datgacon commited on
Commit
d7d0a64
·
verified ·
1 Parent(s): 8a91c87

Upload folder using huggingface_hub

Browse files
Files changed (5) hide show
  1. config.json +30 -0
  2. config_extra.json +6 -0
  3. model.onnx +3 -0
  4. tokenizer.json +0 -0
  5. tokenizer_config.json +24 -0
config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_cross_attention": false,
3
+ "architectures": [
4
+ "BertModel"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": null,
8
+ "classifier_dropout": null,
9
+ "dtype": "float32",
10
+ "eos_token_id": null,
11
+ "gradient_checkpointing": false,
12
+ "hidden_act": "gelu",
13
+ "hidden_dropout_prob": 0.1,
14
+ "hidden_size": 384,
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 1536,
17
+ "is_decoder": false,
18
+ "layer_norm_eps": 1e-12,
19
+ "max_position_embeddings": 512,
20
+ "model_type": "bert",
21
+ "num_attention_heads": 12,
22
+ "num_hidden_layers": 6,
23
+ "pad_token_id": 0,
24
+ "position_embedding_type": "absolute",
25
+ "tie_word_embeddings": true,
26
+ "transformers_version": "5.13.0",
27
+ "type_vocab_size": 2,
28
+ "use_cache": false,
29
+ "vocab_size": 30522
30
+ }
config_extra.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "task": "feature-extraction",
3
+ "pooling": "mean",
4
+ "normalize": true,
5
+ "max_length": 128
6
+ }
model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21c017142f420ef420147f5114b447d377f075822b5da33d7279468e54cb0a4e
3
+ size 22840456
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "cls_token": "[CLS]",
4
+ "do_basic_tokenize": true,
5
+ "do_lower_case": true,
6
+ "is_local": true,
7
+ "local_files_only": false,
8
+ "mask_token": "[MASK]",
9
+ "max_length": 128,
10
+ "model_max_length": 256,
11
+ "never_split": null,
12
+ "pad_to_multiple_of": null,
13
+ "pad_token": "[PAD]",
14
+ "pad_token_type_id": 0,
15
+ "padding_side": "right",
16
+ "sep_token": "[SEP]",
17
+ "stride": 0,
18
+ "strip_accents": null,
19
+ "tokenize_chinese_chars": true,
20
+ "tokenizer_class": "BertTokenizer",
21
+ "truncation_side": "right",
22
+ "truncation_strategy": "longest_first",
23
+ "unk_token": "[UNK]"
24
+ }