mgoin commited on
Commit
09aeb76
1 Parent(s): 5bc5a1d
Files changed (6) hide show
  1. config.json +25 -0
  2. model.onnx +3 -0
  3. special_tokens_map.json +7 -0
  4. tokenizer.json +0 -0
  5. tokenizer_config.json +22 -0
  6. vocab.txt +0 -0
config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "sentence-transformers/all-MiniLM-L6-v2",
3
+ "architectures": [
4
+ "BertModel"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 384,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 1536,
14
+ "layer_norm_eps": 1e-12,
15
+ "max_position_embeddings": 512,
16
+ "model_type": "bert",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 6,
19
+ "pad_token_id": 0,
20
+ "position_embedding_type": "absolute",
21
+ "transformers_version": "4.32.0",
22
+ "type_vocab_size": 2,
23
+ "use_cache": true,
24
+ "vocab_size": 30522
25
+ }
model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6857ff10189cc76cc840d10cca0f4fa87bf2e80889d5db65dc6d7785d5bd705
3
+ size 90387629
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 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "max_length": 128,
8
+ "model_max_length": 512,
9
+ "never_split": null,
10
+ "pad_to_multiple_of": null,
11
+ "pad_token": "[PAD]",
12
+ "pad_token_type_id": 0,
13
+ "padding_side": "right",
14
+ "sep_token": "[SEP]",
15
+ "stride": 0,
16
+ "strip_accents": null,
17
+ "tokenize_chinese_chars": true,
18
+ "tokenizer_class": "BertTokenizer",
19
+ "truncation_side": "right",
20
+ "truncation_strategy": "longest_first",
21
+ "unk_token": "[UNK]"
22
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff