bwang0911 commited on
Commit
5889b4b
1 Parent(s): 9cf3ad7

Upload 6 files

Browse files
config (1).json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "jinaai/jina-bert-v2-de-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
+ }
generation_config (1).json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "pad_token_id": 0,
4
+ "transformers_version": "4.31.0"
5
+ }
special_tokens_map (2).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.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config (2).json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": "<s>",
4
+ "clean_up_tokenization_spaces": true,
5
+ "cls_token": "<s>",
6
+ "eos_token": "</s>",
7
+ "errors": "replace",
8
+ "mask_token": {
9
+ "__type": "AddedToken",
10
+ "content": "<mask>",
11
+ "lstrip": true,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "model_max_length": 512,
17
+ "pad_token": "<pad>",
18
+ "sep_token": "</s>",
19
+ "tokenizer_class": "RobertaTokenizer",
20
+ "trim_offsets": true,
21
+ "unk_token": "<unk>"
22
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff