Commit
•
c79e7a3
1
Parent(s):
abd9402
Initial model commit.
Browse files- .gitignore +2 -0
- config.json +51 -0
- evaluation_results.csv +6 -0
- model.safetensors +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +57 -0
- vocab.txt +0 -0
.gitignore
ADDED
@@ -0,0 +1,2 @@
|
|
|
|
|
|
|
1 |
+
# Ignore .idea folder
|
2 |
+
.idea
|
config.json
ADDED
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "DeepPavlov/rubert-base-cased",
|
3 |
+
"architectures": [
|
4 |
+
"BertForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"directionality": "bidi",
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 768,
|
12 |
+
"id2label": {
|
13 |
+
"0": "anger",
|
14 |
+
"1": "disgust",
|
15 |
+
"2": "fear",
|
16 |
+
"3": "joy",
|
17 |
+
"4": "sadness",
|
18 |
+
"5": "surprise",
|
19 |
+
"6": "neutral"
|
20 |
+
},
|
21 |
+
"initializer_range": 0.02,
|
22 |
+
"intermediate_size": 3072,
|
23 |
+
"label2id": {
|
24 |
+
"anger": 0,
|
25 |
+
"disgust": 1,
|
26 |
+
"fear": 2,
|
27 |
+
"joy": 3,
|
28 |
+
"neutral": 6,
|
29 |
+
"sadness": 4,
|
30 |
+
"surprise": 5
|
31 |
+
},
|
32 |
+
"layer_norm_eps": 1e-12,
|
33 |
+
"max_position_embeddings": 512,
|
34 |
+
"model_type": "bert",
|
35 |
+
"num_attention_heads": 12,
|
36 |
+
"num_hidden_layers": 12,
|
37 |
+
"output_past": true,
|
38 |
+
"pad_token_id": 0,
|
39 |
+
"pooler_fc_size": 768,
|
40 |
+
"pooler_num_attention_heads": 12,
|
41 |
+
"pooler_num_fc_layers": 3,
|
42 |
+
"pooler_size_per_head": 128,
|
43 |
+
"pooler_type": "first_token_transform",
|
44 |
+
"position_embedding_type": "absolute",
|
45 |
+
"problem_type": "multi_label_classification",
|
46 |
+
"torch_dtype": "float32",
|
47 |
+
"transformers_version": "4.39.3",
|
48 |
+
"type_vocab_size": 2,
|
49 |
+
"use_cache": true,
|
50 |
+
"vocab_size": 119547
|
51 |
+
}
|
evaluation_results.csv
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
,anger,disgust,fear,joy,sadness,surprise,neutral,micro avg,macro avg,weighted avg,samples avg
|
2 |
+
precision,0.56,0.65,0.64,0.79,0.68,0.6,0.65,0.69,0.65,0.69,0.65
|
3 |
+
recall,0.44,0.24,0.6,0.8,0.44,0.52,0.58,0.62,0.52,0.62,0.64
|
4 |
+
f1-score,0.49,0.36,0.62,0.8,0.53,0.56,0.61,0.65,0.57,0.65,0.64
|
5 |
+
support,726.0,123.0,98.0,2104.0,379.0,677.0,1787.0,5894.0,5894.0,5894.0,5894.0
|
6 |
+
auc-roc,0.86,0.92,0.93,0.91,0.89,0.88,0.82,0.92,0.89,0.87,
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b7938eae7e0a7ef5a4c341fa4c488cd894fb015dcf0fd913bdb752981e793b4e
|
3 |
+
size 711458836
|
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 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": true,
|
45 |
+
"cls_token": "[CLS]",
|
46 |
+
"do_basic_tokenize": true,
|
47 |
+
"do_lower_case": false,
|
48 |
+
"mask_token": "[MASK]",
|
49 |
+
"model_max_length": 1000000000000000019884624838656,
|
50 |
+
"never_split": null,
|
51 |
+
"pad_token": "[PAD]",
|
52 |
+
"sep_token": "[SEP]",
|
53 |
+
"strip_accents": null,
|
54 |
+
"tokenize_chinese_chars": true,
|
55 |
+
"tokenizer_class": "BertTokenizer",
|
56 |
+
"unk_token": "[UNK]"
|
57 |
+
}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|