Upload BigBirdForSequenceClassification
Browse files- config.json +88 -0
- pytorch_model.bin +3 -0
config.json
ADDED
@@ -0,0 +1,88 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "monologg/kobigbird-bert-base",
|
3 |
+
"architectures": [
|
4 |
+
"BigBirdForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"attention_type": "block_sparse",
|
8 |
+
"block_size": 64,
|
9 |
+
"bos_token_id": 5,
|
10 |
+
"classifier_dropout": null,
|
11 |
+
"eos_token_id": 6,
|
12 |
+
"gradient_checkpointing": false,
|
13 |
+
"hidden_act": "gelu_new",
|
14 |
+
"hidden_dropout_prob": 0.1,
|
15 |
+
"hidden_size": 768,
|
16 |
+
"id2label": {
|
17 |
+
"0": "\uc778\uc0ac\u00b7\ub178\ubb34",
|
18 |
+
"1": "\uc138\ud0c1",
|
19 |
+
"2": "\ubd80\ub3d9\uc0b0",
|
20 |
+
"3": "\uc790\ub3d9\ucc28",
|
21 |
+
"4": "\ubc95\ub960",
|
22 |
+
"5": "\uc138\uae08\u00b7\uc138\ubb34",
|
23 |
+
"6": "\ucea0\ud551",
|
24 |
+
"7": "\ub4f1\uc0b0",
|
25 |
+
"8": "\uace0\ubbfc \uc0c1\ub2f4",
|
26 |
+
"9": "\uccad\uc18c",
|
27 |
+
"10": "\ud55c\ubc29",
|
28 |
+
"11": "\ubb34\uc5ed",
|
29 |
+
"12": "\ubc18\ub824\ub3d9\ubb3c",
|
30 |
+
"13": "\uce58\uacfc",
|
31 |
+
"14": "\uad50\ud1b5\uc0ac\uace0",
|
32 |
+
"15": "\uc778\ubb38\u00b7\uc608\uc220",
|
33 |
+
"16": "\uc601\uc591\u30fb\uc2dd\ub2e8",
|
34 |
+
"17": "\uacfc\ud559",
|
35 |
+
"18": "\uc721\uc544\u00b7\uc544\ub3d9",
|
36 |
+
"19": "\uacbd\uc81c\u00b7\uae08\uc735",
|
37 |
+
"20": "\uc758\ub8cc",
|
38 |
+
"21": "\ubcf4\ud5d8",
|
39 |
+
"22": "\uc0dd\ud65c\uafc0\ud301",
|
40 |
+
"23": "\uc57d\ub8cc"
|
41 |
+
},
|
42 |
+
"initializer_range": 0.02,
|
43 |
+
"intermediate_size": 3072,
|
44 |
+
"label2id": {
|
45 |
+
"\uacbd\uc81c\u00b7\uae08\uc735": 19,
|
46 |
+
"\uace0\ubbfc \uc0c1\ub2f4": 8,
|
47 |
+
"\uacfc\ud559": 17,
|
48 |
+
"\uad50\ud1b5\uc0ac\uace0": 14,
|
49 |
+
"\ub4f1\uc0b0": 7,
|
50 |
+
"\ubb34\uc5ed": 11,
|
51 |
+
"\ubc18\ub824\ub3d9\ubb3c": 12,
|
52 |
+
"\ubc95\ub960": 4,
|
53 |
+
"\ubcf4\ud5d8": 21,
|
54 |
+
"\ubd80\ub3d9\uc0b0": 2,
|
55 |
+
"\uc0dd\ud65c\uafc0\ud301": 22,
|
56 |
+
"\uc138\uae08\u00b7\uc138\ubb34": 5,
|
57 |
+
"\uc138\ud0c1": 1,
|
58 |
+
"\uc57d\ub8cc": 23,
|
59 |
+
"\uc601\uc591\u30fb\uc2dd\ub2e8": 16,
|
60 |
+
"\uc721\uc544\u00b7\uc544\ub3d9": 18,
|
61 |
+
"\uc758\ub8cc": 20,
|
62 |
+
"\uc778\ubb38\u00b7\uc608\uc220": 15,
|
63 |
+
"\uc778\uc0ac\u00b7\ub178\ubb34": 0,
|
64 |
+
"\uc790\ub3d9\ucc28": 3,
|
65 |
+
"\uccad\uc18c": 9,
|
66 |
+
"\uce58\uacfc": 13,
|
67 |
+
"\ucea0\ud551": 6,
|
68 |
+
"\ud55c\ubc29": 10
|
69 |
+
},
|
70 |
+
"layer_norm_eps": 1e-12,
|
71 |
+
"max_position_embeddings": 4096,
|
72 |
+
"model_type": "big_bird",
|
73 |
+
"num_attention_heads": 12,
|
74 |
+
"num_hidden_layers": 12,
|
75 |
+
"num_random_blocks": 3,
|
76 |
+
"pad_token_id": 0,
|
77 |
+
"position_embedding_type": "absolute",
|
78 |
+
"problem_type": "multi_label_classification",
|
79 |
+
"rescale_embeddings": false,
|
80 |
+
"sep_token_id": 3,
|
81 |
+
"tokenizer_class": "BertTokenizer",
|
82 |
+
"torch_dtype": "float32",
|
83 |
+
"transformers_version": "4.27.2",
|
84 |
+
"type_vocab_size": 2,
|
85 |
+
"use_bias": true,
|
86 |
+
"use_cache": true,
|
87 |
+
"vocab_size": 32500
|
88 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a59ee21b6ffb61ff8fc4cb231c59931b4e21e719375c6070a773dc7c1bf932e6
|
3 |
+
size 457553725
|