Upload from seopbo

README.md

@@ -1,3 +1,22 @@
 ---
 license: apache-2.0
+language: ko
+tags:
+  - fill-mask
+  - korean
+  - lassl
+mask_token: "[MASK]"
+widget:
+  - text: 대한민국의 수도는 [MASK] 입니다.
 ---
+
+# LASSL bert-ko-base
+Evaulation results will be released soon.
+
+## How to use
+
+```python
+from transformers import AutoModel, AutoTokenizer
+model = AutoModel.from_pretrained("lassl/bert-ko-base")
+tokenizer = AutoTokenizer.from_pretrained("lassl/bert-ko-base")
+```

config.json

@@ -0,0 +1,24 @@
+{
+  "architectures": [
+    "BertForPreTraining"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.13.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 51200
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:777d157b20ad23d5512b7d182c14984b904c824513e49f12fd9aae03e3e4585c
+size 661562641

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, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "datasets/bert", "tokenizer_class": "BertTokenizer"}