Add SetFit model
Browse files- config.json +27 -17
- config_sentence_transformers.json +3 -3
- model_head.pkl +2 -2
- pytorch_model.bin +2 -2
- special_tokens_map.json +4 -12
- tokenizer.json +0 -0
- tokenizer_config.json +6 -57
- vocab.txt +0 -5
config.json
CHANGED
@@ -1,24 +1,34 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "/root/.cache/torch/sentence_transformers/
|
|
|
3 |
"architectures": [
|
4 |
-
"
|
5 |
],
|
6 |
-
"
|
7 |
-
"
|
8 |
-
"
|
9 |
-
"
|
10 |
-
"
|
11 |
-
"
|
|
|
|
|
|
|
12 |
"initializer_range": 0.02,
|
13 |
-
"
|
14 |
-
|
15 |
-
|
16 |
-
|
17 |
-
"
|
18 |
-
"
|
19 |
-
"
|
20 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
21 |
"torch_dtype": "float32",
|
22 |
"transformers_version": "4.30.2",
|
23 |
-
"vocab_size":
|
24 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "/root/.cache/torch/sentence_transformers/konverner_due_sentiment/",
|
3 |
+
"activation": "gelu",
|
4 |
"architectures": [
|
5 |
+
"DistilBertModel"
|
6 |
],
|
7 |
+
"attention_dropout": 0.1,
|
8 |
+
"dim": 768,
|
9 |
+
"dropout": 0.1,
|
10 |
+
"finetuning_task": "sst-2",
|
11 |
+
"hidden_dim": 3072,
|
12 |
+
"id2label": {
|
13 |
+
"0": "NEGATIVE",
|
14 |
+
"1": "POSITIVE"
|
15 |
+
},
|
16 |
"initializer_range": 0.02,
|
17 |
+
"label2id": {
|
18 |
+
"NEGATIVE": 0,
|
19 |
+
"POSITIVE": 1
|
20 |
+
},
|
21 |
+
"max_position_embeddings": 512,
|
22 |
+
"model_type": "distilbert",
|
23 |
+
"n_heads": 12,
|
24 |
+
"n_layers": 6,
|
25 |
+
"output_past": true,
|
26 |
+
"pad_token_id": 0,
|
27 |
+
"qa_dropout": 0.1,
|
28 |
+
"seq_classif_dropout": 0.2,
|
29 |
+
"sinusoidal_pos_embds": false,
|
30 |
+
"tie_weights_": true,
|
31 |
"torch_dtype": "float32",
|
32 |
"transformers_version": "4.30.2",
|
33 |
+
"vocab_size": 30522
|
34 |
}
|
config_sentence_transformers.json
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
{
|
2 |
"__version__": {
|
3 |
-
"sentence_transformers": "2.
|
4 |
-
"transformers": "4.
|
5 |
-
"pytorch": "
|
6 |
}
|
7 |
}
|
|
|
1 |
{
|
2 |
"__version__": {
|
3 |
+
"sentence_transformers": "2.2.2",
|
4 |
+
"transformers": "4.30.2",
|
5 |
+
"pytorch": "2.0.1+cu118"
|
6 |
}
|
7 |
}
|
model_head.pkl
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:aa5d67404ee478ae72e7836b35add6580a39847741aba1646ce1a7d164d5d17b
|
3 |
+
size 6991
|
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:c5c04e4bb8b2aacc9a97b71d58f85e9ec69089f500643998ef239764dddca2cc
|
3 |
+
size 265484701
|
special_tokens_map.json
CHANGED
@@ -1,15 +1,7 @@
|
|
1 |
{
|
2 |
-
"
|
3 |
-
"
|
4 |
-
"
|
5 |
-
"
|
6 |
-
"content": "<mask>",
|
7 |
-
"lstrip": true,
|
8 |
-
"normalized": false,
|
9 |
-
"rstrip": false,
|
10 |
-
"single_word": false
|
11 |
-
},
|
12 |
-
"pad_token": "<pad>",
|
13 |
-
"sep_token": "</s>",
|
14 |
"unk_token": "[UNK]"
|
15 |
}
|
|
|
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
@@ -1,66 +1,15 @@
|
|
1 |
{
|
2 |
-
"bos_token": {
|
3 |
-
"__type": "AddedToken",
|
4 |
-
"content": "<s>",
|
5 |
-
"lstrip": false,
|
6 |
-
"normalized": true,
|
7 |
-
"rstrip": false,
|
8 |
-
"single_word": false
|
9 |
-
},
|
10 |
"clean_up_tokenization_spaces": true,
|
11 |
-
"cls_token":
|
12 |
-
"__type": "AddedToken",
|
13 |
-
"content": "<s>",
|
14 |
-
"lstrip": false,
|
15 |
-
"normalized": true,
|
16 |
-
"rstrip": false,
|
17 |
-
"single_word": false
|
18 |
-
},
|
19 |
"do_basic_tokenize": true,
|
20 |
"do_lower_case": true,
|
21 |
-
"
|
22 |
-
"__type": "AddedToken",
|
23 |
-
"content": "</s>",
|
24 |
-
"lstrip": false,
|
25 |
-
"normalized": true,
|
26 |
-
"rstrip": false,
|
27 |
-
"single_word": false
|
28 |
-
},
|
29 |
-
"mask_token": {
|
30 |
-
"__type": "AddedToken",
|
31 |
-
"content": "<mask>",
|
32 |
-
"lstrip": true,
|
33 |
-
"normalized": true,
|
34 |
-
"rstrip": false,
|
35 |
-
"single_word": false
|
36 |
-
},
|
37 |
"model_max_length": 512,
|
38 |
"never_split": null,
|
39 |
-
"pad_token":
|
40 |
-
|
41 |
-
"content": "<pad>",
|
42 |
-
"lstrip": false,
|
43 |
-
"normalized": true,
|
44 |
-
"rstrip": false,
|
45 |
-
"single_word": false
|
46 |
-
},
|
47 |
-
"sep_token": {
|
48 |
-
"__type": "AddedToken",
|
49 |
-
"content": "</s>",
|
50 |
-
"lstrip": false,
|
51 |
-
"normalized": true,
|
52 |
-
"rstrip": false,
|
53 |
-
"single_word": false
|
54 |
-
},
|
55 |
"strip_accents": null,
|
56 |
"tokenize_chinese_chars": true,
|
57 |
-
"tokenizer_class": "
|
58 |
-
"unk_token":
|
59 |
-
"__type": "AddedToken",
|
60 |
-
"content": "[UNK]",
|
61 |
-
"lstrip": false,
|
62 |
-
"normalized": true,
|
63 |
-
"rstrip": false,
|
64 |
-
"single_word": false
|
65 |
-
}
|
66 |
}
|
|
|
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": "DistilBertTokenizer",
|
14 |
+
"unk_token": "[UNK]"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
15 |
}
|
vocab.txt
CHANGED
@@ -1,7 +1,3 @@
|
|
1 |
-
<s>
|
2 |
-
<pad>
|
3 |
-
</s>
|
4 |
-
<unk>
|
5 |
[PAD]
|
6 |
[unused0]
|
7 |
[unused1]
|
@@ -30524,4 +30520,3 @@ necessitated
|
|
30524 |
##:
|
30525 |
##?
|
30526 |
##~
|
30527 |
-
<mask>
|
|
|
|
|
|
|
|
|
|
|
1 |
[PAD]
|
2 |
[unused0]
|
3 |
[unused1]
|
|
|
30520 |
##:
|
30521 |
##?
|
30522 |
##~
|
|