Upload 12 files
Browse files- config.json +35 -0
- config_sentence_transformers.json +7 -0
- model-w-mean-pooling.onnx +3 -0
- model.onnx +3 -0
- model.safetensors +3 -0
- modules.json +14 -0
- pytorch_model.bin +3 -0
- sentence_bert_config.json +5 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +15 -0
- vocab.txt +0 -0
config.json
ADDED
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "jinaai/jina-bert-implementation",
|
3 |
+
"model_max_length": 8192,
|
4 |
+
"architectures": [
|
5 |
+
"JinaBertForMaskedLM"
|
6 |
+
],
|
7 |
+
"attention_probs_dropout_prob": 0.0,
|
8 |
+
"auto_map": {
|
9 |
+
"AutoConfig": "jinaai/jina-bert-implementation--configuration_bert.JinaBertConfig",
|
10 |
+
"AutoModelForMaskedLM": "jinaai/jina-bert-implementation--modeling_bert.JinaBertForMaskedLM",
|
11 |
+
"AutoModel": "jinaai/jina-bert-implementation--modeling_bert.JinaBertModel",
|
12 |
+
"AutoModelForSequenceClassification": "jinaai/jina-bert-implementation--modeling_bert.JinaBertForSequenceClassification"
|
13 |
+
},
|
14 |
+
"classifier_dropout": null,
|
15 |
+
"gradient_checkpointing": false,
|
16 |
+
"hidden_act": "gelu",
|
17 |
+
"hidden_dropout_prob": 0.1,
|
18 |
+
"hidden_size": 768,
|
19 |
+
"initializer_range": 0.02,
|
20 |
+
"intermediate_size": 3072,
|
21 |
+
"layer_norm_eps": 1e-12,
|
22 |
+
"max_position_embeddings": 8192,
|
23 |
+
"model_type": "bert",
|
24 |
+
"num_attention_heads": 12,
|
25 |
+
"num_hidden_layers": 12,
|
26 |
+
"pad_token_id": 0,
|
27 |
+
"position_embedding_type": "alibi",
|
28 |
+
"torch_dtype": "float32",
|
29 |
+
"transformers_version": "4.26.0",
|
30 |
+
"type_vocab_size": 2,
|
31 |
+
"use_cache": true,
|
32 |
+
"vocab_size": 30528,
|
33 |
+
"feed_forward_type": "geglu",
|
34 |
+
"emb_pooler": "mean"
|
35 |
+
}
|
config_sentence_transformers.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"__version__": {
|
3 |
+
"sentence_transformers": "2.2.2",
|
4 |
+
"transformers": "4.31.0",
|
5 |
+
"pytorch": "2.0.1"
|
6 |
+
}
|
7 |
+
}
|
model-w-mean-pooling.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f66a1ed716aba330616d750db872e6b535eb585bd6aed390207037b7e4085410
|
3 |
+
size 547365958
|
model.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a6bccce798906f269ee6990d35b8a516390a9593cde824de2e6b9d087b07fa4d
|
3 |
+
size 547390322
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6b70f1386f05b9703ea4edf7f1550a8925399f9580e4cc754cc099efc1e736d8
|
3 |
+
size 274757256
|
modules.json
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
[
|
2 |
+
{
|
3 |
+
"idx": 0,
|
4 |
+
"name": "0",
|
5 |
+
"path": "",
|
6 |
+
"type": "sentence_transformers.models.Transformer"
|
7 |
+
},
|
8 |
+
{
|
9 |
+
"idx": 1,
|
10 |
+
"name": "1",
|
11 |
+
"path": "1_Pooling",
|
12 |
+
"type": "sentence_transformers.models.Pooling"
|
13 |
+
}
|
14 |
+
]
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6cd5a65131aa1db04c4146f474bdf68fac06417cba56789f4e6aaabd190e2818
|
3 |
+
size 274773117
|
sentence_bert_config.json
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"max_seq_length": 8192,
|
3 |
+
"do_lower_case": false,
|
4 |
+
"model_args": {"trust_remote_code": true}
|
5 |
+
}
|
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": 2147483648,
|
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
|
|