taekyoon.choi commited on
Commit
fd614ed
·
1 Parent(s): ffc0810

first model version

Browse files
config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/home1/irteam/.cache/huggingface/transformers/68843c20070ec73ce073d106b7d0236a5ff3d2d50ab4f7f392a77d9dc531a1eb-28cb4cb0ec90571c0938f52131cd8cc0a528d8ae5bb5e045fe5d715c1e2b7ea2-extracted/bert-110M-larva-text-kr",
3
+ "architectures": [
4
+ "BertModel"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 768,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 3072,
13
+ "layer_norm_eps": 1e-12,
14
+ "max_position_embeddings": 512,
15
+ "model_type": "bert",
16
+ "num_attention_heads": 12,
17
+ "num_hidden_layers": 12,
18
+ "pad_token_id": 0,
19
+ "position_embedding_type": "absolute",
20
+ "torch_dtype": "float32",
21
+ "transformers_version": "4.12.2",
22
+ "type_vocab_size": 2,
23
+ "use_cache": true,
24
+ "vocab_size": 32001
25
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:252e88547d14b423d2d5b45aa31e08379e3857a5855897a5f904615bdda6955e
3
+ size 442556215
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
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": "/home1/irteam/.cache/huggingface/transformers/e244d5a15f6000349f20464a22e24b0267ea232925c932ead28218ff17015a78-fb598fe7edd664bbb1c4a484e9929c4cbca71d5629e688480982d0cddb121fd4-extracted/bert-110M-larva-text-kr/special_tokens_map.json", "name_or_path": "/home1/irteam/.cache/huggingface/transformers/e244d5a15f6000349f20464a22e24b0267ea232925c932ead28218ff17015a78-fb598fe7edd664bbb1c4a484e9929c4cbca71d5629e688480982d0cddb121fd4-extracted/bert-110M-larva-text-kr", "do_basic_tokenize": true, "never_split": null, "tokenizer_class": "BertTokenizer"}
vocab.txt ADDED
The diff for this file is too large to render. See raw diff