caseykennington commited on
Commit
b923a93
·
verified ·
1 Parent(s): bba44ed

Upload 7 files

Browse files
config.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "RobertaClass"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "bos_token_id": 0,
7
+ "classifier_dropout": null,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "anger_frustration",
14
+ "1": "interest_desire",
15
+ "2": "confusion_sorrow_boredom",
16
+ "3": "joy_hope",
17
+ "4": "understanding_gratitude_relief",
18
+ "5": "disgust_surprise_alarm_fear"
19
+ },
20
+ "initializer_range": 0.02,
21
+ "intermediate_size": 3072,
22
+ "label2id": {
23
+ "anger_frustration": 0,
24
+ "interest_desire": 1,
25
+ "confusion_sorrow_boredom": 2,
26
+ "joy_hope": 3,
27
+ "understanding_gratitude_relief": 4,
28
+ "disgust_surprise_alarm_fear": 5
29
+ },
30
+ "layer_norm_eps": 1e-05,
31
+ "max_position_embeddings": 514,
32
+ "model_type": "roberta",
33
+ "num_attention_heads": 12,
34
+ "num_hidden_layers": 12,
35
+ "pad_token_id": 1,
36
+ "position_embedding_type": "absolute",
37
+ "transformers_version": "4.47.1",
38
+ "type_vocab_size": 1,
39
+ "use_cache": true,
40
+ "vocab_size": 50265
41
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
misty_emro.py ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ import torch
2
+ from transformers import RobertaModel
3
+
4
+ class RobertaClass(torch.nn.Module):
5
+ def __init__(self, num_classes):
6
+ super(RobertaClass, self).__init__()
7
+ self.roberta = RobertaModel.from_pretrained('roberta-base')
8
+ self.dropout = torch.nn.Dropout(0.3)
9
+ self.classifier = torch.nn.Linear(self.roberta.config.hidden_size, num_classes)
10
+ self.loss_fn = torch.nn.CrossEntropyLoss(label_smoothing=0.1)
11
+
12
+ def forward(self, input_ids, attention_mask, labels=None):
13
+ outputs = self.roberta(
14
+ input_ids=input_ids,
15
+ attention_mask=attention_mask,
16
+ return_dict=True
17
+ )
18
+ pooled_output = torch.mean(outputs.last_hidden_state, dim=1)
19
+ pooled_output = self.dropout(pooled_output)
20
+ logits = self.classifier(pooled_output)
21
+
22
+ if labels is not None:
23
+ loss = self.loss_fn(logits, labels)
24
+ return loss, logits
25
+ else:
26
+ return logits
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00b826b22a1938059fb050d2cc76ae18c8dbe972b7bb590eafa4f99cbd3f2a42
3
+ size 498685166
special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
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": false,
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": "</s>",
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_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<pad>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "50264": {
37
+ "content": "<mask>",
38
+ "lstrip": true,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ }
44
+ },
45
+ "bos_token": "<s>",
46
+ "clean_up_tokenization_spaces": false,
47
+ "cls_token": "<s>",
48
+ "eos_token": "</s>",
49
+ "errors": "replace",
50
+ "extra_special_tokens": {},
51
+ "mask_token": "<mask>",
52
+ "model_max_length": 512,
53
+ "pad_token": "<pad>",
54
+ "sep_token": "</s>",
55
+ "tokenizer_class": "RobertaTokenizer",
56
+ "unk_token": "<unk>"
57
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff