cynthiachan
commited on
Commit
•
2ff4596
1
Parent(s):
9979802
Upload 12 files
Browse files- config.json +107 -0
- merges.txt +0 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +51 -0
- tokenizer.json +0 -0
- tokenizer_config.json +67 -0
- trainer_state.json +0 -0
- training_args.bin +3 -0
- vocab.json +0 -0
config.json
ADDED
@@ -0,0 +1,107 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "microsoft/deberta-base",
|
3 |
+
"architectures": [
|
4 |
+
"DebertaForTokenClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"finetuning_task": "ner",
|
8 |
+
"hidden_act": "gelu",
|
9 |
+
"hidden_dropout_prob": 0.1,
|
10 |
+
"hidden_size": 768,
|
11 |
+
"id2label": {
|
12 |
+
"0": "O",
|
13 |
+
"1": "B-attackID",
|
14 |
+
"2": "I-attackID",
|
15 |
+
"3": "B-bitcoinAddr",
|
16 |
+
"4": "I-bitcoinAddr",
|
17 |
+
"5": "B-cve",
|
18 |
+
"6": "I-cve",
|
19 |
+
"7": "B-defenderThreat",
|
20 |
+
"8": "I-defenderThreat",
|
21 |
+
"9": "B-domain",
|
22 |
+
"10": "I-domain",
|
23 |
+
"11": "B-email",
|
24 |
+
"12": "I-email",
|
25 |
+
"13": "B-md5",
|
26 |
+
"14": "I-md5",
|
27 |
+
"15": "B-sha1",
|
28 |
+
"16": "I-sha1",
|
29 |
+
"17": "B-sha256",
|
30 |
+
"18": "I-sha256",
|
31 |
+
"19": "B-filepath",
|
32 |
+
"20": "I-filepath",
|
33 |
+
"21": "B-hostname",
|
34 |
+
"22": "I-hostname",
|
35 |
+
"23": "B-ipv4",
|
36 |
+
"24": "I-ipv4",
|
37 |
+
"25": "B-ipv6",
|
38 |
+
"26": "I-ipv6",
|
39 |
+
"27": "B-fingerprint",
|
40 |
+
"28": "I-fingerprint",
|
41 |
+
"29": "B-uri",
|
42 |
+
"30": "I-uri",
|
43 |
+
"31": "B-url",
|
44 |
+
"32": "I-url",
|
45 |
+
"33": "B-yara",
|
46 |
+
"34": "I-yara"
|
47 |
+
},
|
48 |
+
"initializer_range": 0.02,
|
49 |
+
"intermediate_size": 3072,
|
50 |
+
"label2id": {
|
51 |
+
"B-attackID": 1,
|
52 |
+
"B-bitcoinAddr": 3,
|
53 |
+
"B-cve": 5,
|
54 |
+
"B-defenderThreat": 7,
|
55 |
+
"B-domain": 9,
|
56 |
+
"B-email": 11,
|
57 |
+
"B-filepath": 19,
|
58 |
+
"B-fingerprint": 27,
|
59 |
+
"B-hostname": 21,
|
60 |
+
"B-ipv4": 23,
|
61 |
+
"B-ipv6": 25,
|
62 |
+
"B-md5": 13,
|
63 |
+
"B-sha1": 15,
|
64 |
+
"B-sha256": 17,
|
65 |
+
"B-uri": 29,
|
66 |
+
"B-url": 31,
|
67 |
+
"B-yara": 33,
|
68 |
+
"I-attackID": 2,
|
69 |
+
"I-bitcoinAddr": 4,
|
70 |
+
"I-cve": 6,
|
71 |
+
"I-defenderThreat": 8,
|
72 |
+
"I-domain": 10,
|
73 |
+
"I-email": 12,
|
74 |
+
"I-filepath": 20,
|
75 |
+
"I-fingerprint": 28,
|
76 |
+
"I-hostname": 22,
|
77 |
+
"I-ipv4": 24,
|
78 |
+
"I-ipv6": 26,
|
79 |
+
"I-md5": 14,
|
80 |
+
"I-sha1": 16,
|
81 |
+
"I-sha256": 18,
|
82 |
+
"I-uri": 30,
|
83 |
+
"I-url": 32,
|
84 |
+
"I-yara": 34,
|
85 |
+
"O": 0
|
86 |
+
},
|
87 |
+
"layer_norm_eps": 1e-07,
|
88 |
+
"max_position_embeddings": 512,
|
89 |
+
"max_relative_positions": -1,
|
90 |
+
"model_type": "deberta",
|
91 |
+
"num_attention_heads": 12,
|
92 |
+
"num_hidden_layers": 12,
|
93 |
+
"pad_token_id": 0,
|
94 |
+
"pooler_dropout": 0,
|
95 |
+
"pooler_hidden_act": "gelu",
|
96 |
+
"pooler_hidden_size": 768,
|
97 |
+
"pos_att_type": [
|
98 |
+
"c2p",
|
99 |
+
"p2c"
|
100 |
+
],
|
101 |
+
"position_biased_input": false,
|
102 |
+
"relative_attention": true,
|
103 |
+
"torch_dtype": "float32",
|
104 |
+
"transformers_version": "4.24.0",
|
105 |
+
"type_vocab_size": 0,
|
106 |
+
"vocab_size": 50265
|
107 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1325742f333ebb74d43901aa85d6ba544a7a4c083485b686fbbbb9252feb8293
|
3 |
+
size 1109143977
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bb9f21e5b2e86f2edbae38cf457fad2797d72d3a9f10b4ffdf14b443d2b3a368
|
3 |
+
size 554585395
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fc9339ac96c3c42ad0930aab1c0dc8fb5618817d86f42f8446768c6ece153401
|
3 |
+
size 14503
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:61c0896db2933a1a110b33eafc55b6a1570d9d1c6fcb5f0fb1d21b1f21f4d574
|
3 |
+
size 623
|
special_tokens_map.json
ADDED
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "[CLS]",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": true,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"cls_token": {
|
10 |
+
"content": "[CLS]",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": true,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"eos_token": {
|
17 |
+
"content": "[SEP]",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": true,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"mask_token": {
|
24 |
+
"content": "[MASK]",
|
25 |
+
"lstrip": true,
|
26 |
+
"normalized": true,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
},
|
30 |
+
"pad_token": {
|
31 |
+
"content": "[PAD]",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": true,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false
|
36 |
+
},
|
37 |
+
"sep_token": {
|
38 |
+
"content": "[SEP]",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": true,
|
41 |
+
"rstrip": false,
|
42 |
+
"single_word": false
|
43 |
+
},
|
44 |
+
"unk_token": {
|
45 |
+
"content": "[UNK]",
|
46 |
+
"lstrip": false,
|
47 |
+
"normalized": true,
|
48 |
+
"rstrip": false,
|
49 |
+
"single_word": false
|
50 |
+
}
|
51 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,67 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": false,
|
3 |
+
"add_prefix_space": true,
|
4 |
+
"bos_token": {
|
5 |
+
"__type": "AddedToken",
|
6 |
+
"content": "[CLS]",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": true,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false
|
11 |
+
},
|
12 |
+
"cls_token": {
|
13 |
+
"__type": "AddedToken",
|
14 |
+
"content": "[CLS]",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": true,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false
|
19 |
+
},
|
20 |
+
"do_lower_case": false,
|
21 |
+
"eos_token": {
|
22 |
+
"__type": "AddedToken",
|
23 |
+
"content": "[SEP]",
|
24 |
+
"lstrip": false,
|
25 |
+
"normalized": true,
|
26 |
+
"rstrip": false,
|
27 |
+
"single_word": false
|
28 |
+
},
|
29 |
+
"errors": "replace",
|
30 |
+
"mask_token": {
|
31 |
+
"__type": "AddedToken",
|
32 |
+
"content": "[MASK]",
|
33 |
+
"lstrip": true,
|
34 |
+
"normalized": true,
|
35 |
+
"rstrip": false,
|
36 |
+
"single_word": false
|
37 |
+
},
|
38 |
+
"model_max_length": 512,
|
39 |
+
"name_or_path": "microsoft/deberta-base",
|
40 |
+
"pad_token": {
|
41 |
+
"__type": "AddedToken",
|
42 |
+
"content": "[PAD]",
|
43 |
+
"lstrip": false,
|
44 |
+
"normalized": true,
|
45 |
+
"rstrip": false,
|
46 |
+
"single_word": false
|
47 |
+
},
|
48 |
+
"sep_token": {
|
49 |
+
"__type": "AddedToken",
|
50 |
+
"content": "[SEP]",
|
51 |
+
"lstrip": false,
|
52 |
+
"normalized": true,
|
53 |
+
"rstrip": false,
|
54 |
+
"single_word": false
|
55 |
+
},
|
56 |
+
"special_tokens_map_file": null,
|
57 |
+
"tokenizer_class": "DebertaTokenizer",
|
58 |
+
"unk_token": {
|
59 |
+
"__type": "AddedToken",
|
60 |
+
"content": "[UNK]",
|
61 |
+
"lstrip": false,
|
62 |
+
"normalized": true,
|
63 |
+
"rstrip": false,
|
64 |
+
"single_word": false
|
65 |
+
},
|
66 |
+
"vocab_type": "gpt2"
|
67 |
+
}
|
trainer_state.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2f04909a361d6d1e8d8ae2b97d2bb8bfbe372d07b7c1d583eb200458d401ed57
|
3 |
+
size 3503
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|