Add 848.4k KcELECTRA-base

config.json

@@ -0,0 +1,21 @@
+{
+  "architectures": [
+    "ElectraForPreTraining"
+  ],
+  "num_hidden_layers": 12,
+  "hidden_size": 768,
+  "intermediate_size": 3072,
+  "num_attention_heads": 12,
+  "embedding_size": 768,
+  "attention_probs_dropout_prob": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "initializer_range": 0.02,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "electra",
+  "type_vocab_size": 2,
+  "vocab_size": 50135,
+  "pad_token_id": 0,
+  "tokenizer_class": "BertTokenizer"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dfb914aabf4627728d6494d8acda390a2f26200850a519f4bb55f1297c0ec86a
+size 498271049

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "unk_token": "[UNK]",
+  "sep_token": "[SEP]",
+  "pad_token": "[PAD]",
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]"
+}

tokenizer_config.json

@@ -0,0 +1,13 @@
+{
+  "do_lower_case": false,
+  "do_basic_tokenize": true,
+  "never_split": null,
+  "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
+}