Mojtaba aka Omid Rohanian commited on
Commit
847df97
1 Parent(s): f14fe06

BioMiniALBERT model and tokeniser.

Browse files
config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/users/engs2263/compact-distilbert/models/bio-miniALBERT-128/final/model",
3
+ "architectures": [
4
+ "MiniAlbertForMaskedLM"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 2,
8
+ "classifier_dropout": null,
9
+ "classifier_dropout_prob": 0.1,
10
+ "down_scale_factor": 1,
11
+ "embedding_size": 128,
12
+ "eos_token_id": 3,
13
+ "gap_size": 0,
14
+ "hidden_act": "gelu",
15
+ "hidden_dropout_prob": 0.1,
16
+ "hidden_size": 768,
17
+ "initializer_range": 0.02,
18
+ "inner_group_num": 1,
19
+ "intermediate_size": 3072,
20
+ "layer_norm_eps": 1e-12,
21
+ "max_position_embeddings": 512,
22
+ "model_type": "bert",
23
+ "net_structure_type": 0,
24
+ "num_attention_heads": 12,
25
+ "num_hidden_groups": 1,
26
+ "num_hidden_layers": 6,
27
+ "num_memory_blocks": 0,
28
+ "pad_token_id": 0,
29
+ "position_embedding_type": "absolute",
30
+ "reduction_factor": 16,
31
+ "torch_dtype": "float32",
32
+ "transformers_version": "4.27.0.dev0",
33
+ "type_vocab_size": 2,
34
+ "use_adapter": true,
35
+ "use_cache": true,
36
+ "vocab_size": 28996
37
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d7d0d78ad4108dc6728525081f4c832c47b46eac23ad256f724691567562817
3
+ size 141468273
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 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "do_lower_case": false,
4
+ "mask_token": "[MASK]",
5
+ "model_max_length": 512,
6
+ "name_or_path": "bert-base-cased",
7
+ "pad_token": "[PAD]",
8
+ "sep_token": "[SEP]",
9
+ "special_tokens_map_file": null,
10
+ "strip_accents": null,
11
+ "tokenize_chinese_chars": true,
12
+ "tokenizer_class": "BertTokenizer",
13
+ "unk_token": "[UNK]"
14
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff