EftychiaKarav commited on
Commit
3c8041b
·
1 Parent(s): 2e412fa

DistilGREEK-BERT model

Browse files
config.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./DistilBERTGreek/checkpoint_1447661",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForMaskedLM"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
11
+ "initializer_range": 0.02,
12
+ "max_position_embeddings": 512,
13
+ "model_type": "distilbert",
14
+ "n_heads": 12,
15
+ "n_layers": 6,
16
+ "pad_token_id": 0,
17
+ "qa_dropout": 0.1,
18
+ "seq_classif_dropout": 0.2,
19
+ "sinusoidal_pos_embds": true,
20
+ "torch_dtype": "float32",
21
+ "transformers_version": "4.27.4",
22
+ "vocab_size": 35000
23
+ }
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59d1c07356125f6d031c3d83161982c5f66b0614de8e8c2c3746a40eeeec0feb
3
+ size 560375173
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c09cbaf86da36db2d0a9ed117049b265797a2498850b7640d8493b1ab68fd249
3
+ size 281752369
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d35c304da43b2b4c2fbb2d0fc0579df24165cea652ad4cea66a1e6a21b9a9552
3
+ size 627
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_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "do_basic_tokenize": true,
4
+ "do_lower_case": true,
5
+ "mask_token": "[MASK]",
6
+ "model_max_length": 1000000000000000019884624838656,
7
+ "never_split": null,
8
+ "pad_token": "[PAD]",
9
+ "sep_token": "[SEP]",
10
+ "strip_accents": true,
11
+ "tokenize_chinese_chars": true,
12
+ "tokenizer_class": "DistilBertGreekTokenizer",
13
+ "unk_token": "[UNK]"
14
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff