first version of wiki-sentence-alignment fine-tuned BERT model and the tokenizer

added_tokens.json

@@ -0,0 +1 @@
+{}

config.json

@@ -0,0 +1,23 @@
+{
+  "architectures": [
+    "BertForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "finetuning_task": "newsela_task2",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "num_labels": 2,
+  "output_attentions": false,
+  "output_hidden_states": true,
+  "pruned_heads": {},
+  "torchscript": false,
+  "type_vocab_size": 2,
+  "vocab_size": 30522
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5155c953cec5e418860e473890db4fd4af1941bc1201064d6071a35c0a9c7925
+size 437985387

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": true, "max_len": 512, "init_inputs": []}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e579a1640c4878d43b4ea5e7906d6336a0993695db677a9d47ad127caf5b207c
+size 1542