Commit from model create scripts

.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 = 128
+DROPOUT_RATE = 0.0
+INITIAL_CHECKPOINT_PATH = \
+    'gs://t5-data/pretrained_models/t5x/mt5_xl/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_xl'
+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 = 2
+
+# 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 = 2048
+network.T5Config.head_dim = 64
+network.T5Config.logits_via_embedding = False
+network.T5Config.mlp_activations = ('gelu', 'linear')
+network.T5Config.mlp_dim = 5120
+network.T5Config.num_decoder_layers = 24
+network.T5Config.num_encoder_layers = 24
+network.T5Config.num_heads = 32
+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-xl",
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "d_ff": 5120,
+  "d_kv": 64,
+  "d_model": 2048,
+  "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": 32,
+  "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
+}

flax_model.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:429ff72f16d7ab8b36957814093c4adcd1ac8ca3c33a200cc764520af56f3b42
+size 14970502847

pytorch_model-00001-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33c5d6bb3cafeb8e4b4395b24e2cf80929a0392c35e7512421c819211e27968e
+size 6679907079

pytorch_model-00002-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9637711248e208528786fa4ad83dbc2a24195f1b393a651ff42ff607281f6dc3
+size 8290756867

pytorch_model-00003-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f2ac16f65f06bb847ef5691c5c2d10f90bbe5a8d822167be490a06bd2fc0d43
+size 2048918251

pytorch_model.bin.index.json

@@ -0,0 +1,567 @@
+{
+  "metadata": {
+    "total_size": 19068313600
+  },
+  "weight_map": {
+    "decoder.block.0.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.0.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.0.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.0.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.0.layer.0.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.0.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.0.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.0.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.0.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.0.layer.1.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.0.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.0.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.0.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.0.layer.2.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.1.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.1.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.1.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.1.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.1.layer.0.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.1.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.1.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.1.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.1.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.1.layer.1.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.1.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.1.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.1.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.1.layer.2.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.10.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.10.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.10.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.10.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.10.layer.0.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.10.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.10.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.10.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.10.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.10.layer.1.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.10.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.10.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.10.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.10.layer.2.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.11.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.11.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.11.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.11.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.11.layer.0.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.11.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.11.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.11.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.11.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.11.layer.1.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.11.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.11.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.11.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.11.layer.2.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.12.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.12.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.12.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.12.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.12.layer.0.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.12.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.12.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.12.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.12.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.12.layer.1.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.12.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.12.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.12.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.12.layer.2.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.13.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.13.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.13.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.13.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.13.layer.0.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.13.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.13.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.13.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.13.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.13.layer.1.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.13.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.13.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.13.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.13.layer.2.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.14.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.14.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.14.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.14.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.14.layer.0.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.14.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.14.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.14.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.14.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.14.layer.1.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.14.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.14.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.14.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.14.layer.2.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.15.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.15.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.15.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.15.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.15.layer.0.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.15.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.15.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.15.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.15.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.15.layer.1.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.15.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.15.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.15.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.15.layer.2.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.16.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.16.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.16.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.16.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.16.layer.0.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.16.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.16.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.16.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.16.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.16.layer.1.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.16.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.16.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.16.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.16.layer.2.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.17.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.17.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.17.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.17.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.17.layer.0.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.17.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.17.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.17.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.17.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.17.layer.1.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.17.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.17.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.17.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.17.layer.2.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.18.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.18.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.18.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.18.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.18.layer.0.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.18.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.18.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.18.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.18.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.18.layer.1.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.18.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.18.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.18.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.18.layer.2.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.19.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.19.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.19.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.19.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.19.layer.0.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.19.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.19.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.19.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.19.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.19.layer.1.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.19.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.19.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.19.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.19.layer.2.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.2.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.2.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.2.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.2.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.2.layer.0.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.2.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.2.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.2.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.2.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.2.layer.1.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.2.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.2.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.2.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.2.layer.2.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.20.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.20.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.20.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.20.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.20.layer.0.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.20.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.20.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.20.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.20.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.20.layer.1.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.20.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.20.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.20.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.20.layer.2.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.21.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.21.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.21.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.21.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.21.layer.0.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.21.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.21.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.21.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.21.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.21.layer.1.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.21.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.21.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.21.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.21.layer.2.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.22.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.22.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.22.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.22.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.22.layer.0.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.22.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.22.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.22.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.22.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.22.layer.1.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.22.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.22.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.22.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.22.layer.2.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.23.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.23.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.23.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.23.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.23.layer.0.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.23.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.23.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.23.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.23.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.23.layer.1.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.23.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.23.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.23.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.23.layer.2.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.3.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.3.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.3.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.3.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.3.layer.0.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.3.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.3.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.3.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.3.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.3.layer.1.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.3.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.3.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.3.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.3.layer.2.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.4.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.4.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.4.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.4.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.4.layer.0.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.4.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.4.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.4.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.4.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.4.layer.1.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.4.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.4.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.4.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.4.layer.2.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.5.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.5.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.5.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.5.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.5.layer.0.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.5.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.5.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.5.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.5.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.5.layer.1.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.5.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.5.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.5.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.5.layer.2.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.6.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.6.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.6.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.6.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.6.layer.0.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.6.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.6.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.6.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.6.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.6.layer.1.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.6.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.6.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.6.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.6.layer.2.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.7.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.7.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.7.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.7.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.7.layer.0.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.7.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.7.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.7.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.7.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.7.layer.1.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.7.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.7.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.7.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.7.layer.2.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.8.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.8.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.8.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.8.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.8.layer.0.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.8.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.8.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.8.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.8.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.8.layer.1.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.8.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.8.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.8.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.8.layer.2.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.9.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.9.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.9.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.9.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.9.layer.0.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.9.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.9.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.9.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.9.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.9.layer.1.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.9.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.9.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.9.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.block.9.layer.2.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.embed_tokens.weight": "pytorch_model-00002-of-00003.bin",
+    "decoder.final_layer_norm.weight": "pytorch_model-00002-of-00003.bin",
+    "encoder.block.0.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.0.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.0.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.0.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.0.layer.0.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.0.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.0.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.0.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.0.layer.1.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.1.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.1.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.1.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.1.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.1.layer.0.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.1.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.1.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.1.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.1.layer.1.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.10.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.10.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.10.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.10.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.10.layer.0.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.10.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.10.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.10.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.10.layer.1.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.11.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.11.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.11.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.11.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.11.layer.0.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.11.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.11.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.11.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.11.layer.1.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.12.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.12.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.12.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.12.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.12.layer.0.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.12.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.12.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.12.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.12.layer.1.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.13.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.13.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.13.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.13.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.13.layer.0.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.13.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.13.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.13.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.13.layer.1.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.14.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.14.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.14.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.14.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.14.layer.0.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.14.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.14.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.14.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.14.layer.1.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.15.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.15.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.15.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.15.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.15.layer.0.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.15.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.15.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.15.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.15.layer.1.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.16.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.16.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.16.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.16.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.16.layer.0.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.16.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.16.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.16.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.16.layer.1.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.17.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.17.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.17.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.17.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.17.layer.0.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.17.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.17.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.17.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.17.layer.1.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.18.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.18.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.18.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.18.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.18.layer.0.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.18.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.18.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.18.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.18.layer.1.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.19.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.19.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.19.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.19.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.19.layer.0.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.19.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.19.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.19.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.19.layer.1.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.2.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.2.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.2.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.2.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.2.layer.0.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.2.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.2.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.2.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.2.layer.1.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.20.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.20.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.20.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.20.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.20.layer.0.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.20.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.20.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.20.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.20.layer.1.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.21.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.21.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.21.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.21.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.21.layer.0.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.21.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.21.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.21.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.21.layer.1.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.22.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.22.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.22.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.22.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.22.layer.0.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.22.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.22.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.22.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.22.layer.1.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.23.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.23.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.23.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.23.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.23.layer.0.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.23.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.23.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.23.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.23.layer.1.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.3.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.3.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.3.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.3.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.3.layer.0.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.3.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.3.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.3.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.3.layer.1.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.4.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.4.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.4.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.4.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.4.layer.0.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.4.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.4.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.4.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.4.layer.1.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.5.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.5.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.5.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.5.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.5.layer.0.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.5.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.5.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.5.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.5.layer.1.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.6.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.6.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.6.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.6.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.6.layer.0.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.6.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.6.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.6.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.6.layer.1.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.7.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.7.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.7.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.7.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.7.layer.0.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.7.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.7.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.7.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.7.layer.1.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.8.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.8.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.8.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.8.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.8.layer.0.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.8.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.8.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.8.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.8.layer.1.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.9.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.9.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.9.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.9.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.9.layer.0.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.9.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.9.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.9.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.block.9.layer.1.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.embed_tokens.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.final_layer_norm.weight": "pytorch_model-00001-of-00003.bin",
+    "lm_head.weight": "pytorch_model-00003-of-00003.bin",
+    "shared.weight": "pytorch_model-00001-of-00003.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

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13edf9346263c231557abbd4b42fd847571a957f938e4f48b2d23ec2f1c58acc
+size 9760

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_xl_NCC", "sp_model_kwargs": {}, "tokenizer_class": "T5Tokenizer"}

train/events.out.tfevents.1649576424.t1v-n-94d01c37-w-3.2758548.0.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6eaa0614ba50b24dc998f7e7b63243ab9fdfae1f284825cecd15e9fc714e03b6
+size 6403

train/events.out.tfevents.1649578354.t1v-n-94d01c37-w-3.2769526.0.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2f6cb0d30dd4337e1c29de2f7df28d582514e6dc117511b1a200431039bf243
+size 10707

train/events.out.tfevents.1649585207.t1v-n-94d01c37-w-3.2804417.0.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3974d6a10de120a1346e96e238e32789c497132381ad3edc8c1ac9c821178d0e
+size 28263

train/events.out.tfevents.1649604716.t1v-n-94d01c37-w-3.2916105.0.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1f6f30f189d95910ac423c65ed57625ded2d0087c11e89244c9a57cde13e9c1
+size 28263

train/events.out.tfevents.1649625471.t1v-n-94d01c37-w-3.3032489.0.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec0cc134882eb7103245909da57535eece1c57e273ce22762229171b926bbb7f
+size 6403

train/events.out.tfevents.1649658143.t1v-n-94d01c37-w-3.3159692.0.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c79a36372d4c751ed1b0bfd11e05e835e24612db30a14e2ee10c9158277de31
+size 6317

train/events.out.tfevents.1649659968.t1v-n-94d01c37-w-3.3170227.0.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc77584288839071e6f8375cd35ad6eee3ef0232b8428ec81f00b93220ee061e
+size 6317

train/events.out.tfevents.1649663312.t1v-n-94d01c37-w-3.3186665.0.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3694f46d96522abe7892f510f983a0521fc09566c98dc66f395fa7cdf876eb61
+size 6317

train/events.out.tfevents.1649665806.t1v-n-94d01c37-w-3.3200483.0.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b50b7c299d2d2e0896ab637e289f90fee498d48b7101741b87d3802ea9ca214
+size 7866

train/events.out.tfevents.1649677709.t1v-n-94d01c37-w-1.41136.0.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f76925dc40b3244836dc508f5254db7336510ae3129a3a37b37c8ce7ce78771c
+size 22411

train/events.out.tfevents.1649693993.t1v-n-94d01c37-w-1.131865.0.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02c01f9901e7ff5009fde1dccc8a8b82ee794226950316436491cc85f7a863eb
+size 75079

train/events.out.tfevents.1649751312.t1v-n-94d01c37-w-1.465030.0.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91f98287e1f1a9e25023b263dbeca18bc5870b07526d745d3437ffbbd294dc5e
+size 110191

train/events.out.tfevents.1649853499.t1v-n-94d01c37-w-1.1031862.0.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3dda7643bef2c672627dae470a9b247f8fc7c44513aeed21cf05e480f8740c50
+size 69227

train/events.out.tfevents.1649910223.t1v-n-94d01c37-w-1.1357507.0.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:adaedf31236ad4eea2176c56799177579f99714714672c4edb7d680c7db20692
+size 15096

train/events.out.tfevents.1649919405.t1v-n-94d01c37-w-1.1411806.0.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4d2bb2140a669742ef9880407ec2ebef2031ae6957d32ca68a7dc4e374c23f7
+size 10707

train/events.out.tfevents.1649961155.t1v-n-94d01c37-w-1.1579646.0.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:667fea9a63e25dd71c2c362da69f2837221cea288beb464437c17003a44ae4b1
+size 53134

train/events.out.tfevents.1650012376.t1v-n-94d01c37-w-1.1854026.0.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7cf5b908c5ba20aaa10783e3a680c49114fbdeac59aa22cf9794c56344903fe
+size 28263

train/events.out.tfevents.1650037350.t1v-n-94d01c37-w-1.1988057.0.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29ed193fd84b02c439e7b4055e0ed9896909f90f40f4a56329a1d102ad30ec74
+size 26372

train/events.out.tfevents.1650082486.t1v-n-94d01c37-w-1.2198868.0.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5cef4109843f49dfe2b0d49d81f6d43022a5a4209a3845065ecab22ac7d4486
+size 6403

train/events.out.tfevents.1650097888.t1v-n-94d01c37-w-1.2260945.0.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aacbb2467a1dcb8f369c0e2d41ce4c73d9d523b75605b0bbd715fdb423eebcaa
+size 32652

train/events.out.tfevents.1650134701.t1v-n-94d01c37-w-1.2449113.0.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4241c13db2a46710277f894245ea41b6a3b77767b20646396427204b3c3a3cde
+size 16559

train/events.out.tfevents.1650145105.t1v-n-94d01c37-w-1.2507564.0.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98e88c4e07c8b62035b03601d6d951c6f24f7b21c22b5ffab1fb7cab7b251d43
+size 10707

train/events.out.tfevents.1650150928.t1v-n-94d01c37-w-1.2539030.0.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8acbe6d1f6c4f40f7ce32ecf27ff394d327b8590ac9d6756077b4b9ce5d4d694
+size 16559

train/events.out.tfevents.1650180232.t1v-n-94d01c37-w-1.2669968.0.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8468b608786eac31b338728da54ed32811f8852ed3c53fd1fc47bef3191195e0
+size 116043

train/events.out.tfevents.1650269484.t1v-n-94d01c37-w-1.3191003.0.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9bcb2d4ce6acc149394e4cd99139e4771a6b7d09af997ada17beca487ced890e
+size 7779

train/events.out.tfevents.1650301631.t1v-n-06e40f6a-w-2.144912.0.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db36ed65485140ddbfd32fcf53d6afb01ba9693556e2209082eff87d11463adc
+size 35581

train/events.out.tfevents.1650331210.t1v-n-06e40f6a-w-2.269071.0.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e91ebae4f5bc78c13ce30a75effbb2786fa015944412de197ab088cb2ecaa156
+size 35581

train/events.out.tfevents.1650354640.t1v-n-06e40f6a-w-2.418760.0.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ed889e112d885dd33c2a50a062293eafc4a5bfb847bd2642034473fb2d2d982
+size 6315

train/events.out.tfevents.1650355218.t1v-n-06e40f6a-w-2.423813.0.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:925d23a9789d019665a3a0f75b8b401b4d0f4c449d3926a401647e4f61406d01
+size 40043

train/events.out.tfevents.1650439634.t1v-n-da2df89d-w-0.68748.0.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d977f60add19dad7e8526ad9aa7416d73caa003069c077ea5998ab104c8d479
+size 6401

train/events.out.tfevents.1650442527.t1v-n-da2df89d-w-0.83496.0.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e4c473f11ae8b5a0182b63d1eec23072cd57e45a459c2d0c3a7290a5196a04b
+size 7860

train/events.out.tfevents.1650450275.t1v-n-51c2c60a-w-3.119563.0.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d719be90fafdd1864d812007443cf9a0ff7b4d7a0bf767d91c9d92254e70534
+size 6401

train/events.out.tfevents.1650451918.t1v-n-51c2c60a-w-3.129431.0.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b22f48a97b35dd71a83c61c50c4a76ada4235e09d6f6dff7c533a2b092323fdd
+size 38584

train/events.out.tfevents.1650489808.t1v-n-214493c0-w-1.96872.0.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29dad258413de9b47cd41acea5c733109736c27d11fcaa573ba98c7b7735807c
+size 6315

train/events.out.tfevents.1650490489.t1v-n-214493c0-w-1.105452.0.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9b8f290c760c6da845beffd909e692b0e394e5fcd5e86239de528158194ddc9
+size 35581

train/events.out.tfevents.1650520938.t1v-n-214493c0-w-1.233747.0.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:300f08ff791c2c31764d1d191f8ce6dedced0fc64cda1fbe5cc7bf4ba77e7040
+size 94111