block.19.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00003.bin",
169
+ "decoder.block.19.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00003.bin",
170
+ "decoder.block.19.layer.1.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
171
+ "decoder.block.19.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00003.bin",
172
+ "decoder.block.19.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00003.bin",
173
+ "decoder.block.19.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00003.bin",
174
+ "decoder.block.19.layer.2.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
175
+ "decoder.block.2.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00003.bin",
176
+ "decoder.block.2.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00003.bin",
177
+ "decoder.block.2.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00003.bin",
178
+ "decoder.block.2.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00003.bin",
179
+ "decoder.block.2.layer.0.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
180
+ "decoder.block.2.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00003.bin",
181
+ "decoder.block.2.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00003.bin",
182
+ "decoder.block.2.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00003.bin",
183
+ "decoder.block.2.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00003.bin",
184
+ "decoder.block.2.layer.1.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
185
+ "decoder.block.2.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00003.bin",
186
+ "decoder.block.2.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00003.bin",
187
+ "decoder.block.2.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00003.bin",
188
+ "decoder.block.2.layer.2.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
189
+ "decoder.block.20.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00003.bin",
190
+ "decoder.block.20.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00003.bin",
191
+ "decoder.block.20.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00003.bin",
192
+ "decoder.block.20.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00003.bin",
193
+ "decoder.block.20.layer.0.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
194
+ "decoder.block.20.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00003.bin",
195
+ "decoder.block.20.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00003.bin",
196
+ "decoder.block.20.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00003.bin",
197
+ "decoder.block.20.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00003.bin",
198
+ "decoder.block.20.layer.1.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
199
+ "decoder.block.20.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00003.bin",
200
+ "decoder.block.20.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00003.bin",
201
+ "decoder.block.20.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00003.bin",
202
+ "decoder.block.20.layer.2.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
203
+ "decoder.block.21.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00003.bin",
204
+ "decoder.block.21.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00003.bin",
205
+ "decoder.block.21.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00003.bin",
206
+ "decoder.block.21.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00003.bin",
207
+ "decoder.block.21.layer.0.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
208
+ "decoder.block.21.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00003.bin",
209
+ "decoder.block.21.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00003.bin",
210
+ "decoder.block.21.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00003.bin",
211
+ "decoder.block.21.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00003.bin",
212
+ "decoder.block.21.layer.1.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
213
+ "decoder.block.21.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00003.bin",
214
+ "decoder.block.21.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00003.bin",
215
+ "decoder.block.21.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00003.bin",
216
+ "decoder.block.21.layer.2.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
217
+ "decoder.block.22.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00003.bin",
218
+ "decoder.block.22.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00003.bin",
219
+ "decoder.block.22.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00003.bin",
220
+ "decoder.block.22.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00003.bin",
221
+ "decoder.block.22.layer.0.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
222
+ "decoder.block.22.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00003.bin",
223
+ "decoder.block.22.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00003.bin",
224
+ "decoder.block.22.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00003.bin",
225
+ "decoder.block.22.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00003.bin",
226
+ "decoder.block.22.layer.1.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
227
+ "decoder.block.22.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00003.bin",
228
+ "decoder.block.22.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00003.bin",
229
+ "decoder.block.22.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00003.bin",
230
+ "decoder.block.22.layer.2.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
231
+ "decoder.block.23.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00003.bin",
232
+ "decoder.block.23.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00003.bin",
233
+ "decoder.block.23.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00003.bin",
234
+ "decoder.block.23.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00003.bin",
235
+ "decoder.block.23.layer.0.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
236
+ "decoder.block.23.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00003.bin",
237
+ "decoder.block.23.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00003.bin",
238
+ "decoder.block.23.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00003.bin",
239
+ "decoder.block.23.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00003.bin",
240
+ "decoder.block.23.layer.1.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
241
+ "decoder.block.23.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00003.bin",
242
+ "decoder.block.23.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00003.bin",
243
+ "decoder.block.23.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00003.bin",
244
+ "decoder.block.23.layer.2.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
245
+ "decoder.block.3.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00003.bin",
246
+ "decoder.block.3.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00003.bin",
247
+ "decoder.block.3.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00003.bin",
248
+ "decoder.block.3.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00003.bin",
249
+ "decoder.block.3.layer.0.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
250
+ "decoder.block.3.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00003.bin",
251
+ "decoder.block.3.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00003.bin",
252
+ "decoder.block.3.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00003.bin",
253
+ "decoder.block.3.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00003.bin",
254
+ "decoder.block.3.layer.1.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
255
+ "decoder.block.3.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00003.bin",
256
+ "decoder.block.3.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00003.bin",
257
+ "decoder.block.3.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00003.bin",
258
+ "decoder.block.3.layer.2.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
259
+ "decoder.block.4.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00003.bin",
260
+ "decoder.block.4.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00003.bin",
261
+ "decoder.block.4.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00003.bin",
262
+ "decoder.block.4.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00003.bin",
263
+ "decoder.block.4.layer.0.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
264
+ "decoder.block.4.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00003.bin",
265
+ "decoder.block.4.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00003.bin",
266
+ "decoder.block.4.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00003.bin",
267
+ "decoder.block.4.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00003.bin",
268
+ "decoder.block.4.layer.1.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
269
+ "decoder.block.4.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00003.bin",
270
+ "decoder.block.4.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00003.bin",
271
+ "decoder.block.4.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00003.bin",
272
+ "decoder.block.4.layer.2.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
273
+ "decoder.block.5.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00003.bin",
274
+ "decoder.block.5.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00003.bin",
275
+ "decoder.block.5.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00003.bin",
276
+ "decoder.block.5.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00003.bin",
277
+ "decoder.block.5.layer.0.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
278
+ "decoder.block.5.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00003.bin",
279
+ "decoder.block.5.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00003.bin",
280
+ "decoder.block.5.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00003.bin",
281
+ "decoder.block.5.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00003.bin",
282
+ "decoder.block.5.layer.1.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
283
+ "decoder.block.5.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00003.bin",
284
+ "decoder.block.5.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00003.bin",
285
+ "decoder.block.5.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00003.bin",
286
+ "decoder.block.5.layer.2.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
287
+ "decoder.block.6.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00003.bin",
288
+ "decoder.block.6.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00003.bin",
289
+ "decoder.block.6.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00003.bin",
290
+ "decoder.block.6.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00003.bin",
291
+ "decoder.block.6.layer.0.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
292
+ "decoder.block.6.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00003.bin",
293
+ "decoder.block.6.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00003.bin",
294
+ "decoder.block.6.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00003.bin",
295
+ "decoder.block.6.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00003.bin",
296
+ "decoder.block.6.layer.1.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
297
+ "decoder.block.6.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00003.bin",
298
+ "decoder.block.6.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00003.bin",
299
+ "decoder.block.6.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00003.bin",
300
+ "decoder.block.6.layer.2.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
301
+ "decoder.block.7.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00003.bin",
302
+ "decoder.block.7.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00003.bin",
303
+ "decoder.block.7.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00003.bin",
304
+ "decoder.block.7.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00003.bin",
305
+ "decoder.block.7.layer.0.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
306
+ "decoder.block.7.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00003.bin",
307
+ "decoder.block.7.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00003.bin",
308
+ "decoder.block.7.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00003.bin",
309
+ "decoder.block.7.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00003.bin",
310
+ "decoder.block.7.layer.1.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
311
+ "decoder.block.7.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00003.bin",
312
+ "decoder.block.7.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00003.bin",
313
+ "decoder.block.7.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00003.bin",
314
+ "decoder.block.7.layer.2.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
315
+ "decoder.block.8.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00003.bin",
316
+ "decoder.block.8.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00003.bin",
317
+ "decoder.block.8.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00003.bin",
318
+ "decoder.block.8.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00003.bin",
319
+ "decoder.block.8.layer.0.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
320
+ "decoder.block.8.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00003.bin",
321
+ "decoder.block.8.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00003.bin",
322
+ "decoder.block.8.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00003.bin",
323
+ "decoder.block.8.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00003.bin",
324
+ "decoder.block.8.layer.1.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
325
+ "decoder.block.8.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00003.bin",
326
+ "decoder.block.8.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00003.bin",
327
+ "decoder.block.8.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00003.bin",
328
+ "decoder.block.8.layer.2.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
329
+ "decoder.block.9.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00003.bin",
330
+ "decoder.block.9.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00003.bin",
331
+ "decoder.block.9.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00003.bin",
332
+ "decoder.block.9.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00003.bin",
333
+ "decoder.block.9.layer.0.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
334
+ "decoder.block.9.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00003.bin",
335
+ "decoder.block.9.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00003.bin",
336
+ "decoder.block.9.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00003.bin",
337
+ "decoder.block.9.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00003.bin",
338
+ "decoder.block.9.layer.1.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
339
+ "decoder.block.9.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00003.bin",
340
+ "decoder.block.9.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00003.bin",
341
+ "decoder.block.9.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00003.bin",
342
+ "decoder.block.9.layer.2.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
343
+ "decoder.embed_tokens.weight": "pytorch_model-00002-of-00003.bin",
344
+ "decoder.final_layer_norm.weight": "pytorch_model-00002-of-00003.bin",
345
+ "encoder.block.0.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00003.bin",
346
+ "encoder.block.0.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00003.bin",
347
+ "encoder.block.0.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00003.bin",
348
+ "encoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "pytorch_model-00001-of-00003.bin",
349
+ "encoder.block.0.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00003.bin",
350
+ "encoder.block.0.layer.0.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
351
+ "encoder.block.0.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00003.bin",
352
+ "encoder.block.0.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00003.bin",
353
+ "encoder.block.0.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00003.bin",
354
+ "encoder.block.0.layer.1.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
355
+ "encoder.block.1.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00003.bin",
356
+ "encoder.block.1.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00003.bin",
357
+ "encoder.block.1.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00003.bin",
358
+ "encoder.block.1.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00003.bin",
359
+ "encoder.block.1.layer.0.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
360
+ "encoder.block.1.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00003.bin",
361
+ "encoder.block.1.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00003.bin",
362
+ "encoder.block.1.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00003.bin",
363
+ "encoder.block.1.layer.1.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
364
+ "encoder.block.10.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00003.bin",
365
+ "encoder.block.10.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00003.bin",
366
+ "encoder.block.10.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00003.bin",
367
+ "encoder.block.10.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00003.bin",
368
+ "encoder.block.10.layer.0.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
369
+ "encoder.block.10.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00003.bin",
370
+ "encoder.block.10.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00003.bin",
371
+ "encoder.block.10.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00003.bin",
372
+ "encoder.block.10.layer.1.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
373
+ "encoder.block.11.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00003.bin",
374
+ "encoder.block.11.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00003.bin",
375
+ "encoder.block.11.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00003.bin",
376
+ "encoder.block.11.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00003.bin",
377
+ "encoder.block.11.layer.0.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
378
+ "encoder.block.11.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00003.bin",
379
+ "encoder.block.11.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00003.bin",
380
+ "encoder.block.11.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00003.bin",
381
+ "encoder.block.11.layer.1.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
382
+ "encoder.block.12.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00003.bin",
383
+ "encoder.block.12.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00003.bin",
384
+ "encoder.block.12.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00003.bin",
385
+ "encoder.block.12.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00003.bin",
386
+ "encoder.block.12.layer.0.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
387
+ "encoder.block.12.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00003.bin",
388
+ "encoder.block.12.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00003.bin",
389
+ "encoder.block.12.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00003.bin",
390
+ "encoder.block.12.layer.1.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
391
+ "encoder.block.13.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00003.bin",
392
+ "encoder.block.13.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00003.bin",
393
+ "encoder.block.13.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00003.bin",
394
+ "encoder.block.13.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00003.bin",
395
+ "encoder.block.13.layer.0.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
396
+ "encoder.block.13.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00003.bin",
397
+ "encoder.block.13.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00003.bin",
398
+ "encoder.block.13.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00003.bin",
399
+ "encoder.block.13.layer.1.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
400
+ "encoder.block.14.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00003.bin",
401
+ "encoder.block.14.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00003.bin",
402
+ "encoder.block.14.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00003.bin",
403
+ "encoder.block.14.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00003.bin",
404
+ "encoder.block.14.layer.0.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
405
+ "encoder.block.14.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00003.bin",
406
+ "encoder.block.14.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00003.bin",
407
+ "encoder.block.14.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00003.bin",
408
+ "encoder.block.14.layer.1.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
409
+ "encoder.block.15.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00003.bin",
410
+ "encoder.block.15.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00003.bin",
411
+ "encoder.block.15.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00003.bin",
412
+ "encoder.block.15.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00003.bin",
413
+ "encoder.block.15.layer.0.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
414
+ "encoder.block.15.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00003.bin",
415
+ "encoder.block.15.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00003.bin",
416
+ "encoder.block.15.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00003.bin",
417
+ "encoder.block.15.layer.1.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
418
+ "encoder.block.16.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00003.bin",
419
+ "encoder.block.16.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00003.bin",
420
+ "encoder.block.16.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00003.bin",
421
+ "encoder.block.16.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00003.bin",
422
+ "encoder.block.16.layer.0.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
423
+ "encoder.block.16.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00003.bin",
424
+ "encoder.block.16.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00003.bin",
425
+ "encoder.block.16.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00003.bin",
426
+ "encoder.block.16.layer.1.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
427
+ "encoder.block.17.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00003.bin",
428
+ "encoder.block.17.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00003.bin",
429
+ "encoder.block.17.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00003.bin",
430
+ "encoder.block.17.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00003.bin",
431
+ "encoder.block.17.layer.0.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
432
+ "encoder.block.17.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00003.bin",
433
+ "encoder.block.17.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00003.bin",
434
+ "encoder.block.17.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00003.bin",
435
+ "encoder.block.17.layer.1.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
436
+ "encoder.block.18.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00003.bin",
437
+ "encoder.block.18.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00003.bin",
438
+ "encoder.block.18.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00003.bin",
439
+ "encoder.block.18.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00003.bin",
440
+ "encoder.block.18.layer.0.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
441
+ "encoder.block.18.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00003.bin",
442
+ "encoder.block.18.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00003.bin",
443
+ "encoder.block.18.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00003.bin",
444
+ "encoder.block.18.layer.1.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
445
+ "encoder.block.19.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00003.bin",
446
+ "encoder.block.19.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00003.bin",
447
+ "encoder.block.19.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00003.bin",
448
+ "encoder.block.19.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00003.bin",
449
+ "encoder.block.19.layer.0.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
450
+ "encoder.block.19.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00003.bin",
451
+ "encoder.block.19.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00003.bin",
452
+ "encoder.block.19.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00003.bin",
453
+ "encoder.block.19.layer.1.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
454
+ "encoder.block.2.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00003.bin",
455
+ "encoder.block.2.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00003.bin",
456
+ "encoder.block.2.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00003.bin",
457
+ "encoder.block.2.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00003.bin",
458
+ "encoder.block.2.layer.0.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
459
+ "encoder.block.2.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00003.bin",
460
+ "encoder.block.2.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00003.bin",
461
+ "encoder.block.2.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00003.bin",
462
+ "encoder.block.2.layer.1.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
463
+ "encoder.block.20.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00003.bin",
464
+ "encoder.block.20.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00003.bin",
465
+ "encoder.block.20.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00003.bin",
466
+ "encoder.block.20.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00003.bin",
467
+ "encoder.block.20.layer.0.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
468
+ "encoder.block.20.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00003.bin",
469
+ "encoder.block.20.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00003.bin",
470
+ "encoder.block.20.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00003.bin",
471
+ "encoder.block.20.layer.1.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
472
+ "encoder.block.21.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00003.bin",
473
+ "encoder.block.21.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00003.bin",
474
+ "encoder.block.21.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00003.bin",
475
+ "encoder.block.21.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00003.bin",
476
+ "encoder.block.21.layer.0.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
477
+ "encoder.block.21.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00003.bin",
478
+ "encoder.block.21.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00003.bin",
479
+ "encoder.block.21.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00003.bin",
480
+ "encoder.block.21.layer.1.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
481
+ "encoder.block.22.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00003.bin",
482
+ "encoder.block.22.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00003.bin",
483
+ "encoder.block.22.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00003.bin",
484
+ "encoder.block.22.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00003.bin",
485
+ "encoder.block.22.layer.0.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
486
+ "encoder.block.22.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00003.bin",
487
+ "encoder.block.22.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00003.bin",
488
+ "encoder.block.22.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00003.bin",
489
+ "encoder.block.22.layer.1.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
490
+ "encoder.block.23.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00003.bin",
491
+ "encoder.block.23.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00003.bin",
492
+ "encoder.block.23.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00003.bin",
493
+ "encoder.block.23.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00003.bin",
494
+ "encoder.block.23.layer.0.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
495
+ "encoder.block.23.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00003.bin",
496
+ "encoder.block.23.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00003.bin",
497
+ "encoder.block.23.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00003.bin",
498
+ "encoder.block.23.layer.1.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
499
+ "encoder.block.3.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00003.bin",
500
+ "encoder.block.3.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00003.bin",
501
+ "encoder.block.3.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00003.bin",
502
+ "encoder.block.3.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00003.bin",
503
+ "encoder.block.3.layer.0.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
504
+ "encoder.block.3.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00003.bin",
505
+ "encoder.block.3.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00003.bin",
506
+ "encoder.block.3.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00003.bin",
507
+ "encoder.block.3.layer.1.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
508
+ "encoder.block.4.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00003.bin",
509
+ "encoder.block.4.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00003.bin",
510
+ "encoder.block.4.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00003.bin",
511
+ "encoder.block.4.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00003.bin",
512
+ "encoder.block.4.layer.0.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
513
+ "encoder.block.4.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00003.bin",
514
+ "encoder.block.4.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00003.bin",
515
+ "encoder.block.4.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00003.bin",
516
+ "encoder.block.4.layer.1.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
517
+ "encoder.block.5.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00003.bin",
518
+ "encoder.block.5.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00003.bin",
519
+ "encoder.block.5.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00003.bin",
520
+ "encoder.block.5.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00003.bin",
521
+ "encoder.block.5.layer.0.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
522
+ "encoder.block.5.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00003.bin",
523
+ "encoder.block.5.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00003.bin",
524
+ "encoder.block.5.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00003.bin",
525
+ "encoder.block.5.layer.1.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
526
+ "encoder.block.6.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00003.bin",
527
+ "encoder.block.6.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00003.bin",
528
+ "encoder.block.6.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00003.bin",
529
+ "encoder.block.6.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00003.bin",
530
+ "encoder.block.6.layer.0.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
531
+ "encoder.block.6.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00003.bin",
532
+ "encoder.block.6.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00003.bin",
533
+ "encoder.block.6.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00003.bin",
534
+ "encoder.block.6.layer.1.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
535
+ "encoder.block.7.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00003.bin",
536
+ "encoder.block.7.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00003.bin",
537
+ "encoder.block.7.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00003.bin",
538
+ "encoder.block.7.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00003.bin",
539
+ "encoder.block.7.layer.0.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
540
+ "encoder.block.7.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00003.bin",
541
+ "encoder.block.7.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00003.bin",
542
+ "encoder.block.7.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00003.bin",
543
+ "encoder.block.7.layer.1.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
544
+ "encoder.block.8.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00003.bin",
545
+ "encoder.block.8.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00003.bin",
546
+ "encoder.block.8.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00003.bin",
547
+ "encoder.block.8.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00003.bin",
548
+ "encoder.block.8.layer.0.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
549
+ "encoder.block.8.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00003.bin",
550
+ "encoder.block.8.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00003.bin",
551
+ "encoder.block.8.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00003.bin",
552
+ "encoder.block.8.layer.1.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
553
+ "encoder.block.9.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00003.bin",
554
+ "encoder.block.9.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00003.bin",
555
+ "encoder.block.9.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00003.bin",
556
+ "encoder.block.9.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00003.bin",
557
+ "encoder.block.9.layer.0.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
558
+ "encoder.block.9.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00003.bin",
559
+ "encoder.block.9.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00003.bin",
560
+ "encoder.block.9.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00003.bin",
561
+ "encoder.block.9.layer.1.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
562
+ "encoder.embed_tokens.weight": "pytorch_model-00001-of-00003.bin",
563
+ "encoder.final_layer_norm.weight": "pytorch_model-00001-of-00003.bin",
564
+ "lm_head.weight": "pytorch_model-00003-of-00003.bin",
565
+ "shared.weight": "pytorch_model-00001-of-00003.bin"
566
+ }
567
+ }
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>"}
spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef78f86560d809067d12bac6c09f19a462cb3af3f54d2b8acbba26e1433125d6
3
+ size 4309802
tf_model.h5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13edf9346263c231557abbd4b42fd847571a957f938e4f48b2d23ec2f1c58acc
3
+ size 9760
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93c3578052e1605d8332eb961bc08d72e246071974e4cc54aa6991826b802aa5
3
+ size 16330369
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "extra_ids": 0, "additional_special_tokens": null, "special_tokens_map_file": "/home/patrick/.cache/torch/transformers/685ac0ca8568ec593a48b61b0a3c272beee9bc194a3c7241d15dcadb5f875e53.f76030f3ec1b96a8199b2593390c610e76ca8028ef3d24680000619ffb646276", "name_or_path": "/home/perk/models/t5_xl_NCC_modern", "sp_model_kwargs": {}, "tokenizer_class": "T5Tokenizer"}
train/events.out.tfevents.1651040807.t1v-n-9b156434-w-1.573572.0.v2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7918bc06d983a968be290cb12d6957354c510e2d4c1258656059fcce218a8c95
3
+ size 47751
train/events.out.tfevents.1651177075.t1v-n-d23fe85f-w-1.80622.0.v2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3b7fed7087476f61e964be33ebe53f0f1f6dba3bb75afd45bece756d019fba7
3
+ size 261771
train/events.out.tfevents.1651387101.t1v-n-03bb65eb-w-3.65968.0.v2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c071b93dd042dcca01d4118916b824bd9c2dc6f7b3b2320f84ee17de5f08c68d
3
+ size 13854
training_eval/balanced_bokmaal_nynorsk_span_corruption_stream/events.out.tfevents.1651040808.t1v-n-9b156434-w-1.573572.1.v2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7514c04af58a110a200e1a4bbdd5bf660406edac704f46d6e69bce4c5ac48422
3
+ size 36666
training_eval/balanced_bokmaal_nynorsk_span_corruption_stream/events.out.tfevents.1651177075.t1v-n-d23fe85f-w-1.80622.1.v2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc8322f5924a8b296631935c6323b48614f2707518bc2cb4ec84e04fc5e6d191
3
+ size 225891
training_eval/balanced_bokmaal_nynorsk_span_corruption_stream/events.out.tfevents.1651387101.t1v-n-03bb65eb-w-3.65968.1.v2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:febd15daee69558f2819c566d3dad9091d7866b2459b6c8fca60f0e98ba04e79
3
+ size 6651