Hugging Face's logo

corto-ai
/
jina-reranker-v1-turbo-en-onnx

Feature Extraction
Transformers
ONNX
Transformers.js
English
bert
reranker
cross-encoder
custom_code
text-embeddings-inference
Inference Endpoints
Model card Files Community
calmodovar23 commited on
Commit
cd41d66
•
1 Parent(s): 8303126

Initial commit

Browse files
Files changed (7) hide show
  1. config.json +36 -0
  2. merges.txt +0 -0
  3. model.onnx +3 -0
  4. special_tokens_map.json +51 -0
  5. tokenizer.json +0 -0
  6. tokenizer_config.json +57 -0
  7. vocab.json +0 -0
config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "jinaai/jina-reranker-v1-turbo-en",
3
+ "architectures": [
4
+ "JinaBertModel"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "auto_map": {
8
+ "AutoConfig": "jinaai/jina-reranker-v1-turbo-en--configuration_bert.JinaBertConfig",
9
+ "AutoModel": "jinaai/jina-reranker-v1-turbo-en--modeling_bert.JinaBertModel",
10
+ "AutoModelForMaskedLM": "jinaai/jina-reranker-v1-turbo-en--modeling_bert.JinaBertForMaskedLM",
11
+ "AutoModelForQuestionAnswering": "jinaai/jina-reranker-v1-turbo-en--modeling_bert.JinaBertForQuestionAnswering",
12
+ "AutoModelForSequenceClassification": "jinaai/jina-reranker-v1-turbo-en--modeling_bert.JinaBertForSequenceClassification",
13
+ "AutoModelForTokenClassification": "jinaai/jina-reranker-v1-turbo-en--modeling_bert.JinaBertForTokenClassification"
14
+ },
15
+ "classifier_dropout": null,
16
+ "emb_pooler": "mean",
17
+ "feed_forward_type": "geglu",
18
+ "gradient_checkpointing": false,
19
+ "hidden_act": "gelu",
20
+ "hidden_dropout_prob": 0.1,
21
+ "hidden_size": 384,
22
+ "initializer_range": 0.02,
23
+ "intermediate_size": 1536,
24
+ "layer_norm_eps": 1e-12,
25
+ "max_position_embeddings": 8192,
26
+ "model_type": "bert",
27
+ "num_attention_heads": 12,
28
+ "num_hidden_layers": 6,
29
+ "pad_token_id": 0,
30
+ "position_embedding_type": "alibi",
31
+ "torch_dtype": "float16",
32
+ "transformers_version": "4.41.2",
33
+ "type_vocab_size": 2,
34
+ "use_cache": true,
35
+ "vocab_size": 61056
36
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1296c66c119de645fa9cdee536d8637740efe85224cfa270281e50f213aa565
3
+ size 151296975
special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "<mask>",
25
+ "lstrip": true,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "<pad>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "</s>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "<unk>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.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": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<pad>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": false,
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.json ADDED
The diff for this file is too large to render. See raw diff