artemkramov commited on
Commit
751d6ab
1 Parent(s): 3318f2a

Upload 8 files

Browse files
config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "benjamin/roberta-base-wechsel-ukrainian",
3
+ "architectures": [
4
+ "FCorefModel"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "coref_head": {
10
+ "dropout_prob": 0.3,
11
+ "ffnn_size": 1024,
12
+ "max_segment_len": 512,
13
+ "max_span_length": 30,
14
+ "top_lambda": 0.4
15
+ },
16
+ "eos_token_id": 2,
17
+ "hidden_act": "gelu",
18
+ "hidden_dropout_prob": 0.1,
19
+ "hidden_size": 768,
20
+ "initializer_range": 0.02,
21
+ "intermediate_size": 3072,
22
+ "layer_norm_eps": 1e-05,
23
+ "max_position_embeddings": 514,
24
+ "model_type": "roberta",
25
+ "num_attention_heads": 12,
26
+ "num_hidden_layers": 12,
27
+ "pad_token_id": 1,
28
+ "position_embedding_type": "absolute",
29
+ "torch_dtype": "float32",
30
+ "transformers_version": "4.21.0",
31
+ "type_vocab_size": 1,
32
+ "use_cache": true,
33
+ "vocab_size": 50265
34
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aadf2757abc337eb99f8c7de0ccf58377ae0e3d0b971fe6a083dafb35671b961
3
+ size 532295477
sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e60d59d103a3650d675c36c75b3a9c4b47e2c494eeea699f21ccd6e055f78feb
3
+ size 854151
special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
15
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "bos_token": "<s>",
4
+ "cls_token": "<s>",
5
+ "eos_token": "</s>",
6
+ "errors": "replace",
7
+ "mask_token": {
8
+ "__type": "AddedToken",
9
+ "content": "<mask>",
10
+ "lstrip": true,
11
+ "normalized": false,
12
+ "rstrip": false,
13
+ "single_word": false
14
+ },
15
+ "model_max_length": 512,
16
+ "name_or_path": "benjamin/roberta-base-wechsel-ukrainian",
17
+ "pad_token": "<pad>",
18
+ "sep_token": "</s>",
19
+ "special_tokens_map_file": null,
20
+ "tokenizer_class": "RobertaTokenizer",
21
+ "trim_offsets": true,
22
+ "unk_token": "<unk>"
23
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff