abbasgolestani
commited on
Commit
•
2e30e83
1
Parent(s):
463a1b5
Upload folder using huggingface_hub
Browse files- config.json +17 -15
- pytorch_model.bin +2 -2
- special_tokens_map.json +5 -53
- tokenizer.json +0 -0
- tokenizer_config.json +12 -83
config.json
CHANGED
@@ -1,34 +1,36 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"architectures": [
|
4 |
-
"
|
5 |
],
|
6 |
"attention_probs_dropout_prob": 0.1,
|
7 |
-
"bos_token_id": 0,
|
8 |
"classifier_dropout": null,
|
9 |
-
"
|
10 |
"hidden_act": "gelu",
|
11 |
"hidden_dropout_prob": 0.1,
|
12 |
-
"hidden_size":
|
13 |
"id2label": {
|
14 |
"0": "LABEL_0"
|
15 |
},
|
16 |
"initializer_range": 0.02,
|
17 |
-
"intermediate_size":
|
18 |
"label2id": {
|
19 |
"LABEL_0": 0
|
20 |
},
|
21 |
-
"layer_norm_eps": 1e-
|
22 |
-
"max_position_embeddings":
|
23 |
-
"model_type": "
|
24 |
-
"num_attention_heads":
|
25 |
-
"num_hidden_layers":
|
26 |
-
"
|
27 |
-
"pad_token_id": 1,
|
28 |
"position_embedding_type": "absolute",
|
|
|
|
|
|
|
|
|
29 |
"torch_dtype": "float32",
|
30 |
"transformers_version": "4.33.2",
|
31 |
-
"type_vocab_size":
|
32 |
"use_cache": true,
|
33 |
-
"vocab_size":
|
34 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "cross-encoder/qnli-electra-base",
|
3 |
"architectures": [
|
4 |
+
"ElectraForSequenceClassification"
|
5 |
],
|
6 |
"attention_probs_dropout_prob": 0.1,
|
|
|
7 |
"classifier_dropout": null,
|
8 |
+
"embedding_size": 768,
|
9 |
"hidden_act": "gelu",
|
10 |
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 768,
|
12 |
"id2label": {
|
13 |
"0": "LABEL_0"
|
14 |
},
|
15 |
"initializer_range": 0.02,
|
16 |
+
"intermediate_size": 3072,
|
17 |
"label2id": {
|
18 |
"LABEL_0": 0
|
19 |
},
|
20 |
+
"layer_norm_eps": 1e-12,
|
21 |
+
"max_position_embeddings": 512,
|
22 |
+
"model_type": "electra",
|
23 |
+
"num_attention_heads": 12,
|
24 |
+
"num_hidden_layers": 12,
|
25 |
+
"pad_token_id": 0,
|
|
|
26 |
"position_embedding_type": "absolute",
|
27 |
+
"summary_activation": "gelu",
|
28 |
+
"summary_last_dropout": 0.1,
|
29 |
+
"summary_type": "first",
|
30 |
+
"summary_use_proj": true,
|
31 |
"torch_dtype": "float32",
|
32 |
"transformers_version": "4.33.2",
|
33 |
+
"type_vocab_size": 2,
|
34 |
"use_cache": true,
|
35 |
+
"vocab_size": 30522
|
36 |
}
|
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:ac9068d3558644e331ad04378b2e99c2401cfb7622438bcf9a16777ccd012021
|
3 |
+
size 437998193
|
special_tokens_map.json
CHANGED
@@ -1,55 +1,7 @@
|
|
1 |
{
|
2 |
-
"
|
3 |
-
|
4 |
-
|
5 |
-
],
|
6 |
-
"
|
7 |
-
"content": "<s>",
|
8 |
-
"lstrip": false,
|
9 |
-
"normalized": false,
|
10 |
-
"rstrip": false,
|
11 |
-
"single_word": false
|
12 |
-
},
|
13 |
-
"cls_token": {
|
14 |
-
"content": "<s>",
|
15 |
-
"lstrip": false,
|
16 |
-
"normalized": false,
|
17 |
-
"rstrip": false,
|
18 |
-
"single_word": false
|
19 |
-
},
|
20 |
-
"eos_token": {
|
21 |
-
"content": "</s>",
|
22 |
-
"lstrip": false,
|
23 |
-
"normalized": false,
|
24 |
-
"rstrip": false,
|
25 |
-
"single_word": false
|
26 |
-
},
|
27 |
-
"mask_token": {
|
28 |
-
"content": "<mask>",
|
29 |
-
"lstrip": true,
|
30 |
-
"normalized": true,
|
31 |
-
"rstrip": false,
|
32 |
-
"single_word": false
|
33 |
-
},
|
34 |
-
"pad_token": {
|
35 |
-
"content": "<pad>",
|
36 |
-
"lstrip": false,
|
37 |
-
"normalized": false,
|
38 |
-
"rstrip": false,
|
39 |
-
"single_word": false
|
40 |
-
},
|
41 |
-
"sep_token": {
|
42 |
-
"content": "</s>",
|
43 |
-
"lstrip": false,
|
44 |
-
"normalized": false,
|
45 |
-
"rstrip": false,
|
46 |
-
"single_word": false
|
47 |
-
},
|
48 |
-
"unk_token": {
|
49 |
-
"content": "<unk>",
|
50 |
-
"lstrip": false,
|
51 |
-
"normalized": false,
|
52 |
-
"rstrip": false,
|
53 |
-
"single_word": false
|
54 |
-
}
|
55 |
}
|
|
|
1 |
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"mask_token": "[MASK]",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"sep_token": "[SEP]",
|
6 |
+
"unk_token": "[UNK]"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
7 |
}
|
tokenizer.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
CHANGED
@@ -1,86 +1,15 @@
|
|
1 |
{
|
2 |
-
"added_tokens_decoder": {
|
3 |
-
"0": {
|
4 |
-
"content": "<s>NOTUSED",
|
5 |
-
"lstrip": false,
|
6 |
-
"normalized": false,
|
7 |
-
"rstrip": false,
|
8 |
-
"single_word": false,
|
9 |
-
"special": true
|
10 |
-
},
|
11 |
-
"1": {
|
12 |
-
"content": "<pad>",
|
13 |
-
"lstrip": false,
|
14 |
-
"normalized": false,
|
15 |
-
"rstrip": false,
|
16 |
-
"single_word": false,
|
17 |
-
"special": true
|
18 |
-
},
|
19 |
-
"2": {
|
20 |
-
"content": "</s>NOTUSED",
|
21 |
-
"lstrip": false,
|
22 |
-
"normalized": false,
|
23 |
-
"rstrip": false,
|
24 |
-
"single_word": false,
|
25 |
-
"special": true
|
26 |
-
},
|
27 |
-
"3": {
|
28 |
-
"content": "<unk>",
|
29 |
-
"lstrip": false,
|
30 |
-
"normalized": false,
|
31 |
-
"rstrip": false,
|
32 |
-
"single_word": false,
|
33 |
-
"special": true
|
34 |
-
},
|
35 |
-
"32004": {
|
36 |
-
"content": "<mask>",
|
37 |
-
"lstrip": true,
|
38 |
-
"normalized": true,
|
39 |
-
"rstrip": false,
|
40 |
-
"single_word": false,
|
41 |
-
"special": true
|
42 |
-
},
|
43 |
-
"5": {
|
44 |
-
"content": "<s>",
|
45 |
-
"lstrip": false,
|
46 |
-
"normalized": false,
|
47 |
-
"rstrip": false,
|
48 |
-
"single_word": false,
|
49 |
-
"special": true
|
50 |
-
},
|
51 |
-
"6": {
|
52 |
-
"content": "</s>",
|
53 |
-
"lstrip": false,
|
54 |
-
"normalized": false,
|
55 |
-
"rstrip": false,
|
56 |
-
"single_word": false,
|
57 |
-
"special": true
|
58 |
-
}
|
59 |
-
},
|
60 |
-
"additional_special_tokens": [
|
61 |
-
"<s>NOTUSED",
|
62 |
-
"</s>NOTUSED"
|
63 |
-
],
|
64 |
-
"bos_token": "<s>",
|
65 |
"clean_up_tokenization_spaces": true,
|
66 |
-
"cls_token": "
|
67 |
-
"
|
68 |
-
"
|
69 |
-
|
70 |
-
|
71 |
-
|
72 |
-
|
73 |
-
|
74 |
-
|
75 |
-
|
76 |
-
"
|
77 |
-
"
|
78 |
-
"pad_to_multiple_of": null,
|
79 |
-
"pad_token": "<pad>",
|
80 |
-
"pad_token_type_id": 0,
|
81 |
-
"padding_side": "right",
|
82 |
-
"sep_token": "</s>",
|
83 |
-
"sp_model_kwargs": {},
|
84 |
-
"tokenizer_class": "CamembertTokenizer",
|
85 |
-
"unk_token": "<unk>"
|
86 |
}
|
|
|
1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2 |
"clean_up_tokenization_spaces": true,
|
3 |
+
"cls_token": "[CLS]",
|
4 |
+
"do_basic_tokenize": true,
|
5 |
+
"do_lower_case": true,
|
6 |
+
"mask_token": "[MASK]",
|
7 |
+
"model_max_length": 512,
|
8 |
+
"never_split": null,
|
9 |
+
"pad_token": "[PAD]",
|
10 |
+
"sep_token": "[SEP]",
|
11 |
+
"strip_accents": null,
|
12 |
+
"tokenize_chinese_chars": true,
|
13 |
+
"tokenizer_class": "ElectraTokenizer",
|
14 |
+
"unk_token": "[UNK]"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
15 |
}
|