do-me commited on
Commit
f3ab632
1 Parent(s): ba8228a

Upload 8 files

Browse files
config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "jinaai/jina-embeddings-v2-small-en",
3
+ "architectures": [
4
+ "JinaBertForMaskedLM"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.0,
7
+ "auto_map": {
8
+ "AutoConfig": "jinaai/jina-bert-implementation--configuration_bert.JinaBertConfig",
9
+ "AutoModel": "jinaai/jina-bert-implementation--modeling_bert.JinaBertModel",
10
+ "AutoModelForMaskedLM": "jinaai/jina-bert-implementation--modeling_bert.JinaBertForMaskedLM",
11
+ "AutoModelForSequenceClassification": "jinaai/jina-bert-implementation--modeling_bert.JinaBertForSequenceClassification"
12
+ },
13
+ "classifier_dropout": null,
14
+ "emb_pooler": "mean",
15
+ "feed_forward_type": "geglu",
16
+ "gradient_checkpointing": false,
17
+ "hidden_act": "gelu",
18
+ "hidden_dropout_prob": 0.1,
19
+ "hidden_size": 512,
20
+ "initializer_range": 0.02,
21
+ "intermediate_size": 2048,
22
+ "layer_norm_eps": 1e-12,
23
+ "max_position_embeddings": 8192,
24
+ "model_max_length": 8192,
25
+ "model_type": "bert",
26
+ "num_attention_heads": 8,
27
+ "num_hidden_layers": 4,
28
+ "pad_token_id": 0,
29
+ "position_embedding_type": "alibi",
30
+ "transformers_version": "4.33.2",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30528
34
+ }
onnx/model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db66d631261bb1fd06871218967e9a6ec0bfe843b89164198cf3d2ab80cb471f
3
+ size 113004695
onnx/model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b15b2f15104f58bb71a13593d935bd4ef16a517b6fbef186e2481286018c847c
3
+ size 28512042
quantize_config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "per_channel": true,
3
+ "reduce_range": true,
4
+ "per_model_config": {
5
+ "model": {
6
+ "op_types": [
7
+ "Unsqueeze",
8
+ "Div",
9
+ "Sub",
10
+ "Transpose",
11
+ "Erf",
12
+ "Gather",
13
+ "Mul",
14
+ "Constant",
15
+ "Shape",
16
+ "Softmax",
17
+ "Sqrt",
18
+ "Add",
19
+ "ReduceMean",
20
+ "Concat",
21
+ "MatMul",
22
+ "Cast",
23
+ "Pow",
24
+ "Reshape",
25
+ "Identity"
26
+ ],
27
+ "weight_type": "QInt8"
28
+ }
29
+ }
30
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "clean_up_tokenization_spaces": true,
3
+ "cls_token": "[CLS]",
4
+ "do_basic_tokenize": true,
5
+ "do_lower_case": true,
6
+ "mask_token": "[MASK]",
7
+ "model_max_length": 8192,
8
+ "never_split": null,
9
+ "pad_token": "[PAD]",
10
+ "sep_token": "[SEP]",
11
+ "strip_accents": null,
12
+ "tokenize_chinese_chars": true,
13
+ "tokenizer_class": "BertTokenizer",
14
+ "unk_token": "[UNK]"
15
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff