commit from igor

README.md

@@ -0,0 +1,47 @@
+# RuBERT for Sentiment Analysis
+Short Russian texts sentiment classification
+
+This is a [DeepPavlov/rubert-base-cased-conversational](https://huggingface.co/DeepPavlov/rubert-base-cased-conversational) model trained on aggregated corpus of 351.797 texts.
+
+## Labels
+    0: NEUTRAL
+    1: POSITIVE
+    2: NEGATIVE
+
+## How to use
+```python
+
+import torch
+from transformers import AutoModelForSequenceClassification
+from transformers import BertTokenizerFast
+
+tokenizer = BertTokenizerFast.from_pretrained('blanchefort/rubert-base-cased-sentiment')
+model = AutoModelForSequenceClassification.from_pretrained('blanchefort/rubert-base-cased-sentiment', return_dict=True)
+
+@torch.no_grad()
+def predict(text):
+    inputs = tokenizer(text, max_length=512, padding=True, truncation=True, return_tensors='pt')
+    outputs = model(**inputs)
+    predicted = torch.nn.functional.softmax(outputs.logits, dim=1)
+    predicted = torch.argmax(predicted, dim=1).numpy()
+    return predicted
+```
+
+
+## Datasets used for model training
+
+**[RuTweetCorp](https://study.mokoron.com/)**
+
+> Рубцова Ю. Автоматическое построение и анализ корпуса коротких текстов (постов микроблогов) для задачи разработки и тренировки тонового классификатора //Инженерия знаний и технологии семантического веба. – 2012. – Т. 1. – С. 109-116.
+
+**[RuReviews](https://github.com/sismetanin/rureviews)**
+
+> RuReviews: An Automatically Annotated Sentiment Analysis Dataset for Product Reviews in Russian.
+
+**[RuSentiment](http://text-machine.cs.uml.edu/projects/rusentiment/)**
+
+> A. Rogers A. Romanov A. Rumshisky S. Volkova M. Gronas A. Gribov RuSentiment: An Enriched Sentiment Analysis Dataset for Social Media in Russian. Proceedings of COLING 2018.
+
+**[Отзывы о медучреждениях](https://github.com/blanchefort/datasets/tree/master/medical_comments)**
+
+> Датасет содержит пользовательские отзывы о медицинских учреждениях. Датасет собран в мае 2019 года с сайта prodoctorov.ru

config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "../huggingface/rubert-base-cased-sentiment",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "directionality": "bidi",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "NEUTRAL",
+    "1": "POSITIVE",
+    "2": "NEGATIVE"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "NEGATIVE": 2,
+    "NEUTRAL": 0,
+    "POSITIVE": 1
+  },
+  "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",
+  "return_dict": true,
+  "type_vocab_size": 2,
+  "vocab_size": 119547
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17c5e6f11e5672c158b12ed629edb94a2d5adfb0c0eacf55c21d250c7381dac1
+size 711509513

special_tokens_map.json

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

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a67fe65cc4493f7934b030d4b5fddbc2622edc062421101c5ba0b6c8b1a77c34
+size 711693676

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "special_tokens_map_file": "/home/igor/.cache/torch/transformers/1f428acdde727eed5de979d6856ce350a470be2a64e134a1fdae04af78a27301.dd8bd9bfd3664b530ea4e645105f557769387b3da9f79bdb55ed556bdd80611d", "name_or_path": "DeepPavlov/rubert-base-cased-conversational", "do_basic_tokenize": true, "never_split": null}