Hugging Face's logo

webis
/
set-encoder-large

Transformers
Safetensors
set-encoder
Inference Endpoints
Model card Files Community
fschlatt commited on
Commit
ca73d7b
·
1 Parent(s): a2b59d9

add model

Browse files
Files changed (7) hide show
  1. added_tokens.json +3 -0
  2. config.json +37 -0
  3. model.safetensors +3 -0
  4. special_tokens_map.json +37 -0
  5. tokenizer.json +0 -0
  6. tokenizer_config.json +66 -0
  7. vocab.txt +0 -0
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "[INT]": 30522
3
+ }
config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "experiments/wandb/run-20240605_134328-5wbd9pb9/files/huggingface_checkpoint",
3
+ "add_extra_token": true,
4
+ "architectures": [
5
+ "SetEncoderElectraModel"
6
+ ],
7
+ "attention_probs_dropout_prob": 0.1,
8
+ "classifier_dropout": null,
9
+ "depth": 100,
10
+ "doc_length": 256,
11
+ "embedding_size": 1024,
12
+ "hidden_act": "gelu",
13
+ "hidden_dropout_prob": 0.1,
14
+ "hidden_size": 1024,
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 4096,
17
+ "layer_norm_eps": 1e-12,
18
+ "max_position_embeddings": 512,
19
+ "model_type": "set-encoder-electra",
20
+ "num_attention_heads": 16,
21
+ "num_hidden_layers": 24,
22
+ "other_sequence_embedding": false,
23
+ "pad_token_id": 0,
24
+ "position_embedding_type": "absolute",
25
+ "query_length": 32,
26
+ "sample_missing_docs": true,
27
+ "save_step": 939,
28
+ "summary_activation": "gelu",
29
+ "summary_last_dropout": 0.1,
30
+ "summary_type": "first",
31
+ "summary_use_proj": true,
32
+ "torch_dtype": "float32",
33
+ "transformers_version": "4.41.1",
34
+ "type_vocab_size": 2,
35
+ "use_cache": true,
36
+ "vocab_size": 30528
37
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9359dd9633434b53a6db5b595d2a6924a9dac88f36aa13009a5f3009ee50c49
3
+ size 1336445804
special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "[MASK]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "[UNK]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,66 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_extra_token": true,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "[PAD]",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "100": {
13
+ "content": "[UNK]",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "101": {
21
+ "content": "[CLS]",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "102": {
29
+ "content": "[SEP]",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "103": {
37
+ "content": "[MASK]",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "30522": {
45
+ "content": "[INT]",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ }
52
+ },
53
+ "clean_up_tokenization_spaces": true,
54
+ "cls_token": "[CLS]",
55
+ "do_lower_case": true,
56
+ "doc_length": 174,
57
+ "mask_token": "[MASK]",
58
+ "model_max_length": 512,
59
+ "pad_token": "[PAD]",
60
+ "query_length": 32,
61
+ "sep_token": "[SEP]",
62
+ "strip_accents": null,
63
+ "tokenize_chinese_chars": true,
64
+ "tokenizer_class": "ElectraTokenizer",
65
+ "unk_token": "[UNK]"
66
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff