koelectra-base-discriminator

README.md

@@ -0,0 +1,55 @@
+---
+language: ko
+license: apache-2.0
+tags:
+  - korean
+---
+
+# KoELECTRA (Base Discriminator)
+
+Pretrained ELECTRA Language Model for Korean (`koelectra-base-discriminator`)
+
+For more detail, please see [original repository](https://github.com/monologg/KoELECTRA/blob/master/README_EN.md).
+
+## Usage
+
+### Load model and tokenizer
+
+```python
+>>> from transformers import ElectraModel, ElectraTokenizer
+
+>>> model = ElectraModel.from_pretrained("monologg/koelectra-base-discriminator")
+>>> tokenizer = ElectraTokenizer.from_pretrained("monologg/koelectra-base-discriminator")
+```
+
+### Tokenizer example
+
+```python
+>>> from transformers import ElectraTokenizer
+>>> tokenizer = ElectraTokenizer.from_pretrained("monologg/koelectra-base-discriminator")
+>>> tokenizer.tokenize("[CLS] 한국어 ELECTRA를 공유합니다. [SEP]")
+['[CLS]', '한국어', 'E', '##L', '##EC', '##T', '##RA', '##를', '공유', '##합니다', '.', '[SEP]']
+>>> tokenizer.convert_tokens_to_ids(['[CLS]', '한국어', 'E', '##L', '##EC', '##T', '##RA', '##를', '공유', '##합니다', '.', '[SEP]'])
+[2, 18429, 41, 6240, 15229, 6204, 20894, 5689, 12622, 10690, 18, 3]
+```
+
+## Example using ElectraForPreTraining
+
+```python
+import torch
+from transformers import ElectraForPreTraining, ElectraTokenizer
+
+discriminator = ElectraForPreTraining.from_pretrained("monologg/koelectra-base-discriminator")
+tokenizer = ElectraTokenizer.from_pretrained("monologg/koelectra-base-discriminator")
+
+sentence = "나는 방금 밥을 먹었다."
+fake_sentence = "나는 내일 밥을 먹었다."
+
+fake_tokens = tokenizer.tokenize(fake_sentence)
+fake_inputs = tokenizer.encode(fake_sentence, return_tensors="pt")
+
+discriminator_outputs = discriminator(fake_inputs)
+predictions = torch.round((torch.sign(discriminator_outputs[0]) + 1) / 2)
+
+print(list(zip(fake_tokens, predictions.tolist()[1:-1])))
+```

config.json

@@ -0,0 +1,20 @@
+{
+  "architectures": [
+    "ElectraForPreTraining"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "embedding_size": 768,
+  "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,
+  "model_type": "electra",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "type_vocab_size": 2,
+  "vocab_size": 32200
+}

gitattributes

@@ -0,0 +1,8 @@
+*.bin.* filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tar.gz filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:374366ceb13a13d6b0754ae3f5bb9851f1a255af7463249355b6d1d6a37fd3ff
+size 443135628

tokenizer_config.json

@@ -0,0 +1,4 @@
+{
+  "do_lower_case": false,
+  "max_len": 512
+}