End of training

README.md

@@ -0,0 +1,52 @@
+---
+license: apache-2.0
+base_model: google/flan-t5-xl
+tags:
+- generated_from_trainer
+model-index:
+- name: flan-t5-xl-dpa-text-classification
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# flan-t5-xl-dpa-text-classification
+
+This model is a fine-tuned version of [google/flan-t5-xl](https://huggingface.co/google/flan-t5-xl) on the None dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0003
+- train_batch_size: 3
+- eval_batch_size: 3
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 1
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.37.2
+- Pytorch 2.2.0+cu121
+- Datasets 2.17.1
+- Tokenizers 0.15.2

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37283efad8ff2b37e67efa7e40a1532e1040f0fd8b58f49588be9999f09d6ee4
+size 4994815936

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:216a69218bd7f6b21eed5657bce0ef951bf18a56df31e0b07930a79a768b1411
+size 4974956088

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b80a24328233e9f951c68190d3bec8daa670029ed2e943e007255371f4bf605
+size 1182941624

model.safetensors.index.json

@@ -0,0 +1,568 @@
+{
+  "metadata": {
+    "total_size": 11152637960
+  },
+  "weight_map": {
+    "classification_head.dense.bias": "model-00003-of-00003.safetensors",
+    "classification_head.dense.weight": "model-00003-of-00003.safetensors",
+    "classification_head.out_proj.bias": "model-00003-of-00003.safetensors",
+    "classification_head.out_proj.weight": "model-00003-of-00003.safetensors",
+    "transformer.decoder.block.0.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
+    "transformer.decoder.block.0.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
+    "transformer.decoder.block.0.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
+    "transformer.decoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "model-00001-of-00003.safetensors",
+    "transformer.decoder.block.0.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
+    "transformer.decoder.block.0.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
+    "transformer.decoder.block.0.layer.1.EncDecAttention.k.weight": "model-00001-of-00003.safetensors",
+    "transformer.decoder.block.0.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.0.layer.1.EncDecAttention.q.weight": "model-00001-of-00003.safetensors",
+    "transformer.decoder.block.0.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.0.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.0.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.0.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.0.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.0.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.1.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.1.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.1.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.1.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.1.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.1.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.1.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.1.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.1.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.1.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.1.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.1.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.1.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.1.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.10.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.10.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.10.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.10.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.10.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.10.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.10.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.10.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.10.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.10.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.10.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.10.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.10.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.10.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.11.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.11.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.11.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.11.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.11.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.11.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.11.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.11.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.11.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.11.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.11.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.11.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.11.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.11.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.12.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.12.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.12.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.12.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.12.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.12.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.12.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.12.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.12.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.12.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.12.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.12.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.12.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.12.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.13.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.13.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.13.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.13.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.13.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.13.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.13.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.13.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.13.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.13.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.13.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.13.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.13.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.13.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.14.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.14.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.14.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.14.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.14.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.14.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.14.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.14.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.14.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.14.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.14.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.14.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.14.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.14.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.15.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.15.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.15.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.15.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.15.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.15.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.15.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.15.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.15.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.15.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.15.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.15.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.15.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.15.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.16.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.16.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.16.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.16.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.16.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.16.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.16.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.16.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.16.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.16.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.16.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.16.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.16.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.16.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.17.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.17.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.17.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.17.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.17.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.17.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.17.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.17.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.17.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.17.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.17.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.17.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.17.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.17.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.18.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.18.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.18.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.18.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.18.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.18.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.18.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.18.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.18.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.18.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.18.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.18.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.18.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.18.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.19.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.19.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.19.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.19.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.19.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.19.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.19.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.19.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.19.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.19.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.19.layer.2.DenseReluDense.wi_0.weight": "model-00003-of-00003.safetensors",
+    "transformer.decoder.block.19.layer.2.DenseReluDense.wi_1.weight": "model-00003-of-00003.safetensors",
+    "transformer.decoder.block.19.layer.2.DenseReluDense.wo.weight": "model-00003-of-00003.safetensors",
+    "transformer.decoder.block.19.layer.2.layer_norm.weight": "model-00003-of-00003.safetensors",
+    "transformer.decoder.block.2.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.2.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.2.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.2.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.2.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.2.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.2.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.2.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.2.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.2.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.2.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.2.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.2.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.2.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.20.layer.0.SelfAttention.k.weight": "model-00003-of-00003.safetensors",
+    "transformer.decoder.block.20.layer.0.SelfAttention.o.weight": "model-00003-of-00003.safetensors",
+    "transformer.decoder.block.20.layer.0.SelfAttention.q.weight": "model-00003-of-00003.safetensors",
+    "transformer.decoder.block.20.layer.0.SelfAttention.v.weight": "model-00003-of-00003.safetensors",
+    "transformer.decoder.block.20.layer.0.layer_norm.weight": "model-00003-of-00003.safetensors",
+    "transformer.decoder.block.20.layer.1.EncDecAttention.k.weight": "model-00003-of-00003.safetensors",
+    "transformer.decoder.block.20.layer.1.EncDecAttention.o.weight": "model-00003-of-00003.safetensors",
+    "transformer.decoder.block.20.layer.1.EncDecAttention.q.weight": "model-00003-of-00003.safetensors",
+    "transformer.decoder.block.20.layer.1.EncDecAttention.v.weight": "model-00003-of-00003.safetensors",
+    "transformer.decoder.block.20.layer.1.layer_norm.weight": "model-00003-of-00003.safetensors",
+    "transformer.decoder.block.20.layer.2.DenseReluDense.wi_0.weight": "model-00003-of-00003.safetensors",
+    "transformer.decoder.block.20.layer.2.DenseReluDense.wi_1.weight": "model-00003-of-00003.safetensors",
+    "transformer.decoder.block.20.layer.2.DenseReluDense.wo.weight": "model-00003-of-00003.safetensors",
+    "transformer.decoder.block.20.layer.2.layer_norm.weight": "model-00003-of-00003.safetensors",
+    "transformer.decoder.block.21.layer.0.SelfAttention.k.weight": "model-00003-of-00003.safetensors",
+    "transformer.decoder.block.21.layer.0.SelfAttention.o.weight": "model-00003-of-00003.safetensors",
+    "transformer.decoder.block.21.layer.0.SelfAttention.q.weight": "model-00003-of-00003.safetensors",
+    "transformer.decoder.block.21.layer.0.SelfAttention.v.weight": "model-00003-of-00003.safetensors",
+    "transformer.decoder.block.21.layer.0.layer_norm.weight": "model-00003-of-00003.safetensors",
+    "transformer.decoder.block.21.layer.1.EncDecAttention.k.weight": "model-00003-of-00003.safetensors",
+    "transformer.decoder.block.21.layer.1.EncDecAttention.o.weight": "model-00003-of-00003.safetensors",
+    "transformer.decoder.block.21.layer.1.EncDecAttention.q.weight": "model-00003-of-00003.safetensors",
+    "transformer.decoder.block.21.layer.1.EncDecAttention.v.weight": "model-00003-of-00003.safetensors",
+    "transformer.decoder.block.21.layer.1.layer_norm.weight": "model-00003-of-00003.safetensors",
+    "transformer.decoder.block.21.layer.2.DenseReluDense.wi_0.weight": "model-00003-of-00003.safetensors",
+    "transformer.decoder.block.21.layer.2.DenseReluDense.wi_1.weight": "model-00003-of-00003.safetensors",
+    "transformer.decoder.block.21.layer.2.DenseReluDense.wo.weight": "model-00003-of-00003.safetensors",
+    "transformer.decoder.block.21.layer.2.layer_norm.weight": "model-00003-of-00003.safetensors",
+    "transformer.decoder.block.22.layer.0.SelfAttention.k.weight": "model-00003-of-00003.safetensors",
+    "transformer.decoder.block.22.layer.0.SelfAttention.o.weight": "model-00003-of-00003.safetensors",
+    "transformer.decoder.block.22.layer.0.SelfAttention.q.weight": "model-00003-of-00003.safetensors",
+    "transformer.decoder.block.22.layer.0.SelfAttention.v.weight": "model-00003-of-00003.safetensors",
+    "transformer.decoder.block.22.layer.0.layer_norm.weight": "model-00003-of-00003.safetensors",
+    "transformer.decoder.block.22.layer.1.EncDecAttention.k.weight": "model-00003-of-00003.safetensors",
+    "transformer.decoder.block.22.layer.1.EncDecAttention.o.weight": "model-00003-of-00003.safetensors",
+    "transformer.decoder.block.22.layer.1.EncDecAttention.q.weight": "model-00003-of-00003.safetensors",
+    "transformer.decoder.block.22.layer.1.EncDecAttention.v.weight": "model-00003-of-00003.safetensors",
+    "transformer.decoder.block.22.layer.1.layer_norm.weight": "model-00003-of-00003.safetensors",
+    "transformer.decoder.block.22.layer.2.DenseReluDense.wi_0.weight": "model-00003-of-00003.safetensors",
+    "transformer.decoder.block.22.layer.2.DenseReluDense.wi_1.weight": "model-00003-of-00003.safetensors",
+    "transformer.decoder.block.22.layer.2.DenseReluDense.wo.weight": "model-00003-of-00003.safetensors",
+    "transformer.decoder.block.22.layer.2.layer_norm.weight": "model-00003-of-00003.safetensors",
+    "transformer.decoder.block.23.layer.0.SelfAttention.k.weight": "model-00003-of-00003.safetensors",
+    "transformer.decoder.block.23.layer.0.SelfAttention.o.weight": "model-00003-of-00003.safetensors",
+    "transformer.decoder.block.23.layer.0.SelfAttention.q.weight": "model-00003-of-00003.safetensors",
+    "transformer.decoder.block.23.layer.0.SelfAttention.v.weight": "model-00003-of-00003.safetensors",
+    "transformer.decoder.block.23.layer.0.layer_norm.weight": "model-00003-of-00003.safetensors",
+    "transformer.decoder.block.23.layer.1.EncDecAttention.k.weight": "model-00003-of-00003.safetensors",
+    "transformer.decoder.block.23.layer.1.EncDecAttention.o.weight": "model-00003-of-00003.safetensors",
+    "transformer.decoder.block.23.layer.1.EncDecAttention.q.weight": "model-00003-of-00003.safetensors",
+    "transformer.decoder.block.23.layer.1.EncDecAttention.v.weight": "model-00003-of-00003.safetensors",
+    "transformer.decoder.block.23.layer.1.layer_norm.weight": "model-00003-of-00003.safetensors",
+    "transformer.decoder.block.23.layer.2.DenseReluDense.wi_0.weight": "model-00003-of-00003.safetensors",
+    "transformer.decoder.block.23.layer.2.DenseReluDense.wi_1.weight": "model-00003-of-00003.safetensors",
+    "transformer.decoder.block.23.layer.2.DenseReluDense.wo.weight": "model-00003-of-00003.safetensors",
+    "transformer.decoder.block.23.layer.2.layer_norm.weight": "model-00003-of-00003.safetensors",
+    "transformer.decoder.block.3.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.3.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.3.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.3.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.3.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.3.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.3.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.3.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.3.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.3.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.3.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.3.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.3.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.3.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.4.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.4.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.4.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.4.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.4.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.4.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.4.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.4.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.4.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.4.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.4.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.4.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.4.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.4.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.5.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.5.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.5.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.5.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.5.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.5.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.5.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.5.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.5.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.5.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.5.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.5.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.5.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.5.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.6.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.6.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.6.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.6.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.6.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.6.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.6.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.6.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.6.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.6.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.6.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.6.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.6.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.6.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.7.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.7.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.7.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.7.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.7.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.7.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.7.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.7.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.7.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.7.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.7.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.7.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.7.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.7.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.8.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.8.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.8.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.8.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.8.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.8.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.8.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.8.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.8.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.8.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.8.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.8.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.8.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.8.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.9.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.9.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.9.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.9.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.9.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.9.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.9.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.9.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.9.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.9.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.9.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.9.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.9.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.block.9.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "transformer.decoder.final_layer_norm.weight": "model-00003-of-00003.safetensors",
+    "transformer.encoder.block.0.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.0.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.0.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.0.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.0.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.0.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.0.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.0.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.0.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.1.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.1.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.1.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.1.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.1.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.1.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.1.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.1.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.1.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.10.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.10.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.10.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.10.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.10.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.10.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.10.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.10.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.10.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.11.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.11.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.11.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.11.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.11.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.11.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.11.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.11.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.11.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.12.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.12.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.12.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.12.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.12.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.12.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.12.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.12.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.12.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.13.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.13.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.13.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.13.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.13.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.13.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.13.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.13.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.13.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.14.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.14.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.14.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.14.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.14.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.14.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.14.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.14.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.14.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.15.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.15.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.15.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.15.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.15.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.15.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.15.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.15.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.15.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.16.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.16.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.16.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.16.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.16.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.16.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.16.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.16.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.16.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.17.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.17.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.17.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.17.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.17.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.17.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.17.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.17.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.17.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.18.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.18.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.18.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.18.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.18.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.18.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.18.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.18.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.18.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.19.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.19.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.19.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.19.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.19.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.19.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.19.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.19.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.19.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.2.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.2.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.2.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.2.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.2.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.2.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.2.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.2.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.2.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.20.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.20.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.20.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.20.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.20.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.20.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.20.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.20.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.20.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.21.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.21.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.21.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.21.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.21.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.21.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.21.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.21.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.21.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.22.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.22.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.22.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.22.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.22.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.22.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.22.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.22.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.22.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.23.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.23.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.23.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.23.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.23.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.23.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.23.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.23.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.23.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.3.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.3.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.3.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.3.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.3.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.3.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.3.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.3.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.3.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.4.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.4.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.4.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.4.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.4.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.4.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.4.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.4.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.4.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.5.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.5.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.5.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.5.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.5.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.5.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.5.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.5.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.5.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.6.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.6.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.6.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.6.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.6.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.6.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.6.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.6.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.6.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.7.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.7.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.7.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.7.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.7.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.7.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.7.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.7.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.7.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.8.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.8.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.8.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.8.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.8.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.8.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.8.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.8.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.8.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.9.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.9.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.9.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.9.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.9.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.9.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.9.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.9.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.block.9.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
+    "transformer.encoder.final_layer_norm.weight": "model-00001-of-00003.safetensors",
+    "transformer.shared.weight": "model-00001-of-00003.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,125 @@
+{
+  "additional_special_tokens": [
+    "<extra_id_0>",
+    "<extra_id_1>",
+    "<extra_id_2>",
+    "<extra_id_3>",
+    "<extra_id_4>",
+    "<extra_id_5>",
+    "<extra_id_6>",
+    "<extra_id_7>",
+    "<extra_id_8>",
+    "<extra_id_9>",
+    "<extra_id_10>",
+    "<extra_id_11>",
+    "<extra_id_12>",
+    "<extra_id_13>",
+    "<extra_id_14>",
+    "<extra_id_15>",
+    "<extra_id_16>",
+    "<extra_id_17>",
+    "<extra_id_18>",
+    "<extra_id_19>",
+    "<extra_id_20>",
+    "<extra_id_21>",
+    "<extra_id_22>",
+    "<extra_id_23>",
+    "<extra_id_24>",
+    "<extra_id_25>",
+    "<extra_id_26>",
+    "<extra_id_27>",
+    "<extra_id_28>",
+    "<extra_id_29>",
+    "<extra_id_30>",
+    "<extra_id_31>",
+    "<extra_id_32>",
+    "<extra_id_33>",
+    "<extra_id_34>",
+    "<extra_id_35>",
+    "<extra_id_36>",
+    "<extra_id_37>",
+    "<extra_id_38>",
+    "<extra_id_39>",
+    "<extra_id_40>",
+    "<extra_id_41>",
+    "<extra_id_42>",
+    "<extra_id_43>",
+    "<extra_id_44>",
+    "<extra_id_45>",
+    "<extra_id_46>",
+    "<extra_id_47>",
+    "<extra_id_48>",
+    "<extra_id_49>",
+    "<extra_id_50>",
+    "<extra_id_51>",
+    "<extra_id_52>",
+    "<extra_id_53>",
+    "<extra_id_54>",
+    "<extra_id_55>",
+    "<extra_id_56>",
+    "<extra_id_57>",
+    "<extra_id_58>",
+    "<extra_id_59>",
+    "<extra_id_60>",
+    "<extra_id_61>",
+    "<extra_id_62>",
+    "<extra_id_63>",
+    "<extra_id_64>",
+    "<extra_id_65>",
+    "<extra_id_66>",
+    "<extra_id_67>",
+    "<extra_id_68>",
+    "<extra_id_69>",
+    "<extra_id_70>",
+    "<extra_id_71>",
+    "<extra_id_72>",
+    "<extra_id_73>",
+    "<extra_id_74>",
+    "<extra_id_75>",
+    "<extra_id_76>",
+    "<extra_id_77>",
+    "<extra_id_78>",
+    "<extra_id_79>",
+    "<extra_id_80>",
+    "<extra_id_81>",
+    "<extra_id_82>",
+    "<extra_id_83>",
+    "<extra_id_84>",
+    "<extra_id_85>",
+    "<extra_id_86>",
+    "<extra_id_87>",
+    "<extra_id_88>",
+    "<extra_id_89>",
+    "<extra_id_90>",
+    "<extra_id_91>",
+    "<extra_id_92>",
+    "<extra_id_93>",
+    "<extra_id_94>",
+    "<extra_id_95>",
+    "<extra_id_96>",
+    "<extra_id_97>",
+    "<extra_id_98>",
+    "<extra_id_99>"
+  ],
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
+size 791656

tokenizer_config.json

@@ -0,0 +1,938 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32000": {
+      "content": "<extra_id_99>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<extra_id_98>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32002": {
+      "content": "<extra_id_97>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32003": {
+      "content": "<extra_id_96>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32004": {
+      "content": "<extra_id_95>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32005": {
+      "content": "<extra_id_94>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32006": {
+      "content": "<extra_id_93>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32007": {
+      "content": "<extra_id_92>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32008": {
+      "content": "<extra_id_91>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32009": {
+      "content": "<extra_id_90>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32010": {
+      "content": "<extra_id_89>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32011": {
+      "content": "<extra_id_88>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32012": {
+      "content": "<extra_id_87>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32013": {
+      "content": "<extra_id_86>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32014": {
+      "content": "<extra_id_85>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32015": {
+      "content": "<extra_id_84>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32016": {
+      "content": "<extra_id_83>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32017": {
+      "content": "<extra_id_82>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32018": {
+      "content": "<extra_id_81>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32019": {
+      "content": "<extra_id_80>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32020": {
+      "content": "<extra_id_79>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32021": {
+      "content": "<extra_id_78>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32022": {
+      "content": "<extra_id_77>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32023": {
+      "content": "<extra_id_76>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32024": {
+      "content": "<extra_id_75>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32025": {
+      "content": "<extra_id_74>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32026": {
+      "content": "<extra_id_73>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32027": {
+      "content": "<extra_id_72>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32028": {
+      "content": "<extra_id_71>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32029": {
+      "content": "<extra_id_70>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32030": {
+      "content": "<extra_id_69>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32031": {
+      "content": "<extra_id_68>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32032": {
+      "content": "<extra_id_67>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32033": {
+      "content": "<extra_id_66>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32034": {
+      "content": "<extra_id_65>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32035": {
+      "content": "<extra_id_64>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32036": {
+      "content": "<extra_id_63>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32037": {
+      "content": "<extra_id_62>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32038": {
+      "content": "<extra_id_61>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32039": {
+      "content": "<extra_id_60>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32040": {
+      "content": "<extra_id_59>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32041": {
+      "content": "<extra_id_58>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32042": {
+      "content": "<extra_id_57>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32043": {
+      "content": "<extra_id_56>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32044": {
+      "content": "<extra_id_55>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32045": {
+      "content": "<extra_id_54>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32046": {
+      "content": "<extra_id_53>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32047": {
+      "content": "<extra_id_52>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32048": {
+      "content": "<extra_id_51>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32049": {
+      "content": "<extra_id_50>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32050": {
+      "content": "<extra_id_49>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32051": {
+      "content": "<extra_id_48>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32052": {
+      "content": "<extra_id_47>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32053": {
+      "content": "<extra_id_46>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32054": {
+      "content": "<extra_id_45>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32055": {
+      "content": "<extra_id_44>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32056": {
+      "content": "<extra_id_43>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32057": {
+      "content": "<extra_id_42>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32058": {
+      "content": "<extra_id_41>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32059": {
+      "content": "<extra_id_40>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32060": {
+      "content": "<extra_id_39>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32061": {
+      "content": "<extra_id_38>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32062": {
+      "content": "<extra_id_37>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32063": {
+      "content": "<extra_id_36>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32064": {
+      "content": "<extra_id_35>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32065": {
+      "content": "<extra_id_34>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32066": {
+      "content": "<extra_id_33>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32067": {
+      "content": "<extra_id_32>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32068": {
+      "content": "<extra_id_31>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32069": {
+      "content": "<extra_id_30>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32070": {
+      "content": "<extra_id_29>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32071": {
+      "content": "<extra_id_28>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32072": {
+      "content": "<extra_id_27>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32073": {
+      "content": "<extra_id_26>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32074": {
+      "content": "<extra_id_25>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32075": {
+      "content": "<extra_id_24>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32076": {
+      "content": "<extra_id_23>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32077": {
+      "content": "<extra_id_22>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32078": {
+      "content": "<extra_id_21>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32079": {
+      "content": "<extra_id_20>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32080": {
+      "content": "<extra_id_19>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32081": {
+      "content": "<extra_id_18>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32082": {
+      "content": "<extra_id_17>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32083": {
+      "content": "<extra_id_16>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32084": {
+      "content": "<extra_id_15>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32085": {
+      "content": "<extra_id_14>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32086": {
+      "content": "<extra_id_13>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32087": {
+      "content": "<extra_id_12>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32088": {
+      "content": "<extra_id_11>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32089": {
+      "content": "<extra_id_10>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32090": {
+      "content": "<extra_id_9>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32091": {
+      "content": "<extra_id_8>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32092": {
+      "content": "<extra_id_7>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32093": {
+      "content": "<extra_id_6>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32094": {
+      "content": "<extra_id_5>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32095": {
+      "content": "<extra_id_4>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32096": {
+      "content": "<extra_id_3>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32097": {
+      "content": "<extra_id_2>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32098": {
+      "content": "<extra_id_1>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32099": {
+      "content": "<extra_id_0>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<extra_id_0>",
+    "<extra_id_1>",
+    "<extra_id_2>",
+    "<extra_id_3>",
+    "<extra_id_4>",
+    "<extra_id_5>",
+    "<extra_id_6>",
+    "<extra_id_7>",
+    "<extra_id_8>",
+    "<extra_id_9>",
+    "<extra_id_10>",
+    "<extra_id_11>",
+    "<extra_id_12>",
+    "<extra_id_13>",
+    "<extra_id_14>",
+    "<extra_id_15>",
+    "<extra_id_16>",
+    "<extra_id_17>",
+    "<extra_id_18>",
+    "<extra_id_19>",
+    "<extra_id_20>",
+    "<extra_id_21>",
+    "<extra_id_22>",
+    "<extra_id_23>",
+    "<extra_id_24>",
+    "<extra_id_25>",
+    "<extra_id_26>",
+    "<extra_id_27>",
+    "<extra_id_28>",
+    "<extra_id_29>",
+    "<extra_id_30>",
+    "<extra_id_31>",
+    "<extra_id_32>",
+    "<extra_id_33>",
+    "<extra_id_34>",
+    "<extra_id_35>",
+    "<extra_id_36>",
+    "<extra_id_37>",
+    "<extra_id_38>",
+    "<extra_id_39>",
+    "<extra_id_40>",
+    "<extra_id_41>",
+    "<extra_id_42>",
+    "<extra_id_43>",
+    "<extra_id_44>",
+    "<extra_id_45>",
+    "<extra_id_46>",
+    "<extra_id_47>",
+    "<extra_id_48>",
+    "<extra_id_49>",
+    "<extra_id_50>",
+    "<extra_id_51>",
+    "<extra_id_52>",
+    "<extra_id_53>",
+    "<extra_id_54>",
+    "<extra_id_55>",
+    "<extra_id_56>",
+    "<extra_id_57>",
+    "<extra_id_58>",
+    "<extra_id_59>",
+    "<extra_id_60>",
+    "<extra_id_61>",
+    "<extra_id_62>",
+    "<extra_id_63>",
+    "<extra_id_64>",
+    "<extra_id_65>",
+    "<extra_id_66>",
+    "<extra_id_67>",
+    "<extra_id_68>",
+    "<extra_id_69>",
+    "<extra_id_70>",
+    "<extra_id_71>",
+    "<extra_id_72>",
+    "<extra_id_73>",
+    "<extra_id_74>",
+    "<extra_id_75>",
+    "<extra_id_76>",
+    "<extra_id_77>",
+    "<extra_id_78>",
+    "<extra_id_79>",
+    "<extra_id_80>",
+    "<extra_id_81>",
+    "<extra_id_82>",
+    "<extra_id_83>",
+    "<extra_id_84>",
+    "<extra_id_85>",
+    "<extra_id_86>",
+    "<extra_id_87>",
+    "<extra_id_88>",
+    "<extra_id_89>",
+    "<extra_id_90>",
+    "<extra_id_91>",
+    "<extra_id_92>",
+    "<extra_id_93>",
+    "<extra_id_94>",
+    "<extra_id_95>",
+    "<extra_id_96>",
+    "<extra_id_97>",
+    "<extra_id_98>",
+    "<extra_id_99>"
+  ],
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "</s>",
+  "extra_ids": 100,
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "T5Tokenizer",
+  "unk_token": "<unk>"
+}