haven-jeon commited on
Commit
a1ac306
1 Parent(s): 36c39d1

first commit

Browse files
README.md ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language: ko
3
+ tags:
4
+ - bart
5
+ license: mit
6
+ ---
7
+
8
+ ## KoBART-base-v2
9
+
10
+ A model trained to handle the semantics of sequences longer than KoBART.
11
+
added_tokens.json ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ {}
2
+
config.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_dropout": 0.0,
3
+ "activation_function": "gelu",
4
+ "add_bias_logits": false,
5
+ "add_final_layer_norm": false,
6
+ "architectures": [
7
+ "BartModel"
8
+ ],
9
+ "attention_dropout": 0.0,
10
+ "bos_token_id": 1,
11
+ "classif_dropout": 0.1,
12
+ "classifier_dropout": 0.1,
13
+ "d_model": 768,
14
+ "decoder_attention_heads": 16,
15
+ "decoder_ffn_dim": 3072,
16
+ "decoder_layerdrop": 0.0,
17
+ "decoder_layers": 6,
18
+ "decoder_start_token_id": 2,
19
+ "do_blenderbot_90_layernorm": false,
20
+ "dropout": 0.1,
21
+ "encoder_attention_heads": 16,
22
+ "encoder_ffn_dim": 3072,
23
+ "encoder_layerdrop": 0.0,
24
+ "encoder_layers": 6,
25
+ "eos_token_id": 1,
26
+ "extra_pos_embeddings": 2,
27
+ "force_bos_token_to_be_generated": false,
28
+ "forced_eos_token_id": 2,
29
+ "gradient_checkpointing": false,
30
+ "id2label": {
31
+ "0": "NEGATIVE",
32
+ "1": "POSITIVE"
33
+ },
34
+ "init_std": 0.02,
35
+ "is_encoder_decoder": true,
36
+ "label2id": {
37
+ "NEGATIVE": 0,
38
+ "POSITIVE": 1
39
+ },
40
+ "max_position_embeddings": 1026,
41
+ "model_type": "bart",
42
+ "normalize_before": false,
43
+ "normalize_embedding": true,
44
+ "num_hidden_layers": 6,
45
+ "pad_token_id": 3,
46
+ "scale_embedding": false,
47
+ "static_position_embeddings": false,
48
+ "transformers_version": "4.5.1",
49
+ "use_cache": true,
50
+ "vocab_size": 30000,
51
+ "tokenizer_class": "PreTrainedTokenizerFast",
52
+ "author": "Heewon Jeon(madjakarta@gmail.com)",
53
+ "kobart_version": 1.0
54
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7082c7f1ae4efcc22c4b0081d71911059f4c5f65f278436c948d14b2d3d934d
3
+ size 495536138
special_tokens_map.json ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ {"bos_token": "</s>", "eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": "<mask>"}
2
+
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
vocab.json ADDED
The diff for this file is too large to render. See raw diff