t

.gitattributes

@@ -25,3 +25,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zstandard filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

config.gin

@@ -0,0 +1,151 @@
+from __gin__ import dynamic_registration
+import __main__ as train_script
+import seqio
+import t5.data.mixtures
+from t5x import adafactor
+from t5x.examples.t5 import network
+from t5x import gin_utils
+from t5x import models
+from t5x import partitioning
+from t5x import trainer
+from t5x import utils
+import tasks
+
+# Macros:
+# ==============================================================================
+BATCH_SIZE = 48
+DROPOUT_RATE = 0.0
+INITIAL_CHECKPOINT_PATH = \
+    'gs://t5-data/pretrained_models/t5x/mt5_xxl/checkpoint_1000000'
+LABEL_SMOOTHING = 0.0
+LOSS_NORMALIZING_FACTOR = None
+MIXTURE_OR_TASK_MODULE = None
+MIXTURE_OR_TASK_NAME = 'ncc_english_span_corruption_stream'
+MODEL = @models.EncoderDecoderModel()
+MODEL_DIR = 'gs://nb-t5x-us-central2/norwegian_NCC_plus_English_t5x_xxl'
+OPTIMIZER = @adafactor.Adafactor()
+RANDOM_SEED = None
+SHUFFLE_TRAIN_EXAMPLES = True
+TASK_FEATURE_LENGTHS = {'inputs': 512, 'targets': 512}
+TRAIN_STEPS = 1500000
+USE_CACHED_TASKS = True
+USE_HARDWARE_RNG = False
+VOCABULARY = @seqio.SentencePieceVocabulary()
+Z_LOSS = 0.0001
+
+# Parameters for adafactor.Adafactor:
+# ==============================================================================
+adafactor.Adafactor.decay_rate = 0.8
+adafactor.Adafactor.logical_factor_rules = \
+    @adafactor.standard_logical_factor_rules()
+adafactor.Adafactor.step_offset = 0
+
+# Parameters for utils.CheckpointConfig:
+# ==============================================================================
+utils.CheckpointConfig.restore = @utils.RestoreCheckpointConfig()
+utils.CheckpointConfig.save = @utils.SaveCheckpointConfig()
+
+# Parameters for utils.create_learning_rate_scheduler:
+# ==============================================================================
+utils.create_learning_rate_scheduler.base_learning_rate = 0.5
+utils.create_learning_rate_scheduler.factors = 'constant * rsqrt_decay'
+utils.create_learning_rate_scheduler.warmup_steps = 10000
+
+# Parameters for train/utils.DatasetConfig:
+# ==============================================================================
+train/utils.DatasetConfig.batch_size = %BATCH_SIZE
+train/utils.DatasetConfig.mixture_or_task_name = %MIXTURE_OR_TASK_NAME
+train/utils.DatasetConfig.module = %MIXTURE_OR_TASK_MODULE
+train/utils.DatasetConfig.pack = True
+train/utils.DatasetConfig.seed = None
+train/utils.DatasetConfig.shuffle = %SHUFFLE_TRAIN_EXAMPLES
+train/utils.DatasetConfig.split = 'train'
+train/utils.DatasetConfig.task_feature_lengths = %TASK_FEATURE_LENGTHS
+train/utils.DatasetConfig.use_cached = %USE_CACHED_TASKS
+
+# Parameters for train_eval/utils.DatasetConfig:
+# ==============================================================================
+train_eval/utils.DatasetConfig.batch_size = %BATCH_SIZE
+train_eval/utils.DatasetConfig.mixture_or_task_name = %MIXTURE_OR_TASK_NAME
+train_eval/utils.DatasetConfig.module = %MIXTURE_OR_TASK_MODULE
+train_eval/utils.DatasetConfig.pack = True
+train_eval/utils.DatasetConfig.seed = 42
+train_eval/utils.DatasetConfig.shuffle = False
+train_eval/utils.DatasetConfig.split = 'validation'
+train_eval/utils.DatasetConfig.task_feature_lengths = %TASK_FEATURE_LENGTHS
+train_eval/utils.DatasetConfig.use_cached = %USE_CACHED_TASKS
+
+# Parameters for models.EncoderDecoderModel:
+# ==============================================================================
+models.EncoderDecoderModel.input_vocabulary = %VOCABULARY
+models.EncoderDecoderModel.label_smoothing = %LABEL_SMOOTHING
+models.EncoderDecoderModel.loss_normalizing_factor = %LOSS_NORMALIZING_FACTOR
+models.EncoderDecoderModel.module = @network.Transformer()
+models.EncoderDecoderModel.optimizer_def = %OPTIMIZER
+models.EncoderDecoderModel.output_vocabulary = %VOCABULARY
+models.EncoderDecoderModel.z_loss = %Z_LOSS
+
+# Parameters for partitioning.PjitPartitioner:
+# ==============================================================================
+partitioning.PjitPartitioner.logical_axis_rules = \
+    @partitioning.standard_logical_axis_rules()
+partitioning.PjitPartitioner.model_parallel_submesh = None
+partitioning.PjitPartitioner.num_partitions = 4
+
+# Parameters for utils.RestoreCheckpointConfig:
+# ==============================================================================
+utils.RestoreCheckpointConfig.dtype = 'float32'
+utils.RestoreCheckpointConfig.mode = 'specific'
+utils.RestoreCheckpointConfig.path = %INITIAL_CHECKPOINT_PATH
+
+# Parameters for utils.SaveCheckpointConfig:
+# ==============================================================================
+utils.SaveCheckpointConfig.dtype = 'float32'
+utils.SaveCheckpointConfig.keep = 3
+utils.SaveCheckpointConfig.period = 20000
+utils.SaveCheckpointConfig.save_dataset = False
+
+# Parameters for seqio.SentencePieceVocabulary:
+# ==============================================================================
+seqio.SentencePieceVocabulary.sentencepiece_model_file = \
+    'gs://t5-data/vocabs/mc4.250000.100extra/sentencepiece.model'
+
+# Parameters for network.T5Config:
+# ==============================================================================
+network.T5Config.dropout_rate = %DROPOUT_RATE
+network.T5Config.dtype = 'bfloat16'
+network.T5Config.emb_dim = 4096
+network.T5Config.head_dim = 64
+network.T5Config.logits_via_embedding = False
+network.T5Config.mlp_activations = ('gelu', 'linear')
+network.T5Config.mlp_dim = 10240
+network.T5Config.num_decoder_layers = 24
+network.T5Config.num_encoder_layers = 24
+network.T5Config.num_heads = 64
+network.T5Config.vocab_size = 250112
+
+# Parameters for train_script.train:
+# ==============================================================================
+train_script.train.checkpoint_cfg = @utils.CheckpointConfig()
+train_script.train.eval_period = 1000
+train_script.train.eval_steps = 20
+train_script.train.infer_eval_dataset_cfg = None
+train_script.train.model = %MODEL
+train_script.train.model_dir = %MODEL_DIR
+train_script.train.partitioner = @partitioning.PjitPartitioner()
+train_script.train.random_seed = %RANDOM_SEED
+train_script.train.summarize_config_fn = @gin_utils.summarize_gin_config
+train_script.train.total_steps = %TRAIN_STEPS
+train_script.train.train_dataset_cfg = @train/utils.DatasetConfig()
+train_script.train.train_eval_dataset_cfg = @train_eval/utils.DatasetConfig()
+train_script.train.trainer_cls = @trainer.Trainer
+train_script.train.use_hardware_rng = %USE_HARDWARE_RNG
+
+# Parameters for trainer.Trainer:
+# ==============================================================================
+trainer.Trainer.learning_rate_fn = @utils.create_learning_rate_scheduler()
+trainer.Trainer.num_microbatches = None
+
+# Parameters for network.Transformer:
+# ==============================================================================
+network.Transformer.config = @network.T5Config()

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "/home/patrick/t5/mt5-xxl",
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "d_ff": 10240,
+  "d_kv": 64,
+  "d_model": 4096,
+  "decoder_start_token_id": 0,
+  "dropout_rate": 0.1,
+  "eos_token_id": 1,
+  "feed_forward_proj": "gated-gelu",
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "layer_norm_epsilon": 1e-06,
+  "model_type": "t5",
+  "num_decoder_layers": 24,
+  "num_heads": 64,
+  "num_layers": 24,
+  "output_past": true,
+  "pad_token_id": 0,
+  "relative_attention_max_distance": 128,
+  "relative_attention_num_buckets": 32,
+  "tie_word_embeddings": false,
+  "tokenizer_class": "T5Tokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.19.2",
+  "use_cache": true,
+  "vocab_size": 250112
+}

pytorch_model-00001-of-00007.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:deaf5768e5a691c5bbc56f2e7386d558719508193d11e105991d3d0895767fe2
+size 5842746828

pytorch_model-00002-of-00007.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fde66349777520cbe4284682de15f0b79c9ef4b0d54930ef8ec585fdc58d4b34
+size 9966130321

pytorch_model-00003-of-00007.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e733af5af5da4abb2a6adb5ca86927104fa50282f28c7c44403ea7da89abba15
+size 6811886805

pytorch_model-00004-of-00007.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94d76e728e726059cfd3fe83b915e0540e2907edd71f1e071da37d8fdc249c4a
+size 9835956831

pytorch_model-00005-of-00007.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7cdc25be15cb97dba4ac67c7a9ba16a0fbfa976c917776b50cff404c91349b00
+size 9999722997

pytorch_model-00006-of-00007.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e5e069da05c8216498b60330139077a8d8c94e75de401d13a6a5c2340d2fb51
+size 9227968551

pytorch_model-00007-of-00007.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14556f7ea1062743c6bc2fa37c2534c55dd2d105d33f8f2fbe621dea68b7387b
+size 4097835755

pytorch_model.bin.index.json

@@ -0,0 +1,567 @@
+{
+  "metadata": {
+    "total_size": 59879899136
+  },
+  "weight_map": {
+    "decoder.block.0.layer.0.SelfAttention.k.weight": "pytorch_model-00004-of-00007.bin",
+    "decoder.block.0.layer.0.SelfAttention.o.weight": "pytorch_model-00004-of-00007.bin",
+    "decoder.block.0.layer.0.SelfAttention.q.weight": "pytorch_model-00004-of-00007.bin",
+    "decoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "pytorch_model-00004-of-00007.bin",
+    "decoder.block.0.layer.0.SelfAttention.v.weight": "pytorch_model-00004-of-00007.bin",
+    "decoder.block.0.layer.0.layer_norm.weight": "pytorch_model-00004-of-00007.bin",
+    "decoder.block.0.layer.1.EncDecAttention.k.weight": "pytorch_model-00004-of-00007.bin",
+    "decoder.block.0.layer.1.EncDecAttention.o.weight": "pytorch_model-00004-of-00007.bin",
+    "decoder.block.0.layer.1.EncDecAttention.q.weight": "pytorch_model-00004-of-00007.bin",
+    "decoder.block.0.layer.1.EncDecAttention.v.weight": "pytorch_model-00004-of-00007.bin",
+    "decoder.block.0.layer.1.layer_norm.weight": "pytorch_model-00004-of-00007.bin",
+    "decoder.block.0.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00004-of-00007.bin",
+    "decoder.block.0.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00004-of-00007.bin",
+    "decoder.block.0.layer.2.DenseReluDense.wo.weight": "pytorch_model-00004-of-00007.bin",
+    "decoder.block.0.layer.2.layer_norm.weight": "pytorch_model-00004-of-00007.bin",
+    "decoder.block.1.layer.0.SelfAttention.k.weight": "pytorch_model-00004-of-00007.bin",
+    "decoder.block.1.layer.0.SelfAttention.o.weight": "pytorch_model-00004-of-00007.bin",
+    "decoder.block.1.layer.0.SelfAttention.q.weight": "pytorch_model-00004-of-00007.bin",
+    "decoder.block.1.layer.0.SelfAttention.v.weight": "pytorch_model-00004-of-00007.bin",
+    "decoder.block.1.layer.0.layer_norm.weight": "pytorch_model-00004-of-00007.bin",
+    "decoder.block.1.layer.1.EncDecAttention.k.weight": "pytorch_model-00004-of-00007.bin",
+    "decoder.block.1.layer.1.EncDecAttention.o.weight": "pytorch_model-00004-of-00007.bin",
+    "decoder.block.1.layer.1.EncDecAttention.q.weight": "pytorch_model-00004-of-00007.bin",
+    "decoder.block.1.layer.1.EncDecAttention.v.weight": "pytorch_model-00004-of-00007.bin",
+    "decoder.block.1.layer.1.layer_norm.weight": "pytorch_model-00004-of-00007.bin",
+    "decoder.block.1.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00004-of-00007.bin",
+    "decoder.block.1.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00004-of-00007.bin",
+    "decoder.block.1.layer.2.DenseReluDense.wo.weight": "pytorch_model-00004-of-00007.bin",
+    "decoder.block.1.layer.2.layer_norm.weight": "pytorch_model-00004-of-00007.bin",
+    "decoder.block.10.layer.0.SelfAttention.k.weight": "pytorch_model-00005-of-00007.bin",
+    "decoder.block.10.layer.0.SelfAttention.o.weight": "pytorch_model-00005-of-00007.bin",
+    "decoder.block.10.layer.0.SelfAttention.q.weight": "pytorch_model-00005-of-00007.bin",
+    "decoder.block.10.layer.0.SelfAttention.v.weight": "pytorch_model-00005-of-00007.bin",
+    "decoder.block.10.layer.0.layer_norm.weight": "pytorch_model-00005-of-00007.bin",
+    "decoder.block.10.layer.1.EncDecAttention.k.weight": "pytorch_model-00005-of-00007.bin",
+    "decoder.block.10.layer.1.EncDecAttention.o.weight": "pytorch_model-00005-of-00007.bin",
+    "decoder.block.10.layer.1.EncDecAttention.q.weight": "pytorch_model-00005-of-00007.bin",
+    "decoder.block.10.layer.1.EncDecAttention.v.weight": "pytorch_model-00005-of-00007.bin",
+    "decoder.block.10.layer.1.layer_norm.weight": "pytorch_model-00005-of-00007.bin",
+    "decoder.block.10.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00005-of-00007.bin",
+    "decoder.block.10.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00005-of-00007.bin",
+    "decoder.block.10.layer.2.DenseReluDense.wo.weight": "pytorch_model-00005-of-00007.bin",
+    "decoder.block.10.layer.2.layer_norm.weight": "pytorch_model-00005-of-00007.bin",
+    "decoder.block.11.layer.0.SelfAttention.k.weight": "pytorch_model-00005-of-00007.bin",
+    "decoder.block.11.layer.0.SelfAttention.o.weight": "pytorch_model-00005-of-00007.bin",
+    "decoder.block.11.layer.0.SelfAttention.q.weight": "pytorch_model-00005-of-00007.bin",
+    "decoder.block.11.layer.0.SelfAttention.v.weight": "pytorch_model-00005-of-00007.bin",
+    "decoder.block.11.layer.0.layer_norm.weight": "pytorch_model-00005-of-00007.bin",
+    "decoder.block.11.layer.1.EncDecAttention.k.weight": "pytorch_model-00005-of-00007.bin",
+    "decoder.block.11.layer.1.EncDecAttention.o.weight": "pytorch_model-00005-of-00007.bin",
+    "decoder.block.11.layer.1.EncDecAttention.q.weight": "pytorch_model-00005-of-00007.bin",
+    "decoder.block.11.layer.1.EncDecAttention.v.weight": "pytorch_model-00005-of-00007.bin",
+    "decoder.block.11.layer.1.layer_norm.weight": "pytorch_model-00005-of-00007.bin",
+    "decoder.block.11.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00005-of-00007.bin",
+    "decoder.block.11.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00005-of-00007.bin",
+    "decoder.block.11.layer.2.DenseReluDense.wo.weight": "pytorch_model-00005-of-00007.bin",
+    "decoder.block.11.layer.2.layer_norm.weight": "pytorch_model-00005-of-00007.bin",
+    "decoder.block.12.layer.0.SelfAttention.k.weight": "pytorch_model-00005-of-00007.bin",
+    "decoder.block.12.layer.0.SelfAttention.o.weight": "pytorch_model-00005-of-00007.bin",
+    "decoder.block.12.layer.0.SelfAttention.q.weight": "pytorch_model-00005-of-00007.bin",
+    "decoder.block.12.layer.0.SelfAttention.v.weight": "pytorch_model-00005-of-00007.bin",
+    "decoder.block.12.layer.0.layer_norm.weight": "pytorch_model-00005-of-00007.bin",
+    "decoder.block.12.layer.1.EncDecAttention.k.weight": "pytorch_model-00005-of-00007.bin",
+    "decoder.block.12.layer.1.EncDecAttention.o.weight": "pytorch_model-00005-of-00007.bin",
+    "decoder.block.12.layer.1.EncDecAttention.q.weight": "pytorch_model-00005-of-00007.bin",
+    "decoder.block.12.layer.1.EncDecAttention.v.weight": "pytorch_model-00005-of-00007.bin",
+    "decoder.block.12.layer.1.layer_norm.weight": "pytorch_model-00005-of-00007.bin",
+    "decoder.block.12.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00005-of-00007.bin",
+    "decoder.block.12.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00005-of-00007.bin",
+    "decoder.block.12.layer.2.DenseReluDense.wo.weight": "pytorch_model-00005-of-00007.bin",
+    "decoder.block.12.layer.2.layer_norm.weight": "pytorch_model-00005-of-00007.bin",
+    "decoder.block.13.layer.0.SelfAttention.k.weight": "pytorch_model-00005-of-00007.bin",
+    "decoder.block.13.layer.0.SelfAttention.o.weight": "pytorch_model-00005-of-00007.bin",
+    "decoder.block.13.layer.0.SelfAttention.q.weight": "pytorch_model-00005-of-00007.bin",
+    "decoder.block.13.layer.0.SelfAttention.v.weight": "pytorch_model-00005-of-00007.bin",
+    "decoder.block.13.layer.0.layer_norm.weight": "pytorch_model-00005-of-00007.bin",
+    "decoder.block.13.layer.1.EncDecAttention.k.weight": "pytorch_model-00005-of-00007.bin",
+    "decoder.block.13.layer.1.EncDecAttention.o.weight": "pytorch_model-00005-of-00007.bin",
+    "decoder.block.13.layer.1.EncDecAttention.q.weight": "pytorch_model-00005-of-00007.bin",
+    "decoder.block.13.layer.1.EncDecAttention.v.weight": "pytorch_model-00005-of-00007.bin",
+    "decoder.block.13.layer.1.layer_norm.weight": "pytorch_model-00005-of-00007.bin",
+    "decoder.block.13.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00005-of-00007.bin",
+    "decoder.block.13.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00005-of-00007.bin",
+    "decoder.block.13.layer.2.DenseReluDense.wo.weight": "pytorch_model-00005-of-00007.bin",
+    "decoder.block.13.layer.2.layer_norm.weight": "pytorch_model-00005-of-00007.bin",
+    "decoder.block.14.layer.0.SelfAttention.k.weight": "pytorch_model-00005-of-00007.bin",
+    "decoder.block.14.layer.0.SelfAttention.o.weight": "pytorch_model-00005-of-00007.bin",
+    "decoder.block.14.layer.0.SelfAttention.q.weight": "pytorch_model-00005-of-00007.bin",
+    "decoder.block.14.layer.0.SelfAttention.v.weight": "pytorch_model-00005-of-00007.bin",
+    "decoder.block.14.layer.0.layer_norm.weight": "pytorch_model-00005-of-00007.bin",
+    "decoder.block.14.layer.1.EncDecAttention.k.weight": "pytorch_model-00005-of-00007.bin",
+    "decoder.block.14.layer.1.EncDecAttention.o.weight": "pytorch_model-00005-of-00007.bin",
+    "decoder.block.14.layer.1.EncDecAttention.q.weight": "pytorch_model-00005-of-00007.bin",
+    "decoder.block.14.layer.1.EncDecAttention.v.weight": "pytorch_model-00005-of-00007.bin",
+    "decoder.block.14.layer.1.layer_norm.weight": "pytorch_model-00005-of-00007.bin",
+    "decoder.block.14.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00005-of-00007.bin",
+    "decoder.block.14.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00005-of-00007.bin",
+    "decoder.block.14.layer.2.DenseReluDense.wo.weight": "pytorch_model-00005-of-00007.bin",
+    "decoder.block.14.layer.2.layer_norm.weight": "pytorch_model-00005-of-00007.bin",
+    "decoder.block.15.layer.0.SelfAttention.k.weight": "pytorch_model-00005-of-00007.bin",
+    "decoder.block.15.layer.0.SelfAttention.o.weight": "pytorch_model-00006-of-00007.bin",
+    "decoder.block.15.layer.0.SelfAttention.q.weight": "pytorch_model-00005-of-00007.bin",
+    "decoder.block.15.layer.0.SelfAttention.v.weight": "pytorch_model-00006-of-00007.bin",
+    "decoder.block.15.layer.0.layer_norm.weight": "pytorch_model-00006-of-00007.bin",
+    "decoder.block.15.layer.1.EncDecAttention.k.weight": "pytorch_model-00006-of-00007.bin",
+    "decoder.block.15.layer.1.EncDecAttention.o.weight": "pytorch_model-00006-of-00007.bin",
+    "decoder.block.15.layer.1.EncDecAttention.q.weight": "pytorch_model-00006-of-00007.bin",
+    "decoder.block.15.layer.1.EncDecAttention.v.weight": "pytorch_model-00006-of-00007.bin",
+    "decoder.block.15.layer.1.layer_norm.weight": "pytorch_model-00006-of-00007.bin",
+    "decoder.block.15.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00006-of-00007.bin",
+    "decoder.block.15.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00006-of-00007.bin",
+    "decoder.block.15.layer.2.DenseReluDense.wo.weight": "pytorch_model-00006-of-00007.bin",
+    "decoder.block.15.layer.2.layer_norm.weight": "pytorch_model-00006-of-00007.bin",
+    "decoder.block.16.layer.0.SelfAttention.k.weight": "pytorch_model-00006-of-00007.bin",
+    "decoder.block.16.layer.0.SelfAttention.o.weight": "pytorch_model-00006-of-00007.bin",
+    "decoder.block.16.layer.0.SelfAttention.q.weight": "pytorch_model-00006-of-00007.bin",
+    "decoder.block.16.layer.0.SelfAttention.v.weight": "pytorch_model-00006-of-00007.bin",
+    "decoder.block.16.layer.0.layer_norm.weight": "pytorch_model-00006-of-00007.bin",
+    "decoder.block.16.layer.1.EncDecAttention.k.weight": "pytorch_model-00006-of-00007.bin",
+    "decoder.block.16.layer.1.EncDecAttention.o.weight": "pytorch_model-00006-of-00007.bin",
+    "decoder.block.16.layer.1.EncDecAttention.q.weight": "pytorch_model-00006-of-00007.bin",
+    "decoder.block.16.layer.1.EncDecAttention.v.weight": "pytorch_model-00006-of-00007.bin",
+    "decoder.block.16.layer.1.layer_norm.weight": "pytorch_model-00006-of-00007.bin",
+    "decoder.block.16.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00006-of-00007.bin",
+    "decoder.block.16.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00006-of-00007.bin",
+    "decoder.block.16.layer.2.DenseReluDense.wo.weight": "pytorch_model-00006-of-00007.bin",
+    "decoder.block.16.layer.2.layer_norm.weight": "pytorch_model-00006-of-00007.bin",
+    "decoder.block.17.layer.0.SelfAttention.k.weight": "pytorch_model-00006-of-00007.bin",
+    "decoder.block.17.layer.0.SelfAttention.o.weight": "pytorch_model-00006-of-00007.bin",
+    "decoder.block.17.layer.0.SelfAttention.q.weight": "pytorch_model-00006-of-00007.bin",
+    "decoder.block.17.layer.0.SelfAttention.v.weight": "pytorch_model-00006-of-00007.bin",
+    "decoder.block.17.layer.0.layer_norm.weight": "pytorch_model-00006-of-00007.bin",
+    "decoder.block.17.layer.1.EncDecAttention.k.weight": "pytorch_model-00006-of-00007.bin",
+    "decoder.block.17.layer.1.EncDecAttention.o.weight": "pytorch_model-00006-of-00007.bin",
+    "decoder.block.17.layer.1.EncDecAttention.q.weight": "pytorch_model-00006-of-00007.bin",
+    "decoder.block.17.layer.1.EncDecAttention.v.weight": "pytorch_model-00006-of-00007.bin",
+    "decoder.block.17.layer.1.layer_norm.weight": "pytorch_model-00006-of-00007.bin",
+    "decoder.block.17.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00006-of-00007.bin",
+    "decoder.block.17.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00006-of-00007.bin",
+    "decoder.block.17.layer.2.DenseReluDense.wo.weight": "pytorch_model-00006-of-00007.bin",
+    "decoder.block.17.layer.2.layer_norm.weight": "pytorch_model-00006-of-00007.bin",
+    "decoder.block.18.layer.0.SelfAttention.k.weight": "pytorch_model-00006-of-00007.bin",
+    "decoder.block.18.layer.0.SelfAttention.o.weight": "pytorch_model-00006-of-00007.bin",
+    "decoder.block.18.layer.0.SelfAttention.q.weight": "pytorch_model-00006-of-00007.bin",
+    "decoder.block.18.layer.0.SelfAttention.v.weight": "pytorch_model-00006-of-00007.bin",
+    "decoder.block.18.layer.0.layer_norm.weight": "pytorch_model-00006-of-00007.bin",
+    "decoder.block.18.layer.1.EncDecAttention.k.weight": "pytorch_model-00006-of-00007.bin",
+    "decoder.block.18.layer.1.EncDecAttention.o.weight": "pytorch_model-00006-of-00007.bin",
+    "decoder.block.18.layer.1.EncDecAttention.q.weight": "pytorch_model-00006-of-00007.bin",
+    "decoder.block.18.layer.1.EncDecAttention.v.weight": "pytorch_model-00006-of-00007.bin",
+    "decoder.block.18.layer.1.layer_norm.weight": "pytorch_model-00006-of-00007.bin",
+    "decoder.block.18.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00006-of-00007.bin",
+    "decoder.block.18.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00006-of-00007.bin",
+    "decoder.block.18.layer.2.DenseReluDense.wo.weight": "pytorch_model-00006-of-00007.bin",
+    "decoder.block.18.layer.2.layer_norm.weight": "pytorch_model-00006-of-00007.bin",
+    "decoder.block.19.layer.0.SelfAttention.k.weight": "pytorch_model-00006-of-00007.bin",
+    "decoder.block.19.layer.0.SelfAttention.o.weight": "pytorch_model-00006-of-00007.bin",
+    "decoder.block.19.layer.0.SelfAttention.q.weight": "pytorch_model-00006-of-00007.bin",
+    "decoder.block.19.layer.0.SelfAttention.v.weight": "pytorch_model-00006-of-00007.bin",
+    "decoder.block.19.layer.0.layer_norm.weight": "pytorch_model-00006-of-00007.bin",
+    "decoder.block.19.layer.1.EncDecAttention.k.weight": "pytorch_model-00006-of-00007.bin",
+    "decoder.block.19.layer.1.EncDecAttention.o.weight": "pytorch_model-00006-of-00007.bin",
+    "decoder.block.19.layer.1.EncDecAttention.q.weight": "pytorch_model-00006-of-00007.bin",
+    "decoder.block.19.layer.1.EncDecAttention.v.weight": "pytorch_model-00006-of-00007.bin",
+    "decoder.block.19.layer.1.layer_norm.weight": "pytorch_model-00006-of-00007.bin",
+    "decoder.block.19.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00006-of-00007.bin",
+    "decoder.block.19.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00006-of-00007.bin",
+    "decoder.block.19.layer.2.DenseReluDense.wo.weight": "pytorch_model-00006-of-00007.bin",
+    "decoder.block.19.layer.2.layer_norm.weight": "pytorch_model-00006-of-00007.bin",
+    "decoder.block.2.layer.0.SelfAttention.k.weight": "pytorch_model-00004-of-00007.bin",
+    "decoder.block.2.layer.0.SelfAttention.o.weight": "pytorch_model-00004-of-00007.bin",
+    "decoder.block.2.layer.0.SelfAttention.q.weight": "pytorch_model-00004-of-00007.bin",
+    "decoder.block.2.layer.0.SelfAttention.v.weight": "pytorch_model-00004-of-00007.bin",
+    "decoder.block.2.layer.0.layer_norm.weight": "pytorch_model-00004-of-00007.bin",
+    "decoder.block.2.layer.1.EncDecAttention.k.weight": "pytorch_model-00004-of-00007.bin",
+    "decoder.block.2.layer.1.EncDecAttention.o.weight": "pytorch_model-00004-of-00007.bin",
+    "decoder.block.2.layer.1.EncDecAttention.q.weight": "pytorch_model-00004-of-00007.bin",
+    "decoder.block.2.layer.1.EncDecAttention.v.weight": "pytorch_model-00004-of-00007.bin",
+    "decoder.block.2.layer.1.layer_norm.weight": "pytorch_model-00004-of-00007.bin",
+    "decoder.block.2.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00004-of-00007.bin",
+    "decoder.block.2.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00004-of-00007.bin",
+    "decoder.block.2.layer.2.DenseReluDense.wo.weight": "pytorch_model-00004-of-00007.bin",
+    "decoder.block.2.layer.2.layer_norm.weight": "pytorch_model-00004-of-00007.bin",
+    "decoder.block.20.layer.0.SelfAttention.k.weight": "pytorch_model-00006-of-00007.bin",
+    "decoder.block.20.layer.0.SelfAttention.o.weight": "pytorch_model-00006-of-00007.bin",
+    "decoder.block.20.layer.0.SelfAttention.q.weight": "pytorch_model-00006-of-00007.bin",
+    "decoder.block.20.layer.0.SelfAttention.v.weight": "pytorch_model-00006-of-00007.bin",
+    "decoder.block.20.layer.0.layer_norm.weight": "pytorch_model-00006-of-00007.bin",
+    "decoder.block.20.layer.1.EncDecAttention.k.weight": "pytorch_model-00006-of-00007.bin",
+    "decoder.block.20.layer.1.EncDecAttention.o.weight": "pytorch_model-00006-of-00007.bin",
+    "decoder.block.20.layer.1.EncDecAttention.q.weight": "pytorch_model-00006-of-00007.bin",
+    "decoder.block.20.layer.1.EncDecAttention.v.weight": "pytorch_model-00006-of-00007.bin",
+    "decoder.block.20.layer.1.layer_norm.weight": "pytorch_model-00006-of-00007.bin",
+    "decoder.block.20.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00006-of-00007.bin",
+    "decoder.block.20.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00006-of-00007.bin",
+    "decoder.block.20.layer.2.DenseReluDense.wo.weight": "pytorch_model-00006-of-00007.bin",
+    "decoder.block.20.layer.2.layer_norm.weight": "pytorch_model-00006-of-00007.bin",
+    "decoder.block.21.layer.0.SelfAttention.k.weight": "pytorch_model-00006-of-00007.bin",
+    "decoder.block.21.layer.0.SelfAttention.o.weight": "pytorch_model-00006-of-00007.bin",
+    "decoder.block.21.layer.0.SelfAttention.q.weight": "pytorch_model-00006-of-00007.bin",
+    "decoder.block.21.layer.0.SelfAttention.v.weight": "pytorch_model-00006-of-00007.bin",
+    "decoder.block.21.layer.0.layer_norm.weight": "pytorch_model-00006-of-00007.bin",
+    "decoder.block.21.layer.1.EncDecAttention.k.weight": "pytorch_model-00006-of-00007.bin",
+    "decoder.block.21.layer.1.EncDecAttention.o.weight": "pytorch_model-00006-of-00007.bin",
+    "decoder.block.21.layer.1.EncDecAttention.q.weight": "pytorch_model-00006-of-00007.bin",
+    "decoder.block.21.layer.1.EncDecAttention.v.weight": "pytorch_model-00006-of-00007.bin",
+    "decoder.block.21.layer.1.layer_norm.weight": "pytorch_model-00006-of-00007.bin",
+    "decoder.block.21.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00006-of-00007.bin",
+    "decoder.block.21.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00006-of-00007.bin",
+    "decoder.block.21.layer.2.DenseReluDense.wo.weight": "pytorch_model-00006-of-00007.bin",
+    "decoder.block.21.layer.2.layer_norm.weight": "pytorch_model-00006-of-00007.bin",
+    "decoder.block.22.layer.0.SelfAttention.k.weight": "pytorch_model-00006-of-00007.bin",
+    "decoder.block.22.layer.0.SelfAttention.o.weight": "pytorch_model-00006-of-00007.bin",
+    "decoder.block.22.layer.0.SelfAttention.q.weight": "pytorch_model-00006-of-00007.bin",
+    "decoder.block.22.layer.0.SelfAttention.v.weight": "pytorch_model-00006-of-00007.bin",
+    "decoder.block.22.layer.0.layer_norm.weight": "pytorch_model-00006-of-00007.bin",
+    "decoder.block.22.layer.1.EncDecAttention.k.weight": "pytorch_model-00006-of-00007.bin",
+    "decoder.block.22.layer.1.EncDecAttention.o.weight": "pytorch_model-00006-of-00007.bin",
+    "decoder.block.22.layer.1.EncDecAttention.q.weight": "pytorch_model-00006-of-00007.bin",
+    "decoder.block.22.layer.1.EncDecAttention.v.weight": "pytorch_model-00006-of-00007.bin",
+    "decoder.block.22.layer.1.layer_norm.weight": "pytorch_model-00006-of-00007.bin",
+    "decoder.block.22.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00006-of-00007.bin",
+    "decoder.block.22.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00006-of-00007.bin",
+    "decoder.block.22.layer.2.DenseReluDense.wo.weight": "pytorch_model-00006-of-00007.bin",
+    "decoder.block.22.layer.2.layer_norm.weight": "pytorch_model-00006-of-00007.bin",
+    "decoder.block.23.layer.0.SelfAttention.k.weight": "pytorch_model-00006-of-00007.bin",
+    "decoder.block.23.layer.0.SelfAttention.o.weight": "pytorch_model-00006-of-00007.bin",
+    "decoder.block.23.layer.0.SelfAttention.q.weight": "pytorch_model-00006-of-00007.bin",
+    "decoder.block.23.layer.0.SelfAttention.v.weight": "pytorch_model-00006-of-00007.bin",
+    "decoder.block.23.layer.0.layer_norm.weight": "pytorch_model-00006-of-00007.bin",
+    "decoder.block.23.layer.1.EncDecAttention.k.weight": "pytorch_model-00006-of-00007.bin",
+    "decoder.block.23.layer.1.EncDecAttention.o.weight": "pytorch_model-00006-of-00007.bin",
+    "decoder.block.23.layer.1.EncDecAttention.q.weight": "pytorch_model-00006-of-00007.bin",
+    "decoder.block.23.layer.1.EncDecAttention.v.weight": "pytorch_model-00006-of-00007.bin",
+    "decoder.block.23.layer.1.layer_norm.weight": "pytorch_model-00006-of-00007.bin",
+    "decoder.block.23.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00006-of-00007.bin",
+    "decoder.block.23.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00006-of-00007.bin",
+    "decoder.block.23.layer.2.DenseReluDense.wo.weight": "pytorch_model-00006-of-00007.bin",
+    "decoder.block.23.layer.2.layer_norm.weight": "pytorch_model-00006-of-00007.bin",
+    "decoder.block.3.layer.0.SelfAttention.k.weight": "pytorch_model-00004-of-00007.bin",
+    "decoder.block.3.layer.0.SelfAttention.o.weight": "pytorch_model-00004-of-00007.bin",
+    "decoder.block.3.layer.0.SelfAttention.q.weight": "pytorch_model-00004-of-00007.bin",
+    "decoder.block.3.layer.0.SelfAttention.v.weight": "pytorch_model-00004-of-00007.bin",
+    "decoder.block.3.layer.0.layer_norm.weight": "pytorch_model-00004-of-00007.bin",
+    "decoder.block.3.layer.1.EncDecAttention.k.weight": "pytorch_model-00004-of-00007.bin",
+    "decoder.block.3.layer.1.EncDecAttention.o.weight": "pytorch_model-00004-of-00007.bin",
+    "decoder.block.3.layer.1.EncDecAttention.q.weight": "pytorch_model-00004-of-00007.bin",
+    "decoder.block.3.layer.1.EncDecAttention.v.weight": "pytorch_model-00004-of-00007.bin",
+    "decoder.block.3.layer.1.layer_norm.weight": "pytorch_model-00004-of-00007.bin",
+    "decoder.block.3.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00004-of-00007.bin",
+    "decoder.block.3.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00004-of-00007.bin",
+    "decoder.block.3.layer.2.DenseReluDense.wo.weight": "pytorch_model-00004-of-00007.bin",
+    "decoder.block.3.layer.2.layer_norm.weight": "pytorch_model-00004-of-00007.bin",
+    "decoder.block.4.layer.0.SelfAttention.k.weight": "pytorch_model-00004-of-00007.bin",
+    "decoder.block.4.layer.0.SelfAttention.o.weight": "pytorch_model-00004-of-00007.bin",
+    "decoder.block.4.layer.0.SelfAttention.q.weight": "pytorch_model-00004-of-00007.bin",
+    "decoder.block.4.layer.0.SelfAttention.v.weight": "pytorch_model-00004-of-00007.bin",
+    "decoder.block.4.layer.0.layer_norm.weight": "pytorch_model-00004-of-00007.bin",
+    "decoder.block.4.layer.1.EncDecAttention.k.weight": "pytorch_model-00004-of-00007.bin",
+    "decoder.block.4.layer.1.EncDecAttention.o.weight": "pytorch_model-00004-of-00007.bin",
+    "decoder.block.4.layer.1.EncDecAttention.q.weight": "pytorch_model-00004-of-00007.bin",
+    "decoder.block.4.layer.1.EncDecAttention.v.weight": "pytorch_model-00004-of-00007.bin",
+    "decoder.block.4.layer.1.layer_norm.weight": "pytorch_model-00004-of-00007.bin",
+    "decoder.block.4.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00004-of-00007.bin",
+    "decoder.block.4.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00004-of-00007.bin",
+    "decoder.block.4.layer.2.DenseReluDense.wo.weight": "pytorch_model-00004-of-00007.bin",
+    "decoder.block.4.layer.2.layer_norm.weight": "pytorch_model-00004-of-00007.bin",
+    "decoder.block.5.layer.0.SelfAttention.k.weight": "pytorch_model-00004-of-00007.bin",
+    "decoder.block.5.layer.0.SelfAttention.o.weight": "pytorch_model-00004-of-00007.bin",
+    "decoder.block.5.layer.0.SelfAttention.q.weight": "pytorch_model-00004-of-00007.bin",
+    "decoder.block.5.layer.0.SelfAttention.v.weight": "pytorch_model-00004-of-00007.bin",
+    "decoder.block.5.layer.0.layer_norm.weight": "pytorch_model-00004-of-00007.bin",
+    "decoder.block.5.layer.1.EncDecAttention.k.weight": "pytorch_model-00004-of-00007.bin",
+    "decoder.block.5.layer.1.EncDecAttention.o.weight": "pytorch_model-00004-of-00007.bin",
+    "decoder.block.5.layer.1.EncDecAttention.q.weight": "pytorch_model-00004-of-00007.bin",
+    "decoder.block.5.layer.1.EncDecAttention.v.weight": "pytorch_model-00004-of-00007.bin",
+    "decoder.block.5.layer.1.layer_norm.weight": "pytorch_model-00004-of-00007.bin",
+    "decoder.block.5.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00005-of-00007.bin",
+    "decoder.block.5.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00005-of-00007.bin",
+    "decoder.block.5.layer.2.DenseReluDense.wo.weight": "pytorch_model-00005-of-00007.bin",
+    "decoder.block.5.layer.2.layer_norm.weight": "pytorch_model-00005-of-00007.bin",
+    "decoder.block.6.layer.0.SelfAttention.k.weight": "pytorch_model-00005-of-00007.bin",
+    "decoder.block.6.layer.0.SelfAttention.o.weight": "pytorch_model-00005-of-00007.bin",
+    "decoder.block.6.layer.0.SelfAttention.q.weight": "pytorch_model-00005-of-00007.bin",
+    "decoder.block.6.layer.0.SelfAttention.v.weight": "pytorch_model-00005-of-00007.bin",
+    "decoder.block.6.layer.0.layer_norm.weight": "pytorch_model-00005-of-00007.bin",
+    "decoder.block.6.layer.1.EncDecAttention.k.weight": "pytorch_model-00005-of-00007.bin",
+    "decoder.block.6.layer.1.EncDecAttention.o.weight": "pytorch_model-00005-of-00007.bin",
+    "decoder.block.6.layer.1.EncDecAttention.q.weight": "pytorch_model-00005-of-00007.bin",
+    "decoder.block.6.layer.1.EncDecAttention.v.weight": "pytorch_model-00005-of-00007.bin",
+    "decoder.block.6.layer.1.layer_norm.weight": "pytorch_model-00005-of-00007.bin",
+    "decoder.block.6.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00005-of-00007.bin",
+    "decoder.block.6.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00005-of-00007.bin",
+    "decoder.block.6.layer.2.DenseReluDense.wo.weight": "pytorch_model-00005-of-00007.bin",
+    "decoder.block.6.layer.2.layer_norm.weight": "pytorch_model-00005-of-00007.bin",
+    "decoder.block.7.layer.0.SelfAttention.k.weight": "pytorch_model-00005-of-00007.bin",
+    "decoder.block.7.layer.0.SelfAttention.o.weight": "pytorch_model-00005-of-00007.bin",
+    "decoder.block.7.layer.0.SelfAttention.q.weight": "pytorch_model-00005-of-00007.bin",
+    "decoder.block.7.layer.0.SelfAttention.v.weight": "pytorch_model-00005-of-00007.bin",
+    "decoder.block.7.layer.0.layer_norm.weight": "pytorch_model-00005-of-00007.bin",
+    "decoder.block.7.layer.1.EncDecAttention.k.weight": "pytorch_model-00005-of-00007.bin",
+    "decoder.block.7.layer.1.EncDecAttention.o.weight": "pytorch_model-00005-of-00007.bin",
+    "decoder.block.7.layer.1.EncDecAttention.q.weight": "pytorch_model-00005-of-00007.bin",
+    "decoder.block.7.layer.1.EncDecAttention.v.weight": "pytorch_model-00005-of-00007.bin",
+    "decoder.block.7.layer.1.layer_norm.weight": "pytorch_model-00005-of-00007.bin",
+    "decoder.block.7.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00005-of-00007.bin",
+    "decoder.block.7.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00005-of-00007.bin",
+    "decoder.block.7.layer.2.DenseReluDense.wo.weight": "pytorch_model-00005-of-00007.bin",
+    "decoder.block.7.layer.2.layer_norm.weight": "pytorch_model-00005-of-00007.bin",
+    "decoder.block.8.layer.0.SelfAttention.k.weight": "pytorch_model-00005-of-00007.bin",
+    "decoder.block.8.layer.0.SelfAttention.o.weight": "pytorch_model-00005-of-00007.bin",
+    "decoder.block.8.layer.0.SelfAttention.q.weight": "pytorch_model-00005-of-00007.bin",
+    "decoder.block.8.layer.0.SelfAttention.v.weight": "pytorch_model-00005-of-00007.bin",
+    "decoder.block.8.layer.0.layer_norm.weight": "pytorch_model-00005-of-00007.bin",
+    "decoder.block.8.layer.1.EncDecAttention.k.weight": "pytorch_model-00005-of-00007.bin",
+    "decoder.block.8.layer.1.EncDecAttention.o.weight": "pytorch_model-00005-of-00007.bin",
+    "decoder.block.8.layer.1.EncDecAttention.q.weight": "pytorch_model-00005-of-00007.bin",
+    "decoder.block.8.layer.1.EncDecAttention.v.weight": "pytorch_model-00005-of-00007.bin",
+    "decoder.block.8.layer.1.layer_norm.weight": "pytorch_model-00005-of-00007.bin",
+    "decoder.block.8.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00005-of-00007.bin",
+    "decoder.block.8.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00005-of-00007.bin",
+    "decoder.block.8.layer.2.DenseReluDense.wo.weight": "pytorch_model-00005-of-00007.bin",
+    "decoder.block.8.layer.2.layer_norm.weight": "pytorch_model-00005-of-00007.bin",
+    "decoder.block.9.layer.0.SelfAttention.k.weight": "pytorch_model-00005-of-00007.bin",
+    "decoder.block.9.layer.0.SelfAttention.o.weight": "pytorch_model-00005-of-00007.bin",
+    "decoder.block.9.layer.0.SelfAttention.q.weight": "pytorch_model-00005-of-00007.bin",
+    "decoder.block.9.layer.0.SelfAttention.v.weight": "pytorch_model-00005-of-00007.bin",
+    "decoder.block.9.layer.0.layer_norm.weight": "pytorch_model-00005-of-00007.bin",
+    "decoder.block.9.layer.1.EncDecAttention.k.weight": "pytorch_model-00005-of-00007.bin",
+    "decoder.block.9.layer.1.EncDecAttention.o.weight": "pytorch_model-00005-of-00007.bin",
+    "decoder.block.9.layer.1.EncDecAttention.q.weight": "pytorch_model-00005-of-00007.bin",
+    "decoder.block.9.layer.1.EncDecAttention.v.weight": "pytorch_model-00005-of-00007.bin",
+    "decoder.block.9.layer.1.layer_norm.weight": "pytorch_model-00005-of-00007.bin",
+    "decoder.block.9.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00005-of-00007.bin",
+    "decoder.block.9.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00005-of-00007.bin",
+    "decoder.block.9.layer.2.DenseReluDense.wo.weight": "pytorch_model-00005-of-00007.bin",
+    "decoder.block.9.layer.2.layer_norm.weight": "pytorch_model-00005-of-00007.bin",
+    "decoder.embed_tokens.weight": "pytorch_model-00004-of-00007.bin",
+    "decoder.final_layer_norm.weight": "pytorch_model-00006-of-00007.bin",
+    "encoder.block.0.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00007.bin",
+    "encoder.block.0.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00007.bin",
+    "encoder.block.0.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00007.bin",
+    "encoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "pytorch_model-00001-of-00007.bin",
+    "encoder.block.0.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00007.bin",
+    "encoder.block.0.layer.0.layer_norm.weight": "pytorch_model-00001-of-00007.bin",
+    "encoder.block.0.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00007.bin",
+    "encoder.block.0.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00007.bin",
+    "encoder.block.0.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00007.bin",
+    "encoder.block.0.layer.1.layer_norm.weight": "pytorch_model-00001-of-00007.bin",
+    "encoder.block.1.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00007.bin",
+    "encoder.block.1.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00007.bin",
+    "encoder.block.1.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00007.bin",
+    "encoder.block.1.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00007.bin",
+    "encoder.block.1.layer.0.layer_norm.weight": "pytorch_model-00001-of-00007.bin",
+    "encoder.block.1.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00007.bin",
+    "encoder.block.1.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00007.bin",
+    "encoder.block.1.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00007.bin",
+    "encoder.block.1.layer.1.layer_norm.weight": "pytorch_model-00001-of-00007.bin",
+    "encoder.block.10.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00007.bin",
+    "encoder.block.10.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00007.bin",
+    "encoder.block.10.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00007.bin",
+    "encoder.block.10.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00007.bin",
+    "encoder.block.10.layer.0.layer_norm.weight": "pytorch_model-00002-of-00007.bin",
+    "encoder.block.10.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00007.bin",
+    "encoder.block.10.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00007.bin",
+    "encoder.block.10.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00007.bin",
+    "encoder.block.10.layer.1.layer_norm.weight": "pytorch_model-00002-of-00007.bin",
+    "encoder.block.11.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00007.bin",
+    "encoder.block.11.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00007.bin",
+    "encoder.block.11.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00007.bin",
+    "encoder.block.11.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00007.bin",
+    "encoder.block.11.layer.0.layer_norm.weight": "pytorch_model-00002-of-00007.bin",
+    "encoder.block.11.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00007.bin",
+    "encoder.block.11.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00007.bin",
+    "encoder.block.11.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00007.bin",
+    "encoder.block.11.layer.1.layer_norm.weight": "pytorch_model-00002-of-00007.bin",
+    "encoder.block.12.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00007.bin",
+    "encoder.block.12.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00007.bin",
+    "encoder.block.12.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00007.bin",
+    "encoder.block.12.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00007.bin",
+    "encoder.block.12.layer.0.layer_norm.weight": "pytorch_model-00002-of-00007.bin",
+    "encoder.block.12.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00007.bin",
+    "encoder.block.12.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00007.bin",
+    "encoder.block.12.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00007.bin",
+    "encoder.block.12.layer.1.layer_norm.weight": "pytorch_model-00002-of-00007.bin",
+    "encoder.block.13.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00007.bin",
+    "encoder.block.13.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00007.bin",
+    "encoder.block.13.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00007.bin",
+    "encoder.block.13.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00007.bin",
+    "encoder.block.13.layer.0.layer_norm.weight": "pytorch_model-00002-of-00007.bin",
+    "encoder.block.13.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00007.bin",
+    "encoder.block.13.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00007.bin",
+    "encoder.block.13.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00007.bin",
+    "encoder.block.13.layer.1.layer_norm.weight": "pytorch_model-00002-of-00007.bin",
+    "encoder.block.14.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00007.bin",
+    "encoder.block.14.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00007.bin",
+    "encoder.block.14.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00007.bin",
+    "encoder.block.14.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00007.bin",
+    "encoder.block.14.layer.0.layer_norm.weight": "pytorch_model-00002-of-00007.bin",
+    "encoder.block.14.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00007.bin",
+    "encoder.block.14.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00007.bin",
+    "encoder.block.14.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00007.bin",
+    "encoder.block.14.layer.1.layer_norm.weight": "pytorch_model-00002-of-00007.bin",
+    "encoder.block.15.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00007.bin",
+    "encoder.block.15.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00007.bin",
+    "encoder.block.15.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00007.bin",
+    "encoder.block.15.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00007.bin",
+    "encoder.block.15.layer.0.layer_norm.weight": "pytorch_model-00003-of-00007.bin",
+    "encoder.block.15.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00007.bin",
+    "encoder.block.15.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00007.bin",
+    "encoder.block.15.layer.1.DenseReluDense.wo.weight": "pytorch_model-00003-of-00007.bin",
+    "encoder.block.15.layer.1.layer_norm.weight": "pytorch_model-00003-of-00007.bin",
+    "encoder.block.16.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00007.bin",
+    "encoder.block.16.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00007.bin",
+    "encoder.block.16.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00007.bin",
+    "encoder.block.16.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00007.bin",
+    "encoder.block.16.layer.0.layer_norm.weight": "pytorch_model-00003-of-00007.bin",
+    "encoder.block.16.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00007.bin",
+    "encoder.block.16.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00007.bin",
+    "encoder.block.16.layer.1.DenseReluDense.wo.weight": "pytorch_model-00003-of-00007.bin",
+    "encoder.block.16.layer.1.layer_norm.weight": "pytorch_model-00003-of-00007.bin",
+    "encoder.block.17.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00007.bin",
+    "encoder.block.17.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00007.bin",
+    "encoder.block.17.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00007.bin",
+    "encoder.block.17.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00007.bin",
+    "encoder.block.17.layer.0.layer_norm.weight": "pytorch_model-00003-of-00007.bin",
+    "encoder.block.17.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00007.bin",
+    "encoder.block.17.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00007.bin",
+    "encoder.block.17.layer.1.DenseReluDense.wo.weight": "pytorch_model-00003-of-00007.bin",
+    "encoder.block.17.layer.1.layer_norm.weight": "pytorch_model-00003-of-00007.bin",
+    "encoder.block.18.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00007.bin",
+    "encoder.block.18.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00007.bin",
+    "encoder.block.18.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00007.bin",
+    "encoder.block.18.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00007.bin",
+    "encoder.block.18.layer.0.layer_norm.weight": "pytorch_model-00003-of-00007.bin",
+    "encoder.block.18.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00007.bin",
+    "encoder.block.18.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00007.bin",
+    "encoder.block.18.layer.1.DenseReluDense.wo.weight": "pytorch_model-00003-of-00007.bin",
+    "encoder.block.18.layer.1.layer_norm.weight": "pytorch_model-00003-of-00007.bin",
+    "encoder.block.19.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00007.bin",
+    "encoder.block.19.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00007.bin",
+    "encoder.block.19.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00007.bin",
+    "encoder.block.19.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00007.bin",
+    "encoder.block.19.layer.0.layer_norm.weight": "pytorch_model-00003-of-00007.bin",
+    "encoder.block.19.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00007.bin",
+    "encoder.block.19.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00007.bin",
+    "encoder.block.19.layer.1.DenseReluDense.wo.weight": "pytorch_model-00003-of-00007.bin",
+    "encoder.block.19.layer.1.layer_norm.weight": "pytorch_model-00003-of-00007.bin",
+    "encoder.block.2.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00007.bin",
+    "encoder.block.2.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00007.bin",
+    "encoder.block.2.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00007.bin",
+    "encoder.block.2.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00007.bin",
+    "encoder.block.2.layer.0.layer_norm.weight": "pytorch_model-00002-of-00007.bin",
+    "encoder.block.2.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00007.bin",
+    "encoder.block.2.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00007.bin",
+    "encoder.block.2.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00007.bin",
+    "encoder.block.2.layer.1.layer_norm.weight": "pytorch_model-00002-of-00007.bin",
+    "encoder.block.20.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00007.bin",
+    "encoder.block.20.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00007.bin",
+    "encoder.block.20.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00007.bin",
+    "encoder.block.20.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00007.bin",
+    "encoder.block.20.layer.0.layer_norm.weight": "pytorch_model-00003-of-00007.bin",
+    "encoder.block.20.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00007.bin",
+    "encoder.block.20.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00007.bin",
+    "encoder.block.20.layer.1.DenseReluDense.wo.weight": "pytorch_model-00003-of-00007.bin",
+    "encoder.block.20.layer.1.layer_norm.weight": "pytorch_model-00003-of-00007.bin",
+    "encoder.block.21.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00007.bin",
+    "encoder.block.21.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00007.bin",
+    "encoder.block.21.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00007.bin",
+    "encoder.block.21.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00007.bin",
+    "encoder.block.21.layer.0.layer_norm.weight": "pytorch_model-00003-of-00007.bin",
+    "encoder.block.21.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00007.bin",
+    "encoder.block.21.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00007.bin",
+    "encoder.block.21.layer.1.DenseReluDense.wo.weight": "pytorch_model-00003-of-00007.bin",
+    "encoder.block.21.layer.1.layer_norm.weight": "pytorch_model-00003-of-00007.bin",
+    "encoder.block.22.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00007.bin",
+    "encoder.block.22.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00007.bin",
+    "encoder.block.22.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00007.bin",
+    "encoder.block.22.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00007.bin",
+    "encoder.block.22.layer.0.layer_norm.weight": "pytorch_model-00003-of-00007.bin",
+    "encoder.block.22.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00007.bin",
+    "encoder.block.22.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00007.bin",
+    "encoder.block.22.layer.1.DenseReluDense.wo.weight": "pytorch_model-00003-of-00007.bin",
+    "encoder.block.22.layer.1.layer_norm.weight": "pytorch_model-00003-of-00007.bin",
+    "encoder.block.23.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00007.bin",
+    "encoder.block.23.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00007.bin",
+    "encoder.block.23.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00007.bin",
+    "encoder.block.23.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00007.bin",
+    "encoder.block.23.layer.0.layer_norm.weight": "pytorch_model-00003-of-00007.bin",
+    "encoder.block.23.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00007.bin",
+    "encoder.block.23.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00007.bin",
+    "encoder.block.23.layer.1.DenseReluDense.wo.weight": "pytorch_model-00003-of-00007.bin",
+    "encoder.block.23.layer.1.layer_norm.weight": "pytorch_model-00003-of-00007.bin",
+    "encoder.block.3.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00007.bin",
+    "encoder.block.3.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00007.bin",
+    "encoder.block.3.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00007.bin",
+    "encoder.block.3.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00007.bin",
+    "encoder.block.3.layer.0.layer_norm.weight": "pytorch_model-00002-of-00007.bin",
+    "encoder.block.3.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00007.bin",
+    "encoder.block.3.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00007.bin",
+    "encoder.block.3.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00007.bin",
+    "encoder.block.3.layer.1.layer_norm.weight": "pytorch_model-00002-of-00007.bin",
+    "encoder.block.4.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00007.bin",
+    "encoder.block.4.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00007.bin",
+    "encoder.block.4.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00007.bin",
+    "encoder.block.4.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00007.bin",
+    "encoder.block.4.layer.0.layer_norm.weight": "pytorch_model-00002-of-00007.bin",
+    "encoder.block.4.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00007.bin",
+    "encoder.block.4.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00007.bin",
+    "encoder.block.4.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00007.bin",
+    "encoder.block.4.layer.1.layer_norm.weight": "pytorch_model-00002-of-00007.bin",
+    "encoder.block.5.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00007.bin",
+    "encoder.block.5.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00007.bin",
+    "encoder.block.5.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00007.bin",
+    "encoder.block.5.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00007.bin",
+    "encoder.block.5.layer.0.layer_norm.weight": "pytorch_model-00002-of-00007.bin",
+    "encoder.block.5.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00007.bin",
+    "encoder.block.5.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00007.bin",
+    "encoder.block.5.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00007.bin",
+    "encoder.block.5.layer.1.layer_norm.weight": "pytorch_model-00002-of-00007.bin",
+    "encoder.block.6.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00007.bin",
+    "encoder.block.6.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00007.bin",
+    "encoder.block.6.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00007.bin",
+    "encoder.block.6.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00007.bin",
+    "encoder.block.6.layer.0.layer_norm.weight": "pytorch_model-00002-of-00007.bin",
+    "encoder.block.6.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00007.bin",
+    "encoder.block.6.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00007.bin",
+    "encoder.block.6.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00007.bin",
+    "encoder.block.6.layer.1.layer_norm.weight": "pytorch_model-00002-of-00007.bin",
+    "encoder.block.7.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00007.bin",
+    "encoder.block.7.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00007.bin",
+    "encoder.block.7.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00007.bin",
+    "encoder.block.7.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00007.bin",
+    "encoder.block.7.layer.0.layer_norm.weight": "pytorch_model-00002-of-00007.bin",
+    "encoder.block.7.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00007.bin",
+    "encoder.block.7.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00007.bin",
+    "encoder.block.7.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00007.bin",
+    "encoder.block.7.layer.1.layer_norm.weight": "pytorch_model-00002-of-00007.bin",
+    "encoder.block.8.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00007.bin",
+    "encoder.block.8.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00007.bin",
+    "encoder.block.8.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00007.bin",
+    "encoder.block.8.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00007.bin",
+    "encoder.block.8.layer.0.layer_norm.weight": "pytorch_model-00002-of-00007.bin",
+    "encoder.block.8.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00007.bin",
+    "encoder.block.8.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00007.bin",
+    "encoder.block.8.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00007.bin",
+    "encoder.block.8.layer.1.layer_norm.weight": "pytorch_model-00002-of-00007.bin",
+    "encoder.block.9.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00007.bin",
+    "encoder.block.9.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00007.bin",
+    "encoder.block.9.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00007.bin",
+    "encoder.block.9.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00007.bin",
+    "encoder.block.9.layer.0.layer_norm.weight": "pytorch_model-00002-of-00007.bin",
+    "encoder.block.9.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00007.bin",
+    "encoder.block.9.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00007.bin",
+    "encoder.block.9.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00007.bin",
+    "encoder.block.9.layer.1.layer_norm.weight": "pytorch_model-00002-of-00007.bin",
+    "encoder.embed_tokens.weight": "pytorch_model-00001-of-00007.bin",
+    "encoder.final_layer_norm.weight": "pytorch_model-00003-of-00007.bin",
+    "lm_head.weight": "pytorch_model-00007-of-00007.bin",
+    "shared.weight": "pytorch_model-00001-of-00007.bin"
+  }
+}

special_tokens_map.json

@@ -0,0 +1 @@
+{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>"}

spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef78f86560d809067d12bac6c09f19a462cb3af3f54d2b8acbba26e1433125d6
+size 4309802

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93c3578052e1605d8332eb961bc08d72e246071974e4cc54aa6991826b802aa5
+size 16330369

tokenizer_config.json

@@ -0,0 +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_xxl_NCC", "sp_model_kwargs": {}, "tokenizer_class": "T5Tokenizer"}

train/events.out.tfevents.1651509675.t1v-n-2e172807-w-2.42614.0.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6cedc3fbaaf32a13c12bab18c261e0c7d851e40bba13594b82bb47d69fa28eda
+size 10780

train/events.out.tfevents.1651512925.t1v-n-2e172807-w-2.60209.0.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4a98cc1420dfd8ad9279df8bb1df3d62260175e98bad8ceddebcdf160580791
+size 6318

train/events.out.tfevents.1651516244.t1v-n-2e172807-w-2.77098.0.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7a9f2c7011f2c1cae568a42f33c41d96c9c70688677473757e7e190641eb9c3
+size 6403

train/events.out.tfevents.1651518120.t1v-n-2e172807-w-2.88027.0.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba5ca9715017497ac8400abbe1a2125f44acbbf5a215585d94cafde062fe4f72
+size 6318

train/events.out.tfevents.1651519081.t1v-n-2e172807-w-2.95267.0.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02fb41912affac506bddd870b3f894251b41e3e9e419927f4647b3bdfd2fd084
+size 9321

train/events.out.tfevents.1651524618.t1v-n-2e172807-w-2.122205.0.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0830f6e3df08cffe97b0dd9bf814894781106d806d3a5ace6493df3aee462239
+size 457050

train/events.out.tfevents.1651842149.t1v-n-8dabd809-w-2.24421.0.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de9ab18a367cbcf480704f1348ff5ea5f07ee6999aa8c58483503243a68c9b71
+size 6403

train/events.out.tfevents.1651854519.t1v-n-1ec3bc64-w-6.22910.0.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8e57ea85326bab1af3f2272189c51361f62fd60e35a113b2a2c8730ab9c5d47
+size 178990

train/events.out.tfevents.1651985030.t1v-n-1ad4ca7f-w-2.12503.0.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53dd02aff27c2f42b8c4d586aa50ad8bb564c8b9f1e1222d70b447efc143042b
+size 152728

train/events.out.tfevents.1652106455.t1v-n-25d830de-w-3.12788.0.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e85882b9d2ffcf2a2c0589127f614434481936832c32d9783d2875c6a00206e5
+size 6339

training_eval/ncc_english_span_corruption_stream/events.out.tfevents.1651509675.t1v-n-2e172807-w-2.42614.1.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8af11da484014ae72daabe4a3c801a3ef77c3998da1f7ecc5fa1f64bf599c661
+size 4041

training_eval/ncc_english_span_corruption_stream/events.out.tfevents.1651512926.t1v-n-2e172807-w-2.60209.1.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:137a241098ca5f12b8c07e8249d010205fef1f38fa23e2c0e9edc2a9c42a20d1
+size 40

training_eval/ncc_english_span_corruption_stream/events.out.tfevents.1651516245.t1v-n-2e172807-w-2.77098.1.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2fdf1eac991c83b8191e02b88bdbf990e176e7e4d5c4a1cf06a8098560fcb2e
+size 40

training_eval/ncc_english_span_corruption_stream/events.out.tfevents.1651518120.t1v-n-2e172807-w-2.88027.1.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99326f9d5a7241816f2c420a1413cd0b6768d5c0fd7dcb720a8ad1c131bbb603
+size 40

training_eval/ncc_english_span_corruption_stream/events.out.tfevents.1651519081.t1v-n-2e172807-w-2.95267.1.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eef1457d054bb7d298c918ce4e82711d3d8df0509c5a602852f298af1a749ea8
+size 2736

training_eval/ncc_english_span_corruption_stream/events.out.tfevents.1651524618.t1v-n-2e172807-w-2.122205.1.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7c344a4f590a914673e20cb24e2b7e8978aa7bf103326cae6151719e1334310
+size 402066

training_eval/ncc_english_span_corruption_stream/events.out.tfevents.1651842149.t1v-n-8dabd809-w-2.24421.1.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a268cee07d94c56f32fd416fc60082e352d04f1c9b568d3ffc512d8334f2df5
+size 40

training_eval/ncc_english_span_corruption_stream/events.out.tfevents.1651854519.t1v-n-1ec3bc64-w-6.22910.1.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d0bf0227c3db700433470d480061366c99934e83f15ddc1eaf6ef8156be463c
+size 154116

training_eval/ncc_english_span_corruption_stream/events.out.tfevents.1651985030.t1v-n-1ad4ca7f-w-2.12503.1.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:994a7e45600eed3dc42192dbee4c8cc609c6d0dc686d2456760933ea0af3a251
+size 130626

training_eval/ncc_english_span_corruption_stream/events.out.tfevents.1652106455.t1v-n-25d830de-w-3.12788.1.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74de5256233ca07850af91d69ce43dc1b29c114d703b7d4f1ad1d46af82f4433
+size 40