Mojtaba aka Omid Rohanian commited on
Commit
b420287
1 Parent(s): 54cde85

First version of the Bio-MobileBERT model and tokenizer.

Browse files
config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distil-biobert/models/bio-mobilebert/final/model-85k",
3
+ "architectures": [
4
+ "MobileBertForMaskedLM"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_activation": false,
8
+ "classifier_dropout": null,
9
+ "embedding_size": 128,
10
+ "hidden_act": "relu",
11
+ "hidden_dropout_prob": 0.0,
12
+ "hidden_size": 512,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 512,
15
+ "intra_bottleneck_size": 128,
16
+ "key_query_shared_bottleneck": true,
17
+ "layer_norm_eps": 1e-12,
18
+ "max_position_embeddings": 512,
19
+ "model_type": "mobilebert",
20
+ "normalization_type": "no_norm",
21
+ "num_attention_heads": 4,
22
+ "num_feedforward_networks": 4,
23
+ "num_hidden_layers": 24,
24
+ "pad_token_id": 0,
25
+ "torch_dtype": "float32",
26
+ "transformers_version": "4.17.0",
27
+ "trigram_input": true,
28
+ "true_hidden_size": 128,
29
+ "type_vocab_size": 2,
30
+ "use_bottleneck": true,
31
+ "use_bottleneck_attention": false,
32
+ "vocab_size": 30522
33
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78d6f6e4b835af53e7128ecb6aa64eb43cfc3493edb621642c77da1bf71c77da
3
+ size 146842235
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "special_tokens_map_file": null, "name_or_path": "google/mobilebert-uncased", "tokenizer_class": "MobileBertTokenizer"}
vocab.txt ADDED
The diff for this file is too large to render. See raw diff