cgpeltier-janes
commited on
Commit
•
8fe6689
1
Parent(s):
14f9d95
Upload 8 files
Browse files- config.json +54 -0
- merges.txt +0 -0
- pytorch_model.bin +2 -2
- special_tokens_map.json +51 -0
- tokenizer.json +0 -0
- tokenizer_config.json +67 -0
- training_args.bin +2 -2
- vocab.json +0 -0
config.json
CHANGED
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "microsoft/deberta-base",
|
3 |
+
"architectures": [
|
4 |
+
"DebertaForTokenClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"hidden_act": "gelu",
|
8 |
+
"hidden_dropout_prob": 0.1,
|
9 |
+
"hidden_size": 768,
|
10 |
+
"id2label": {
|
11 |
+
"0": "O",
|
12 |
+
"1": "B-PER",
|
13 |
+
"2": "I-PER",
|
14 |
+
"3": "B-ORG",
|
15 |
+
"4": "I-ORG",
|
16 |
+
"5": "B-LOC",
|
17 |
+
"6": "I-LOC",
|
18 |
+
"7": "B-MISC",
|
19 |
+
"8": "I-MISC"
|
20 |
+
},
|
21 |
+
"initializer_range": 0.02,
|
22 |
+
"intermediate_size": 3072,
|
23 |
+
"label2id": {
|
24 |
+
"B-LOC": "5",
|
25 |
+
"B-MISC": "7",
|
26 |
+
"B-ORG": "3",
|
27 |
+
"B-PER": "1",
|
28 |
+
"I-LOC": "6",
|
29 |
+
"I-MISC": "8",
|
30 |
+
"I-ORG": "4",
|
31 |
+
"I-PER": "2",
|
32 |
+
"O": "0"
|
33 |
+
},
|
34 |
+
"layer_norm_eps": 1e-07,
|
35 |
+
"max_position_embeddings": 512,
|
36 |
+
"max_relative_positions": -1,
|
37 |
+
"model_type": "deberta",
|
38 |
+
"num_attention_heads": 12,
|
39 |
+
"num_hidden_layers": 12,
|
40 |
+
"pad_token_id": 0,
|
41 |
+
"pooler_dropout": 0,
|
42 |
+
"pooler_hidden_act": "gelu",
|
43 |
+
"pooler_hidden_size": 768,
|
44 |
+
"pos_att_type": [
|
45 |
+
"c2p",
|
46 |
+
"p2c"
|
47 |
+
],
|
48 |
+
"position_biased_input": false,
|
49 |
+
"relative_attention": true,
|
50 |
+
"torch_dtype": "float32",
|
51 |
+
"transformers_version": "4.20.1",
|
52 |
+
"type_vocab_size": 0,
|
53 |
+
"vocab_size": 50265
|
54 |
+
}
|
merges.txt
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d7cd69b1c47e7dc2eca94f7f404fb3ce98f9385f1a02b115f392c3a7b66e5bfd
|
3 |
+
size 554505395
|
special_tokens_map.json
CHANGED
@@ -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
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
CHANGED
@@ -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 |
+
}
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aebf0abc860eede690ad4735a1308917ac866776269a7534c50f02d23d28b9d8
|
3 |
+
size 3311
|
vocab.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|