Upload BertForSequenceClassification

config.json

@@ -1,41 +1,41 @@
-{
-  "_name_or_path": "unthinkable/RuFinBERT_turbo_multitarget",
-  "architectures": [
-    "BertForSequenceClassification"
-  ],
-  "attention_probs_dropout_prob": 0.1,
-  "classifier_dropout": null,
-  "emb_size": 312,
-  "gradient_checkpointing": false,
-  "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.1,
-  "hidden_size": 312,
-  "id2label": {
-    "0": "POSITIVE",
-    "1": "NEGATIVE",
-    "2": "NEUTRAL",
-    "3": "NOT_RELATED_TO_RUSSIAN_ECONOMY",
-    "4": "RELATED_TO_RUSSIAN_ECONOMY"
-  },
-  "initializer_range": 0.02,
-  "intermediate_size": 600,
-  "label2id": {
-    "POSITIVE": 0,
-    "NEGATIVE": 1,
-    "NEUTRAL": 2,
-    "NOT_RELATED_TO_RUSSIAN_ECONOMY": 3,
-    "RELATED_TO_RUSSIAN_ECONOMY": 4
-  },
-  "layer_norm_eps": 1e-12,
-  "max_position_embeddings": 2048,
-  "model_type": "bert",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 3,
-  "pad_token_id": 0,
-  "position_embedding_type": "absolute",
-  "torch_dtype": "float16",
-  "transformers_version": "4.42.3",
-  "type_vocab_size": 2,
-  "use_cache": true,
-  "vocab_size": 83828
-}
+{
+  "_name_or_path": "../checkpoints/rufinbert_4_turbo_2_target",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "emb_size": 312,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 312,
+  "id2label": {
+    "0": "POSITIVE",
+    "1": "NEGATIVE",
+    "2": "NEUTRAL",
+    "3": "NOT_RELATED_TO_RUSSIAN_ECONOMY",
+    "4": "RELATED_TO_RUSSIAN_ECONOMY"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 600,
+  "label2id": {
+    "NEGATIVE": 1,
+    "NEUTRAL": 2,
+    "NOT_RELATED_TO_RUSSIAN_ECONOMY": 3,
+    "POSITIVE": 0,
+    "RELATED_TO_RUSSIAN_ECONOMY": 4
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 2048,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 3,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 83828
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0b42632b276b7ca58e714c9eb26bd2478986ee56b077c2060fd3ac24d7fd884
+size 104617496

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27208f9c6a0f4baa087582233dde9699b54dea48771deacc732382697cc06d9c
+size 12170244

model.safetensors.index.json

@@ -0,0 +1,64 @@
+{
+  "metadata": {
+    "total_size": 116781332
+  },
+  "weight_map": {
+    "bert.embeddings.LayerNorm.bias": "model-00002-of-00002.safetensors",
+    "bert.embeddings.LayerNorm.weight": "model-00002-of-00002.safetensors",
+    "bert.embeddings.position_embeddings.weight": "model-00002-of-00002.safetensors",
+    "bert.embeddings.token_type_embeddings.weight": "model-00002-of-00002.safetensors",
+    "bert.embeddings.word_embeddings.weight": "model-00001-of-00002.safetensors",
+    "bert.encoder.layer.0.attention.output.LayerNorm.bias": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.0.attention.output.LayerNorm.weight": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.0.attention.output.dense.bias": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.0.attention.output.dense.weight": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.0.attention.self.key.bias": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.0.attention.self.key.weight": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.0.attention.self.query.bias": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.0.attention.self.query.weight": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.0.attention.self.value.bias": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.0.attention.self.value.weight": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.0.intermediate.dense.bias": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.0.intermediate.dense.weight": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.0.output.LayerNorm.bias": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.0.output.LayerNorm.weight": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.0.output.dense.bias": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.0.output.dense.weight": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.1.attention.output.LayerNorm.bias": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.1.attention.output.LayerNorm.weight": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.1.attention.output.dense.bias": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.1.attention.output.dense.weight": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.1.attention.self.key.bias": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.1.attention.self.key.weight": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.1.attention.self.query.bias": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.1.attention.self.query.weight": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.1.attention.self.value.bias": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.1.attention.self.value.weight": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.1.intermediate.dense.bias": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.1.intermediate.dense.weight": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.1.output.LayerNorm.bias": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.1.output.LayerNorm.weight": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.1.output.dense.bias": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.1.output.dense.weight": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.2.attention.output.LayerNorm.bias": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.2.attention.output.LayerNorm.weight": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.2.attention.output.dense.bias": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.2.attention.output.dense.weight": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.2.attention.self.key.bias": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.2.attention.self.key.weight": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.2.attention.self.query.bias": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.2.attention.self.query.weight": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.2.attention.self.value.bias": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.2.attention.self.value.weight": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.2.intermediate.dense.bias": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.2.intermediate.dense.weight": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.2.output.LayerNorm.bias": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.2.output.LayerNorm.weight": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.2.output.dense.bias": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.2.output.dense.weight": "model-00002-of-00002.safetensors",
+    "bert.pooler.dense.bias": "model-00002-of-00002.safetensors",
+    "bert.pooler.dense.weight": "model-00002-of-00002.safetensors",
+    "classifier.bias": "model-00002-of-00002.safetensors",
+    "classifier.weight": "model-00002-of-00002.safetensors"
+  }
+}