Hugging Face's logo

howey
/
HDT-E

Transformers
Safetensors
English
hed
Model card Files
xet
Community
howey commited on
Commit
e929158
·
verified ·
1 Parent(s): 97d11af

Upload 7 files

Browse files

Pretrained HDT Encoder with HUPD+Wikipedia+Unarxive

Files changed (7) hide show
  1. added_tokens.json +6 -0
  2. config.json +42 -0
  3. model.safetensors +3 -0
  4. special_tokens_map.json +48 -0
  5. tokenizer.json +0 -0
  6. tokenizer_config.json +93 -0
  7. vocab.txt +0 -0
added_tokens.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "<cls>": 28997,
3
+ "<doc>": 28998,
4
+ "<s>": 28996,
5
+ "<sec>": 28999
6
+ }
config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "HEForPreTraining"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "bos_token_id": 28996,
7
+ "classifier_dropout": 0.1,
8
+ "d_ff": 3072,
9
+ "d_kv": 64,
10
+ "d_model": 768,
11
+ "decode_anchor_tokens": false,
12
+ "decoder_start_token_id": 28996,
13
+ "dense_act_fn": "relu",
14
+ "dropout_rate": 0.1,
15
+ "eos_token_id": null,
16
+ "eval_splits": null,
17
+ "feed_forward_proj": "relu",
18
+ "hidden_dropout_prob": 0.1,
19
+ "initializer_factor": 1.0,
20
+ "is_encoder_decoder": true,
21
+ "is_gated_act": false,
22
+ "layer_norm_epsilon": 1e-06,
23
+ "max_decoder_position_embeddings": 512,
24
+ "max_encoder_position_embeddings": 8192,
25
+ "model_type": "hed",
26
+ "num_decoder_layers": 12,
27
+ "num_heads": 12,
28
+ "num_layers": 12,
29
+ "pad_token_id": 0,
30
+ "pool_scheme": "first-token",
31
+ "pos_emb": "scaled-sinusoidal",
32
+ "position_embedding_type": "absolute",
33
+ "prediction_head": false,
34
+ "relative_attention_max_distance": 128,
35
+ "relative_attention_num_buckets": 32,
36
+ "sep_token_id": 102,
37
+ "torch_dtype": "float32",
38
+ "transformers_version": "4.38.0",
39
+ "use_bias": false,
40
+ "use_cache": true,
41
+ "vocab_size": 29000
42
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8747f7fc66adad8212e6ccd2e45b96c2601e1c4a23458c4e6906d99b84c7df3
3
+ size 431411828
special_tokens_map.json ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<doc>",
4
+ "<sec>"
5
+ ],
6
+ "bos_token": {
7
+ "content": "<s>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false
12
+ },
13
+ "cls_token": {
14
+ "content": "<cls>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ },
20
+ "mask_token": {
21
+ "content": "[MASK]",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false
26
+ },
27
+ "pad_token": {
28
+ "content": "[PAD]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false
33
+ },
34
+ "sep_token": {
35
+ "content": "[SEP]",
36
+ "lstrip": false,
37
+ "normalized": false,
38
+ "rstrip": false,
39
+ "single_word": false
40
+ },
41
+ "unk_token": {
42
+ "content": "[UNK]",
43
+ "lstrip": false,
44
+ "normalized": false,
45
+ "rstrip": false,
46
+ "single_word": false
47
+ }
48
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,93 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "28996": {
44
+ "content": "<s>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "28997": {
52
+ "content": "<cls>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "28998": {
60
+ "content": "<doc>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "28999": {
68
+ "content": "<sec>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ }
75
+ },
76
+ "additional_special_tokens": [
77
+ "<doc>",
78
+ "<sec>"
79
+ ],
80
+ "bos_token": "<s>",
81
+ "clean_up_tokenization_spaces": true,
82
+ "cls_token": "<cls>",
83
+ "do_lower_case": false,
84
+ "extra_ids": 0,
85
+ "mask_token": "[MASK]",
86
+ "model_max_length": 512,
87
+ "pad_token": "[PAD]",
88
+ "sep_token": "[SEP]",
89
+ "strip_accents": null,
90
+ "tokenize_chinese_chars": true,
91
+ "tokenizer_class": "BertTokenizer",
92
+ "unk_token": "[UNK]"
93
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff