yassin99 commited on
Commit
d5387c5
1 Parent(s): 2c499a8

First model version

Browse files
README.md ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - ru
4
+ ---
5
+
6
+ # rubert-base-cased
7
+
8
+ RuBERT \(Russian, cased, 12‑layer, 768‑hidden, 12‑heads, 180M parameters\) was trained on the Russian part of Wikipedia and news data. We used this training data to build a vocabulary of Russian subtokens and took a multilingual version of BERT‑base as an initialization for RuBERT\[1\].
9
+
10
+ 08.11.2021: upload model with MLM and NSP heads
11
+
12
+ \[1\]: Kuratov, Y., Arkhipov, M. \(2019\). Adaptation of Deep Bidirectional Multilingual Transformers for Russian Language. arXiv preprint [arXiv:1905.07213](https://arxiv.org/abs/1905.07213).
config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertModel"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "directionality": "bidi",
7
+ "hidden_act": "gelu",
8
+ "hidden_dropout_prob": 0.1,
9
+ "hidden_size": 768,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 3072,
12
+ "layer_norm_eps": 1e-12,
13
+ "max_position_embeddings": 512,
14
+ "model_type": "bert",
15
+ "num_attention_heads": 12,
16
+ "num_hidden_layers": 12,
17
+ "output_past": true,
18
+ "pad_token_id": 0,
19
+ "pooler_fc_size": 768,
20
+ "pooler_num_attention_heads": 12,
21
+ "pooler_num_fc_layers": 3,
22
+ "pooler_size_per_head": 128,
23
+ "pooler_type": "first_token_transform",
24
+ "type_vocab_size": 2,
25
+ "vocab_size": 119547
26
+ }
flax_model.msgpack ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8da346601df87881d568b074d00dd9346ef528b3b77edcf57f2d5ed682256902
3
+ size 714274024
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5691c9cb13c98d396ae2e584f4d01a098fc9416a882425ece4359b807730890
3
+ size 714355318
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
tf_model.h5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4f7801c2424dca59b6b9beb4af2f268f792b97de5000e9fb5855fe55634626a
3
+ size 1083389236
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"do_lower_case": false}
vocab.txt ADDED
The diff for this file is too large to render. See raw diff