ruhzi commited on
Commit
1106384
·
verified ·
1 Parent(s): 1c0a64b

Upload folder using huggingface_hub

Browse files
config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model_type": "distilbert",
3
+ "architectures": [
4
+ "Hecto"
5
+ ],
6
+ "hidden_size": 768,
7
+ "num_labels": 4,
8
+ "id2label": {
9
+ "0": "World",
10
+ "1": "Sports",
11
+ "2": "Business",
12
+ "3": "Sci/Tech"
13
+ },
14
+ "label2id": {
15
+ "World": 0,
16
+ "Sports": 1,
17
+ "Business": 2,
18
+ "Sci/Tech": 3
19
+ },
20
+ "moe_type": "heterogeneous",
21
+ "experts": {
22
+ "expert_0": {
23
+ "type": "ffnn",
24
+ "layers": [
25
+ 256,
26
+ 128
27
+ ],
28
+ "activation": "tanh"
29
+ },
30
+ "expert_1": {
31
+ "type": "gru",
32
+ "input_dim": 256,
33
+ "hidden_dim": 128,
34
+ "bidirectional": false
35
+ }
36
+ },
37
+ "gating": {
38
+ "type": "top1",
39
+ "temperature": 1.5,
40
+ "mlp_dims": [
41
+ 256,
42
+ 128,
43
+ 2
44
+ ],
45
+ "regularization": {
46
+ "entropy_loss": true,
47
+ "load_balancing": true
48
+ }
49
+ },
50
+ "encoder": {
51
+ "base_model": "distilbert-base-uncased",
52
+ "freeze_encoder": false
53
+ },
54
+ "transformers_version": "4.41.1"
55
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:837304236fddff052d25447e390dc6bbc1298ba9ba08b8b4408c2d7cfefccedb
3
+ size 267932374
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