Commit from model create scripts

.gitattributes

@@ -7,21 +7,15 @@
 *.h5 filter=lfs diff=lfs merge=lfs -text
 *.joblib filter=lfs diff=lfs merge=lfs -text
 *.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
 *.model filter=lfs diff=lfs merge=lfs -text
 *.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
 *.onnx filter=lfs diff=lfs merge=lfs -text
 *.ot filter=lfs diff=lfs merge=lfs -text
 *.parquet filter=lfs diff=lfs merge=lfs -text
 *.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
 *.pt filter=lfs diff=lfs merge=lfs -text
 *.pth filter=lfs diff=lfs merge=lfs -text
 *.rar filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
 saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.tar.* filter=lfs diff=lfs merge=lfs -text
 *.tflite filter=lfs diff=lfs merge=lfs -text
@@ -29,5 +23,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.wasm filter=lfs diff=lfs merge=lfs -text
 *.xz filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
-*.zst 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 +1,179 @@
+from __gin__ import dynamic_registration
+import __main__ as train_script
+import seqio
+from t5.data import 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 = 32
+DROPOUT_RATE = 0.1
+EVAL_PERIOD = 1000
+EVAL_STEPS = 20
+EVALUATOR_NUM_EXAMPLES = None
+EVALUATOR_USE_MEMORY_CACHE = True
+INITIAL_CHECKPOINT_PATH = \
+    'gs://north-t5x/pretrained_models/xl/scandinavian3k_t5x_xl/checkpoint_3000000'
+JSON_WRITE_N_RESULTS = None
+LABEL_SMOOTHING = 0.0
+LOSS_NORMALIZING_FACTOR = None
+MIXTURE_OR_TASK_MODULE = None
+MIXTURE_OR_TASK_NAME = 'translate'
+MODEL = @models.EncoderDecoderModel()
+MODEL_DIR = 'gs://nb-t5x-us-central2/finetuned/scandi3_3stammer_v2_xl'
+OPTIMIZER = @adafactor.Adafactor()
+RANDOM_SEED = 0
+TASK_FEATURE_LENGTHS = {'inputs': 512, 'targets': 512}
+TRAIN_STEPS = 3100000
+USE_CACHED_TASKS = False
+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 = 0.001
+utils.create_learning_rate_scheduler.factors = 'constant'
+utils.create_learning_rate_scheduler.warmup_steps = 1000
+
+# Parameters for infer_eval/utils.DatasetConfig:
+# ==============================================================================
+infer_eval/utils.DatasetConfig.batch_size = %BATCH_SIZE
+infer_eval/utils.DatasetConfig.mixture_or_task_name = %MIXTURE_OR_TASK_NAME
+infer_eval/utils.DatasetConfig.module = %MIXTURE_OR_TASK_MODULE
+infer_eval/utils.DatasetConfig.pack = False
+infer_eval/utils.DatasetConfig.seed = 42
+infer_eval/utils.DatasetConfig.shuffle = False
+infer_eval/utils.DatasetConfig.split = 'validation'
+infer_eval/utils.DatasetConfig.task_feature_lengths = %TASK_FEATURE_LENGTHS
+infer_eval/utils.DatasetConfig.use_cached = %USE_CACHED_TASKS
+
+# 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 = True
+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 seqio.Evaluator:
+# ==============================================================================
+seqio.Evaluator.logger_cls = \
+    [@seqio.PyLoggingLogger, @seqio.TensorBoardLogger, @seqio.JSONLogger]
+seqio.Evaluator.num_examples = %EVALUATOR_NUM_EXAMPLES
+seqio.Evaluator.use_memory_cache = %EVALUATOR_USE_MEMORY_CACHE
+
+# Parameters for seqio.JSONLogger:
+# ==============================================================================
+seqio.JSONLogger.write_n_results = %JSON_WRITE_N_RESULTS
+
+# Parameters for partitioning.PjitPartitioner:
+# ==============================================================================
+partitioning.PjitPartitioner.logical_axis_rules = \
+    @partitioning.standard_logical_axis_rules()
+partitioning.PjitPartitioner.model_parallel_submesh = None
+partitioning.PjitPartitioner.num_partitions = 1
+
+# 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 = None
+utils.SaveCheckpointConfig.period = 10000
+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 = %EVAL_PERIOD
+train_script.train.eval_steps = %EVAL_STEPS
+train_script.train.infer_eval_dataset_cfg = @infer_eval/utils.DatasetConfig()
+train_script.train.inference_evaluator_cls = @seqio.Evaluator
+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 +1,39 @@
+{
+  "_name_or_path": "/home/perk/models/fine_North_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,
+  "max_length": 512,
+  "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,
+  "task_specific_params": {
+    "text-generation": {
+      "max_length": 512
+    },
+    "translation": {
+      "max_length": 512
+    }
+  },
+  "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:c5882153d56a329e86abc10daf4e4dc771d690369add41eb936b256a91031db3
+size 14970502847

pytorch_model-00001-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9236153faa68b527944c8dc35705ea3d314f0faf315f1a8051cb8e34d24a8a94
+size 6679907079

pytorch_model-00002-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:255498c1b6cfeca0f3475a276cd15b824b67f4b27cc1319da835668d4374e19d
+size 8290756867

pytorch_model-00003-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:048b388a46353b0d9d75d64e9eea8a58e41cc596e894cd182ba06b36d127dc73
+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

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/fine_North_xl", "sp_model_kwargs": {}, "tokenizer_class": "T5Tokenizer"}

train/events.out.tfevents.1667313761.t1v-n-98890786-w-3.107946.0.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb149b1a611244a8bde406504455d900aeaae61499e86dd48ca8cfcda631d358
+size 146222

train/events.out.tfevents.1667400693.t1v-n-98890786-w-3.649083.0.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28b10857dc793e8936cfa7d6d2c822be42c3cc072530582085907299784c2dda
+size 91606

train/events.out.tfevents.1667456762.t1v-n-98890786-w-0.31970.0.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1194f52238a0106ff77ff5fb4dc9ede7e30697f6a986082596be6c1b18318320
+size 7415

training_eval/translate/events.out.tfevents.1667313761.t1v-n-98890786-w-3.107946.1.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:adb146ff4bdf2110e2b343e806b5ad66ee3f56d4516388b6d6844885cb444151
+size 117607

training_eval/translate/events.out.tfevents.1667400693.t1v-n-98890786-w-3.649083.1.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36036394873c53e6f1be36a4ad88462908c8233caab7291c507fdfb148ac876a
+size 71327

training_eval/translate/events.out.tfevents.1667456762.t1v-n-98890786-w-0.31970.1.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cefdd4bb4ac7c1ce49ef53eebbdc35712b286b89b991268996e05d8fd28d8ead
+size 40