Upload 9 files

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[MASK]": 128000
+}

config.json

@@ -0,0 +1,38 @@
+{
+  "_name_or_path": "portugueseNLP/medialbertina_pt-pt_1b5",
+  "architectures": [
+    "DebertaV2ForMaskedLM"
+  ],
+  "attention_head_size": 64,
+  "attention_probs_dropout_prob": 0.1,
+  "conv_act": "gelu",
+  "conv_kernel_size": 3,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1536,
+  "initializer_range": 0.02,
+  "intermediate_size": 6144,
+  "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": 24,
+  "num_hidden_layers": 48,
+  "pad_token_id": 0,
+  "pooler_dropout": 0,
+  "pooler_hidden_act": "gelu",
+  "pooler_hidden_size": 1536,
+  "pos_att_type": [
+    "p2c",
+    "c2p"
+  ],
+  "position_biased_input": false,
+  "position_buckets": 256,
+  "relative_attention": true,
+  "share_att_key": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.36.2",
+  "type_vocab_size": 0,
+  "vocab_size": 128100
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83c136fcead70e01a8fa303a1e59e4d567d467fcab2c8c06fb5f909f2a7b76cd
+size 4999085984

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0bdf6440e7228cf1faf424e2fa76ef44fab4bb18512df4a1dc62e49676573777
+size 1269179000

model.safetensors.index.json

@@ -0,0 +1,790 @@
+{
+  "metadata": {
+    "total_size": 6268166544
+  },
+  "weight_map": {
+    "cls.predictions.bias": "model-00002-of-00002.safetensors",
+    "cls.predictions.transform.LayerNorm.bias": "model-00002-of-00002.safetensors",
+    "cls.predictions.transform.LayerNorm.weight": "model-00002-of-00002.safetensors",
+    "cls.predictions.transform.dense.bias": "model-00002-of-00002.safetensors",
+    "cls.predictions.transform.dense.weight": "model-00002-of-00002.safetensors",
+    "deberta.embeddings.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.embeddings.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.embeddings.word_embeddings.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.LayerNorm.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.LayerNorm.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.conv.LayerNorm.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.conv.LayerNorm.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.conv.conv.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.conv.conv.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.0.attention.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.0.attention.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.0.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.0.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.0.attention.self.key_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.0.attention.self.key_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.0.attention.self.query_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.0.attention.self.query_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.0.attention.self.value_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.0.attention.self.value_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.0.intermediate.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.0.intermediate.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.0.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.0.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.0.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.0.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.1.attention.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.1.attention.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.1.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.1.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.1.attention.self.key_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.1.attention.self.key_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.1.attention.self.query_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.1.attention.self.query_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.1.attention.self.value_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.1.attention.self.value_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.1.intermediate.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.1.intermediate.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.1.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.1.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.1.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.1.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.10.attention.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.10.attention.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.10.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.10.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.10.attention.self.key_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.10.attention.self.key_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.10.attention.self.query_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.10.attention.self.query_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.10.attention.self.value_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.10.attention.self.value_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.10.intermediate.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.10.intermediate.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.10.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.10.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.10.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.10.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.11.attention.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.11.attention.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.11.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.11.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.11.attention.self.key_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.11.attention.self.key_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.11.attention.self.query_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.11.attention.self.query_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.11.attention.self.value_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.11.attention.self.value_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.11.intermediate.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.11.intermediate.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.11.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.11.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.11.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.11.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.12.attention.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.12.attention.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.12.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.12.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.12.attention.self.key_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.12.attention.self.key_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.12.attention.self.query_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.12.attention.self.query_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.12.attention.self.value_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.12.attention.self.value_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.12.intermediate.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.12.intermediate.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.12.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.12.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.12.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.12.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.13.attention.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.13.attention.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.13.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.13.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.13.attention.self.key_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.13.attention.self.key_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.13.attention.self.query_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.13.attention.self.query_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.13.attention.self.value_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.13.attention.self.value_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.13.intermediate.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.13.intermediate.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.13.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.13.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.13.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.13.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.14.attention.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.14.attention.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.14.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.14.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.14.attention.self.key_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.14.attention.self.key_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.14.attention.self.query_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.14.attention.self.query_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.14.attention.self.value_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.14.attention.self.value_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.14.intermediate.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.14.intermediate.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.14.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.14.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.14.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.14.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.15.attention.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.15.attention.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.15.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.15.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.15.attention.self.key_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.15.attention.self.key_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.15.attention.self.query_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.15.attention.self.query_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.15.attention.self.value_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.15.attention.self.value_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.15.intermediate.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.15.intermediate.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.15.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.15.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.15.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.15.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.16.attention.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.16.attention.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.16.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.16.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.16.attention.self.key_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.16.attention.self.key_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.16.attention.self.query_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.16.attention.self.query_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.16.attention.self.value_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.16.attention.self.value_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.16.intermediate.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.16.intermediate.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.16.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.16.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.16.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.16.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.17.attention.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.17.attention.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.17.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.17.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.17.attention.self.key_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.17.attention.self.key_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.17.attention.self.query_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.17.attention.self.query_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.17.attention.self.value_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.17.attention.self.value_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.17.intermediate.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.17.intermediate.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.17.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.17.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.17.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.17.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.18.attention.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.18.attention.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.18.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.18.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.18.attention.self.key_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.18.attention.self.key_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.18.attention.self.query_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.18.attention.self.query_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.18.attention.self.value_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.18.attention.self.value_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.18.intermediate.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.18.intermediate.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.18.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.18.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.18.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.18.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.19.attention.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.19.attention.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.19.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.19.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.19.attention.self.key_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.19.attention.self.key_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.19.attention.self.query_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.19.attention.self.query_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.19.attention.self.value_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.19.attention.self.value_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.19.intermediate.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.19.intermediate.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.19.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.19.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.19.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.19.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.2.attention.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.2.attention.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.2.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.2.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.2.attention.self.key_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.2.attention.self.key_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.2.attention.self.query_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.2.attention.self.query_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.2.attention.self.value_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.2.attention.self.value_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.2.intermediate.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.2.intermediate.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.2.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.2.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.2.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.2.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.20.attention.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.20.attention.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.20.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.20.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.20.attention.self.key_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.20.attention.self.key_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.20.attention.self.query_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.20.attention.self.query_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.20.attention.self.value_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.20.attention.self.value_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.20.intermediate.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.20.intermediate.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.20.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.20.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.20.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.20.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.21.attention.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.21.attention.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.21.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.21.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.21.attention.self.key_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.21.attention.self.key_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.21.attention.self.query_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.21.attention.self.query_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.21.attention.self.value_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.21.attention.self.value_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.21.intermediate.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.21.intermediate.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.21.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.21.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.21.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.21.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.22.attention.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.22.attention.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.22.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.22.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.22.attention.self.key_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.22.attention.self.key_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.22.attention.self.query_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.22.attention.self.query_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.22.attention.self.value_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.22.attention.self.value_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.22.intermediate.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.22.intermediate.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.22.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.22.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.22.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.22.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.23.attention.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.23.attention.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.23.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.23.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.23.attention.self.key_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.23.attention.self.key_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.23.attention.self.query_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.23.attention.self.query_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.23.attention.self.value_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.23.attention.self.value_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.23.intermediate.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.23.intermediate.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.23.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.23.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.23.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.23.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.24.attention.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.24.attention.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.24.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.24.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.24.attention.self.key_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.24.attention.self.key_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.24.attention.self.query_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.24.attention.self.query_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.24.attention.self.value_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.24.attention.self.value_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.24.intermediate.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.24.intermediate.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.24.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.24.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.24.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.24.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.25.attention.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.25.attention.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.25.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.25.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.25.attention.self.key_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.25.attention.self.key_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.25.attention.self.query_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.25.attention.self.query_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.25.attention.self.value_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.25.attention.self.value_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.25.intermediate.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.25.intermediate.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.25.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.25.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.25.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.25.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.26.attention.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.26.attention.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.26.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.26.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.26.attention.self.key_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.26.attention.self.key_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.26.attention.self.query_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.26.attention.self.query_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.26.attention.self.value_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.26.attention.self.value_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.26.intermediate.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.26.intermediate.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.26.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.26.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.26.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.26.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.27.attention.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.27.attention.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.27.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.27.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.27.attention.self.key_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.27.attention.self.key_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.27.attention.self.query_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.27.attention.self.query_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.27.attention.self.value_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.27.attention.self.value_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.27.intermediate.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.27.intermediate.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.27.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.27.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.27.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.27.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.28.attention.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.28.attention.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.28.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.28.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.28.attention.self.key_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.28.attention.self.key_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.28.attention.self.query_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.28.attention.self.query_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.28.attention.self.value_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.28.attention.self.value_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.28.intermediate.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.28.intermediate.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.28.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.28.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.28.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.28.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.29.attention.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.29.attention.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.29.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.29.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.29.attention.self.key_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.29.attention.self.key_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.29.attention.self.query_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.29.attention.self.query_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.29.attention.self.value_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.29.attention.self.value_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.29.intermediate.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.29.intermediate.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.29.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.29.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.29.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.29.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.3.attention.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.3.attention.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.3.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.3.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.3.attention.self.key_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.3.attention.self.key_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.3.attention.self.query_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.3.attention.self.query_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.3.attention.self.value_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.3.attention.self.value_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.3.intermediate.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.3.intermediate.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.3.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.3.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.3.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.3.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.30.attention.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.30.attention.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.30.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.30.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.30.attention.self.key_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.30.attention.self.key_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.30.attention.self.query_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.30.attention.self.query_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.30.attention.self.value_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.30.attention.self.value_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.30.intermediate.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.30.intermediate.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.30.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.30.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.30.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.30.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.31.attention.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.31.attention.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.31.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.31.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.31.attention.self.key_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.31.attention.self.key_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.31.attention.self.query_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.31.attention.self.query_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.31.attention.self.value_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.31.attention.self.value_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.31.intermediate.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.31.intermediate.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.31.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.31.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.31.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.31.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.32.attention.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.32.attention.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.32.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.32.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.32.attention.self.key_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.32.attention.self.key_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.32.attention.self.query_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.32.attention.self.query_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.32.attention.self.value_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.32.attention.self.value_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.32.intermediate.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.32.intermediate.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.32.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.32.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.32.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.32.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.33.attention.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.33.attention.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.33.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.33.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.33.attention.self.key_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.33.attention.self.key_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.33.attention.self.query_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.33.attention.self.query_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.33.attention.self.value_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.33.attention.self.value_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.33.intermediate.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.33.intermediate.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.33.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.33.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.33.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.33.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.34.attention.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.34.attention.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.34.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.34.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.34.attention.self.key_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.34.attention.self.key_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.34.attention.self.query_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.34.attention.self.query_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.34.attention.self.value_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.34.attention.self.value_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.34.intermediate.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.34.intermediate.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.34.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.34.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.34.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.34.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.35.attention.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.35.attention.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.35.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.35.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.35.attention.self.key_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.35.attention.self.key_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.35.attention.self.query_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.35.attention.self.query_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.35.attention.self.value_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.35.attention.self.value_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.35.intermediate.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.35.intermediate.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.35.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.35.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.35.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.35.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.36.attention.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.36.attention.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.36.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.36.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.36.attention.self.key_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.36.attention.self.key_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.36.attention.self.query_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.36.attention.self.query_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.36.attention.self.value_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.36.attention.self.value_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.36.intermediate.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.36.intermediate.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.36.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.36.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.36.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.36.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.37.attention.output.LayerNorm.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.37.attention.output.LayerNorm.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.37.attention.output.dense.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.37.attention.output.dense.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.37.attention.self.key_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.37.attention.self.key_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.37.attention.self.query_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.37.attention.self.query_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.37.attention.self.value_proj.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.37.attention.self.value_proj.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.37.intermediate.dense.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.37.intermediate.dense.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.37.output.LayerNorm.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.37.output.LayerNorm.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.37.output.dense.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.37.output.dense.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.38.attention.output.LayerNorm.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.38.attention.output.LayerNorm.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.38.attention.output.dense.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.38.attention.output.dense.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.38.attention.self.key_proj.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.38.attention.self.key_proj.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.38.attention.self.query_proj.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.38.attention.self.query_proj.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.38.attention.self.value_proj.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.38.attention.self.value_proj.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.38.intermediate.dense.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.38.intermediate.dense.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.38.output.LayerNorm.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.38.output.LayerNorm.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.38.output.dense.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.38.output.dense.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.39.attention.output.LayerNorm.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.39.attention.output.LayerNorm.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.39.attention.output.dense.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.39.attention.output.dense.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.39.attention.self.key_proj.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.39.attention.self.key_proj.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.39.attention.self.query_proj.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.39.attention.self.query_proj.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.39.attention.self.value_proj.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.39.attention.self.value_proj.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.39.intermediate.dense.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.39.intermediate.dense.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.39.output.LayerNorm.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.39.output.LayerNorm.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.39.output.dense.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.39.output.dense.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.4.attention.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.4.attention.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.4.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.4.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.4.attention.self.key_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.4.attention.self.key_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.4.attention.self.query_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.4.attention.self.query_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.4.attention.self.value_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.4.attention.self.value_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.4.intermediate.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.4.intermediate.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.4.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.4.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.4.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.4.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.40.attention.output.LayerNorm.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.40.attention.output.LayerNorm.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.40.attention.output.dense.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.40.attention.output.dense.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.40.attention.self.key_proj.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.40.attention.self.key_proj.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.40.attention.self.query_proj.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.40.attention.self.query_proj.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.40.attention.self.value_proj.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.40.attention.self.value_proj.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.40.intermediate.dense.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.40.intermediate.dense.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.40.output.LayerNorm.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.40.output.LayerNorm.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.40.output.dense.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.40.output.dense.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.41.attention.output.LayerNorm.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.41.attention.output.LayerNorm.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.41.attention.output.dense.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.41.attention.output.dense.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.41.attention.self.key_proj.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.41.attention.self.key_proj.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.41.attention.self.query_proj.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.41.attention.self.query_proj.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.41.attention.self.value_proj.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.41.attention.self.value_proj.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.41.intermediate.dense.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.41.intermediate.dense.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.41.output.LayerNorm.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.41.output.LayerNorm.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.41.output.dense.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.41.output.dense.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.42.attention.output.LayerNorm.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.42.attention.output.LayerNorm.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.42.attention.output.dense.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.42.attention.output.dense.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.42.attention.self.key_proj.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.42.attention.self.key_proj.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.42.attention.self.query_proj.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.42.attention.self.query_proj.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.42.attention.self.value_proj.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.42.attention.self.value_proj.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.42.intermediate.dense.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.42.intermediate.dense.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.42.output.LayerNorm.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.42.output.LayerNorm.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.42.output.dense.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.42.output.dense.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.43.attention.output.LayerNorm.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.43.attention.output.LayerNorm.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.43.attention.output.dense.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.43.attention.output.dense.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.43.attention.self.key_proj.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.43.attention.self.key_proj.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.43.attention.self.query_proj.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.43.attention.self.query_proj.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.43.attention.self.value_proj.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.43.attention.self.value_proj.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.43.intermediate.dense.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.43.intermediate.dense.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.43.output.LayerNorm.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.43.output.LayerNorm.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.43.output.dense.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.43.output.dense.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.44.attention.output.LayerNorm.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.44.attention.output.LayerNorm.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.44.attention.output.dense.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.44.attention.output.dense.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.44.attention.self.key_proj.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.44.attention.self.key_proj.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.44.attention.self.query_proj.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.44.attention.self.query_proj.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.44.attention.self.value_proj.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.44.attention.self.value_proj.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.44.intermediate.dense.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.44.intermediate.dense.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.44.output.LayerNorm.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.44.output.LayerNorm.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.44.output.dense.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.44.output.dense.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.45.attention.output.LayerNorm.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.45.attention.output.LayerNorm.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.45.attention.output.dense.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.45.attention.output.dense.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.45.attention.self.key_proj.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.45.attention.self.key_proj.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.45.attention.self.query_proj.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.45.attention.self.query_proj.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.45.attention.self.value_proj.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.45.attention.self.value_proj.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.45.intermediate.dense.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.45.intermediate.dense.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.45.output.LayerNorm.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.45.output.LayerNorm.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.45.output.dense.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.45.output.dense.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.46.attention.output.LayerNorm.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.46.attention.output.LayerNorm.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.46.attention.output.dense.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.46.attention.output.dense.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.46.attention.self.key_proj.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.46.attention.self.key_proj.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.46.attention.self.query_proj.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.46.attention.self.query_proj.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.46.attention.self.value_proj.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.46.attention.self.value_proj.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.46.intermediate.dense.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.46.intermediate.dense.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.46.output.LayerNorm.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.46.output.LayerNorm.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.46.output.dense.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.46.output.dense.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.47.attention.output.LayerNorm.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.47.attention.output.LayerNorm.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.47.attention.output.dense.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.47.attention.output.dense.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.47.attention.self.key_proj.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.47.attention.self.key_proj.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.47.attention.self.query_proj.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.47.attention.self.query_proj.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.47.attention.self.value_proj.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.47.attention.self.value_proj.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.47.intermediate.dense.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.47.intermediate.dense.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.47.output.LayerNorm.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.47.output.LayerNorm.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.47.output.dense.bias": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.47.output.dense.weight": "model-00002-of-00002.safetensors",
+    "deberta.encoder.layer.5.attention.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.5.attention.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.5.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.5.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.5.attention.self.key_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.5.attention.self.key_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.5.attention.self.query_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.5.attention.self.query_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.5.attention.self.value_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.5.attention.self.value_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.5.intermediate.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.5.intermediate.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.5.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.5.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.5.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.5.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.6.attention.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.6.attention.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.6.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.6.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.6.attention.self.key_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.6.attention.self.key_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.6.attention.self.query_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.6.attention.self.query_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.6.attention.self.value_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.6.attention.self.value_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.6.intermediate.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.6.intermediate.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.6.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.6.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.6.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.6.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.7.attention.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.7.attention.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.7.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.7.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.7.attention.self.key_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.7.attention.self.key_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.7.attention.self.query_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.7.attention.self.query_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.7.attention.self.value_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.7.attention.self.value_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.7.intermediate.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.7.intermediate.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.7.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.7.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.7.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.7.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.8.attention.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.8.attention.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.8.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.8.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.8.attention.self.key_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.8.attention.self.key_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.8.attention.self.query_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.8.attention.self.query_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.8.attention.self.value_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.8.attention.self.value_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.8.intermediate.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.8.intermediate.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.8.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.8.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.8.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.8.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.9.attention.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.9.attention.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.9.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.9.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.9.attention.self.key_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.9.attention.self.key_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.9.attention.self.query_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.9.attention.self.query_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.9.attention.self.value_proj.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.9.attention.self.value_proj.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.9.intermediate.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.9.intermediate.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.9.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.9.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.9.output.dense.bias": "model-00001-of-00002.safetensors",
+    "deberta.encoder.layer.9.output.dense.weight": "model-00001-of-00002.safetensors",
+    "deberta.encoder.rel_embeddings.weight": "model-00002-of-00002.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

spm.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5598d5e96f339a8d980c15f9afd405a2e5e1be7db41de3ed13b0f03fac1e8c17
+size 2447305

tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128000": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "[CLS]",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "sp_model_kwargs": {},
+  "split_by_punct": false,
+  "tokenizer_class": "DebertaV2Tokenizer",
+  "unk_token": "[UNK]",
+  "vocab_type": "spm"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3fd17e422d362bdda8b57ad0ed67164eced1fd275b3b83eacf959bf7b9b7dca
+size 4664