Add original model

classes.dict

@@ -0,0 +1,3 @@
+1	90717
+2	49736
+0	49438

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

rubert_sentiment.json

@@ -0,0 +1,116 @@
+{
+  "dataset_reader": {
+    "class_name": "basic_classification_reader",
+    "x": "text",
+    "y": "sentiment",
+    "data_path": "/content/drive/MyDrive/BERT/train/",
+    "train": "train.csv",
+    "valid": "valid.csv"
+  },
+  "dataset_iterator": {
+    "class_name": "basic_classification_iterator",
+    "seed": 42
+  },
+  "chainer": {
+    "in": [
+      "x"
+    ],
+    "in_y": [
+      "y"
+    ],
+    "pipe": [
+      {
+        "id": "classes_vocab",
+        "class_name": "simple_vocab",
+        "fit_on": [
+          "y"
+        ],
+        "save_path": "/content/drive/MyDrive/BERT/sentiment_bert_model/classes.dict",
+        "load_path": "/content/drive/MyDrive/BERT/sentiment_bert_model/classes.dict",
+        "in": "y",
+        "out": "y_ids"
+      },
+      {
+        "class_name": "torch_transformers_preprocessor",
+        "vocab_file": "/content/drive/MyDrive/BERT/rubert-base-cased-sentiment/",
+        "do_lower_case": true,
+        "max_seq_length": 512,
+        "in": [
+          "x"
+        ],
+        "out": [
+          "bert_features"
+        ]
+      },
+      {
+        "in": "y_ids",
+        "out": "y_onehot",
+        "class_name": "one_hotter",
+        "depth": "#classes_vocab.len",
+        "single_vector": true
+      },
+      {
+        "class_name": "torch_transformers_classifier",
+        "n_classes": 3,
+        "return_probas": true,
+        "pretrained_bert": "/content/drive/MyDrive/BERT/rubert-base-cased-sentiment/",
+        "save_path": "/content/drive/MyDrive/BERT/sentiment_bert_model/model",
+        "load_path": "/content/drive/MyDrive/BERT/sentiment_bert_model/model",
+        "optimizer": "AdamW",
+        "optimizer_parameters": {
+          "lr": 1e-05
+        },
+        "learning_rate_drop_patience": 5,
+        "learning_rate_drop_div": 2.0,
+        "in": [
+          "bert_features"
+        ],
+        "in_y": [
+          "y_ids"
+        ],
+        "out": [
+          "y_pred_probas"
+        ]
+      },
+      {
+        "in": "y_pred_probas",
+        "out": "y_pred_ids",
+        "class_name": "proba2labels",
+        "max_proba": true
+      },
+      {
+        "in": "y_pred_ids",
+        "out": "y_pred_labels",
+        "ref": "classes_vocab"
+      }
+    ],
+    "out": [
+      "y_pred_labels"
+    ]
+  },
+  "train": {
+    "epochs": 5,
+    "batch_size": 8,
+    "metrics": [
+      "accuracy",
+      "f1_macro",
+      "f1_weighted",
+      {
+        "name": "roc_auc",
+        "inputs": [
+          "y_onehot",
+          "y_pred_probas"
+        ]
+      }
+    ],
+    "validation_patience": 2,
+    "val_every_n_epochs": 1,
+    "log_every_n_epochs": 1,
+    "show_examples": false,
+    "evaluation_targets": [
+      "train",
+      "valid"
+    ],
+    "class_name": "nn_trainer"
+  }
+}

special_tokens_map.json

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

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}