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 +1,152 @@
+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://nb-t5x-us-central2/norwegian_NCC_plus_English_t5x_xxl/checkpoint_1500000'
+LABEL_SMOOTHING = 0.0
+LOSS_NORMALIZING_FACTOR = None
+MIXTURE_OR_TASK_MODULE = None
+MIXTURE_OR_TASK_NAME = 'ncc_english_prefix_lm_stream'
+MODEL = @models.EncoderDecoderModel()
+MODEL_DIR = \
+    'gs://t5x-training/pretrained_models/norwegian_NCC_plus_English_pluss100k_lm_t5x_xxl'
+OPTIMIZER = @adafactor.Adafactor()
+RANDOM_SEED = None
+SHUFFLE_TRAIN_EXAMPLES = True
+TASK_FEATURE_LENGTHS = {'inputs': 512, 'targets': 512}
+TRAIN_STEPS = 1600000
+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 = 5000
+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 sha256:9cb5772aa50f2fe1398cdea5c3d3ebbdf934d62dd8078fd2023c326e8e0d0a03
+size 5842746828

pytorch_model-00002-of-00007.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c67d919a9bb71cf1c19c136b26a6bd9b660dbdeed893a0996fb879736028ffab
+size 9966130321

pytorch_model-00003-of-00007.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a09b1fa39592a8a65914d27043bb85e9c37a22716a7cb5a20f5199855050c40
+size 6811886805

pytorch_model-00004-of-00007.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:921af55a707d11957d28e470f53760d69617ec0522d5413a0beac372755895aa
+size 9835956831

pytorch_model-00005-of-00007.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31f97e6e75212e6e9aded7d0a2bcd4c8394e196ebd36e3ad9c00c1d99758801a
+size 9999722997

pytorch_model-00006-of-00007.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fcfbaf1cd35c562402d772561bbe0db957c76d0841536d30f69dc587485d40e9
+size 9227968551

pytorch_model-00007-of-00007.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6cda203bc1783da76be8f6a3b9e9a71c4a14b97e28bb5dd62a92be08d5f50ac9
+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

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

train/events.out.tfevents.1652084275.t1v-n-1ad4ca7f-w-2.507325.0.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0727325829d431b0c1affbf1db8cdbaae2944ad8263ee8573f81ce8e67b06f3
+size 6362

train/events.out.tfevents.1652085367.t1v-n-1ad4ca7f-w-2.514921.0.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fb20ac22f00855703538756a7c44b44831b9963a765e915fe1f735ee528216c
+size 6362

train/events.out.tfevents.1652088324.t1v-n-1ad4ca7f-w-2.529191.0.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ac5fad47cb1ec5fae0f4920f317009572741392795bfc0de043d871dcdfc249
+size 27043

train/events.out.tfevents.1652107892.t1v-n-25d830de-w-3.32680.0.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4566516691f0b3bd5a68d9fb62c833348d61da26aa525cbdcf2f4d6a33f6e21
+size 6447

train/events.out.tfevents.1652127110.t1v-n-973e8a0e-w-7.48888.0.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37ce5dfc6caee0980bafed9668a6196f19a42b788e2a3110ddfbae9e67603f63
+size 7906

train/events.out.tfevents.1652130744.t1v-n-009e3459-w-5.25821.0.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e361e0c945b5d2776a492227c4006559dc19510918ef513f520b81b361c1044
+size 120065

train/events.out.tfevents.1652219584.t1v-n-85febe56-w-6.16054.0.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5415dd2cc36bd9bcc6d1c8be5701b303df3260ce7ee82d97b48a8986b9c2bf9
+size 6447

train/events.out.tfevents.1652250802.t1v-n-ce83d6bd-w-0.89574.0.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4e65ef8cce5d182eacc2700d88d91ce2c055b6102ca06f4b2d84d1e6023ec2f
+size 28587

training_eval/ncc_english_prefix_lm_stream/events.out.tfevents.1652084276.t1v-n-1ad4ca7f-w-2.507325.1.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c0bec92851b4069c18c11c8619fb39c191ccaff2b2ca1f4238c74cb62c5754d
+size 40

training_eval/ncc_english_prefix_lm_stream/events.out.tfevents.1652085367.t1v-n-1ad4ca7f-w-2.514921.1.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63d7cdc77f0d50164886ab199d06549b5f6b57ed67dcd241ea1f52743582162f
+size 40

training_eval/ncc_english_prefix_lm_stream/events.out.tfevents.1652088324.t1v-n-1ad4ca7f-w-2.529191.1.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8f18c8ebb256f930488ce77f8530b740bafbe5bff920384f9467952f2478858
+size 18396

training_eval/ncc_english_prefix_lm_stream/events.out.tfevents.1652107892.t1v-n-25d830de-w-3.32680.1.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0550c35a736caf75f39d8b2fac0c0752c41d1a928e5a231968c3cc045a374fea
+size 40

training_eval/ncc_english_prefix_lm_stream/events.out.tfevents.1652127111.t1v-n-973e8a0e-w-7.48888.1.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:835cbf12f141b92acef82937cfff00ceac81843e4b2eb17c2d6f7aba2407967c
+size 1431

training_eval/ncc_english_prefix_lm_stream/events.out.tfevents.1652130744.t1v-n-009e3459-w-5.25821.1.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7d4455ecc2ae7034ccf31b0ec1e127d87f5a750337154972323b08599f8c6fd
+size 100611

training_eval/ncc_english_prefix_lm_stream/events.out.tfevents.1652219584.t1v-n-85febe56-w-6.16054.1.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3177ecfeca84c3d08956f4f13b41b6e27681633aa569ff49556fff5fed3484dc
+size 40

training_eval/ncc_english_prefix_lm_stream/events.out.tfevents.1652250802.t1v-n-ce83d6bd-w-0.89574.1.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4319097a392eae9cb9e72509eb3b2cd30c6f1606adcfa3041fa81b4bbddb9cc5
+size 19701