Bert-base-kor-v1 처음 업로드
Browse files- added_tokens.json +24 -0
- config.json +24 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +31 -0
- tokenizer.json +0 -0
- tokenizer_config.json +16 -0
- vocab.txt +0 -0
added_tokens.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"[BOS]": 30000,
|
| 3 |
+
"[EOS]": 30001,
|
| 4 |
+
"[UNK0]": 30002,
|
| 5 |
+
"[UNK1]": 30003,
|
| 6 |
+
"[UNK2]": 30004,
|
| 7 |
+
"[UNK3]": 30005,
|
| 8 |
+
"[UNK4]": 30006,
|
| 9 |
+
"[UNK5]": 30007,
|
| 10 |
+
"[UNK6]": 30008,
|
| 11 |
+
"[UNK7]": 30009,
|
| 12 |
+
"[UNK8]": 30010,
|
| 13 |
+
"[UNK9]": 30011,
|
| 14 |
+
"[unused0]": 30012,
|
| 15 |
+
"[unused1]": 30013,
|
| 16 |
+
"[unused2]": 30014,
|
| 17 |
+
"[unused3]": 30015,
|
| 18 |
+
"[unused4]": 30016,
|
| 19 |
+
"[unused5]": 30017,
|
| 20 |
+
"[unused6]": 30018,
|
| 21 |
+
"[unused7]": 30019,
|
| 22 |
+
"[unused8]": 30020,
|
| 23 |
+
"[unused9]": 30021
|
| 24 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"BertForPreTraining"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"classifier_dropout": null,
|
| 7 |
+
"hidden_act": "gelu",
|
| 8 |
+
"hidden_dropout_prob": 0.1,
|
| 9 |
+
"hidden_size": 768,
|
| 10 |
+
"initializer_range": 0.02,
|
| 11 |
+
"intermediate_size": 3072,
|
| 12 |
+
"layer_norm_eps": 1e-12,
|
| 13 |
+
"max_position_embeddings": 512,
|
| 14 |
+
"model_type": "bert",
|
| 15 |
+
"num_attention_heads": 12,
|
| 16 |
+
"num_hidden_layers": 12,
|
| 17 |
+
"pad_token_id": 0,
|
| 18 |
+
"position_embedding_type": "absolute",
|
| 19 |
+
"torch_dtype": "float32",
|
| 20 |
+
"transformers_version": "4.21.2",
|
| 21 |
+
"type_vocab_size": 2,
|
| 22 |
+
"use_cache": true,
|
| 23 |
+
"vocab_size": 30022
|
| 24 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ebbc598cc90a9b72b01580050d0302587ffe0c2b96f0822d3c64819220ef56fd
|
| 3 |
+
size 438960547
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"[BOS]",
|
| 4 |
+
"[EOS]",
|
| 5 |
+
"[UNK0]",
|
| 6 |
+
"[UNK1]",
|
| 7 |
+
"[UNK2]",
|
| 8 |
+
"[UNK3]",
|
| 9 |
+
"[UNK4]",
|
| 10 |
+
"[UNK5]",
|
| 11 |
+
"[UNK6]",
|
| 12 |
+
"[UNK7]",
|
| 13 |
+
"[UNK8]",
|
| 14 |
+
"[UNK9]",
|
| 15 |
+
"[unused0]",
|
| 16 |
+
"[unused1]",
|
| 17 |
+
"[unused2]",
|
| 18 |
+
"[unused3]",
|
| 19 |
+
"[unused4]",
|
| 20 |
+
"[unused5]",
|
| 21 |
+
"[unused6]",
|
| 22 |
+
"[unused7]",
|
| 23 |
+
"[unused8]",
|
| 24 |
+
"[unused9]"
|
| 25 |
+
],
|
| 26 |
+
"cls_token": "[CLS]",
|
| 27 |
+
"mask_token": "[MASK]",
|
| 28 |
+
"pad_token": "[PAD]",
|
| 29 |
+
"sep_token": "[SEP]",
|
| 30 |
+
"unk_token": "[UNK]"
|
| 31 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": "[CLS]",
|
| 3 |
+
"do_basic_tokenize": true,
|
| 4 |
+
"do_lower_case": false,
|
| 5 |
+
"mask_token": "[MASK]",
|
| 6 |
+
"max_len": 128,
|
| 7 |
+
"name_or_path": "../../data11/ai_hub/vocab/tl1-1줄-mecab-30000",
|
| 8 |
+
"never_split": null,
|
| 9 |
+
"pad_token": "[PAD]",
|
| 10 |
+
"sep_token": "[SEP]",
|
| 11 |
+
"special_tokens_map_file": "../../data11/ai_hub/vocab/tl1-1줄-mecab-30000/special_tokens_map.json",
|
| 12 |
+
"strip_accents": false,
|
| 13 |
+
"tokenize_chinese_chars": true,
|
| 14 |
+
"tokenizer_class": "BertTokenizer",
|
| 15 |
+
"unk_token": "[UNK]"
|
| 16 |
+
}
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|