Upload config.json

config.json

@@ -1,21 +1,27 @@
 {
-    "architectures": [
-        "RobertaForSequenceClassification"
-    ],
-    "attention_probs_dropout_prob": 0.1,
-    "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": 514,
-    "model_type": "roberta",
-    "num_attention_heads": 12,
-    "num_hidden_layers": 12,
-    "pad_token_id": 1,
-    "type_vocab_size": 1,
-    "vocab_size": 50265,
-    "problem_type": "multi_label_classification",
-    "num_labels": 50
+  "_name_or_path": "ai-forever/ruRoberta-large",
+  "architectures": [
+    "RobertaForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 1,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.44.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
 }