initial commit

README.md

@@ -0,0 +1,33 @@
+---
+language: ["ru"]
+tags:
+- russian
+- classification
+- sentiment
+- multiclass
+widget:
+- text: "����� ������� ��� ���� �������� ����!"
+---
+## Sentiment model based on rubert-base-cased-conversational
+This model was initialized with [rubert-base-cased-conversational](https://huggingface.co/DeepPavlov/rubert-base-cased-conversational) weights and trained on a batch of datasets collected by [Smetanin](https://duckduckgo.com), using the same training sampling presented in [this wonderful work](https://huggingface.co/cointegrated/rubert-tiny-sentiment-balanced). This approach allows for a uniform distribution among different datasets and three classes of sentiment labels: negative, neutral, and positive. Datasets were prepared by David Dale and are hosted [here](https://drive.google.com/file/d/1dir_lixYfReDXxRS5oGGljH8T_f7vVqm/view).
+
+I chose rubert-base-cased-conversational weights because, according to Smetanin's work, this model ranks first among all other multilingual and popular Russian language models with BERT base architecture.
+
+### Training and Testing Details
+This model was trained and tested using the code and hyperparameters from the [rubert-tiny-sentiment-balanced](https://huggingface.co/cointegrated/rubert-tiny-sentiment-balanced) work.
+
+### Labels
+There are only three labels: negative - 0, neutral - 1, positive - 2
+
+## Results
+It outperforms rubert-tiny-sentiment-balanced on four datasets, underperforms on one (linis), and has the same performance on mokoron and rureviews. See [this](https://huggingface.co/cointegrated/rubert-tiny-sentiment-balanced) for the comparison.
+
+| Source | Macro F1 |
+| ----------- | ----------- |
+| SentiRuEval2016_banks | 0.88 | 
+| SentiRuEval2016_tele  | 0.79 |
+| kaggle_news | 0.73 |
+| linis | 0.46 |
+| mokoron | 0.98 |
+| rureviews | 0.77 |
+| rusentiment | 0.74 |

config.json

@@ -0,0 +1,43 @@
+{
+  "_name_or_path": "./rubert-base-cased-conversational",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "negative",
+    "1": "neutral",
+    "2": "positive"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "negative": 0,
+    "neutral": 1,
+    "positive": 2
+  },
+  "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",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.26.1",
+  "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 sha256:70b394766f740ff58672f9a80322965002849db45c45dcfb9c47590d52eda1a5
+size 711493997

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,16 @@
+{
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "name_or_path": "./rubert-base-cased-conversational",
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "special_tokens_map_file": "./rubert-base-cased-conversational/special_tokens_map.json",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}