new model

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* 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
+*.txt filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "dicta-il/dictabert-large",
+  "architectures": [
+    "BertForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "newmodern": true,
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 128000
+}

generation_config.json

@@ -0,0 +1,5 @@
+{
+  "_from_model_config": true,
+  "pad_token_id": 0,
+  "transformers_version": "4.38.2"
+}

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4b6e30404012cf295c9e5d86f5cc0f7df1e10d0895a2d4c1e9cc951fad3eaa1
+size 845525888

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54e478c05eefefbcba066607fed6fe5640e3a0160efa5be6f0cb10444e74c41e
+size 848169992

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:194874115cc4fc8dd71dbd8398ec6bc57dd1398c5bb991ea950c9067e927c768
+size 46708632

model.safetensors.index.json

@@ -0,0 +1,401 @@
+{
+  "metadata": {
+    "total_size": 1740357632
+  },
+  "weight_map": {
+    "bert.embeddings.LayerNorm.bias": "model-00001-of-00003.safetensors",
+    "bert.embeddings.LayerNorm.weight": "model-00001-of-00003.safetensors",
+    "bert.embeddings.position_embeddings.weight": "model-00001-of-00003.safetensors",
+    "bert.embeddings.token_type_embeddings.weight": "model-00001-of-00003.safetensors",
+    "bert.embeddings.word_embeddings.weight": "model-00001-of-00003.safetensors",
+    "bert.encoder.layer.0.attention.output.LayerNorm.bias": "model-00001-of-00003.safetensors",
+    "bert.encoder.layer.0.attention.output.LayerNorm.weight": "model-00001-of-00003.safetensors",
+    "bert.encoder.layer.0.attention.output.dense.bias": "model-00001-of-00003.safetensors",
+    "bert.encoder.layer.0.attention.output.dense.weight": "model-00001-of-00003.safetensors",
+    "bert.encoder.layer.0.attention.self.key.bias": "model-00001-of-00003.safetensors",
+    "bert.encoder.layer.0.attention.self.key.weight": "model-00001-of-00003.safetensors",
+    "bert.encoder.layer.0.attention.self.query.bias": "model-00001-of-00003.safetensors",
+    "bert.encoder.layer.0.attention.self.query.weight": "model-00001-of-00003.safetensors",
+    "bert.encoder.layer.0.attention.self.value.bias": "model-00001-of-00003.safetensors",
+    "bert.encoder.layer.0.attention.self.value.weight": "model-00001-of-00003.safetensors",
+    "bert.encoder.layer.0.intermediate.dense.bias": "model-00001-of-00003.safetensors",
+    "bert.encoder.layer.0.intermediate.dense.weight": "model-00001-of-00003.safetensors",
+    "bert.encoder.layer.0.output.LayerNorm.bias": "model-00001-of-00003.safetensors",
+    "bert.encoder.layer.0.output.LayerNorm.weight": "model-00001-of-00003.safetensors",
+    "bert.encoder.layer.0.output.dense.bias": "model-00001-of-00003.safetensors",
+    "bert.encoder.layer.0.output.dense.weight": "model-00001-of-00003.safetensors",
+    "bert.encoder.layer.1.attention.output.LayerNorm.bias": "model-00001-of-00003.safetensors",
+    "bert.encoder.layer.1.attention.output.LayerNorm.weight": "model-00001-of-00003.safetensors",
+    "bert.encoder.layer.1.attention.output.dense.bias": "model-00001-of-00003.safetensors",
+    "bert.encoder.layer.1.attention.output.dense.weight": "model-00001-of-00003.safetensors",
+    "bert.encoder.layer.1.attention.self.key.bias": "model-00001-of-00003.safetensors",
+    "bert.encoder.layer.1.attention.self.key.weight": "model-00001-of-00003.safetensors",
+    "bert.encoder.layer.1.attention.self.query.bias": "model-00001-of-00003.safetensors",
+    "bert.encoder.layer.1.attention.self.query.weight": "model-00001-of-00003.safetensors",
+    "bert.encoder.layer.1.attention.self.value.bias": "model-00001-of-00003.safetensors",
+    "bert.encoder.layer.1.attention.self.value.weight": "model-00001-of-00003.safetensors",
+    "bert.encoder.layer.1.intermediate.dense.bias": "model-00001-of-00003.safetensors",
+    "bert.encoder.layer.1.intermediate.dense.weight": "model-00001-of-00003.safetensors",
+    "bert.encoder.layer.1.output.LayerNorm.bias": "model-00001-of-00003.safetensors",
+    "bert.encoder.layer.1.output.LayerNorm.weight": "model-00001-of-00003.safetensors",
+    "bert.encoder.layer.1.output.dense.bias": "model-00001-of-00003.safetensors",
+    "bert.encoder.layer.1.output.dense.weight": "model-00001-of-00003.safetensors",
+    "bert.encoder.layer.10.attention.output.LayerNorm.bias": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.10.attention.output.LayerNorm.weight": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.10.attention.output.dense.bias": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.10.attention.output.dense.weight": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.10.attention.self.key.bias": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.10.attention.self.key.weight": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.10.attention.self.query.bias": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.10.attention.self.query.weight": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.10.attention.self.value.bias": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.10.attention.self.value.weight": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.10.intermediate.dense.bias": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.10.intermediate.dense.weight": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.10.output.LayerNorm.bias": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.10.output.LayerNorm.weight": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.10.output.dense.bias": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.10.output.dense.weight": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.11.attention.output.LayerNorm.bias": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.11.attention.output.LayerNorm.weight": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.11.attention.output.dense.bias": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.11.attention.output.dense.weight": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.11.attention.self.key.bias": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.11.attention.self.key.weight": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.11.attention.self.query.bias": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.11.attention.self.query.weight": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.11.attention.self.value.bias": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.11.attention.self.value.weight": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.11.intermediate.dense.bias": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.11.intermediate.dense.weight": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.11.output.LayerNorm.bias": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.11.output.LayerNorm.weight": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.11.output.dense.bias": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.11.output.dense.weight": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.12.attention.output.LayerNorm.bias": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.12.attention.output.LayerNorm.weight": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.12.attention.output.dense.bias": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.12.attention.output.dense.weight": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.12.attention.self.key.bias": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.12.attention.self.key.weight": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.12.attention.self.query.bias": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.12.attention.self.query.weight": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.12.attention.self.value.bias": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.12.attention.self.value.weight": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.12.intermediate.dense.bias": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.12.intermediate.dense.weight": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.12.output.LayerNorm.bias": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.12.output.LayerNorm.weight": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.12.output.dense.bias": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.12.output.dense.weight": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.13.attention.output.LayerNorm.bias": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.13.attention.output.LayerNorm.weight": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.13.attention.output.dense.bias": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.13.attention.output.dense.weight": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.13.attention.self.key.bias": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.13.attention.self.key.weight": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.13.attention.self.query.bias": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.13.attention.self.query.weight": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.13.attention.self.value.bias": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.13.attention.self.value.weight": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.13.intermediate.dense.bias": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.13.intermediate.dense.weight": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.13.output.LayerNorm.bias": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.13.output.LayerNorm.weight": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.13.output.dense.bias": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.13.output.dense.weight": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.14.attention.output.LayerNorm.bias": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.14.attention.output.LayerNorm.weight": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.14.attention.output.dense.bias": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.14.attention.output.dense.weight": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.14.attention.self.key.bias": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.14.attention.self.key.weight": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.14.attention.self.query.bias": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.14.attention.self.query.weight": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.14.attention.self.value.bias": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.14.attention.self.value.weight": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.14.intermediate.dense.bias": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.14.intermediate.dense.weight": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.14.output.LayerNorm.bias": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.14.output.LayerNorm.weight": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.14.output.dense.bias": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.14.output.dense.weight": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.15.attention.output.LayerNorm.bias": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.15.attention.output.LayerNorm.weight": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.15.attention.output.dense.bias": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.15.attention.output.dense.weight": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.15.attention.self.key.bias": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.15.attention.self.key.weight": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.15.attention.self.query.bias": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.15.attention.self.query.weight": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.15.attention.self.value.bias": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.15.attention.self.value.weight": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.15.intermediate.dense.bias": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.15.intermediate.dense.weight": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.15.output.LayerNorm.bias": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.15.output.LayerNorm.weight": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.15.output.dense.bias": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.15.output.dense.weight": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.16.attention.output.LayerNorm.bias": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.16.attention.output.LayerNorm.weight": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.16.attention.output.dense.bias": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.16.attention.output.dense.weight": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.16.attention.self.key.bias": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.16.attention.self.key.weight": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.16.attention.self.query.bias": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.16.attention.self.query.weight": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.16.attention.self.value.bias": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.16.attention.self.value.weight": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.16.intermediate.dense.bias": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.16.intermediate.dense.weight": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.16.output.LayerNorm.bias": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.16.output.LayerNorm.weight": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.16.output.dense.bias": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.16.output.dense.weight": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.17.attention.output.LayerNorm.bias": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.17.attention.output.LayerNorm.weight": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.17.attention.output.dense.bias": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.17.attention.output.dense.weight": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.17.attention.self.key.bias": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.17.attention.self.key.weight": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.17.attention.self.query.bias": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.17.attention.self.query.weight": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.17.attention.self.value.bias": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.17.attention.self.value.weight": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.17.intermediate.dense.bias": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.17.intermediate.dense.weight": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.17.output.LayerNorm.bias": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.17.output.LayerNorm.weight": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.17.output.dense.bias": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.17.output.dense.weight": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.18.attention.output.LayerNorm.bias": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.18.attention.output.LayerNorm.weight": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.18.attention.output.dense.bias": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.18.attention.output.dense.weight": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.18.attention.self.key.bias": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.18.attention.self.key.weight": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.18.attention.self.query.bias": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.18.attention.self.query.weight": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.18.attention.self.value.bias": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.18.attention.self.value.weight": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.18.intermediate.dense.bias": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.18.intermediate.dense.weight": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.18.output.LayerNorm.bias": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.18.output.LayerNorm.weight": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.18.output.dense.bias": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.18.output.dense.weight": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.19.attention.output.LayerNorm.bias": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.19.attention.output.LayerNorm.weight": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.19.attention.output.dense.bias": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.19.attention.output.dense.weight": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.19.attention.self.key.bias": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.19.attention.self.key.weight": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.19.attention.self.query.bias": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.19.attention.self.query.weight": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.19.attention.self.value.bias": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.19.attention.self.value.weight": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.19.intermediate.dense.bias": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.19.intermediate.dense.weight": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.19.output.LayerNorm.bias": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.19.output.LayerNorm.weight": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.19.output.dense.bias": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.19.output.dense.weight": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.2.attention.output.LayerNorm.bias": "model-00001-of-00003.safetensors",
+    "bert.encoder.layer.2.attention.output.LayerNorm.weight": "model-00001-of-00003.safetensors",
+    "bert.encoder.layer.2.attention.output.dense.bias": "model-00001-of-00003.safetensors",
+    "bert.encoder.layer.2.attention.output.dense.weight": "model-00001-of-00003.safetensors",
+    "bert.encoder.layer.2.attention.self.key.bias": "model-00001-of-00003.safetensors",
+    "bert.encoder.layer.2.attention.self.key.weight": "model-00001-of-00003.safetensors",
+    "bert.encoder.layer.2.attention.self.query.bias": "model-00001-of-00003.safetensors",
+    "bert.encoder.layer.2.attention.self.query.weight": "model-00001-of-00003.safetensors",
+    "bert.encoder.layer.2.attention.self.value.bias": "model-00001-of-00003.safetensors",
+    "bert.encoder.layer.2.attention.self.value.weight": "model-00001-of-00003.safetensors",
+    "bert.encoder.layer.2.intermediate.dense.bias": "model-00001-of-00003.safetensors",
+    "bert.encoder.layer.2.intermediate.dense.weight": "model-00001-of-00003.safetensors",
+    "bert.encoder.layer.2.output.LayerNorm.bias": "model-00001-of-00003.safetensors",
+    "bert.encoder.layer.2.output.LayerNorm.weight": "model-00001-of-00003.safetensors",
+    "bert.encoder.layer.2.output.dense.bias": "model-00001-of-00003.safetensors",
+    "bert.encoder.layer.2.output.dense.weight": "model-00001-of-00003.safetensors",
+    "bert.encoder.layer.20.attention.output.LayerNorm.bias": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.20.attention.output.LayerNorm.weight": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.20.attention.output.dense.bias": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.20.attention.output.dense.weight": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.20.attention.self.key.bias": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.20.attention.self.key.weight": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.20.attention.self.query.bias": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.20.attention.self.query.weight": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.20.attention.self.value.bias": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.20.attention.self.value.weight": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.20.intermediate.dense.bias": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.20.intermediate.dense.weight": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.20.output.LayerNorm.bias": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.20.output.LayerNorm.weight": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.20.output.dense.bias": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.20.output.dense.weight": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.21.attention.output.LayerNorm.bias": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.21.attention.output.LayerNorm.weight": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.21.attention.output.dense.bias": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.21.attention.output.dense.weight": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.21.attention.self.key.bias": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.21.attention.self.key.weight": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.21.attention.self.query.bias": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.21.attention.self.query.weight": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.21.attention.self.value.bias": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.21.attention.self.value.weight": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.21.intermediate.dense.bias": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.21.intermediate.dense.weight": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.21.output.LayerNorm.bias": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.21.output.LayerNorm.weight": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.21.output.dense.bias": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.21.output.dense.weight": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.22.attention.output.LayerNorm.bias": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.22.attention.output.LayerNorm.weight": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.22.attention.output.dense.bias": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.22.attention.output.dense.weight": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.22.attention.self.key.bias": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.22.attention.self.key.weight": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.22.attention.self.query.bias": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.22.attention.self.query.weight": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.22.attention.self.value.bias": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.22.attention.self.value.weight": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.22.intermediate.dense.bias": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.22.intermediate.dense.weight": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.22.output.LayerNorm.bias": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.22.output.LayerNorm.weight": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.22.output.dense.bias": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.22.output.dense.weight": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.23.attention.output.LayerNorm.bias": "model-00003-of-00003.safetensors",
+    "bert.encoder.layer.23.attention.output.LayerNorm.weight": "model-00003-of-00003.safetensors",
+    "bert.encoder.layer.23.attention.output.dense.bias": "model-00003-of-00003.safetensors",
+    "bert.encoder.layer.23.attention.output.dense.weight": "model-00003-of-00003.safetensors",
+    "bert.encoder.layer.23.attention.self.key.bias": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.23.attention.self.key.weight": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.23.attention.self.query.bias": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.23.attention.self.query.weight": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.23.attention.self.value.bias": "model-00003-of-00003.safetensors",
+    "bert.encoder.layer.23.attention.self.value.weight": "model-00003-of-00003.safetensors",
+    "bert.encoder.layer.23.intermediate.dense.bias": "model-00003-of-00003.safetensors",
+    "bert.encoder.layer.23.intermediate.dense.weight": "model-00003-of-00003.safetensors",
+    "bert.encoder.layer.23.output.LayerNorm.bias": "model-00003-of-00003.safetensors",
+    "bert.encoder.layer.23.output.LayerNorm.weight": "model-00003-of-00003.safetensors",
+    "bert.encoder.layer.23.output.dense.bias": "model-00003-of-00003.safetensors",
+    "bert.encoder.layer.23.output.dense.weight": "model-00003-of-00003.safetensors",
+    "bert.encoder.layer.3.attention.output.LayerNorm.bias": "model-00001-of-00003.safetensors",
+    "bert.encoder.layer.3.attention.output.LayerNorm.weight": "model-00001-of-00003.safetensors",
+    "bert.encoder.layer.3.attention.output.dense.bias": "model-00001-of-00003.safetensors",
+    "bert.encoder.layer.3.attention.output.dense.weight": "model-00001-of-00003.safetensors",
+    "bert.encoder.layer.3.attention.self.key.bias": "model-00001-of-00003.safetensors",
+    "bert.encoder.layer.3.attention.self.key.weight": "model-00001-of-00003.safetensors",
+    "bert.encoder.layer.3.attention.self.query.bias": "model-00001-of-00003.safetensors",
+    "bert.encoder.layer.3.attention.self.query.weight": "model-00001-of-00003.safetensors",
+    "bert.encoder.layer.3.attention.self.value.bias": "model-00001-of-00003.safetensors",
+    "bert.encoder.layer.3.attention.self.value.weight": "model-00001-of-00003.safetensors",
+    "bert.encoder.layer.3.intermediate.dense.bias": "model-00001-of-00003.safetensors",
+    "bert.encoder.layer.3.intermediate.dense.weight": "model-00001-of-00003.safetensors",
+    "bert.encoder.layer.3.output.LayerNorm.bias": "model-00001-of-00003.safetensors",
+    "bert.encoder.layer.3.output.LayerNorm.weight": "model-00001-of-00003.safetensors",
+    "bert.encoder.layer.3.output.dense.bias": "model-00001-of-00003.safetensors",
+    "bert.encoder.layer.3.output.dense.weight": "model-00001-of-00003.safetensors",
+    "bert.encoder.layer.4.attention.output.LayerNorm.bias": "model-00001-of-00003.safetensors",
+    "bert.encoder.layer.4.attention.output.LayerNorm.weight": "model-00001-of-00003.safetensors",
+    "bert.encoder.layer.4.attention.output.dense.bias": "model-00001-of-00003.safetensors",
+    "bert.encoder.layer.4.attention.output.dense.weight": "model-00001-of-00003.safetensors",
+    "bert.encoder.layer.4.attention.self.key.bias": "model-00001-of-00003.safetensors",
+    "bert.encoder.layer.4.attention.self.key.weight": "model-00001-of-00003.safetensors",
+    "bert.encoder.layer.4.attention.self.query.bias": "model-00001-of-00003.safetensors",
+    "bert.encoder.layer.4.attention.self.query.weight": "model-00001-of-00003.safetensors",
+    "bert.encoder.layer.4.attention.self.value.bias": "model-00001-of-00003.safetensors",
+    "bert.encoder.layer.4.attention.self.value.weight": "model-00001-of-00003.safetensors",
+    "bert.encoder.layer.4.intermediate.dense.bias": "model-00001-of-00003.safetensors",
+    "bert.encoder.layer.4.intermediate.dense.weight": "model-00001-of-00003.safetensors",
+    "bert.encoder.layer.4.output.LayerNorm.bias": "model-00001-of-00003.safetensors",
+    "bert.encoder.layer.4.output.LayerNorm.weight": "model-00001-of-00003.safetensors",
+    "bert.encoder.layer.4.output.dense.bias": "model-00001-of-00003.safetensors",
+    "bert.encoder.layer.4.output.dense.weight": "model-00001-of-00003.safetensors",
+    "bert.encoder.layer.5.attention.output.LayerNorm.bias": "model-00001-of-00003.safetensors",
+    "bert.encoder.layer.5.attention.output.LayerNorm.weight": "model-00001-of-00003.safetensors",
+    "bert.encoder.layer.5.attention.output.dense.bias": "model-00001-of-00003.safetensors",
+    "bert.encoder.layer.5.attention.output.dense.weight": "model-00001-of-00003.safetensors",
+    "bert.encoder.layer.5.attention.self.key.bias": "model-00001-of-00003.safetensors",
+    "bert.encoder.layer.5.attention.self.key.weight": "model-00001-of-00003.safetensors",
+    "bert.encoder.layer.5.attention.self.query.bias": "model-00001-of-00003.safetensors",
+    "bert.encoder.layer.5.attention.self.query.weight": "model-00001-of-00003.safetensors",
+    "bert.encoder.layer.5.attention.self.value.bias": "model-00001-of-00003.safetensors",
+    "bert.encoder.layer.5.attention.self.value.weight": "model-00001-of-00003.safetensors",
+    "bert.encoder.layer.5.intermediate.dense.bias": "model-00001-of-00003.safetensors",
+    "bert.encoder.layer.5.intermediate.dense.weight": "model-00001-of-00003.safetensors",
+    "bert.encoder.layer.5.output.LayerNorm.bias": "model-00001-of-00003.safetensors",
+    "bert.encoder.layer.5.output.LayerNorm.weight": "model-00001-of-00003.safetensors",
+    "bert.encoder.layer.5.output.dense.bias": "model-00001-of-00003.safetensors",
+    "bert.encoder.layer.5.output.dense.weight": "model-00001-of-00003.safetensors",
+    "bert.encoder.layer.6.attention.output.LayerNorm.bias": "model-00001-of-00003.safetensors",
+    "bert.encoder.layer.6.attention.output.LayerNorm.weight": "model-00001-of-00003.safetensors",
+    "bert.encoder.layer.6.attention.output.dense.bias": "model-00001-of-00003.safetensors",
+    "bert.encoder.layer.6.attention.output.dense.weight": "model-00001-of-00003.safetensors",
+    "bert.encoder.layer.6.attention.self.key.bias": "model-00001-of-00003.safetensors",
+    "bert.encoder.layer.6.attention.self.key.weight": "model-00001-of-00003.safetensors",
+    "bert.encoder.layer.6.attention.self.query.bias": "model-00001-of-00003.safetensors",
+    "bert.encoder.layer.6.attention.self.query.weight": "model-00001-of-00003.safetensors",
+    "bert.encoder.layer.6.attention.self.value.bias": "model-00001-of-00003.safetensors",
+    "bert.encoder.layer.6.attention.self.value.weight": "model-00001-of-00003.safetensors",
+    "bert.encoder.layer.6.intermediate.dense.bias": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.6.intermediate.dense.weight": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.6.output.LayerNorm.bias": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.6.output.LayerNorm.weight": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.6.output.dense.bias": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.6.output.dense.weight": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.7.attention.output.LayerNorm.bias": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.7.attention.output.LayerNorm.weight": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.7.attention.output.dense.bias": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.7.attention.output.dense.weight": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.7.attention.self.key.bias": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.7.attention.self.key.weight": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.7.attention.self.query.bias": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.7.attention.self.query.weight": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.7.attention.self.value.bias": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.7.attention.self.value.weight": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.7.intermediate.dense.bias": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.7.intermediate.dense.weight": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.7.output.LayerNorm.bias": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.7.output.LayerNorm.weight": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.7.output.dense.bias": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.7.output.dense.weight": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.8.attention.output.LayerNorm.bias": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.8.attention.output.LayerNorm.weight": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.8.attention.output.dense.bias": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.8.attention.output.dense.weight": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.8.attention.self.key.bias": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.8.attention.self.key.weight": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.8.attention.self.query.bias": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.8.attention.self.query.weight": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.8.attention.self.value.bias": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.8.attention.self.value.weight": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.8.intermediate.dense.bias": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.8.intermediate.dense.weight": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.8.output.LayerNorm.bias": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.8.output.LayerNorm.weight": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.8.output.dense.bias": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.8.output.dense.weight": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.9.attention.output.LayerNorm.bias": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.9.attention.output.LayerNorm.weight": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.9.attention.output.dense.bias": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.9.attention.output.dense.weight": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.9.attention.self.key.bias": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.9.attention.self.key.weight": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.9.attention.self.query.bias": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.9.attention.self.query.weight": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.9.attention.self.value.bias": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.9.attention.self.value.weight": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.9.intermediate.dense.bias": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.9.intermediate.dense.weight": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.9.output.LayerNorm.bias": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.9.output.LayerNorm.weight": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.9.output.dense.bias": "model-00002-of-00003.safetensors",
+    "bert.encoder.layer.9.output.dense.weight": "model-00002-of-00003.safetensors",
+    "cls.predictions.bias": "model-00003-of-00003.safetensors",
+    "cls.predictions.transform.LayerNorm.bias": "model-00003-of-00003.safetensors",
+    "cls.predictions.transform.LayerNorm.weight": "model-00003-of-00003.safetensors",
+    "cls.predictions.transform.dense.bias": "model-00003-of-00003.safetensors",
+    "cls.predictions.transform.dense.weight": "model-00003-of-00003.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "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
+  }
+}

tokenizer_config.json

@@ -0,0 +1,63 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[UNK]",
+      "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": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "[BLANK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

vocab.txt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0fb90bfa35244d26f0065d1fcd0b5becc3da3d44d616a7e2aacaf6320b9fa2d0
+size 1500244