christianbaluti
commited on
Upload 7 files
Browse files- config.json +35 -0
- dataset_infos.json +67 -0
- model.safetensors +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +56 -0
- vocab.txt +0 -0
config.json
ADDED
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "distilbert-base-uncased-finetuned-sst-2-english",
|
3 |
+
"activation": "gelu",
|
4 |
+
"architectures": [
|
5 |
+
"DistilBertForSequenceClassification"
|
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 |
+
"problem_type": "single_label_classification",
|
28 |
+
"qa_dropout": 0.1,
|
29 |
+
"seq_classif_dropout": 0.2,
|
30 |
+
"sinusoidal_pos_embds": false,
|
31 |
+
"tie_weights_": true,
|
32 |
+
"torch_dtype": "float32",
|
33 |
+
"transformers_version": "4.46.3",
|
34 |
+
"vocab_size": 30522
|
35 |
+
}
|
dataset_infos.json
ADDED
@@ -0,0 +1,67 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"GonzaloA--fake_news": {
|
3 |
+
"description": "",
|
4 |
+
"citation": "",
|
5 |
+
"homepage": "",
|
6 |
+
"license": "",
|
7 |
+
"features": {
|
8 |
+
"Unnamed: 0": {
|
9 |
+
"dtype": "int64",
|
10 |
+
"id": null,
|
11 |
+
"_type": "Value"
|
12 |
+
},
|
13 |
+
"title": {
|
14 |
+
"dtype": "string",
|
15 |
+
"id": null,
|
16 |
+
"_type": "Value"
|
17 |
+
},
|
18 |
+
"text": {
|
19 |
+
"dtype": "string",
|
20 |
+
"id": null,
|
21 |
+
"_type": "Value"
|
22 |
+
},
|
23 |
+
"label": {
|
24 |
+
"dtype": "int64",
|
25 |
+
"id": null,
|
26 |
+
"_type": "Value"
|
27 |
+
}
|
28 |
+
},
|
29 |
+
"post_processed": null,
|
30 |
+
"supervised_keys": null,
|
31 |
+
"task_templates": null,
|
32 |
+
"builder_name": "csv",
|
33 |
+
"config_name": "default",
|
34 |
+
"version": {
|
35 |
+
"version_str": "0.0.0",
|
36 |
+
"description": null,
|
37 |
+
"major": 0,
|
38 |
+
"minor": 0,
|
39 |
+
"patch": 0
|
40 |
+
},
|
41 |
+
"splits": {
|
42 |
+
"train": {
|
43 |
+
"name": "train",
|
44 |
+
"num_bytes": 62966324,
|
45 |
+
"num_examples": 24353,
|
46 |
+
"dataset_name": "fake_news"
|
47 |
+
},
|
48 |
+
"validation": {
|
49 |
+
"name": "validation",
|
50 |
+
"num_bytes": 21099303,
|
51 |
+
"num_examples": 8117,
|
52 |
+
"dataset_name": "fake_news"
|
53 |
+
},
|
54 |
+
"test": {
|
55 |
+
"name": "test",
|
56 |
+
"num_bytes": 21187575,
|
57 |
+
"num_examples": 8117,
|
58 |
+
"dataset_name": "fake_news"
|
59 |
+
}
|
60 |
+
},
|
61 |
+
"download_checksums": null,
|
62 |
+
"download_size": 64821337,
|
63 |
+
"post_processing_size": null,
|
64 |
+
"dataset_size": 105253202,
|
65 |
+
"size_in_bytes": 170074539
|
66 |
+
}
|
67 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cf3856489876e39ff3b7ed4b1d27d6adb0b4e648a9d69c629870fa2549b38b23
|
3 |
+
size 267832560
|
special_tokens_map.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"mask_token": "[MASK]",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"sep_token": "[SEP]",
|
6 |
+
"unk_token": "[UNK]"
|
7 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"100": {
|
12 |
+
"content": "[UNK]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"101": {
|
20 |
+
"content": "[CLS]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"102": {
|
28 |
+
"content": "[SEP]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"103": {
|
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": false,
|
45 |
+
"cls_token": "[CLS]",
|
46 |
+
"do_lower_case": true,
|
47 |
+
"extra_special_tokens": {},
|
48 |
+
"mask_token": "[MASK]",
|
49 |
+
"model_max_length": 512,
|
50 |
+
"pad_token": "[PAD]",
|
51 |
+
"sep_token": "[SEP]",
|
52 |
+
"strip_accents": null,
|
53 |
+
"tokenize_chinese_chars": true,
|
54 |
+
"tokenizer_class": "DistilBertTokenizer",
|
55 |
+
"unk_token": "[UNK]"
|
56 |
+
}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|