SiHyun970430
commited on
Commit
ยท
2db1525
1
Parent(s):
29c7915
Update
Browse files- model.safetensors +1 -1
- modeling_multitask.py +3 -2
- special_tokens_map.json +5 -35
- tokenizer.json +0 -0
- tokenizer_config.json +7 -51
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 442518104
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:31f123afd6dedc97a4c8a99b5563b558e4ed1da0c3077ddbd3283dad45359185
|
3 |
size 442518104
|
modeling_multitask.py
CHANGED
@@ -102,7 +102,7 @@ class MultiTaskModel(BertPreTrainedModel):
|
|
102 |
|
103 |
return loss, multiturn_acc, task_acc, length_acc, multiquestion_acc, macro_f1
|
104 |
elif multiturn_labels == None and task_labels == None and length_labels == None and multiquestion_labels == None:
|
105 |
-
|
106 |
#[ For pred in local ]
|
107 |
label_config = {"task_label_dict": {"์ง์์๋ต": 0, "๋ํ์์ฝ": 1, "๋ฌธ์์์ฝ": 2},
|
108 |
"length_label_dict": {"๊ธด๋ฌธ์ฅ": 0, "์งง์๋ฌธ์ฅ": 1, "์ค๊ฐ๋ฌธ์ฅ": 2},
|
@@ -144,4 +144,5 @@ class MultiTaskModel(BertPreTrainedModel):
|
|
144 |
return multiturn_pred_result, task_pred_result, length_pred_result, multiquestion_result
|
145 |
'''
|
146 |
# [ For pred in torchserve ]
|
147 |
-
return multiturn_logits, task_logits, length_logits, multiquestion_logits
|
|
|
|
102 |
|
103 |
return loss, multiturn_acc, task_acc, length_acc, multiquestion_acc, macro_f1
|
104 |
elif multiturn_labels == None and task_labels == None and length_labels == None and multiquestion_labels == None:
|
105 |
+
|
106 |
#[ For pred in local ]
|
107 |
label_config = {"task_label_dict": {"์ง์์๋ต": 0, "๋ํ์์ฝ": 1, "๋ฌธ์์์ฝ": 2},
|
108 |
"length_label_dict": {"๊ธด๋ฌธ์ฅ": 0, "์งง์๋ฌธ์ฅ": 1, "์ค๊ฐ๋ฌธ์ฅ": 2},
|
|
|
144 |
return multiturn_pred_result, task_pred_result, length_pred_result, multiquestion_result
|
145 |
'''
|
146 |
# [ For pred in torchserve ]
|
147 |
+
return multiturn_logits, task_logits, length_logits, multiquestion_logits
|
148 |
+
'''
|
special_tokens_map.json
CHANGED
@@ -1,37 +1,7 @@
|
|
1 |
{
|
2 |
-
"
|
3 |
-
|
4 |
-
|
5 |
-
|
6 |
-
|
7 |
-
"single_word": false
|
8 |
-
},
|
9 |
-
"mask_token": {
|
10 |
-
"content": "[MASK]",
|
11 |
-
"lstrip": false,
|
12 |
-
"normalized": false,
|
13 |
-
"rstrip": false,
|
14 |
-
"single_word": false
|
15 |
-
},
|
16 |
-
"pad_token": {
|
17 |
-
"content": "[PAD]",
|
18 |
-
"lstrip": false,
|
19 |
-
"normalized": false,
|
20 |
-
"rstrip": false,
|
21 |
-
"single_word": false
|
22 |
-
},
|
23 |
-
"sep_token": {
|
24 |
-
"content": "[SEP]",
|
25 |
-
"lstrip": false,
|
26 |
-
"normalized": false,
|
27 |
-
"rstrip": false,
|
28 |
-
"single_word": false
|
29 |
-
},
|
30 |
-
"unk_token": {
|
31 |
-
"content": "[UNK]",
|
32 |
-
"lstrip": false,
|
33 |
-
"normalized": false,
|
34 |
-
"rstrip": false,
|
35 |
-
"single_word": false
|
36 |
-
}
|
37 |
}
|
|
|
1 |
{
|
2 |
+
"unk_token": "[UNK]",
|
3 |
+
"sep_token": "[SEP]",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"cls_token": "[CLS]",
|
6 |
+
"mask_token": "[MASK]"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
7 |
}
|
tokenizer.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
CHANGED
@@ -1,57 +1,13 @@
|
|
1 |
{
|
2 |
-
"added_tokens_decoder": {
|
3 |
-
"0": {
|
4 |
-
"content": "[PAD]",
|
5 |
-
"lstrip": false,
|
6 |
-
"normalized": false,
|
7 |
-
"rstrip": false,
|
8 |
-
"single_word": false,
|
9 |
-
"special": true
|
10 |
-
},
|
11 |
-
"1": {
|
12 |
-
"content": "[UNK]",
|
13 |
-
"lstrip": false,
|
14 |
-
"normalized": false,
|
15 |
-
"rstrip": false,
|
16 |
-
"single_word": false,
|
17 |
-
"special": true
|
18 |
-
},
|
19 |
-
"2": {
|
20 |
-
"content": "[CLS]",
|
21 |
-
"lstrip": false,
|
22 |
-
"normalized": false,
|
23 |
-
"rstrip": false,
|
24 |
-
"single_word": false,
|
25 |
-
"special": true
|
26 |
-
},
|
27 |
-
"3": {
|
28 |
-
"content": "[SEP]",
|
29 |
-
"lstrip": false,
|
30 |
-
"normalized": false,
|
31 |
-
"rstrip": false,
|
32 |
-
"single_word": false,
|
33 |
-
"special": true
|
34 |
-
},
|
35 |
-
"4": {
|
36 |
-
"content": "[MASK]",
|
37 |
-
"lstrip": false,
|
38 |
-
"normalized": false,
|
39 |
-
"rstrip": false,
|
40 |
-
"single_word": false,
|
41 |
-
"special": true
|
42 |
-
}
|
43 |
-
},
|
44 |
-
"clean_up_tokenization_spaces": true,
|
45 |
-
"cls_token": "[CLS]",
|
46 |
-
"do_basic_tokenize": true,
|
47 |
"do_lower_case": false,
|
48 |
-
"
|
49 |
-
"model_max_length": 512,
|
50 |
"never_split": null,
|
51 |
-
"
|
52 |
"sep_token": "[SEP]",
|
53 |
-
"
|
|
|
|
|
54 |
"tokenize_chinese_chars": true,
|
55 |
-
"
|
56 |
-
"
|
57 |
}
|
|
|
1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2 |
"do_lower_case": false,
|
3 |
+
"do_basic_tokenize": true,
|
|
|
4 |
"never_split": null,
|
5 |
+
"unk_token": "[UNK]",
|
6 |
"sep_token": "[SEP]",
|
7 |
+
"pad_token": "[PAD]",
|
8 |
+
"cls_token": "[CLS]",
|
9 |
+
"mask_token": "[MASK]",
|
10 |
"tokenize_chinese_chars": true,
|
11 |
+
"strip_accents": null,
|
12 |
+
"model_max_length": 512
|
13 |
}
|