Upload 12 files

config.json

@@ -0,0 +1,34 @@
+{
+  "architectures": [
+    "DebertaV2ForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 2048,
+  "initializer_range": 0.01,
+  "intermediate_size": 8192,
+  "layer_norm_eps": 1e-07,
+  "max_position_embeddings": 512,
+  "max_relative_positions": -1,
+  "model_type": "deberta-v2",
+  "norm_rel_ebd": "layer_norm",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 3,
+  "pooler_dropout": 0,
+  "pooler_hidden_act": "gelu",
+  "pooler_hidden_size": 1024,
+  "pos_att_type": [
+    "p2c",
+    "c2p"
+  ],
+  "position_biased_input": false,
+  "position_buckets": 256,
+  "relative_attention": true,
+  "share_att_key": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.21.3",
+  "type_vocab_size": 0,
+  "vocab_size": 63998
+}

gitattributes.txt

@@ -0,0 +1,32 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.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
+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
+*.tgz 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
+*tfevents* filter=lfs diff=lfs merge=lfs -text

pytorch_model-00001-of-00006.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58cf5c907b55c049566b8138f5c0c58c94e697180d4b7258f18d4499cb990c62
+size 994331035

pytorch_model-00002-of-00006.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9096970105021af7e31640a36b15347a3aed36b8c269dda6704011a342e08ecb
+size 990388609

pytorch_model-00003-of-00006.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab1b72f39862c72db82114744c37b9d17e9c684f040560a6081f343de3afa724
+size 990405691

pytorch_model-00004-of-00006.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bab60524f04d4ddbbd633ac75907caf9b2d6cc8a2628fa0af30982a2bdf975dd
+size 990405755

pytorch_model-00005-of-00006.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:336033420a6c5a3438fc0c90e31d5c6b4f79e60ed6ddb864df2020a66dc2659e
+size 990405755

pytorch_model-00006-of-00006.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb41ad853eb7780c00465dcb961dc7782600e3a8b5e044fb1968b9bc2bdea562
+size 948419306

pytorch_model.bin.index.json

@@ -0,0 +1,405 @@
+{
+  "metadata": {
+    "total_size": 5904482288
+  },
+  "weight_map": {
+    "cls.predictions.bias": "pytorch_model-00006-of-00006.bin",
+    "cls.predictions.decoder.bias": "pytorch_model-00006-of-00006.bin",
+    "cls.predictions.decoder.weight": "pytorch_model-00006-of-00006.bin",
+    "cls.predictions.transform.LayerNorm.bias": "pytorch_model-00006-of-00006.bin",
+    "cls.predictions.transform.LayerNorm.weight": "pytorch_model-00006-of-00006.bin",
+    "cls.predictions.transform.dense.bias": "pytorch_model-00006-of-00006.bin",
+    "cls.predictions.transform.dense.weight": "pytorch_model-00006-of-00006.bin",
+    "deberta.embeddings.LayerNorm.bias": "pytorch_model-00001-of-00006.bin",
+    "deberta.embeddings.LayerNorm.weight": "pytorch_model-00001-of-00006.bin",
+    "deberta.embeddings.position_ids": "pytorch_model-00001-of-00006.bin",
+    "deberta.embeddings.word_embeddings.weight": "pytorch_model-00001-of-00006.bin",
+    "deberta.encoder.LayerNorm.bias": "pytorch_model-00006-of-00006.bin",
+    "deberta.encoder.LayerNorm.weight": "pytorch_model-00006-of-00006.bin",
+    "deberta.encoder.layer.0.attention.output.LayerNorm.bias": "pytorch_model-00001-of-00006.bin",
+    "deberta.encoder.layer.0.attention.output.LayerNorm.weight": "pytorch_model-00001-of-00006.bin",
+    "deberta.encoder.layer.0.attention.output.dense.bias": "pytorch_model-00001-of-00006.bin",
+    "deberta.encoder.layer.0.attention.output.dense.weight": "pytorch_model-00001-of-00006.bin",
+    "deberta.encoder.layer.0.attention.self.key_proj.bias": "pytorch_model-00001-of-00006.bin",
+    "deberta.encoder.layer.0.attention.self.key_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "deberta.encoder.layer.0.attention.self.query_proj.bias": "pytorch_model-00001-of-00006.bin",
+    "deberta.encoder.layer.0.attention.self.query_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "deberta.encoder.layer.0.attention.self.value_proj.bias": "pytorch_model-00001-of-00006.bin",
+    "deberta.encoder.layer.0.attention.self.value_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "deberta.encoder.layer.0.intermediate.dense.bias": "pytorch_model-00001-of-00006.bin",
+    "deberta.encoder.layer.0.intermediate.dense.weight": "pytorch_model-00001-of-00006.bin",
+    "deberta.encoder.layer.0.output.LayerNorm.bias": "pytorch_model-00001-of-00006.bin",
+    "deberta.encoder.layer.0.output.LayerNorm.weight": "pytorch_model-00001-of-00006.bin",
+    "deberta.encoder.layer.0.output.dense.bias": "pytorch_model-00001-of-00006.bin",
+    "deberta.encoder.layer.0.output.dense.weight": "pytorch_model-00001-of-00006.bin",
+    "deberta.encoder.layer.1.attention.output.LayerNorm.bias": "pytorch_model-00001-of-00006.bin",
+    "deberta.encoder.layer.1.attention.output.LayerNorm.weight": "pytorch_model-00001-of-00006.bin",
+    "deberta.encoder.layer.1.attention.output.dense.bias": "pytorch_model-00001-of-00006.bin",
+    "deberta.encoder.layer.1.attention.output.dense.weight": "pytorch_model-00001-of-00006.bin",
+    "deberta.encoder.layer.1.attention.self.key_proj.bias": "pytorch_model-00001-of-00006.bin",
+    "deberta.encoder.layer.1.attention.self.key_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "deberta.encoder.layer.1.attention.self.query_proj.bias": "pytorch_model-00001-of-00006.bin",
+    "deberta.encoder.layer.1.attention.self.query_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "deberta.encoder.layer.1.attention.self.value_proj.bias": "pytorch_model-00001-of-00006.bin",
+    "deberta.encoder.layer.1.attention.self.value_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "deberta.encoder.layer.1.intermediate.dense.bias": "pytorch_model-00001-of-00006.bin",
+    "deberta.encoder.layer.1.intermediate.dense.weight": "pytorch_model-00001-of-00006.bin",
+    "deberta.encoder.layer.1.output.LayerNorm.bias": "pytorch_model-00001-of-00006.bin",
+    "deberta.encoder.layer.1.output.LayerNorm.weight": "pytorch_model-00001-of-00006.bin",
+    "deberta.encoder.layer.1.output.dense.bias": "pytorch_model-00001-of-00006.bin",
+    "deberta.encoder.layer.1.output.dense.weight": "pytorch_model-00001-of-00006.bin",
+    "deberta.encoder.layer.10.attention.output.LayerNorm.bias": "pytorch_model-00003-of-00006.bin",
+    "deberta.encoder.layer.10.attention.output.LayerNorm.weight": "pytorch_model-00003-of-00006.bin",
+    "deberta.encoder.layer.10.attention.output.dense.bias": "pytorch_model-00003-of-00006.bin",
+    "deberta.encoder.layer.10.attention.output.dense.weight": "pytorch_model-00003-of-00006.bin",
+    "deberta.encoder.layer.10.attention.self.key_proj.bias": "pytorch_model-00003-of-00006.bin",
+    "deberta.encoder.layer.10.attention.self.key_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "deberta.encoder.layer.10.attention.self.query_proj.bias": "pytorch_model-00003-of-00006.bin",
+    "deberta.encoder.layer.10.attention.self.query_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "deberta.encoder.layer.10.attention.self.value_proj.bias": "pytorch_model-00003-of-00006.bin",
+    "deberta.encoder.layer.10.attention.self.value_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "deberta.encoder.layer.10.intermediate.dense.bias": "pytorch_model-00003-of-00006.bin",
+    "deberta.encoder.layer.10.intermediate.dense.weight": "pytorch_model-00003-of-00006.bin",
+    "deberta.encoder.layer.10.output.LayerNorm.bias": "pytorch_model-00003-of-00006.bin",
+    "deberta.encoder.layer.10.output.LayerNorm.weight": "pytorch_model-00003-of-00006.bin",
+    "deberta.encoder.layer.10.output.dense.bias": "pytorch_model-00003-of-00006.bin",
+    "deberta.encoder.layer.10.output.dense.weight": "pytorch_model-00003-of-00006.bin",
+    "deberta.encoder.layer.11.attention.output.LayerNorm.bias": "pytorch_model-00003-of-00006.bin",
+    "deberta.encoder.layer.11.attention.output.LayerNorm.weight": "pytorch_model-00003-of-00006.bin",
+    "deberta.encoder.layer.11.attention.output.dense.bias": "pytorch_model-00003-of-00006.bin",
+    "deberta.encoder.layer.11.attention.output.dense.weight": "pytorch_model-00003-of-00006.bin",
+    "deberta.encoder.layer.11.attention.self.key_proj.bias": "pytorch_model-00003-of-00006.bin",
+    "deberta.encoder.layer.11.attention.self.key_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "deberta.encoder.layer.11.attention.self.query_proj.bias": "pytorch_model-00003-of-00006.bin",
+    "deberta.encoder.layer.11.attention.self.query_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "deberta.encoder.layer.11.attention.self.value_proj.bias": "pytorch_model-00003-of-00006.bin",
+    "deberta.encoder.layer.11.attention.self.value_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "deberta.encoder.layer.11.intermediate.dense.bias": "pytorch_model-00003-of-00006.bin",
+    "deberta.encoder.layer.11.intermediate.dense.weight": "pytorch_model-00003-of-00006.bin",
+    "deberta.encoder.layer.11.output.LayerNorm.bias": "pytorch_model-00003-of-00006.bin",
+    "deberta.encoder.layer.11.output.LayerNorm.weight": "pytorch_model-00003-of-00006.bin",
+    "deberta.encoder.layer.11.output.dense.bias": "pytorch_model-00003-of-00006.bin",
+    "deberta.encoder.layer.11.output.dense.weight": "pytorch_model-00003-of-00006.bin",
+    "deberta.encoder.layer.12.attention.output.LayerNorm.bias": "pytorch_model-00004-of-00006.bin",
+    "deberta.encoder.layer.12.attention.output.LayerNorm.weight": "pytorch_model-00004-of-00006.bin",
+    "deberta.encoder.layer.12.attention.output.dense.bias": "pytorch_model-00004-of-00006.bin",
+    "deberta.encoder.layer.12.attention.output.dense.weight": "pytorch_model-00004-of-00006.bin",
+    "deberta.encoder.layer.12.attention.self.key_proj.bias": "pytorch_model-00003-of-00006.bin",
+    "deberta.encoder.layer.12.attention.self.key_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "deberta.encoder.layer.12.attention.self.query_proj.bias": "pytorch_model-00003-of-00006.bin",
+    "deberta.encoder.layer.12.attention.self.query_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "deberta.encoder.layer.12.attention.self.value_proj.bias": "pytorch_model-00004-of-00006.bin",
+    "deberta.encoder.layer.12.attention.self.value_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "deberta.encoder.layer.12.intermediate.dense.bias": "pytorch_model-00004-of-00006.bin",
+    "deberta.encoder.layer.12.intermediate.dense.weight": "pytorch_model-00004-of-00006.bin",
+    "deberta.encoder.layer.12.output.LayerNorm.bias": "pytorch_model-00004-of-00006.bin",
+    "deberta.encoder.layer.12.output.LayerNorm.weight": "pytorch_model-00004-of-00006.bin",
+    "deberta.encoder.layer.12.output.dense.bias": "pytorch_model-00004-of-00006.bin",
+    "deberta.encoder.layer.12.output.dense.weight": "pytorch_model-00004-of-00006.bin",
+    "deberta.encoder.layer.13.attention.output.LayerNorm.bias": "pytorch_model-00004-of-00006.bin",
+    "deberta.encoder.layer.13.attention.output.LayerNorm.weight": "pytorch_model-00004-of-00006.bin",
+    "deberta.encoder.layer.13.attention.output.dense.bias": "pytorch_model-00004-of-00006.bin",
+    "deberta.encoder.layer.13.attention.output.dense.weight": "pytorch_model-00004-of-00006.bin",
+    "deberta.encoder.layer.13.attention.self.key_proj.bias": "pytorch_model-00004-of-00006.bin",
+    "deberta.encoder.layer.13.attention.self.key_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "deberta.encoder.layer.13.attention.self.query_proj.bias": "pytorch_model-00004-of-00006.bin",
+    "deberta.encoder.layer.13.attention.self.query_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "deberta.encoder.layer.13.attention.self.value_proj.bias": "pytorch_model-00004-of-00006.bin",
+    "deberta.encoder.layer.13.attention.self.value_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "deberta.encoder.layer.13.intermediate.dense.bias": "pytorch_model-00004-of-00006.bin",
+    "deberta.encoder.layer.13.intermediate.dense.weight": "pytorch_model-00004-of-00006.bin",
+    "deberta.encoder.layer.13.output.LayerNorm.bias": "pytorch_model-00004-of-00006.bin",
+    "deberta.encoder.layer.13.output.LayerNorm.weight": "pytorch_model-00004-of-00006.bin",
+    "deberta.encoder.layer.13.output.dense.bias": "pytorch_model-00004-of-00006.bin",
+    "deberta.encoder.layer.13.output.dense.weight": "pytorch_model-00004-of-00006.bin",
+    "deberta.encoder.layer.14.attention.output.LayerNorm.bias": "pytorch_model-00004-of-00006.bin",
+    "deberta.encoder.layer.14.attention.output.LayerNorm.weight": "pytorch_model-00004-of-00006.bin",
+    "deberta.encoder.layer.14.attention.output.dense.bias": "pytorch_model-00004-of-00006.bin",
+    "deberta.encoder.layer.14.attention.output.dense.weight": "pytorch_model-00004-of-00006.bin",
+    "deberta.encoder.layer.14.attention.self.key_proj.bias": "pytorch_model-00004-of-00006.bin",
+    "deberta.encoder.layer.14.attention.self.key_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "deberta.encoder.layer.14.attention.self.query_proj.bias": "pytorch_model-00004-of-00006.bin",
+    "deberta.encoder.layer.14.attention.self.query_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "deberta.encoder.layer.14.attention.self.value_proj.bias": "pytorch_model-00004-of-00006.bin",
+    "deberta.encoder.layer.14.attention.self.value_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "deberta.encoder.layer.14.intermediate.dense.bias": "pytorch_model-00004-of-00006.bin",
+    "deberta.encoder.layer.14.intermediate.dense.weight": "pytorch_model-00004-of-00006.bin",
+    "deberta.encoder.layer.14.output.LayerNorm.bias": "pytorch_model-00004-of-00006.bin",
+    "deberta.encoder.layer.14.output.LayerNorm.weight": "pytorch_model-00004-of-00006.bin",
+    "deberta.encoder.layer.14.output.dense.bias": "pytorch_model-00004-of-00006.bin",
+    "deberta.encoder.layer.14.output.dense.weight": "pytorch_model-00004-of-00006.bin",
+    "deberta.encoder.layer.15.attention.output.LayerNorm.bias": "pytorch_model-00004-of-00006.bin",
+    "deberta.encoder.layer.15.attention.output.LayerNorm.weight": "pytorch_model-00004-of-00006.bin",
+    "deberta.encoder.layer.15.attention.output.dense.bias": "pytorch_model-00004-of-00006.bin",
+    "deberta.encoder.layer.15.attention.output.dense.weight": "pytorch_model-00004-of-00006.bin",
+    "deberta.encoder.layer.15.attention.self.key_proj.bias": "pytorch_model-00004-of-00006.bin",
+    "deberta.encoder.layer.15.attention.self.key_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "deberta.encoder.layer.15.attention.self.query_proj.bias": "pytorch_model-00004-of-00006.bin",
+    "deberta.encoder.layer.15.attention.self.query_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "deberta.encoder.layer.15.attention.self.value_proj.bias": "pytorch_model-00004-of-00006.bin",
+    "deberta.encoder.layer.15.attention.self.value_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "deberta.encoder.layer.15.intermediate.dense.bias": "pytorch_model-00004-of-00006.bin",
+    "deberta.encoder.layer.15.intermediate.dense.weight": "pytorch_model-00004-of-00006.bin",
+    "deberta.encoder.layer.15.output.LayerNorm.bias": "pytorch_model-00004-of-00006.bin",
+    "deberta.encoder.layer.15.output.LayerNorm.weight": "pytorch_model-00004-of-00006.bin",
+    "deberta.encoder.layer.15.output.dense.bias": "pytorch_model-00004-of-00006.bin",
+    "deberta.encoder.layer.15.output.dense.weight": "pytorch_model-00004-of-00006.bin",
+    "deberta.encoder.layer.16.attention.output.LayerNorm.bias": "pytorch_model-00004-of-00006.bin",
+    "deberta.encoder.layer.16.attention.output.LayerNorm.weight": "pytorch_model-00004-of-00006.bin",
+    "deberta.encoder.layer.16.attention.output.dense.bias": "pytorch_model-00004-of-00006.bin",
+    "deberta.encoder.layer.16.attention.output.dense.weight": "pytorch_model-00004-of-00006.bin",
+    "deberta.encoder.layer.16.attention.self.key_proj.bias": "pytorch_model-00004-of-00006.bin",
+    "deberta.encoder.layer.16.attention.self.key_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "deberta.encoder.layer.16.attention.self.query_proj.bias": "pytorch_model-00004-of-00006.bin",
+    "deberta.encoder.layer.16.attention.self.query_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "deberta.encoder.layer.16.attention.self.value_proj.bias": "pytorch_model-00004-of-00006.bin",
+    "deberta.encoder.layer.16.attention.self.value_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "deberta.encoder.layer.16.intermediate.dense.bias": "pytorch_model-00004-of-00006.bin",
+    "deberta.encoder.layer.16.intermediate.dense.weight": "pytorch_model-00004-of-00006.bin",
+    "deberta.encoder.layer.16.output.LayerNorm.bias": "pytorch_model-00004-of-00006.bin",
+    "deberta.encoder.layer.16.output.LayerNorm.weight": "pytorch_model-00004-of-00006.bin",
+    "deberta.encoder.layer.16.output.dense.bias": "pytorch_model-00004-of-00006.bin",
+    "deberta.encoder.layer.16.output.dense.weight": "pytorch_model-00004-of-00006.bin",
+    "deberta.encoder.layer.17.attention.output.LayerNorm.bias": "pytorch_model-00005-of-00006.bin",
+    "deberta.encoder.layer.17.attention.output.LayerNorm.weight": "pytorch_model-00005-of-00006.bin",
+    "deberta.encoder.layer.17.attention.output.dense.bias": "pytorch_model-00005-of-00006.bin",
+    "deberta.encoder.layer.17.attention.output.dense.weight": "pytorch_model-00005-of-00006.bin",
+    "deberta.encoder.layer.17.attention.self.key_proj.bias": "pytorch_model-00005-of-00006.bin",
+    "deberta.encoder.layer.17.attention.self.key_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "deberta.encoder.layer.17.attention.self.query_proj.bias": "pytorch_model-00004-of-00006.bin",
+    "deberta.encoder.layer.17.attention.self.query_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "deberta.encoder.layer.17.attention.self.value_proj.bias": "pytorch_model-00005-of-00006.bin",
+    "deberta.encoder.layer.17.attention.self.value_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "deberta.encoder.layer.17.intermediate.dense.bias": "pytorch_model-00005-of-00006.bin",
+    "deberta.encoder.layer.17.intermediate.dense.weight": "pytorch_model-00005-of-00006.bin",
+    "deberta.encoder.layer.17.output.LayerNorm.bias": "pytorch_model-00005-of-00006.bin",
+    "deberta.encoder.layer.17.output.LayerNorm.weight": "pytorch_model-00005-of-00006.bin",
+    "deberta.encoder.layer.17.output.dense.bias": "pytorch_model-00005-of-00006.bin",
+    "deberta.encoder.layer.17.output.dense.weight": "pytorch_model-00005-of-00006.bin",
+    "deberta.encoder.layer.18.attention.output.LayerNorm.bias": "pytorch_model-00005-of-00006.bin",
+    "deberta.encoder.layer.18.attention.output.LayerNorm.weight": "pytorch_model-00005-of-00006.bin",
+    "deberta.encoder.layer.18.attention.output.dense.bias": "pytorch_model-00005-of-00006.bin",
+    "deberta.encoder.layer.18.attention.output.dense.weight": "pytorch_model-00005-of-00006.bin",
+    "deberta.encoder.layer.18.attention.self.key_proj.bias": "pytorch_model-00005-of-00006.bin",
+    "deberta.encoder.layer.18.attention.self.key_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "deberta.encoder.layer.18.attention.self.query_proj.bias": "pytorch_model-00005-of-00006.bin",
+    "deberta.encoder.layer.18.attention.self.query_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "deberta.encoder.layer.18.attention.self.value_proj.bias": "pytorch_model-00005-of-00006.bin",
+    "deberta.encoder.layer.18.attention.self.value_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "deberta.encoder.layer.18.intermediate.dense.bias": "pytorch_model-00005-of-00006.bin",
+    "deberta.encoder.layer.18.intermediate.dense.weight": "pytorch_model-00005-of-00006.bin",
+    "deberta.encoder.layer.18.output.LayerNorm.bias": "pytorch_model-00005-of-00006.bin",
+    "deberta.encoder.layer.18.output.LayerNorm.weight": "pytorch_model-00005-of-00006.bin",
+    "deberta.encoder.layer.18.output.dense.bias": "pytorch_model-00005-of-00006.bin",
+    "deberta.encoder.layer.18.output.dense.weight": "pytorch_model-00005-of-00006.bin",
+    "deberta.encoder.layer.19.attention.output.LayerNorm.bias": "pytorch_model-00005-of-00006.bin",
+    "deberta.encoder.layer.19.attention.output.LayerNorm.weight": "pytorch_model-00005-of-00006.bin",
+    "deberta.encoder.layer.19.attention.output.dense.bias": "pytorch_model-00005-of-00006.bin",
+    "deberta.encoder.layer.19.attention.output.dense.weight": "pytorch_model-00005-of-00006.bin",
+    "deberta.encoder.layer.19.attention.self.key_proj.bias": "pytorch_model-00005-of-00006.bin",
+    "deberta.encoder.layer.19.attention.self.key_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "deberta.encoder.layer.19.attention.self.query_proj.bias": "pytorch_model-00005-of-00006.bin",
+    "deberta.encoder.layer.19.attention.self.query_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "deberta.encoder.layer.19.attention.self.value_proj.bias": "pytorch_model-00005-of-00006.bin",
+    "deberta.encoder.layer.19.attention.self.value_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "deberta.encoder.layer.19.intermediate.dense.bias": "pytorch_model-00005-of-00006.bin",
+    "deberta.encoder.layer.19.intermediate.dense.weight": "pytorch_model-00005-of-00006.bin",
+    "deberta.encoder.layer.19.output.LayerNorm.bias": "pytorch_model-00005-of-00006.bin",
+    "deberta.encoder.layer.19.output.LayerNorm.weight": "pytorch_model-00005-of-00006.bin",
+    "deberta.encoder.layer.19.output.dense.bias": "pytorch_model-00005-of-00006.bin",
+    "deberta.encoder.layer.19.output.dense.weight": "pytorch_model-00005-of-00006.bin",
+    "deberta.encoder.layer.2.attention.output.LayerNorm.bias": "pytorch_model-00001-of-00006.bin",
+    "deberta.encoder.layer.2.attention.output.LayerNorm.weight": "pytorch_model-00001-of-00006.bin",
+    "deberta.encoder.layer.2.attention.output.dense.bias": "pytorch_model-00001-of-00006.bin",
+    "deberta.encoder.layer.2.attention.output.dense.weight": "pytorch_model-00001-of-00006.bin",
+    "deberta.encoder.layer.2.attention.self.key_proj.bias": "pytorch_model-00001-of-00006.bin",
+    "deberta.encoder.layer.2.attention.self.key_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "deberta.encoder.layer.2.attention.self.query_proj.bias": "pytorch_model-00001-of-00006.bin",
+    "deberta.encoder.layer.2.attention.self.query_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "deberta.encoder.layer.2.attention.self.value_proj.bias": "pytorch_model-00001-of-00006.bin",
+    "deberta.encoder.layer.2.attention.self.value_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "deberta.encoder.layer.2.intermediate.dense.bias": "pytorch_model-00002-of-00006.bin",
+    "deberta.encoder.layer.2.intermediate.dense.weight": "pytorch_model-00002-of-00006.bin",
+    "deberta.encoder.layer.2.output.LayerNorm.bias": "pytorch_model-00002-of-00006.bin",
+    "deberta.encoder.layer.2.output.LayerNorm.weight": "pytorch_model-00002-of-00006.bin",
+    "deberta.encoder.layer.2.output.dense.bias": "pytorch_model-00002-of-00006.bin",
+    "deberta.encoder.layer.2.output.dense.weight": "pytorch_model-00002-of-00006.bin",
+    "deberta.encoder.layer.20.attention.output.LayerNorm.bias": "pytorch_model-00005-of-00006.bin",
+    "deberta.encoder.layer.20.attention.output.LayerNorm.weight": "pytorch_model-00005-of-00006.bin",
+    "deberta.encoder.layer.20.attention.output.dense.bias": "pytorch_model-00005-of-00006.bin",
+    "deberta.encoder.layer.20.attention.output.dense.weight": "pytorch_model-00005-of-00006.bin",
+    "deberta.encoder.layer.20.attention.self.key_proj.bias": "pytorch_model-00005-of-00006.bin",
+    "deberta.encoder.layer.20.attention.self.key_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "deberta.encoder.layer.20.attention.self.query_proj.bias": "pytorch_model-00005-of-00006.bin",
+    "deberta.encoder.layer.20.attention.self.query_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "deberta.encoder.layer.20.attention.self.value_proj.bias": "pytorch_model-00005-of-00006.bin",
+    "deberta.encoder.layer.20.attention.self.value_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "deberta.encoder.layer.20.intermediate.dense.bias": "pytorch_model-00005-of-00006.bin",
+    "deberta.encoder.layer.20.intermediate.dense.weight": "pytorch_model-00005-of-00006.bin",
+    "deberta.encoder.layer.20.output.LayerNorm.bias": "pytorch_model-00005-of-00006.bin",
+    "deberta.encoder.layer.20.output.LayerNorm.weight": "pytorch_model-00005-of-00006.bin",
+    "deberta.encoder.layer.20.output.dense.bias": "pytorch_model-00005-of-00006.bin",
+    "deberta.encoder.layer.20.output.dense.weight": "pytorch_model-00005-of-00006.bin",
+    "deberta.encoder.layer.21.attention.output.LayerNorm.bias": "pytorch_model-00005-of-00006.bin",
+    "deberta.encoder.layer.21.attention.output.LayerNorm.weight": "pytorch_model-00005-of-00006.bin",
+    "deberta.encoder.layer.21.attention.output.dense.bias": "pytorch_model-00005-of-00006.bin",
+    "deberta.encoder.layer.21.attention.output.dense.weight": "pytorch_model-00005-of-00006.bin",
+    "deberta.encoder.layer.21.attention.self.key_proj.bias": "pytorch_model-00005-of-00006.bin",
+    "deberta.encoder.layer.21.attention.self.key_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "deberta.encoder.layer.21.attention.self.query_proj.bias": "pytorch_model-00005-of-00006.bin",
+    "deberta.encoder.layer.21.attention.self.query_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "deberta.encoder.layer.21.attention.self.value_proj.bias": "pytorch_model-00005-of-00006.bin",
+    "deberta.encoder.layer.21.attention.self.value_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "deberta.encoder.layer.21.intermediate.dense.bias": "pytorch_model-00005-of-00006.bin",
+    "deberta.encoder.layer.21.intermediate.dense.weight": "pytorch_model-00005-of-00006.bin",
+    "deberta.encoder.layer.21.output.LayerNorm.bias": "pytorch_model-00005-of-00006.bin",
+    "deberta.encoder.layer.21.output.LayerNorm.weight": "pytorch_model-00005-of-00006.bin",
+    "deberta.encoder.layer.21.output.dense.bias": "pytorch_model-00005-of-00006.bin",
+    "deberta.encoder.layer.21.output.dense.weight": "pytorch_model-00005-of-00006.bin",
+    "deberta.encoder.layer.22.attention.output.LayerNorm.bias": "pytorch_model-00006-of-00006.bin",
+    "deberta.encoder.layer.22.attention.output.LayerNorm.weight": "pytorch_model-00006-of-00006.bin",
+    "deberta.encoder.layer.22.attention.output.dense.bias": "pytorch_model-00006-of-00006.bin",
+    "deberta.encoder.layer.22.attention.output.dense.weight": "pytorch_model-00006-of-00006.bin",
+    "deberta.encoder.layer.22.attention.self.key_proj.bias": "pytorch_model-00006-of-00006.bin",
+    "deberta.encoder.layer.22.attention.self.key_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "deberta.encoder.layer.22.attention.self.query_proj.bias": "pytorch_model-00006-of-00006.bin",
+    "deberta.encoder.layer.22.attention.self.query_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "deberta.encoder.layer.22.attention.self.value_proj.bias": "pytorch_model-00006-of-00006.bin",
+    "deberta.encoder.layer.22.attention.self.value_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "deberta.encoder.layer.22.intermediate.dense.bias": "pytorch_model-00006-of-00006.bin",
+    "deberta.encoder.layer.22.intermediate.dense.weight": "pytorch_model-00006-of-00006.bin",
+    "deberta.encoder.layer.22.output.LayerNorm.bias": "pytorch_model-00006-of-00006.bin",
+    "deberta.encoder.layer.22.output.LayerNorm.weight": "pytorch_model-00006-of-00006.bin",
+    "deberta.encoder.layer.22.output.dense.bias": "pytorch_model-00006-of-00006.bin",
+    "deberta.encoder.layer.22.output.dense.weight": "pytorch_model-00006-of-00006.bin",
+    "deberta.encoder.layer.23.attention.output.LayerNorm.bias": "pytorch_model-00006-of-00006.bin",
+    "deberta.encoder.layer.23.attention.output.LayerNorm.weight": "pytorch_model-00006-of-00006.bin",
+    "deberta.encoder.layer.23.attention.output.dense.bias": "pytorch_model-00006-of-00006.bin",
+    "deberta.encoder.layer.23.attention.output.dense.weight": "pytorch_model-00006-of-00006.bin",
+    "deberta.encoder.layer.23.attention.self.key_proj.bias": "pytorch_model-00006-of-00006.bin",
+    "deberta.encoder.layer.23.attention.self.key_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "deberta.encoder.layer.23.attention.self.query_proj.bias": "pytorch_model-00006-of-00006.bin",
+    "deberta.encoder.layer.23.attention.self.query_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "deberta.encoder.layer.23.attention.self.value_proj.bias": "pytorch_model-00006-of-00006.bin",
+    "deberta.encoder.layer.23.attention.self.value_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "deberta.encoder.layer.23.intermediate.dense.bias": "pytorch_model-00006-of-00006.bin",
+    "deberta.encoder.layer.23.intermediate.dense.weight": "pytorch_model-00006-of-00006.bin",
+    "deberta.encoder.layer.23.output.LayerNorm.bias": "pytorch_model-00006-of-00006.bin",
+    "deberta.encoder.layer.23.output.LayerNorm.weight": "pytorch_model-00006-of-00006.bin",
+    "deberta.encoder.layer.23.output.dense.bias": "pytorch_model-00006-of-00006.bin",
+    "deberta.encoder.layer.23.output.dense.weight": "pytorch_model-00006-of-00006.bin",
+    "deberta.encoder.layer.3.attention.output.LayerNorm.bias": "pytorch_model-00002-of-00006.bin",
+    "deberta.encoder.layer.3.attention.output.LayerNorm.weight": "pytorch_model-00002-of-00006.bin",
+    "deberta.encoder.layer.3.attention.output.dense.bias": "pytorch_model-00002-of-00006.bin",
+    "deberta.encoder.layer.3.attention.output.dense.weight": "pytorch_model-00002-of-00006.bin",
+    "deberta.encoder.layer.3.attention.self.key_proj.bias": "pytorch_model-00002-of-00006.bin",
+    "deberta.encoder.layer.3.attention.self.key_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "deberta.encoder.layer.3.attention.self.query_proj.bias": "pytorch_model-00002-of-00006.bin",
+    "deberta.encoder.layer.3.attention.self.query_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "deberta.encoder.layer.3.attention.self.value_proj.bias": "pytorch_model-00002-of-00006.bin",
+    "deberta.encoder.layer.3.attention.self.value_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "deberta.encoder.layer.3.intermediate.dense.bias": "pytorch_model-00002-of-00006.bin",
+    "deberta.encoder.layer.3.intermediate.dense.weight": "pytorch_model-00002-of-00006.bin",
+    "deberta.encoder.layer.3.output.LayerNorm.bias": "pytorch_model-00002-of-00006.bin",
+    "deberta.encoder.layer.3.output.LayerNorm.weight": "pytorch_model-00002-of-00006.bin",
+    "deberta.encoder.layer.3.output.dense.bias": "pytorch_model-00002-of-00006.bin",
+    "deberta.encoder.layer.3.output.dense.weight": "pytorch_model-00002-of-00006.bin",
+    "deberta.encoder.layer.4.attention.output.LayerNorm.bias": "pytorch_model-00002-of-00006.bin",
+    "deberta.encoder.layer.4.attention.output.LayerNorm.weight": "pytorch_model-00002-of-00006.bin",
+    "deberta.encoder.layer.4.attention.output.dense.bias": "pytorch_model-00002-of-00006.bin",
+    "deberta.encoder.layer.4.attention.output.dense.weight": "pytorch_model-00002-of-00006.bin",
+    "deberta.encoder.layer.4.attention.self.key_proj.bias": "pytorch_model-00002-of-00006.bin",
+    "deberta.encoder.layer.4.attention.self.key_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "deberta.encoder.layer.4.attention.self.query_proj.bias": "pytorch_model-00002-of-00006.bin",
+    "deberta.encoder.layer.4.attention.self.query_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "deberta.encoder.layer.4.attention.self.value_proj.bias": "pytorch_model-00002-of-00006.bin",
+    "deberta.encoder.layer.4.attention.self.value_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "deberta.encoder.layer.4.intermediate.dense.bias": "pytorch_model-00002-of-00006.bin",
+    "deberta.encoder.layer.4.intermediate.dense.weight": "pytorch_model-00002-of-00006.bin",
+    "deberta.encoder.layer.4.output.LayerNorm.bias": "pytorch_model-00002-of-00006.bin",
+    "deberta.encoder.layer.4.output.LayerNorm.weight": "pytorch_model-00002-of-00006.bin",
+    "deberta.encoder.layer.4.output.dense.bias": "pytorch_model-00002-of-00006.bin",
+    "deberta.encoder.layer.4.output.dense.weight": "pytorch_model-00002-of-00006.bin",
+    "deberta.encoder.layer.5.attention.output.LayerNorm.bias": "pytorch_model-00002-of-00006.bin",
+    "deberta.encoder.layer.5.attention.output.LayerNorm.weight": "pytorch_model-00002-of-00006.bin",
+    "deberta.encoder.layer.5.attention.output.dense.bias": "pytorch_model-00002-of-00006.bin",
+    "deberta.encoder.layer.5.attention.output.dense.weight": "pytorch_model-00002-of-00006.bin",
+    "deberta.encoder.layer.5.attention.self.key_proj.bias": "pytorch_model-00002-of-00006.bin",
+    "deberta.encoder.layer.5.attention.self.key_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "deberta.encoder.layer.5.attention.self.query_proj.bias": "pytorch_model-00002-of-00006.bin",
+    "deberta.encoder.layer.5.attention.self.query_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "deberta.encoder.layer.5.attention.self.value_proj.bias": "pytorch_model-00002-of-00006.bin",
+    "deberta.encoder.layer.5.attention.self.value_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "deberta.encoder.layer.5.intermediate.dense.bias": "pytorch_model-00002-of-00006.bin",
+    "deberta.encoder.layer.5.intermediate.dense.weight": "pytorch_model-00002-of-00006.bin",
+    "deberta.encoder.layer.5.output.LayerNorm.bias": "pytorch_model-00002-of-00006.bin",
+    "deberta.encoder.layer.5.output.LayerNorm.weight": "pytorch_model-00002-of-00006.bin",
+    "deberta.encoder.layer.5.output.dense.bias": "pytorch_model-00002-of-00006.bin",
+    "deberta.encoder.layer.5.output.dense.weight": "pytorch_model-00002-of-00006.bin",
+    "deberta.encoder.layer.6.attention.output.LayerNorm.bias": "pytorch_model-00002-of-00006.bin",
+    "deberta.encoder.layer.6.attention.output.LayerNorm.weight": "pytorch_model-00002-of-00006.bin",
+    "deberta.encoder.layer.6.attention.output.dense.bias": "pytorch_model-00002-of-00006.bin",
+    "deberta.encoder.layer.6.attention.output.dense.weight": "pytorch_model-00002-of-00006.bin",
+    "deberta.encoder.layer.6.attention.self.key_proj.bias": "pytorch_model-00002-of-00006.bin",
+    "deberta.encoder.layer.6.attention.self.key_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "deberta.encoder.layer.6.attention.self.query_proj.bias": "pytorch_model-00002-of-00006.bin",
+    "deberta.encoder.layer.6.attention.self.query_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "deberta.encoder.layer.6.attention.self.value_proj.bias": "pytorch_model-00002-of-00006.bin",
+    "deberta.encoder.layer.6.attention.self.value_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "deberta.encoder.layer.6.intermediate.dense.bias": "pytorch_model-00002-of-00006.bin",
+    "deberta.encoder.layer.6.intermediate.dense.weight": "pytorch_model-00002-of-00006.bin",
+    "deberta.encoder.layer.6.output.LayerNorm.bias": "pytorch_model-00002-of-00006.bin",
+    "deberta.encoder.layer.6.output.LayerNorm.weight": "pytorch_model-00002-of-00006.bin",
+    "deberta.encoder.layer.6.output.dense.bias": "pytorch_model-00002-of-00006.bin",
+    "deberta.encoder.layer.6.output.dense.weight": "pytorch_model-00002-of-00006.bin",
+    "deberta.encoder.layer.7.attention.output.LayerNorm.bias": "pytorch_model-00003-of-00006.bin",
+    "deberta.encoder.layer.7.attention.output.LayerNorm.weight": "pytorch_model-00003-of-00006.bin",
+    "deberta.encoder.layer.7.attention.output.dense.bias": "pytorch_model-00003-of-00006.bin",
+    "deberta.encoder.layer.7.attention.output.dense.weight": "pytorch_model-00003-of-00006.bin",
+    "deberta.encoder.layer.7.attention.self.key_proj.bias": "pytorch_model-00002-of-00006.bin",
+    "deberta.encoder.layer.7.attention.self.key_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "deberta.encoder.layer.7.attention.self.query_proj.bias": "pytorch_model-00002-of-00006.bin",
+    "deberta.encoder.layer.7.attention.self.query_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "deberta.encoder.layer.7.attention.self.value_proj.bias": "pytorch_model-00002-of-00006.bin",
+    "deberta.encoder.layer.7.attention.self.value_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "deberta.encoder.layer.7.intermediate.dense.bias": "pytorch_model-00003-of-00006.bin",
+    "deberta.encoder.layer.7.intermediate.dense.weight": "pytorch_model-00003-of-00006.bin",
+    "deberta.encoder.layer.7.output.LayerNorm.bias": "pytorch_model-00003-of-00006.bin",
+    "deberta.encoder.layer.7.output.LayerNorm.weight": "pytorch_model-00003-of-00006.bin",
+    "deberta.encoder.layer.7.output.dense.bias": "pytorch_model-00003-of-00006.bin",
+    "deberta.encoder.layer.7.output.dense.weight": "pytorch_model-00003-of-00006.bin",
+    "deberta.encoder.layer.8.attention.output.LayerNorm.bias": "pytorch_model-00003-of-00006.bin",
+    "deberta.encoder.layer.8.attention.output.LayerNorm.weight": "pytorch_model-00003-of-00006.bin",
+    "deberta.encoder.layer.8.attention.output.dense.bias": "pytorch_model-00003-of-00006.bin",
+    "deberta.encoder.layer.8.attention.output.dense.weight": "pytorch_model-00003-of-00006.bin",
+    "deberta.encoder.layer.8.attention.self.key_proj.bias": "pytorch_model-00003-of-00006.bin",
+    "deberta.encoder.layer.8.attention.self.key_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "deberta.encoder.layer.8.attention.self.query_proj.bias": "pytorch_model-00003-of-00006.bin",
+    "deberta.encoder.layer.8.attention.self.query_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "deberta.encoder.layer.8.attention.self.value_proj.bias": "pytorch_model-00003-of-00006.bin",
+    "deberta.encoder.layer.8.attention.self.value_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "deberta.encoder.layer.8.intermediate.dense.bias": "pytorch_model-00003-of-00006.bin",
+    "deberta.encoder.layer.8.intermediate.dense.weight": "pytorch_model-00003-of-00006.bin",
+    "deberta.encoder.layer.8.output.LayerNorm.bias": "pytorch_model-00003-of-00006.bin",
+    "deberta.encoder.layer.8.output.LayerNorm.weight": "pytorch_model-00003-of-00006.bin",
+    "deberta.encoder.layer.8.output.dense.bias": "pytorch_model-00003-of-00006.bin",
+    "deberta.encoder.layer.8.output.dense.weight": "pytorch_model-00003-of-00006.bin",
+    "deberta.encoder.layer.9.attention.output.LayerNorm.bias": "pytorch_model-00003-of-00006.bin",
+    "deberta.encoder.layer.9.attention.output.LayerNorm.weight": "pytorch_model-00003-of-00006.bin",
+    "deberta.encoder.layer.9.attention.output.dense.bias": "pytorch_model-00003-of-00006.bin",
+    "deberta.encoder.layer.9.attention.output.dense.weight": "pytorch_model-00003-of-00006.bin",
+    "deberta.encoder.layer.9.attention.self.key_proj.bias": "pytorch_model-00003-of-00006.bin",
+    "deberta.encoder.layer.9.attention.self.key_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "deberta.encoder.layer.9.attention.self.query_proj.bias": "pytorch_model-00003-of-00006.bin",
+    "deberta.encoder.layer.9.attention.self.query_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "deberta.encoder.layer.9.attention.self.value_proj.bias": "pytorch_model-00003-of-00006.bin",
+    "deberta.encoder.layer.9.attention.self.value_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "deberta.encoder.layer.9.intermediate.dense.bias": "pytorch_model-00003-of-00006.bin",
+    "deberta.encoder.layer.9.intermediate.dense.weight": "pytorch_model-00003-of-00006.bin",
+    "deberta.encoder.layer.9.output.LayerNorm.bias": "pytorch_model-00003-of-00006.bin",
+    "deberta.encoder.layer.9.output.LayerNorm.weight": "pytorch_model-00003-of-00006.bin",
+    "deberta.encoder.layer.9.output.dense.bias": "pytorch_model-00003-of-00006.bin",
+    "deberta.encoder.layer.9.output.dense.weight": "pytorch_model-00003-of-00006.bin",
+    "deberta.encoder.rel_embeddings.weight": "pytorch_model-00006-of-00006.bin"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,9 @@
+{
+  "bos_token": "[BOS]",
+  "cls_token": "[CLS]",
+  "eos_token": "[EOS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,13 @@
+{
+  "bos_token": "[BOS]",
+  "cls_token": "[CLS]",
+  "eos_token": "[EOS]",
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "name_or_path": "kakaobrain/kogpt",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "special_tokens_map_file": null,
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "unk_token": "[UNK]"
+}