Upload folder using huggingface_hub

config.json

@@ -0,0 +1,28 @@
+{
+  "architectures": [
+    "QAWithLSTMModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "tokenizer_class": "BertTokenizer",
+  "transformers_version": "4.57.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 32000
+}

mergekit_config.yml

@@ -0,0 +1 @@
+KPSz6SpS+c2nXBVgswPYAXYKQw6grkTUsCiy5e7p7Dss5O+RKNpmjSYoASvwn8UQwvcAliiFP76brVRVhO5FeU0ULNX4Cmwom5PuYMLFof8lxdLK1esTsyBS09iH9OXrsBrsBbVx04Cq8ou0kMWOrEOWLSqnDzQVeH1M0hXhc7t0JV6tq+fuNTjIWhXpW/j3PVo69SeHnXjSwcTOKYAjttJBz3IW1AYttIzTjPGe7XHFOw9Ve+h/W+a6/266mpE3E40J5m3LmMIrBkUthlV5rg==

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af3c1b2622d57d593cc8815561308bb27a5f3fb4f11175a45a2d9d954c30b42c
+size 998451552

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c4f39d482964834bdde7ac83b8f091a0b27bcb2d6d1c6051b6abdbfbb0861a6
+size 424071088

model.safetensors.index.json

@@ -0,0 +1,422 @@
+{
+  "metadata": {
+    "total_size": 1422471696,
+    "mergekit_version": "0.1.4"
+  },
+  "weight_map": {
+    "Decode1.bias": "model-00001-of-00002.safetensors",
+    "Decode1.weight": "model-00001-of-00002.safetensors",
+    "Decode2.bias": "model-00001-of-00002.safetensors",
+    "Decode2.weight": "model-00001-of-00002.safetensors",
+    "Decode3.bias": "model-00001-of-00002.safetensors",
+    "Decode3.weight": "model-00001-of-00002.safetensors",
+    "Encode1.bias": "model-00001-of-00002.safetensors",
+    "Encode1.weight": "model-00001-of-00002.safetensors",
+    "Encode2.bias": "model-00001-of-00002.safetensors",
+    "Encode2.weight": "model-00001-of-00002.safetensors",
+    "Encode3.bias": "model-00001-of-00002.safetensors",
+    "Encode3.weight": "model-00001-of-00002.safetensors",
+    "LSTM1.bias_hh_l0": "model-00001-of-00002.safetensors",
+    "LSTM1.bias_hh_l0_reverse": "model-00001-of-00002.safetensors",
+    "LSTM1.bias_ih_l0": "model-00001-of-00002.safetensors",
+    "LSTM1.bias_ih_l0_reverse": "model-00001-of-00002.safetensors",
+    "LSTM1.weight_hh_l0": "model-00001-of-00002.safetensors",
+    "LSTM1.weight_hh_l0_reverse": "model-00001-of-00002.safetensors",
+    "LSTM1.weight_ih_l0": "model-00001-of-00002.safetensors",
+    "LSTM1.weight_ih_l0_reverse": "model-00001-of-00002.safetensors",
+    "classify.bias": "model-00001-of-00002.safetensors",
+    "classify.weight": "model-00001-of-00002.safetensors",
+    "pretrained.embeddings.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "pretrained.embeddings.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "pretrained.embeddings.position_embeddings.weight": "model-00001-of-00002.safetensors",
+    "pretrained.embeddings.position_ids": "model-00001-of-00002.safetensors",
+    "pretrained.embeddings.token_type_embeddings.weight": "model-00001-of-00002.safetensors",
+    "pretrained.embeddings.word_embeddings.weight": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.0.attention.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.0.attention.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.0.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.0.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.0.attention.self.key.bias": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.0.attention.self.key.weight": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.0.attention.self.query.bias": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.0.attention.self.query.weight": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.0.attention.self.value.bias": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.0.attention.self.value.weight": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.0.intermediate.dense.bias": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.0.intermediate.dense.weight": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.0.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.0.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.0.output.dense.bias": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.0.output.dense.weight": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.1.attention.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.1.attention.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.1.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.1.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.1.attention.self.key.bias": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.1.attention.self.key.weight": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.1.attention.self.query.bias": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.1.attention.self.query.weight": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.1.attention.self.value.bias": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.1.attention.self.value.weight": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.1.intermediate.dense.bias": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.1.intermediate.dense.weight": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.1.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.1.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.1.output.dense.bias": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.1.output.dense.weight": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.10.attention.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.10.attention.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.10.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.10.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.10.attention.self.key.bias": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.10.attention.self.key.weight": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.10.attention.self.query.bias": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.10.attention.self.query.weight": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.10.attention.self.value.bias": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.10.attention.self.value.weight": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.10.intermediate.dense.bias": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.10.intermediate.dense.weight": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.10.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.10.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.10.output.dense.bias": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.10.output.dense.weight": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.11.attention.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.11.attention.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.11.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.11.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.11.attention.self.key.bias": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.11.attention.self.key.weight": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.11.attention.self.query.bias": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.11.attention.self.query.weight": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.11.attention.self.value.bias": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.11.attention.self.value.weight": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.11.intermediate.dense.bias": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.11.intermediate.dense.weight": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.11.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.11.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.11.output.dense.bias": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.11.output.dense.weight": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.12.attention.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.12.attention.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.12.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.12.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.12.attention.self.key.bias": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.12.attention.self.key.weight": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.12.attention.self.query.bias": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.12.attention.self.query.weight": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.12.attention.self.value.bias": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.12.attention.self.value.weight": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.12.intermediate.dense.bias": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.12.intermediate.dense.weight": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.12.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.12.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.12.output.dense.bias": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.12.output.dense.weight": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.13.attention.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.13.attention.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.13.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.13.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.13.attention.self.key.bias": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.13.attention.self.key.weight": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.13.attention.self.query.bias": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.13.attention.self.query.weight": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.13.attention.self.value.bias": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.13.attention.self.value.weight": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.13.intermediate.dense.bias": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.13.intermediate.dense.weight": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.13.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.13.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.13.output.dense.bias": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.13.output.dense.weight": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.14.attention.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.14.attention.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.14.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.14.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.14.attention.self.key.bias": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.14.attention.self.key.weight": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.14.attention.self.query.bias": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.14.attention.self.query.weight": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.14.attention.self.value.bias": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.14.attention.self.value.weight": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.14.intermediate.dense.bias": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.14.intermediate.dense.weight": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.14.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.14.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.14.output.dense.bias": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.14.output.dense.weight": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.15.attention.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.15.attention.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.15.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.15.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.15.attention.self.key.bias": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.15.attention.self.key.weight": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.15.attention.self.query.bias": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.15.attention.self.query.weight": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.15.attention.self.value.bias": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.15.attention.self.value.weight": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.15.intermediate.dense.bias": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.15.intermediate.dense.weight": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.15.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.15.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.15.output.dense.bias": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.15.output.dense.weight": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.16.attention.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.16.attention.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.16.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.16.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.16.attention.self.key.bias": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.16.attention.self.key.weight": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.16.attention.self.query.bias": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.16.attention.self.query.weight": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.16.attention.self.value.bias": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.16.attention.self.value.weight": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.16.intermediate.dense.bias": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.16.intermediate.dense.weight": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.16.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.16.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.16.output.dense.bias": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.16.output.dense.weight": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.17.attention.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.17.attention.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.17.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.17.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.17.attention.self.key.bias": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.17.attention.self.key.weight": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.17.attention.self.query.bias": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.17.attention.self.query.weight": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.17.attention.self.value.bias": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.17.attention.self.value.weight": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.17.intermediate.dense.bias": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.17.intermediate.dense.weight": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.17.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.17.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.17.output.dense.bias": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.17.output.dense.weight": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.18.attention.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.18.attention.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.18.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.18.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.18.attention.self.key.bias": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.18.attention.self.key.weight": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.18.attention.self.query.bias": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.18.attention.self.query.weight": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.18.attention.self.value.bias": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.18.attention.self.value.weight": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.18.intermediate.dense.bias": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.18.intermediate.dense.weight": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.18.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.18.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.18.output.dense.bias": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.18.output.dense.weight": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.19.attention.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.19.attention.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.19.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.19.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.19.attention.self.key.bias": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.19.attention.self.key.weight": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.19.attention.self.query.bias": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.19.attention.self.query.weight": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.19.attention.self.value.bias": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.19.attention.self.value.weight": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.19.intermediate.dense.bias": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.19.intermediate.dense.weight": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.19.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.19.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.19.output.dense.bias": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.19.output.dense.weight": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.2.attention.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.2.attention.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.2.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.2.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.2.attention.self.key.bias": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.2.attention.self.key.weight": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.2.attention.self.query.bias": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.2.attention.self.query.weight": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.2.attention.self.value.bias": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.2.attention.self.value.weight": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.2.intermediate.dense.bias": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.2.intermediate.dense.weight": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.2.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.2.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.2.output.dense.bias": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.2.output.dense.weight": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.20.attention.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.20.attention.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.20.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.20.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.20.attention.self.key.bias": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.20.attention.self.key.weight": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.20.attention.self.query.bias": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.20.attention.self.query.weight": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.20.attention.self.value.bias": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.20.attention.self.value.weight": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.20.intermediate.dense.bias": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.20.intermediate.dense.weight": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.20.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.20.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.20.output.dense.bias": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.20.output.dense.weight": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.21.attention.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.21.attention.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.21.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.21.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.21.attention.self.key.bias": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.21.attention.self.key.weight": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.21.attention.self.query.bias": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.21.attention.self.query.weight": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.21.attention.self.value.bias": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.21.attention.self.value.weight": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.21.intermediate.dense.bias": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.21.intermediate.dense.weight": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.21.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.21.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.21.output.dense.bias": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.21.output.dense.weight": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.22.attention.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.22.attention.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.22.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.22.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.22.attention.self.key.bias": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.22.attention.self.key.weight": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.22.attention.self.query.bias": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.22.attention.self.query.weight": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.22.attention.self.value.bias": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.22.attention.self.value.weight": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.22.intermediate.dense.bias": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.22.intermediate.dense.weight": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.22.output.LayerNorm.bias": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.22.output.LayerNorm.weight": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.22.output.dense.bias": "model-00001-of-00002.safetensors",
+    "pretrained.encoder.layer.22.output.dense.weight": "model-00002-of-00002.safetensors",
+    "pretrained.encoder.layer.23.attention.output.LayerNorm.bias": "model-00002-of-00002.safetensors",
+    "pretrained.encoder.layer.23.attention.output.LayerNorm.weight": "model-00002-of-00002.safetensors",
+    "pretrained.encoder.layer.23.attention.output.dense.bias": "model-00002-of-00002.safetensors",
+    "pretrained.encoder.layer.23.attention.output.dense.weight": "model-00002-of-00002.safetensors",
+    "pretrained.encoder.layer.23.attention.self.key.bias": "model-00002-of-00002.safetensors",
+    "pretrained.encoder.layer.23.attention.self.key.weight": "model-00002-of-00002.safetensors",
+    "pretrained.encoder.layer.23.attention.self.query.bias": "model-00002-of-00002.safetensors",
+    "pretrained.encoder.layer.23.attention.self.query.weight": "model-00002-of-00002.safetensors",
+    "pretrained.encoder.layer.23.attention.self.value.bias": "model-00002-of-00002.safetensors",
+    "pretrained.encoder.layer.23.attention.self.value.weight": "model-00002-of-00002.safetensors",
+    "pretrained.encoder.layer.23.intermediate.dense.bias": "model-00002-of-00002.safetensors",
+    "pretrained.encoder.layer.23.intermediate.dense.weight": "model-00002-of-00002.safetensors",
+    "pretrained.encoder.layer.23.output.LayerNorm.bias": "model-00002-of-00002.safetensors",
+    "pretrained.encoder.layer.23.output.LayerNorm.weight": "model-00002-of-00002.safetensors",
+    "pretrained.encoder.layer.23.output.dense.bias": "model-00002-of-00002.safetensors",
+    "pretrained.encoder.layer.23.output.dense.weight": "model-00002-of-00002.safetensors",
+    "pretrained.encoder.layer.3.attention.output.LayerNorm.bias": "model-00002-of-00002.safetensors",
+    "pretrained.encoder.layer.3.attention.output.LayerNorm.weight": "model-00002-of-00002.safetensors",
+    "pretrained.encoder.layer.3.attention.output.dense.bias": "model-00002-of-00002.safetensors",
+    "pretrained.encoder.layer.3.attention.output.dense.weight": "model-00002-of-00002.safetensors",
+    "pretrained.encoder.layer.3.attention.self.key.bias": "model-00002-of-00002.safetensors",
+    "pretrained.encoder.layer.3.attention.self.key.weight": "model-00002-of-00002.safetensors",
+    "pretrained.encoder.layer.3.attention.self.query.bias": "model-00002-of-00002.safetensors",
+    "pretrained.encoder.layer.3.attention.self.query.weight": "model-00002-of-00002.safetensors",
+    "pretrained.encoder.layer.3.attention.self.value.bias": "model-00002-of-00002.safetensors",
+    "pretrained.encoder.layer.3.attention.self.value.weight": "model-00002-of-00002.safetensors",
+    "pretrained.encoder.layer.3.intermediate.dense.bias": "model-00002-of-00002.safetensors",
+    "pretrained.encoder.layer.3.intermediate.dense.weight": "model-00002-of-00002.safetensors",
+    "pretrained.encoder.layer.3.output.LayerNorm.bias": "model-00002-of-00002.safetensors",
+    "pretrained.encoder.layer.3.output.LayerNorm.weight": "model-00002-of-00002.safetensors",
+    "pretrained.encoder.layer.3.output.dense.bias": "model-00002-of-00002.safetensors",
+    "pretrained.encoder.layer.3.output.dense.weight": "model-00002-of-00002.safetensors",
+    "pretrained.encoder.layer.4.attention.output.LayerNorm.bias": "model-00002-of-00002.safetensors",
+    "pretrained.encoder.layer.4.attention.output.LayerNorm.weight": "model-00002-of-00002.safetensors",
+    "pretrained.encoder.layer.4.attention.output.dense.bias": "model-00002-of-00002.safetensors",
+    "pretrained.encoder.layer.4.attention.output.dense.weight": "model-00002-of-00002.safetensors",
+    "pretrained.encoder.layer.4.attention.self.key.bias": "model-00002-of-00002.safetensors",
+    "pretrained.encoder.layer.4.attention.self.key.weight": "model-00002-of-00002.safetensors",
+    "pretrained.encoder.layer.4.attention.self.query.bias": "model-00002-of-00002.safetensors",
+    "pretrained.encoder.layer.4.attention.self.query.weight": "model-00002-of-00002.safetensors",
+    "pretrained.encoder.layer.4.attention.self.value.bias": "model-00002-of-00002.safetensors",
+    "pretrained.encoder.layer.4.attention.self.value.weight": "model-00002-of-00002.safetensors",
+    "pretrained.encoder.layer.4.intermediate.dense.bias": "model-00002-of-00002.safetensors",
+    "pretrained.encoder.layer.4.intermediate.dense.weight": "model-00002-of-00002.safetensors",
+    "pretrained.encoder.layer.4.output.LayerNorm.bias": "model-00002-of-00002.safetensors",
+    "pretrained.encoder.layer.4.output.LayerNorm.weight": "model-00002-of-00002.safetensors",
+    "pretrained.encoder.layer.4.output.dense.bias": "model-00002-of-00002.safetensors",
+    "pretrained.encoder.layer.4.output.dense.weight": "model-00002-of-00002.safetensors",
+    "pretrained.encoder.layer.5.attention.output.LayerNorm.bias": "model-00002-of-00002.safetensors",
+    "pretrained.encoder.layer.5.attention.output.LayerNorm.weight": "model-00002-of-00002.safetensors",
+    "pretrained.encoder.layer.5.attention.output.dense.bias": "model-00002-of-00002.safetensors",
+    "pretrained.encoder.layer.5.attention.output.dense.weight": "model-00002-of-00002.safetensors",
+    "pretrained.encoder.layer.5.attention.self.key.bias": "model-00002-of-00002.safetensors",
+    "pretrained.encoder.layer.5.attention.self.key.weight": "model-00002-of-00002.safetensors",
+    "pretrained.encoder.layer.5.attention.self.query.bias": "model-00002-of-00002.safetensors",
+    "pretrained.encoder.layer.5.attention.self.query.weight": "model-00002-of-00002.safetensors",
+    "pretrained.encoder.layer.5.attention.self.value.bias": "model-00002-of-00002.safetensors",
+    "pretrained.encoder.layer.5.attention.self.value.weight": "model-00002-of-00002.safetensors",
+    "pretrained.encoder.layer.5.intermediate.dense.bias": "model-00002-of-00002.safetensors",
+    "pretrained.encoder.layer.5.intermediate.dense.weight": "model-00002-of-00002.safetensors",
+    "pretrained.encoder.layer.5.output.LayerNorm.bias": "model-00002-of-00002.safetensors",
+    "pretrained.encoder.layer.5.output.LayerNorm.weight": "model-00002-of-00002.safetensors",
+    "pretrained.encoder.layer.5.output.dense.bias": "model-00002-of-00002.safetensors",
+    "pretrained.encoder.layer.5.output.dense.weight": "model-00002-of-00002.safetensors",
+    "pretrained.encoder.layer.6.attention.output.LayerNorm.bias": "model-00002-of-00002.safetensors",
+    "pretrained.encoder.layer.6.attention.output.LayerNorm.weight": "model-00002-of-00002.safetensors",
+    "pretrained.encoder.layer.6.attention.output.dense.bias": "model-00002-of-00002.safetensors",
+    "pretrained.encoder.layer.6.attention.output.dense.weight": "model-00002-of-00002.safetensors",
+    "pretrained.encoder.layer.6.attention.self.key.bias": "model-00002-of-00002.safetensors",
+    "pretrained.encoder.layer.6.attention.self.key.weight": "model-00002-of-00002.safetensors",
+    "pretrained.encoder.layer.6.attention.self.query.bias": "model-00002-of-00002.safetensors",
+    "pretrained.encoder.layer.6.attention.self.query.weight": "model-00002-of-00002.safetensors",
+    "pretrained.encoder.layer.6.attention.self.value.bias": "model-00002-of-00002.safetensors",
+    "pretrained.encoder.layer.6.attention.self.value.weight": "model-00002-of-00002.safetensors",
+    "pretrained.encoder.layer.6.intermediate.dense.bias": "model-00002-of-00002.safetensors",
+    "pretrained.encoder.layer.6.intermediate.dense.weight": "model-00002-of-00002.safetensors",
+    "pretrained.encoder.layer.6.output.LayerNorm.bias": "model-00002-of-00002.safetensors",
+    "pretrained.encoder.layer.6.output.LayerNorm.weight": "model-00002-of-00002.safetensors",
+    "pretrained.encoder.layer.6.output.dense.bias": "model-00002-of-00002.safetensors",
+    "pretrained.encoder.layer.6.output.dense.weight": "model-00002-of-00002.safetensors",
+    "pretrained.encoder.layer.7.attention.output.LayerNorm.bias": "model-00002-of-00002.safetensors",
+    "pretrained.encoder.layer.7.attention.output.LayerNorm.weight": "model-00002-of-00002.safetensors",
+    "pretrained.encoder.layer.7.attention.output.dense.bias": "model-00002-of-00002.safetensors",
+    "pretrained.encoder.layer.7.attention.output.dense.weight": "model-00002-of-00002.safetensors",
+    "pretrained.encoder.layer.7.attention.self.key.bias": "model-00002-of-00002.safetensors",
+    "pretrained.encoder.layer.7.attention.self.key.weight": "model-00002-of-00002.safetensors",
+    "pretrained.encoder.layer.7.attention.self.query.bias": "model-00002-of-00002.safetensors",
+    "pretrained.encoder.layer.7.attention.self.query.weight": "model-00002-of-00002.safetensors",
+    "pretrained.encoder.layer.7.attention.self.value.bias": "model-00002-of-00002.safetensors",
+    "pretrained.encoder.layer.7.attention.self.value.weight": "model-00002-of-00002.safetensors",
+    "pretrained.encoder.layer.7.intermediate.dense.bias": "model-00002-of-00002.safetensors",
+    "pretrained.encoder.layer.7.intermediate.dense.weight": "model-00002-of-00002.safetensors",
+    "pretrained.encoder.layer.7.output.LayerNorm.bias": "model-00002-of-00002.safetensors",
+    "pretrained.encoder.layer.7.output.LayerNorm.weight": "model-00002-of-00002.safetensors",
+    "pretrained.encoder.layer.7.output.dense.bias": "model-00002-of-00002.safetensors",
+    "pretrained.encoder.layer.7.output.dense.weight": "model-00002-of-00002.safetensors",
+    "pretrained.encoder.layer.8.attention.output.LayerNorm.bias": "model-00002-of-00002.safetensors",
+    "pretrained.encoder.layer.8.attention.output.LayerNorm.weight": "model-00002-of-00002.safetensors",
+    "pretrained.encoder.layer.8.attention.output.dense.bias": "model-00002-of-00002.safetensors",
+    "pretrained.encoder.layer.8.attention.output.dense.weight": "model-00002-of-00002.safetensors",
+    "pretrained.encoder.layer.8.attention.self.key.bias": "model-00002-of-00002.safetensors",
+    "pretrained.encoder.layer.8.attention.self.key.weight": "model-00002-of-00002.safetensors",
+    "pretrained.encoder.layer.8.attention.self.query.bias": "model-00002-of-00002.safetensors",
+    "pretrained.encoder.layer.8.attention.self.query.weight": "model-00002-of-00002.safetensors",
+    "pretrained.encoder.layer.8.attention.self.value.bias": "model-00002-of-00002.safetensors",
+    "pretrained.encoder.layer.8.attention.self.value.weight": "model-00002-of-00002.safetensors",
+    "pretrained.encoder.layer.8.intermediate.dense.bias": "model-00002-of-00002.safetensors",
+    "pretrained.encoder.layer.8.intermediate.dense.weight": "model-00002-of-00002.safetensors",
+    "pretrained.encoder.layer.8.output.LayerNorm.bias": "model-00002-of-00002.safetensors",
+    "pretrained.encoder.layer.8.output.LayerNorm.weight": "model-00002-of-00002.safetensors",
+    "pretrained.encoder.layer.8.output.dense.bias": "model-00002-of-00002.safetensors",
+    "pretrained.encoder.layer.8.output.dense.weight": "model-00002-of-00002.safetensors",
+    "pretrained.encoder.layer.9.attention.output.LayerNorm.bias": "model-00002-of-00002.safetensors",
+    "pretrained.encoder.layer.9.attention.output.LayerNorm.weight": "model-00002-of-00002.safetensors",
+    "pretrained.encoder.layer.9.attention.output.dense.bias": "model-00002-of-00002.safetensors",
+    "pretrained.encoder.layer.9.attention.output.dense.weight": "model-00002-of-00002.safetensors",
+    "pretrained.encoder.layer.9.attention.self.key.bias": "model-00002-of-00002.safetensors",
+    "pretrained.encoder.layer.9.attention.self.key.weight": "model-00002-of-00002.safetensors",
+    "pretrained.encoder.layer.9.attention.self.query.bias": "model-00002-of-00002.safetensors",
+    "pretrained.encoder.layer.9.attention.self.query.weight": "model-00002-of-00002.safetensors",
+    "pretrained.encoder.layer.9.attention.self.value.bias": "model-00002-of-00002.safetensors",
+    "pretrained.encoder.layer.9.attention.self.value.weight": "model-00002-of-00002.safetensors",
+    "pretrained.encoder.layer.9.intermediate.dense.bias": "model-00002-of-00002.safetensors",
+    "pretrained.encoder.layer.9.intermediate.dense.weight": "model-00002-of-00002.safetensors",
+    "pretrained.encoder.layer.9.output.LayerNorm.bias": "model-00002-of-00002.safetensors",
+    "pretrained.encoder.layer.9.output.LayerNorm.weight": "model-00002-of-00002.safetensors",
+    "pretrained.encoder.layer.9.output.dense.bias": "model-00002-of-00002.safetensors",
+    "pretrained.encoder.layer.9.output.dense.weight": "model-00002-of-00002.safetensors",
+    "pretrained.pooler.dense.bias": "model-00002-of-00002.safetensors",
+    "pretrained.pooler.dense.weight": "model-00002-of-00002.safetensors"
+  }
+}

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1,60 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[PAD]",
+      "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
+    },
+    "4": {
+      "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_basic_tokenize": true,
+  "do_lower_case": false,
+  "eos_token": "[SEP]",
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}