bwang0911 commited on
Commit
d868eba
1 Parent(s): 95b7d1c

Upload 7 files

Browse files
config (4).json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "jinaai/jina-bert-base-de-en-bpe-61k",
3
+ "architectures": [
4
+ "JinaBertForMaskedLM"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "attn_implementation": "torch",
8
+ "auto_map": {
9
+ "AutoConfig": "jinaai/jina-bert-implementation--configuration_bert.JinaBertConfig",
10
+ "AutoModel": "jinaai/jina-bert-implementation--modeling_bert.JinaBertModel",
11
+ "AutoModelForMaskedLM": "jinaai/jina-bert-implementation--modeling_bert.JinaBertForMaskedLM",
12
+ "AutoModelForQuestionAnswering": "jinaai/jina-bert-implementation--modeling_bert.JinaBertForQuestionAnswering",
13
+ "AutoModelForSequenceClassification": "jinaai/jina-bert-implementation--modeling_bert.JinaBertForSequenceClassification",
14
+ "AutoModelForTokenClassification": "jinaai/jina-bert-implementation--modeling_bert.JinaBertForTokenClassification"
15
+ },
16
+ "classifier_dropout": null,
17
+ "emb_pooler": "mean",
18
+ "feed_forward_type": "geglu",
19
+ "gradient_checkpointing": false,
20
+ "hidden_act": "gelu",
21
+ "hidden_dropout_prob": 0.1,
22
+ "hidden_size": 768,
23
+ "initializer_range": 0.02,
24
+ "intermediate_size": 3072,
25
+ "layer_norm_eps": 1e-12,
26
+ "max_position_embeddings": 8192,
27
+ "model_type": "bert",
28
+ "num_attention_heads": 12,
29
+ "num_hidden_layers": 12,
30
+ "pad_token_id": 0,
31
+ "position_embedding_type": "alibi",
32
+ "torch_dtype": "float16",
33
+ "transformers_version": "4.31.0",
34
+ "type_vocab_size": 2,
35
+ "use_cache": true,
36
+ "vocab_size": 61056
37
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model (1).bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7ed0e5f7aa0fbaf70db652dd783b4b8d9da415f6e6e405c91e069d364ad1eed
3
+ size 321664570
special_tokens_map (6).json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
15
+ }
tokenizer (4).json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config (6).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
+ "4": {
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": true,
47
+ "cls_token": "<s>",
48
+ "eos_token": "</s>",
49
+ "errors": "replace",
50
+ "mask_token": "<mask>",
51
+ "model_max_length": 512,
52
+ "pad_token": "<pad>",
53
+ "sep_token": "</s>",
54
+ "tokenizer_class": "RobertaTokenizer",
55
+ "trim_offsets": true,
56
+ "unk_token": "<unk>"
57
+ }
vocab (2).json ADDED
The diff for this file is too large to render. See raw diff