first version

config.json

@@ -0,0 +1,22 @@
+{
+    "architectures": [
+        "MegatronBertForPreTraining"
+    ],
+    "attention_probs_dropout_prob": 0.1,
+    "hidden_act": "gelu_new",
+    "hidden_dropout_prob": 0.1,
+    "hidden_size": 768,
+    "gradient_checkpointing": false,
+    "initializer_range": 0.2,
+    "intermediate_size": 3072,
+    "layer_norm_eps": 1e-12,
+    "max_position_embeddings": 512,
+    "model_type": "megatron-bert",
+    "num_attention_heads": 12,
+    "num_hidden_layers": 12,
+    "pad_token_id": 0,
+    "position_embedding_type": "absolute",
+    "type_vocab_size": 2,
+    "use_cache": false,
+    "vocab_size": 32000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13f4dd62482312223ac5298691ab7e61a0654748471d6c41aa0c9b9efc6d4a4f
+size 222742747

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": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "do_basic_tokenize": true, "never_split": null, "model_max_length": 512, "special_tokens_map_file": "/Users/dongjun/.cache/huggingface/transformers/aeaaa3afd086a040be912f92ffe7b5f85008b744624f4517c4216bcc32b51cf0.054ece8d16bd524c8a00f0e8a976c00d5de22a755ffb79e353ee2954d9289e26", "name_or_path": "klue/bert-base", "tokenizer_class": "BertTokenizer"}