abazoge commited on
Commit
91916fd
1 Parent(s): bfdcfe5

Upload 7 files

Browse files
config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./output_dir/checkpoint-12700",
3
+ "architectures": [
4
+ "LongformerForMaskedLM"
5
+ ],
6
+ "attention_mode": "longformer",
7
+ "attention_probs_dropout_prob": 0.1,
8
+ "attention_window": [
9
+ 512,
10
+ 512,
11
+ 512,
12
+ 512,
13
+ 512,
14
+ 512,
15
+ 512,
16
+ 512,
17
+ 512,
18
+ 512,
19
+ 512,
20
+ 512
21
+ ],
22
+ "bos_token_id": 5,
23
+ "classifier_dropout": null,
24
+ "eos_token_id": 6,
25
+ "gradient_checkpointing": false,
26
+ "hidden_act": "gelu",
27
+ "hidden_dropout_prob": 0.1,
28
+ "hidden_size": 768,
29
+ "ignore_attention_mask": false,
30
+ "initializer_range": 0.02,
31
+ "intermediate_size": 3072,
32
+ "layer_norm_eps": 1e-12,
33
+ "max_position_embeddings": 4098,
34
+ "model_type": "longformer",
35
+ "num_attention_heads": 12,
36
+ "num_hidden_layers": 12,
37
+ "onnx_export": false,
38
+ "pad_token_id": 1,
39
+ "position_embedding_type": "absolute",
40
+ "sep_token_id": 6,
41
+ "torch_dtype": "float32",
42
+ "transformers_version": "4.24.0",
43
+ "type_vocab_size": 1,
44
+ "use_cache": true,
45
+ "vocab_size": 32005
46
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e225cbcadbbdc5ca2d19ec656133043dbc36c7e3bd14b4dafa01ab8b66092014
3
+ size 538770845
sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:701a6bfe3db86b7bc1f4174e54f11bc24da195751c04a3ccea354a599de5c43b
3
+ size 791347
special_tokens_map.json ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<s>NOTUSED",
4
+ "</s>NOTUSED"
5
+ ],
6
+ "bos_token": "<s>",
7
+ "cls_token": "<s>",
8
+ "eos_token": "</s>",
9
+ "mask_token": {
10
+ "content": "<mask>",
11
+ "lstrip": true,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<pad>",
17
+ "sep_token": "</s>",
18
+ "unk_token": "<unk>"
19
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<s>NOTUSED",
4
+ "</s>NOTUSED"
5
+ ],
6
+ "bos_token": "<s>",
7
+ "cls_token": "<s>",
8
+ "eos_token": "</s>",
9
+ "mask_token": {
10
+ "__type": "AddedToken",
11
+ "content": "<mask>",
12
+ "lstrip": true,
13
+ "normalized": true,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ },
17
+ "max_len": 512,
18
+ "model_max_length": 4096,
19
+ "name_or_path": "./DrBERT_512_7GB_77740",
20
+ "pad_token": "<pad>",
21
+ "sep_token": "</s>",
22
+ "sp_model_kwargs": {},
23
+ "special_tokens_map_file": "./TokenizerFromScratchMLM/DrBERT_8GB_MLM/special_tokens_map.json",
24
+ "tokenizer_class": "CamembertTokenizer",
25
+ "unk_token": "<unk>"
26
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f79061a090b4c98c3846833bf02347560e8fe3b2ced5fde608ffe518f6330fe
3
+ size 3439