Push model files with MedDRA thesaurus embeddings

README.md

@@ -0,0 +1,12 @@
+---
+language:
+- ru
+---
+
+# rubert-base-cased
+
+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\[1\].
+
+08.11.2021: upload model with MLM and NSP heads
+
+\[1\]: 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

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "DeepPavlov/rubert-base-cased",
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 0,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.15.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 119547
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0a0216856db094c274125b7f357d844d9657a3b30f78455f2143f869a26163c
+size 711495089

special_tokens_map.json

@@ -0,0 +1 @@
+{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}

thesaurus_embeddings_meddra_origin.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1e70ce03cd01cb6582d79087fe85a6ff14263dbefdb18ab699b668028b650ed
+size 77037291

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": false}